swap-uniba/LLaMAntino-2-chat-13b-hf-UltraChat-ITA
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
9e4e67647170584d04f5b61e4fbfd92b9f0aba2d
LLaMAntino-2-chat-13b-hf-Ul…/res_ultrachat_13B.txt

1895 lines
3.2 MiB
Plaintext
Raw Normal View History

初始化项目，由ModelHub XC社区提供模型 Model: swap-uniba/LLaMAntino-2-chat-13b-hf-UltraChat-ITA Source: Original Platform
2026-04-27 04:59:02 +08:00
/leonardo/prod/spack/03/ccsdeploy/hosts/cineca.it/BA/setup-var.sh: riga 61: $(tty): redirezione ambigua
Node IP: 10.6.1.54
master_addr is only used for static rdzv_backend and when rdzv_endpoint is not specified.
WARNING:torch.distributed.run:
*****************************************
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
*****************************************
INFO:torch.distributed.launcher.api:Starting elastic_operator with launch configs:
entrypoint : finetune_chat_llama_13B.py
min_nodes : 3
max_nodes : 3
nproc_per_node : 4
run_id : 29353
rdzv_backend : c10d
rdzv_endpoint : 10.6.1.54:29500
rdzv_configs : {'timeout': 900}
max_restarts : 0
monitor_interval : 5
log_dir : None
metrics_cfg : {}
INFO:torch.distributed.elastic.agent.server.local_elastic_agent:log directory set to: /tmp/torchelastic_szpr_trh/29353_fzy75qgg
INFO:torch.distributed.elastic.agent.server.api:[default] starting workers for entrypoint: python3
INFO:torch.distributed.elastic.agent.server.api:[default] Rendezvous'ing worker group
master_addr is only used for static rdzv_backend and when rdzv_endpoint is not specified.
WARNING:torch.distributed.run:
*****************************************
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
*****************************************
INFO:torch.distributed.launcher.api:Starting elastic_operator with launch configs:
entrypoint : finetune_chat_llama_13B.py
min_nodes : 3
max_nodes : 3
nproc_per_node : 4
run_id : 29353
rdzv_backend : c10d
rdzv_endpoint : 10.6.1.54:29500
rdzv_configs : {'timeout': 900}
max_restarts : 0
monitor_interval : 5
log_dir : None
metrics_cfg : {}
INFO:torch.distributed.elastic.agent.server.local_elastic_agent:log directory set to: /tmp/torchelastic_9wl7vyc5/29353_wgoojszx
INFO:torch.distributed.elastic.agent.server.api:[default] starting workers for entrypoint: python3
INFO:torch.distributed.elastic.agent.server.api:[default] Rendezvous'ing worker group
master_addr is only used for static rdzv_backend and when rdzv_endpoint is not specified.
WARNING:torch.distributed.run:
*****************************************
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.
*****************************************
INFO:torch.distributed.launcher.api:Starting elastic_operator with launch configs:
entrypoint : finetune_chat_llama_13B.py
min_nodes : 3
max_nodes : 3
nproc_per_node : 4
run_id : 29353
rdzv_backend : c10d
rdzv_endpoint : 10.6.1.54:29500
rdzv_configs : {'timeout': 900}
max_restarts : 0
monitor_interval : 5
log_dir : None
metrics_cfg : {}
INFO:torch.distributed.elastic.agent.server.local_elastic_agent:log directory set to: /tmp/torchelastic_wpk04vb4/29353_qulo0whx
INFO:torch.distributed.elastic.agent.server.api:[default] starting workers for entrypoint: python3
INFO:torch.distributed.elastic.agent.server.api:[default] Rendezvous'ing worker group
INFO:torch.distributed.elastic.agent.server.api:[default] Rendezvous complete for workers. Result:
restart_count=0
master_addr=lrdn2110-net6-3.leonardo.local
master_port=37919
group_rank=0
group_world_size=3
local_ranks=[0, 1, 2, 3]
role_ranks=[0, 1, 2, 3]
global_ranks=[0, 1, 2, 3]
role_world_sizes=[12, 12, 12, 12]
global_world_sizes=[12, 12, 12, 12]
INFO:torch.distributed.elastic.agent.server.api:[default] Starting worker group
INFO:torch.distributed.elastic.agent.server.local_elastic_agent:Starting a FileTimerServer with /tmp/watchdog_timer_f92edb7d-4d3d-442d-aad6-058dd23fc6be ...
INFO:torch.distributed.elastic.agent.server.api:[default] Rendezvous complete for workers. Result:
restart_count=0
master_addr=lrdn2110-net6-3.leonardo.local
master_port=37919
group_rank=1
group_world_size=3
local_ranks=[0, 1, 2, 3]
role_ranks=[4, 5, 6, 7]
global_ranks=[4, 5, 6, 7]
role_world_sizes=[12, 12, 12, 12]
global_world_sizes=[12, 12, 12, 12]
INFO:torch.distributed.elastic.agent.server.api:[default] Starting worker group
INFO:torch.distributed.elastic.agent.server.api:[default] Rendezvous complete for workers. Result:
restart_count=0
master_addr=lrdn2110-net6-3.leonardo.local
master_port=37919
group_rank=2
group_world_size=3
local_ranks=[0, 1, 2, 3]
role_ranks=[8, 9, 10, 11]
global_ranks=[8, 9, 10, 11]
role_world_sizes=[12, 12, 12, 12]
global_world_sizes=[12, 12, 12, 12]
INFO:torch.distributed.elastic.agent.server.api:[default] Starting worker group
INFO:torch.distributed.elastic.agent.server.local_elastic_agent:Starting a FileTimerServer with /tmp/watchdog_timer_63960e88-d48a-42f3-ba13-7de9376a3825 ...
INFO:torch.distributed.elastic.agent.server.local_elastic_agent:FileTimerServer started
INFO:torch.distributed.elastic.multiprocessing:Setting worker0 reply file to: /tmp/torchelastic_szpr_trh/29353_fzy75qgg/attempt_0/0/error.json
INFO:torch.distributed.elastic.multiprocessing:Setting worker1 reply file to: /tmp/torchelastic_szpr_trh/29353_fzy75qgg/attempt_0/1/error.json
INFO:torch.distributed.elastic.multiprocessing:Setting worker2 reply file to: /tmp/torchelastic_szpr_trh/29353_fzy75qgg/attempt_0/2/error.json
INFO:torch.distributed.elastic.multiprocessing:Setting worker3 reply file to: /tmp/torchelastic_szpr_trh/29353_fzy75qgg/attempt_0/3/error.json
INFO:torch.distributed.elastic.agent.server.local_elastic_agent:Starting a FileTimerServer with /tmp/watchdog_timer_b96ab573-7472-4b9b-bb4a-dd5e32bb7a2d ...
INFO:torch.distributed.elastic.agent.server.local_elastic_agent:FileTimerServer started
INFO:torch.distributed.elastic.multiprocessing:Setting worker0 reply file to: /tmp/torchelastic_9wl7vyc5/29353_wgoojszx/attempt_0/0/error.json
INFO:torch.distributed.elastic.multiprocessing:Setting worker1 reply file to: /tmp/torchelastic_9wl7vyc5/29353_wgoojszx/attempt_0/1/error.json
INFO:torch.distributed.elastic.multiprocessing:Setting worker2 reply file to: /tmp/torchelastic_9wl7vyc5/29353_wgoojszx/attempt_0/2/error.json
INFO:torch.distributed.elastic.multiprocessing:Setting worker3 reply file to: /tmp/torchelastic_9wl7vyc5/29353_wgoojszx/attempt_0/3/error.json
INFO:torch.distributed.elastic.agent.server.local_elastic_agent:FileTimerServer started
INFO:torch.distributed.elastic.multiprocessing:Setting worker0 reply file to: /tmp/torchelastic_wpk04vb4/29353_qulo0whx/attempt_0/0/error.json
INFO:torch.distributed.elastic.multiprocessing:Setting worker1 reply file to: /tmp/torchelastic_wpk04vb4/29353_qulo0whx/attempt_0/1/error.json
INFO:torch.distributed.elastic.multiprocessing:Setting worker2 reply file to: /tmp/torchelastic_wpk04vb4/29353_qulo0whx/attempt_0/2/error.json
INFO:torch.distributed.elastic.multiprocessing:Setting worker3 reply file to: /tmp/torchelastic_wpk04vb4/29353_qulo0whx/attempt_0/3/error.json
INFO
WARN
Clearing GPU cache for all ranks
--> Running with torch dist debug set to detail
Using device: cuda
################{'': 'cuda:0'}################
INFO
WARN
Using device: Using device: Using device: Clearing GPU cache for all ranks
Using device: cuda
################{'': 'cuda:1'}################
cuda
################{'': 'cuda:2'}################
cuda
################{'': 'cuda:3'}################
cuda
################{'': 'cuda:0'}################
INFO
WARN
INFO
WARN
INFO
WARN
INFO
WARN
Clearing GPU cache for all ranks
Using device: cuda
################{'': 'cuda:0'}################
Using device: cuda
################{'': 'cuda:1'}################
INFO
WARN
Using device: cuda
################{'': 'cuda:2'}################
Using device: cuda
################{'': 'cuda:3'}################
Using device: cuda
################{'': 'cuda:1'}################
Using device: cuda
################{'': 'cuda:2'}################
Using device: cuda
################{'': 'cuda:3'}################
INFO
WARN
INFO
WARN
INFO
WARN
INFO
WARN
INFO
WARN
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/config.json
Model config LlamaConfig {
"_name_or_path": "/leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/config.json
Model config LlamaConfig {
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/config.json
Model config LlamaConfig {
"_name_or_path": "/leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/config.json
Model config LlamaConfig {
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/config.json
Model config LlamaConfig {
"_name_or_path": "/leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/config.json
Model config LlamaConfig {
"_name_or_path": "/leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}
"_name_or_path": "/leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/config.json
Model config LlamaConfig {
"_name_or_path": "/leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA",
"architectures": [
"LlamaForCausalLM"
],
"_name_or_path": "/leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/config.json
Model config LlamaConfig {
"_name_or_path": "/leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA",
"architectures": [
"LlamaForCausalLM"
],
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/config.json
Model config LlamaConfig {
"_name_or_path": "/leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/config.json
Model config LlamaConfig {
"_name_or_path": "/leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/config.json
Model config LlamaConfig {
"_name_or_path": "/leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/config.json
Model config LlamaConfig {
"_name_or_path": "/leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}
Detected PIL version 10.1.0
Detected PIL version 10.1.0
Detected PIL version 10.1.0
Detected PIL version 10.1.0
Detected PIL version 10.1.0
Detected PIL version 10.1.0
Detected PIL version 10.1.0
Detected PIL version 10.1.0
Detected PIL version 10.1.0
Detected PIL version 10.1.0
Detected PIL version 10.1.0
Detected PIL version 10.1.0
Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in 8-bit or 4-bit. Pass your own torch_dtype to specify the dtype of the remaining non-linear layers or pass torch_dtype=torch.float16 to remove this warning.
Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in 8-bit or 4-bit. Pass your own torch_dtype to specify the dtype of the remaining non-linear layers or pass torch_dtype=torch.float16 to remove this warning.
Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in 8-bit or 4-bit. Pass your own torch_dtype to specify the dtype of the remaining non-linear layers or pass torch_dtype=torch.float16 to remove this warning.
Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in 8-bit or 4-bit. Pass your own torch_dtype to specify the dtype of the remaining non-linear layers or pass torch_dtype=torch.float16 to remove this warning.
Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in 8-bit or 4-bit. Pass your own torch_dtype to specify the dtype of the remaining non-linear layers or pass torch_dtype=torch.float16 to remove this warning.
Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in 8-bit or 4-bit. Pass your own torch_dtype to specify the dtype of the remaining non-linear layers or pass torch_dtype=torch.float16 to remove this warning.
Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in 8-bit or 4-bit. Pass your own torch_dtype to specify the dtype of the remaining non-linear layers or pass torch_dtype=torch.float16 to remove this warning.
Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in 8-bit or 4-bit. Pass your own torch_dtype to specify the dtype of the remaining non-linear layers or pass torch_dtype=torch.float16 to remove this warning.
loading weights file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/model.safetensors.index.json
loading weights file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/model.safetensors.index.json
loading weights file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/model.safetensors.index.json
loading weights file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/model.safetensors.index.json
Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in 8-bit or 4-bit. Pass your own torch_dtype to specify the dtype of the remaining non-linear layers or pass torch_dtype=torch.float16 to remove this warning.
Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in 8-bit or 4-bit. Pass your own torch_dtype to specify the dtype of the remaining non-linear layers or pass torch_dtype=torch.float16 to remove this warning.
Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in 8-bit or 4-bit. Pass your own torch_dtype to specify the dtype of the remaining non-linear layers or pass torch_dtype=torch.float16 to remove this warning.
Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in 8-bit or 4-bit. Pass your own torch_dtype to specify the dtype of the remaining non-linear layers or pass torch_dtype=torch.float16 to remove this warning.
loading weights file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/model.safetensors.index.json
loading weights file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/model.safetensors.index.json
loading weights file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/model.safetensors.index.json
loading weights file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/model.safetensors.index.json
loading weights file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/model.safetensors.index.json
loading weights file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/model.safetensors.index.json
loading weights file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/model.safetensors.index.json
loading weights file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/model.safetensors.index.json
Instantiating LlamaForCausalLM model under default dtype torch.float16.
Instantiating LlamaForCausalLM model under default dtype torch.float16.
Instantiating LlamaForCausalLM model under default dtype torch.float16.
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}
Instantiating LlamaForCausalLM model under default dtype torch.float16.
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}
Instantiating LlamaForCausalLM model under default dtype torch.float16.
Instantiating LlamaForCausalLM model under default dtype torch.float16.
Instantiating LlamaForCausalLM model under default dtype torch.float16.
Instantiating LlamaForCausalLM model under default dtype torch.float16.
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}
Instantiating LlamaForCausalLM model under default dtype torch.float16.
Instantiating LlamaForCausalLM model under default dtype torch.float16.
Instantiating LlamaForCausalLM model under default dtype torch.float16.
Instantiating LlamaForCausalLM model under default dtype torch.float16.
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}
Detected 8-bit loading: activating 8-bit loading for this model
Detected 8-bit loading: activating 8-bit loading for this model
Detected 8-bit loading: activating 8-bit loading for this model
Detected 8-bit loading: activating 8-bit loading for this model
Detected 8-bit loading: activating 8-bit loading for this model
Detected 8-bit loading: activating 8-bit loading for this model
Detected 8-bit loading: activating 8-bit loading for this model
Detected 8-bit loading: activating 8-bit loading for this model
Detected 8-bit loading: activating 8-bit loading for this model
Detected 8-bit loading: activating 8-bit loading for this model
Detected 8-bit loading: activating 8-bit loading for this model
Detected 8-bit loading: activating 8-bit loading for this model
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 33%|███▎ | 1/3 [00:26<00:52, 26.19s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [00:26<00:52, 26.42s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [00:26<00:52, 26.44s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [00:26<00:52, 26.44s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:49<00:24, 24.37s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:49<00:24, 24.50s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:49<00:24, 24.51s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:49<00:24, 24.57s/it] Loading checkpoint shards: 100%|██████████| 3/3 [01:01<00:00, 18.85s/it] Loading checkpoint shards: 100%|██████████| 3/3 [01:01<00:00, 20.57s/it]
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 3/3 [01:01<00:00, 18.91s/it] Loading checkpoint shards: 100%|██████████| 3/3 [01:01<00:00, 20.62s/it]
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 3/3 [01:01<00:00, 18.96s/it] Loading checkpoint shards: 100%|██████████| 3/3 [01:01<00:00, 20.62s/it]
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/generation_config.json
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}
Loading checkpoint shards: 100%|██████████| 3/3 [01:01<00:00, 18.97s/it] Loading checkpoint shards: 100%|██████████| 3/3 [01:01<00:00, 20.64s/it]
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/generation_config.json
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/generation_config.json
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/generation_config.json
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
Assigning <pad> to the pad_token key of the tokenizer
Assigning <pad> to the pad_token key of the tokenizer
Assigning <pad> to the pad_token key of the tokenizer
Assigning <pad> to the pad_token key of the tokenizer
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 33%|███▎ | 1/3 [00:33<01:06, 33.44s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [00:33<01:07, 33.70s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [00:33<01:07, 33.71s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [00:33<01:07, 33.71s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [01:03<00:31, 31.66s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [01:04<00:31, 31.80s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [01:04<00:31, 31.85s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [01:04<00:31, 31.81s/it] Loading checkpoint shards: 100%|██████████| 3/3 [01:20<00:00, 24.94s/it] Loading checkpoint shards: 100%|██████████| 3/3 [01:20<00:00, 26.97s/it]
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/generation_config.json
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}
Loading checkpoint shards: 100%|██████████| 3/3 [01:21<00:00, 24.97s/it] Loading checkpoint shards: 100%|██████████| 3/3 [01:21<00:00, 27.00s/it]
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 3/3 [01:21<00:00, 24.99s/it] Loading checkpoint shards: 100%|██████████| 3/3 [01:21<00:00, 27.02s/it]
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 3/3 [01:21<00:00, 25.04s/it] Loading checkpoint shards: 100%|██████████| 3/3 [01:21<00:00, 27.03s/it]
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/generation_config.json
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/generation_config.json
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/generation_config.json
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
Assigning <pad> to the pad_token key of the tokenizer
Assigning <pad> to the pad_token key of the tokenizer
Assigning <pad> to the pad_token key of the tokenizer
Assigning <pad> to the pad_token key of the tokenizer
Dataset({
features: ['id', 'data'],
num_rows: 512837
})
Dataset({
features: ['id', 'data'],
num_rows: 512837
})
Dataset({
features: ['id', 'data'],
num_rows: 512837
})
Dataset({
features: ['text'],
num_rows: 512837
})
NVIDIA PG506-242 cuda:3 Allocated: 7.4 GB
Dataset({
features: ['text'],
num_rows: 512837
})
NVIDIA PG506-243 cuda:1 Allocated: 7.4 GB
PyTorch: setting up devices
PyTorch: setting up devices
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/peft/utils/other.py:102: FutureWarning: prepare_model_for_int8_training is deprecated and will be removed in a future version. Use prepare_model_for_kbit_training instead.
warnings.warn(
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/peft/utils/other.py:102: FutureWarning: prepare_model_for_int8_training is deprecated and will be removed in a future version. Use prepare_model_for_kbit_training instead.
warnings.warn(
Dataset({
features: ['text'],
num_rows: 512837
})
NVIDIA PG506-242 cuda:2 Allocated: 7.4 GB
PyTorch: setting up devices
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/peft/utils/other.py:102: FutureWarning: prepare_model_for_int8_training is deprecated and will be removed in a future version. Use prepare_model_for_kbit_training instead.
warnings.warn(
Dataset({
features: ['id', 'data'],
num_rows: 512837
})
Dataset({
features: ['text'],
num_rows: 512837
})
NVIDIA PG506-243 cuda:0 Allocated: 7.4 GB
PyTorch: setting up devices
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/peft/utils/other.py:102: FutureWarning: prepare_model_for_int8_training is deprecated and will be removed in a future version. Use prepare_model_for_kbit_training instead.
warnings.warn(
Dataset({
features: ['id', 'data'],
num_rows: 512837
})
Dataset({
features: ['text'],
num_rows: 512837
})
NVIDIA PG506-242 cuda:3 Allocated: 7.4 GB
PyTorch: setting up devices
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/peft/utils/other.py:102: FutureWarning: prepare_model_for_int8_training is deprecated and will be removed in a future version. Use prepare_model_for_kbit_training instead.
warnings.warn(
Dataset({
features: ['id', 'data'],
num_rows: 512837
})
Dataset({
features: ['text'],
num_rows: 512837
})
NVIDIA PG506-243 cuda:0 Allocated: 7.4 GB
PyTorch: setting up devices
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/peft/utils/other.py:102: FutureWarning: prepare_model_for_int8_training is deprecated and will be removed in a future version. Use prepare_model_for_kbit_training instead.
warnings.warn(
Dataset({
features: ['id', 'data'],
num_rows: 512837
})
Dataset({
features: ['text'],
num_rows: 512837
})
NVIDIA PG506-243 cuda:1 Allocated: 7.4 GB
PyTorch: setting up devices
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/peft/utils/other.py:102: FutureWarning: prepare_model_for_int8_training is deprecated and will be removed in a future version. Use prepare_model_for_kbit_training instead.
warnings.warn(
Dataset({
features: ['id', 'data'],
num_rows: 512837
})
Dataset({
features: ['text'],
num_rows: 512837
})
NVIDIA PG506-242 cuda:2 Allocated: 7.4 GB
PyTorch: setting up devices
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/peft/utils/other.py:102: FutureWarning: prepare_model_for_int8_training is deprecated and will be removed in a future version. Use prepare_model_for_kbit_training instead.
warnings.warn(
NVIDIA PG506-242 cuda:3 Allocated: 8.2 GB
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/trl/trainer/sft_trainer.py:227: UserWarning: You passed `packing=True` to the SFTTrainer, and you are training your model with `max_steps` strategy. The dataset will be iterated until the `max_steps` are reached.
warnings.warn(
NVIDIA PG506-242 cuda:3 Allocated: 8.2 GB
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/trl/trainer/sft_trainer.py:227: UserWarning: You passed `packing=True` to the SFTTrainer, and you are training your model with `max_steps` strategy. The dataset will be iterated until the `max_steps` are reached.
warnings.warn(
NVIDIA PG506-243 cuda:1 Allocated: 8.2 GB
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/trl/trainer/sft_trainer.py:227: UserWarning: You passed `packing=True` to the SFTTrainer, and you are training your model with `max_steps` strategy. The dataset will be iterated until the `max_steps` are reached.
warnings.warn(
NVIDIA PG506-242 cuda:2 Allocated: 8.2 GB
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/trl/trainer/sft_trainer.py:227: UserWarning: You passed `packing=True` to the SFTTrainer, and you are training your model with `max_steps` strategy. The dataset will be iterated until the `max_steps` are reached.
warnings.warn(
You have loaded a model on multiple GPUs. `is_model_parallel` attribute will be force-set to `True` to avoid any unexpected behavior such as device placement mismatching.
The model is loaded in 8-bit precision. To train this model you need to add additional modules inside the model such as adapters using `peft` library and freeze the model weights. Please check the examples in https://github.com/huggingface/peft for more details.
max_steps is given, it will override any value given in num_train_epochs
NVIDIA PG506-243 cuda:0 Allocated: 8.2 GB
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/trl/trainer/sft_trainer.py:227: UserWarning: You passed `packing=True` to the SFTTrainer, and you are training your model with `max_steps` strategy. The dataset will be iterated until the `max_steps` are reached.
warnings.warn(
Currently training with a batch size of: 8
NCCL version 2.14.3+cuda11.7
You have loaded a model on multiple GPUs. `is_model_parallel` attribute will be force-set to `True` to avoid any unexpected behavior such as device placement mismatching.
The model is loaded in 8-bit precision. To train this model you need to add additional modules inside the model such as adapters using `peft` library and freeze the model weights. Please check the examples in https://github.com/huggingface/peft for more details.
max_steps is given, it will override any value given in num_train_epochs
NVIDIA PG506-243 cuda:0 Allocated: 8.2 GB
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/trl/trainer/sft_trainer.py:227: UserWarning: You passed `packing=True` to the SFTTrainer, and you are training your model with `max_steps` strategy. The dataset will be iterated until the `max_steps` are reached.
warnings.warn(
Currently training with a batch size of: 8
NVIDIA PG506-243 cuda:1 Allocated: 8.2 GB
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/trl/trainer/sft_trainer.py:227: UserWarning: You passed `packing=True` to the SFTTrainer, and you are training your model with `max_steps` strategy. The dataset will be iterated until the `max_steps` are reached.
warnings.warn(
NVIDIA PG506-242 cuda:2 Allocated: 8.2 GB
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/trl/trainer/sft_trainer.py:227: UserWarning: You passed `packing=True` to the SFTTrainer, and you are training your model with `max_steps` strategy. The dataset will be iterated until the `max_steps` are reached.
warnings.warn(
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 33%|███▎ | 1/3 [01:06<02:12, 66.21s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [01:06<02:12, 66.39s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [01:06<02:12, 66.40s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [01:06<02:12, 66.41s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [02:15<01:07, 67.96s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [02:15<01:08, 68.14s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [02:15<01:08, 68.11s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [02:15<01:08, 68.10s/it] Loading checkpoint shards: 100%|██████████| 3/3 [03:13<00:00, 63.37s/it] Loading checkpoint shards: 100%|██████████| 3/3 [03:13<00:00, 64.48s/it]
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/generation_config.json
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}
Loading checkpoint shards: 100%|██████████| 3/3 [03:13<00:00, 63.46s/it] Loading checkpoint shards: 100%|██████████| 3/3 [03:13<00:00, 64.52s/it]
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 3/3 [03:13<00:00, 63.47s/it] Loading checkpoint shards: 100%|██████████| 3/3 [03:13<00:00, 64.54s/it]
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 3/3 [03:13<00:00, 63.45s/it] Loading checkpoint shards: 100%|██████████| 3/3 [03:13<00:00, 64.54s/it]
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/generation_config.json
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/generation_config.json
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/generation_config.json
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
Assigning <pad> to the pad_token key of the tokenizer
Assigning <pad> to the pad_token key of the tokenizer
Assigning <pad> to the pad_token key of the tokenizer
Assigning <pad> to the pad_token key of the tokenizer
Dataset({
features: ['id', 'data'],
num_rows: 512837
})
Dataset({
features: ['id', 'data'],
num_rows: 512837
})
Dataset({
features: ['text'],
num_rows: 512837
})
NVIDIA PG506-242 cuda:2 Allocated: 7.4 GB
PyTorch: setting up devices
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/peft/utils/other.py:102: FutureWarning: prepare_model_for_int8_training is deprecated and will be removed in a future version. Use prepare_model_for_kbit_training instead.
warnings.warn(
Dataset({
features: ['text'],
num_rows: 512837
})
NVIDIA PG506-243 cuda:0 Allocated: 7.4 GB
PyTorch: setting up devices
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/peft/utils/other.py:102: FutureWarning: prepare_model_for_int8_training is deprecated and will be removed in a future version. Use prepare_model_for_kbit_training instead.
warnings.warn(
Dataset({
features: ['id', 'data'],
num_rows: 512837
})
Dataset({
features: ['text'],
num_rows: 512837
})
NVIDIA PG506-243 cuda:1 Allocated: 7.4 GB
PyTorch: setting up devices
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/peft/utils/other.py:102: FutureWarning: prepare_model_for_int8_training is deprecated and will be removed in a future version. Use prepare_model_for_kbit_training instead.
warnings.warn(
Dataset({
features: ['id', 'data'],
num_rows: 512837
})
Dataset({
features: ['text'],
num_rows: 512837
})
NVIDIA PG506-242 cuda:3 Allocated: 7.4 GB
PyTorch: setting up devices
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/peft/utils/other.py:102: FutureWarning: prepare_model_for_int8_training is deprecated and will be removed in a future version. Use prepare_model_for_kbit_training instead.
warnings.warn(
You have loaded a model on multiple GPUs. `is_model_parallel` attribute will be force-set to `True` to avoid any unexpected behavior such as device placement mismatching.
The model is loaded in 8-bit precision. To train this model you need to add additional modules inside the model such as adapters using `peft` library and freeze the model weights. Please check the examples in https://github.com/huggingface/peft for more details.
max_steps is given, it will override any value given in num_train_epochs
NVIDIA PG506-243 cuda:0 Allocated: 8.2 GB
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/trl/trainer/sft_trainer.py:227: UserWarning: You passed `packing=True` to the SFTTrainer, and you are training your model with `max_steps` strategy. The dataset will be iterated until the `max_steps` are reached.
warnings.warn(
NVIDIA PG506-242 cuda:2 Allocated: 8.2 GB
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/trl/trainer/sft_trainer.py:227: UserWarning: You passed `packing=True` to the SFTTrainer, and you are training your model with `max_steps` strategy. The dataset will be iterated until the `max_steps` are reached.
warnings.warn(
Currently training with a batch size of: 8
NVIDIA PG506-243 cuda:1 Allocated: 8.2 GB
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/trl/trainer/sft_trainer.py:227: UserWarning: You passed `packing=True` to the SFTTrainer, and you are training your model with `max_steps` strategy. The dataset will be iterated until the `max_steps` are reached.
warnings.warn(
NVIDIA PG506-242 cuda:3 Allocated: 8.2 GB
/leonardo/home/userexternal/mpoligna/.local/lib/python3.10/site-packages/trl/trainer/sft_trainer.py:227: UserWarning: You passed `packing=True` to the SFTTrainer, and you are training your model with `max_steps` strategy. The dataset will be iterated until the `max_steps` are reached.
warnings.warn(
***** Running training *****
Num examples = 512,837
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 96
Gradient Accumulation steps = 1
Total optimization steps = 15,000
Number of trainable parameters = 52,428,800
***** Running training *****
Num examples = 512,837
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 96
Gradient Accumulation steps = 1
Total optimization steps = 15,000
Number of trainable parameters = 52,428,800
***** Running training *****
Num examples = 512,837
Num Epochs = 3
Instantaneous batch size per device = 8
Total train batch size (w. parallel, distributed & accumulation) = 96
Gradient Accumulation steps = 1
Total optimization steps = 15,000
Number of trainable parameters = 52,428,800
0%| | 0/15000 [00:00<?, ?it/s]You're using a LlamaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
0%| | 0/15000 [00:00<?, ?it/s] 0%| | 1/15000 [00:38<161:18:59, 38.72s/it] 0%| | 2/15000 [00:53<103:09:18, 24.76s/it] 0%| | 3/15000 [01:08<83:46:52, 20.11s/it] 0%| | 4/15000 [01:22<74:42:35, 17.94s/it] 0%| | 5/15000 [01:37<69:59:36, 16.80s/it] 0%| | 6/15000 [01:52<66:51:33, 16.05s/it] 0%| | 7/15000 [02:06<65:02:08, 15.62s/it] 0%| | 8/15000 [02:21<63:53:54, 15.34s/it] 0%| | 9/15000 [02:36<63:05:29, 15.15s/it] 0%| | 10/15000 [02:51<62:22:20, 14.98s/it] 0%| | 11/15000 [03:27<89:16:08, 21.44s/it] 0%| | 12/15000 [03:41<80:40:05, 19.38s/it] 0%| | 13/15000 [03:56<74:42:25, 17.95s/it] 0%| | 14/15000 [04:11<70:47:25, 17.01s/it] 0%| | 15/15000 [04:25<67:41:02, 16.26s/it] 0%| | 16/15000 [04:40<65:47:44, 15.81s/it] 0%| | 17/15000 [04:55<64:22:36, 15.47s/it] 0%| | 18/15000 [05:09<63:25:07, 15.24s/it] 0%| 0%| | 0/15000 [00:00<?, ?it/s] 0%| | 1/15000 [00:38<161:44:18, 38.82s/it] 0%| | 2/15000 [00:53<103:11:10, 24.77s/it] 0%| | 3/15000 [01:08<83:51:56, 20.13s/it] 0%| | 4/15000 [01:23<74:49:46, 17.96s/it] 0%| | 5/15000 [01:37<69:59:08, 16.80s/it] 0%| | 6/15000 [01:52<66:54:24, 16.06s/it] 0%| | 7/15000 [02:06<64:48:45, 15.56s/it] 0%| | 8/15000 [02:21<63:49:54, 15.33s/it] 0%| | 9/15000 [02:36<63:00:41, 15.13s/it] 0%| | 10/15000 [02:51<62:18:38, 14.96s/it] 0%| | 11/15000 [03:27<89:18:47, 21.45s/it] 0%| | 12/15000 [03:41<80:50:00, 19.42s/it] 0%| | 13/15000 [03:56<74:43:04, 17.95s/it] 0%| | 14/15000 [04:11<70:44:16, 16.99s/it] 0%| | 15/15000 [04:25<67:47:25, 16.29s/it] 0%| | 16/15000 [04:40<65:47:51, 15.81s/it] 0%| | 17/15000 [04:55<64:23:33, 15.47s/it] 0%| | 18/15000 [05:09<63:18:04, 15.21s/it] 0%| 0%| | 1/15000 [00:38<161:59:22, 38.88s/it] 0%| | 2/15000 [00:53<102:50:24, 24.68s/it] 0%| | 3/15000 [01:08<83:39:27, 20.08s/it] 0%| | 4/15000 [01:22<74:46:17, 17.95s/it] 0%| | 5/15000 [01:37<69:49:49, 16.76s/it] 0%| | 6/15000 [01:52<66:50:14, 16.05s/it] 0%| | 7/15000 [02:07<65:07:46, 15.64s/it] 0%| | 8/15000 [02:21<63:52:34, 15.34s/it] 0%| | 9/15000 [02:36<62:55:52, 15.11s/it] 0%| | 10/15000 [02:51<62:23:12, 14.98s/it] 0%| | 11/15000 [03:27<89:12:41, 21.43s/it] 0%| | 12/15000 [03:41<80:46:51, 19.40s/it] 0%| | 13/15000 [03:56<74:52:18, 17.98s/it] 0%| | 14/15000 [04:11<70:39:54, 16.98s/it] 0%| | 15/15000 [04:25<67:52:02, 16.30s/it] 0%| | 16/15000 [04:40<65:44:56, 15.80s/it] 0%| | 17/15000 [04:55<64:20:06, 15.46s/it] 0%| | 18/15000 [05:09<63:14:10, 15.19s/it] 0%| | 19/15000 [05:24<62:31:19, 15.02s/it] 0| 19/15000 [05:24<62:31:40, 15.03s/it] 0%| | 20/15000 [05:39<61:57:45, 14.89s/it] 0%| | 21/15000 [05:53<61:36:46, 14.81s/it] 0%| | 22/15000 [06:29<88:08:26, 21.18s/it] 0%| | 23/15000 [06:44<79:49:29, 19.19s/it] 0%| | 24/15000 [06:59<74:17:20, 17.86s/it] 0%| | 25/15000 [07:13<70:11:20, 16.87s/it] 0%| | 26/15000 [07:28<67:18:25, 16.18s/it] 0%| | 27/15000 [07:42<65:22:52, 15.72s/it] 0%| | 28/15000 [07:57<64:10:04, 15.43s/it] 0%| | 29/15000 [08:12<63:03:00, 15.16s/it] 0%| | 30/15000 [08:26<62:28:43, 15.02s/it] 0%| | 31/15000 [08:41<61:59:04, 14.91s/it] 0%| | 32/15000 [08:56<61:36:19, 14.82s/it] 0%| | 33/15000 [09:32<88:11:44, 21.21s/it] 0%| | 34/15000 [09:46<79:45:07, 19.18s/it] 0%| | 35/15000 [10:01<74:09:31, 17.84s/it] 0%| | 36/15000 [10:16<70:10:17, 16.88s/it] 0%| | 37/15000 [10:30<67:30:35, 16.24s/it] 0%|
{'loss': 1.3994, 'learning_rate': 4.4444444444444447e-05, 'epoch': 0.02}
{'loss': 1.3994, 'learning_rate': 4.4444444444444447e-05, 'epoch': 0.02}
| 95/15000 [26:28<65:22:29, 15.79s/it] 1%| | 96/15000 [26:43<63:45:11, 15.40s/it] 1%| | 97/15000 [26:58<62:53:42, 15.19s/it] 1%| | 98/15000 [27:12<62:09:59, 15.02s/it] 1%| | 99/15000 [27:27<61:39:19, 14.90s/it] 1%| | 100/15000 [27:42<61:23:17, 14.83s/it] 1%| | 100/15000 [27:42<61:23:17, 14.83s/it] 1%| | 101/15000 [28:18<88:11:26, 21.31s/it] 1%| | 102/15000 [28:33<79:55:34, 19.31s/it] 1%| | 103/15000 [28:47<74:18:09, 17.96s/it] 1%| | 104/15000 [29:02<70:01:37, 16.92s/it] 1%| | 105/15000 [29:16<67:08:45, 16.23s/it] 1%| | 106/15000 [29:31<65:00:42, 15.71s/it] 1%| | 107/15000 [29:46<63:40:25, 15.39s/it] 1%| | 108/15000 [30:00<62:37:36, 15.14s/it] 1%| | 109/15000 [30:15<62:09:11, 15.03s/it] 1%| | 110/15000 [30:30<61:34:33, 14.89s/it] 1%| | 111/15000 [30:44<61:06:47, 1 | 95/15000 [26:28<65:13:45, 15.75s/it] 1%| | 96/15000 [26:43<63:46:43, 15.41s/it] 1%| | 97/15000 [26:58<62:53:46, 15.19s/it] 1%| | 98/15000 [27:12<62:12:41, 15.03s/it] 1%| | 99/15000 [27:27<61:51:23, 14.94s/it] 1%| | 100/15000 [27:41<61:19:15, 14.82s/it] 1%| | 100/15000 [27:42<61:19:15, 14.82s/it] 1%| | 101/15000 [28:18<88:14:48, 21.32s/it] 1%| | 102/15000 [28:33<79:52:10, 19.30s/it] 1%| | 103/15000 [28:47<74:10:47, 17.93s/it] 1%| | 104/15000 [29:02<69:57:31, 16.91s/it] 1%| | 105/15000 [29:16<67:08:00, 16.23s/it] 1%| | 106/15000 [29:31<65:04:43, 15.73s/it] 1%| | 107/15000 [29:46<63:34:48, 15.37s/it] 1%| | 108/15000 [30:00<62:40:47, 15.15s/it] 1%| | 109/15000 [30:15<62:11:59, 15.04s/it] 1%| | 110/15000 [30:30<61:38:02, 14.90s/it] 1%| | 111/15000 [30:44<61:13:13, 1/it] 1%| | 96/15000 [26:43<63:53:19, 15.43s/it] 1%| | 97/15000 [26:57<62:48:28, 15.17s/it] 1%| | 98/15000 [27:12<62:15:02, 15.04s/it] 1%| | 99/15000 [27:27<61:43:02, 14.91s/it] 1%| | 100/15000 [27:41<61:18:02, 14.81s/it] 1%| | 100/15000 [27:42<61:18:02, 14.81s/it] 1%| | 101/15000 [28:18<88:16:42, 21.33s/it] 1%| | 102/15000 [28:33<79:56:23, 19.32s/it] 1%| | 103/15000 [28:47<74:02:30, 17.89s/it] 1%| | 104/15000 [29:02<70:01:00, 16.92s/it] 1%| | 105/15000 [29:16<67:00:34, 16.20s/it] 1%| | 106/15000 [29:31<65:06:03, 15.74s/it] 1%| | 107/15000 [29:46<63:44:26, 15.41s/it] 1%| | 108/15000 [30:00<62:45:59, 15.17s/it] 1%| | 109/15000 [30:15<62:07:05, 15.02s/it] 1%| | 110/15000 [30:29<61:33:50, 14.88s/it] 1%| | 111/15000 [30:44<61:14:53, 14.81s/it] 1%| | 112/15000 [30:54.80s/it] 1%| | 112/15000 [30:59<61:02:44, 14.76s/it] 1%| | 113/15000 [31:36<88:22:47, 21.37s/it] 1%| | 114/15000 [31:50<79:49:50, 19.31s/it] 1%| | 115/15000 [32:05<74:00:26, 17.90s/it] 1%| | 116/15000 [32:19<70:01:55, 16.94s/it] 1%| | 117/15000 [32:34<67:04:54, 16.23s/it] 1%| | 118/15000 [32:49<65:04:29, 15.74s/it] 1%| | 119/15000 [33:03<63:41:48, 15.41s/it] 1%| | 120/15000 [33:18<62:43:39, 15.18s/it] 1%| | 121/15000 [33:32<61:57:31, 14.99s/it] 1%| | 122/15000 [33:47<61:40:02, 14.92s/it] 1%| | 123/15000 [34:02<61:16:58, 14.83s/it] 1%| | 124/15000 [34:39<88:31:01, 21.42s/it] 1%| | 125/15000 [34:53<80:06:33, 19.39s/it] 1%| | 126/15000 [35:08<74:11:48, 17.96s/it] 1%| | 127/15000 [35:22<69:58:57, 16.94s/it] 1%| | 128/15000 [35:37<67:11:08, 16.26s/it] 1%| | 129/15000 [35:52<65:11:34, 15.78s/it] 1%| | 130/15
{'loss': 1.0676, 'learning_rate': 8.888888888888889e-05, 'epoch': 0.04}
{'loss': 1.0676, 'learning_rate': 8.888888888888889e-05, 'epoch': 0.04}
186/15000 [51:38<65:16:56, 15.86s/it] 1%| | 187/15000 [51:52<63:43:30, 15.49s/it] 1%|▏ | 188/15000 [52:07<62:44:45, 15.25s/it] 1%|▏ | 189/15000 [52:22<62:04:53, 15.09s/it] 1%|▏ | 190/15000 [52:36<61:36:13, 14.97s/it] 1%|▏ | 191/15000 [52:51<61:16:04, 14.89s/it] 1%|▏ | 192/15000 [53:28<88:15:06, 21.46s/it] 1%|▏ | 193/15000 [53:43<80:07:00, 19.48s/it] 1%|▏ | 194/15000 [53:57<74:17:42, 18.06s/it] 1%|▏ | 195/15000 [54:12<70:08:00, 17.05s/it] 1%|▏ | 196/15000 [54:27<67:14:21, 16.35s/it] 1%|▏ | 197/15000 [54:42<65:15:13, 15.87s/it] 1%|▏ | 198/15000 [54:56<63:51:06, 15.53s/it] 1%|▏ | 199/15000 [55:11<62:49:00, 15.28s/it] 1%|▏ | 200/15000 [55:26<62:10:31, 15.12s/it] 1%|▏ | 200/15000 [55:26<62:10:31, 15.12s/it] 1%|▏ | 201/15000 [55:41<61:49:22, 15.04s/it] 1%|▏ | 186/15000 [51:38<65:18:10, 15.87s/it] 1%| | 187/15000 [51:52<63:49:33, 15.51s/it] 1%|▏ | 188/15000 [52:07<62:48:06, 15.26s/it] 1%|▏ | 189/15000 [52:22<61:55:41, 15.05s/it] 1%|▏ | 190/15000 [52:36<61:37:45, 14.98s/it] 1%|▏ | 191/15000 [52:51<61:15:08, 14.89s/it] 1%|▏ | 192/15000 [53:28<88:18:57, 21.47s/it] 1%|▏ | 193/15000 [53:43<80:06:30, 19.48s/it] 1%|▏ | 194/15000 [53:57<74:10:39, 18.04s/it] 1%|▏ | 195/15000 [54:12<70:06:45, 17.05s/it] 1%|▏ | 196/15000 [54:27<67:17:06, 16.36s/it] 1%|▏ | 197/15000 [54:42<65:19:09, 15.89s/it] 1%|▏ | 198/15000 [54:56<63:50:52, 15.53s/it] 1%|▏ | 199/15000 [55:11<62:45:03, 15.26s/it] 1%|▏ | 200/15000 [55:26<62:10:37, 15.12s/it] 1%|▏ | 200/15000 [55:26<62:10:37, 15.12s/it] 1%|▏ | 201/15000 [55:41<61:51:14, 15.05s/it] 1%|▏ | %| | 187/15000 [51:52<63:47:21, 15.50s/it] 1%|▏ | 188/15000 [52:07<62:41:07, 15.24s/it] 1%|▏ | 189/15000 [52:22<62:02:19, 15.08s/it] 1%|▏ | 190/15000 [52:36<61:33:43, 14.96s/it] 1%|▏ | 191/15000 [52:51<61:11:52, 14.88s/it] 1%|▏ | 192/15000 [53:28<88:19:16, 21.47s/it] 1%|▏ | 193/15000 [53:43<80:07:41, 19.48s/it] 1%|▏ | 194/15000 [53:57<74:15:29, 18.06s/it] 1%|▏ | 195/15000 [54:12<70:07:20, 17.05s/it] 1%|▏ | 196/15000 [54:27<67:17:41, 16.36s/it] 1%|▏ | 197/15000 [54:41<65:13:44, 15.86s/it] 1%|▏ | 198/15000 [54:56<63:50:16, 15.53s/it] 1%|▏ | 199/15000 [55:11<62:49:55, 15.28s/it] 1%|▏ | 200/15000 [55:26<62:07:44, 15.11s/it] 1%|▏ | 200/15000 [55:26<62:07:44, 15.11s/it] 1%|▏ | 201/15000 [55:41<61:54:42, 15.06s/it] 1%|▏ | 202/15000 [55:55<61:26:01, 14.95s/it] 1%202/15000 [55:55<61:26:17, 14.95s/it] 1%|▏ | 203/15000 [56:10<61:07:09, 14.87s/it] 1%|▏ | 204/15000 [56:47<88:20:12, 21.49s/it] 1%|▏ | 205/15000 [57:02<79:57:11, 19.45s/it] 1%|▏ | 206/15000 [57:16<74:00:05, 18.01s/it] 1%|▏ | 207/15000 [57:31<69:59:28, 17.03s/it] 1%|▏ | 208/15000 [57:46<66:57:25, 16.30s/it] 1%|▏ | 209/15000 [58:00<64:56:40, 15.81s/it] 1%|▏ | 210/15000 [58:15<63:33:58, 15.47s/it] 1%|▏ | 211/15000 [58:30<62:28:08, 15.21s/it] 1%|▏ | 212/15000 [58:44<61:46:23, 15.04s/it] 1%|▏ | 213/15000 [58:59<61:12:09, 14.90s/it] 1%|▏ | 214/15000 [59:14<61:02:06, 14.86s/it] 1%|▏ | 215/15000 [59:51<89:02:51, 21.68s/it] 1%|▏ | 216/15000 [1:00:06<80:35:25, 19.62s/it] 1%|▏ | 217/15000 [1:00:21<74:35:35, 18.17s/it] 1%|▏ | 218/15000 [1:00:35<70:07:20, 17.08s/it] 1%|▏ | 219/15000 [1:00:50<67:12:50, 16.37s/it] 1%|▏
{'loss': 1.0221, 'learning_rate': 0.00013333333333333334, 'epoch': 0.06}
{'loss': 1.0221, 'learning_rate': 0.00013333333333333334, 'epoch': 0.06}
:08<63:08:04, 15.45s/it] 2%|▏ | 290/15000 [1:20:23<62:19:52, 15.25s/it] 2%|▏ | 291/15000 [1:20:37<61:29:50, 15.05s/it] 2%|▏ | 292/15000 [1:20:52<61:06:36, 14.96s/it] 2%|▏ | 293/15000 [1:21:06<60:41:52, 14.86s/it] 2%|▏ | 294/15000 [1:21:21<60:24:20, 14.79s/it] 2%|▏ | 295/15000 [1:21:58<87:18:21, 21.37s/it] 2%|▏ | 296/15000 [1:22:13<79:08:15, 19.38s/it] 2%|▏ | 297/15000 [1:22:27<73:25:45, 17.98s/it] 2%|▏ | 298/15000 [1:22:42<69:18:51, 16.97s/it] 2%|▏ | 299/15000 [1:22:57<66:36:50, 16.31s/it] 2%|▏ | 300/15000 [1:23:11<64:31:53, 15.80s/it] 2%|▏ | 300/15000 [1:23:12<64:31:53, 15.80s/it] 2%|▏ | 301/15000 [1:23:26<63:31:08, 15.56s/it] 2%|▏ | 302/15000 [1:23:41<62:31:07, 15.31s/it] 2%|▏ | 303/15000 [1:23:56<61:40:02, 15.11s/it] 2%|▏ | 304/15000 [1:24:10<61:07:26, 14.97s/i:08<63:09:08, 15.45s/it] 2%|▏ | 290/15000 [1:20:23<62:14:11, 15.23s/it] 2%|▏ | 291/15000 [1:20:37<61:35:10, 15.07s/it] 2%|▏ | 292/15000 [1:20:52<61:08:49, 14.97s/it] 2%|▏ | 293/15000 [1:21:07<60:40:33, 14.85s/it] 2%|▏ | 294/15000 [1:21:21<60:18:30, 14.76s/it] 2%|▏ | 295/15000 [1:21:58<87:21:29, 21.39s/it] 2%|▏ | 296/15000 [1:22:13<79:06:10, 19.37s/it] 2%|▏ | 297/15000 [1:22:27<73:28:01, 17.99s/it] 2%|▏ | 298/15000 [1:22:42<69:26:59, 17.01s/it] 2%|▏ | 299/15000 [1:22:57<66:35:21, 16.31s/it] 2%|▏ | 300/15000 [1:23:11<64:36:52, 15.82s/it] 2%|▏ | 300/15000 [1:23:12<64:36:52, 15.82s/it] 2%|▏ | 301/15000 [1:23:26<63:31:47, 15.56s/it] 2%|▏ | 302/15000 [1:23:41<62:27:08, 15.30s/it] 2%|▏ | 303/15000 [1:23:56<61:43:11, 15.12s/it] 2%|▏ | 304/15000 [1:24:10<61:07:42, 14.97s/i| 290/15000 [1:20:22<62:12:15, 15.22s/it] 2%|▏ | 291/15000 [1:20:37<61:32:35, 15.06s/it] 2%|▏ | 292/15000 [1:20:52<61:02:11, 14.94s/it] 2%|▏ | 293/15000 [1:21:06<60:40:27, 14.85s/it] 2%|▏ | 294/15000 [1:21:21<60:20:55, 14.77s/it] 2%|▏ | 295/15000 [1:21:58<87:23:15, 21.39s/it] 2%|▏ | 296/15000 [1:22:13<79:09:07, 19.38s/it] 2%|▏ | 297/15000 [1:22:27<73:24:21, 17.97s/it] 2%|▏ | 298/15000 [1:22:42<69:27:15, 17.01s/it] 2%|▏ | 299/15000 [1:22:57<66:33:19, 16.30s/it] 2%|▏ | 300/15000 [1:23:11<64:35:34, 15.82s/it] 2%|▏ | 300/15000 [1:23:12<64:35:34, 15.82s/it] 2%|▏ | 301/15000 [1:23:26<63:28:03, 15.54s/it] 2%|▏ | 302/15000 [1:23:41<62:26:22, 15.29s/it] 2%|▏ | 303/15000 [1:23:56<61:43:20, 15.12s/it] 2%|▏ | 304/15000 [1:24:10<61:04:14, 14.96s/it] 2%|▏ | 305/15000 [1:24:25<6t] 2%|▏ | 305/15000 [1:24:25<60:47:39, 14.89s/it] 2%|▏ | 306/15000 [1:25:02<87:23:31, 21.41s/it] 2%|▏ | 307/15000 [1:25:16<79:16:08, 19.42s/it] 2%|▏ | 308/15000 [1:25:31<73:33:12, 18.02s/it] 2%|▏ | 309/15000 [1:25:46<69:22:24, 17.00s/it] 2%|▏ | 310/15000 [1:26:00<66:32:00, 16.31s/it] 2%|▏ | 311/15000 [1:26:15<64:31:41, 15.81s/it] 2%|▏ | 312/15000 [1:26:30<63:16:05, 15.51s/it] 2%|▏ | 313/15000 [1:26:45<62:06:56, 15.23s/it] 2%|▏ | 314/15000 [1:26:59<61:29:34, 15.07s/it] 2%|▏ | 315/15000 [1:27:14<61:10:40, 15.00s/it] 2%|▏ | 316/15000 [1:27:29<60:52:06, 14.92s/it] 2%|▏ | 317/15000 [1:28:06<87:42:03, 21.50s/it] 2%|▏ | 318/15000 [1:28:20<79:24:26, 19.47s/it] 2%|▏ | 319/15000 [1:28:35<73:38:36, 18.06s/it] 2%|▏ | 320/15000 [1:28:50<69:31:52, 17.05s/it] 2%|▏ | 321/15000 [1:29:05<66:43:19, 16.36s/it] 2%|▏
{'loss': 0.9925, 'learning_rate': 0.00017777777777777779, 'epoch': 0.07}
{'loss': 0.9925, 'learning_rate': 0.00017777777777777779, 'epoch': 0.07}
:11, 15.76s/it] 3%|▎ | 392/15000 [1:48:36<62:40:52, 15.45s/it] 3%|▎ | 393/15000 [1:48:51<61:46:02, 15.22s/it] 3%|▎ | 394/15000 [1:49:05<61:03:29, 15.05s/it] 3%|▎ | 395/15000 [1:49:20<60:29:44, 14.91s/it] 3%|▎ | 396/15000 [1:49:35<60:04:03, 14.81s/it] 3%|▎ | 397/15000 [1:50:12<87:03:51, 21.46s/it] 3%|▎ | 398/15000 [1:50:26<78:37:30, 19.38s/it] 3%|▎ | 399/15000 [1:50:41<73:03:14, 18.01s/it] 3%|▎ | 400/15000 [1:50:56<68:58:06, 17.01s/it] 3%|▎ | 400/15000 [1:50:56<68:58:06, 17.01s/it] 3%|▎ | 401/15000 [1:51:10<66:20:20, 16.36s/it] 3%|▎ | 402/15000 [1:51:25<64:18:35, 15.86s/it] 3%|▎ | 403/15000 [1:51:40<62:50:15, 15.50s/it] 3%|▎ | 404/15000 [1:51:54<61:40:33, 15.21s/it] 3%|▎ | 405/15000 [1:52:09<61:05:20, 15.07s/it] 3%|▎ | 406/15000 [1:52:24<60:39:08, 14.96s/it] 3%|<7C>:25, 15.76s/it] 3%|▎ | 392/15000 [1:48:36<62:35:24, 15.42s/it] 3%|▎ | 393/15000 [1:48:51<61:42:39, 15.21s/it] 3%|▎ | 394/15000 [1:49:05<61:01:02, 15.04s/it] 3%|▎ | 395/15000 [1:49:20<60:32:09, 14.92s/it] 3%|▎ | 396/15000 [1:49:35<60:10:03, 14.83s/it] 3%|▎ | 397/15000 [1:50:11<87:00:49, 21.45s/it] 3%|▎ | 398/15000 [1:50:26<78:38:39, 19.39s/it] 3%|▎ | 399/15000 [1:50:41<73:06:06, 18.02s/it] 3%|▎ | 400/15000 [1:50:56<68:54:45, 16.99s/it] 3%|▎ | 400/15000 [1:50:56<68:54:45, 16.99s/it] 3%|▎ | 401/15000 [1:51:11<66:29:09, 16.39s/it] 3%|▎ | 402/15000 [1:51:25<64:12:45, 15.84s/it] 3%|▎ | 403/15000 [1:51:40<62:45:47, 15.48s/it] 3%|▎ | 404/15000 [1:51:54<61:52:05, 15.26s/it] 3%|▎ | 405/15000 [1:52:09<61:03:01, 15.06s/it] 3%|▎ | 406/15000 [1:52:24<60:43:16, 14.98s/it] 3%|<7C>00 [1:48:36<62:38:48, 15.44s/it] 3%|▎ | 393/15000 [1:48:51<61:44:48, 15.22s/it] 3%|▎ | 394/15000 [1:49:05<60:56:09, 15.02s/it] 3%|▎ | 395/15000 [1:49:20<60:24:25, 14.89s/it] 3%|▎ | 396/15000 [1:49:34<60:06:07, 14.82s/it] 3%|▎ | 397/15000 [1:50:11<87:04:46, 21.47s/it] 3%|▎ | 398/15000 [1:50:26<78:49:08, 19.43s/it] 3%|▎ | 399/15000 [1:50:41<72:59:05, 18.00s/it] 3%|▎ | 400/15000 [1:50:56<69:02:40, 17.02s/it] 3%|▎ | 400/15000 [1:50:56<69:02:40, 17.02s/it] 3%|▎ | 401/15000 [1:51:10<66:22:21, 16.37s/it] 3%|▎ | 402/15000 [1:51:25<64:15:30, 15.85s/it] 3%|▎ | 403/15000 [1:51:40<62:47:43, 15.49s/it] 3%|▎ | 404/15000 [1:51:54<61:46:52, 15.24s/it] 3%|▎ | 405/15000 [1:52:09<61:07:44, 15.08s/it] 3%|▎ | 406/15000 [1:52:24<60:32:45, 14.94s/it] 3%|▎ | 407/15000 [1:52:38<60:11:38, <20><> | 407/15000 [1:52:38<60:09:38, 14.84s/it] 3%|▎ | 408/15000 [1:53:15<86:56:20, 21.45s/it] 3%|▎ | 409/15000 [1:53:30<78:39:58, 19.41s/it] 3%|▎ | 410/15000 [1:53:44<72:50:22, 17.97s/it] 3%|▎ | 411/15000 [1:53:59<68:57:45, 17.02s/it] 3%|▎ | 412/15000 [1:54:14<65:57:21, 16.28s/it] 3%|▎ | 413/15000 [1:54:28<63:56:53, 15.78s/it] 3%|▎ | 414/15000 [1:54:43<62:26:58, 15.41s/it] 3%|▎ | 415/15000 [1:54:58<61:26:45, 15.17s/it] 3%|▎ | 416/15000 [1:55:12<60:51:15, 15.02s/it] 3%|▎ | 417/15000 [1:55:27<60:24:23, 14.91s/it] 3%|▎ | 418/15000 [1:55:42<60:03:01, 14.83s/it] 3%|▎ | 419/15000 [1:55:56<59:53:18, 14.79s/it] 3%|▎ | 420/15000 [1:56:33<86:40:14, 21.40s/it] 3%|▎ | 421/15000 [1:56:48<78:35:30, 19.41s/it] 3%|▎ | 422/15000 [1:57:02<72:40:33, 17.95s/it] 3%|▎ | 423/15000 [1:57:17<68:44:22, 16.98s/it] 3%|▎ | 424/150
{'loss': 0.9731, 'learning_rate': 0.00019999417253661235, 'epoch': 0.09}
{'loss': 0.9731, 'learning_rate': 0.00019999417253661235, 'epoch': 0.09}
53<62:08:13, 15.42s/it] 3%|▎ | 495/15000 [2:17:07<61:10:40, 15.18s/it] 3%|▎ | 496/15000 [2:17:22<60:30:47, 15.02s/it] 3%|▎ | 497/15000 [2:17:37<59:59:12, 14.89s/it] 3%|▎ | 498/15000 [2:17:51<59:43:49, 14.83s/it] 3%|▎ | 499/15000 [2:18:28<86:15:19, 21.41s/it] 3%|▎ | 500/15000 [2:18:43<78:05:19, 19.39s/it] 3%|▎ | 500/15000 [2:18:43<78:05:19, 19.39s/it] 3%|▎ | 501/15000 [2:18:58<72:34:33, 18.02s/it] 3%|▎ | 502/15000 [2:19:12<68:26:31, 16.99s/it] 3%|▎ | 503/15000 [2:19:27<65:40:11, 16.31s/it] 3%|▎ | 504/15000 [2:19:42<63:38:08, 15.80s/it] 3%|▎ | 505/15000 [2:19:56<62:12:26, 15.45s/it] 3%|▎ | 506/15000 [2:20:11<61:20:02, 15.23s/it] 3%|▎ | 507/15000 [2:20:26<60:34:26, 15.05s/it] 3%|▎ | 508/15000 [2:20:40<60:09:26, 14.94s/it] 3%|▎ | 509/15000 [2:20:55<59:47:20, 14.85s/it4s/it] 3%|▎ | 494/15000 [2:16:53<62:00:15, 15.39s/it] 3%|▎ | 495/15000 [2:17:08<61:12:39, 15.19s/it] 3%|▎ | 496/15000 [2:17:22<60:26:37, 15.00s/it] 3%|▎ | 497/15000 [2:17:37<60:05:09, 14.91s/it] 3%|▎ | 498/15000 [2:17:51<59:42:19, 14.82s/it] 3%|▎ | 499/15000 [2:18:28<86:17:01, 21.42s/it] 3%|▎ | 500/15000 [2:18:43<78:02:45, 19.38s/it] 3%|▎ | 500/15000 [2:18:43<78:02:45, 19.38s/it] 3%|▎ | 501/15000 [2:18:58<72:31:47, 18.01s/it] 3%|▎ | 502/15000 [2:19:12<68:25:19, 16.99s/it] 3%|▎ | 503/15000 [2:19:27<65:40:26, 16.31s/it] 3%|▎ | 504/15000 [2:19:42<63:36:32, 15.80s/it] 3%|▎ | 505/15000 [2:19:56<62:11:21, 15.45s/it] 3%|▎ | 506/15000 [2:20:11<61:13:08, 15.21s/it] 3%|▎ | 507/15000 [2:20:26<60:41:03, 15.07s/it] 3%|▎ | 508/15000 [2:20:40<60:07:56, 14.94s/it] 3%|▎ 5s/it] 3%|▎ | 494/15000 [2:16:53<62:04:24, 15.40s/it] 3%|▎ | 495/15000 [2:17:08<61:07:07, 15.17s/it] 3%|▎ | 496/15000 [2:17:22<60:37:00, 15.05s/it] 3%|▎ | 497/15000 [2:17:37<60:03:52, 14.91s/it] 3%|▎ | 498/15000 [2:17:51<59:39:04, 14.81s/it] 3%|▎ | 499/15000 [2:18:28<86:15:23, 21.41s/it] 3%|▎ | 500/15000 [2:18:43<78:00:42, 19.37s/it] 3%|▎ | 500/15000 [2:18:43<78:00:42, 19.37s/it] 3%|▎ | 501/15000 [2:18:58<72:28:37, 18.00s/it] 3%|▎ | 502/15000 [2:19:12<68:26:26, 16.99s/it] 3%|▎ | 503/15000 [2:19:27<65:42:09, 16.32s/it] 3%|▎ | 504/15000 [2:19:42<63:40:01, 15.81s/it] 3%|▎ | 505/15000 [2:19:56<62:12:21, 15.45s/it] 3%|▎ | 506/15000 [2:20:11<61:16:34, 15.22s/it] 3%|▎ | 507/15000 [2:20:26<60:42:49, 15.08s/it] 3%|▎ | 508/15000 [2:20:40<60:01:58, 14.91s/it] 3%|▎ | 509/15000 [2:20:55<59:51:32, 14.87s/it] 3%|▎ | 510/15000 [2:21:10<59:33:05, 14.80s/it] 3%|▎ | 511/15000 [2:21:46<86:00:27, 21.37s/it] 3%|▎ | 512/15000 [2:22:01<77:50:46, 19.34s/it] 3%|▎ | 513/15000 [2:22:15<71:59:17, 17.89s/it] 3%|▎ | 514/15000 [2:22:30<68:12:15, 16.95s/it] 3%|▎ | 515/15000 [2:22:45<65:30:34, 16.28s/it] 3%|▎ | 516/15000 [2:22:59<63:19:16, 15.74s/it] 3%|▎ | 517/15000 [2:23:14<62:09:20, 15.45s/it] 3%|▎ | 518/15000 [2:23:29<61:05:05, 15.18s/it] 3%|▎ | 519/15000 [2:23:43<60:22:31, 15.01s/it] 3%|▎ | 520/15000 [2:23:58<60:08:17, 14.95s/it] 3%|▎ | 521/15000 [2:24:13<59:47:33, 14.87s/it] 3%|▎ | 522/15000 [2:24:49<85:56:51, 21.37s/it] 3%|▎ | 523/15000 [2:25:04<77:51:43, 19.36s/it] 3%|▎ | 524/15000 [2:25:19<72:13:48, 17.96s/it] 4%|▎ | 525/15000 [2:25:33<68:12:14, 16.96s/it] 4%|▎ | 526/15000 [2:25:
{'loss': 0.9581, 'learning_rate': 0.00019994755690455152, 'epoch': 0.11}
{'loss': 0.9581, 'learning_rate': 0.00019994755690455152, 'epoch': 0.11}
4%|▍ | 596/15000 [2:45:08<62:03:21, 15.51s/it] 4%|▍ | 597/15000 [2:45:23<61:03:40, 15.26s/it] 4%|▍ | 598/15000 [2:45:38<60:19:06, 15.08s/it] 4%|▍ | 599/15000 [2:45:53<59:53:41, 14.97s/it] 4%|▍ | 600/15000 [2:46:07<59:37:36, 14.91s/it] 4%|▍ | 600/15000 [2:46:07<59:37:36, 14.91s/it] 4%|▍ | 601/15000 [2:46:44<85:46:06, 21.44s/it] 4%|▍ | 602/15000 [2:46:59<77:39:31, 19.42s/it] 4%|▍ | 603/15000 [2:47:13<71:58:37, 18.00s/it] 4%|▍ | 604/15000 [2:47:28<68:01:54, 17.01s/it] 4%|▍ | 605/15000 [2:47:43<65:12:23, 16.31s/it] 4%|▍ | 606/15000 [2:47:57<63:19:39, 15.84s/it] 4%|▍ | 607/15000 [2:48:12<61:56:03, 15.49s/it] 4%|▍ | 608/15000 [2:48:27<61:05:29, 15.28s/it] 4%|▍ | 609/15000 [2:48:41<60:12:42, 15.06s/it] 4%|▍ | 610/15000 [2:48:56<59:50:19, 14.97s/it] 4%|▍ | 611/14%|▍ | 596/15000 [2:45:08<62:00:08, 15.50s/it] 4%|▍ | 597/15000 [2:45:23<60:57:02, 15.23s/it] 4%|▍ | 598/15000 [2:45:38<60:22:16, 15.09s/it] 4%|▍ | 599/15000 [2:45:53<59:57:24, 14.99s/it] 4%|▍ | 600/15000 [2:46:07<59:37:06, 14.90s/it] 4%|▍ | 600/15000 [2:46:07<59:37:06, 14.90s/it] 4%|▍ | 601/15000 [2:46:44<85:49:39, 21.46s/it] 4%|▍ | 602/15000 [2:46:59<77:36:15, 19.40s/it] 4%|▍ | 603/15000 [2:47:13<71:52:47, 17.97s/it] 4%|▍ | 604/15000 [2:47:28<68:04:47, 17.02s/it] 4%|▍ | 605/15000 [2:47:43<65:16:23, 16.32s/it] 4%|▍ | 606/15000 [2:47:57<63:16:33, 15.83s/it] 4%|▍ | 607/15000 [2:48:12<61:59:54, 15.51s/it] 4%|▍ | 608/15000 [2:48:27<61:02:47, 15.27s/it] 4%|▍ | 609/15000 [2:48:41<60:12:43, 15.06s/it] 4%|▍ | 610/15000 [2:48:56<59:46:02, 14.95s/it] 4%|▍ | 611/118, 15.46s/it] 4%|▍ | 597/15000 [2:45:23<60:58:20, 15.24s/it] 4%|▍ | 598/15000 [2:45:38<60:21:21, 15.09s/it] 4%|▍ | 599/15000 [2:45:52<59:51:56, 14.97s/it] 4%|▍ | 600/15000 [2:46:07<59:37:55, 14.91s/it] 4%|▍ | 600/15000 [2:46:07<59:37:55, 14.91s/it] 4%|▍ | 601/15000 [2:46:44<85:45:00, 21.44s/it] 4%|▍ | 602/15000 [2:46:59<77:37:55, 19.41s/it] 4%|▍ | 603/15000 [2:47:13<71:57:33, 17.99s/it] 4%|▍ | 604/15000 [2:47:28<68:06:42, 17.03s/it] 4%|▍ | 605/15000 [2:47:43<65:17:05, 16.33s/it] 4%|▍ | 606/15000 [2:47:57<63:19:58, 15.84s/it] 4%|▍ | 607/15000 [2:48:12<61:59:07, 15.50s/it] 4%|▍ | 608/15000 [2:48:27<61:01:25, 15.26s/it] 4%|▍ | 609/15000 [2:48:41<60:16:23, 15.08s/it] 4%|▍ | 610/15000 [2:48:56<59:42:17, 14.94s/it] 4%|▍ | 611/15000 [2:49:11<59:23:41, 14.86s/it] 4%|<7C><>5000 [2:49:11<59:33:40, 14.90s/it] 4%|▍ | 612/15000 [2:49:25<59:01:01, 14.77s/it] 4%|▍ | 613/15000 [2:50:02<85:30:58, 21.40s/it] 4%|▍ | 614/15000 [2:50:17<77:19:24, 19.35s/it] 4%|▍ | 615/15000 [2:50:32<71:42:22, 17.95s/it] 4%|▍ | 616/15000 [2:50:46<67:43:10, 16.95s/it] 4%|▍ | 617/15000 [2:51:01<65:07:26, 16.30s/it] 4%|▍ | 618/15000 [2:51:16<63:05:52, 15.79s/it] 4%|▍ | 619/15000 [2:51:30<61:46:10, 15.46s/it] 4%|▍ | 620/15000 [2:51:45<60:45:52, 15.21s/it] 4%|▍ | 621/15000 [2:51:59<59:58:35, 15.02s/it] 4%|▍ | 622/15000 [2:52:14<59:34:08, 14.92s/it] 4%|▍ | 623/15000 [2:52:29<59:14:06, 14.83s/it] 4%|▍ | 624/15000 [2:53:05<85:20:40, 21.37s/it] 4%|▍ | 625/15000 [2:53:20<77:18:37, 19.36s/it] 4%|▍ | 626/15000 [2:53:35<71:36:09, 17.93s/it] 4%|▍ | 627/15000 [2:53:49<67:42:58, 16.96s/it] 4%|▍ | 628/15000 [2:54:04<64:47:
{'loss': 0.9496, 'learning_rate': 0.0001998543473718677, 'epoch': 0.13}
{'loss': 0.9496, 'learning_rate': 0.0001998543473718677, 'epoch': 0.13}
| 698/15000 [3:13:22<61:25:24, 15.46s/it] 5%|▍ | 699/15000 [3:13:37<60:33:00, 15.24s/it] 5%|▍ | 700/15000 [3:13:52<59:58:49, 15.10s/it] 5%|▍ | 700/15000 [3:13:52<59:58:49, 15.10s/it] 5%|▍ | 701/15000 [3:14:07<59:39:34, 15.02s/it] 5%|▍ | 702/15000 [3:14:22<59:23:11, 14.95s/it] 5%|▍ | 703/15000 [3:14:36<59:06:23, 14.88s/it] 5%|▍ | 704/15000 [3:15:13<85:24:33, 21.51s/it] 5%|▍ | 705/15000 [3:15:28<77:21:53, 19.48s/it] 5%|▍ | 706/15000 [3:15:43<71:38:41, 18.04s/it] 5%|▍ | 707/15000 [3:15:57<67:38:47, 17.04s/it] 5%|▍ | 708/15000 [3:16:12<64:51:58, 16.34s/it] 5%|▍ | 709/15000 [3:16:27<62:59:47, 15.87s/it] 5%|▍ | 710/15000 [3:16:41<61:30:27, 15.50s/it] 5%|▍ | 711/15000 [3:16:56<60:27:36, 15.23s/it] 5%|▍ | 712/15000 [3:17:11<59:55:02, 15.10s/it] 5%|▍ | 713/15000 [3:1 | 698/15000 [3:13:22<61:28:06, 15.47s/it] 5%|▍ | 699/15000 [3:13:37<60:38:44, 15.27s/it] 5%|▍ | 700/15000 [3:13:52<59:56:37, 15.09s/it] 5%|▍ | 700/15000 [3:13:52<59:56:37, 15.09s/it] 5%|▍ | 701/15000 [3:14:07<59:38:31, 15.02s/it] 5%|▍ | 702/15000 [3:14:21<59:14:29, 14.92s/it] 5%|▍ | 703/15000 [3:14:36<59:06:13, 14.88s/it] 5%|▍ | 704/15000 [3:15:13<85:26:01, 21.51s/it] 5%|▍ | 705/15000 [3:15:28<77:23:00, 19.49s/it] 5%|▍ | 706/15000 [3:15:43<71:34:53, 18.03s/it] 5%|▍ | 707/15000 [3:15:57<67:41:46, 17.05s/it] 5%|▍ | 708/15000 [3:16:12<64:54:44, 16.35s/it] 5%|▍ | 709/15000 [3:16:27<62:58:38, 15.86s/it] 5%|▍ | 710/15000 [3:16:41<61:30:12, 15.49s/it] 5%|▍ | 711/15000 [3:16:56<60:26:52, 15.23s/it] 5%|▍ | 712/15000 [3:17:11<59:53:07, 15.09s/it] 5%|▍ | 713/15000 [3:1s/it] 5%|▍ | 699/15000 [3:13:37<60:34:44, 15.25s/it] 5%|▍ | 700/15000 [3:13:52<59:56:57, 15.09s/it] 5%|▍ | 700/15000 [3:13:52<59:56:57, 15.09s/it] 5%|▍ | 701/15000 [3:14:07<59:38:50, 15.02s/it] 5%|▍ | 702/15000 [3:14:21<59:13:28, 14.91s/it] 5%|▍ | 703/15000 [3:14:36<59:15:38, 14.92s/it] 5%|▍ | 704/15000 [3:15:13<85:33:37, 21.55s/it] 5%|▍ | 705/15000 [3:15:28<77:18:03, 19.47s/it] 5%|▍ | 706/15000 [3:15:43<71:41:18, 18.06s/it] 5%|▍ | 707/15000 [3:15:57<67:37:12, 17.03s/it] 5%|▍ | 708/15000 [3:16:12<64:52:35, 16.34s/it] 5%|▍ | 709/15000 [3:16:27<62:54:38, 15.85s/it] 5%|▍ | 710/15000 [3:16:41<61:27:29, 15.48s/it] 5%|▍ | 711/15000 [3:16:56<60:24:17, 15.22s/it] 5%|▍ | 712/15000 [3:17:11<59:51:43, 15.08s/it] 5%|▍ | 713/15000 [3:17:25<59:22:57, 14.96s/it] 5%|▍ 7:25<59:19:53, 14.95s/it] 5%|▍ | 714/15000 [3:17:40<59:03:11, 14.88s/it] 5%|▍ | 715/15000 [3:18:17<85:15:42, 21.49s/it] 5%|▍ | 716/15000 [3:18:32<77:02:58, 19.42s/it] 5%|▍ | 717/15000 [3:18:46<71:28:13, 18.01s/it] 5%|▍ | 718/15000 [3:19:01<67:37:41, 17.05s/it] 5%|▍ | 719/15000 [3:19:16<64:46:42, 16.33s/it] 5%|▍ | 720/15000 [3:19:31<62:56:00, 15.87s/it] 5%|▍ | 721/15000 [3:19:45<61:34:53, 15.53s/it] 5%|▍ | 722/15000 [3:20:00<60:41:36, 15.30s/it] 5%|▍ | 723/15000 [3:20:15<59:54:17, 15.11s/it] 5%|▍ | 724/15000 [3:20:30<59:36:15, 15.03s/it] 5%|▍ | 725/15000 [3:20:44<59:06:44, 14.91s/it] 5%|▍ | 726/15000 [3:21:21<84:45:42, 21.38s/it] 5%|▍ | 727/15000 [3:21:35<76:42:06, 19.35s/it] 5%|▍ | 728/15000 [3:21:50<71:18:44, 17.99s/it] 5%|▍ | 729/15000 [3:22:05<67:20:20, 16.99s/it] 5%|▍ | 730/15000 [3:22:19<64:26:47, 16.26
{'loss': 0.94, 'learning_rate': 0.00019971458739130598, 'epoch': 0.15}
{'loss': 0.94, 'learning_rate': 0.00019971458739130598, 'epoch': 0.15}
22:46, 21.37s/it] 5%|▌ | 784/15000 [3:37:22<76:24:46, 19.35s/it] 5%|▌ | 785/15000 [3:37:37<70:44:36, 17.92s/it] 5%|▌ | 786/15000 [3:37:51<66:49:17, 16.92s/it] 5%|▌ | 787/15000 [3:38:06<64:05:09, 16.23s/it] 5%|▌ | 788/15000 [3:38:20<62:13:52, 15.76s/it] 5%|▌ | 789/15000 [3:38:35<60:56:19, 15.44s/it] 5%|▌ | 790/15000 [3:38:50<59:56:24, 15.19s/it] 5%|▌ | 791/15000 [3:39:04<59:18:41, 15.03s/it] 5%|▌ | 792/15000 [3:39:19<58:49:27, 14.90s/it] 5%|▌ | 793/15000 [3:39:34<58:24:37, 14.80s/it] 5%|▌ | 794/15000 [3:39:48<58:10:48, 14.74s/it] 5%|▌ | 795/15000 [3:40:25<84:25:45, 21.40s/it] 5%|▌ | 796/15000 [3:40:40<76:21:20, 19.35s/it] 5%|▌ | 797/15000 [3:40:54<70:47:17, 17.94s/it] 5%|▌ | 798/15000 [3:41:09<66:57:36, 16.97s/it] 5%|▌ | 799/15000 [3:41:24<64:08:49, 16.26s/it] 5%|▌ | 800/15000 [3:41:38<62:07:20, 15.75s/it] 00/15000 [3:41:38<62:14:17, 15.78s/it] 5%|▌ | 800/15000 [3:41:38<62:14:17, 15.78s/it] 5%|▌ | 801/15000 [3:41:53<61:04:35, 15.49s/it] 5%|▌ | 802/15000 [3:42:08<60:03:54, 15.23s/it] 5%|▌ | 803/15000 [3:42:22<59:24:49, 15.07s/it] 5%|▌ | 804/15000 [3:42:37<59:08:22, 15.00s/it] 5%|▌ | 805/15000 [3:42:52<58:42:57, 14.89s/it] 5%|▌ | 806/15000 [3:43:29<84:37:25, 21.46s/it] 5%|▌ | 807/15000 [3:43:43<76:24:38, 19.38s/it] 5%|▌ | 808/15000 [3:43:58<71:01:57, 18.02s/it] 5%|▌ | 809/15000 [3:44:13<66:58:29, 16.99s/it] 5%|▌ | 810/15000 [3:44:27<64:08:21, 16.27s/it] 5%|▌ | 811/15000 [3:44:42<62:12:29, 15.78s/it] 5%|▌ | 812/15000 [3:44:57<61:00:28, 15.48s/it] 5%|▌ | 813/15000 [3:45:11<60:03:50, 15.24s/it] 5%|▌ | 814/15000 [3:45:26<59:30:36, 15.10s/it] 5%|▌ | 815/15000 [3:45:41<58:500/15000 [3:41:38<62:16:38, 15.79s/it] 5%|▌ | 800/15000 [3:41:39<62:16:38, 15.79s/it] 5%|▌ | 801/15000 [3:41:53<60:57:50, 15.46s/it] 5%|▌ | 802/15000 [3:42:08<60:08:55, 15.25s/it] 5%|▌ | 803/15000 [3:42:23<59:27:15, 15.08s/it] 5%|▌ | 804/15000 [3:42:37<59:01:03, 14.97s/it] 5%|▌ | 805/15000 [3:42:52<58:34:37, 14.86s/it] 5%|▌ | 806/15000 [3:43:29<84:37:00, 21.46s/it] 5%|▌ | 807/15000 [3:43:43<76:21:22, 19.37s/it] 5%|▌ | 808/15000 [3:43:58<70:53:36, 17.98s/it] 5%|▌ | 809/15000 [3:44:13<67:04:02, 17.01s/it] 5%|▌ | 810/15000 [3:44:27<64:18:23, 16.31s/it] 5%|▌ | 811/15000 [3:44:42<62:16:35, 15.80s/it] 5%|▌ | 812/15000 [3:44:57<60:54:17, 15.45s/it] 5%|▌ | 813/15000 [3:45:11<60:08:10, 15.26s/it] 5%|▌ | 814/15000 [3:45:26<59:27:46, 15.09s/it] 5%|▌ | 815/15000 [3:45:41<59:0 5%|▌ | 800/15000 [3:41:38<62:07:20, 15.75s/it] 5%|▌ | 801/15000 [3:41:53<61:04:27, 15.48s/it] 5%|▌ | 802/15000 [3:42:08<60:06:59, 15.24s/it] 5%|▌ | 803/15000 [3:42:23<59:32:15, 15.10s/it] 5%|▌ | 804/15000 [3:42:37<59:03:25, 14.98s/it] 5%|▌ | 805/15000 [3:42:52<58:37:42, 14.87s/it] 5%|▌ | 806/15000 [3:43:29<84:28:33, 21.43s/it] 5%|▌ | 807/15000 [3:43:43<76:31:15, 19.41s/it] 5%|▌ | 808/15000 [3:43:58<70:55:34, 17.99s/it] 5%|▌ | 809/15000 [3:44:13<67:05:05, 17.02s/it] 5%|▌ | 810/15000 [3:44:27<64:10:52, 16.28s/it] 5%|▌ | 811/15000 [3:44:42<62:17:02, 15.80s/it] 5%|▌ | 812/15000 [3:44:57<60:59:54, 15.48s/it] 5%|▌ | 813/15000 [3:45:11<60:07:39, 15.26s/it] 5%|▌ | 814/15000 [3:45:26<59:23:56, 15.07s/it] 5%|▌ | 815/15000 [3:45:41<58:59:34, 14.97s/it] 5%|▌ | 816/1
| 885/15000 [4:05:00<57:54:27, 14.77s/it] 6%|▌ | 886/15000 [4:05:37<83:45:53, 21.37s/it] 6%|▌ | 887/15000 [4:05:52<75:50:40, 19.35s/it] 6%|▌ | 888/15000 [4:06:06<70:21:31, 17.95s/it] 6%|▌ | 889/15000 [4:06:21<66:24:16, 16.94s/it] 6%|▌ | 890/15000 [4:06:36<63:46:00, 16.27s/it] 6%|▌ | 891/15000 [4:06:50<61:49:37, 15.78s/it] 6%|▌ | 892/15000 [4:07:05<60:35:47, 15.46s/it] 6%|▌ | 893/15000 [4:07:20<59:48:17, 15.26s/it] 6%|▌ | 894/15000 [4:07:34<59:02:16, 15.07s/it] 6%|▌ | 895/15000 [4:07:49<58:27:23, 14.92s/it] 6%|▌ | 896/15000 [4:08:04<58:19:48, 14.89s/it] 6%|▌ | 897/15000 [4:08:41<84:18:07, 21.52s/it] 6%|▌ | 898/15000 [4:08:55<76:17:08, 19.47s/it] 6%|▌ | 899/15000 [4:09:10<70:40:53, 18.05s/it] 6%|▌ | 900/15000 [4:09:25<66:40:16, 17.02s/it] 6%|▌ | 900/15000 [{'loss': 0.9312, 'learning_rate': 0.0001995283421166614, 'epoch': 0.17}
| 885/15000 [4:05:00<57:50:36, 14.75s/it] 6%|▌ | 886/15000 [4:05:37<83:48:36, 21.38s/it] 6%|▌ | 887/15000 [4:05:52<75:57:24, 19.38s/it] 6%|▌ | 888/15000 [4:06:06<70:23:35, 17.96s/it] 6%|▌ | 889/15000 [4:06:21<66:27:00, 16.95s/it] 6%|▌ | 890/15000 [4:06:36<63:39:23, 16.24s/it] 6%|▌ | 891/15000 [4:06:50<61:45:30, 15.76s/it] 6%|▌ | 892/15000 [4:07:05<60:31:27, 15.44s/it] 6%|▌ | 893/15000 [4:07:20<59:46:33, 15.25s/it] 6%|▌ | 894/15000 [4:07:34<59:07:15, 15.09s/it] 6%|▌ | 895/15000 [4:07:49<58:36:55, 14.96s/it] 6%|▌ | 896/15000 [4:08:04<58:15:54, 14.87s/it] 6%|▌ | 897/15000 [4:08:41<84:26:01, 21.55s/it] 6%|▌ | 898/15000 [4:08:56<76:20:11, 19.49s/it] 6%|▌ | 899/15000 [4:09:10<70:33:56, 18.02s/it] 6%|▌ | 900/15000 [4:09:25<66:39:19, 17.02s/it] 6%|▌ | 900/15000 [{'loss': 0.9312, 'learning_rate': 0.0001995283421166614, 'epoch': 0.17}
.77s/it] 6%|▌ | 886/15000 [4:05:37<83:49:50, 21.38s/it] 6%|▌ | 887/15000 [4:05:52<75:53:43, 19.36s/it] 6%|▌ | 888/15000 [4:06:06<70:20:21, 17.94s/it] 6%|▌ | 889/15000 [4:06:21<66:26:29, 16.95s/it] 6%|▌ | 890/15000 [4:06:35<63:40:54, 16.25s/it] 6%|▌ | 891/15000 [4:06:50<61:57:09, 15.81s/it] 6%|▌ | 892/15000 [4:07:05<60:38:16, 15.47s/it] 6%|▌ | 893/15000 [4:07:20<59:42:02, 15.24s/it] 6%|▌ | 894/15000 [4:07:34<59:00:04, 15.06s/it] 6%|▌ | 895/15000 [4:07:49<58:38:14, 14.97s/it] 6%|▌ | 896/15000 [4:08:04<58:14:23, 14.87s/it] 6%|▌ | 897/15000 [4:08:41<84:18:08, 21.52s/it] 6%|▌ | 898/15000 [4:08:55<76:21:25, 19.49s/it] 6%|▌ | 899/15000 [4:09:10<70:31:56, 18.01s/it] 6%|▌ | 900/15000 [4:09:25<66:47:21, 17.05s/it] 6%|▌ | 900/15000 [4:09:25<66:47:21, 17.05s/it] 6%|▌ 4:09:25<66:39:19, 17.02s/it] 6%|▌ | 901/15000 [4:09:40<64:10:53, 16.39s/it] 6%|▌ | 902/15000 [4:09:54<62:11:14, 15.88s/it] 6%|▌ | 903/15000 [4:10:09<60:48:20, 15.53s/it] 6%|▌ | 904/15000 [4:10:24<59:46:29, 15.27s/it] 6%|▌ | 905/15000 [4:10:38<59:00:16, 15.07s/it] 6%|▌ | 906/15000 [4:10:53<58:39:55, 14.98s/it] 6%|▌ | 907/15000 [4:11:08<58:17:26, 14.89s/it] 6%|▌ | 908/15000 [4:11:45<84:10:44, 21.50s/it] 6%|▌ | 909/15000 [4:11:59<76:10:05, 19.46s/it] 6%|▌ | 910/15000 [4:12:14<70:22:09, 17.98s/it] 6%|▌ | 911/15000 [4:12:29<66:29:20, 16.99s/it] 6%|▌ | 912/15000 [4:12:43<63:45:43, 16.29s/it] 6%|▌ | 913/15000 [4:12:58<61:40:06, 15.76s/it] 6%|▌ | 914/15000 [4:13:13<60:31:12, 15.47s/it] 6%|▌ | 915/15000 [4:13:27<59:30:24, 15.21s/it] 6%|▌ | 916/15000 [4:13:42<58:49:13, 15.04s/it] 6%|▌ | 917/15000 [4:13:56<58:12:43, 14.4:09:25<66:40:16, 17.02s/it] 6%|▌ | 901/15000 [4:09:40<64:09:26, 16.38s/it] 6%|▌ | 902/15000 [4:09:54<62:16:56, 15.90s/it] 6%|▌ | 903/15000 [4:10:09<60:53:42, 15.55s/it] 6%|▌ | 904/15000 [4:10:24<59:47:19, 15.27s/it] 6%|▌ | 905/15000 [4:10:38<58:59:25, 15.07s/it] 6%|▌ | 906/15000 [4:10:53<58:35:10, 14.96s/it] 6%|▌ | 907/15000 [4:11:08<58:13:53, 14.88s/it] 6%|▌ | 908/15000 [4:11:45<84:03:41, 21.47s/it] 6%|▌ | 909/15000 [4:11:59<76:05:35, 19.44s/it] 6%|▌ | 910/15000 [4:12:14<70:28:39, 18.01s/it] 6%|▌ | 911/15000 [4:12:29<66:29:44, 16.99s/it] 6%|▌ | 912/15000 [4:12:43<63:41:04, 16.27s/it] 6%|▌ | 913/15000 [4:12:58<61:45:00, 15.78s/it] 6%|▌ | 914/15000 [4:13:13<60:31:03, 15.47s/it] 6%|▌ | 915/15000 [4:13:27<59:26:21, 15.19s/it] 6%|▌ | 916/15000 [4:13:42<58:42:57, 15.01s/it] 6%|▌ | 917/15000 [4:13:56<58:20:04, 14. | 901/15000 [4:09:40<64:13:37, 16.40s/it] 6%|▌ | 902/15000 [4:09:54<62:16:06, 15.90s/it] 6%|▌ | 903/15000 [4:10:09<60:48:04, 15.53s/it] 6%|▌ | 904/15000 [4:10:24<59:43:03, 15.25s/it] 6%|▌ | 905/15000 [4:10:38<59:04:41, 15.09s/it] 6%|▌ | 906/15000 [4:10:53<58:39:16, 14.98s/it] 6%|▌ | 907/15000 [4:11:08<58:20:01, 14.90s/it] 6%|▌ | 908/15000 [4:11:45<84:04:55, 21.48s/it] 6%|▌ | 909/15000 [4:11:59<76:00:42, 19.42s/it] 6%|▌ | 910/15000 [4:12:14<70:30:23, 18.01s/it] 6%|▌ | 911/15000 [4:12:29<66:26:07, 16.98s/it] 6%|▌ | 912/15000 [4:12:43<63:40:16, 16.27s/it] 6%|▌ | 913/15000 [4:12:58<61:49:51, 15.80s/it] 6%|▌ | 914/15000 [4:13:12<60:26:15, 15.45s/it] 6%|▌ | 915/15000 [4:13:27<59:22:55, 15.18s/it] 6%|▌ | 916/15000 [4:13:42<58:50:22, 15.04s/it] 6%|▌ | 917/15000 [4:13:56<58:18:34, 14.91s/it] 6%|▌ | 918/15000 [4:1
{'loss': 0.923, 'learning_rate': 0.00019929569837240564, 'epoch': 0.19}
{'loss': 0.923, 'learning_rate': 0.00019929569837240564, 'epoch': 0.19}
| 987/15000 [4:33:16<57:44:35, 14.83s/it] 7%|▋ | 988/15000 [4:33:52<83:32:48, 21.47s/it] 7%|▋ | 989/15000 [4:34:07<75:34:55, 19.42s/it] 7%|▋ | 990/15000 [4:34:22<69:57:38, 17.98s/it] 7%|▋ | 991/15000 [4:34:36<66:07:37, 16.99s/it] 7%|▋ | 992/15000 [4:34:51<63:29:21, 16.32s/it] 7%|▋ | 993/15000 [4:35:06<61:31:40, 15.81s/it] 7%|▋ | 994/15000 [4:35:21<60:15:59, 15.49s/it] 7%|▋ | 995/15000 [4:35:35<59:12:33, 15.22s/it] 7%|▋ | 996/15000 [4:35:50<58:30:30, 15.04s/it] 7%|▋ | 997/15000 [4:36:04<58:06:32, 14.94s/it] 7%|▋ | 998/15000 [4:36:19<57:35:03, 14.81s/it] 7%|▋ | 999/15000 [4:36:56<83:25:21, 21.45s/it] 7%|▋ | 1000/15000 [4:37:11<75:28:45, 19.41s/it] 7%|▋ | 1000/15000 [4:37:11<75:28:45, 19.41s/it] 7%|▋ | 1001/15000 [4:37:25<70:11:36, 18.05s/it] 7%|▋ | 1002/15000 [4:37| 987/15000 [4:33:16<57:43:54, 14.83s/it] 7%|▋ | 988/15000 [4:33:52<83:35:53, 21.48s/it] 7%|▋ | 989/15000 [4:34:07<75:28:06, 19.39s/it] 7%|▋ | 990/15000 [4:34:22<69:57:39, 17.98s/it] 7%|▋ | 991/15000 [4:34:36<66:04:57, 16.98s/it] 7%|▋ | 992/15000 [4:34:51<63:34:56, 16.34s/it] 7%|▋ | 993/15000 [4:35:06<61:33:34, 15.82s/it] 7%|▋ | 994/15000 [4:35:21<60:15:16, 15.49s/it] 7%|▋ | 995/15000 [4:35:35<59:13:43, 15.22s/it] 7%|▋ | 996/15000 [4:35:50<58:35:02, 15.06s/it] 7%|▋ | 997/15000 [4:36:04<58:06:04, 14.94s/it] 7%|▋ | 998/15000 [4:36:19<57:40:56, 14.83s/it] 7%|▋ | 999/15000 [4:36:56<83:23:21, 21.44s/it] 7%|▋ | 1000/15000 [4:37:10<75:21:09, 19.38s/it] 7%|▋ | 1000/15000 [4:37:11<75:21:09, 19.38s/it] 7%|▋ | 1001/15000 [4:37:25<70:15:19, 18.07s/it] 7%|▋ | 1002/15000 [4:37 7%|▋ | 988/15000 [4:33:52<83:27:40, 21.44s/it] 7%|▋ | 989/15000 [4:34:07<75:29:41, 19.40s/it] 7%|▋ | 990/15000 [4:34:22<70:01:16, 17.99s/it] 7%|▋ | 991/15000 [4:34:36<66:10:15, 17.00s/it] 7%|▋ | 992/15000 [4:34:51<63:26:59, 16.31s/it] 7%|▋ | 993/15000 [4:35:06<61:27:33, 15.80s/it] 7%|▋ | 994/15000 [4:35:20<60:12:41, 15.48s/it] 7%|▋ | 995/15000 [4:35:35<59:10:47, 15.21s/it] 7%|▋ | 996/15000 [4:35:50<58:36:44, 15.07s/it] 7%|▋ | 997/15000 [4:36:04<58:04:20, 14.93s/it] 7%|▋ | 998/15000 [4:36:19<57:38:43, 14.82s/it] 7%|▋ | 999/15000 [4:36:56<83:22:27, 21.44s/it] 7%|▋ | 1000/15000 [4:37:10<75:28:34, 19.41s/it] 7%|▋ | 1000/15000 [4:37:11<75:28:34, 19.41s/it] 7%|▋ | 1001/15000 [4:37:25<70:19:58, 18.09s/it] 7%|▋ | 1002/15000 [4:37:40<66:22:54, 17.07s/it] 7%|▋ :40<66:23:11, 17.07s/it] 7%|▋ | 1003/15000 [4:37:55<63:35:48, 16.36s/it] 7%|▋ | 1004/15000 [4:38:10<61:30:16, 15.82s/it] 7%|▋ | 1005/15000 [4:38:24<60:04:32, 15.45s/it] 7%|▋ | 1006/15000 [4:38:39<59:17:24, 15.25s/it] 7%|▋ | 1007/15000 [4:38:54<58:42:51, 15.11s/it] 7%|▋ | 1008/15000 [4:39:08<58:07:37, 14.96s/it] 7%|▋ | 1009/15000 [4:39:23<57:44:28, 14.86s/it] 7%|▋ | 1010/15000 [4:39:38<57:28:25, 14.79s/it] 7%|▋ | 1011/15000 [4:40:14<83:19:32, 21.44s/it] 7%|▋ | 1012/15000 [4:40:29<75:26:41, 19.42s/it] 7%|▋ | 1013/15000 [4:40:44<69:40:00, 17.93s/it] 7%|▋ | 1014/15000 [4:40:58<66:04:37, 17.01s/it] 7%|▋ | 1015/15000 [4:41:13<63:16:06, 16.29s/it] 7%|▋ | 1016/15000 [4:41:28<61:25:36, 15.81s/it] 7%|▋ | 1017/15000 [4:41:42<59:55:55, 15.43s/it] 7%|▋ | 1018/15000 [4:41:57<59:06:30, 15.22s/it] 7%|▋ | 1019/15000 [4:42:12
{'loss': 0.9178, 'learning_rate': 0.00019901676461321068, 'epoch': 0.21}
{'loss': 0.9178, 'learning_rate': 0.00019901676461321068, 'epoch': 0.21}
7<57:41:51, 14.93s/it] 7%|▋ | 1089/15000 [5:01:32<57:24:31, 14.86s/it] 7%|▋ | 1090/15000 [5:02:09<82:48:03, 21.43s/it] 7%|▋ | 1091/15000 [5:02:23<75:00:40, 19.41s/it] 7%|▋ | 1092/15000 [5:02:38<69:27:55, 17.98s/it] 7%|▋ | 1093/15000 [5:02:53<65:35:09, 16.98s/it] 7%|▋ | 1094/15000 [5:03:07<62:58:37, 16.30s/it] 7%|▋ | 1095/15000 [5:03:22<61:03:16, 15.81s/it] 7%|▋ | 1096/15000 [5:03:37<59:46:02, 15.47s/it] 7%|▋ | 1097/15000 [5:03:51<58:48:41, 15.23s/it] 7%|▋ | 1098/15000 [5:04:06<58:10:06, 15.06s/it] 7%|▋ | 1099/15000 [5:04:21<57:44:30, 14.95s/it] 7%|▋ | 1100/15000 [5:04:35<57:15:13, 14.83s/it] 7%|▋ | 1100/15000 [5:04:36<57:15:13, 14.83s/it] 7%|▋ | 1101/15000 [5:05:13<83:09:50, 21.54s/it] 7%|▋ | 1102/15000 [5:05:27<75:12:01, 19.48s/it] 7%|▋ | 1103/15000 [5:05:42<69:/it] 7%|▋ | 1088/15000 [5:01:17<57:39:20, 14.92s/it] 7%|▋ | 1089/15000 [5:01:32<57:18:10, 14.83s/it] 7%|▋ | 1090/15000 [5:02:09<82:51:03, 21.44s/it] 7%|▋ | 1091/15000 [5:02:23<74:59:07, 19.41s/it] 7%|▋ | 1092/15000 [5:02:38<69:27:36, 17.98s/it] 7%|▋ | 1093/15000 [5:02:53<65:35:26, 16.98s/it] 7%|▋ | 1094/15000 [5:03:07<63:00:23, 16.31s/it] 7%|▋ | 1095/15000 [5:03:22<61:03:12, 15.81s/it] 7%|▋ | 1096/15000 [5:03:37<59:46:06, 15.48s/it] 7%|▋ | 1097/15000 [5:03:52<58:58:39, 15.27s/it] 7%|▋ | 1098/15000 [5:04:06<58:11:07, 15.07s/it] 7%|▋ | 1099/15000 [5:04:21<57:42:40, 14.95s/it] 7%|▋ | 1100/15000 [5:04:35<57:19:27, 14.85s/it] 7%|▋ | 1100/15000 [5:04:36<57:19:27, 14.85s/it] 7%|▋ | 1101/15000 [5:05:13<83:07:04, 21.53s/it] 7%|▋ | 1102/15000 [5:05:27<75:08:55, 19.47s/it] /it] 7%|▋ | 1088/15000 [5:01:17<57:44:42, 14.94s/it] 7%|▋ | 1089/15000 [5:01:32<57:18:49, 14.83s/it] 7%|▋ | 1090/15000 [5:02:09<82:59:21, 21.48s/it] 7%|▋ | 1091/15000 [5:02:23<74:56:19, 19.40s/it] 7%|▋ | 1092/15000 [5:02:38<69:28:48, 17.98s/it] 7%|▋ | 1093/15000 [5:02:53<65:37:55, 16.99s/it] 7%|▋ | 1094/15000 [5:03:07<62:55:53, 16.29s/it] 7%|▋ | 1095/15000 [5:03:22<60:56:04, 15.78s/it] 7%|▋ | 1096/15000 [5:03:37<59:43:50, 15.47s/it] 7%|▋ | 1097/15000 [5:03:51<58:49:46, 15.23s/it] 7%|▋ | 1098/15000 [5:04:06<58:18:23, 15.10s/it] 7%|▋ | 1099/15000 [5:04:21<57:41:09, 14.94s/it] 7%|▋ | 1100/15000 [5:04:35<57:20:35, 14.85s/it] 7%|▋ | 1100/15000 [5:04:36<57:20:35, 14.85s/it] 7%|▋ | 1101/15000 [5:05:13<83:05:39, 21.52s/it] 7%|▋ | 1102/15000 [5:05:27<75:04:28, 19.45s/it] 7%|▋ | 1103/15000 [5:05:42<69:37:54, 18.04s/it] 7%|▋ | 1104/15000 [5:05:56<65:33:42, 16.98s/it] 7%|▋ | 1105/15000 [5:06:11<62:51:01, 16.28s/it] 7%|▋ | 1106/15000 [5:06:26<61:06:59, 15.84s/it] 7%|▋ | 1107/15000 [5:06:40<59:40:48, 15.46s/it] 7%|▋ | 1108/15000 [5:06:55<58:43:50, 15.22s/it] 7%|▋ | 1109/15000 [5:07:10<58:01:40, 15.04s/it] 7%|▋ | 1110/15000 [5:07:24<57:26:51, 14.89s/it] 7%|▋ | 1111/15000 [5:07:39<57:15:19, 14.84s/it] 7%|▋ | 1112/15000 [5:07:54<56:56:25, 14.76s/it] 7%|▋ | 1113/15000 [5:08:30<82:34:47, 21.41s/it] 7%|▋ | 1114/15000 [5:08:45<74:29:45, 19.31s/it] 7%|▋ | 1115/15000 [5:09:00<69:08:52, 17.93s/it] 7%|▋ | 1116/15000 [5:09:14<65:19:07, 16.94s/it] 7%|▋ | 1117/15000 [5:09:29<62:37:11, 16.24s/it] 7%|▋ | 1118/15000 [5:09:43<60:44:40, 15.75s/it] 7%|▋ | 1119/15000 [5:09:58<59:41:51, 15.48s/it] 7
{'loss': 0.9094, 'learning_rate': 0.00019869167087338907, 'epoch': 0.22}
{'loss': 0.9094, 'learning_rate': 0.00019869167087338907, 'epoch': 0.22}
188/15000 [5:29:06<58:13:48, 15.18s/it] 8%|▊ | 1189/15000 [5:29:21<57:41:59, 15.04s/it] 8%|▊ | 1190/15000 [5:29:35<57:10:33, 14.90s/it] 8%|▊ | 1191/15000 [5:29:50<56:52:40, 14.83s/it] 8%|▊ | 1192/15000 [5:30:26<81:35:54, 21.27s/it] 8%|▊ | 1193/15000 [5:30:41<73:56:24, 19.28s/it] 8%|▊ | 1194/15000 [5:30:55<68:28:32, 17.86s/it] 8%|▊ | 1195/15000 [5:31:10<64:47:16, 16.90s/it] 8%|▊ | 1196/15000 [5:31:25<62:18:33, 16.25s/it] 8%|▊ | 1197/15000 [5:31:39<60:22:17, 15.75s/it] 8%|▊ | 1198/15000 [5:31:54<59:05:27, 15.41s/it] 8%|▊ | 1199/15000 [5:32:08<58:05:15, 15.15s/it] 8%|▊ | 1200/15000 [5:32:23<57:35:46, 15.03s/it] 8%|▊ | 1200/15000 [5:32:23<57:35:46, 15.03s/it] 8%|▊ | 1201/15000 [5:32:38<57:14:48, 14.94s/it] 8%|▊ | 1202/15000 [5:32:52<56:49:42, 14.83s/it] 8%|▊ | 1203/1188/15000 [5:29:06<58:20:30, 15.21s/it] 8%|▊ | 1189/15000 [5:29:21<57:42:51, 15.04s/it] 8%|▊ | 1190/15000 [5:29:35<57:09:51, 14.90s/it] 8%|▊ | 1191/15000 [5:29:50<56:58:26, 14.85s/it] 8%|▊ | 1192/15000 [5:30:26<81:35:11, 21.27s/it] 8%|▊ | 1193/15000 [5:30:41<73:53:59, 19.27s/it] 8%|▊ | 1194/15000 [5:30:55<68:36:02, 17.89s/it] 8%|▊ | 1195/15000 [5:31:10<64:46:01, 16.89s/it] 8%|▊ | 1196/15000 [5:31:25<62:12:19, 16.22s/it] 8%|▊ | 1197/15000 [5:31:39<60:26:22, 15.76s/it] 8%|▊ | 1198/15000 [5:31:54<58:56:01, 15.37s/it] 8%|▊ | 1199/15000 [5:32:08<58:02:07, 15.14s/it] 8%|▊ | 1200/15000 [5:32:23<57:36:05, 15.03s/it] 8%|▊ | 1200/15000 [5:32:23<57:36:05, 15.03s/it] 8%|▊ | 1201/15000 [5:32:38<57:19:59, 14.96s/it] 8%|▊ | 1202/15000 [5:32:53<56:58:54, 14.87s/it] 8%|▊ | 1203/18%|▊ | 1189/15000 [5:29:20<57:42:39, 15.04s/it] 8%|▊ | 1190/15000 [5:29:35<57:08:24, 14.90s/it] 8%|▊ | 1191/15000 [5:29:50<56:51:36, 14.82s/it] 8%|▊ | 1192/15000 [5:30:26<81:30:54, 21.25s/it] 8%|▊ | 1193/15000 [5:30:41<73:53:53, 19.27s/it] 8%|▊ | 1194/15000 [5:30:55<68:37:05, 17.89s/it] 8%|▊ | 1195/15000 [5:31:10<64:47:16, 16.90s/it] 8%|▊ | 1196/15000 [5:31:25<62:18:50, 16.25s/it] 8%|▊ | 1197/15000 [5:31:39<60:21:29, 15.74s/it] 8%|▊ | 1198/15000 [5:31:54<59:00:43, 15.39s/it] 8%|▊ | 1199/15000 [5:32:08<58:16:22, 15.20s/it] 8%|▊ | 1200/15000 [5:32:23<57:35:38, 15.02s/it] 8%|▊ | 1200/15000 [5:32:23<57:35:38, 15.02s/it] 8%|▊ | 1201/15000 [5:32:38<57:11:22, 14.92s/it] 8%|▊ | 1202/15000 [5:32:52<56:54:32, 14.85s/it] 8%|▊ | 1203/15000 [5:33:07<56:37:28, 14.77s/it] 8%|<7C><>5000 [5:33:07<56:30:50, 14.75s/it] 8%|▊ | 1204/15000 [5:33:43<81:22:11, 21.23s/it] 8%|▊ | 1205/15000 [5:33:58<73:52:56, 19.28s/it] 8%|▊ | 1206/15000 [5:34:13<68:23:50, 17.85s/it] 8%|▊ | 1207/15000 [5:34:27<64:43:01, 16.89s/it] 8%|▊ | 1208/15000 [5:34:42<62:10:24, 16.23s/it] 8%|▊ | 1209/15000 [5:34:57<60:20:20, 15.75s/it] 8%|▊ | 1210/15000 [5:35:11<58:54:52, 15.38s/it] 8%|▊ | 1211/15000 [5:35:26<58:04:26, 15.16s/it] 8%|▊ | 1212/15000 [5:35:40<57:32:46, 15.03s/it] 8%|▊ | 1213/15000 [5:35:55<57:10:34, 14.93s/it] 8%|▊ | 1214/15000 [5:36:10<56:54:28, 14.86s/it] 8%|▊ | 1215/15000 [5:36:47<82:10:18, 21.46s/it] 8%|▊ | 1216/15000 [5:37:01<74:19:27, 19.41s/it] 8%|▊ | 1217/15000 [5:37:16<68:47:57, 17.97s/it] 8%|▊ | 1218/15000 [5:37:31<65:03:21, 16.99s/it] 8%|▊ | 1219/15000 [5:37:45<62:16:42, 16.27s/it] 8%|▊ | 1220/1500
{'loss': 0.894, 'learning_rate': 0.00019832056870627417, 'epoch': 0.24}
{'loss': 0.894, 'learning_rate': 0.00019832056870627417, 'epoch': 0.24}
37, 15.87s/it] 9%|▊ | 1289/15000 [5:57:06<59:08:52, 15.53s/it] 9%|▊ | 1290/15000 [5:57:21<58:17:20, 15.31s/it] 9%|▊ | 1291/15000 [5:57:35<57:36:11, 15.13s/it] 9%|▊ | 1292/15000 [5:57:50<57:12:57, 15.03s/it] 9%|▊ | 1293/15000 [5:58:05<56:49:30, 14.92s/it] 9%|▊ | 1294/15000 [5:58:42<81:53:18, 21.51s/it] 9%|▊ | 1295/15000 [5:58:56<74:01:30, 19.44s/it] 9%|▊ | 1296/15000 [5:59:11<68:33:39, 18.01s/it] 9%|▊ | 1297/15000 [5:59:26<64:43:23, 17.00s/it] 9%|▊ | 1298/15000 [5:59:40<62:02:31, 16.30s/it] 9%|▊ | 1299/15000 [5:59:55<60:05:00, 15.79s/it] 9%|▊ | 1300/15000 [6:00:10<58:49:08, 15.46s/it] 9%|▊ | 1300/15000 [6:00:10<58:49:08, 15.46s/it] 9%|▊ | 1301/15000 [6:00:25<58:13:35, 15.30s/it] 9%|▊ | 1302/15000 [6:00:39<57:37:51, 15.15s/it] 9%|▊ | 1303/15000 [6:00:54<57:05:03, 102, 15.88s/it] 9%|▊ | 1289/15000 [5:57:06<59:14:10, 15.55s/it] 9%|▊ | 1290/15000 [5:57:21<58:13:12, 15.29s/it] 9%|▊ | 1291/15000 [5:57:35<57:31:32, 15.11s/it] 9%|▊ | 1292/15000 [5:57:50<57:18:27, 15.05s/it] 9%|▊ | 1293/15000 [5:58:05<56:42:04, 14.89s/it] 9%|▊ | 1294/15000 [5:58:42<81:55:51, 21.52s/it] 9%|▊ | 1295/15000 [5:58:56<73:59:25, 19.44s/it] 9%|▊ | 1296/15000 [5:59:11<68:37:47, 18.03s/it] 9%|▊ | 1297/15000 [5:59:26<64:48:43, 17.03s/it] 9%|▊ | 1298/15000 [5:59:40<62:05:14, 16.31s/it] 9%|▊ | 1299/15000 [5:59:55<60:02:09, 15.77s/it] 9%|▊ | 1300/15000 [6:00:10<58:45:53, 15.44s/it] 9%|▊ | 1300/15000 [6:00:10<58:45:53, 15.44s/it] 9%|▊ | 1301/15000 [6:00:24<58:09:35, 15.28s/it] 9%|▊ | 1302/15000 [6:00:39<57:33:30, 15.13s/it] 9%|▊ | 1303/15000 [6:00:54<57:09:15, 100 [5:57:06<59:10:26, 15.54s/it] 9%|▊ | 1290/15000 [5:57:21<58:19:44, 15.32s/it] 9%|▊ | 1291/15000 [5:57:35<57:40:11, 15.14s/it] 9%|▊ | 1292/15000 [5:57:50<57:08:58, 15.01s/it] 9%|▊ | 1293/15000 [5:58:05<56:46:28, 14.91s/it] 9%|▊ | 1294/15000 [5:58:42<81:50:11, 21.50s/it] 9%|▊ | 1295/15000 [5:58:56<74:07:05, 19.47s/it] 9%|▊ | 1296/15000 [5:59:11<68:36:36, 18.02s/it] 9%|▊ | 1297/15000 [5:59:26<64:45:54, 17.01s/it] 9%|▊ | 1298/15000 [5:59:40<61:57:33, 16.28s/it] 9%|▊ | 1299/15000 [5:59:55<60:07:57, 15.80s/it] 9%|▊ | 1300/15000 [6:00:09<58:46:49, 15.45s/it] 9%|▊ | 1300/15000 [6:00:10<58:46:49, 15.45s/it] 9%|▊ | 1301/15000 [6:00:24<58:07:08, 15.27s/it] 9%|▊ | 1302/15000 [6:00:39<57:37:21, 15.14s/it] 9%|▊ | 1303/15000 [6:00:54<57:06:00, 15.01s/it] 9%|▊ | 1304/15000 [65.00s/it] 9%|▊ | 1304/15000 [6:01:09<56:37:56, 14.89s/it] 9%|▊ | 1305/15000 [6:01:23<56:22:22, 14.82s/it] 9%|▊ | 1306/15000 [6:02:01<82:25:13, 21.67s/it] 9%|▊ | 1307/15000 [6:02:16<74:33:07, 19.60s/it] 9%|▊ | 1308/15000 [6:02:30<68:48:08, 18.09s/it] 9%|▊ | 1309/15000 [6:02:45<64:52:22, 17.06s/it] 9%|▊ | 1310/15000 [6:03:00<62:19:51, 16.39s/it] 9%|▊ | 1311/15000 [6:03:14<60:17:05, 15.85s/it] 9%|▊ | 1312/15000 [6:03:29<59:08:20, 15.55s/it] 9%|▉ | 1313/15000 [6:03:44<58:11:50, 15.31s/it] 9%|▉ | 1314/15000 [6:03:59<57:25:40, 15.11s/it] 9%|▉ | 1315/15000 [6:04:13<56:44:59, 14.93s/it] 9%|▉ | 1316/15000 [6:04:28<56:28:10, 14.86s/it] 9%|▉ | 1317/15000 [6:05:05<81:35:47, 21.47s/it] 9%|▉ | 1318/15000 [6:05:19<73:46:39, 19.41s/it] 9%|▉ | 1319/15000 [6:05:34<68:19:46, 17.98s/it] 9%|▉ | 1320/15000 [6:05:49<64:30:07, 16.9
{'loss': 0.9133, 'learning_rate': 0.00019790363111356837, 'epoch': 0.26}
{'loss': 0.9133, 'learning_rate': 0.00019790363111356837, 'epoch': 0.26}
78s/it] 9%|▉ | 1390/15000 [6:25:05<58:15:40, 15.41s/it] 9%|▉ | 1391/15000 [6:25:20<57:28:35, 15.20s/it] 9%|▉ | 1392/15000 [6:25:34<56:51:13, 15.04s/it] 9%|▉ | 1393/15000 [6:25:49<56:26:39, 14.93s/it] 9%|▉ | 1394/15000 [6:26:04<56:08:58, 14.86s/it] 9%|▉ | 1395/15000 [6:26:19<55:55:39, 14.80s/it] 9%|▉ | 1396/15000 [6:26:55<80:24:59, 21.28s/it] 9%|▉ | 1397/15000 [6:27:10<72:50:03, 19.28s/it] 9%|▉ | 1398/15000 [6:27:24<67:37:12, 17.90s/it] 9%|▉ | 1399/15000 [6:27:39<64:00:19, 16.94s/it] 9%|▉ | 1400/15000 [6:27:54<61:25:51, 16.26s/it] 9%|▉ | 1400/15000 [6:27:54<61:25:51, 16.26s/it] 9%|▉ | 1401/15000 [6:28:08<59:49:47, 15.84s/it] 9%|▉ | 1402/15000 [6:28:23<58:27:36, 15.48s/it] 9%|▉ | 1403/15000 [6:28:38<57:39:41, 15.27s/it] 9%|▉ | 1404/15000 [6:28:52<56:54:11, 15.07s/i | 1389/15000 [6:24:51<59:34:14, 15.76s/it] 9%|▉ | 1390/15000 [6:25:05<58:17:17, 15.42s/it] 9%|▉ | 1391/15000 [6:25:20<57:20:45, 15.17s/it] 9%|▉ | 1392/15000 [6:25:35<56:58:24, 15.07s/it] 9%|▉ | 1393/15000 [6:25:49<56:22:42, 14.92s/it] 9%|▉ | 1394/15000 [6:26:04<56:12:28, 14.87s/it] 9%|▉ | 1395/15000 [6:26:19<55:53:40, 14.79s/it] 9%|▉ | 1396/15000 [6:26:55<80:28:05, 21.29s/it] 9%|▉ | 1397/15000 [6:27:10<72:50:26, 19.28s/it] 9%|▉ | 1398/15000 [6:27:24<67:38:41, 17.90s/it] 9%|▉ | 1399/15000 [6:27:39<64:02:06, 16.95s/it] 9%|▉ | 1400/15000 [6:27:54<61:29:07, 16.28s/it] 9%|▉ | 1400/15000 [6:27:54<61:29:07, 16.28s/it] 9%|▉ | 1401/15000 [6:28:09<59:48:57, 15.83s/it] 9%|▉ | 1402/15000 [6:28:23<58:28:04, 15.48s/it] 9%|▉ | 1403/15000 [6:28:38<57:33:20, 15.24s/it] 9%|▉ | 1389/15000 [6:24:51<59:31:26, 15.74s/it] 9%|▉ | 1390/15000 [6:25:05<58:18:20, 15.42s/it] 9%|▉ | 1391/15000 [6:25:20<57:21:44, 15.17s/it] 9%|▉ | 1392/15000 [6:25:34<56:50:22, 15.04s/it] 9%|▉ | 1393/15000 [6:25:49<56:29:55, 14.95s/it] 9%|▉ | 1394/15000 [6:26:04<56:14:19, 14.88s/it] 9%|▉ | 1395/15000 [6:26:18<55:50:59, 14.78s/it] 9%|▉ | 1396/15000 [6:26:55<80:30:24, 21.30s/it] 9%|▉ | 1397/15000 [6:27:10<72:50:01, 19.28s/it] 9%|▉ | 1398/15000 [6:27:24<67:43:35, 17.93s/it] 9%|▉ | 1399/15000 [6:27:39<63:54:30, 16.92s/it] 9%|▉ | 1400/15000 [6:27:54<61:23:18, 16.25s/it] 9%|▉ | 1400/15000 [6:27:54<61:23:18, 16.25s/it] 9%|▉ | 1401/15000 [6:28:09<59:51:20, 15.85s/it] 9%|▉ | 1402/15000 [6:28:23<58:30:20, 15.49s/it] 9%|▉ | 1403/15000 [6:28:38<57:36:43, 15.25s/it] 9%|▉ | 1404/15000 [6:28:53<57:01:47, 15.10s/it] 9%|▉ | 1405/15000 [6:29:07<56:23:53, 14.93s/it] 9%|▉ | 1406/15000 [6:29:22<56:10:02, 14.87s/it] 9%|▉ | 1407/15000 [6:29:59<81:13:20, 21.51s/it] 9%|▉ | 1408/15000 [6:30:14<73:28:44, 19.46s/it] 9%|▉ | 1409/15000 [6:30:28<67:57:43, 18.00s/it] 9%|▉ | 1410/15000 [6:30:43<64:10:46, 17.00s/it] 9%|▉ | 1411/15000 [6:30:57<61:25:24, 16.27s/it] 9%|▉ | 1412/15000 [6:31:12<59:45:31, 15.83s/it] 9%|▉ | 1413/15000 [6:31:27<58:24:27, 15.48s/it] 9%|▉ | 1414/15000 [6:31:42<57:30:07, 15.24s/it] 9%|▉ | 1415/15000 [6:31:56<56:59:58, 15.10s/it] 9%|▉ | 1416/15000 [6:32:11<56:20:52, 14.93s/it] 9%|▉ | 1417/15000 [6:32:26<56:11:43, 14.89s/it] 9%|▉ | 1418/15000 [6:33:02<80:44:47, 21.40s/it] 9%|▉ | 1419/15000 [6:33:17<73:06:19, 19.38s/it] 9%|▉ | 1420/15000 [6:33:32<67:47:19, 17.97s/it] 9%|▉ |
{'loss': 0.9243, 'learning_rate': 0.00019744105246469263, 'epoch': 0.28}
{'loss': 0.9243, 'learning_rate': 0.00019744105246469263, 'epoch': 0.28}
:35<60:54:49, 16.23s/it] 10%|▉ | 1490/15000 [6:52:49<59:15:09, 15.79s/it] 10%|▉ | 1491/15000 [6:53:04<57:55:28, 15.44s/it] 10%|▉ | 1492/15000 [6:53:19<57:07:03, 15.22s/it] 10%|▉ | 1493/15000 [6:53:33<56:19:20, 15.01s/it] 10%|▉ | 1494/15000 [6:53:48<55:59:21, 14.92s/it] 10%|▉ | 1495/15000 [6:54:02<55:32:17, 14.80s/it] 10%|▉ | 1496/15000 [6:54:39<80:02:36, 21.34s/it] 10%|▉ | 1497/15000 [6:54:54<72:27:28, 19.32s/it] 10%|▉ | 1498/15000 [6:55:08<67:11:47, 17.92s/it] 10%|▉ | 1499/15000 [6:55:23<63:31:21, 16.94s/it] 10%|█ | 1500/15000 [6:55:38<61:00:24, 16.27s/it] 10%|█ | 1500/15000 [6:55:38<61:00:24, 16.27s/it] 10%|█ | 1501/15000 [6:55:53<59:29:51, 15.87s/it] 10%|█ | 1502/15000 [6:56:07<58:05:30, 15.49s/it] 10%|█ | 1503/15000 [6:56:22<57:14:09, 15.27s/it] 10%|█ | 1504/15000 [6:56:37<5:35<61:00:19, 16.25s/it] 10%|▉ | 1490/15000 [6:52:49<59:12:37, 15.78s/it] 10%|▉ | 1491/15000 [6:53:04<58:00:59, 15.46s/it] 10%|▉ | 1492/15000 [6:53:19<57:04:15, 15.21s/it] 10%|▉ | 1493/15000 [6:53:33<56:23:43, 15.03s/it] 10%|▉ | 1494/15000 [6:53:48<55:56:05, 14.91s/it] 10%|▉ | 1495/15000 [6:54:03<55:38:04, 14.83s/it] 10%|▉ | 1496/15000 [6:54:39<79:52:36, 21.29s/it] 10%|▉ | 1497/15000 [6:54:54<72:30:28, 19.33s/it] 10%|▉ | 1498/15000 [6:55:08<67:14:38, 17.93s/it] 10%|▉ | 1499/15000 [6:55:23<63:30:08, 16.93s/it] 10%|█ | 1500/15000 [6:55:38<61:01:11, 16.27s/it] 10%|█ | 1500/15000 [6:55:38<61:01:11, 16.27s/it] 10%|█ | 1501/15000 [6:55:53<59:22:29, 15.83s/it] 10%|█ | 1502/15000 [6:56:07<58:05:20, 15.49s/it] 10%|█ | 1503/15000 [6:56:22<57:05:50, 15.23s/it] 10%|█ | 1504/15000 [6:56:37<5| 1490/15000 [6:52:49<59:14:44, 15.79s/it] 10%|▉ | 1491/15000 [6:53:04<57:58:19, 15.45s/it] 10%|▉ | 1492/15000 [6:53:19<57:02:10, 15.20s/it] 10%|▉ | 1493/15000 [6:53:33<56:23:11, 15.03s/it] 10%|▉ | 1494/15000 [6:53:48<55:49:22, 14.88s/it] 10%|▉ | 1495/15000 [6:54:02<55:33:32, 14.81s/it] 10%|▉ | 1496/15000 [6:54:39<80:00:25, 21.33s/it] 10%|▉ | 1497/15000 [6:54:54<72:30:44, 19.33s/it] 10%|▉ | 1498/15000 [6:55:08<67:10:28, 17.91s/it] 10%|▉ | 1499/15000 [6:55:23<63:34:10, 16.95s/it] 10%|█ | 1500/15000 [6:55:38<60:55:40, 16.25s/it] 10%|█ | 1500/15000 [6:55:38<60:55:40, 16.25s/it] 10%|█ | 1501/15000 [6:55:52<59:25:08, 15.85s/it] 10%|█ | 1502/15000 [6:56:07<58:07:46, 15.50s/it] 10%|█ | 1503/15000 [6:56:22<57:02:07, 15.21s/it] 10%|█ | 1504/15000 [6:56:36<56:23:51, 15.04s/it] 10%|█ | 1506:24:27, 15.05s/it] 10%|█ | 1505/15000 [6:56:51<55:51:03, 14.90s/it] 10%|█ | 1506/15000 [6:57:06<55:35:30, 14.83s/it] 10%|█ | 1507/15000 [6:57:20<55:18:03, 14.75s/it] 10%|█ | 1508/15000 [6:57:57<79:35:26, 21.24s/it] 10%|█ | 1509/15000 [6:58:11<72:05:09, 19.24s/it] 10%|█ | 1510/15000 [6:58:26<66:59:52, 17.88s/it] 10%|█ | 1511/15000 [6:58:40<63:09:25, 16.86s/it] 10%|█ | 1512/15000 [6:58:55<60:33:23, 16.16s/it] 10%|█ | 1513/15000 [6:59:10<58:53:32, 15.72s/it] 10%|█ | 1514/15000 [6:59:24<57:29:08, 15.35s/it] 10%|█ | 1515/15000 [6:59:39<56:50:30, 15.17s/it] 10%|█ | 1516/15000 [6:59:53<56:06:09, 14.98s/it] 10%|█ | 1517/15000 [7:00:08<55:45:53, 14.89s/it] 10%|█ | 1518/15000 [7:00:23<55:21:09, 14.78s/it] 10%|█ | 1519/15000 [7:00:59<79:42:59, 21.29s/it] 10%|█ | 1520/15000 [7:01:14<72:13:55, 19.29s/it] 10%|█ | 1521/15000 [7:01:28<66:5
{'loss': 0.9194, 'learning_rate': 0.00019693304840617457, 'epoch': 0.3}
{'loss': 0.9194, 'learning_rate': 0.00019693304840617457, 'epoch': 0.3}
11%|█ | 1590/15000 [7:20:33<60:34:32, 16.26s/it] 11%|█ | 1591/15000 [7:20:48<58:49:05, 15.79s/it] 11%|█ | 1592/15000 [7:21:02<57:26:15, 15.42s/it] 11%|█ | 1593/15000 [7:21:17<56:40:49, 15.22s/it] 11%|█ | 1594/15000 [7:21:32<56:06:33, 15.07s/it] 11%|█ | 1595/15000 [7:21:46<55:39:20, 14.95s/it] 11%|█ | 1596/15000 [7:22:01<55:24:02, 14.88s/it] 11%|█ | 1597/15000 [7:22:38<79:47:17, 21.43s/it] 11%|█ | 1598/15000 [7:22:52<72:06:50, 19.37s/it] 11%|█ | 1599/15000 [7:23:07<66:47:47, 17.94s/it] 11%|█ | 1600/15000 [7:23:22<63:11:05, 16.98s/it] 11%|█ | 1600/15000 [7:23:22<63:11:05, 16.98s/it] 11%|█ | 1601/15000 [7:23:36<60:37:20, 16.29s/it] 11%|█ | 1602/15000 [7:23:51<58:58:35, 15.85s/it] 11%|█ | 1603/15000 [7:24:06<57:26:30, 15.44s/it] 11%|█ | 1604/15000 [7:24:20<56:34:05, 15.20s/it] 11%|36:51, 16.27s/it] 11%|█ | 1591/15000 [7:20:47<58:43:54, 15.77s/it] 11%|█ | 1592/15000 [7:21:02<57:31:56, 15.45s/it] 11%|█ | 1593/15000 [7:21:17<56:42:38, 15.23s/it] 11%|█ | 1594/15000 [7:21:32<56:06:46, 15.07s/it] 11%|█ | 1595/15000 [7:21:46<55:37:58, 14.94s/it] 11%|█ | 1596/15000 [7:22:01<55:25:36, 14.89s/it] 11%|█ | 1597/15000 [7:22:37<79:39:52, 21.40s/it] 11%|█ | 1598/15000 [7:22:52<72:06:37, 19.37s/it] 11%|█ | 1599/15000 [7:23:07<66:53:37, 17.97s/it] 11%|█ | 1600/15000 [7:23:21<63:10:28, 16.97s/it] 11%|█ | 1600/15000 [7:23:22<63:10:28, 16.97s/it] 11%|█ | 1601/15000 [7:23:36<60:43:19, 16.31s/it] 11%|█ | 1602/15000 [7:23:51<58:51:24, 15.81s/it] 11%|█ | 1603/15000 [7:24:06<57:30:16, 15.45s/it] 11%|█ | 1604/15000 [7:24:20<56:33:09, 15.20s/it] 11%|█ | 1605/15000 [7:24:35<55:55:54 11%|█ | 1590/15000 [7:20:33<60:42:07, 16.30s/it] 11%|█ | 1591/15000 [7:20:48<58:48:45, 15.79s/it] 11%|█ | 1592/15000 [7:21:02<57:33:02, 15.45s/it] 11%|█ | 1593/15000 [7:21:17<56:42:04, 15.23s/it] 11%|█ | 1594/15000 [7:21:32<56:05:56, 15.06s/it] 11%|█ | 1595/15000 [7:21:46<55:43:38, 14.97s/it] 11%|█ | 1596/15000 [7:22:01<55:19:03, 14.86s/it] 11%|█ | 1597/15000 [7:22:38<79:44:07, 21.42s/it] 11%|█ | 1598/15000 [7:22:52<72:06:49, 19.37s/it] 11%|█ | 1599/15000 [7:23:07<66:49:42, 17.95s/it] 11%|█ | 1600/15000 [7:23:22<63:11:11, 16.98s/it] 11%|█ | 1600/15000 [7:23:22<63:11:11, 16.98s/it] 11%|█ | 1601/15000 [7:23:36<60:37:42, 16.29s/it] 11%|█ | 1602/15000 [7:23:51<58:52:56, 15.82s/it] 11%|█ | 1603/15000 [7:24:06<57:29:09, 15.45s/it] 11%|█ | 1604/15000 [7:24:20<56:28:51, 15.18s/it] 11%|█ | 1605/15000 [7:24:35<55:57:13, 15.04s/it] 11%|█ | 1606/15000 [7:24:49<55:28:45, 14.91s/it] 11%|█ | 1607/15000 [7:25:04<55:09:41, 14.83s/it] 11%|█ | 1608/15000 [7:25:41<79:21:33, 21.33s/it] 11%|█ | 1609/15000 [7:25:55<71:57:41, 19.35s/it] 11%|█ | 1610/15000 [7:26:10<66:46:11, 17.95s/it] 11%|█ | 1611/15000 [7:26:24<62:51:25, 16.90s/it] 11%|█ | 1612/15000 [7:26:39<60:26:40, 16.25s/it] 11%|█ | 1613/15000 [7:26:54<58:39:56, 15.78s/it] 11%|█ | 1614/15000 [7:27:09<57:24:52, 15.44s/it] 11%|█ | 1615/15000 [7:27:23<56:23:49, 15.17s/it] 11%|█ | 1616/15000 [7:27:38<55:39:19, 14.97s/it] 11%|█ | 1617/15000 [7:27:52<55:26:20, 14.91s/it] 11%|█ | 1618/15000 [7:28:07<55:00:19, 14.80s/it] 11%|█ | 1619/15000 [7:28:22<54:52:57, 14.77s/it] 11%|█ | 1620/15000 [7:28:58<78:55:44, 21.24s/it] 11%|█ | 1621/15000 [7:29:13<71:37:36, 19.27s/it] 11%|█
{'loss': 0.9122, 'learning_rate': 0.00019637985576111778, 'epoch': 0.32}
{'loss': 0.9122, 'learning_rate': 0.00019637985576111778, 'epoch': 0.32}
1690/15000 [7:48:18<62:44:08, 16.97s/it] 11%|█▏ | 1691/15000 [7:48:32<60:24:06, 16.34s/it] 11%|█▏ | 1692/15000 [7:48:47<58:32:59, 15.84s/it] 11%|█▏ | 1693/15000 [7:49:02<57:17:07, 15.50s/it] 11%|█▏ | 1694/15000 [7:49:16<56:23:32, 15.26s/it] 11%|█▏ | 1695/15000 [7:49:31<55:51:52, 15.12s/it] 11%|█▏ | 1696/15000 [7:49:46<55:28:35, 15.01s/it] 11%|█▏ | 1697/15000 [7:50:01<55:14:26, 14.95s/it] 11%|█▏ | 1698/15000 [7:50:37<78:55:16, 21.36s/it] 11%|█▏ | 1699/15000 [7:50:52<71:36:37, 19.38s/it] 11%|█▏ | 1700/15000 [7:51:06<66:15:05, 17.93s/it] 11%|█▏ | 1700/15000 [7:51:07<66:15:05, 17.93s/it] 11%|█▏ | 1701/15000 [7:51:22<63:06:09, 17.08s/it] 11%|█▏ | 1702/15000 [7:51:36<60:23:06, 16.35s/it] 11%|█▏ | 1703/15000 [7:51:51<58:47:42, 15.92s/it] 11%|█▏ | 1704/15000 [7:52:06<57:18:11, 15.521690/15000 [7:48:18<62:49:16, 16.99s/it] 11%|█▏ | 1691/15000 [7:48:32<60:13:11, 16.29s/it] 11%|█▏ | 1692/15000 [7:48:47<58:34:05, 15.84s/it] 11%|█▏ | 1693/15000 [7:49:02<57:12:04, 15.47s/it] 11%|█▏ | 1694/15000 [7:49:16<56:20:12, 15.24s/it] 11%|█▏ | 1695/15000 [7:49:31<55:55:09, 15.13s/it] 11%|█▏ | 1696/15000 [7:49:46<55:27:04, 15.00s/it] 11%|█▏ | 1697/15000 [7:50:01<55:16:07, 14.96s/it] 11%|█▏ | 1698/15000 [7:50:37<78:56:33, 21.36s/it] 11%|█▏ | 1699/15000 [7:50:52<71:39:08, 19.39s/it] 11%|█▏ | 1700/15000 [7:51:07<66:20:25, 17.96s/it] 11%|█▏ | 1700/15000 [7:51:07<66:20:25, 17.96s/it] 11%|█▏ | 1701/15000 [7:51:22<63:02:28, 17.07s/it] 11%|█▏ | 1702/15000 [7:51:36<60:30:10, 16.38s/it] 11%|█▏ | 1703/15000 [7:51:51<58:40:32, 15.89s/it] 11%|█▏ | 1704/15000 [7:52:06<57:22:36, 15.5411%|█▏ | 1691/15000 [7:48:32<60:16:33, 16.30s/it] 11%|█▏ | 1692/15000 [7:48:47<58:32:27, 15.84s/it] 11%|█▏ | 1693/15000 [7:49:02<57:13:19, 15.48s/it] 11%|█▏ | 1694/15000 [7:49:16<56:24:19, 15.26s/it] 11%|█▏ | 1695/15000 [7:49:31<55:54:10, 15.13s/it] 11%|█▏ | 1696/15000 [7:49:46<55:23:57, 14.99s/it] 11%|█▏ | 1697/15000 [7:50:01<55:13:01, 14.94s/it] 11%|█▏ | 1698/15000 [7:50:37<78:52:25, 21.35s/it] 11%|█▏ | 1699/15000 [7:50:52<71:34:00, 19.37s/it] 11%|█▏ | 1700/15000 [7:51:06<66:22:17, 17.97s/it] 11%|█▏ | 1700/15000 [7:51:07<66:22:17, 17.97s/it] 11%|█▏ | 1701/15000 [7:51:21<63:05:53, 17.08s/it] 11%|█▏ | 1702/15000 [7:51:36<60:33:12, 16.39s/it] 11%|█▏ | 1703/15000 [7:51:51<58:41:10, 15.89s/it] 11%|█▏ | 1704/15000 [7:52:06<57:21:28, 15.53s/it] 11%|█▏ | 1705/15000 [7:5s/it] 11%|█▏ | 1705/15000 [7:52:20<56:27:30, 15.29s/it] 11%|█▏ | 1706/15000 [7:52:35<55:47:37, 15.11s/it] 11%|█▏ | 1707/15000 [7:52:50<55:29:28, 15.03s/it] 11%|█▏ | 1708/15000 [7:53:05<55:05:53, 14.92s/it] 11%|█▏ | 1709/15000 [7:53:41<78:46:28, 21.34s/it] 11%|█▏ | 1710/15000 [7:53:56<71:19:13, 19.32s/it] 11%|█▏ | 1711/15000 [7:54:10<66:14:24, 17.94s/it] 11%|█▏ | 1712/15000 [7:54:25<62:37:21, 16.97s/it] 11%|█▏ | 1713/15000 [7:54:40<59:54:47, 16.23s/it] 11%|█▏ | 1714/15000 [7:54:54<58:18:03, 15.80s/it] 11%|█▏ | 1715/15000 [7:55:09<56:59:20, 15.44s/it] 11%|█▏ | 1716/15000 [7:55:24<56:10:51, 15.23s/it] 11%|█▏ | 1717/15000 [7:55:38<55:37:50, 15.08s/it] 11%|█▏ | 1718/15000 [7:55:53<55:20:24, 15.00s/it] 11%|█▏ | 1719/15000 [7:56:08<55:00:43, 14.91s/it] 11%|█▏ | 1720/15000 [7:56:44<78:55:43, 21.40s/it] 11%|█▏ | 1721
{'loss': 0.9072, 'learning_rate': 0.00019578173241879872, 'epoch': 0.34}
{'loss': 0.9072, 'learning_rate': 0.00019578173241879872, 'epoch': 0.34}
<EFBFBD> | 1788/15000 [8:15:32<70:33:54, 19.23s/it] 12%|█▏ | 1789/15000 [8:15:47<65:30:16, 17.85s/it] 12%|█▏ | 1790/15000 [8:16:02<62:00:50, 16.90s/it] 12%|█▏ | 1791/15000 [8:16:16<59:29:09, 16.21s/it] 12%|█▏ | 1792/15000 [8:16:31<57:49:51, 15.76s/it] 12%|█▏ | 1793/15000 [8:16:46<56:35:45, 15.43s/it] 12%|█▏ | 1794/15000 [8:17:00<55:40:19, 15.18s/it] 12%|█▏ | 1795/15000 [8:17:15<55:13:44, 15.06s/it] 12%|█▏ | 1796/15000 [8:17:30<54:45:25, 14.93s/it] 12%|█▏ | 1797/15000 [8:17:44<54:30:29, 14.86s/it] 12%|█▏ | 1798/15000 [8:17:59<54:23:31, 14.83s/it] 12%|█▏ | 1799/15000 [8:18:36<78:05:29, 21.30s/it] 12%|█▏ | 1800/15000 [8:18:50<70:43:59, 19.29s/it] 12%|█▏ | 1800/15000 [8:18:50<70:43:59, 19.29s/it] 12%|█▏ | 1801/15000 [8:19:05<65:50:31, 17.96s/it] 12%|█▏ | 1802/15000 [8:19:20<62:10 [8:15:18<77:52:46, 21.22s/it] 12%|█▏ | 1788/15000 [8:15:32<70:31:48, 19.22s/it] 12%|█▏ | 1789/15000 [8:15:47<65:26:42, 17.83s/it] 12%|█▏ | 1790/15000 [8:16:02<61:58:46, 16.89s/it] 12%|█▏ | 1791/15000 [8:16:16<59:35:19, 16.24s/it] 12%|█▏ | 1792/15000 [8:16:31<57:44:53, 15.74s/it] 12%|█▏ | 1793/15000 [8:16:46<56:40:36, 15.45s/it] 12%|█▏ | 1794/15000 [8:17:00<55:39:05, 15.17s/it] 12%|█▏ | 1795/15000 [8:17:15<55:11:00, 15.04s/it] 12%|█▏ | 1796/15000 [8:17:30<54:47:21, 14.94s/it] 12%|█▏ | 1797/15000 [8:17:44<54:28:52, 14.86s/it] 12%|█▏ | 1798/15000 [8:17:59<54:16:50, 14.80s/it] 12%|█▏ | 1799/15000 [8:18:36<78:05:38, 21.30s/it] 12%|█▏ | 1800/15000 [8:18:50<70:50:41, 19.32s/it] 12%|█▏ | 1800/15000 [8:18:50<70:50:41, 19.32s/it] 12%|█▏ | 1801/15000 [8:19:05<65:55:29, 17.98s/it] 120 [8:15:18<77:41:29, 21.17s/it] 12%|█▏ | 1788/15000 [8:15:32<70:30:03, 19.21s/it] 12%|█▏ | 1789/15000 [8:15:47<65:27:44, 17.84s/it] 12%|█▏ | 1790/15000 [8:16:02<61:58:57, 16.89s/it] 12%|█▏ | 1791/15000 [8:16:16<59:31:52, 16.22s/it] 12%|█▏ | 1792/15000 [8:16:31<57:51:57, 15.77s/it] 12%|█▏ | 1793/15000 [8:16:46<56:35:12, 15.42s/it] 12%|█▏ | 1794/15000 [8:17:00<55:41:56, 15.18s/it] 12%|█▏ | 1795/15000 [8:17:15<55:12:46, 15.05s/it] 12%|█▏ | 1796/15000 [8:17:30<54:44:33, 14.93s/it] 12%|█▏ | 1797/15000 [8:17:44<54:33:27, 14.88s/it] 12%|█▏ | 1798/15000 [8:17:59<54:14:41, 14.79s/it] 12%|█▏ | 1799/15000 [8:18:36<78:14:23, 21.34s/it] 12%|█▏ | 1800/15000 [8:18:50<70:43:28, 19.29s/it] 12%|█▏ | 1800/15000 [8:18:50<70:43:28, 19.29s/it] 12%|█▏ | 1801/15000 [8:19:05<65:59:29, 18.00s/it] 12%|█▏ | 1802/15000 [8:19:20<62:17:50, 16.99s/it] 12%|█▏ | 1803/15000 [8:19:35<59:50:55, 16.33s/it] 12%|█▏ | 1804/15000 [8:19:49<58:00:21, 15.82s/it] 12%|█▏ | 1805/15000 [8:20:04<56:46:38, 15.49s/it] 12%|█▏ | 1806/15000 [8:20:19<56:02:57, 15.29s/it] 12%|█▏ | 1807/15000 [8:20:33<55:17:20, 15.09s/it] 12%|█▏ | 1808/15000 [8:20:48<54:58:25, 15.00s/it] 12%|█▏ | 1809/15000 [8:21:03<54:32:17, 14.88s/it] 12%|█▏ | 1810/15000 [8:21:39<78:25:33, 21.41s/it] 12%|█▏ | 1811/15000 [8:21:54<71:14:12, 19.44s/it] 12%|█▏ | 1812/15000 [8:22:09<65:46:11, 17.95s/it] 12%|█▏ | 1813/15000 [8:22:24<62:17:26, 17.01s/it] 12%|█▏ | 1814/15000 [8:22:38<59:41:30, 16.30s/it] 12%|█▏ | 1815/15000 [8:22:53<57:57:45, 15.83s/it] 12%|█▏ | 1816/15000 [8:23:08<56:39:44, 15.47s/it] 12%|█▏ | 1817/15000 [8:23:22<55:43:24, 15.22s/it] 12%|█▏ | 1818/15000 [8
5<55:26:35, 15.22s/it] 13%|█▎ | 1885/15000 [8:42:10<54:55:53, 15.08s/it] 13%|█▎ | 1886/15000 [8:42:25<54:29:55, 14.96s/it] 13%|█▎ | 1887/15000 [8:42:39<54:06:47, 14.86s/it] 13%|█▎ | 1888/15000 [8:43:16<78:10:24, 21.46s/it] 13%|█▎ | 1889/15000 [8:43:31<70:43:17, 19.42s/it] 13%|█▎ | 1890/15000 [8:43:45<65:17:20, 17.93s/it] 13%|█▎ | 1891/15000 [8:44:00<61:52:14, 16.99s/it] 13%|█▎ | 1892/15000 [8:44:15<59:14:16, 16.27s/it] 13%|█▎ | 1893/15000 [8:44:30<57:31:52, 15.80s/it] 13%|█▎ | 1894/15000 [8:44:44<56:04:48, 15.40s/it] 13%|█▎ | 1895/15000 [8:44:59<55:20:20, 15.20s/it] 13%|█▎ | 1896/15000 [8:45:13<54:39:41, 15.02s/it] 13%|█▎ | 1897/15000 [8:45:28<54:19:12, 14.92s/it] 13%|█▎ | 1898/15000 [8:45:43<53:59:34, 14.84s/it] 13%|█▎ | 1899/15000 [8:46:19<77:35:58, 21.32s/it] 13%|█▎ | 1900/15000 [8:46:34<70:08:12, 19.27s/it] {'loss': 0.9041, 'learning_rate': 0.00019513895721444286, 'epoch': 0.36}
5<55:25:32, 15.21s/it] 13%|█▎ | 1885/15000 [8:42:10<54:56:04, 15.08s/it] 13%|█▎ | 1886/15000 [8:42:25<54:29:17, 14.96s/it] 13%|█▎ | 1887/15000 [8:42:39<54:00:24, 14.83s/it] 13%|█▎ | 1888/15000 [8:43:16<78:07:40, 21.45s/it] 13%|█▎ | 1889/15000 [8:43:31<70:42:59, 19.42s/it] 13%|█▎ | 1890/15000 [8:43:45<65:22:17, 17.95s/it] 13%|█▎ | 1891/15000 [8:44:00<61:47:25, 16.97s/it] 13%|█▎ | 1892/15000 [8:44:15<59:15:10, 16.27s/it] 13%|█▎ | 1893/15000 [8:44:29<57:27:50, 15.78s/it] 13%|█▎ | 1894/15000 [8:44:44<56:07:53, 15.42s/it] 13%|█▎ | 1895/15000 [8:44:59<55:16:41, 15.19s/it] 13%|█▎ | 1896/15000 [8:45:13<54:42:44, 15.03s/it] 13%|█▎ | 1897/15000 [8:45:28<54:16:44, 14.91s/it] 13%|█▎ | 1898/15000 [8:45:43<54:08:40, 14.88s/it] 13%|█▎ | 1899/15000 [8:46:19<77:30:40, 21.30s/it] 13%|█▎ | 1900/15000 [8:46:34<70:12:37, 19.29s/it] {'loss': 0.9041, 'learning_rate': 0.00019513895721444286, 'epoch': 0.36}
| 1885/15000 [8:42:10<54:50:13, 15.05s/it] 13%|█▎ | 1886/15000 [8:42:25<54:25:11, 14.94s/it] 13%|█▎ | 1887/15000 [8:42:39<54:01:03, 14.83s/it] 13%|█▎ | 1888/15000 [8:43:16<78:05:15, 21.44s/it] 13%|█▎ | 1889/15000 [8:43:31<70:45:09, 19.43s/it] 13%|█▎ | 1890/15000 [8:43:46<65:29:37, 17.98s/it] 13%|█▎ | 1891/15000 [8:44:00<61:49:50, 16.98s/it] 13%|█▎ | 1892/15000 [8:44:15<59:11:06, 16.25s/it] 13%|█▎ | 1893/15000 [8:44:29<57:21:53, 15.76s/it] 13%|█▎ | 1894/15000 [8:44:44<56:08:57, 15.42s/it] 13%|█▎ | 1895/15000 [8:44:59<55:17:49, 15.19s/it] 13%|█▎ | 1896/15000 [8:45:13<54:44:39, 15.04s/it] 13%|█▎ | 1897/15000 [8:45:28<54:21:49, 14.94s/it] 13%|█▎ | 1898/15000 [8:45:43<54:04:13, 14.86s/it] 13%|█▎ | 1899/15000 [8:46:19<77:29:51, 21.30s/it] 13%|█▎ | 1900/15000 [8:46:34<70:09:50, 19.28s/it] 13%|█▎ | 1900/15000 [8:46:34<70:12:37, 19.29s/it] 13%|█▎ | 1901/15000 [8:46:49<65:20:23, 17.96s/it] 13%|█▎ | 1902/15000 [8:47:03<61:35:53, 16.93s/it] 13%|█▎ | 1903/15000 [8:47:18<59:15:14, 16.29s/it] 13%|█▎ | 1904/15000 [8:47:32<57:26:36, 15.79s/it] 13%|█▎ | 1905/15000 [8:47:47<56:14:07, 15.46s/it] 13%|█▎ | 1906/15000 [8:48:02<55:21:48, 15.22s/it] 13%|█▎ | 1907/15000 [8:48:16<54:42:27, 15.04s/it] 13%|█▎ | 1908/15000 [8:48:31<54:20:12, 14.94s/it] 13%|█▎ | 1909/15000 [8:48:46<54:06:03, 14.88s/it] 13%|█▎ | 1910/15000 [8:49:01<53:53:15, 14.82s/it] 13%|█▎ | 1911/15000 [8:49:37<77:42:36, 21.37s/it] 13%|█▎ | 1912/15000 [8:49:52<70:16:57, 19.33s/it] 13%|█▎ | 1913/15000 [8:50:07<65:14:48, 17.95s/it] 13%|█▎ | 1914/15000 [8:50:21<61:40:25, 16.97s/it] 13%|█▎ | 1915/15000 [8:50:36<59: 13%|█▎ | 1900/15000 [8:46:34<70:08:12, 19.27s/it] 13%|█▎ | 1901/15000 [8:46:48<65:17:00, 17.94s/it] 13%|█▎ | 1902/15000 [8:47:03<61:47:50, 16.99s/it] 13%|█▎ | 1903/15000 [8:47:18<59:12:28, 16.27s/it] 13%|█▎ | 1904/15000 [8:47:32<57:20:06, 15.76s/it] 13%|█▎ | 1905/15000 [8:47:47<56:11:04, 15.45s/it] 13%|█▎ | 1906/15000 [8:48:02<55:16:34, 15.20s/it] 13%|█▎ | 1907/15000 [8:48:16<54:48:06, 15.07s/it] 13%|█▎ | 1908/15000 [8:48:31<54:23:33, 14.96s/it] 13%|█▎ | 1909/15000 [8:48:46<54:04:45, 14.87s/it] 13%|█▎ | 1910/15000 [8:49:01<53:53:40, 14.82s/it] 13%|█▎ | 1911/15000 [8:49:37<77:37:34, 21.35s/it] 13%|█▎ | 1912/15000 [8:49:52<70:25:37, 19.37s/it] 13%|█▎ | 1913/15000 [8:50:07<65:20:23, 17.97s/it] 13%|█▎ | 1914/15000 [8:50:21<61:47:23, 17.00s/it] 13%|█▎ | 1915/15000 [8:50:36<59: 13%|█▎ | 1900/15000 [8:46:34<70:09:50, 19.28s/it] 13%|█▎ | 1901/15000 [8:46:48<65:20:08, 17.96s/it] 13%|█▎ | 1902/15000 [8:47:03<61:44:59, 16.97s/it] 13%|█▎ | 1903/15000 [8:47:18<59:10:41, 16.27s/it] 13%|█▎ | 1904/15000 [8:47:32<57:28:44, 15.80s/it] 13%|█▎ | 1905/15000 [8:47:47<56:13:57, 15.46s/it] 13%|█▎ | 1906/15000 [8:48:02<55:17:05, 15.20s/it] 13%|█▎ | 1907/15000 [8:48:16<54:46:23, 15.06s/it] 13%|█▎ | 1908/15000 [8:48:31<54:20:40, 14.94s/it] 13%|█▎ | 1909/15000 [8:48:46<54:03:53, 14.87s/it] 13%|█▎ | 1910/15000 [8:49:01<53:54:41, 14.83s/it] 13%|█▎ | 1911/15000 [8:49:37<77:37:54, 21.35s/it] 13%|█▎ | 1912/15000 [8:49:52<70:23:47, 19.36s/it] 13%|█▎ | 1913/15000 [8:50:07<65:19:43, 17.97s/it] 13%|█▎ | 1914/15000 [8:50:21<61:43:07, 16.98s/it] 13%|█▎ | 1915/15000 [8:50:36<59:12:16, 16.29s/it] 13%|█▎ | 19
{'loss': 0.8979, 'learning_rate': 0.00019445182979923654, 'epoch': 0.37}
{'loss': 0.8979, 'learning_rate': 0.00019445182979923654, 'epoch': 0.37}
] 13%|█▎ | 1999/15000 [9:13:42<53:36:17, 14.84s/it] 13%|█▎ | 2000/15000 [9:14:18<77:09:57, 21.37s/it] 13%|█▎ | 2000/15000 [9:14:18<77:09:57, 21.37s/it]Saving model checkpoint to /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-2000
tokenizer config file saved in /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-2000/tokenizer_config.json
Special tokens file saved in /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-2000/special_tokens_map.json
| 1998/15000 [9:13:27<53:45:02, 14.88s/it] 13%|█▎ | 1999/15000 [9:13:42<53:30:22, 14.82s/it] 13%|█▎ | 2000/15000 [9:14:18<77:07:40, 21.36s/it] 13%|█▎ | 2000/15000 [9:14:18<77:07:40, 21.36s/it] 13%|█▎ | 2001/15000 [9:14:38<75:05:32, 20.80s/it] 13%|█▎ | 2002/15000 [9:14:52<68:33:07, 18.99s/it] 13%|█▎ | 2003/15000 [9:15:07<63:46:33, 17.67s/it] 13%|█▎ | 2004/15000 [9:15:22<60:37:55, 16.80s/it] 13%|█▎ | 2005/15000 [9:15:36<58:14:38, 16.14s/it] 13%|█▎ | 2006/15000 [9:15:51<56:39:52, 15.70s/it] 13%|█▎ | 2007/15000 [9:16:06<55:31:21, 15.38s/it] 13%|█▎ | 2008/15000 [9:16:20<54:50:06, 15.19s/it] 13%|█▎ | 2009/15000 [9:16:35<54:16:30, 15.04s/it] 13%|█▎ | 2010/15000 [9:16:50<53:43:32, 14.89s/it] 13%|█▎ | 2011/15000 [9:17:26<76:50:14, 21.30s/it] 13%|█▎ | 2012/15000 [9:17:41<69:43:37, 19 | 1998/15000 [9:13:27<53:50:24, 14.91s/it] 13%|█▎ | 1999/15000 [9:13:42<53:32:14, 14.82s/it] 13%|█▎ | 2000/15000 [9:14:18<76:59:36, 21.32s/it] 13%|█▎ | 2000/15000 [9:14:18<76:59:36, 21.32s/it] 13%|█▎ | 2001/15000 [9:14:38<75:10:06, 20.82s/it] 13%|█▎ | 2002/15000 [9:14:52<68:35:18, 19.00s/it] 13%|█▎ | 2003/15000 [9:15:07<63:45:43, 17.66s/it] 13%|█▎ | 2004/15000 [9:15:22<60:35:09, 16.78s/it] 13%|█▎ | 2005/15000 [9:15:36<58:10:45, 16.12s/it] 13%|█▎ | 2006/15000 [9:15:51<56:41:52, 15.71s/it] 13%|█▎ | 2007/15000 [9:16:06<55:26:01, 15.36s/it] 13%|█▎ | 2008/15000 [9:16:20<54:50:36, 15.20s/it] 13%|█▎ | 2009/15000 [9:16:35<54:12:53, 15.02s/it] 13%|█▎ | 2010/15000 [9:16:50<53:55:16, 14.94s/it] 13%|█▎ | 2011/15000 [9:17:26<76:53:07, 21.31s/it] 13%|█▎ | 2012/15000 [9:17:41<69:40:43, 19 13%|█▎ | 2001/15000 [9:14:38<75:16:18, 20.85s/it] 13%|█▎ | 2002/15000 [9:14:52<68:33:14, 18.99s/it] 13%|█▎ | 2003/15000 [9:15:07<63:49:09, 17.68s/it] 13%|█▎ | 2004/15000 [9:15:22<60:30:04, 16.76s/it] 13%|█▎ | 2005/15000 [9:15:36<58:10:50, 16.12s/it] 13%|█▎ | 2006/15000 [9:15:51<56:36:37, 15.68s/it] 13%|█▎ | 2007/15000 [9:16:06<55:37:18, 15.41s/it] 13%|█▎ | 2008/15000 [9:16:20<54:50:12, 15.19s/it] 13%|█▎ | 2009/15000 [9:16:35<54:15:35, 15.04s/it] 13%|█▎ | 2010/15000 [9:16:50<53:49:07, 14.92s/it] 13%|█▎ | 2011/15000 [9:17:26<76:54:10, 21.31s/it] 13%|█▎ | 2012/15000 [9:17:41<69:44:20, 19.33s/it] 13%|█▎ | 2013/15000 [9:17:55<64:35:42, 17.91s/it] 13%|█▎ | 2014/15000 [9:18:10<61:03:50, 16.93s/it] 13%|█▎ | 2015/15000 [9:18:24<58:29:12, 16.22s/it] 13%|█▎ | 2016/15000 [9:18:39<56:50:55, 15.76s/it] 13%|█▎ | 2017/15000.31s/it] 13%|█▎ | 2013/15000 [9:17:55<64:41:29, 17.93s/it] 13%|█▎ | 2014/15000 [9:18:10<61:07:54, 16.95s/it] 13%|█▎ | 2015/15000 [9:18:24<58:29:27, 16.22s/it] 13%|█▎ | 2016/15000 [9:18:39<56:43:19, 15.73s/it] 13%|█▎ | 2017/15000 [9:18:54<55:39:23, 15.43s/it] 13%|█▎ | 2018/15000 [9:19:08<54:46:52, 15.19s/it] 13%|█▎ | 2019/15000 [9:19:23<54:11:46, 15.03s/it] 13%|█▎ | 2020/15000 [9:19:38<53:46:45, 14.92s/it] 13%|█▎ | 2021/15000 [9:19:52<53:29:39, 14.84s/it] 13%|█▎ | 2022/15000 [9:20:07<53:13:12, 14.76s/it] 13%|█▎ | 2023/15000 [9:20:43<76:22:47, 21.19s/it] 13%|█▎ | 2024/15000 [9:20:58<69:15:29, 19.21s/it] 14%|█▎ | 2025/15000 [9:21:12<64:22:35, 17.86s/it] 14%|█▎ | 2026/15000 [9:21:27<60:43:08, 16.85s/it] 14%|█▎ | 2027/15000 [9:21:42<58:16:38, 16.17s/it] 14%|█▎ | 2028/15000 [9:21:56<56:43:42, 15.74s/it] 14%|█▎ | 2
{'loss': 0.8945, 'learning_rate': 0.00019372067050063438, 'epoch': 0.39}
{'loss': 0.8945, 'learning_rate': 0.00019372067050063438, 'epoch': 0.39}
5000 [9:40:30<56:28:13, 15.75s/it] 14%|█▍ | 2096/15000 [9:40:45<55:15:16, 15.42s/it] 14%|█▍ | 2097/15000 [9:41:00<54:20:30, 15.16s/it] 14%|█▍ | 2098/15000 [9:41:14<53:54:48, 15.04s/it] 14%|█▍ | 2099/15000 [9:41:29<53:30:30, 14.93s/it] 14%|█▍ | 2100/15000 [9:41:44<53:16:42, 14.87s/it] 14%|█▍ | 2100/15000 [9:41:44<53:16:42, 14.87s/it] 14%|█▍ | 2101/15000 [9:42:20<76:29:28, 21.35s/it] 14%|█▍ | 2102/15000 [9:42:35<69:09:03, 19.30s/it] 14%|█▍ | 2103/15000 [9:42:50<64:13:34, 17.93s/it] 14%|█▍ | 2104/15000 [9:43:04<60:51:24, 16.99s/it] 14%|█▍ | 2105/15000 [9:43:19<58:20:30, 16.29s/it] 14%|█▍ | 2106/15000 [9:43:34<56:34:25, 15.80s/it] 14%|█▍ | 2107/15000 [9:43:48<55:18:46, 15.44s/it] 14%|█▍ | 2108/15000 [9:44:03<54:24:37, 15.19s/it] 14%|█▍ | 2109/15000 [9:44:18<54:02:45, 15.09s/it] 5000 [9:40:30<56:26:10, 15.74s/it] 14%|█▍ | 2096/15000 [9:40:45<55:22:41, 15.45s/it] 14%|█▍ | 2097/15000 [9:41:00<54:21:09, 15.16s/it] 14%|█▍ | 2098/15000 [9:41:14<53:52:39, 15.03s/it] 14%|█▍ | 2099/15000 [9:41:29<53:34:44, 14.95s/it] 14%|█▍ | 2100/15000 [9:41:44<53:20:19, 14.89s/it] 14%|█▍ | 2100/15000 [9:41:44<53:20:19, 14.89s/it] 14%|█▍ | 2101/15000 [9:42:20<76:26:47, 21.34s/it] 14%|█▍ | 2102/15000 [9:42:35<69:15:18, 19.33s/it] 14%|█▍ | 2103/15000 [9:42:50<64:14:13, 17.93s/it] 14%|█▍ | 2104/15000 [9:43:04<60:50:34, 16.98s/it] 14%|█▍ | 2105/15000 [9:43:19<58:20:15, 16.29s/it] 14%|█▍ | 2106/15000 [9:43:34<56:35:13, 15.80s/it] 14%|█▍ | 2107/15000 [9:43:48<55:11:57, 15.41s/it] 14%|█▍ | 2108/15000 [9:44:03<54:29:03, 15.21s/it] 14%|█▍ | 2109/15000 [9:44:18<53:59:53, 15.08s/it] █▍ | 2100/15000 [9:41:44<53:13:41, 14.85s/it] 14%|█▍ | 2100/15000 [9:41:44<53:13:41, 14.85s/it] 14%|█▍ | 2101/15000 [9:42:20<76:27:22, 21.34s/it] 14%|█▍ | 2102/15000 [9:42:35<69:16:05, 19.33s/it] 14%|█▍ | 2103/15000 [9:42:50<64:19:12, 17.95s/it] 14%|█▍ | 2104/15000 [9:43:04<60:49:03, 16.98s/it] 14%|█▍ | 2105/15000 [9:43:19<58:11:43, 16.25s/it] 14%|█▍ | 2106/15000 [9:43:34<56:32:45, 15.79s/it] 14%|█▍ | 2107/15000 [9:43:48<55:18:43, 15.44s/it] 14%|█▍ | 2108/15000 [9:44:03<54:31:20, 15.23s/it] 14%|█▍ | 2109/15000 [9:44:18<53:57:10, 15.07s/it] 14%|█▍ | 2110/15000 [9:44:32<53:32:11, 14.95s/it] 14%|█▍ | 2111/15000 [9:44:47<53:19:21, 14.89s/it] 14%|█▍ | 2112/15000 [9:45:24<76:55:29, 21.49s/it] 14%|█▍ | 2113/15000 [9:45:38<69:30:15, 19.42s/it] 14%|█▍ | 2114/15000 [9:45:53 14%|█▍ | 2110/15000 [9:44:32<53:33:49, 14.96s/it] 14%|█▍ | 2111/15000 [9:44:47<53:13:28, 14.87s/it] 14%|█▍ | 2112/15000 [9:45:24<76:59:16, 21.51s/it] 14%|█▍ | 2113/15000 [9:45:39<69:31:10, 19.42s/it] 14%|█▍ | 2114/15000 [9:45:53<64:13:55, 17.94s/it] 14%|█▍ | 2115/15000 [9:46:08<60:48:31, 16.99s/it] 14%|█▍ | 2116/15000 [9:46:23<58:24:23, 16.32s/it] 14%|█▍ | 2117/15000 [9:46:37<56:41:32, 15.84s/it] 14%|█▍ | 2118/15000 [9:46:52<55:24:47, 15.49s/it] 14%|█▍ | 2119/15000 [9:47:07<54:30:41, 15.23s/it] 14%|█▍ | 2120/15000 [9:47:21<53:54:29, 15.07s/it] 14%|█▍ | 2121/15000 [9:47:36<53:32:33, 14.97s/it] 14%|█▍ | 2122/15000 [9:47:51<53:18:58, 14.90s/it] 14%|█▍ | 2123/15000 [9:48:28<77:01:49, 21.54s/it] 14%|█▍ | 2124/15000 [9:48:42<69:34:29, 19.45s/it] 14%|█▍ | 2125/15000 [9:48:57<64:26:18, 18.02s/it] 14%|█▍ | 2126/15000
{'loss': 0.8946, 'learning_rate': 0.00019294582017302797, 'epoch': 0.41}
{'loss': 0.8946, 'learning_rate': 0.00019294582017302797, 'epoch': 0.41}
<EFBFBD> | 2192/15000 [10:07:28<63:29:52, 17.85s/it] 15%|█▍ | 2193/15000 [10:07:43<60:07:19, 16.90s/it] 15%|█▍ | 2194/15000 [10:07:58<57:38:09, 16.20s/it] 15%|█▍ | 2195/15000 [10:08:12<55:53:52, 15.72s/it] 15%|█▍ | 2196/15000 [10:08:27<54:44:10, 15.39s/it] 15%|█▍ | 2197/15000 [10:08:42<54:03:37, 15.20s/it] 15%|█▍ | 2198/15000 [10:08:56<53:25:41, 15.02s/it] 15%|█▍ | 2199/15000 [10:09:11<52:52:44, 14.87s/it] 15%|█▍ | 2200/15000 [10:09:25<52:42:10, 14.82s/it] 15%|█▍ | 2200/15000 [10:09:26<52:42:10, 14.82s/it] 15%|█▍ | 2201/15000 [10:09:40<52:50:18, 14.86s/it] 15%|█▍ | 2202/15000 [10:10:17<75:56:11, 21.36s/it] 15%|█▍ | 2203/15000 [10:10:32<68:49:37, 19.36s/it] 15%|█▍ | 2204/15000 [10:10:46<63:47:58, 17.95s/it] 15%|█▍ | 2205/15000 [10:11:01<60:06:43, 16.91s/it] 15%|█▍ | 2206/150<35> | 2192/15000 [10:07:28<63:31:30, 17.86s/it] 15%|█▍ | 2193/15000 [10:07:43<60:01:10, 16.87s/it] 15%|█▍ | 2194/15000 [10:07:58<57:42:58, 16.23s/it] 15%|█▍ | 2195/15000 [10:08:12<55:58:40, 15.74s/it] 15%|█▍ | 2196/15000 [10:08:27<54:47:57, 15.41s/it] 15%|█▍ | 2197/15000 [10:08:42<54:03:06, 15.20s/it] 15%|█▍ | 2198/15000 [10:08:56<53:22:34, 15.01s/it] 15%|█▍ | 2199/15000 [10:09:11<52:54:10, 14.88s/it] 15%|█▍ | 2200/15000 [10:09:25<52:34:54, 14.79s/it] 15%|█▍ | 2200/15000 [10:09:26<52:34:54, 14.79s/it] 15%|█▍ | 2201/15000 [10:09:40<52:43:12, 14.83s/it] 15%|█▍ | 2202/15000 [10:10:17<75:56:29, 21.36s/it] 15%|█▍ | 2203/15000 [10:10:32<68:48:17, 19.36s/it] 15%|█▍ | 2204/15000 [10:10:46<63:45:29, 17.94s/it] 15%|█▍ | 2205/15000 [10:11:01<60:14:42, 16.95s/it] 15%|█▍ | 2206/1504:22, 15.39s/it] 15%|█▍ | 2197/15000 [10:08:41<53:59:23, 15.18s/it] 15%|█▍ | 2198/15000 [10:08:56<53:22:39, 15.01s/it] 15%|█▍ | 2199/15000 [10:09:11<52:57:29, 14.89s/it] 15%|█▍ | 2200/15000 [10:09:25<52:37:40, 14.80s/it] 15%|█▍ | 2200/15000 [10:09:26<52:37:40, 14.80s/it] 15%|█▍ | 2201/15000 [10:09:40<52:46:03, 14.84s/it] 15%|█▍ | 2202/15000 [10:10:17<76:01:35, 21.39s/it] 15%|█▍ | 2203/15000 [10:10:32<68:49:37, 19.36s/it] 15%|█▍ | 2204/15000 [10:10:46<63:44:08, 17.93s/it] 15%|█▍ | 2205/15000 [10:11:01<60:13:15, 16.94s/it] 15%|█▍ | 2206/15000 [10:11:15<57:46:44, 16.26s/it] 15%|█▍ | 2207/15000 [10:11:30<56:07:37, 15.79s/it] 15%|█▍ | 2208/15000 [10:11:45<55:00:25, 15.48s/it] 15%|█▍ | 2209/15000 [10:12:00<54:08:53, 15.24s/it] 15%|█▍ | 2210/15000 [10:12:14<53:30:28, 15.06s/it] 100 [10:11:16<57:46:48, 16.26s/it] 15%|█▍ | 2207/15000 [10:11:30<56:05:08, 15.78s/it] 15%|█▍ | 2208/15000 [10:11:45<55:02:50, 15.49s/it] 15%|█▍ | 2209/15000 [10:12:00<54:15:58, 15.27s/it] 15%|█▍ | 2210/15000 [10:12:14<53:30:18, 15.06s/it] 15%|█▍ | 2211/15000 [10:12:29<53:11:47, 14.97s/it] 15%|█▍ | 2212/15000 [10:12:44<52:51:50, 14.88s/it] 15%|█▍ | 2213/15000 [10:13:21<76:15:41, 21.47s/it] 15%|█▍ | 2214/15000 [10:13:35<68:59:05, 19.42s/it] 15%|█▍ | 2215/15000 [10:13:50<63:49:13, 17.97s/it] 15%|█▍ | 2216/15000 [10:14:05<60:24:51, 17.01s/it] 15%|█▍ | 2217/15000 [10:14:19<57:54:54, 16.31s/it] 15%|█▍ | 2218/15000 [10:14:34<56:03:12, 15.79s/it] 15%|█▍ | 2219/15000 [10:14:49<54:52:34, 15.46s/it] 15%|█▍ | 2220/15000 [10:15:03<54:04:35, 15.23s/it] 15%|█▍ | 2221/15000 [10:15:18<53:23:58, 15.04s/it] 15%|█▍ | 2222/15000 [10:15:33<53
{'loss': 0.8888, 'learning_rate': 0.0001921276400388451, 'epoch': 0.43}
{'loss': 0.8888, 'learning_rate': 0.0001921276400388451, 'epoch': 0.43}
9:26, 15.24s/it] 15%|█▌ | 2288/15000 [10:33:53<53:16:04, 15.09s/it] 15%|█▌ | 2289/15000 [10:34:08<52:45:30, 14.94s/it] 15%|█▌ | 2290/15000 [10:34:22<52:26:23, 14.85s/it] 15%|█▌ | 2291/15000 [10:34:59<75:26:36, 21.37s/it] 15%|█▌ | 2292/15000 [10:35:14<68:22:09, 19.37s/it] 15%|█▌ | 2293/15000 [10:35:28<63:25:58, 17.97s/it] 15%|█▌ | 2294/15000 [10:35:43<59:55:35, 16.98s/it] 15%|█▌ | 2295/15000 [10:35:58<57:27:03, 16.28s/it] 15%|█▌ | 2296/15000 [10:36:12<55:46:31, 15.81s/it] 15%|█▌ | 2297/15000 [10:36:27<54:35:07, 15.47s/it] 15%|█▌ | 2298/15000 [10:36:42<53:45:47, 15.24s/it] 15%|█▌ | 2299/15000 [10:36:56<53:01:58, 15.03s/it] 15%|█▌ | 2300/15000 [10:37:11<52:41:24, 14.94s/it] 15%|█▌ | 2300/15000 [10:37:11<52:41:24, 14.94s/it] 15%|█▌ | 2301/15000 [10:37:26<52:37:16, 14.92s/it] 12:28, 15.26s/it] 15%|█▌ | 2288/15000 [10:33:53<53:13:33, 15.07s/it] 15%|█▌ | 2289/15000 [10:34:08<52:47:09, 14.95s/it] 15%|█▌ | 2290/15000 [10:34:22<52:25:09, 14.85s/it] 15%|█▌ | 2291/15000 [10:34:59<75:32:41, 21.40s/it] 15%|█▌ | 2292/15000 [10:35:14<68:24:56, 19.38s/it] 15%|█▌ | 2293/15000 [10:35:28<63:24:49, 17.97s/it] 15%|█▌ | 2294/15000 [10:35:43<60:00:17, 17.00s/it] 15%|█▌ | 2295/15000 [10:35:57<57:23:32, 16.26s/it] 15%|█▌ | 2296/15000 [10:36:12<55:43:14, 15.79s/it] 15%|█▌ | 2297/15000 [10:36:27<54:33:01, 15.46s/it] 15%|█▌ | 2298/15000 [10:36:41<53:38:37, 15.20s/it] 15%|█▌ | 2299/15000 [10:36:56<53:01:40, 15.03s/it] 15%|█▌ | 2300/15000 [10:37:11<52:42:41, 14.94s/it] 15%|█▌ | 2300/15000 [10:37:11<52:42:41, 14.94s/it] 15%|█▌ | 2301/15000 [10:37:26<52:36:05, 14.91s/it] 1| 2292/15000 [10:35:13<68:23:10, 19.37s/it] 15%|█▌ | 2293/15000 [10:35:28<63:24:16, 17.96s/it] 15%|█▌ | 2294/15000 [10:35:43<60:00:33, 17.00s/it] 15%|█▌ | 2295/15000 [10:35:57<57:26:48, 16.28s/it] 15%|█▌ | 2296/15000 [10:36:12<55:44:35, 15.80s/it] 15%|█▌ | 2297/15000 [10:36:27<54:34:26, 15.47s/it] 15%|█▌ | 2298/15000 [10:36:41<53:39:33, 15.21s/it] 15%|█▌ | 2299/15000 [10:36:56<53:05:26, 15.05s/it] 15%|█▌ | 2300/15000 [10:37:11<52:36:29, 14.91s/it] 15%|█▌ | 2300/15000 [10:37:11<52:36:29, 14.91s/it] 15%|█▌ | 2301/15000 [10:37:26<52:29:56, 14.88s/it] 15%|█▌ | 2302/15000 [10:38:02<75:35:59, 21.43s/it] 15%|█▌ | 2303/15000 [10:38:17<68:29:47, 19.42s/it] 15%|█▌ | 2304/15000 [10:38:32<63:28:20, 18.00s/it] 15%|█▌ | 2305/15000 [10:38:46<59:49:18, 16.96s/it] 15%|█▌ | 2306/15000 [10:395%|█▌ | 2302/15000 [10:38:02<75:30:44, 21.41s/it] 15%|█▌ | 2303/15000 [10:38:17<68:26:23, 19.40s/it] 15%|█▌ | 2304/15000 [10:38:32<63:26:55, 17.99s/it] 15%|█▌ | 2305/15000 [10:38:46<59:57:03, 17.00s/it] 15%|█▌ | 2306/15000 [10:39:01<57:21:50, 16.27s/it] 15%|█▌ | 2307/15000 [10:39:16<55:43:12, 15.80s/it] 15%|█▌ | 2308/15000 [10:39:30<54:25:25, 15.44s/it] 15%|█▌ | 2309/15000 [10:39:45<53:38:45, 15.22s/it] 15%|█▌ | 2310/15000 [10:39:59<52:57:16, 15.02s/it] 15%|█▌ | 2311/15000 [10:40:14<52:31:31, 14.90s/it] 15%|█▌ | 2312/15000 [10:40:29<52:22:35, 14.86s/it] 15%|█▌ | 2313/15000 [10:40:44<52:10:58, 14.81s/it] 15%|█▌ | 2314/15000 [10:41:20<74:58:10, 21.27s/it] 15%|█▌ | 2315/15000 [10:41:35<67:59:24, 19.30s/it] 15%|█▌ | 2316/15000 [10:41:49<63:05:55, 17.91s/it] 15%|█▌ | 2317/15000 [10:42:04<59:30:37, 16.89s/it] 15%|█▌
{'loss': 0.8878, 'learning_rate': 0.00019126651152015403, 'epoch': 0.45}
{'loss': 0.8878, 'learning_rate': 0.00019126651152015403, 'epoch': 0.45}
48s/it] 16%|█▌ | 2388/15000 [11:01:39<53:29:59, 15.27s/it] 16%|█▌ | 2389/15000 [11:01:53<52:46:41, 15.07s/it] 16%|█▌ | 2390/15000 [11:02:08<52:23:51, 14.96s/it] 16%|█▌ | 2391/15000 [11:02:22<52:00:34, 14.85s/it] 16%|█▌ | 2392/15000 [11:02:59<74:46:07, 21.35s/it] 16%|█▌ | 2393/15000 [11:03:14<67:42:17, 19.33s/it] 16%|█▌ | 2394/15000 [11:03:28<62:46:52, 17.93s/it] 16%|█▌ | 2395/15000 [11:03:43<59:17:25, 16.93s/it] 16%|█▌ | 2396/15000 [11:03:58<56:59:42, 16.28s/it] 16%|█▌ | 2397/15000 [11:04:12<55:17:49, 15.80s/it] 16%|█▌ | 2398/15000 [11:04:27<54:10:23, 15.48s/it] 16%|█▌ | 2399/15000 [11:04:41<53:10:19, 15.19s/it] 16%|█▌ | 2400/15000 [11:04:56<52:32:21, 15.01s/it] 16%|█▌ | 2400/15000 [11:04:56<52:32:21, 15.01s/it] 16%|█▌ | 2401/15000 [11:05:11<52:32:27, 15.01s/it] 16%|█▌:04:42<53:11:26, 15.20s/it] 16%|█▌ | 2400/15000 [11:04:56<52:35:51, 15.03s/it] 16%|█▌ | 2400/15000 [11:04:56<52:35:51, 15.03s/it] 16%|█▌ | 2401/15000 [11:05:11<52:31:01, 15.01s/it] 16%|█▌ | 2402/15000 [11:05:26<52:12:17, 14.92s/it] 16%|█▌ | 2403/15000 [11:06:04<76:11:13, 21.77s/it] 16%|█▌ | 2404/15000 [11:06:18<68:43:20, 19.64s/it] 16%|█▌ | 2405/15000 [11:06:33<63:26:12, 18.13s/it] 16%|█▌ | 2406/15000 [11:06:48<59:50:53, 17.11s/it] 16%|█▌ | 2407/15000 [11:07:02<57:13:21, 16.36s/it] 16%|█▌ | 2408/15000 [11:07:17<55:27:42, 15.86s/it] 16%|█▌ | 2409/15000 [11:07:32<54:06:09, 15.47s/it] 16%|█▌ | 2410/15000 [11:07:46<53:18:00, 15.24s/it] 16%|█▌ | 2411/15000 [11:08:02<53:21:36, 15.26s/it] 16%|█▌ | 2412/15000 [11:08:16<52:37:07, 15.05s/it] 16%|█▌ | 2413/15000 [11:08:31<52:10:40, 14:04:42<53:10:13, 15.19s/it] 16%|█▌ | 2400/15000 [11:04:56<52:39:36, 15.05s/it] 16%|█▌ | 2400/15000 [11:04:56<52:39:36, 15.05s/it] 16%|█▌ | 2401/15000 [11:05:11<52:27:25, 14.99s/it] 16%|█▌ | 2402/15000 [11:05:26<52:13:15, 14.92s/it] 16%|█▌ | 2403/15000 [11:06:04<76:08:47, 21.76s/it] 16%|█▌ | 2404/15000 [11:06:18<68:45:54, 19.65s/it] 16%|█▌ | 2405/15000 [11:06:33<63:23:29, 18.12s/it] 16%|█▌ | 2406/15000 [11:06:48<59:48:28, 17.10s/it] 16%|█▌ | 2407/15000 [11:07:02<57:19:04, 16.39s/it] 16%|█▌ | 2408/15000 [11:07:17<55:31:58, 15.88s/it] 16%|█▌ | 2409/15000 [11:07:32<54:13:37, 15.50s/it] 16%|█▌ | 2410/15000 [11:07:46<53:16:58, 15.24s/it] 16%|█▌ | 2411/15000 [11:08:02<53:19:40, 15.25s/it] 16%|█▌ | 2412/15000 [11:08:16<52:34:21, 15.04s/it] 16%|█▌ | 2413/15000 [11:08:31<52:12:18, 14 | 2402/15000 [11:05:26<52:10:57, 14.91s/it] 16%|█▌ | 2403/15000 [11:06:04<76:09:57, 21.77s/it] 16%|█▌ | 2404/15000 [11:06:18<68:43:42, 19.64s/it] 16%|█▌ | 2405/15000 [11:06:33<63:29:10, 18.15s/it] 16%|█▌ | 2406/15000 [11:06:48<59:49:28, 17.10s/it] 16%|█▌ | 2407/15000 [11:07:02<57:20:50, 16.39s/it] 16%|█▌ | 2408/15000 [11:07:17<55:28:27, 15.86s/it] 16%|█▌ | 2409/15000 [11:07:32<54:11:49, 15.50s/it] 16%|█▌ | 2410/15000 [11:07:46<53:23:16, 15.27s/it] 16%|█▌ | 2411/15000 [11:08:01<53:17:16, 15.24s/it] 16%|█▌ | 2412/15000 [11:08:16<52:36:34, 15.05s/it] 16%|█▌ | 2413/15000 [11:08:31<52:14:39, 14.94s/it] 16%|█▌ | 2414/15000 [11:09:07<74:27:26, 21.30s/it] 16%|█▌ | 2415/15000 [11:09:22<67:29:21, 19.31s/it] 16%|█▌ | 2416/15000 [11:09:36<62:41:32, 17.93s/it] 16%|█▌ | 2417/15000 [11:09:51<59:10:55, 16.93s/it] 16%|█▌ | 2418/
{'loss': 0.8819, 'learning_rate': 0.00019036283606085053, 'epoch': 0.47}
{'loss': 0.8819, 'learning_rate': 0.00019036283606085053, 'epoch': 0.47}
▋ | 2495/15000 [11:31:27<62:13:52, 17.92s/it] 17%|█▋ | 2496/15000 [11:31:42<58:55:16, 16.96s/it] 17%|█▋ | 2497/15000 [11:31:57<56:30:15, 16.27s/it] 17%|█▋ | 2498/15000 [11:32:12<54:56:06, 15.82s/it] 17%|█▋ | 2499/15000 [11:32:26<53:38:43, 15.45s/it] 17%|█▋ | 2500/15000 [11:32:41<52:51:44, 15.22s/it] 17%|█▋ | 2500/15000 [11:32:41<52:51:44, 15.22s/it] 17%|█▋ | 2501/15000 [11:32:56<52:29:11, 15.12s/it] 17%|█▋ | 2502/15000 [11:33:11<52:08:07, 15.02s/it] 17%|█▋ | 2503/15000 [11:33:25<51:42:44, 14.90s/it] 17%|█▋ | 2504/15000 [11:34:01<73:56:40, 21.30s/it] 17%|█▋ | 2505/15000 [11:34:16<67:00:41, 19.31s/it] 17%|█▋ | 2506/15000 [11:34:31<62:01:15, 17.87s/it] 17%|█▋ | 2507/15000 [11:34:45<58:53:11, 16.97s/it] 17%|█▋ | 2508/15000 [11:35:00<56:30:42, 16.29s/it] 17%|█▋ | 2509/1▋ | 2495/15000 [11:31:28<62:16:31, 17.93s/it] 17%|█▋ | 2496/15000 [11:31:42<58:58:03, 16.98s/it] 17%|█▋ | 2497/15000 [11:31:57<56:28:35, 16.26s/it] 17%|█▋ | 2498/15000 [11:32:12<54:53:46, 15.81s/it] 17%|█▋ | 2499/15000 [11:32:26<53:40:39, 15.46s/it] 17%|█▋ | 2500/15000 [11:32:41<52:49:13, 15.21s/it] 17%|█▋ | 2500/15000 [11:32:41<52:49:13, 15.21s/it] 17%|█▋ | 2501/15000 [11:32:56<52:24:03, 15.09s/it] 17%|█▋ | 2502/15000 [11:33:10<52:01:57, 14.99s/it] 17%|█▋ | 2503/15000 [11:33:25<51:48:01, 14.92s/it] 17%|█▋ | 2504/15000 [11:34:01<73:51:12, 21.28s/it] 17%|█▋ | 2505/15000 [11:34:16<67:04:42, 19.33s/it] 17%|█▋ | 2506/15000 [11:34:31<62:06:03, 17.89s/it] 17%|█▋ | 2507/15000 [11:34:45<58:53:12, 16.97s/it] 17%|█▋ | 2508/15000 [11:35:00<56:32:58, 16.30s/it] 17%|█▋ | 2509/1:43:59, 15.47s/it] 17%|█▋ | 2500/15000 [11:32:41<52:50:02, 15.22s/it] 17%|█▋ | 2500/15000 [11:32:41<52:50:02, 15.22s/it] 17%|█▋ | 2501/15000 [11:32:56<52:26:56, 15.11s/it] 17%|█▋ | 2502/15000 [11:33:10<52:02:02, 14.99s/it] 17%|█▋ | 2503/15000 [11:33:25<51:43:08, 14.90s/it] 17%|█▋ | 2504/15000 [11:34:01<73:55:40, 21.30s/it] 17%|█▋ | 2505/15000 [11:34:16<66:58:25, 19.30s/it] 17%|█▋ | 2506/15000 [11:34:31<62:12:12, 17.92s/it] 17%|█▋ | 2507/15000 [11:34:45<58:55:22, 16.98s/it] 17%|█▋ | 2508/15000 [11:35:00<56:32:15, 16.29s/it] 17%|█▋ | 2509/15000 [11:35:15<54:47:54, 15.79s/it] 17%|█▋ | 2510/15000 [11:35:29<53:38:03, 15.46s/it] 17%|█▋ | 2511/15000 [11:35:44<52:48:49, 15.22s/it] 17%|█▋ | 2512/15000 [11:35:59<52:17:47, 15.08s/it] 17%|█▋ | 2513/15000 [11:36:14<52:05:25, 15.02s/it] 5000 [11:35:15<54:51:23, 15.81s/it] 17%|█▋ | 2510/15000 [11:35:30<53:39:14, 15.46s/it] 17%|█▋ | 2511/15000 [11:35:44<52:46:52, 15.21s/it] 17%|█▋ | 2512/15000 [11:35:59<52:16:08, 15.07s/it] 17%|█▋ | 2513/15000 [11:36:14<51:59:31, 14.99s/it] 17%|█▋ | 2514/15000 [11:36:29<51:52:54, 14.96s/it] 17%|█▋ | 2515/15000 [11:37:05<73:57:53, 21.33s/it] 17%|█▋ | 2516/15000 [11:37:19<67:04:07, 19.34s/it] 17%|█▋ | 2517/15000 [11:37:34<62:12:03, 17.94s/it] 17%|█▋ | 2518/15000 [11:37:49<58:45:17, 16.95s/it] 17%|█▋ | 2519/15000 [11:38:03<56:23:27, 16.27s/it] 17%|█▋ | 2520/15000 [11:38:18<54:40:44, 15.77s/it] 17%|█▋ | 2521/15000 [11:38:33<53:34:34, 15.46s/it] 17%|█▋ | 2522/15000 [11:38:48<52:56:39, 15.27s/it] 17%|█▋ | 2523/15000 [11:39:02<52:15:58, 15.08s/it] 17%|█▋ | 2524/15000 [11:39:17<51:49:49, 14.96s/it] 17%|█▋ | 2525/15000 [11:39:32<
{'loss': 0.8812, 'learning_rate': 0.00018941703493951164, 'epoch': 0.49}
{'loss': 0.8812, 'learning_rate': 0.00018941703493951164, 'epoch': 0.49}
:57:46, 15.07s/it] 17%|█▋ | 2591/15000 [11:57:50<51:27:53, 14.93s/it] 17%|█▋ | 2592/15000 [11:58:05<51:13:14, 14.86s/it] 17%|█▋ | 2593/15000 [11:58:43<75:35:53, 21.94s/it] 17%|█▋ | 2594/15000 [11:58:58<68:05:34, 19.76s/it] 17%|█▋ | 2595/15000 [11:59:13<62:52:40, 18.25s/it] 17%|█▋ | 2596/15000 [11:59:27<59:09:39, 17.17s/it] 17%|█▋ | 2597/15000 [11:59:42<56:35:28, 16.43s/it] 17%|█▋ | 2598/15000 [11:59:57<54:42:51, 15.88s/it] 17%|█▋ | 2599/15000 [12:00:12<53:37:33, 15.57s/it] 17%|█▋ | 2600/15000 [12:00:26<52:41:19, 15.30s/it] 17%|█▋ | 2600/15000 [12:00:26<52:41:19, 15.30s/it] 17%|█▋ | 2601/15000 [12:00:41<52:11:52, 15.16s/it] 17%|█▋ | 2602/15000 [12:00:56<51:42:28, 15.01s/it] 17%|█▋ | 2603/15000 [12:01:10<51:23:08, 14.92s/it] 17%|█▋ | 2604/15000 [12:01:47<73:35:44, 21.37s/it] :47:50, 15.03s/it] 17%|█▋ | 2591/15000 [11:57:50<51:29:06, 14.94s/it] 17%|█▋ | 2592/15000 [11:58:05<51:10:58, 14.85s/it] 17%|█▋ | 2593/15000 [11:58:44<75:44:55, 21.98s/it] 17%|█▋ | 2594/15000 [11:58:58<67:58:02, 19.72s/it] 17%|█▋ | 2595/15000 [11:59:13<62:46:54, 18.22s/it] 17%|█▋ | 2596/15000 [11:59:27<59:05:36, 17.15s/it] 17%|█▋ | 2597/15000 [11:59:42<56:42:30, 16.46s/it] 17%|█▋ | 2598/15000 [11:59:57<54:51:10, 15.92s/it] 17%|█▋ | 2599/15000 [12:00:12<53:37:00, 15.56s/it] 17%|█▋ | 2600/15000 [12:00:26<52:39:44, 15.29s/it] 17%|█▋ | 2600/15000 [12:00:26<52:39:44, 15.29s/it] 17%|█▋ | 2601/15000 [12:00:41<52:15:04, 15.17s/it] 17%|█▋ | 2602/15000 [12:00:56<51:42:46, 15.02s/it] 17%|█▋ | 2603/15000 [12:01:10<51:17:45, 14.90s/it] 17%|█▋ | 2604/15000 [12:01:47<73:35:11, 21.37s/it] | 2595/15000 [11:59:13<62:46:26, 18.22s/it] 17%|█▋ | 2596/15000 [11:59:27<59:12:16, 17.18s/it] 17%|█▋ | 2597/15000 [11:59:42<56:36:34, 16.43s/it] 17%|█▋ | 2598/15000 [11:59:57<54:57:21, 15.95s/it] 17%|█▋ | 2599/15000 [12:00:11<53:35:36, 15.56s/it] 17%|█▋ | 2600/15000 [12:00:26<52:39:34, 15.29s/it] 17%|█▋ | 2600/15000 [12:00:26<52:39:34, 15.29s/it] 17%|█▋ | 2601/15000 [12:00:41<52:15:06, 15.17s/it] 17%|█▋ | 2602/15000 [12:00:56<51:44:31, 15.02s/it] 17%|█▋ | 2603/15000 [12:01:10<51:22:36, 14.92s/it] 17%|█▋ | 2604/15000 [12:01:47<73:29:31, 21.34s/it] 17%|█▋ | 2605/15000 [12:02:01<66:38:20, 19.35s/it] 17%|█▋ | 2606/15000 [12:02:16<61:49:52, 17.96s/it] 17%|█▋ | 2607/15000 [12:02:31<58:26:11, 16.98s/it] 17%|█▋ | 2608/15000 [12:02:45<56:03:14, 16.28s/it] 17%|█▋ | 2609/15000 [12: 17%|█▋ | 2605/15000 [12:02:02<66:40:18, 19.36s/it] 17%|█▋ | 2606/15000 [12:02:16<61:49:35, 17.96s/it] 17%|█▋ | 2607/15000 [12:02:31<58:25:22, 16.97s/it] 17%|█▋ | 2608/15000 [12:02:46<56:05:13, 16.29s/it] 17%|█▋ | 2609/15000 [12:03:00<54:23:33, 15.80s/it] 17%|█▋ | 2610/15000 [12:03:15<53:10:13, 15.45s/it] 17%|█▋ | 2611/15000 [12:03:30<52:26:29, 15.24s/it] 17%|█▋ | 2612/15000 [12:03:44<51:46:08, 15.04s/it] 17%|█▋ | 2613/15000 [12:03:59<51:20:38, 14.92s/it] 17%|█▋ | 2614/15000 [12:04:14<51:13:04, 14.89s/it] 17%|█▋ | 2615/15000 [12:04:28<51:06:58, 14.86s/it] 17%|█▋ | 2616/15000 [12:05:05<73:33:37, 21.38s/it] 17%|█▋ | 2617/15000 [12:05:20<66:28:50, 19.33s/it] 17%|█▋ | 2618/15000 [12:05:34<61:38:54, 17.92s/it] 17%|█▋ | 2619/15000 [12:05:49<58:18:46, 16.96s/it] 17%|█▋ | 2620/15000 [12:06:04<55:58:10, 16.28s/it] 17%|█▋
{'loss': 0.8796, 'learning_rate': 0.00018842954907300236, 'epoch': 0.51}
| 2686/15000 [12:24:24<57:50:59, 16.91s/it] 18%|█▊ | 2687/15000 [12:24:39<55:31:37, 16.23s/it] 18%|█▊ | 2688/15000 [12:24:54<53:57:31, 15.78s/it] 18%|█▊ | 2689/15000 [12:25:08<52:46:05, 15.43s/it] 18%|█▊ | 2690/15000 [12:25:23<52:04:38, 15.23s/it] 18%|█▊ | 2691/15000 [12:25:38<51:31:19, 15.07s/it] 18%|█▊ | 2692/15000 [12:25:52<50:56:17, 14.90s/it] 18%|█▊ | 2693/15000 [12:26:07<50:46:06, 14.85s/it] 18%|█▊ | 2694/15000 [12:26:43<72:50:29, 21.31s/it] 18%|█▊ | 2695/15000 [12:26:58<66:00:40, 19.31s/it] 18%|█▊ | 2696/15000 [12:27:13<61:11:15, 17.90s/it] 18%|█▊ | 2697/15000 [12:27:27<57:46:02, 16.90s/it] 18%|█▊ | 2698/15000 [12:27:42<55:35:31, 16.27s/it] 18%|█▊ | 2699/15000 [12:27:57<53:52:54, 15.77s/it] 18%|█▊ | 2700/15000 [12:28:11<52:49:47, 15.46s/it] 18%|█▊ | 2700/15000 [12:{'loss': 0.8796, 'learning_rate': 0.00018842954907300236, 'epoch': 0.51}
| 2686/15000 [12:24:24<57:53:20, 16.92s/it] 18%|█▊ | 2687/15000 [12:24:39<55:29:32, 16.22s/it] 18%|█▊ | 2688/15000 [12:24:54<53:56:20, 15.77s/it] 18%|█▊ | 2689/15000 [12:25:08<52:45:52, 15.43s/it] 18%|█▊ | 2690/15000 [12:25:23<52:01:51, 15.22s/it] 18%|█▊ | 2691/15000 [12:25:38<51:33:51, 15.08s/it] 18%|█▊ | 2692/15000 [12:25:52<50:57:08, 14.90s/it] 18%|█▊ | 2693/15000 [12:26:07<50:49:15, 14.87s/it] 18%|█▊ | 2694/15000 [12:26:43<72:48:41, 21.30s/it] 18%|█▊ | 2695/15000 [12:26:58<65:57:03, 19.29s/it] 18%|█▊ | 2696/15000 [12:27:13<61:05:55, 17.88s/it] 18%|█▊ | 2697/15000 [12:27:27<57:48:48, 16.92s/it] 18%|█▊ | 2698/15000 [12:27:42<55:35:12, 16.27s/it] 18%|█▊ | 2699/15000 [12:27:57<53:55:36, 15.78s/it] 18%|█▊ | 2700/15000 [12:28:11<52:49:00, 15.46s/it] 18%|█▊ | 2700/15000 [12:5.22s/it] 18%|█▊ | 2691/15000 [12:25:38<51:25:41, 15.04s/it] 18%|█▊ | 2692/15000 [12:25:52<51:01:41, 14.93s/it] 18%|█▊ | 2693/15000 [12:26:07<50:42:10, 14.83s/it] 18%|█▊ | 2694/15000 [12:26:43<72:49:53, 21.31s/it] 18%|█▊ | 2695/15000 [12:26:58<66:00:58, 19.31s/it] 18%|█▊ | 2696/15000 [12:27:12<61:08:26, 17.89s/it] 18%|█▊ | 2697/15000 [12:27:27<57:52:14, 16.93s/it] 18%|█▊ | 2698/15000 [12:27:42<55:34:34, 16.26s/it] 18%|█▊ | 2699/15000 [12:27:57<54:00:02, 15.80s/it] 18%|█▊ | 2700/15000 [12:28:11<52:48:32, 15.46s/it] 18%|█▊ | 2700/15000 [12:28:11<52:48:32, 15.46s/it] 18%|█▊ | 2701/15000 [12:28:26<52:06:11, 15.25s/it] 18%|█▊ | 2702/15000 [12:28:41<51:29:49, 15.07s/it] 18%|█▊ | 2703/15000 [12:28:55<51:00:15, 14.93s/it] 18%|█▊ | 2704/15000 [12:29:10<50:41:54, 14.84s/it] 18%|█<>28:11<52:49:00, 15.46s/it] 18%|█▊ | 2701/15000 [12:28:26<52:05:20, 15.25s/it] 18%|█▊ | 2702/15000 [12:28:41<51:28:53, 15.07s/it] 18%|█▊ | 2703/15000 [12:28:55<51:07:41, 14.97s/it] 18%|█▊ | 2704/15000 [12:29:10<50:35:39, 14.81s/it] 18%|█▊ | 2705/15000 [12:29:46<72:39:29, 21.27s/it] 18%|█▊ | 2706/15000 [12:30:01<65:51:09, 19.28s/it] 18%|█▊ | 2707/15000 [12:30:16<61:09:11, 17.91s/it] 18%|█▊ | 2708/15000 [12:30:30<57:43:32, 16.91s/it] 18%|█▊ | 2709/15000 [12:30:45<55:30:17, 16.26s/it] 18%|█▊ | 2710/15000 [12:30:59<53:47:31, 15.76s/it] 18%|█▊ | 2711/15000 [12:31:14<52:44:36, 15.45s/it] 18%|█▊ | 2712/15000 [12:31:29<51:52:54, 15.20s/it] 18%|█▊ | 2713/15000 [12:31:43<51:15:56, 15.02s/it] 18%|█▊ | 2714/15000 [12:31:58<50:54:19, 14.92s/it] 18%|█▊ | 2715/15000 [12:32:13<50:39:10, 14.84s/it] 18%|█▊ | 2716/15000 [12:32:49<72:49:36, 28:11<52:49:47, 15.46s/it] 18%|█▊ | 2701/15000 [12:28:26<52:02:40, 15.23s/it] 18%|█▊ | 2702/15000 [12:28:41<51:29:34, 15.07s/it] 18%|█▊ | 2703/15000 [12:28:55<51:09:32, 14.98s/it] 18%|█▊ | 2704/15000 [12:29:10<50:43:17, 14.85s/it] 18%|█▊ | 2705/15000 [12:29:46<72:40:36, 21.28s/it] 18%|█▊ | 2706/15000 [12:30:01<65:44:42, 19.25s/it] 18%|█▊ | 2707/15000 [12:30:16<61:08:08, 17.90s/it] 18%|█▊ | 2708/15000 [12:30:30<57:46:50, 16.92s/it] 18%|█▊ | 2709/15000 [12:30:45<55:26:50, 16.24s/it] 18%|█▊ | 2710/15000 [12:30:59<53:43:34, 15.74s/it] 18%|█▊ | 2711/15000 [12:31:14<52:44:19, 15.45s/it] 18%|█▊ | 2712/15000 [12:31:29<51:50:20, 15.19s/it] 18%|█▊ | 2713/15000 [12:31:43<51:14:47, 15.01s/it] 18%|█▊ | 2714/15000 [12:31:58<50:59:26, 14.94s/it] 18%|█▊ | 2715/15000 [12:32:13<50:35:17, 14.82s/it] 18%|█▊ | 2716/15000 [12:32:49<72:50:48,
{'loss': 0.8806, 'learning_rate': 0.0001874008388109276, 'epoch': 0.52}
{'loss': 0.8806, 'learning_rate': 0.0001874008388109276, 'epoch': 0.52}
15000 [12:52:08<60:59:57, 17.98s/it] 19%|█▊ | 2787/15000 [12:52:23<57:32:57, 16.96s/it] 19%|█▊ | 2788/15000 [12:52:38<55:08:06, 16.25s/it] 19%|█▊ | 2789/15000 [12:52:52<53:32:40, 15.79s/it] 19%|█▊ | 2790/15000 [12:53:07<52:23:29, 15.45s/it] 19%|█▊ | 2791/15000 [12:53:21<51:33:02, 15.20s/it] 19%|█▊ | 2792/15000 [12:53:36<50:56:52, 15.02s/it] 19%|█▊ | 2793/15000 [12:53:51<50:38:20, 14.93s/it] 19%|█▊ | 2794/15000 [12:54:05<50:17:29, 14.83s/it] 19%|█▊ | 2795/15000 [12:54:42<72:23:04, 21.35s/it] 19%|█▊ | 2796/15000 [12:54:57<65:35:25, 19.35s/it] 19%|█▊ | 2797/15000 [12:55:11<60:46:55, 17.93s/it] 19%|█▊ | 2798/15000 [12:55:26<57:25:57, 16.94s/it] 19%|█▊ | 2799/15000 [12:55:41<55:04:09, 16.25s/it] 19%|█▊ | 2800/15000 [12:55:55<53:31:27, 15.79s/it] 19%|█▊ | 2800/15000 [12:55:55<53:<3A><>▊ | 2798/15000 [12:55:26<57:24:17, 16.94s/it] 19%|█▊ | 2799/15000 [12:55:41<55:08:19, 16.27s/it] 19%|█▊ | 2800/15000 [12:55:55<53:24:46, 15.76s/it] 19%|█▊ | 2800/15000 [12:55:55<53:24:46, 15.76s/it] 19%|█▊ | 2801/15000 [12:56:10<52:32:01, 15.50s/it] 19%|█▊ | 2802/15000 [12:56:25<51:36:16, 15.23s/it] 19%|█▊ | 2803/15000 [12:56:40<51:06:43, 15.09s/it] 19%|█▊ | 2804/15000 [12:56:54<50:38:28, 14.95s/it] 19%|█▊ | 2805/15000 [12:57:09<50:15:34, 14.84s/it] 19%|█▊ | 2806/15000 [12:57:45<72:22:55, 21.37s/it] 19%|█▊ | 2807/15000 [12:58:00<65:39:01, 19.38s/it] 19%|█▊ | 2808/15000 [12:58:15<60:49:56, 17.96s/it] 19%|█▊ | 2809/15000 [12:58:29<57:30:25, 16.98s/it] 19%|█▊ | 2810/15000 [12:58:44<55:07:04, 16.28s/it] 19%|█▊ | 2811/15000 [12:58:59<53:24:53, 15.78s/it] 19%|█▊ | 2812<31><32>▊ | 2798/15000 [12:55:26<57:29:54, 16.96s/it] 19%|█▊ | 2799/15000 [12:55:41<55:00:23, 16.23s/it] 19%|█▊ | 2800/15000 [12:55:55<53:32:44, 15.80s/it] 19%|█▊ | 2800/15000 [12:55:56<53:32:44, 15.80s/it] 19%|█▊ | 2801/15000 [12:56:10<52:34:40, 15.52s/it] 19%|█▊ | 2802/15000 [12:56:25<51:40:08, 15.25s/it] 19%|█▊ | 2803/15000 [12:56:39<51:02:29, 15.07s/it] 19%|█▊ | 2804/15000 [12:56:54<50:35:41, 14.93s/it] 19%|█▊ | 2805/15000 [12:57:09<50:12:40, 14.82s/it] 19%|█▊ | 2806/15000 [12:57:45<72:27:54, 21.39s/it] 19%|█▊ | 2807/15000 [12:58:00<65:46:11, 19.42s/it] 19%|█▊ | 2808/15000 [12:58:15<60:54:03, 17.98s/it] 19%|█▊ | 2809/15000 [12:58:29<57:22:20, 16.94s/it] 19%|█▊ | 2810/15000 [12:58:44<55:07:32, 16.28s/it] 19%|█▊ | 2811/15000 [12:58:59<53:26:01, 15.78s/it] 19%|█▊ | 281231:27, 15.79s/it] 19%|█▊ | 2801/15000 [12:56:10<52:31:49, 15.50s/it] 19%|█▊ | 2802/15000 [12:56:25<51:41:13, 15.25s/it] 19%|█▊ | 2803/15000 [12:56:39<51:08:15, 15.09s/it] 19%|█▊ | 2804/15000 [12:56:54<50:35:42, 14.93s/it] 19%|█▊ | 2805/15000 [12:57:09<50:19:14, 14.85s/it] 19%|█▊ | 2806/15000 [12:57:45<72:28:42, 21.40s/it] 19%|█▊ | 2807/15000 [12:58:00<65:36:55, 19.37s/it] 19%|█▊ | 2808/15000 [12:58:15<60:50:54, 17.97s/it] 19%|█▊ | 2809/15000 [12:58:29<57:28:37, 16.97s/it] 19%|█▊ | 2810/15000 [12:58:44<55:03:05, 16.26s/it] 19%|█▊ | 2811/15000 [12:58:59<53:26:51, 15.79s/it] 19%|█▊ | 2812/15000 [12:59:13<52:15:32, 15.44s/it] 19%|█▉ | 2813/15000 [12:59:28<51:32:29, 15.23s/it] 19%|█▉ | 2814/15000 [12:59:43<50:54:13, 15.04s/it] 19%|█▉ | 2815/15000 [12:59:57<50:37:37, 14.96s/it] 19%|█▉ | 2816/15000 [13:00:12<50:12:32, 14.84s/i
{'loss': 0.8993, 'learning_rate': 0.00018633138372102468, 'epoch': 0.54}
{'loss': 0.8993, 'learning_rate': 0.00018633138372102468, 'epoch': 0.54}
50:22:19, 14.98s/it] 19%|█▉ | 2894/15000 [13:21:49<49:57:29, 14.86s/it] 19%|█▉ | 2895/15000 [13:22:04<49:49:29, 14.82s/it] 19%|█▉ | 2896/15000 [13:22:40<71:32:33, 21.28s/it] 19%|█▉ | 2897/15000 [13:22:55<64:44:48, 19.26s/it] 19%|█▉ | 2898/15000 [13:23:09<60:13:57, 17.92s/it] 19%|█▉ | 2899/15000 [13:23:24<56:50:03, 16.91s/it] 19%|█▉ | 2900/15000 [13:23:39<54:35:43, 16.24s/it] 19%|█▉ | 2900/15000 [13:23:39<54:35:43, 16.24s/it] 19%|█▉ | 2901/15000 [13:23:54<53:17:02, 15.85s/it] 19%|█▉ | 2902/15000 [13:24:08<52:00:41, 15.48s/it] 19%|█▉ | 2903/15000 [13:24:23<51:13:26, 15.24s/it] 19%|█▉ | 2904/15000 [13:24:38<50:38:52, 15.07s/it] 19%|█▉ | 2905/15000 [13:24:52<50:04:19, 14.90s/it] 19%|█▉ | 2906/15000 [13:25:07<49:55:39, 14.86s/it] 19%|█▉ | 2907/15000 [13:25:43<71:30:38, 21.29s/it50:22:54, 14.98s/it] 19%|█▉ | 2894/15000 [13:21:49<50:01:42, 14.88s/it] 19%|█▉ | 2895/15000 [13:22:04<49:44:40, 14.79s/it] 19%|█▉ | 2896/15000 [13:22:40<71:32:39, 21.28s/it] 19%|█▉ | 2897/15000 [13:22:55<64:47:06, 19.27s/it] 19%|█▉ | 2898/15000 [13:23:09<60:16:25, 17.93s/it] 19%|█▉ | 2899/15000 [13:23:24<56:46:52, 16.89s/it] 19%|█▉ | 2900/15000 [13:23:39<54:40:37, 16.27s/it] 19%|█▉ | 2900/15000 [13:23:39<54:40:37, 16.27s/it] 19%|█▉ | 2901/15000 [13:23:54<53:17:02, 15.85s/it] 19%|█▉ | 2902/15000 [13:24:08<51:56:10, 15.45s/it] 19%|█▉ | 2903/15000 [13:24:23<51:13:06, 15.24s/it] 19%|█▉ | 2904/15000 [13:24:38<50:44:32, 15.10s/it] 19%|█▉ | 2905/15000 [13:24:52<50:08:20, 14.92s/it] 19%|█▉ | 2906/15000 [13:25:07<49:56:49, 14.87s/it] 19%|█▉ | 2907/15000 [13:25:43<71:29:54, 21.28s/it | 2898/15000 [13:23:09<60:05:32, 17.88s/it] 19%|█▉ | 2899/15000 [13:23:24<56:53:31, 16.93s/it] 19%|█▉ | 2900/15000 [13:23:39<54:35:10, 16.24s/it] 19%|█▉ | 2900/15000 [13:23:39<54:35:10, 16.24s/it] 19%|█▉ | 2901/15000 [13:23:53<53:14:38, 15.84s/it] 19%|█▉ | 2902/15000 [13:24:08<52:04:36, 15.50s/it] 19%|█▉ | 2903/15000 [13:24:23<51:15:23, 15.25s/it] 19%|█▉ | 2904/15000 [13:24:37<50:36:50, 15.06s/it] 19%|█▉ | 2905/15000 [13:24:52<50:07:51, 14.92s/it] 19%|█▉ | 2906/15000 [13:25:07<49:53:21, 14.85s/it] 19%|█▉ | 2907/15000 [13:25:43<71:36:12, 21.32s/it] 19%|█▉ | 2908/15000 [13:25:58<64:53:11, 19.32s/it] 19%|█▉ | 2909/15000 [13:26:12<60:12:07, 17.92s/it] 19%|█▉ | 2910/15000 [13:26:27<56:55:22, 16.95s/it] 19%|█▉ | 2911/15000 [13:26:42<54:40:04, 16.28s/it] 19%|█▉ | 2912/15000 [1] 19%|█▉ | 2908/15000 [13:25:58<64:54:04, 19.32s/it] 19%|█▉ | 2909/15000 [13:26:13<60:13:57, 17.93s/it] 19%|█▉ | 2910/15000 [13:26:27<56:55:24, 16.95s/it] 19%|█▉ | 2911/15000 [13:26:42<54:34:13, 16.25s/it] 19%|█▉ | 2912/15000 [13:26:57<52:59:50, 15.78s/it] 19%|█▉ | 2913/15000 [13:27:11<51:51:40, 15.45s/it] 19%|█▉ | 2914/15000 [13:27:26<51:05:52, 15.22s/it] 19%|█▉ | 2915/15000 [13:27:41<50:35:16, 15.07s/it] 19%|█▉ | 2916/15000 [13:27:55<50:09:04, 14.94s/it] 19%|█▉ | 2917/15000 [13:28:10<49:55:11, 14.87s/it] 19%|█▉ | 2918/15000 [13:28:46<71:43:50, 21.37s/it] 19%|█▉ | 2919/15000 [13:29:01<64:58:12, 19.36s/it] 19%|█▉ | 2920/15000 [13:29:16<60:12:42, 17.94s/it] 19%|█▉ | 2921/15000 [13:29:30<56:51:03, 16.94s/it] 19%|█▉ | 2922/15000 [13:29:45<54:43:31, 16.31s/it] 19%|█▉ | 2923/15000 [13:30:00<52:52:15, 15.76s/it] 19%|█▉
{'loss': 0.895, 'learning_rate': 0.00018522168236559695, 'epoch': 0.56}
{'loss': 0.895, 'learning_rate': 0.00018522168236559695, 'epoch': 0.56}
| 2989/15000 [13:48:20<54:15:37, 16.26s/it] 20%|█▉ | 2990/15000 [13:48:34<52:40:05, 15.79s/it] 20%|█▉ | 2991/15000 [13:48:49<51:31:46, 15.45s/it] 20%|█▉ | 2992/15000 [13:49:04<50:45:40, 15.22s/it] 20%|█▉ | 2993/15000 [13:49:18<50:04:56, 15.02s/it] 20%|█▉ | 2994/15000 [13:49:33<49:45:45, 14.92s/it] 20%|█▉ | 2995/15000 [13:49:48<49:30:52, 14.85s/it] 20%|█▉ | 2996/15000 [13:50:24<71:08:19, 21.33s/it] 20%|█▉ | 2997/15000 [13:50:39<64:30:45, 19.35s/it] 20%|█▉ | 2998/15000 [13:50:53<59:49:18, 17.94s/it] 20%|█▉ | 2999/15000 [13:51:08<56:29:40, 16.95s/it] 20%|██ | 3000/15000 [13:51:23<54:13:12, 16.27s/it] 20%|██ | 3000/15000 [13:51:23<54:13:12, 16.27s/it] 20%|██ | 3001/15000 [13:51:38<52:48:23, 15.84s/it] 20%|██ | 3002/15000 [13:51:52<51:41:43, 15.51s/it] 20%|██ | 3003/15000 [1 | 2989/15000 [13:48:20<54:14:40, 16.26s/it] 20%|█▉ | 2990/15000 [13:48:34<52:40:15, 15.79s/it] 20%|█▉ | 2991/15000 [13:48:49<51:35:21, 15.47s/it] 20%|█▉ | 2992/15000 [13:49:04<50:45:58, 15.22s/it] 20%|█▉ | 2993/15000 [13:49:18<50:09:07, 15.04s/it] 20%|█▉ | 2994/15000 [13:49:33<49:38:28, 14.88s/it] 20%|█▉ | 2995/15000 [13:49:48<49:36:18, 14.88s/it] 20%|█▉ | 2996/15000 [13:50:24<71:05:00, 21.32s/it] 20%|█▉ | 2997/15000 [13:50:39<64:30:57, 19.35s/it] 20%|█▉ | 2998/15000 [13:50:53<59:42:48, 17.91s/it] 20%|█▉ | 2999/15000 [13:51:08<56:33:34, 16.97s/it] 20%|██ | 3000/15000 [13:51:23<54:10:25, 16.25s/it] 20%|██ | 3000/15000 [13:51:23<54:10:25, 16.25s/it] 20%|██ | 3001/15000 [13:51:37<52:49:19, 15.85s/it] 20%|██ | 3002/15000 [13:51:52<51:39:30, 15.50s/it] 20%|██ | 3003/15000 [1 15.03s/it] 20%|█▉ | 2994/15000 [13:49:33<49:47:53, 14.93s/it] 20%|█▉ | 2995/15000 [13:49:47<49:30:53, 14.85s/it] 20%|█▉ | 2996/15000 [13:50:24<71:08:45, 21.34s/it] 20%|█▉ | 2997/15000 [13:50:39<64:28:37, 19.34s/it] 20%|█▉ | 2998/15000 [13:50:53<59:45:15, 17.92s/it] 20%|█▉ | 2999/15000 [13:51:08<56:28:13, 16.94s/it] 20%|██ | 3000/15000 [13:51:23<54:12:45, 16.26s/it] 20%|██ | 3000/15000 [13:51:23<54:12:45, 16.26s/it] 20%|██ | 3001/15000 [13:51:37<52:49:29, 15.85s/it] 20%|██ | 3002/15000 [13:51:52<51:41:40, 15.51s/it] 20%|██ | 3003/15000 [13:52:07<50:52:43, 15.27s/it] 20%|██ | 3004/15000 [13:52:21<50:14:42, 15.08s/it] 20%|██ | 3005/15000 [13:52:36<49:55:53, 14.99s/it] 20%|██ | 3006/15000 [13:52:51<49:36:41, 14.89s/it] 20%|██ | 3007/15000 [13:53:27<70:53:13, 21.28s/it] 20%|<7C><>3:52:07<50:56:13, 15.28s/it] 20%|██ | 3004/15000 [13:52:22<50:16:20, 15.09s/it] 20%|██ | 3005/15000 [13:52:36<49:53:15, 14.97s/it] 20%|██ | 3006/15000 [13:52:51<49:37:27, 14.89s/it] 20%|██ | 3007/15000 [13:53:27<70:58:43, 21.31s/it] 20%|██ | 3008/15000 [13:53:42<64:12:59, 19.28s/it] 20%|██ | 3009/15000 [13:53:57<59:39:17, 17.91s/it] 20%|██ | 3010/15000 [13:54:11<56:29:51, 16.96s/it] 20%|██ | 3011/15000 [13:54:26<54:09:54, 16.26s/it] 20%|██ | 3012/15000 [13:54:41<52:35:13, 15.79s/it] 20%|██ | 3013/15000 [13:54:55<51:26:07, 15.45s/it] 20%|██ | 3014/15000 [13:55:10<50:38:37, 15.21s/it] 20%|██ | 3015/15000 [13:55:25<50:04:03, 15.04s/it] 20%|██ | 3016/15000 [13:55:39<49:41:06, 14.93s/it] 20%|██ | 3017/15000 [13:55:54<49:24:02, 14.84s/it] 20%|██ | 3018/15000 [13:56:09<49:15:13, 14.80s/it] 20%|██ | 3019/15000 [13:56:45<71:04:5
14.87s/it] 21%|██ | 3085/15000 [14:14:42<48:54:04, 14.78s/it] 21%|██ | 3086/15000 [14:15:19<70:20:31, 21.25s/it] 21%|██ | 3087/15000 [14:15:33<63:47:46, 19.28s/it] 21%|██ | 3088/15000 [14:15:48<59:20:06, 17.93s/it] 21%|██ | 3089/15000 [14:16:03<56:02:52, 16.94s/it] 21%|██ | 3090/15000 [14:16:18<53:46:04, 16.25s/it] 21%|██ | 3091/15000 [14:16:32<52:15:37, 15.80s/it] 21%|██ | 3092/15000 [14:16:47<51:05:27, 15.45s/it] 21%|██ | 3093/15000 [14:17:01<50:13:23, 15.18s/it] 21%|██ | 3094/15000 [14:17:16<49:46:54, 15.05s/it] 21%|██ | 3095/15000 [14:17:31<49:24:43, 14.94s/it] 21%|██ | 3096/15000 [14:17:46<49:09:49, 14.87s/it] 21%|██ | 3097/15000 [14:18:22<70:24:52, 21.30s/it] 21%|██ | 3098/15000 [14:18:36<63:44:21, 19.28s/it] 21%|██ | 3099/15000 [14:18:51<59:07:08, 17.88s/it] 21%|██ | 3100/15000 [14:19:06<55:50:47, 16.89s/it] {'loss': 0.8924, 'learning_rate': 0.00018407225206909208, 'epoch': 0.58}
14.86s/it] 21%|██ | 3085/15000 [14:14:42<48:53:45, 14.77s/it] 21%|██ | 3086/15000 [14:15:19<70:22:00, 21.26s/it] 21%|██ | 3087/15000 [14:15:34<63:50:35, 19.29s/it] 21%|██ | 3088/15000 [14:15:48<59:12:15, 17.89s/it] 21%|██ | 3089/15000 [14:16:03<56:00:18, 16.93s/it] 21%|██ | 3090/15000 [14:16:18<53:48:08, 16.26s/it] 21%|██ | 3091/15000 [14:16:32<52:09:45, 15.77s/it] 21%|██ | 3092/15000 [14:16:47<51:07:57, 15.46s/it] 21%|██ | 3093/15000 [14:17:01<50:17:19, 15.20s/it] 21%|██ | 3094/15000 [14:17:16<49:47:38, 15.06s/it] 21%|██ | 3095/15000 [14:17:31<49:31:50, 14.98s/it] 21%|██ | 3096/15000 [14:17:46<49:06:49, 14.85s/it] 21%|██ | 3097/15000 [14:18:22<70:20:32, 21.27s/it] 21%|██ | 3098/15000 [14:18:37<63:49:37, 19.31s/it] 21%|██ | 3099/15000 [14:18:51<59:08:34, 17.89s/it] 21%|██ | 3100/15000 [14:19:06<55:53:45, 16.91s/it] {'loss': 0.8924, 'learning_rate': 0.00018407225206909208, 'epoch': 0.58}
9/15000 [14:16:03<56:00:43, 16.93s/it] 21%|██ | 3090/15000 [14:16:17<53:45:27, 16.25s/it] 21%|██ | 3091/15000 [14:16:32<52:14:19, 15.79s/it] 21%|██ | 3092/15000 [14:16:47<51:07:28, 15.46s/it] 21%|██ | 3093/15000 [14:17:01<50:21:03, 15.22s/it] 21%|██ | 3094/15000 [14:17:16<49:53:27, 15.09s/it] 21%|██ | 3095/15000 [14:17:31<49:24:22, 14.94s/it] 21%|██ | 3096/15000 [14:17:46<49:08:49, 14.86s/it] 21%|██ | 3097/15000 [14:18:22<70:17:42, 21.26s/it] 21%|██ | 3098/15000 [14:18:36<63:43:22, 19.27s/it] 21%|██ | 3099/15000 [14:18:51<59:06:45, 17.88s/it] 21%|██ | 3100/15000 [14:19:06<55:53:46, 16.91s/it] 21%|██ | 3100/15000 [14:19:06<55:53:46, 16.91s/it] 21%|██ | 3101/15000 [14:19:20<53:51:21, 16.29s/it] 21%|██ | 3102/15000 [14:19:35<52:18:01, 15.82s/it] 21%|██ | 3103/15000 [14:19:50<5 21%|██ | 3100/15000 [14:19:06<55:50:47, 16.89s/it] 21%|██ | 3101/15000 [14:19:21<53:50:01, 16.29s/it] 21%|██ | 3102/15000 [14:19:35<52:13:25, 15.80s/it] 21%|██ | 3103/15000 [14:19:50<51:13:32, 15.50s/it] 21%|██ | 3104/15000 [14:20:05<50:19:58, 15.23s/it] 21%|██ | 3105/15000 [14:20:19<49:46:40, 15.07s/it] 21%|██ | 3106/15000 [14:20:34<49:27:10, 14.97s/it] 21%|██ | 3107/15000 [14:20:49<49:15:15, 14.91s/it] 21%|██ | 3108/15000 [14:21:25<70:16:37, 21.27s/it] 21%|██ | 3109/15000 [14:21:40<63:44:30, 19.30s/it] 21%|██ | 3110/15000 [14:21:54<59:12:04, 17.92s/it] 21%|██ | 3111/15000 [14:22:09<55:56:14, 16.94s/it] 21%|██ | 3112/15000 [14:22:24<53:40:46, 16.26s/it] 21%|██ | 3113/15000 [14:22:38<52:09:08, 15.79s/it] 21%|██ | 3114/15000 [14:22:53<50:59:30, 15.44s/it] 21%|██ | 31 21%|██ | 3100/15000 [14:19:06<55:53:45, 16.91s/it] 21%|██ | 3101/15000 [14:19:21<53:48:07, 16.28s/it] 21%|██ | 3102/15000 [14:19:35<52:14:40, 15.81s/it] 21%|██ | 3103/15000 [14:19:50<51:10:08, 15.48s/it] 21%|██ | 3104/15000 [14:20:05<50:21:21, 15.24s/it] 21%|██ | 3105/15000 [14:20:19<49:38:34, 15.02s/it] 21%|██ | 3106/15000 [14:20:34<49:22:29, 14.94s/it] 21%|██ | 3107/15000 [14:20:49<49:16:02, 14.91s/it] 21%|██ | 3108/15000 [14:21:25<70:16:39, 21.27s/it] 21%|██ | 3109/15000 [14:21:40<63:47:55, 19.32s/it] 21%|██ | 3110/15000 [14:21:54<59:13:45, 17.93s/it] 21%|██ | 3111/15000 [14:22:09<55:58:32, 16.95s/it] 21%|██ | 3112/15000 [14:22:24<53:38:24, 16.24s/it] 21%|██ | 3113/15000 [14:22:38<52:03:11, 15.76s/it] 21%|██ | 3114/15000 [14:22:53<51:03:43, 15.47s/it] 21%|██ | 311:11:02, 15.49s/it] 21%|██ | 3104/15000 [14:20:05<50:18:56, 15.23s/it] 21%|██ | 3105/15000 [14:20:19<49:45:42, 15.06s/it] 21%|██ | 3106/15000 [14:20:34<49:29:50, 14.98s/it] 21%|██ | 3107/15000 [14:20:49<49:12:52, 14.90s/it] 21%|██ | 3108/15000 [14:21:25<70:17:57, 21.28s/it] 21%|██ | 3109/15000 [14:21:40<63:46:50, 19.31s/it] 21%|██ | 3110/15000 [14:21:54<59:08:47, 17.91s/it] 21%|██ | 3111/15000 [14:22:09<55:56:25, 16.94s/it] 21%|██ | 3112/15000 [14:22:24<53:41:14, 16.26s/it] 21%|██ | 3113/15000 [14:22:38<52:08:07, 15.79s/it] 21%|██ | 3114/15000 [14:22:53<50:58:35, 15.44s/it] 21%|██ | 3115/15000 [14:23:08<50:17:29, 15.23s/it] 21%|██ | 3116/15000 [14:23:22<49:38:31, 15.04s/it] 21%|██ | 3117/15000 [14:23:37<49:17:38, 14.93s/it] 21%|██ | 3118/15000 [14:23:52<49:06:35, 14.88s/it] 21%|██ | 3119/15000 [14:24:28<70:12:25, 21.27s
{'loss': 0.8901, 'learning_rate': 0.00018288362867693414, 'epoch': 0.6}
{'loss': 0.8901, 'learning_rate': 0.00018288362867693414, 'epoch': 0.6}
196/15000 [14:45:27<48:51:03, 14.90s/it] 21%|██▏ | 3197/15000 [14:46:03<69:59:09, 21.35s/it] 21%|██▏ | 3198/15000 [14:46:18<63:30:56, 19.37s/it] 21%|██▏ | 3199/15000 [14:46:32<58:50:56, 17.95s/it] 21%|██▏ | 3200/15000 [14:46:47<55:39:51, 16.98s/it] 21%|██▏ | 3200/15000 [14:46:47<55:39:51, 16.98s/it] 21%|██▏ | 3201/15000 [14:47:02<53:40:34, 16.38s/it] 21%|██▏ | 3202/15000 [14:47:17<51:50:57, 15.82s/it] 21%|██▏ | 3203/15000 [14:47:31<50:53:55, 15.53s/it] 21%|██▏ | 3204/15000 [14:47:46<50:02:00, 15.27s/it] 21%|██▏ | 3205/15000 [14:48:01<49:18:29, 15.05s/it] 21%|██▏ | 3206/15000 [14:48:15<48:52:45, 14.92s/it] 21%|██▏ | 3207/15000 [14:48:30<48:34:59, 14.83s/it] 21%|██▏ | 3208/15000 [14:48:45<48:27:53, 14.80s/it] 21%|██▏ | 3209/15000 [14:49:21<70:03:06, 21.39s/it] 21%|██<E29688><E29688>196/15000 [14:45:26<48:48:16, 14.88s/it] 21%|██▏ | 3197/15000 [14:46:03<70:05:22, 21.38s/it] 21%|██▏ | 3198/15000 [14:46:18<63:32:37, 19.38s/it] 21%|██▏ | 3199/15000 [14:46:32<58:50:41, 17.95s/it] 21%|██▏ | 3200/15000 [14:46:47<55:29:58, 16.93s/it] 21%|██▏ | 3200/15000 [14:46:47<55:29:58, 16.93s/it] 21%|██▏ | 3201/15000 [14:47:02<53:35:56, 16.35s/it] 21%|██▏ | 3202/15000 [14:47:17<51:55:03, 15.84s/it] 21%|██▏ | 3203/15000 [14:47:31<50:55:29, 15.54s/it] 21%|██▏ | 3204/15000 [14:47:46<50:05:13, 15.29s/it] 21%|██▏ | 3205/15000 [14:48:01<49:21:28, 15.06s/it] 21%|██▏ | 3206/15000 [14:48:15<48:55:48, 14.94s/it] 21%|██▏ | 3207/15000 [14:48:30<48:36:29, 14.84s/it] 21%|██▏ | 3208/15000 [14:48:45<48:24:58, 14.78s/it] 21%|██▏ | 3209/15000 [14:49:21<69:59:28, 21.37s/it] 21%|██<E29688><E29688>, 16.96s/it] 21%|██▏ | 3200/15000 [14:46:47<55:35:05, 16.96s/it] 21%|██▏ | 3201/15000 [14:47:02<53:33:53, 16.34s/it] 21%|██▏ | 3202/15000 [14:47:17<51:58:26, 15.86s/it] 21%|██▏ | 3203/15000 [14:47:31<50:49:16, 15.51s/it] 21%|██▏ | 3204/15000 [14:47:46<49:58:21, 15.25s/it] 21%|██▏ | 3205/15000 [14:48:01<49:21:09, 15.06s/it] 21%|██▏ | 3206/15000 [14:48:15<48:52:42, 14.92s/it] 21%|██▏ | 3207/15000 [14:48:30<48:36:04, 14.84s/it] 21%|██▏ | 3208/15000 [14:48:44<48:29:58, 14.81s/it] 21%|██▏ | 3209/15000 [14:49:21<70:04:41, 21.40s/it] 21%|██▏ | 3210/15000 [14:49:36<63:25:38, 19.37s/it] 21%|██▏ | 3211/15000 [14:49:51<58:47:18, 17.95s/it] 21%|██▏ | 3212/15000 [14:50:05<55:32:19, 16.96s/it] 21%|██▏ | 3213/15000 [14:50:20<53:21:08, 16.29s/it] 21%|██▏ | 3214/15000 [14:50:<3A> | 3210/15000 [14:49:36<63:31:46, 19.40s/it] 21%|██▏ | 3211/15000 [14:49:51<58:49:12, 17.96s/it] 21%|██▏ | 3212/15000 [14:50:05<55:27:10, 16.94s/it] 21%|██▏ | 3213/15000 [14:50:20<53:20:49, 16.29s/it] 21%|██▏ | 3214/15000 [14:50:35<51:41:12, 15.79s/it] 21%|██▏ | 3215/15000 [14:50:49<50:35:10, 15.45s/it] 21%|██▏ | 3216/15000 [14:51:04<49:48:43, 15.22s/it] 21%|██▏ | 3217/15000 [14:51:19<49:14:16, 15.04s/it] 21%|██▏ | 3218/15000 [14:51:33<48:54:57, 14.95s/it] 21%|██▏ | 3219/15000 [14:51:48<48:39:01, 14.87s/it] 21%|██▏ | 3220/15000 [14:52:24<69:46:12, 21.32s/it] 21%|██▏ | 3221/15000 [14:52:39<63:23:08, 19.37s/it] 21%|██▏ | 3222/15000 [14:52:54<58:41:59, 17.94s/it] 21%|██▏ | 3223/15000 [14:53:08<55:21:50, 16.92s/it] 21%|██▏ | 3224/15000 [14:53:23<53:09:37, 16.25s/it] 22%|██▏ | 3225/15000 [14:53:38<51:31:22, 15.75s/
{'loss': 0.8873, 'learning_rate': 0.0001816563663057211, 'epoch': 0.62}
{'loss': 0.8873, 'learning_rate': 0.0001816563663057211, 'epoch': 0.62}
] 22%|██▏ | 3289/15000 [15:11:28<58:15:02, 17.91s/it] 22%|██▏ | 3290/15000 [15:11:42<54:57:14, 16.89s/it] 22%|██▏ | 3291/15000 [15:11:57<52:53:48, 16.26s/it] 22%|██▏ | 3292/15000 [15:12:12<51:25:54, 15.81s/it] 22%|██▏ | 3293/15000 [15:12:26<50:12:52, 15.44s/it] 22%|██▏ | 3294/15000 [15:12:41<49:25:34, 15.20s/it] 22%|██▏ | 3295/15000 [15:12:56<48:57:34, 15.06s/it] 22%|██▏ | 3296/15000 [15:13:11<48:35:16, 14.95s/it] 22%|██▏ | 3297/15000 [15:13:25<48:14:07, 14.84s/it] 22%|██▏ | 3298/15000 [15:14:02<69:44:36, 21.46s/it] 22%|██▏ | 3299/15000 [15:14:17<63:05:43, 19.41s/it] 22%|██▏ | 3300/15000 [15:14:31<58:23:26, 17.97s/it] 22%|██▏ | 3300/15000 [15:14:32<58:23:26, 17.97s/it] 22%|██▏ | 3301/15000 [15:14:46<55:23:27, 17.04s/it] 22%|██▏ | 3302/15000 [15:15:01<53:01:44] 22%|██▏ | 3289/15000 [15:11:28<58:10:21, 17.88s/it] 22%|██▏ | 3290/15000 [15:11:42<55:01:25, 16.92s/it] 22%|██▏ | 3291/15000 [15:11:57<52:49:39, 16.24s/it] 22%|██▏ | 3292/15000 [15:12:12<51:20:02, 15.78s/it] 22%|██▏ | 3293/15000 [15:12:26<50:10:26, 15.43s/it] 22%|██▏ | 3294/15000 [15:12:41<49:32:38, 15.24s/it] 22%|██▏ | 3295/15000 [15:12:56<48:59:17, 15.07s/it] 22%|██▏ | 3296/15000 [15:13:10<48:35:22, 14.95s/it] 22%|██▏ | 3297/15000 [15:13:25<48:18:46, 14.86s/it] 22%|██▏ | 3298/15000 [15:14:02<69:36:49, 21.42s/it] 22%|██▏ | 3299/15000 [15:14:17<63:08:52, 19.43s/it] 22%|██▏ | 3300/15000 [15:14:31<58:27:05, 17.99s/it] 22%|██▏ | 3300/15000 [15:14:32<58:27:05, 17.99s/it] 22%|██▏ | 3301/15000 [15:14:46<55:24:06, 17.05s/it] 22%|██▏ | 3302/15000 [15:15:01<53:07:413/15000 [15:12:26<50:13:49, 15.45s/it] 22%|██▏ | 3294/15000 [15:12:41<49:32:10, 15.23s/it] 22%|██▏ | 3295/15000 [15:12:56<48:51:15, 15.03s/it] 22%|██▏ | 3296/15000 [15:13:10<48:33:57, 14.94s/it] 22%|██▏ | 3297/15000 [15:13:25<48:16:56, 14.85s/it] 22%|██▏ | 3298/15000 [15:14:02<69:46:03, 21.46s/it] 22%|██▏ | 3299/15000 [15:14:17<63:04:36, 19.41s/it] 22%|██▏ | 3300/15000 [15:14:31<58:23:58, 17.97s/it] 22%|██▏ | 3300/15000 [15:14:31<58:23:58, 17.97s/it] 22%|██▏ | 3301/15000 [15:14:46<55:26:58, 17.06s/it] 22%|██▏ | 3302/15000 [15:15:01<53:03:21, 16.33s/it] 22%|██▏ | 3303/15000 [15:15:15<51:22:27, 15.81s/it] 22%|██▏ | 3304/15000 [15:15:30<50:17:33, 15.48s/it] 22%|██▏ | 3305/15000 [15:15:45<49:26:41, 15.22s/it] 22%|██▏ | 3306/15000 [15:15:59<48:51:19, 15.04s/it] 22%|██▏ , 16.35s/it] 22%|██▏ | 3303/15000 [15:15:15<51:20:06, 15.80s/it] 22%|██▏ | 3304/15000 [15:15:30<50:13:54, 15.46s/it] 22%|██▏ | 3305/15000 [15:15:45<49:29:32, 15.23s/it] 22%|██▏ | 3306/15000 [15:15:59<48:52:16, 15.05s/it] 22%|██▏ | 3307/15000 [15:16:14<48:26:51, 14.92s/it] 22%|██▏ | 3308/15000 [15:16:29<48:09:20, 14.83s/it] 22%|██▏ | 3309/15000 [15:17:05<69:29:11, 21.40s/it] 22%|██▏ | 3310/15000 [15:17:20<62:48:54, 19.34s/it] 22%|██▏ | 3311/15000 [15:17:35<58:20:12, 17.97s/it] 22%|██▏ | 3312/15000 [15:17:49<55:07:32, 16.98s/it] 22%|██▏ | 3313/15000 [15:18:04<52:47:20, 16.26s/it] 22%|██▏ | 3314/15000 [15:18:19<51:16:57, 15.80s/it] 22%|██▏ | 3315/15000 [15:18:33<50:07:48, 15.44s/it] 22%|██▏ | 3316/15000 [15:18:48<49:28:43, 15.25s/it] 22%|██▏ | 3317/15000 [15:19:03<48:54:22, 15.07s/it] 22%|██▏ | 3318/15000 [
{'loss': 0.8762, 'learning_rate': 0.000180391037084905, 'epoch': 0.64}
23%|██▎ | 3386/15000 [15:38:06<48:01:31, 14.89s/it] 23%|██▎ | 3387/15000 [15:38:20<47:46:43, 14.81s/it] 23%|██▎ | 3388/15000 [15:38:57<69:06:28, 21.43s/it] 23%|██▎ | 3389/15000 [15:39:12<62:36:32, 19.41s/it] 23%|██▎ | 3390/15000 [15:39:27<58:02:01, 17.99s/it] 23%|██▎ | 3391/15000 [15:39:41<54:49:31, 17.00s/it] 23%|██▎ | 3392/15000 [15:39:56<52:28:48, 16.28s/it] 23%|██▎ | 3393/15000 [15:40:10<50:56:31, 15.80s/it] 23%|██▎ | 3394/15000 [15:40:25<49:46:04, 15.44s/it] 23%|██▎ | 3395/15000 [15:40:40<49:03:21, 15.22s/it] 23%|██▎ | 3396/15000 [15:40:54<48:23:59, 15.02s/it] 23%|██▎ | 3397/15000 [15:41:09<48:07:20, 14.93s/it] 23%|██▎ | 3398/15000 [15:41:24<47:54:32, 14.87s/it] 23%|██▎ | 3399/15000 [15:42:01<69:16:30, 21.50s/it] 23%|██▎ | 3400/15000 [15:42:15<62:43:50, 19.47s/it] {'loss': 0.8762, 'learning_rate': 0.000180391037084905, 'epoch': 0.64}
| 3397/15000 [15:41:09<48:06:03, 14.92s/it] 23%|██▎ | 3398/15000 [15:41:24<47:49:54, 14.84s/it] 23%|██▎ | 3399/15000 [15:42:01<69:19:27, 21.51s/it] 23%|██▎ | 3400/15000 [15:42:16<62:44:05, 19.47s/it] 23%|██▎ | 3400/15000 [15:42:16<62:44:05, 19.47s/it] 23%|██▎ | 3401/15000 [15:42:30<58:12:42, 18.07s/it] 23%|██▎ | 3402/15000 [15:42:45<55:03:38, 17.09s/it] 23%|██▎ | 3403/15000 [15:43:00<52:41:59, 16.36s/it] 23%|██▎ | 3404/15000 [15:43:14<50:59:51, 15.83s/it] 23%|██▎ | 3405/15000 [15:43:29<49:52:50, 15.49s/it] 23%|██▎ | 3406/15000 [15:43:44<49:06:18, 15.25s/it] 23%|██▎ | 3407/15000 [15:43:58<48:34:32, 15.08s/it] 23%|██▎ | 3408/15000 [15:44:13<48:10:07, 14.96s/it] 23%|██▎ | 3409/15000 [15:44:28<47:56:15, 14.89s/it] 23%|██▎ | 3410/15000 [15:44:43<47:54:50, 14.88s/it] 23%|█<><E29688>| 3397/15000 [15:41:09<48:05:34, 14.92s/it] 23%|██▎ | 3398/15000 [15:41:24<47:53:15, 14.86s/it] 23%|██▎ | 3399/15000 [15:42:01<69:20:18, 21.52s/it] 23%|██▎ | 3400/15000 [15:42:15<62:38:07, 19.44s/it] 23%|██▎ | 3400/15000 [15:42:16<62:38:07, 19.44s/it] 23%|██▎ | 3401/15000 [15:42:30<58:15:42, 18.08s/it] 23%|██▎ | 3402/15000 [15:42:45<55:01:54, 17.08s/it] 23%|██▎ | 3403/15000 [15:43:00<52:39:05, 16.34s/it] 23%|██▎ | 3404/15000 [15:43:15<51:07:19, 15.87s/it] 23%|██▎ | 3405/15000 [15:43:29<49:59:43, 15.52s/it] 23%|██▎ | 3406/15000 [15:43:44<49:02:19, 15.23s/it] 23%|██▎ | 3407/15000 [15:43:58<48:30:10, 15.06s/it] 23%|██▎ | 3408/15000 [15:44:13<48:14:40, 14.98s/it] 23%|██▎ | 3409/15000 [15:44:28<47:56:55, 14.89s/it] 23%|██▎ | 3410/15000 [15:44:43<47:51:05, 14.86s/it] 23%|█<><E29688> 23%|██▎ | 3400/15000 [15:42:16<62:43:50, 19.47s/it] 23%|██▎ | 3401/15000 [15:42:30<58:17:39, 18.09s/it] 23%|██▎ | 3402/15000 [15:42:45<55:01:53, 17.08s/it] 23%|██▎ | 3403/15000 [15:43:00<52:39:58, 16.35s/it] 23%|██▎ | 3404/15000 [15:43:14<51:01:21, 15.84s/it] 23%|██▎ | 3405/15000 [15:43:29<49:55:10, 15.50s/it] 23%|██▎ | 3406/15000 [15:43:44<49:02:53, 15.23s/it] 23%|██▎ | 3407/15000 [15:43:58<48:36:30, 15.09s/it] 23%|██▎ | 3408/15000 [15:44:13<48:15:11, 14.99s/it] 23%|██▎ | 3409/15000 [15:44:28<47:59:25, 14.91s/it] 23%|██▎ | 3410/15000 [15:44:43<47:46:17, 14.84s/it] 23%|██▎ | 3411/15000 [15:45:20<69:06:13, 21.47s/it] 23%|██▎ | 3412/15000 [15:45:34<62:26:21, 19.40s/it] 23%|██▎ | 3413/15000 [15:45:49<57:47:05, 17.95s/it] 23%|██▎ | 3414/15000 [15:46:03<54:35:44, 16.96s/it] 23%|██▎ | 3415/15000 [15:<3A>▎ | 3411/15000 [15:45:20<69:07:33, 21.47s/it] 23%|██▎ | 3412/15000 [15:45:34<62:31:44, 19.43s/it] 23%|██▎ | 3413/15000 [15:45:49<57:49:17, 17.96s/it] 23%|██▎ | 3414/15000 [15:46:03<54:35:27, 16.96s/it] 23%|██▎ | 3415/15000 [15:46:18<52:21:38, 16.27s/it] 23%|██▎ | 3416/15000 [15:46:33<50:53:58, 15.82s/it] 23%|██▎ | 3417/15000 [15:46:47<49:45:33, 15.47s/it] 23%|██▎ | 3418/15000 [15:47:02<49:01:48, 15.24s/it] 23%|██▎ | 3419/15000 [15:47:17<48:26:21, 15.06s/it] 23%|██▎ | 3420/15000 [15:47:31<48:01:25, 14.93s/it] 23%|██▎ | 3421/15000 [15:47:46<47:45:30, 14.85s/it] 23%|██▎ | 3422/15000 [15:48:23<69:08:30, 21.50s/it] 23%|██▎ | 3423/15000 [15:48:38<62:30:19, 19.44s/it] 23%|██▎ | 3424/15000 [15:48:52<57:53:32, 18.00s/it] 23%|██▎ | 3425/15000 [15:49:07<54:44:34, 17.03s/it] 23%|██▎ | 3426/15000 [15:49:22<52:30:00, 16.3
{'loss': 0.8731, 'learning_rate': 0.00017908823089007457, 'epoch': 0.66}
{'loss': 0.8731, 'learning_rate': 0.00017908823089007457, 'epoch': 0.66}
/it] 23%|██▎ | 3490/15000 [16:07:14<68:05:59, 21.30s/it] 23%|██▎ | 3491/15000 [16:07:29<61:43:24, 19.31s/it] 23%|██▎ | 3492/15000 [16:07:43<57:22:29, 17.95s/it] 23%|██▎ | 3493/15000 [16:07:58<54:06:26, 16.93s/it] 23%|██▎ | 3494/15000 [16:08:13<51:52:07, 16.23s/it] 23%|██▎ | 3495/15000 [16:08:27<50:22:47, 15.76s/it] 23%|██▎ | 3496/15000 [16:08:42<49:20:00, 15.44s/it] 23%|██▎ | 3497/15000 [16:08:56<48:25:19, 15.15s/it] 23%|██▎ | 3498/15000 [16:09:11<47:55:47, 15.00s/it] 23%|██▎ | 3499/15000 [16:09:26<47:31:35, 14.88s/it] 23%|██▎ | 3500/15000 [16:09:40<47:14:53, 14.79s/it] 23%|██▎ | 3500/15000 [16:09:40<47:14:53, 14.79s/it] 23%|██▎ | 3501/15000 [16:10:17<68:36:09, 21.48s/it] 23%|██▎ | 3502/15000 [16:10:32<62:01:12, 19.42s/it] 23%|██▎ | 3503/15000 [16:10:47<57:29/it] 23%|██▎ | 3490/15000 [16:07:14<68:16:47, 21.36s/it] 23%|██▎ | 3491/15000 [16:07:29<61:40:48, 19.29s/it] 23%|██▎ | 3492/15000 [16:07:43<57:20:22, 17.94s/it] 23%|██▎ | 3493/15000 [16:07:58<54:04:47, 16.92s/it] 23%|██▎ | 3494/15000 [16:08:13<51:52:25, 16.23s/it] 23%|██▎ | 3495/15000 [16:08:27<50:22:56, 15.77s/it] 23%|██▎ | 3496/15000 [16:08:42<49:12:44, 15.40s/it] 23%|██▎ | 3497/15000 [16:08:56<48:25:56, 15.16s/it] 23%|██▎ | 3498/15000 [16:09:11<47:55:46, 15.00s/it] 23%|██▎ | 3499/15000 [16:09:26<47:36:40, 14.90s/it] 23%|██▎ | 3500/15000 [16:09:40<47:18:47, 14.81s/it] 23%|██▎ | 3500/15000 [16:09:40<47:18:47, 14.81s/it] 23%|██▎ | 3501/15000 [16:10:17<68:31:05, 21.45s/it] 23%|██▎ | 3502/15000 [16:10:32<62:01:27, 19.42s/it] 23%|██▎ | 3503/15000 [16:10:47<57:323494/15000 [16:08:13<51:56:55, 16.25s/it] 23%|██▎ | 3495/15000 [16:08:27<50:20:15, 15.75s/it] 23%|██▎ | 3496/15000 [16:08:42<49:14:10, 15.41s/it] 23%|██▎ | 3497/15000 [16:08:56<48:23:32, 15.14s/it] 23%|██▎ | 3498/15000 [16:09:11<47:58:24, 15.02s/it] 23%|██▎ | 3499/15000 [16:09:26<47:35:46, 14.90s/it] 23%|██▎ | 3500/15000 [16:09:40<47:15:23, 14.79s/it] 23%|██▎ | 3500/15000 [16:09:40<47:15:23, 14.79s/it] 23%|██▎ | 3501/15000 [16:10:17<68:37:02, 21.48s/it] 23%|██▎ | 3502/15000 [16:10:32<62:04:55, 19.44s/it] 23%|██▎ | 3503/15000 [16:10:47<57:28:48, 18.00s/it] 23%|██▎ | 3504/15000 [16:11:01<54:14:05, 16.98s/it] 23%|██▎ | 3505/15000 [16:11:16<52:03:41, 16.30s/it] 23%|██▎ | 3506/15000 [16:11:31<50:27:29, 15.80s/it] 23%|██▎ | 3507/15000 [16:11:45<49:22:38, 15.47s/it] 23%|██<E29688>:54, 18.02s/it] 23%|██▎ | 3504/15000 [16:11:01<54:15:39, 16.99s/it] 23%|██▎ | 3505/15000 [16:11:16<52:03:54, 16.31s/it] 23%|██▎ | 3506/15000 [16:11:31<50:26:09, 15.80s/it] 23%|██▎ | 3507/15000 [16:11:45<49:20:15, 15.45s/it] 23%|██▎ | 3508/15000 [16:12:00<48:34:32, 15.22s/it] 23%|██▎ | 3509/15000 [16:12:15<48:09:45, 15.09s/it] 23%|██▎ | 3510/15000 [16:12:29<47:43:24, 14.95s/it] 23%|██▎ | 3511/15000 [16:12:44<47:25:49, 14.86s/it] 23%|██▎ | 3512/15000 [16:13:21<68:39:48, 21.52s/it] 23%|██▎ | 3513/15000 [16:13:36<62:05:05, 19.46s/it] 23%|██▎ | 3514/15000 [16:13:50<57:32:24, 18.03s/it] 23%|██▎ | 3515/15000 [16:14:05<54:11:59, 16.99s/it] 23%|██▎ | 3516/15000 [16:14:20<52:01:31, 16.31s/it] 23%|██▎ | 3517/15000 [16:14:34<50:19:41, 15.78s/it] 23%|██▎ | 3518/15000 [16:14:49<49:28:34, 15.51s/it] 23%|██▎ | 3519/1500
{'loss': 0.8698, 'learning_rate': 0.00017774855506796496, 'epoch': 0.67}
{'loss': 0.8698, 'learning_rate': 0.00017774855506796496, 'epoch': 0.67}
t] 24%|██▍ | 3587/15000 [16:33:57<48:13:57, 15.21s/it] 24%|██▍ | 3588/15000 [16:34:11<47:42:31, 15.05s/it] 24%|██▍ | 3589/15000 [16:34:26<47:21:41, 14.94s/it] 24%|██▍ | 3590/15000 [16:34:41<47:06:04, 14.86s/it] 24%|██▍ | 3591/15000 [16:35:17<67:49:52, 21.40s/it] 24%|██▍ | 3592/15000 [16:35:32<61:27:25, 19.39s/it] 24%|██▍ | 3593/15000 [16:35:47<56:52:05, 17.95s/it] 24%|██▍ | 3594/15000 [16:36:01<53:35:29, 16.91s/it] 24%|██▍ | 3595/15000 [16:36:16<51:25:47, 16.23s/it] 24%|██▍ | 3596/15000 [16:36:30<49:54:57, 15.76s/it] 24%|██▍ | 3597/15000 [16:36:45<48:55:09, 15.44s/it] 24%|██▍ | 3598/15000 [16:37:00<48:07:11, 15.19s/it] 24%|██▍ | 3599/15000 [16:37:14<47:40:32, 15.05s/it] 24%|██▍ | 3600/15000 [16:37:29<47:14:25, 14.92s/it] 24%|██▍ | 3600/15000 [16:37:29<47:14:2 | 3598/15000 [16:37:00<48:11:24, 15.22s/it] 24%|██▍ | 3599/15000 [16:37:14<47:34:40, 15.02s/it] 24%|██▍ | 3600/15000 [16:37:29<47:16:36, 14.93s/it] 24%|██▍ | 3600/15000 [16:37:29<47:16:36, 14.93s/it] 24%|██▍ | 3601/15000 [16:37:44<47:20:41, 14.95s/it] 24%|██▍ | 3602/15000 [16:38:21<68:01:34, 21.49s/it] 24%|██▍ | 3603/15000 [16:38:35<61:27:36, 19.41s/it] 24%|██▍ | 3604/15000 [16:38:50<56:55:24, 17.98s/it] 24%|██▍ | 3605/15000 [16:39:05<53:43:41, 16.97s/it] 24%|██▍ | 3606/15000 [16:39:19<51:35:24, 16.30s/it] 24%|██▍ | 3607/15000 [16:39:34<49:57:35, 15.79s/it] 24%|██▍ | 3608/15000 [16:39:49<48:50:57, 15.44s/it] 24%|██▍ | 3609/15000 [16:40:03<48:12:06, 15.23s/it] 24%|██▍ | 3610/15000 [16:40:18<47:32:17, 15.03s/it] 24%|██▍ | 3611/15000 [16:40:33<47:09:58, 14.91s/it] 24%|<7C><> | 3598/15000 [16:37:00<48:06:29, 15.19s/it] 24%|██▍ | 3599/15000 [16:37:15<47:41:25, 15.06s/it] 24%|██▍ | 3600/15000 [16:37:29<47:17:36, 14.93s/it] 24%|██▍ | 3600/15000 [16:37:29<47:17:36, 14.93s/it] 24%|██▍ | 3601/15000 [16:37:44<47:15:24, 14.92s/it] 24%|██▍ | 3602/15000 [16:38:21<68:01:46, 21.49s/it] 24%|██▍ | 3603/15000 [16:38:35<61:29:17, 19.42s/it] 24%|██▍ | 3604/15000 [16:38:50<56:57:19, 17.99s/it] 24%|██▍ | 3605/15000 [16:39:05<53:38:23, 16.95s/it] 24%|██▍ | 3606/15000 [16:39:19<51:29:00, 16.27s/it] 24%|██▍ | 3607/15000 [16:39:34<49:56:34, 15.78s/it] 24%|██▍ | 3608/15000 [16:39:49<48:55:09, 15.46s/it] 24%|██▍ | 3609/15000 [16:40:03<48:07:54, 15.21s/it] 24%|██▍ | 3610/15000 [16:40:18<47:37:12, 15.05s/it] 24%|██▍ | 3611/15000 [16:40:33<47:14:38, 14.93s/it] 24%|<7C><>5, 14.92s/it] 24%|██▍ | 3601/15000 [16:37:44<47:17:40, 14.94s/it] 24%|██▍ | 3602/15000 [16:38:21<68:03:53, 21.50s/it] 24%|██▍ | 3603/15000 [16:38:35<61:26:58, 19.41s/it] 24%|██▍ | 3604/15000 [16:38:50<56:52:53, 17.97s/it] 24%|██▍ | 3605/15000 [16:39:05<53:45:27, 16.98s/it] 24%|██▍ | 3606/15000 [16:39:19<51:29:54, 16.27s/it] 24%|██▍ | 3607/15000 [16:39:34<49:58:25, 15.79s/it] 24%|██▍ | 3608/15000 [16:39:49<48:56:07, 15.46s/it] 24%|██▍ | 3609/15000 [16:40:03<48:10:25, 15.22s/it] 24%|██▍ | 3610/15000 [16:40:18<47:37:02, 15.05s/it] 24%|██▍ | 3611/15000 [16:40:33<47:13:49, 14.93s/it] 24%|██▍ | 3612/15000 [16:40:47<46:58:53, 14.85s/it] 24%|██▍ | 3613/15000 [16:41:02<46:45:35, 14.78s/it] 24%|██▍ | 3614/15000 [16:41:39<67:38:52, 21.39s/it] 24%|██▍ | 3615/15000 [16:41:53<61:14:52, 19.37s/it] 24%|██▍ | 3616/15000
{'loss': 0.8679, 'learning_rate': 0.0001763726341533227, 'epoch': 0.69}
{'loss': 0.8679, 'learning_rate': 0.0001763726341533227, 'epoch': 0.69}
04s/it] 25%|██▍ | 3691/15000 [17:02:43<46:53:54, 14.93s/it] 25%|██▍ | 3692/15000 [17:02:58<46:40:51, 14.86s/it] 25%|██▍ | 3693/15000 [17:03:35<67:38:51, 21.54s/it] 25%|██▍ | 3694/15000 [17:03:50<61:10:50, 19.48s/it] 25%|██▍ | 3695/15000 [17:04:04<56:38:00, 18.03s/it] 25%|██▍ | 3696/15000 [17:04:19<53:30:22, 17.04s/it] 25%|██▍ | 3697/15000 [17:04:34<51:16:00, 16.33s/it] 25%|██▍ | 3698/15000 [17:04:49<49:42:56, 15.84s/it] 25%|██▍ | 3699/15000 [17:05:03<48:39:25, 15.50s/it] 25%|██▍ | 3700/15000 [17:05:18<47:53:26, 15.26s/it] 25%|██▍ | 3700/15000 [17:05:18<47:53:26, 15.26s/it] 25%|██▍ | 3701/15000 [17:05:33<47:39:26, 15.18s/it] 25%|██▍ | 3702/15000 [17:05:48<47:09:30, 15.03s/it] 25%|██▍ | 3703/15000 [17:06:02<46:53:57, 14.95s/it] 25%|██▍ | 3704/15000 [17:06:39<6799s/it] 25%|██▍ | 3691/15000 [17:02:43<46:49:34, 14.91s/it] 25%|██▍ | 3692/15000 [17:02:58<46:38:40, 14.85s/it] 25%|██▍ | 3693/15000 [17:03:35<67:39:51, 21.54s/it] 25%|██▍ | 3694/15000 [17:03:50<61:10:52, 19.48s/it] 25%|██▍ | 3695/15000 [17:04:04<56:38:11, 18.04s/it] 25%|██▍ | 3696/15000 [17:04:19<53:35:08, 17.07s/it] 25%|██▍ | 3697/15000 [17:04:34<51:18:50, 16.34s/it] 25%|██▍ | 3698/15000 [17:04:49<49:44:08, 15.84s/it] 25%|██▍ | 3699/15000 [17:05:03<48:39:08, 15.50s/it] 25%|██▍ | 3700/15000 [17:05:18<47:56:30, 15.27s/it] 25%|██▍ | 3700/15000 [17:05:18<47:56:30, 15.27s/it] 25%|██▍ | 3701/15000 [17:05:33<47:39:01, 15.18s/it] 25%|██▍ | 3702/15000 [17:05:48<47:08:03, 15.02s/it] 25%|██▍ | 3703/15000 [17:06:02<46:52:36, 14.94s/it] 25%|██▍ | 3704/15000 [17:06:39<67 | 3695/15000 [17:04:04<56:34:46, 18.02s/it] 25%|██▍ | 3696/15000 [17:04:19<53:28:58, 17.03s/it] 25%|██▍ | 3697/15000 [17:04:34<51:19:45, 16.35s/it] 25%|██▍ | 3698/15000 [17:04:48<49:42:46, 15.83s/it] 25%|██▍ | 3699/15000 [17:05:03<48:36:25, 15.48s/it] 25%|██▍ | 3700/15000 [17:05:18<47:57:47, 15.28s/it] 25%|██▍ | 3700/15000 [17:05:18<47:57:47, 15.28s/it] 25%|██▍ | 3701/15000 [17:05:33<47:32:37, 15.15s/it] 25%|██▍ | 3702/15000 [17:05:48<47:12:23, 15.04s/it] 25%|██▍ | 3703/15000 [17:06:02<46:56:31, 14.96s/it] 25%|██▍ | 3704/15000 [17:06:39<67:36:01, 21.54s/it] 25%|██▍ | 3705/15000 [17:06:54<61:05:26, 19.47s/it] 25%|██▍ | 3706/15000 [17:07:09<56:36:09, 18.04s/it] 25%|██▍ | 3707/15000 [17:07:23<53:31:23, 17.06s/it] 25%|██▍ | 3708/15000 [17:07:38<51:11:05, 16.32s/it] 25%|█<>:35:47, 21.54s/it] 25%|██▍ | 3705/15000 [17:06:54<61:08:44, 19.49s/it] 25%|██▍ | 3706/15000 [17:07:09<56:36:12, 18.04s/it] 25%|██▍ | 3707/15000 [17:07:23<53:21:48, 17.01s/it] 25%|██▍ | 3708/15000 [17:07:38<51:11:04, 16.32s/it] 25%|██▍ | 3709/15000 [17:07:53<49:37:04, 15.82s/it] 25%|██▍ | 3710/15000 [17:08:07<48:40:21, 15.52s/it] 25%|██▍ | 3711/15000 [17:08:22<47:45:48, 15.23s/it] 25%|██▍ | 3712/15000 [17:08:37<47:17:11, 15.08s/it] 25%|██▍ | 3713/15000 [17:08:51<46:56:14, 14.97s/it] 25%|██▍ | 3714/15000 [17:09:06<46:37:46, 14.87s/it] 25%|██▍ | 3715/15000 [17:09:43<67:05:24, 21.40s/it] 25%|██▍ | 3716/15000 [17:09:57<60:47:33, 19.40s/it] 25%|██▍ | 3717/15000 [17:10:12<56:18:43, 17.97s/it] 25%|██▍ | 3718/15000 [17:10:27<53:07:54, 16.95s/it] 25%|██▍ | 3719/15000 [17:10:41<50:51:36, 16.23s/it] 25%|██▍ | 3720/1
{'loss': 0.8652, 'learning_rate': 0.0001749611095777581, 'epoch': 0.71}
{'loss': 0.8652, 'learning_rate': 0.0001749611095777581, 'epoch': 0.71}
s/it] 25%|██▌ | 3788/15000 [17:29:46<49:09:02, 15.78s/it] 25%|██▌ | 3789/15000 [17:30:00<48:05:31, 15.44s/it] 25%|██▌ | 3790/15000 [17:30:15<47:25:11, 15.23s/it] 25%|██▌ | 3791/15000 [17:30:30<46:46:05, 15.02s/it] 25%|██▌ | 3792/15000 [17:30:44<46:27:58, 14.92s/it] 25%|██▌ | 3793/15000 [17:30:59<46:11:47, 14.84s/it] 25%|██▌ | 3794/15000 [17:31:36<66:50:55, 21.48s/it] 25%|██▌ | 3795/15000 [17:31:50<60:20:44, 19.39s/it] 25%|██▌ | 3796/15000 [17:32:05<56:00:39, 18.00s/it] 25%|██▌ | 3797/15000 [17:32:20<52:50:57, 16.98s/it] 25%|██▌ | 3798/15000 [17:32:34<50:41:53, 16.29s/it] 25%|██▌ | 3799/15000 [17:32:49<49:18:14, 15.85s/it] 25%|██▌ | 3800/15000 [17:33:04<48:14:37, 15.51s/it] 25%|██▌ | 3800/15000 [17:33:04<48:14:37, 15.51s/it] 25%|██▌ | 3801/15000 [17:33:19<47:3 | 3799/15000 [17:32:49<49:20:43, 15.86s/it] 25%|██▌ | 3800/15000 [17:33:04<48:10:50, 15.49s/it] 25%|██▌ | 3800/15000 [17:33:04<48:10:50, 15.49s/it] 25%|██▌ | 3801/15000 [17:33:19<47:33:25, 15.29s/it] 25%|██▌ | 3802/15000 [17:33:34<47:06:28, 15.14s/it] 25%|██▌ | 3803/15000 [17:33:48<46:43:54, 15.02s/it] 25%|██▌ | 3804/15000 [17:34:03<46:26:52, 14.93s/it] 25%|██▌ | 3805/15000 [17:34:18<46:19:14, 14.90s/it] 25%|██▌ | 3806/15000 [17:34:55<66:53:33, 21.51s/it] 25%|██▌ | 3807/15000 [17:35:10<60:41:24, 19.52s/it] 25%|██▌ | 3808/15000 [17:35:24<56:13:19, 18.08s/it] 25%|██▌ | 3809/15000 [17:35:39<53:09:59, 17.10s/it] 25%|██▌ | 3810/15000 [17:35:54<50:58:29, 16.40s/it] 25%|██▌ | 3811/15000 [17:36:09<49:17:44, 15.86s/it] 25%|██▌ | 3812/15000 [17:36:23<48:12:01, 15.51s/it] 25% | 3799/15000 [17:32:49<49:13:28, 15.82s/it] 25%|██▌ | 3800/15000 [17:33:04<48:13:22, 15.50s/it] 25%|██▌ | 3800/15000 [17:33:04<48:13:22, 15.50s/it] 25%|██▌ | 3801/15000 [17:33:19<47:42:15, 15.33s/it] 25%|██▌ | 3802/15000 [17:33:34<47:01:59, 15.12s/it] 25%|██▌ | 3803/15000 [17:33:48<46:43:37, 15.02s/it] 25%|██▌ | 3804/15000 [17:34:03<46:31:17, 14.96s/it] 25%|██▌ | 3805/15000 [17:34:18<46:17:17, 14.89s/it] 25%|██▌ | 3806/15000 [17:34:55<66:51:50, 21.50s/it] 25%|██▌ | 3807/15000 [17:35:10<60:39:56, 19.51s/it] 25%|██▌ | 3808/15000 [17:35:24<56:10:12, 18.07s/it] 25%|██▌ | 3809/15000 [17:35:39<53:01:41, 17.06s/it] 25%|██▌ | 3810/15000 [17:35:54<50:56:04, 16.39s/it] 25%|██▌ | 3811/15000 [17:36:09<49:17:19, 15.86s/it] 25%|██▌ | 3812/15000 [17:36:23<48:13:34, 15.52s/it] 25%8:46, 15.32s/it] 25%|██▌ | 3802/15000 [17:33:34<47:09:42, 15.16s/it] 25%|██▌ | 3803/15000 [17:33:48<46:42:05, 15.02s/it] 25%|██▌ | 3804/15000 [17:34:03<46:25:52, 14.93s/it] 25%|██▌ | 3805/15000 [17:34:18<46:15:30, 14.88s/it] 25%|██▌ | 3806/15000 [17:34:55<66:58:29, 21.54s/it] 25%|██▌ | 3807/15000 [17:35:10<60:37:43, 19.50s/it] 25%|██▌ | 3808/15000 [17:35:24<56:11:18, 18.07s/it] 25%|██▌ | 3809/15000 [17:35:39<53:06:10, 17.08s/it] 25%|██▌ | 3810/15000 [17:35:54<50:52:57, 16.37s/it] 25%|██▌ | 3811/15000 [17:36:09<49:17:45, 15.86s/it] 25%|██▌ | 3812/15000 [17:36:23<48:13:58, 15.52s/it] 25%|██▌ | 3813/15000 [17:36:38<47:25:15, 15.26s/it] 25%|██▌ | 3814/15000 [17:36:53<46:56:09, 15.11s/it] 25%|██▌ | 3815/15000 [17:37:07<46:35:11, 14.99s/it] 25%|██▌ | 3816/15000 [17:37:22<46:18:53, 14.91s/it] 25%|██▌ | 3817/150
{'loss': 0.8627, 'learning_rate': 0.00017351463937072004, 'epoch': 0.73}
{'loss': 0.8627, 'learning_rate': 0.00017351463937072004, 'epoch': 0.73}
15.47s/it] 26%|██▌ | 3892/15000 [17:58:34<46:58:53, 15.23s/it] 26%|██▌ | 3893/15000 [17:58:49<46:31:47, 15.08s/it] 26%|██▌ | 3894/15000 [17:59:04<45:59:09, 14.91s/it] 26%|██▌ | 3895/15000 [17:59:18<45:48:16, 14.85s/it] 26%|██▌ | 3896/15000 [17:59:56<66:21:34, 21.51s/it] 26%|██▌ | 3897/15000 [18:00:10<59:56:58, 19.44s/it] 26%|██▌ | 3898/15000 [18:00:25<55:34:19, 18.02s/it] 26%|██▌ | 3899/15000 [18:00:39<52:24:04, 16.99s/it] 26%|██▌ | 3900/15000 [18:00:54<50:22:59, 16.34s/it] 26%|██▌ | 3900/15000 [18:00:54<50:22:59, 16.34s/it] 26%|██▌ | 3901/15000 [18:01:09<48:56:42, 15.88s/it] 26%|██▌ | 3902/15000 [18:01:24<47:44:41, 15.49s/it] 26%|██▌ | 3903/15000 [18:01:38<46:53:08, 15.21s/it] 26%|██▌ | 3904/15000 [18:01:53<46:20:13, 15.03s/it] 26%|██▌ | 3905/15000 [18:02:0715.48s/it] 26%|██▌ | 3892/15000 [17:58:35<46:58:55, 15.23s/it] 26%|██▌ | 3893/15000 [17:58:49<46:31:29, 15.08s/it] 26%|██▌ | 3894/15000 [17:59:04<46:06:17, 14.94s/it] 26%|██▌ | 3895/15000 [17:59:19<45:49:41, 14.86s/it] 26%|██▌ | 3896/15000 [17:59:55<66:13:10, 21.47s/it] 26%|██▌ | 3897/15000 [18:00:10<59:57:49, 19.44s/it] 26%|██▌ | 3898/15000 [18:00:25<55:34:17, 18.02s/it] 26%|██▌ | 3899/15000 [18:00:39<52:21:07, 16.98s/it] 26%|██▌ | 3900/15000 [18:00:54<50:17:01, 16.31s/it] 26%|██▌ | 3900/15000 [18:00:54<50:17:01, 16.31s/it] 26%|██▌ | 3901/15000 [18:01:09<48:56:11, 15.87s/it] 26%|██▌ | 3902/15000 [18:01:24<47:50:21, 15.52s/it] 26%|██▌ | 3903/15000 [18:01:38<46:55:21, 15.22s/it] 26%|██▌ | 3904/15000 [18:01:53<46:21:56, 15.04s/it] 26%|██▌ | 3905/15000 [18:02:08 | 3896/15000 [17:59:55<66:16:20, 21.49s/it] 26%|██▌ | 3897/15000 [18:00:10<59:53:56, 19.42s/it] 26%|██▌ | 3898/15000 [18:00:25<55:30:03, 18.00s/it] 26%|██▌ | 3899/15000 [18:00:39<52:28:58, 17.02s/it] 26%|██▌ | 3900/15000 [18:00:54<50:16:10, 16.30s/it] 26%|██▌ | 3900/15000 [18:00:54<50:16:10, 16.30s/it] 26%|██▌ | 3901/15000 [18:01:09<48:53:14, 15.86s/it] 26%|██▌ | 3902/15000 [18:01:24<47:45:26, 15.49s/it] 26%|██▌ | 3903/15000 [18:01:38<47:00:11, 15.25s/it] 26%|██▌ | 3904/15000 [18:01:53<46:23:08, 15.05s/it] 26%|██▌ | 3905/15000 [18:02:07<45:57:12, 14.91s/it] 26%|██▌ | 3906/15000 [18:02:22<45:42:10, 14.83s/it] 26%|██▌ | 3907/15000 [18:02:59<65:51:53, 21.38s/it] 26%|██▌ | 3908/15000 [18:03:13<59:36:22, 19.35s/it] 26%|██▌ | 3909/15000 [18:03:28<55:13:29, 17.93s/it] 26%|<7C><45:57:41, 14.91s/it] 26%|██▌ | 3906/15000 [18:02:22<45:40:33, 14.82s/it] 26%|██▌ | 3907/15000 [18:02:59<65:51:45, 21.37s/it] 26%|██▌ | 3908/15000 [18:03:13<59:38:47, 19.36s/it] 26%|██▌ | 3909/15000 [18:03:28<55:16:23, 17.94s/it] 26%|██▌ | 3910/15000 [18:03:43<52:16:04, 16.97s/it] 26%|██▌ | 3911/15000 [18:03:57<50:03:15, 16.25s/it] 26%|██▌ | 3912/15000 [18:04:12<48:41:46, 15.81s/it] 26%|██▌ | 3913/15000 [18:04:27<47:39:02, 15.47s/it] 26%|██▌ | 3914/15000 [18:04:42<47:01:18, 15.27s/it] 26%|██▌ | 3915/15000 [18:04:56<46:25:50, 15.08s/it] 26%|██▌ | 3916/15000 [18:05:11<45:58:24, 14.93s/it] 26%|██▌ | 3917/15000 [18:05:26<45:49:40, 14.89s/it] 26%|██▌ | 3918/15000 [18:06:03<66:16:40, 21.53s/it] 26%|██▌ | 3919/15000 [18:06:17<59:56:51, 19.48s/it] 26%|██▌ | 3920/15000 [18:06:32<55:29:56, 18.03s/it] 26%|██▌ | 392
{'loss': 0.8614, 'learning_rate': 0.000172033897852734, 'epoch': 0.75}
{'loss': 0.8614, 'learning_rate': 0.000172033897852734, 'epoch': 0.75}
.99s/it] 27%|██▋ | 3989/15000 [18:25:41<52:00:23, 17.00s/it] 27%|██▋ | 3990/15000 [18:25:55<49:51:42, 16.30s/it] 27%|██▋ | 3991/15000 [18:26:10<48:15:22, 15.78s/it] 27%|██▋ | 3992/15000 [18:26:25<47:14:15, 15.45s/it] 27%|██▋ | 3993/15000 [18:26:39<46:27:53, 15.20s/it] 27%|██▋ | 3994/15000 [18:26:54<46:03:57, 15.07s/it] 27%|██▋ | 3995/15000 [18:27:09<45:44:00, 14.96s/it] 27%|██▋ | 3996/15000 [18:27:23<45:27:31, 14.87s/it] 27%|██▋ | 3997/15000 [18:28:00<65:27:57, 21.42s/it] 27%|██▋ | 3998/15000 [18:28:15<59:17:37, 19.40s/it] 27%|██▋ | 3999/15000 [18:28:30<55:00:35, 18.00s/it] 27%|██▋ | 4000/15000 [18:28:44<51:52:39, 16.98s/it] 27%|██▋ | 4000/15000 [18:28:44<51:52:39, 16.98s/it]Saving model checkpoint to /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-4000
tokenizer config file saved in /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-4000/tokenizer_config.json
Special tokens file saved in /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-4000/special_tokens_map.json
<EFBFBD><EFBFBD> | 4000/15000 [18:28:44<51:58:11, 17.01s/it] 27%|██▋ | 4000/15000 [18:28:44<51:58:11, 17.01s/it] 27%|██▋ | 4001/15000 [18:29:04<53:58:39, 17.67s/it] 27%|██▋ | 4002/15000 [18:29:18<51:20:41, 16.81s/it] 27%|██▋ | 4003/15000 [18:29:33<49:18:54, 16.14s/it] 27%|██▋ | 4004/15000 [18:29:48<48:01:54, 15.73s/it] 27%|██▋ | 4005/15000 [18:30:02<47:10:40, 15.45s/it] 27%|██▋ | 4006/15000 [18:30:17<46:19:23, 15.17s/it] 27%|██▋ | 4007/15000 [18:30:32<45:45:02, 14.98s/it] 27%|██▋ | 4008/15000 [18:30:46<45:34:20, 14.93s/it] 27%|██▋ | 4009/15000 [18:31:23<65:35:17, 21.48s/it] 27%|██▋ | 4010/15000 [18:31:38<59:14:34, 19.41s/it] 27%|██▋ | 4011/15000 [18:31:52<55:00:14, 18.02s/it] 27%|██▋ | 4012/15000 [18:32:07<51:51:07, 16.99s/it] 27%|██▋ | 4013/15000 [18:32:22<49:46:29, 16.31s/it] <20><> | 4000/15000 [18:28:44<51:51:45, 16.97s/it] 27%|██▋ | 4000/15000 [18:28:44<51:51:45, 16.97s/it] 27%|██▋ | 4001/15000 [18:29:03<53:57:33, 17.66s/it] 27%|██▋ | 4002/15000 [18:29:18<51:18:58, 16.80s/it] 27%|██▋ | 4003/15000 [18:29:33<49:18:26, 16.14s/it] 27%|██▋ | 4004/15000 [18:29:48<48:03:48, 15.74s/it] 27%|██▋ | 4005/15000 [18:30:02<47:07:42, 15.43s/it] 27%|██▋ | 4006/15000 [18:30:17<46:19:48, 15.17s/it] 27%|██▋ | 4007/15000 [18:30:31<45:45:02, 14.98s/it] 27%|██▋ | 4008/15000 [18:30:46<45:30:08, 14.90s/it] 27%|██▋ | 4009/15000 [18:31:23<65:37:18, 21.49s/it] 27%|██▋ | 4010/15000 [18:31:38<59:16:01, 19.41s/it] 27%|██▋ | 4011/15000 [18:31:52<54:56:25, 18.00s/it] 27%|██▋ | 4012/15000 [18:32:07<51:58:30, 17.03s/it] 27%|██▋ | 4013/15000 [18:32:22<49:44:23, 16.30s/it] 27%|██▋ | 4001/15000 [18:29:04<54:07:52, 17.72s/it] 27%|██▋ | 4002/15000 [18:29:18<51:20:15, 16.80s/it] 27%|██▋ | 4003/15000 [18:29:33<49:23:27, 16.17s/it] 27%|██▋ | 4004/15000 [18:29:48<48:02:34, 15.73s/it] 27%|██▋ | 4005/15000 [18:30:02<46:58:56, 15.38s/it] 27%|██▋ | 4006/15000 [18:30:17<46:14:57, 15.14s/it] 27%|██▋ | 4007/15000 [18:30:32<45:50:34, 15.01s/it] 27%|██▋ | 4008/15000 [18:30:46<45:32:56, 14.92s/it] 27%|██▋ | 4009/15000 [18:31:23<65:30:43, 21.46s/it] 27%|██▋ | 4010/15000 [18:31:38<59:22:01, 19.45s/it] 27%|██▋ | 4011/15000 [18:31:52<54:56:11, 18.00s/it] 27%|██▋ | 4012/15000 [18:32:07<51:57:11, 17.02s/it] 27%|██▋ | 4013/15000 [18:32:22<49:43:13, 16.29s/it] 27%|██▋ | 4014/15000 [18:32:36<48:08:32, 15.78s/it] 27%|██▋ | 4015/15000 [18:32:51<47:06:48, 15.44s/it] 27%|██▋ | 4016/15000 [18:33:06<46:227%|██▋ | 4014/15000 [18:32:36<48:09:55, 15.78s/it] 27%|██▋ | 4015/15000 [18:32:51<47:10:30, 15.46s/it] 27%|██▋ | 4016/15000 [18:33:06<46:21:39, 15.19s/it] 27%|██▋ | 4017/15000 [18:33:20<45:55:11, 15.05s/it] 27%|██▋ | 4018/15000 [18:33:35<45:35:15, 14.94s/it] 27%|██▋ | 4019/15000 [18:33:50<45:12:42, 14.82s/it] 27%|██▋ | 4020/15000 [18:34:26<65:24:44, 21.45s/it] 27%|██▋ | 4021/15000 [18:34:41<59:17:15, 19.44s/it] 27%|██▋ | 4022/15000 [18:34:56<54:57:21, 18.02s/it] 27%|██▋ | 4023/15000 [18:35:11<51:51:08, 17.01s/it] 27%|██▋ | 4024/15000 [18:35:25<49:49:59, 16.34s/it] 27%|██▋ | 4025/15000 [18:35:40<48:20:28, 15.86s/it] 27%|██▋ | 4026/15000 [18:35:55<47:13:48, 15.49s/it] 27%|██▋ | 4027/15000 [18:36:10<46:36:58, 15.29s/it] 27%|██▋ | 4028/15000 [18:36:24<46:04:38, 15.12s/it] 27%|██▋ | 4029/15000 [18:36:39<45:31
{'loss': 0.8638, 'learning_rate': 0.0001705195753210446, 'epoch': 0.77}
{'loss': 0.8638, 'learning_rate': 0.0001705195753210446, 'epoch': 0.77}
5, 16.29s/it] 27%|██▋ | 4093/15000 [18:54:31<47:55:21, 15.82s/it] 27%|██▋ | 4094/15000 [18:54:46<47:02:40, 15.53s/it] 27%|██▋ | 4095/15000 [18:55:01<46:23:07, 15.31s/it] 27%|██▋ | 4096/15000 [18:55:16<45:54:42, 15.16s/it] 27%|██▋ | 4097/15000 [18:55:31<45:37:03, 15.06s/it] 27%|██▋ | 4098/15000 [18:55:46<45:26:14, 15.00s/it] 27%|██▋ | 4099/15000 [18:56:22<65:00:44, 21.47s/it] 27%|██▋ | 4100/15000 [18:56:37<58:56:33, 19.47s/it] 27%|██▋ | 4100/15000 [18:56:37<58:56:33, 19.47s/it] 27%|██▋ | 4101/15000 [18:56:52<54:52:00, 18.12s/it] 27%|██▋ | 4102/15000 [18:57:07<51:54:43, 17.15s/it] 27%|██▋ | 4103/15000 [18:57:22<49:43:58, 16.43s/it] 27%|██▋ | 4104/15000 [18:57:36<48:07:33, 15.90s/it] 27%|██▋ | 4105/15000 [18:57:51<47:03:47, 15.55s/it] 27%|██▋ | 4106/15000 [18:582, 16.31s/it] 27%|██▋ | 4093/15000 [18:54:31<47:57:44, 15.83s/it] 27%|██▋ | 4094/15000 [18:54:46<47:01:56, 15.53s/it] 27%|██▋ | 4095/15000 [18:55:01<46:20:29, 15.30s/it] 27%|██▋ | 4096/15000 [18:55:16<45:52:35, 15.15s/it] 27%|██▋ | 4097/15000 [18:55:31<45:36:04, 15.06s/it] 27%|██▋ | 4098/15000 [18:55:46<45:25:01, 15.00s/it] 27%|██▋ | 4099/15000 [18:56:22<65:03:12, 21.48s/it] 27%|██▋ | 4100/15000 [18:56:37<58:57:15, 19.47s/it] 27%|██▋ | 4100/15000 [18:56:37<58:57:15, 19.47s/it] 27%|██▋ | 4101/15000 [18:56:52<54:47:40, 18.10s/it] 27%|██▋ | 4102/15000 [18:57:07<51:55:38, 17.15s/it] 27%|██▋ | 4103/15000 [18:57:21<49:39:03, 16.40s/it] 27%|██▋ | 4104/15000 [18:57:36<48:14:41, 15.94s/it] 27%|██▋ | 4105/15000 [18:57:51<47:02:49, 15.55s/it] 27%|██▋ | 4106/15000 [18:58 [18:55:01<46:16:40, 15.28s/it] 27%|██▋ | 4096/15000 [18:55:16<45:53:54, 15.15s/it] 27%|██▋ | 4097/15000 [18:55:31<45:36:45, 15.06s/it] 27%|██▋ | 4098/15000 [18:55:45<45:21:42, 14.98s/it] 27%|██▋ | 4099/15000 [18:56:22<65:07:22, 21.51s/it] 27%|██▋ | 4100/15000 [18:56:37<58:55:28, 19.46s/it] 27%|██▋ | 4100/15000 [18:56:37<58:55:28, 19.46s/it] 27%|██▋ | 4101/15000 [18:56:52<54:55:30, 18.14s/it] 27%|██▋ | 4102/15000 [18:57:07<51:51:42, 17.13s/it] 27%|██▋ | 4103/15000 [18:57:21<49:39:55, 16.41s/it] 27%|██▋ | 4104/15000 [18:57:36<48:10:57, 15.92s/it] 27%|██▋ | 4105/15000 [18:57:51<47:07:52, 15.57s/it] 27%|██▋ | 4106/15000 [18:58:06<46:21:45, 15.32s/it] 27%|██▋ | 4107/15000 [18:58:20<45:46:54, 15.13s/it] 27%|██▋ | 4108/15000 [18:58:35<45:24:13, 15.01s/it] 27%|██▋ |:06<46:21:26, 15.32s/it] 27%|██▋ | 4107/15000 [18:58:20<45:47:02, 15.13s/it] 27%|██▋ | 4108/15000 [18:58:35<45:23:13, 15.00s/it] 27%|██▋ | 4109/15000 [18:58:50<45:10:23, 14.93s/it] 27%|██▋ | 4110/15000 [18:59:28<66:11:19, 21.88s/it] 27%|██▋ | 4111/15000 [18:59:43<59:44:09, 19.75s/it] 27%|██▋ | 4112/15000 [18:59:57<55:10:39, 18.24s/it] 27%|██▋ | 4113/15000 [19:00:12<51:53:08, 17.16s/it] 27%|██▋ | 4114/15000 [19:00:27<49:41:18, 16.43s/it] 27%|██▋ | 4115/15000 [19:00:41<47:59:12, 15.87s/it] 27%|██▋ | 4116/15000 [19:00:56<46:55:06, 15.52s/it] 27%|██▋ | 4117/15000 [19:01:11<46:08:40, 15.26s/it] 27%|██▋ | 4118/15000 [19:01:26<45:39:12, 15.10s/it] 27%|██▋ | 4119/15000 [19:01:40<45:22:14, 15.01s/it] 27%|██▋ | 4120/15000 [19:01:55<45:04:40, 14.92s/it] 27%|██▋ | 4121/15000 [19:02:32<65:04:28, 21.53s/it] 27%|██▋ |
{'loss': 0.8605, 'learning_rate': 0.00016897237772781044, 'epoch': 0.79}
{'loss': 0.8605, 'learning_rate': 0.00016897237772781044, 'epoch': 0.79}
85/15000 [19:20:01<45:42:02, 15.21s/it] 28%|██▊ | 4186/15000 [19:20:16<45:17:55, 15.08s/it] 28%|██▊ | 4187/15000 [19:20:31<44:48:50, 14.92s/it] 28%|██▊ | 4188/15000 [19:20:45<44:34:06, 14.84s/it] 28%|██▊ | 4189/15000 [19:21:22<64:19:38, 21.42s/it] 28%|██▊ | 4190/15000 [19:21:37<58:18:21, 19.42s/it] 28%|██▊ | 4191/15000 [19:21:51<53:59:47, 17.98s/it] 28%|██▊ | 4192/15000 [19:22:06<50:56:47, 16.97s/it] 28%|██▊ | 4193/15000 [19:22:21<48:52:53, 16.28s/it] 28%|██▊ | 4194/15000 [19:22:35<47:28:34, 15.82s/it] 28%|██▊ | 4195/15000 [19:22:50<46:18:20, 15.43s/it] 28%|██▊ | 4196/15000 [19:23:05<45:32:18, 15.17s/it] 28%|██▊ | 4197/15000 [19:23:19<45:05:50, 15.03s/it] 28%|██▊ | 4198/15000 [19:23:34<44:40:09, 14.89s/it] 28%|██▊ | 4199/15000 [19:23:49<44:31:03, 14.84s/it] 28%|██▊ | 4200/15000 [19:24:25<64:09:57, 21.39s/it] 85/15000 [19:20:01<45:43:26, 15.22s/it] 28%|██▊ | 4186/15000 [19:20:16<45:12:56, 15.05s/it] 28%|██▊ | 4187/15000 [19:20:31<44:48:49, 14.92s/it] 28%|██▊ | 4188/15000 [19:20:45<44:40:06, 14.87s/it] 28%|██▊ | 4189/15000 [19:21:22<64:21:39, 21.43s/it] 28%|██▊ | 4190/15000 [19:21:37<58:12:58, 19.39s/it] 28%|██▊ | 4191/15000 [19:21:51<54:01:10, 17.99s/it] 28%|██▊ | 4192/15000 [19:22:06<50:57:39, 16.97s/it] 28%|██▊ | 4193/15000 [19:22:21<48:51:31, 16.28s/it] 28%|██▊ | 4194/15000 [19:22:35<47:28:46, 15.82s/it] 28%|██▊ | 4195/15000 [19:22:50<46:25:31, 15.47s/it] 28%|██▊ | 4196/15000 [19:23:05<45:36:04, 15.19s/it] 28%|██▊ | 4197/15000 [19:23:19<45:06:55, 15.03s/it] 28%|██▊ | 4198/15000 [19:23:34<44:43:24, 14.91s/it] 28%|██▊ | 4199/15000 [19:23:49<44:28:00, 14.82s/it] 28%|██▊ | 4200/15000 [19:24:25<64:06:04, 21.37s/it] <20>█▊ | 4188/15000 [19:20:45<44:34:36, 14.84s/it] 28%|██▊ | 4189/15000 [19:21:22<64:22:13, 21.43s/it] 28%|██▊ | 4190/15000 [19:21:37<58:18:57, 19.42s/it] 28%|██▊ | 4191/15000 [19:21:51<54:00:10, 17.99s/it] 28%|██▊ | 4192/15000 [19:22:06<51:00:47, 16.99s/it] 28%|██▊ | 4193/15000 [19:22:21<48:53:39, 16.29s/it] 28%|██▊ | 4194/15000 [19:22:35<47:21:55, 15.78s/it] 28%|██▊ | 4195/15000 [19:22:50<46:18:07, 15.43s/it] 28%|██▊ | 4196/15000 [19:23:05<45:34:07, 15.18s/it] 28%|██▊ | 4197/15000 [19:23:19<45:05:22, 15.03s/it] 28%|██▊ | 4198/15000 [19:23:34<44:42:07, 14.90s/it] 28%|██▊ | 4199/15000 [19:23:48<44:30:58, 14.84s/it] 28%|██▊ | 4200/15000 [19:24:25<64:16:43, 21.43s/it] 28%|██▊ | 4200/15000 [19:24:25<64:16:43, 21.43s/it] 28%|██▊ | 4201/15000 [19:24:40<58:17:46, 19.43s/ 28%|██▊ | 4200/15000 [19:24:25<64:09:57, 21.39s/it] 28%|██▊ | 4201/15000 [19:24:40<58:16:25, 19.43s/it] 28%|██▊ | 4202/15000 [19:24:55<54:03:44, 18.02s/it] 28%|██▊ | 4203/15000 [19:25:09<50:59:58, 17.00s/it] 28%|██▊ | 4204/15000 [19:25:24<48:53:05, 16.30s/it] 28%|██▊ | 4205/15000 [19:25:39<47:27:06, 15.82s/it] 28%|██▊ | 4206/15000 [19:25:53<46:23:13, 15.47s/it] 28%|██▊ | 4207/15000 [19:26:08<45:40:10, 15.23s/it] 28%|██▊ | 4208/15000 [19:26:23<45:18:20, 15.11s/it] 28%|██▊ | 4209/15000 [19:26:38<44:52:37, 14.97s/it] 28%|██▊ | 4210/15000 [19:26:52<44:45:49, 14.94s/it] 28%|██▊ | 4211/15000 [19:27:07<44:28:28, 14.84s/it] 28%|██▊ | 4212/15000 [19:27:44<64:13:44, 21.43s/it] 28%|██▊ | 4213/15000 [19:27:59<58:15:03, 19.44s/it] 28%|██▊ | 4214/15000 [19:28:13<53:59:49, 18.02s/i
{'loss': 0.858, 'learning_rate': 0.00016739302635100108, 'epoch': 0.8}
{'loss': 0.858, 'learning_rate': 0.00016739302635100108, 'epoch': 0.8}
1:51, 18.00s/it] 29%|██▊ | 4294/15000 [19:50:28<50:29:57, 16.98s/it] 29%|██▊ | 4295/15000 [19:50:42<48:19:44, 16.25s/it] 29%|██▊ | 4296/15000 [19:50:57<46:57:58, 15.80s/it] 29%|██▊ | 4297/15000 [19:51:12<45:55:59, 15.45s/it] 29%|██▊ | 4298/15000 [19:51:27<45:22:52, 15.27s/it] 29%|██▊ | 4299/15000 [19:51:41<44:41:18, 15.03s/it] 29%|██▊ | 4300/15000 [19:51:56<44:20:48, 14.92s/it] 29%|██▊ | 4300/15000 [19:51:56<44:20:48, 14.92s/it] 29%|██▊ | 4301/15000 [19:52:10<44:09:13, 14.86s/it] 29%|██▊ | 4302/15000 [19:52:48<64:00:08, 21.54s/it] 29%|██▊ | 4303/15000 [19:53:02<57:52:24, 19.48s/it] 29%|██▊ | 4304/15000 [19:53:17<53:38:43, 18.06s/it] 29%|██▊ | 4305/15000 [19:53:32<50:37:13, 17.04s/it] 29%|██▊ | 4306/15000 [19:53:46<48:33:58, 16.35s/it] 29%|██▊ | 4307/15000 [198:46, 17.98s/it] 29%|██▊ | 4294/15000 [19:50:28<50:29:43, 16.98s/it] 29%|██▊ | 4295/15000 [19:50:42<48:23:46, 16.28s/it] 29%|██▊ | 4296/15000 [19:50:57<46:56:41, 15.79s/it] 29%|██▊ | 4297/15000 [19:51:12<45:55:14, 15.45s/it] 29%|██▊ | 4298/15000 [19:51:26<45:15:01, 15.22s/it] 29%|██▊ | 4299/15000 [19:51:41<44:43:19, 15.05s/it] 29%|██▊ | 4300/15000 [19:51:56<44:19:19, 14.91s/it] 29%|██▊ | 4300/15000 [19:51:56<44:19:19, 14.91s/it] 29%|██▊ | 4301/15000 [19:52:11<44:17:18, 14.90s/it] 29%|██▊ | 4302/15000 [19:52:48<63:57:46, 21.52s/it] 29%|██▊ | 4303/15000 [19:53:02<57:49:05, 19.46s/it] 29%|██▊ | 4304/15000 [19:53:17<53:38:41, 18.06s/it] 29%|██▊ | 4305/15000 [19:53:32<50:34:59, 17.03s/it] 29%|██▊ | 4306/15000 [19:53:46<48:32:56, 16.34s/it] 29%|██▊ | 4307/15000 [19000 [19:50:57<47:01:07, 15.81s/it] 29%|██▊ | 4297/15000 [19:51:12<45:58:24, 15.46s/it] 29%|██▊ | 4298/15000 [19:51:26<45:08:28, 15.18s/it] 29%|██▊ | 4299/15000 [19:51:41<44:43:49, 15.05s/it] 29%|██▊ | 4300/15000 [19:51:56<44:22:39, 14.93s/it] 29%|██▊ | 4300/15000 [19:51:56<44:22:39, 14.93s/it] 29%|██▊ | 4301/15000 [19:52:10<44:12:09, 14.87s/it] 29%|██▊ | 4302/15000 [19:52:48<64:00:50, 21.54s/it] 29%|██▊ | 4303/15000 [19:53:02<57:52:32, 19.48s/it] 29%|██▊ | 4304/15000 [19:53:17<53:38:30, 18.05s/it] 29%|██▊ | 4305/15000 [19:53:32<50:38:13, 17.04s/it] 29%|██▊ | 4306/15000 [19:53:46<48:32:38, 16.34s/it] 29%|██▊ | 4307/15000 [19:54:01<46:58:52, 15.82s/it] 29%|██▊ | 4308/15000 [19:54:16<45:57:57, 15.48s/it] 29%|██▊ | 4309/15000 [19:54:30<45:16:13, 15.24s/it] 29%|██▊ :54:01<47:08:54, 15.87s/it] 29%|██▊ | 4308/15000 [19:54:16<45:55:52, 15.47s/it] 29%|██▊ | 4309/15000 [19:54:30<45:16:26, 15.25s/it] 29%|██▊ | 4310/15000 [19:54:45<44:44:30, 15.07s/it] 29%|██▊ | 4311/15000 [19:55:00<44:22:37, 14.95s/it] 29%|██▊ | 4312/15000 [19:55:14<44:13:36, 14.90s/it] 29%|██▉ | 4313/15000 [19:55:51<63:47:53, 21.49s/it] 29%|██▉ | 4314/15000 [19:56:06<57:44:48, 19.45s/it] 29%|██▉ | 4315/15000 [19:56:21<53:26:03, 18.00s/it] 29%|██▉ | 4316/15000 [19:56:35<50:28:18, 17.01s/it] 29%|██▉ | 4317/15000 [19:56:50<48:19:44, 16.29s/it] 29%|██▉ | 4318/15000 [19:57:05<46:50:58, 15.79s/it] 29%|██▉ | 4319/15000 [19:57:19<45:51:59, 15.46s/it] 29%|██▉ | 4320/15000 [19:57:34<45:04:12, 15.19s/it] 29%|██▉ | 4321/15000 [19:57:48<44:31:17, 15.01s/it] 29%|██▉ | 4322/15000 [19:58:03<44:07:41, 14.88s/it] 29%|██▉
{'loss': 0.8563, 'learning_rate': 0.00016578225745814907, 'epoch': 0.82}
4386/15000 [20:15:58<46:58:16, 15.93s/it] 29%|██▉ | 4387/15000 [20:16:13<45:53:44, 15.57s/it] 29%|██▉ | 4388/15000 [20:16:27<45:14:38, 15.35s/it] 29%|██▉ | 4389/15000 [20:16:42<44:36:44, 15.14s/it] 29%|██▉ | 4390/15000 [20:16:57<44:15:03, 15.01s/it] 29%|██▉ | 4391/15000 [20:17:12<44:05:27, 14.96s/it] 29%|██▉ | 4392/15000 [20:17:49<63:49:31, 21.66s/it] 29%|██▉ | 4393/15000 [20:18:04<57:37:55, 19.56s/it] 29%|██▉ | 4394/15000 [20:18:18<53:22:56, 18.12s/it] 29%|██▉ | 4395/15000 [20:18:33<50:26:20, 17.12s/it] 29%|██▉ | 4396/15000 [20:18:48<48:17:15, 16.39s/it] 29%|██▉ | 4397/15000 [20:19:02<46:43:26, 15.86s/it] 29%|██▉ | 4398/15000 [20:19:17<45:41:05, 15.51s/it] 29%|██▉ | 4399/15000 [20:19:32<44:58:23, 15.27s/it] 29%|██▉ | 4400/15000 [20:19:47<44:30:23, 15.12s/it] 29%|██{'loss': 0.8563, 'learning_rate': 0.00016578225745814907, 'epoch': 0.82}
4386/15000 [20:15:58<46:55:35, 15.92s/it] 29%|██▉ | 4387/15000 [20:16:13<45:55:52, 15.58s/it] 29%|██▉ | 4388/15000 [20:16:27<45:11:49, 15.33s/it] 29%|██▉ | 4389/15000 [20:16:42<44:40:30, 15.16s/it] 29%|██▉ | 4390/15000 [20:16:57<44:15:03, 15.01s/it] 29%|██▉ | 4391/15000 [20:17:12<44:02:35, 14.95s/it] 29%|██▉ | 4392/15000 [20:17:49<63:49:08, 21.66s/it] 29%|██▉ | 4393/15000 [20:18:04<57:40:03, 19.57s/it] 29%|██▉ | 4394/15000 [20:18:18<53:20:47, 18.11s/it] 29%|██▉ | 4395/15000 [20:18:33<50:28:02, 17.13s/it] 29%|██▉ | 4396/15000 [20:18:48<48:19:27, 16.41s/it] 29%|██▉ | 4397/15000 [20:19:03<46:47:31, 15.89s/it] 29%|██▉ | 4398/15000 [20:19:17<45:38:31, 15.50s/it] 29%|██▉ | 4399/15000 [20:19:32<44:59:48, 15.28s/it] 29%|██▉ | 4400/15000 [20:19:47<44:32:39, 15.13s/it] 29%|██|██▉ | 4389/15000 [20:16:42<44:37:30, 15.14s/it] 29%|██▉ | 4390/15000 [20:16:57<44:13:27, 15.01s/it] 29%|██▉ | 4391/15000 [20:17:11<44:05:14, 14.96s/it] 29%|██▉ | 4392/15000 [20:17:49<63:47:26, 21.65s/it] 29%|██▉ | 4393/15000 [20:18:03<57:38:32, 19.56s/it] 29%|██▉ | 4394/15000 [20:18:18<53:23:56, 18.13s/it] 29%|██▉ | 4395/15000 [20:18:33<50:26:02, 17.12s/it] 29%|██▉ | 4396/15000 [20:18:48<48:15:19, 16.38s/it] 29%|██▉ | 4397/15000 [20:19:02<46:51:16, 15.91s/it] 29%|██▉ | 4398/15000 [20:19:17<45:41:28, 15.51s/it] 29%|██▉ | 4399/15000 [20:19:32<44:58:18, 15.27s/it] 29%|██▉ | 4400/15000 [20:19:47<44:31:30, 15.12s/it] 29%|██▉ | 4400/15000 [20:19:47<44:31:30, 15.12s/it] 29%|██▉ | 4401/15000 [20:20:02<44:25:23, 15.09s/it] 29%|██▉ | 4402/15000 [20:20:16<44:05:37, 14.9▉ | 4400/15000 [20:19:47<44:30:23, 15.12s/it] 29%|██▉ | 4401/15000 [20:20:02<44:26:56, 15.10s/it] 29%|██▉ | 4402/15000 [20:20:16<44:07:07, 14.99s/it] 29%|██▉ | 4403/15000 [20:20:31<43:52:12, 14.90s/it] 29%|██▉ | 4404/15000 [20:21:09<64:23:16, 21.88s/it] 29%|██▉ | 4405/15000 [20:21:24<58:10:58, 19.77s/it] 29%|██▉ | 4406/15000 [20:21:39<53:41:01, 18.24s/it] 29%|██▉ | 4407/15000 [20:21:53<50:26:23, 17.14s/it] 29%|██▉ | 4408/15000 [20:22:08<48:26:14, 16.46s/it] 29%|██▉ | 4409/15000 [20:22:23<46:47:39, 15.91s/it] 29%|██▉ | 4410/15000 [20:22:38<45:51:59, 15.59s/it] 29%|██▉ | 4411/15000 [20:22:52<45:03:59, 15.32s/it] 29%|██▉ | 4412/15000 [20:23:07<44:33:20, 15.15s/it] 29%|██▉ | 4413/15000 [20:23:22<44:14:46, 15.05s/it] 29%|██▉ | 4414/15000 [20:23:37<43:56:54, 14.95s/it] 29%|██▉ | 4415/15000 [20:24:13<63:05:31, 21.46s▉ | 4400/15000 [20:19:47<44:32:39, 15.13s/it] 29%|██▉ | 4401/15000 [20:20:02<44:26:18, 15.09s/it] 29%|██▉ | 4402/15000 [20:20:16<44:03:22, 14.97s/it] 29%|██▉ | 4403/15000 [20:20:31<43:52:25, 14.90s/it] 29%|██▉ | 4404/15000 [20:21:09<64:20:06, 21.86s/it] 29%|██▉ | 4405/15000 [20:21:24<58:07:47, 19.75s/it] 29%|██▉ | 4406/15000 [20:21:39<53:35:02, 18.21s/it] 29%|██▉ | 4407/15000 [20:21:53<50:30:42, 17.17s/it] 29%|██▉ | 4408/15000 [20:22:08<48:26:33, 16.46s/it] 29%|██▉ | 4409/15000 [20:22:23<46:52:26, 15.93s/it] 29%|██▉ | 4410/15000 [20:22:38<45:54:47, 15.61s/it] 29%|██▉ | 4411/15000 [20:22:52<45:06:28, 15.34s/it] 29%|██▉ | 4412/15000 [20:23:07<44:32:25, 15.14s/it] 29%|██▉ | 4413/15000 [20:23:22<44:09:49, 15.02s/it] 29%|██▉ | 4414/15000 [20:23:37<43:57:50, 14.95s/it] 29%|██▉ | 4415/15000 [20:24:13<63:05:32, 21.46
{'loss': 0.8562, 'learning_rate': 0.000164140821963114, 'epoch': 0.84}
{'loss': 0.8562, 'learning_rate': 0.000164140821963114, 'epoch': 0.84}
2:22:38, 21.37s/it] 30%|██▉ | 4495/15000 [20:46:20<56:31:49, 19.37s/it] 30%|██▉ | 4496/15000 [20:46:35<52:26:08, 17.97s/it] 30%|██▉ | 4497/15000 [20:46:50<49:34:00, 16.99s/it] 30%|██▉ | 4498/15000 [20:47:04<47:34:46, 16.31s/it] 30%|██▉ | 4499/15000 [20:47:19<46:10:11, 15.83s/it] 30%|███ | 4500/15000 [20:47:34<45:03:37, 15.45s/it] 30%|███ | 4500/15000 [20:47:34<45:03:37, 15.45s/it] 30%|███ | 4501/15000 [20:47:48<44:28:48, 15.25s/it] 30%|███ | 4502/15000 [20:48:03<43:56:38, 15.07s/it] 30%|███ | 4503/15000 [20:48:18<43:38:53, 14.97s/it] 30%|███ | 4504/15000 [20:48:33<43:25:50, 14.90s/it] 30%|███ | 4505/15000 [20:49:09<62:43:34, 21.52s/it] 30%|███ | 4506/15000 [20:49:24<56:49:07, 19.49s/it] 30%|███ | 4507/15000 [20:49:39<52:36:41, 18.05s/it] 30%|███ | 4508/15000 2:22:33, 21.37s/it] 30%|██▉ | 4495/15000 [20:46:20<56:29:36, 19.36s/it] 30%|██▉ | 4496/15000 [20:46:35<52:27:05, 17.98s/it] 30%|██▉ | 4497/15000 [20:46:50<49:35:23, 17.00s/it] 30%|██▉ | 4498/15000 [20:47:04<47:33:03, 16.30s/it] 30%|██▉ | 4499/15000 [20:47:19<46:09:13, 15.82s/it] 30%|███ | 4500/15000 [20:47:34<45:06:47, 15.47s/it] 30%|███ | 4500/15000 [20:47:34<45:06:47, 15.47s/it] 30%|███ | 4501/15000 [20:47:48<44:33:11, 15.28s/it] 30%|███ | 4502/15000 [20:48:03<43:55:45, 15.06s/it] 30%|███ | 4503/15000 [20:48:18<43:36:38, 14.96s/it] 30%|███ | 4504/15000 [20:48:33<43:24:53, 14.89s/it] 30%|███ | 4505/15000 [20:49:10<62:45:06, 21.53s/it] 30%|███ | 4506/15000 [20:49:24<56:44:27, 19.47s/it] 30%|███ | 4507/15000 [20:49:39<52:41:01, 18.08s/it] 30%|███ | 4508/15000 /15000 [20:46:50<49:33:37, 16.99s/it] 30%|██▉ | 4498/15000 [20:47:04<47:33:26, 16.30s/it] 30%|██▉ | 4499/15000 [20:47:19<46:11:07, 15.83s/it] 30%|███ | 4500/15000 [20:47:34<45:07:12, 15.47s/it] 30%|███ | 4500/15000 [20:47:34<45:07:12, 15.47s/it] 30%|███ | 4501/15000 [20:47:48<44:24:12, 15.23s/it] 30%|███ | 4502/15000 [20:48:03<43:53:38, 15.05s/it] 30%|███ | 4503/15000 [20:48:18<43:35:52, 14.95s/it] 30%|███ | 4504/15000 [20:48:32<43:27:11, 14.90s/it] 30%|███ | 4505/15000 [20:49:09<62:43:40, 21.52s/it] 30%|███ | 4506/15000 [20:49:24<56:48:10, 19.49s/it] 30%|███ | 4507/15000 [20:49:39<52:41:15, 18.08s/it] 30%|███ | 4508/15000 [20:49:54<49:55:54, 17.13s/it] 30%|███ | 4509/15000 [20:50:08<47:45:02, 16.39s/it] 30%|███ | 4510/15000 [20:50:23<46:23:43, 15.92s/it] 30%|███ [20:49:54<49:53:19, 17.12s/it] 30%|███ | 4509/15000 [20:50:09<47:44:22, 16.38s/it] 30%|███ | 4510/15000 [20:50:23<46:21:39, 15.91s/it] 30%|███ | 4511/15000 [20:50:38<45:17:38, 15.55s/it] 30%|███ | 4512/15000 [20:50:53<44:39:07, 15.33s/it] 30%|███ | 4513/15000 [20:51:08<44:05:57, 15.14s/it] 30%|███ | 4514/15000 [20:51:22<43:48:23, 15.04s/it] 30%|███ | 4515/15000 [20:51:37<43:28:06, 14.92s/it] 30%|███ | 4516/15000 [20:52:14<62:48:06, 21.56s/it] 30%|███ | 4517/15000 [20:52:29<56:49:15, 19.51s/it] 30%|███ | 4518/15000 [20:52:44<52:39:32, 18.09s/it] 30%|███ | 4519/15000 [20:52:58<49:51:46, 17.13s/it] 30%|███ | 4520/15000 [20:53:13<47:55:14, 16.46s/it] 30%|███ | 4521/15000 [20:53:28<46:28:13, 15.96s/it] 30%|███ | 4522/15000 [20:53:43<45:19:26, 15.57s/it] 30%|███ | 4523/15000 [20:53:57<44:31:30, 15.30s/it] 30%|███
{'loss': 0.8548, 'learning_rate': 0.00016246948507601914, 'epoch': 0.86}
{'loss': 0.8548, 'learning_rate': 0.00016246948507601914, 'epoch': 0.86}
| 4587/15000 [21:11:52<49:02:42, 16.96s/it] 31%|███ | 4588/15000 [21:12:07<47:13:06, 16.33s/it] 31%|███ | 4589/15000 [21:12:22<45:51:52, 15.86s/it] 31%|███ | 4590/15000 [21:12:37<44:43:05, 15.46s/it] 31%|███ | 4591/15000 [21:12:51<44:09:06, 15.27s/it] 31%|███ | 4592/15000 [21:13:06<43:27:53, 15.03s/it] 31%|███ | 4593/15000 [21:13:21<43:17:06, 14.97s/it] 31%|███ | 4594/15000 [21:13:35<42:58:42, 14.87s/it] 31%|███ | 4595/15000 [21:14:12<62:01:39, 21.46s/it] 31%|███ | 4596/15000 [21:14:27<56:03:13, 19.40s/it] 31%|███ | 4597/15000 [21:14:42<52:00:01, 17.99s/it] 31%|███ | 4598/15000 [21:14:56<49:04:26, 16.98s/it] 31%|███ | 4599/15000 [21:15:11<46:59:21, 16.26s/it] 31%|███ | 4600/15000 [21:15:26<45:39:28, 15.80s/it] 31%|███ | 4600/15000 [21:15:26<45:39:28, 15.80s/it] 31%|█ | 4587/15000 [21:11:53<49:09:53, 17.00s/it] 31%|███ | 4588/15000 [21:12:07<47:02:18, 16.26s/it] 31%|███ | 4589/15000 [21:12:22<45:45:23, 15.82s/it] 31%|███ | 4590/15000 [21:12:37<44:44:30, 15.47s/it] 31%|███ | 4591/15000 [21:12:51<44:09:34, 15.27s/it] 31%|███ | 4592/15000 [21:13:06<43:32:51, 15.06s/it] 31%|███ | 4593/15000 [21:13:21<43:11:04, 14.94s/it] 31%|███ | 4594/15000 [21:13:35<42:53:35, 14.84s/it] 31%|███ | 4595/15000 [21:14:12<62:01:10, 21.46s/it] 31%|███ | 4596/15000 [21:14:27<56:11:12, 19.44s/it] 31%|███ | 4597/15000 [21:14:42<52:02:09, 18.01s/it] 31%|███ | 4598/15000 [21:14:56<49:02:06, 16.97s/it] 31%|███ | 4599/15000 [21:15:11<47:03:28, 16.29s/it] 31%|███ | 4600/15000 [21:15:25<45:36:39, 15.79s/it] 31%|███ | 4600/15000 [21:15:26<45:36:39, 15.79s/it] 31%|█31%|███ | 4590/15000 [21:12:37<44:49:01, 15.50s/it] 31%|███ | 4591/15000 [21:12:51<44:02:49, 15.23s/it] 31%|███ | 4592/15000 [21:13:06<43:33:07, 15.06s/it] 31%|███ | 4593/15000 [21:13:21<43:13:15, 14.95s/it] 31%|███ | 4594/15000 [21:13:35<42:55:07, 14.85s/it] 31%|███ | 4595/15000 [21:14:12<62:02:17, 21.46s/it] 31%|███ | 4596/15000 [21:14:27<56:08:03, 19.42s/it] 31%|███ | 4597/15000 [21:14:41<51:56:37, 17.98s/it] 31%|███ | 4598/15000 [21:14:56<49:02:48, 16.97s/it] 31%|███ | 4599/15000 [21:15:11<47:02:47, 16.28s/it] 31%|███ | 4600/15000 [21:15:25<45:40:49, 15.81s/it] 31%|███ | 4600/15000 [21:15:26<45:40:49, 15.81s/it] 31%|███ | 4601/15000 [21:15:40<44:52:31, 15.54s/it] 31%|███ | 4602/15000 [21:15:55<44:05:31, 15.27s/it] 31%|███ | 4603/15000 [21:16:10<43:31:52, 1██ | 4601/15000 [21:15:40<44:55:22, 15.55s/it] 31%|███ | 4602/15000 [21:15:55<44:06:40, 15.27s/it] 31%|███ | 4603/15000 [21:16:10<43:34:51, 15.09s/it] 31%|███ | 4604/15000 [21:16:24<43:10:05, 14.95s/it] 31%|███ | 4605/15000 [21:16:39<42:52:01, 14.85s/it] 31%|███ | 4606/15000 [21:16:54<42:40:48, 14.78s/it] 31%|███ | 4607/15000 [21:17:30<61:32:04, 21.31s/it] 31%|███ | 4608/15000 [21:17:45<55:42:08, 19.30s/it] 31%|███ | 4609/15000 [21:17:59<51:39:32, 17.90s/it] 31%|███ | 4610/15000 [21:18:14<48:51:04, 16.93s/it] 31%|███ | 4611/15000 [21:18:29<46:52:58, 16.25s/it] 31%|███ | 4612/15000 [21:18:44<45:37:02, 15.81s/it] 31%|███ | 4613/15000 [21:18:58<44:35:58, 15.46s/it] 31%|███ | 4614/15000 [21:19:13<43:47:44, 15.18s/it] 31%|███ | 4615/15000 [21:19:27<43:25:03, 15.05s/it] 31%|███ | 4616/15000 [21:19:42<43:01:24, 14
{'loss': 0.8519, 'learning_rate': 0.0001607690259465229, 'epoch': 0.88}
{'loss': 0.8519, 'learning_rate': 0.0001607690259465229, 'epoch': 0.88}
5/15000 [21:41:40<43:01:33, 15.03s/it] 31%|███▏ | 4696/15000 [21:41:55<42:42:53, 14.92s/it] 31%|███▏ | 4697/15000 [21:42:32<61:38:36, 21.54s/it] 31%|███▏ | 4698/15000 [21:42:47<55:51:30, 19.52s/it] 31%|███▏ | 4699/15000 [21:43:01<51:41:02, 18.06s/it] 31%|███▏ | 4700/15000 [21:43:16<48:52:43, 17.08s/it] 31%|███▏ | 4700/15000 [21:43:16<48:52:43, 17.08s/it] 31%|███▏ | 4701/15000 [21:43:31<46:55:33, 16.40s/it] 31%|███▏ | 4702/15000 [21:43:46<45:27:05, 15.89s/it] 31%|███▏ | 4703/15000 [21:44:00<44:34:29, 15.58s/it] 31%|███▏ | 4704/15000 [21:44:15<43:59:05, 15.38s/it] 31%|███▏ | 4705/15000 [21:44:30<43:18:27, 15.14s/it] 31%|███▏ | 4706/15000 [21:44:45<43:03:28, 15.06s/it] 31%|███▏ | 4707/15000 [21:44:59<42:40:43, 14.93s/it] 31%|███▏ | 4708/15000 [21:45:38<62:40:195/15000 [21:41:40<42:59:04, 15.02s/it] 31%|███▏ | 4696/15000 [21:41:55<42:41:51, 14.92s/it] 31%|███▏ | 4697/15000 [21:42:32<61:46:59, 21.59s/it] 31%|███▏ | 4698/15000 [21:42:47<55:48:36, 19.50s/it] 31%|███▏ | 4699/15000 [21:43:01<51:41:39, 18.07s/it] 31%|███▏ | 4700/15000 [21:43:16<48:51:35, 17.08s/it] 31%|███▏ | 4700/15000 [21:43:16<48:51:35, 17.08s/it] 31%|███▏ | 4701/15000 [21:43:31<46:55:30, 16.40s/it] 31%|███▏ | 4702/15000 [21:43:46<45:24:31, 15.87s/it] 31%|███▏ | 4703/15000 [21:44:00<44:33:27, 15.58s/it] 31%|███▏ | 4704/15000 [21:44:15<44:01:55, 15.40s/it] 31%|███▏ | 4705/15000 [21:44:30<43:15:53, 15.13s/it] 31%|███▏ | 4706/15000 [21:44:45<43:00:18, 15.04s/it] 31%|███▏ | 4707/15000 [21:44:59<42:42:23, 14.94s/it] 31%|███▏ | 4708/15000 [21:45:38<62:41:49|███▏ | 4698/15000 [21:42:46<55:49:45, 19.51s/it] 31%|███▏ | 4699/15000 [21:43:01<51:41:06, 18.06s/it] 31%|███▏ | 4700/15000 [21:43:16<48:49:32, 17.07s/it] 31%|███▏ | 4700/15000 [21:43:16<48:49:32, 17.07s/it] 31%|███▏ | 4701/15000 [21:43:31<46:53:24, 16.39s/it] 31%|███▏ | 4702/15000 [21:43:46<45:29:36, 15.90s/it] 31%|███▏ | 4703/15000 [21:44:00<44:33:22, 15.58s/it] 31%|███▏ | 4704/15000 [21:44:15<43:56:11, 15.36s/it] 31%|███▏ | 4705/15000 [21:44:30<43:21:52, 15.16s/it] 31%|███▏ | 4706/15000 [21:44:45<43:02:04, 15.05s/it] 31%|███▏ | 4707/15000 [21:44:59<42:38:28, 14.91s/it] 31%|███▏ | 4708/15000 [21:45:38<62:41:56, 21.93s/it] 31%|███▏ | 4709/15000 [21:45:52<56:30:44, 19.77s/it] 31%|███▏ | 4710/15000 [21:46:07<52:10:10, 18.25s/it] 31%|███▏ | 4711/, 21.92s/it] 31%|███▏ | 4709/15000 [21:45:52<56:35:20, 19.80s/it] 31%|███▏ | 4710/15000 [21:46:07<52:03:51, 18.21s/it] 31%|███▏ | 4711/15000 [21:46:22<49:17:15, 17.25s/it] 31%|███▏ | 4712/15000 [21:46:37<47:07:38, 16.49s/it] 31%|███▏ | 4713/15000 [21:46:51<45:24:48, 15.89s/it] 31%|███▏ | 4714/15000 [21:47:06<44:23:11, 15.53s/it] 31%|███▏ | 4715/15000 [21:47:20<43:35:25, 15.26s/it] 31%|███▏ | 4716/15000 [21:47:35<43:06:24, 15.09s/it] 31%|███▏ | 4717/15000 [21:47:50<42:39:00, 14.93s/it] 31%|███▏ | 4718/15000 [21:48:04<42:25:15, 14.85s/it] 31%|███▏ | 4719/15000 [21:48:41<61:05:30, 21.39s/it] 31%|███▏ | 4720/15000 [21:48:56<55:19:56, 19.38s/it] 31%|███▏ | 4721/15000 [21:49:10<51:19:45, 17.98s/it] 31%|███▏ | 4722/15000 [21:49:25<48:27:30, 16.97s/it] 31%|███▏ | 4723/15000 [21:49:40<46:27:20, 16.27s/it] 31%|
{'loss': 0.8509, 'learning_rate': 0.00015904023730059228, 'epoch': 0.9}
{'loss': 0.8509, 'learning_rate': 0.00015904023730059228, 'epoch': 0.9}
.51s/it] 32%|███▏ | 4788/15000 [22:07:45<55:10:49, 19.45s/it] 32%|███▏ | 4789/15000 [22:08:00<51:09:02, 18.03s/it] 32%|███▏ | 4790/15000 [22:08:14<48:21:01, 17.05s/it] 32%|███▏ | 4791/15000 [22:08:29<46:23:31, 16.36s/it] 32%|███▏ | 4792/15000 [22:08:44<44:59:45, 15.87s/it] 32%|███▏ | 4793/15000 [22:08:59<44:03:11, 15.54s/it] 32%|███▏ | 4794/15000 [22:09:14<43:25:59, 15.32s/it] 32%|███▏ | 4795/15000 [22:09:28<43:00:31, 15.17s/it] 32%|███▏ | 4796/15000 [22:09:43<42:40:45, 15.06s/it] 32%|███▏ | 4797/15000 [22:09:58<42:25:56, 14.97s/it] 32%|███▏ | 4798/15000 [22:10:35<61:08:51, 21.58s/it] 32%|███▏ | 4799/15000 [22:10:50<55:13:12, 19.49s/it] 32%|███▏ | 4800/15000 [22:11:04<51:21:15, 18.13s/it] 32%|███▏ | 4800/15000 [22:11:05<51:21:15, 18.13s/it] 32%|███▏0 [22:11:05<51:18:32, 18.11s/it] 32%|███▏ | 4800/15000 [22:11:05<51:18:32, 18.11s/it] 32%|███▏ | 4801/15000 [22:11:19<48:26:01, 17.10s/it] 32%|███▏ | 4802/15000 [22:11:34<46:36:14, 16.45s/it] 32%|███▏ | 4803/15000 [22:11:49<44:58:06, 15.88s/it] 32%|███▏ | 4804/15000 [22:12:04<44:00:31, 15.54s/it] 32%|███▏ | 4805/15000 [22:12:18<43:26:00, 15.34s/it] 32%|███▏ | 4806/15000 [22:12:33<42:56:53, 15.17s/it] 32%|███▏ | 4807/15000 [22:12:48<42:36:24, 15.05s/it] 32%|███▏ | 4808/15000 [22:13:03<42:27:20, 15.00s/it] 32%|███▏ | 4809/15000 [22:13:18<42:13:11, 14.91s/it] 32%|███▏ | 4810/15000 [22:13:55<61:06:26, 21.59s/it] 32%|███▏ | 4811/15000 [22:14:09<55:13:56, 19.51s/it] 32%|███▏ | 4812/15000 [22:14:24<51:15:48, 18.11s/it] 32%|███▏ | 4813/15000 [22:14:39<48:20:13, 17.00 [22:11:04<51:14:25, 18.08s/it] 32%|███▏ | 4800/15000 [22:11:05<51:14:25, 18.08s/it] 32%|███▏ | 4801/15000 [22:11:19<48:34:05, 17.14s/it] 32%|███▏ | 4802/15000 [22:11:34<46:32:44, 16.43s/it] 32%|███▏ | 4803/15000 [22:11:49<44:59:27, 15.88s/it] 32%|███▏ | 4804/15000 [22:12:04<44:05:30, 15.57s/it] 32%|███▏ | 4805/15000 [22:12:18<43:23:00, 15.32s/it] 32%|███▏ | 4806/15000 [22:12:33<42:55:13, 15.16s/it] 32%|███▏ | 4807/15000 [22:12:48<42:32:46, 15.03s/it] 32%|███▏ | 4808/15000 [22:13:03<42:41:48, 15.08s/it] 32%|███▏ | 4809/15000 [22:13:18<42:12:12, 14.91s/it] 32%|███▏ | 4810/15000 [22:13:55<61:04:55, 21.58s/it] 32%|███▏ | 4811/15000 [22:14:09<55:14:33, 19.52s/it] 32%|███▏ | 4812/15000 [22:14:24<51:13:01, 18.10s/it] 32%|███▏ | 4813/15000 [22:14:39<48:21:49, 17.0 | 4801/15000 [22:11:19<48:26:20, 17.10s/it] 32%|███▏ | 4802/15000 [22:11:34<46:34:13, 16.44s/it] 32%|███▏ | 4803/15000 [22:11:49<45:05:54, 15.92s/it] 32%|███▏ | 4804/15000 [22:12:03<43:59:26, 15.53s/it] 32%|███▏ | 4805/15000 [22:12:18<43:25:45, 15.34s/it] 32%|███▏ | 4806/15000 [22:12:33<42:56:44, 15.17s/it] 32%|███▏ | 4807/15000 [22:12:48<42:39:57, 15.07s/it] 32%|███▏ | 4808/15000 [22:13:03<42:27:02, 14.99s/it] 32%|███▏ | 4809/15000 [22:13:17<42:14:22, 14.92s/it] 32%|███▏ | 4810/15000 [22:13:55<61:05:25, 21.58s/it] 32%|███▏ | 4811/15000 [22:14:09<55:16:36, 19.53s/it] 32%|███▏ | 4812/15000 [22:14:24<51:13:39, 18.10s/it] 32%|███▏ | 4813/15000 [22:14:39<48:19:04, 17.08s/it] 32%|███▏ | 4814/15000 [22:14:54<46:21:31, 16.38s/it] 32%|███▏ | 4815/15000 [22:15:08<44:51:06, 15.85s/it] 32%|███▏ | 4816/15000
{'loss': 0.8497, 'learning_rate': 0.000157283925070947, 'epoch': 0.92}
{'loss': 0.8497, 'learning_rate': 0.000157283925070947, 'epoch': 0.92}
| 4890/15000 [22:36:05<54:17:59, 19.34s/it] 33%|███▎ | 4891/15000 [22:36:19<50:17:14, 17.91s/it] 33%|███▎ | 4892/15000 [22:36:34<47:37:43, 16.96s/it] 33%|███▎ | 4893/15000 [22:36:49<45:37:32, 16.25s/it] 33%|███▎ | 4894/15000 [22:37:03<44:20:35, 15.80s/it] 33%|███▎ | 4895/15000 [22:37:18<43:20:20, 15.44s/it] 33%|███▎ | 4896/15000 [22:37:33<42:47:29, 15.25s/it] 33%|███▎ | 4897/15000 [22:37:47<42:18:20, 15.07s/it] 33%|███▎ | 4898/15000 [22:38:02<41:55:06, 14.94s/it] 33%|███▎ | 4899/15000 [22:38:17<41:39:52, 14.85s/it] 33%|███▎ | 4900/15000 [22:38:54<60:14:01, 21.47s/it] 33%|███▎ | 4900/15000 [22:38:54<60:14:01, 21.47s/it] 33%|███▎ | 4901/15000 [22:39:08<54:44:00, 19.51s/it] 33%|███▎ | 4902/15000 [22:39:23<50:38:13, 18.05s/it] 33%|███▎ | 4903/15000 [22:39:38<4 | 4890/15000 [22:36:05<54:19:42, 19.35s/it] 33%|███▎ | 4891/15000 [22:36:19<50:21:44, 17.93s/it] 33%|███▎ | 4892/15000 [22:36:34<47:31:53, 16.93s/it] 33%|███▎ | 4893/15000 [22:36:49<45:37:58, 16.25s/it] 33%|███▎ | 4894/15000 [22:37:03<44:18:05, 15.78s/it] 33%|███▎ | 4895/15000 [22:37:18<43:25:13, 15.47s/it] 33%|███▎ | 4896/15000 [22:37:33<42:45:49, 15.24s/it] 33%|███▎ | 4897/15000 [22:37:47<42:15:01, 15.06s/it] 33%|███▎ | 4898/15000 [22:38:02<41:57:50, 14.95s/it] 33%|███▎ | 4899/15000 [22:38:17<41:41:22, 14.86s/it] 33%|███▎ | 4900/15000 [22:38:54<60:19:26, 21.50s/it] 33%|███▎ | 4900/15000 [22:38:54<60:19:26, 21.50s/it] 33%|███▎ | 4901/15000 [22:39:08<54:42:55, 19.50s/it] 33%|███▎ | 4902/15000 [22:39:23<50:36:56, 18.04s/it] 33%|███▎ | 4903/15000 [22:39:38<4t] 33%|███▎ | 4893/15000 [22:36:49<45:41:52, 16.28s/it] 33%|███▎ | 4894/15000 [22:37:03<44:16:36, 15.77s/it] 33%|███▎ | 4895/15000 [22:37:18<43:23:21, 15.46s/it] 33%|███▎ | 4896/15000 [22:37:33<42:45:09, 15.23s/it] 33%|███▎ | 4897/15000 [22:37:47<42:17:53, 15.07s/it] 33%|███▎ | 4898/15000 [22:38:02<41:55:53, 14.94s/it] 33%|███▎ | 4899/15000 [22:38:16<41:37:11, 14.83s/it] 33%|███▎ | 4900/15000 [22:38:54<60:19:20, 21.50s/it] 33%|███▎ | 4900/15000 [22:38:54<60:19:20, 21.50s/it] 33%|███▎ | 4901/15000 [22:39:08<54:39:47, 19.49s/it] 33%|███▎ | 4902/15000 [22:39:23<50:36:56, 18.04s/it] 33%|███▎ | 4903/15000 [22:39:38<47:44:48, 17.02s/it] 33%|███▎ | 4904/15000 [22:39:52<45:49:42, 16.34s/it] 33%|███▎ | 4905/15000 [22:40:07<44:20:28, 15.81s/it] 33%|███▎ 7:45:50, 17.03s/it] 33%|███▎ | 4904/15000 [22:39:53<45:49:10, 16.34s/it] 33%|███▎ | 4905/15000 [22:40:07<44:22:16, 15.82s/it] 33%|███▎ | 4906/15000 [22:40:22<43:18:40, 15.45s/it] 33%|███▎ | 4907/15000 [22:40:36<42:33:22, 15.18s/it] 33%|███▎ | 4908/15000 [22:40:51<42:06:02, 15.02s/it] 33%|███▎ | 4909/15000 [22:41:06<41:48:52, 14.92s/it] 33%|███▎ | 4910/15000 [22:41:20<41:32:53, 14.82s/it] 33%|███▎ | 4911/15000 [22:41:57<60:03:05, 21.43s/it] 33%|███▎ | 4912/15000 [22:42:12<54:20:35, 19.39s/it] 33%|███▎ | 4913/15000 [22:42:26<50:29:51, 18.02s/it] 33%|███▎ | 4914/15000 [22:42:41<47:33:28, 16.97s/it] 33%|███▎ | 4915/15000 [22:42:56<45:31:31, 16.25s/it] 33%|███▎ | 4916/15000 [22:43:10<44:16:59, 15.81s/it] 33%|███▎ | 4917/15000 [22:43:25<43:17:23, 15.46s/it] 33%|███▎ | 4918/15000 [22:43:40<42:38:28, 15.23s/it
{'loss': 0.8509, 'learning_rate': 0.000155500908021347, 'epoch': 0.94}
{'loss': 0.8509, 'learning_rate': 0.000155500908021347, 'epoch': 0.94}
95/15000 [23:05:06<43:54:39, 15.80s/it] 33%|███▎ | 4996/15000 [23:05:21<43:04:54, 15.50s/it] 33%|███▎ | 4997/15000 [23:05:35<42:20:03, 15.24s/it] 33%|███▎ | 4998/15000 [23:05:50<41:52:47, 15.07s/it] 33%|███▎ | 4999/15000 [23:06:05<41:37:08, 14.98s/it] 33%|███▎ | 5000/15000 [23:06:19<41:18:37, 14.87s/it] 33%|███▎ | 5000/15000 [23:06:20<41:18:37, 14.87s/it] 33%|███▎ | 5001/15000 [23:06:34<41:15:18, 14.85s/it] 33%|███▎ | 5002/15000 [23:07:11<59:28:00, 21.41s/it] 33%|███▎ | 5003/15000 [23:07:26<53:51:08, 19.39s/it] 33%|███▎ | 5004/15000 [23:07:40<49:52:55, 17.96s/it] 33%|███▎ | 5005/15000 [23:07:55<47:14:00, 17.01s/it] 33%|███▎ | 5006/15000 [23:08:10<45:22:29, 16.34s/it] 33%|███▎ | 5007/15000 [23:08:25<43:58:26, 15.84s/it] 33%|███▎ | 5008/15000 [23:08:39<42:55:595/15000 [23:05:06<43:56:29, 15.81s/it] 33%|███▎ | 4996/15000 [23:05:21<43:01:27, 15.48s/it] 33%|███▎ | 4997/15000 [23:05:35<42:22:15, 15.25s/it] 33%|███▎ | 4998/15000 [23:05:50<41:52:40, 15.07s/it] 33%|███▎ | 4999/15000 [23:06:05<41:37:17, 14.98s/it] 33%|███▎ | 5000/15000 [23:06:19<41:20:43, 14.88s/it] 33%|███▎ | 5000/15000 [23:06:20<41:20:43, 14.88s/it] 33%|███▎ | 5001/15000 [23:06:34<41:16:41, 14.86s/it] 33%|███▎ | 5002/15000 [23:07:11<59:23:16, 21.38s/it] 33%|███▎ | 5003/15000 [23:07:26<53:56:43, 19.43s/it] 33%|███▎ | 5004/15000 [23:07:40<49:53:02, 17.97s/it] 33%|███▎ | 5005/15000 [23:07:55<47:13:45, 17.01s/it] 33%|███▎ | 5006/15000 [23:08:10<45:23:49, 16.35s/it] 33%|███▎ | 5007/15000 [23:08:24<43:56:48, 15.83s/it] 33%|███▎ | 5008/15000 [23:08:39<42:56:1%|███▎ | 4998/15000 [23:05:50<41:56:42, 15.10s/it] 33%|███▎ | 4999/15000 [23:06:05<41:31:20, 14.95s/it] 33%|███▎ | 5000/15000 [23:06:19<41:16:42, 14.86s/it] 33%|███▎ | 5000/15000 [23:06:20<41:16:42, 14.86s/it] 33%|███▎ | 5001/15000 [23:06:34<41:16:12, 14.86s/it] 33%|███▎ | 5002/15000 [23:07:11<59:26:58, 21.41s/it] 33%|███▎ | 5003/15000 [23:07:26<53:54:25, 19.41s/it] 33%|███▎ | 5004/15000 [23:07:40<49:56:42, 17.99s/it] 33%|███▎ | 5005/15000 [23:07:55<47:15:31, 17.02s/it] 33%|███▎ | 5006/15000 [23:08:10<45:20:56, 16.34s/it] 33%|███▎ | 5007/15000 [23:08:24<43:57:59, 15.84s/it] 33%|███▎ | 5008/15000 [23:08:39<42:55:19, 15.46s/it] 33%|███▎ | 5009/15000 [23:08:54<42:17:08, 15.24s/it] 33%|███▎ | 5010/15000 [23:09:08<41:48:28, 15.07s/it] 33%|███▎ | 50112, 15.47s/it] 33%|███▎ | 5009/15000 [23:08:54<42:17:02, 15.24s/it] 33%|███▎ | 5010/15000 [23:09:09<41:49:56, 15.07s/it] 33%|███▎ | 5011/15000 [23:09:23<41:27:41, 14.94s/it] 33%|███▎ | 5012/15000 [23:09:38<41:11:00, 14.84s/it] 33%|███▎ | 5013/15000 [23:10:14<59:16:31, 21.37s/it] 33%|███▎ | 5014/15000 [23:10:29<53:40:45, 19.35s/it] 33%|███▎ | 5015/15000 [23:10:44<49:42:15, 17.92s/it] 33%|███▎ | 5016/15000 [23:10:58<47:00:10, 16.95s/it] 33%|███▎ | 5017/15000 [23:11:13<45:03:21, 16.25s/it] 33%|███▎ | 5018/15000 [23:11:28<43:47:02, 15.79s/it] 33%|███▎ | 5019/15000 [23:11:42<42:47:06, 15.43s/it] 33%|███▎ | 5020/15000 [23:11:57<42:04:20, 15.18s/it] 33%|███▎ | 5021/15000 [23:12:12<41:42:17, 15.05s/it] 33%|███▎ | 5022/15000 [23:12:26<41:19:35, 14.91s/it] 33%|███▎ | 5023/15000 [23:12:41<41:12:33, 14.87s/it] 33%
{'loss': 0.8481, 'learning_rate': 0.0001536920173648984, 'epoch': 0.95}
{'loss': 0.8481, 'learning_rate': 0.0001536920173648984, 'epoch': 0.95}
5.21s/it] 34%|███▍ | 5088/15000 [23:30:46<41:21:41, 15.02s/it] 34%|███▍ | 5089/15000 [23:31:01<41:04:57, 14.92s/it] 34%|███▍ | 5090/15000 [23:31:16<40:50:51, 14.84s/it] 34%|███▍ | 5091/15000 [23:31:30<40:41:24, 14.78s/it] 34%|███▍ | 5092/15000 [23:32:07<59:00:36, 21.44s/it] 34%|███▍ | 5093/15000 [23:32:22<53:23:33, 19.40s/it] 34%|███▍ | 5094/15000 [23:32:37<49:29:32, 17.99s/it] 34%|███▍ | 5095/15000 [23:32:51<46:41:22, 16.97s/it] 34%|███▍ | 5096/15000 [23:33:06<44:45:08, 16.27s/it] 34%|███▍ | 5097/15000 [23:33:21<43:23:02, 15.77s/it] 34%|███▍ | 5098/15000 [23:33:35<42:28:44, 15.44s/it] 34%|███▍ | 5099/15000 [23:33:50<41:50:41, 15.21s/it] 34%|███▍ | 5100/15000 [23:34:05<41:25:52, 15.07s/it] 34%|███▍ | 5100/15000 [23:34:05<41:25:52, 15.07s/it] 34%|███<E29688><E29688>00 [23:34:05<41:22:10, 15.04s/it] 34%|███▍ | 5100/15000 [23:34:05<41:22:10, 15.04s/it] 34%|███▍ | 5101/15000 [23:34:19<41:07:49, 14.96s/it] 34%|███▍ | 5102/15000 [23:34:34<40:56:18, 14.89s/it] 34%|███▍ | 5103/15000 [23:35:11<59:10:56, 21.53s/it] 34%|███▍ | 5104/15000 [23:35:26<53:28:16, 19.45s/it] 34%|███▍ | 5105/15000 [23:35:40<49:23:41, 17.97s/it] 34%|███▍ | 5106/15000 [23:35:55<46:38:22, 16.97s/it] 34%|███▍ | 5107/15000 [23:36:10<44:44:34, 16.28s/it] 34%|███▍ | 5108/15000 [23:36:24<43:25:40, 15.80s/it] 34%|███▍ | 5109/15000 [23:36:39<42:24:19, 15.43s/it] 34%|███▍ | 5110/15000 [23:36:54<41:51:26, 15.24s/it] 34%|███▍ | 5111/15000 [23:37:08<41:20:00, 15.05s/it] 34%|███▍ | 5112/15000 [23:37:23<41:02:30, 14.94s/it] 34%|███▍ | 5113/15000 [23:37:38<40:45:59, 14.00 [23:34:05<41:24:44, 15.06s/it] 34%|███▍ | 5100/15000 [23:34:05<41:24:44, 15.06s/it] 34%|███▍ | 5101/15000 [23:34:20<41:11:33, 14.98s/it] 34%|███▍ | 5102/15000 [23:34:34<40:57:36, 14.90s/it] 34%|███▍ | 5103/15000 [23:35:11<59:08:07, 21.51s/it] 34%|███▍ | 5104/15000 [23:35:26<53:27:42, 19.45s/it] 34%|███▍ | 5105/15000 [23:35:40<49:24:55, 17.98s/it] 34%|███▍ | 5106/15000 [23:35:55<46:35:57, 16.96s/it] 34%|███▍ | 5107/15000 [23:36:10<44:45:24, 16.29s/it] 34%|███▍ | 5108/15000 [23:36:24<43:23:00, 15.79s/it] 34%|███▍ | 5109/15000 [23:36:39<42:27:11, 15.45s/it] 34%|███▍ | 5110/15000 [23:36:54<41:52:03, 15.24s/it] 34%|███▍ | 5111/15000 [23:37:08<41:15:14, 15.02s/it] 34%|███▍ | 5112/15000 [23:37:23<41:04:09, 14.95s/it] 34%|███▍ | 5113/15000 [23:37:38<40:47:24, 14.<2E> | 5101/15000 [23:34:19<41:05:52, 14.95s/it] 34%|███▍ | 5102/15000 [23:34:34<40:53:50, 14.87s/it] 34%|███▍ | 5103/15000 [23:35:11<59:09:02, 21.52s/it] 34%|███▍ | 5104/15000 [23:35:26<53:25:56, 19.44s/it] 34%|███▍ | 5105/15000 [23:35:40<49:24:55, 17.98s/it] 34%|███▍ | 5106/15000 [23:35:55<46:40:17, 16.98s/it] 34%|███▍ | 5107/15000 [23:36:10<44:46:48, 16.30s/it] 34%|███▍ | 5108/15000 [23:36:24<43:23:24, 15.79s/it] 34%|███▍ | 5109/15000 [23:36:39<42:27:04, 15.45s/it] 34%|███▍ | 5110/15000 [23:36:54<41:48:43, 15.22s/it] 34%|███▍ | 5111/15000 [23:37:08<41:20:23, 15.05s/it] 34%|███▍ | 5112/15000 [23:37:23<41:02:30, 14.94s/it] 34%|███▍ | 5113/15000 [23:37:38<40:48:42, 14.86s/it] 34%|███▍ | 5114/15000 [23:38:14<58:57:06, 21.47s/it] 34%|███▍ | 5115/15000 [23:38:29<53:19:01, 19.42s/it] 34%|███▍ | 5116/1500
warnings.warn("The dataset reached end and the iterator is reset to the start.")
34%|███▍ | 5175/15000 [23:54:59<44:28:00, 16.29s/it] 35%|███▍ | 5176/15000 [23:55:14<42:58:16, 15.75s/it] 35%|███▍ | 5177/15000 [23:55:28<42:10:02, 15.45s/it] 35%|███▍ | 5178/15000 [23:55:43<41:32:01, 15.22s/it] 35%|███▍ | 5179/15000 [23:55:58<40:57:59, 15.02s/it] 35%|███▍ | 5180/15000 [23:56:12<40:41:29, 14.92s/it] 35%|███▍ | 5181/15000 [23:56:27<40:29:09, 14.84s/it] 35%|███▍ | 5182/15000 [23:56:55<51:33:31, 18.91s/it] 35%|███▍ | 5183/15000 [23:57:10<48:04:16, 17.63s/it] 35%|███▍ | 5184/15000 [23:57:25<45:33:45, 16.71s/it] 35%|███▍ | 5185/15000 [23:57:39<43:52:41, 16.09s/it] 35%|███▍ | 5186/15000 [23:57:54<42:51:05, 15.72s/it] 35%|███▍ | 5187/15000 [23:58:09<41:56:37, 15.39s/it] 35%|███▍ | 5188/15000 [23:58:23<41:18:15, 15.15s/it] 35%|███▍ | 5189/15000 [23:58:38<40:53:38, 15.01s/it] 35%|███▍ 34%|███▍ | 5175/15000 [23:54:59<44:27:16, 16.29s/it] 35%|███▍ | 5176/15000 [23:55:14<43:02:53, 15.77s/it] 35%|███▍ | 5177/15000 [23:55:28<42:09:27, 15.45s/it] 35%|███▍ | 5178/15000 [23:55:43<41:29:10, 15.21s/it] 35%|███▍ | 5179/15000 [23:55:58<41:01:52, 15.04s/it] 35%|███▍ | 5180/15000 [23:56:12<40:44:44, 14.94s/it] 35%|███▍ | 5181/15000 [23:56:27<40:29:52, 14.85s/it] 35%|███▍ | 5182/15000 [23:56:55<51:32:13, 18.90s/it] 35%|███▍ | 5183/15000 [23:57:10<48:01:52, 17.61s/it] 35%|███▍ | 5184/15000 [23:57:25<45:37:50, 16.73s/it] 35%|███▍ | 5185/15000 [23:57:39<43:51:08, 16.08s/it] 35%|███▍ | 5186/15000 [23:57:54<42:45:31, 15.68s/it] 35%|███▍ | 5187/15000 [23:58:09<41:54:28, 15.37s/it] 35%|███▍ | 5188/15000 [23:58:23<41:18:22, 15.16s/it] 35%|███▍ | 5189/15000 [23:58:38<41:00:58, 15.05s/it] 35%|███▍ 35%|███▍ | 5182/15000 [23:56:55<51:31:52, 18.90s/it] 35%|███▍ | 5183/15000 [23:57:10<48:02:07, 17.62s/it] 35%|███▍ | 5184/15000 [23:57:25<45:37:20, 16.73s/it] 35%|███▍ | 5185/15000 [23:57:39<43:57:37, 16.12s/it] 35%|███▍ | 5186/15000 [23:57:54<42:44:24, 15.68s/it] 35%|███▍ | 5187/15000 [23:58:09<41:56:18, 15.39s/it] 35%|███▍ | 5188/15000 [23:58:23<41:21:34, 15.17s/it] 35%|███▍ | 5189/15000 [23:58:38<40:52:05, 15.00s/it] 35%|███▍ | 5190/15000 [23:58:52<40:30:26, 14.87s/it] 35%|███▍ | 5191/15000 [23:59:07<40:25:21, 14.84s/it] 35%|███▍ | 5192/15000 [23:59:22<40:16:05, 14.78s/it] 35%|███▍ | 5193/15000 [23:59:53<53:19:30, 19.57s/it] 35%|███▍ | 5194/15000 [24:00:07<49:18:26, 18.10s/it] 35%|███▍ | 5195/15000 [24:00:22<46:30:52, 17.08s/it] 35%|███▍ | 5196/15000 [24:00:37<44:31:47, 16.35s/it] 35%|███▍ {'loss': 0.8584, 'learning_rate': 0.0001518580963765555, 'epoch': 0.97}
{'loss': 0.8584, 'learning_rate': 0.0001518580963765555, 'epoch': 0.97}
{'loss': 0.8584, 'learning_rate': 0.0001518580963765555, 'epoch': 0.97}
| 5190/15000 [23:58:53<40:33:08, 14.88s/it] 35%|███▍ | 5191/15000 [23:59:07<40:25:44, 14.84s/it] 35%|███▍ | 5192/15000 [23:59:22<40:17:27, 14.79s/it] 35%|███▍ | 5193/15000 [23:59:53<53:16:00, 19.55s/it] 35%|███▍ | 5194/15000 [24:00:07<49:13:02, 18.07s/it] 35%|███▍ | 5195/15000 [24:00:22<46:30:40, 17.08s/it] 35%|███▍ | 5196/15000 [24:00:37<44:38:36, 16.39s/it] 35%|███▍ | 5197/15000 [24:00:51<43:10:04, 15.85s/it] 35%|███▍ | 5198/15000 [24:01:06<42:09:09, 15.48s/it] 35%|███▍ | 5199/15000 [24:01:21<41:29:58, 15.24s/it] 35%|███▍ | 5200/15000 [24:01:35<40:57:35, 15.05s/it] 35%|███▍ | 5200/15000 [24:01:35<40:57:35, 15.05s/it] 35%|███▍ | 5201/15000 [24:01:50<40:40:37, 14.94s/it] 35%|███▍ | 5202/15000 [24:02:05<40:28:59, 14.87s/it] 35%|███▍ | 5203/15000 [24:02:19< | 5190/15000 [23:58:53<40:32:34, 14.88s/it] 35%|███▍ | 5191/15000 [23:59:07<40:24:50, 14.83s/it] 35%|███▍ | 5192/15000 [23:59:22<40:15:47, 14.78s/it] 35%|███▍ | 5193/15000 [23:59:53<53:17:40, 19.56s/it] 35%|███▍ | 5194/15000 [24:00:07<49:15:42, 18.09s/it] 35%|███▍ | 5195/15000 [24:00:22<46:30:44, 17.08s/it] 35%|███▍ | 5196/15000 [24:00:37<44:30:59, 16.35s/it] 35%|███▍ | 5197/15000 [24:00:51<43:08:19, 15.84s/it] 35%|███▍ | 5198/15000 [24:01:06<42:11:09, 15.49s/it] 35%|███▍ | 5199/15000 [24:01:21<41:29:05, 15.24s/it] 35%|███▍ | 5200/15000 [24:01:35<40:53:23, 15.02s/it] 35%|███▍ | 5200/15000 [24:01:35<40:53:23, 15.02s/it] 35%|███▍ | 5201/15000 [24:01:50<40:40:24, 14.94s/it] 35%|███▍ | 5202/15000 [24:02:05<40:33:06, 14.90s/it] 35%|███▍ | 5203/15000 [24:02:19< | 5197/15000 [24:00:51<43:07:34, 15.84s/it] 35%|███▍ | 5198/15000 [24:01:06<42:08:38, 15.48s/it] 35%|███▍ | 5199/15000 [24:01:21<41:26:17, 15.22s/it] 35%|███▍ | 5200/15000 [24:01:35<40:57:56, 15.05s/it] 35%|███▍ | 5200/15000 [24:01:35<40:57:56, 15.05s/it] 35%|███▍ | 5201/15000 [24:01:50<40:42:43, 14.96s/it] 35%|███▍ | 5202/15000 [24:02:05<40:31:00, 14.89s/it] 35%|███▍ | 5203/15000 [24:02:19<40:19:53, 14.82s/it] 35%|███▍ | 5204/15000 [24:02:34<40:13:08, 14.78s/it] 35%|███▍ | 5205/15000 [24:03:10<57:45:35, 21.23s/it] 35%|███▍ | 5206/15000 [24:03:25<52:27:34, 19.28s/it] 35%|███▍ | 5207/15000 [24:03:40<48:38:32, 17.88s/it] 35%|███▍ | 5208/15000 [24:03:54<45:58:43, 16.90s/it] 35%|███▍ | 5209/15000 [24:04:09<44:07:33, 16.22s/it] 35%|███▍ | 5210/15000 [24:04:240:18:00, 14.81s/it] 35%|███▍ | 5204/15000 [24:02:34<40:13:49, 14.78s/it] 35%|███▍ | 5205/15000 [24:03:10<57:46:36, 21.24s/it] 35%|███▍ | 5206/15000 [24:03:25<52:26:38, 19.28s/it] 35%|███▍ | 5207/15000 [24:03:40<48:42:03, 17.90s/it] 35%|███▍ | 5208/15000 [24:03:54<45:57:37, 16.90s/it] 35%|███▍ | 5209/15000 [24:04:09<44:09:51, 16.24s/it] 35%|███▍ | 5210/15000 [24:04:24<42:51:55, 15.76s/it] 35%|███▍ | 5211/15000 [24:04:38<41:54:54, 15.41s/it] 35%|███▍ | 5212/15000 [24:04:53<41:21:49, 15.21s/it] 35%|███▍ | 5213/15000 [24:05:08<40:55:44, 15.06s/it] 35%|███▍ | 5214/15000 [24:05:22<40:31:51, 14.91s/it] 35%|███▍ | 5215/15000 [24:05:37<40:20:26, 14.84s/it] 35%|███▍ | 5216/15000 [24:06:13<57:44:36, 21.25s/it] 35%|███▍ | 5217/15000 [24:06:28<52:24:54, 19.29s/it] 35%|███▍ | 5218/15000 [24:06:42<48:28:00, 17.84s/i
███▌ | 5287/15000 [24:25:45<45:44:15, 16.95s/it] 35%|███▌ | 5288/15000 [24:26:00<43:56:43, 16.29s/it] 35%|███▌ | 5289/15000 [24:26:14<42:37:06, 15.80s/it] 35%|███▌ | 5290/15000 [24:26:29<41:38:53, 15.44s/it] 35%|███▌ | 5291/15000 [24:26:44<41:05:05, 15.23s/it] 35%|███▌ | 5292/15000 [24:26:58<40:33:09, 15.04s/it] 35%|███▌ | 5293/15000 [24:27:13<40:18:05, 14.95s/it] 35%|███▌ | 5294/15000 [24:27:28<40:01:42, 14.85s/it] 35%|███▌ | 5295/15000 [24:28:06<58:55:33, 21.86s/it] 35%|███▌ | 5296/15000 [24:28:20<53:01:39, 19.67s/it] 35%|███▌ | 5297/15000 [24:28:35<48:57:39, 18.17s/it] 35%|███▌ | 5298/15000 [24:28:50<46:08:19, 17.12s/it] 35%|███▌ | 5299/15000 [24:29:04<44:03:26, 16.35s/it] 35%|███▌ | 5300/15000 [24:29:19<42:36:56, 15.82s/it] 35%|███▌ | 5300/1{'loss': 0.834, 'learning_rate': 0.00015000000000000001, 'epoch': 0.99}
{'loss': 0.834, 'learning_rate': 0.00015000000000000001, 'epoch': 0.99}
295/15000 [24:28:06<59:01:28, 21.89s/it] 35%|███▌ | 5296/15000 [24:28:20<53:01:48, 19.67s/it] 35%|███▌ | 5297/15000 [24:28:35<48:53:47, 18.14s/it] 35%|███▌ | 5298/15000 [24:28:50<46:03:34, 17.09s/it] 35%|███▌ | 5299/15000 [24:29:04<44:09:55, 16.39s/it] 35%|███▌ | 5300/15000 [24:29:19<42:40:58, 15.84s/it] 35%|███▌ | 5300/15000 [24:29:19<42:40:58, 15.84s/it] 35%|███▌ | 5301/15000 [24:29:34<41:44:25, 15.49s/it] 35%|███▌ | 5302/15000 [24:29:48<41:01:34, 15.23s/it] 35%|███▌ | 5303/15000 [24:30:03<40:41:40, 15.11s/it] 35%|███▌ | 5304/15000 [24:30:18<40:16:20, 14.95s/it] 35%|███▌ | 5305/15000 [24:30:32<39:58:11, 14.84s/it] 35%|███▌ | 5306/15000 [24:30:47<39:50:14, 14.79s/it] 35%|███▌ | 5307/15000 [24:31:24<57:40:56, 21.42s/it] 35%|███▌ | 5308/15000 [24:31:39<52:12:295/15000 [24:28:06<58:57:42, 21.87s/it] 35%|███▌ | 5296/15000 [24:28:21<53:05:23, 19.70s/it] 35%|███▌ | 5297/15000 [24:28:35<48:53:14, 18.14s/it] 35%|███▌ | 5298/15000 [24:28:50<46:04:35, 17.10s/it] 35%|███▌ | 5299/15000 [24:29:04<44:06:26, 16.37s/it] 35%|███▌ | 5300/15000 [24:29:19<42:36:15, 15.81s/it] 35%|███▌ | 5300/15000 [24:29:19<42:36:15, 15.81s/it] 35%|███▌ | 5301/15000 [24:29:34<41:47:23, 15.51s/it] 35%|███▌ | 5302/15000 [24:29:48<41:04:37, 15.25s/it] 35%|███▌ | 5303/15000 [24:30:03<40:38:33, 15.09s/it] 35%|███▌ | 5304/15000 [24:30:18<40:17:40, 14.96s/it] 35%|███▌ | 5305/15000 [24:30:32<39:56:57, 14.83s/it] 35%|███▌ | 5306/15000 [24:30:47<39:49:06, 14.79s/it] 35%|███▌ | 5307/15000 [24:31:24<57:48:02, 21.47s/it] 35%|███▌ | 5308/15000 [24:31:39<52:15:5000 [24:29:19<42:36:56, 15.82s/it] 35%|███▌ | 5301/15000 [24:29:34<41:45:34, 15.50s/it] 35%|███▌ | 5302/15000 [24:29:48<41:08:34, 15.27s/it] 35%|███▌ | 5303/15000 [24:30:03<40:35:48, 15.07s/it] 35%|███▌ | 5304/15000 [24:30:18<40:13:43, 14.94s/it] 35%|███▌ | 5305/15000 [24:30:32<39:57:34, 14.84s/it] 35%|███▌ | 5306/15000 [24:30:47<39:49:29, 14.79s/it] 35%|███▌ | 5307/15000 [24:31:24<57:43:40, 21.44s/it] 35%|███▌ | 5308/15000 [24:31:39<52:16:10, 19.42s/it] 35%|███▌ | 5309/15000 [24:31:53<48:25:13, 17.99s/it] 35%|███▌ | 5310/15000 [24:32:08<45:40:44, 16.97s/it] 35%|███▌ | 5311/15000 [24:32:22<43:45:08, 16.26s/it] 35%|███▌ | 5312/15000 [24:32:37<42:22:54, 15.75s/it] 35%|███▌ | 5313/15000 [24:32:52<41:26:05, 15.40s/it] 35%|███▌ | 5314/15000 [24:33:06<40:50:31, 15.18s/it] 35%|███▌ | 5315/15000 [24:33:21<40:217, 19.41s/it] 35%|███▌ | 5309/15000 [24:31:53<48:19:19, 17.95s/it] 35%|███▌ | 5310/15000 [24:32:08<45:41:22, 16.97s/it] 35%|███▌ | 5311/15000 [24:32:23<43:48:06, 16.27s/it] 35%|███▌ | 5312/15000 [24:32:37<42:23:31, 15.75s/it] 35%|███▌ | 5313/15000 [24:32:52<41:25:35, 15.40s/it] 35%|███▌ | 5314/15000 [24:33:06<40:50:12, 15.18s/it] 35%|███▌ | 5315/15000 [24:33:21<40:26:38, 15.03s/it] 35%|███▌ | 5316/15000 [24:33:36<40:06:35, 14.91s/it] 35%|███▌ | 5317/15000 [24:33:50<39:55:06, 14.84s/it] 35%|███▌ | 5318/15000 [24:34:27<57:30:05, 21.38s/it] 35%|███▌ | 5319/15000 [24:34:42<52:08:28, 19.39s/it] 35%|███▌ | 5320/15000 [24:34:56<48:23:06, 17.99s/it] 35%|███▌ | 5321/15000 [24:35:11<45:36:30, 16.96s/it] 35%|███▌ | 5322/15000 [24:35:26<43:48:47, 16.30s/it] 35%|███▌ | 5323/15000 [24:35:40<42:24:29, 15.78s/it] 35
{'loss': 0.827, 'learning_rate': 0.00014811859444908052, 'epoch': 1.01}
{'loss': 0.827, 'learning_rate': 0.00014811859444908052, 'epoch': 1.01}
█▌ | 5392/15000 [24:54:48<41:16:57, 15.47s/it] 36%|███▌ | 5393/15000 [24:55:02<40:37:45, 15.22s/it] 36%|███▌ | 5394/15000 [24:55:17<40:09:08, 15.05s/it] 36%|███▌ | 5395/15000 [24:55:32<39:54:07, 14.96s/it] 36%|███▌ | 5396/15000 [24:55:46<39:42:36, 14.89s/it] 36%|███▌ | 5397/15000 [24:56:01<39:30:59, 14.81s/it] 36%|███▌ | 5398/15000 [24:56:38<57:28:14, 21.55s/it] 36%|███▌ | 5399/15000 [24:56:53<51:55:03, 19.47s/it] 36%|███▌ | 5400/15000 [24:57:08<48:07:45, 18.05s/it] 36%|███▌ | 5400/15000 [24:57:08<48:07:45, 18.05s/it] 36%|███▌ | 5401/15000 [24:57:22<45:31:04, 17.07s/it] 36%|███▌ | 5402/15000 [24:57:37<43:35:42, 16.35s/it] 36%|███▌ | 5403/15000 [24:57:52<42:14:01, 15.84s/it] 36%|███▌ | 5404/15000 [24:58:06<41:14:05, 15.47s/it] 36%|███▌ | 5405/15000 [000 [24:57:08<48:04:20, 18.03s/it] 36%|███▌ | 5400/15000 [24:57:08<48:04:20, 18.03s/it] 36%|███▌ | 5401/15000 [24:57:23<45:33:25, 17.09s/it] 36%|███▌ | 5402/15000 [24:57:37<43:35:18, 16.35s/it] 36%|███▌ | 5403/15000 [24:57:52<42:15:50, 15.85s/it] 36%|███▌ | 5404/15000 [24:58:07<41:18:38, 15.50s/it] 36%|███▌ | 5405/15000 [24:58:21<40:33:43, 15.22s/it] 36%|███▌ | 5406/15000 [24:58:36<40:05:05, 15.04s/it] 36%|███▌ | 5407/15000 [24:58:50<39:43:30, 14.91s/it] 36%|███▌ | 5408/15000 [24:59:05<39:32:22, 14.84s/it] 36%|███▌ | 5409/15000 [24:59:42<57:30:59, 21.59s/it] 36%|███▌ | 5410/15000 [24:59:57<52:08:44, 19.58s/it] 36%|███▌ | 5411/15000 [25:00:12<48:06:44, 18.06s/it] 36%|███▌ | 5412/15000 [25:00:26<45:20:46, 17.03s/it] 36%|███▌ | 5413/15000 [25:00:41<43:27:04, 16000 [24:57:08<48:02:13, 18.01s/it] 36%|███▌ | 5400/15000 [24:57:08<48:02:13, 18.01s/it] 36%|███▌ | 5401/15000 [24:57:23<45:35:10, 17.10s/it] 36%|███▌ | 5402/15000 [24:57:37<43:32:54, 16.33s/it] 36%|███▌ | 5403/15000 [24:57:52<42:14:04, 15.84s/it] 36%|███▌ | 5404/15000 [24:58:06<41:15:10, 15.48s/it] 36%|███▌ | 5405/15000 [24:58:21<40:38:14, 15.25s/it] 36%|███▌ | 5406/15000 [24:58:36<40:06:44, 15.05s/it] 36%|███▌ | 5407/15000 [24:58:50<39:43:30, 14.91s/it] 36%|███▌ | 5408/15000 [24:59:05<39:33:30, 14.85s/it] 36%|███▌ | 5409/15000 [24:59:42<57:29:36, 21.58s/it] 36%|███▌ | 5410/15000 [24:59:57<52:01:18, 19.53s/it] 36%|███▌ | 5411/15000 [25:00:12<48:12:25, 18.10s/it] 36%|███▌ | 5412/15000 [25:00:26<45:21:11, 17.03s/it] 36%|███▌ | 5413/15000 [25:00:41<43:29:31, 1624:58:21<40:37:13, 15.24s/it] 36%|███▌ | 5406/15000 [24:58:36<40:06:04, 15.05s/it] 36%|███▌ | 5407/15000 [24:58:50<39:46:18, 14.93s/it] 36%|███▌ | 5408/15000 [24:59:05<39:37:27, 14.87s/it] 36%|███▌ | 5409/15000 [24:59:42<57:32:09, 21.60s/it] 36%|███▌ | 5410/15000 [24:59:57<52:02:45, 19.54s/it] 36%|███▌ | 5411/15000 [25:00:12<48:06:30, 18.06s/it] 36%|███▌ | 5412/15000 [25:00:26<45:23:27, 17.04s/it] 36%|███▌ | 5413/15000 [25:00:41<43:23:37, 16.29s/it] 36%|███▌ | 5414/15000 [25:00:56<42:03:23, 15.79s/it] 36%|███▌ | 5415/15000 [25:01:10<41:03:25, 15.42s/it] 36%|███▌ | 5416/15000 [25:01:25<40:34:09, 15.24s/it] 36%|███▌ | 5417/15000 [25:01:40<40:06:05, 15.06s/it] 36%|███▌ | 5418/15000 [25:01:54<39:45:04, 14.93s/it] 36%|███▌ | 5419/15000 [25:02:09<39:30:20, 14.84s/it] 36%|███▌ | 5420/15000 [25:02:46<57:20:41,
{'loss': 0.8251, 'learning_rate': 0.0001462147568039977, 'epoch': 1.03}
{'loss': 0.8251, 'learning_rate': 0.0001462147568039977, 'epoch': 1.03}
| 5490/15000 [25:22:06<47:22:32, 17.93s/it] 37%|███▋ | 5491/15000 [25:22:20<44:48:41, 16.97s/it] 37%|███▋ | 5492/15000 [25:22:35<42:56:21, 16.26s/it] 37%|███▋ | 5493/15000 [25:22:49<41:35:55, 15.75s/it] 37%|███▋ | 5494/15000 [25:23:04<40:49:22, 15.46s/it] 37%|███▋ | 5495/15000 [25:23:19<40:05:15, 15.18s/it] 37%|███▋ | 5496/15000 [25:23:33<39:38:02, 15.01s/it] 37%|███▋ | 5497/15000 [25:23:48<39:22:00, 14.91s/it] 37%|███▋ | 5498/15000 [25:24:03<39:05:53, 14.81s/it] 37%|███▋ | 5499/15000 [25:24:17<39:01:24, 14.79s/it] 37%|███▋ | 5500/15000 [25:24:54<56:39:22, 21.47s/it] 37%|███▋ | 5500/15000 [25:24:55<56:39:22, 21.47s/it] 37%|███▋ | 5501/15000 [25:25:09<51:22:03, 19.47s/it] 37%|███▋ | 5502/15000 [25:25:24<47:42:38, 18.08s/it] 37%|███▋ | 5503/15000 [25:25:39 | 5490/15000 [25:22:06<47:29:39, 17.98s/it] 37%|███▋ | 5491/15000 [25:22:20<44:45:16, 16.94s/it] 37%|███▋ | 5492/15000 [25:22:35<43:00:04, 16.28s/it] 37%|███▋ | 5493/15000 [25:22:50<41:40:25, 15.78s/it] 37%|███▋ | 5494/15000 [25:23:04<40:44:07, 15.43s/it] 37%|███▋ | 5495/15000 [25:23:19<40:06:15, 15.19s/it] 37%|███▋ | 5496/15000 [25:23:33<39:30:15, 14.96s/it] 37%|███▋ | 5497/15000 [25:23:48<39:18:58, 14.89s/it] 37%|███▋ | 5498/15000 [25:24:03<39:07:17, 14.82s/it] 37%|███▋ | 5499/15000 [25:24:17<39:03:27, 14.80s/it] 37%|███▋ | 5500/15000 [25:24:54<56:44:58, 21.51s/it] 37%|███▋ | 5500/15000 [25:24:55<56:44:58, 21.51s/it] 37%|███▋ | 5501/15000 [25:25:09<51:26:01, 19.49s/it] 37%|███▋ | 5502/15000 [25:25:24<47:40:13, 18.07s/it] 37%|███▋ | 5503/15000 [25:25:39 | 5497/15000 [25:23:48<39:18:16, 14.89s/it] 37%|███▋ | 5498/15000 [25:24:03<39:05:54, 14.81s/it] 37%|███▋ | 5499/15000 [25:24:17<39:03:03, 14.80s/it] 37%|███▋ | 5500/15000 [25:24:54<56:41:38, 21.48s/it] 37%|███▋ | 5500/15000 [25:24:55<56:41:38, 21.48s/it] 37%|███▋ | 5501/15000 [25:25:09<51:26:13, 19.49s/it] 37%|███▋ | 5502/15000 [25:25:24<47:35:15, 18.04s/it] 37%|███▋ | 5503/15000 [25:25:39<44:56:52, 17.04s/it] 37%|███▋ | 5504/15000 [25:25:53<43:02:09, 16.32s/it] 37%|███▋ | 5505/15000 [25:26:08<41:46:03, 15.84s/it] 37%|███▋ | 5506/15000 [25:26:23<40:52:33, 15.50s/it] 37%|███▋ | 5507/15000 [25:26:37<40:11:00, 15.24s/it] 37%|███▋ | 5508/15000 [25:26:52<39:45:37, 15.08s/it] 37%|███▋ | 5509/15000 [25:27:07<39:24:08, 14.95s/it] 37%|███▋ | 5510/15000 [25:27:<44:54:58, 17.03s/it] 37%|███▋ | 5504/15000 [25:25:53<42:59:17, 16.30s/it] 37%|███▋ | 5505/15000 [25:26:08<41:45:09, 15.83s/it] 37%|███▋ | 5506/15000 [25:26:23<40:50:26, 15.49s/it] 37%|███▋ | 5507/15000 [25:26:37<40:12:39, 15.25s/it] 37%|███▋ | 5508/15000 [25:26:52<39:44:48, 15.07s/it] 37%|███▋ | 5509/15000 [25:27:07<39:27:10, 14.96s/it] 37%|███▋ | 5510/15000 [25:27:21<39:09:40, 14.86s/it] 37%|███▋ | 5511/15000 [25:27:58<56:43:30, 21.52s/it] 37%|███▋ | 5512/15000 [25:28:13<51:16:13, 19.45s/it] 37%|███▋ | 5513/15000 [25:28:28<47:24:24, 17.99s/it] 37%|███▋ | 5514/15000 [25:28:42<44:47:22, 17.00s/it] 37%|███▋ | 5515/15000 [25:28:57<42:54:50, 16.29s/it] 37%|███▋ | 5516/15000 [25:29:12<41:36:59, 15.80s/it] 37%|███▋ | 5517/15000 [25:29:26<40:42:38, 15.45s/it] 37%|███▋ | 5518/15000 [25:29:41<39:59:11, 15.18s/
|███▋ | 5587/15000 [25:48:47<39:21:57, 15.06s/it] 37%|███▋ | 5588/15000 [25:49:02<39:04:58, 14.95s/it] 37%|███▋ | 5589/15000 [25:49:16<38:46:19, 14.83s/it] 37%|███▋ | 5590/15000 [25:49:31<38:34:24, 14.76s/it] 37%|███▋ | 5591/15000 [25:50:08<55:53:35, 21.39s/it] 37%|███▋ | 5592/15000 [25:50:22<50:37:21, 19.37s/it] 37%|███▋ | 5593/15000 [25:50:37<46:59:01, 17.98s/it] 37%|███▋ | 5594/15000 [25:50:52<44:20:16, 16.97s/it] 37%|███▋ | 5595/15000 [25:51:06<42:32:56, 16.29s/it] 37%|███▋ | 5596/15000 [25:51:21<41:12:13, 15.77s/it] 37%|███▋ | 5597/15000 [25:51:36<40:19:53, 15.44s/it] 37%|███▋ | 5598/15000 [25:51:50<39:38:35, 15.18s/it] 37%|███▋ | 5599/15000 [25:52:05<39:12:15, 15.01s/it] 37%|███▋ | 5600/15000 [25:52:20<39:00:34, 14.94s/it] 37%|███▋ | 5600/{'loss': 0.821, 'learning_rate': 0.00014428937460242417, 'epoch': 1.05}
{'loss': 0.821, 'learning_rate': 0.00014428937460242417, 'epoch': 1.05}
5595/15000 [25:51:06<42:30:23, 16.27s/it] 37%|███▋ | 5596/15000 [25:51:21<41:18:03, 15.81s/it] 37%|███▋ | 5597/15000 [25:51:36<40:15:59, 15.42s/it] 37%|███▋ | 5598/15000 [25:51:50<39:45:44, 15.22s/it] 37%|███▋ | 5599/15000 [25:52:05<39:14:17, 15.03s/it] 37%|███▋ | 5600/15000 [25:52:19<38:54:45, 14.90s/it] 37%|███▋ | 5600/15000 [25:52:20<38:54:45, 14.90s/it] 37%|███▋ | 5601/15000 [25:52:34<38:48:22, 14.86s/it] 37%|███▋ | 5602/15000 [25:53:11<56:06:04, 21.49s/it] 37%|███▋ | 5603/15000 [25:53:26<50:48:36, 19.47s/it] 37%|███▋ | 5604/15000 [25:53:41<46:58:09, 18.00s/it] 37%|███▋ | 5605/15000 [25:53:55<44:17:57, 16.97s/it] 37%|███▋ | 5606/15000 [25:54:10<42:28:44, 16.28s/it] 37%|███▋ | 5607/15000 [25:54:24<41:12:21, 15.79s/it] 37%|███▋ | 5608/15000 [25:54:39<40:095595/15000 [25:51:06<42:28:53, 16.26s/it] 37%|███▋ | 5596/15000 [25:51:21<41:20:02, 15.82s/it] 37%|███▋ | 5597/15000 [25:51:36<40:20:02, 15.44s/it] 37%|███▋ | 5598/15000 [25:51:50<39:42:18, 15.20s/it] 37%|███▋ | 5599/15000 [25:52:05<39:09:47, 15.00s/it] 37%|███▋ | 5600/15000 [25:52:19<38:53:03, 14.89s/it] 37%|███▋ | 5600/15000 [25:52:20<38:53:03, 14.89s/it] 37%|███▋ | 5601/15000 [25:52:34<38:53:00, 14.89s/it] 37%|███▋ | 5602/15000 [25:53:11<56:04:40, 21.48s/it] 37%|███▋ | 5603/15000 [25:53:26<50:47:08, 19.46s/it] 37%|███▋ | 5604/15000 [25:53:41<46:59:06, 18.00s/it] 37%|███▋ | 5605/15000 [25:53:55<44:16:18, 16.96s/it] 37%|███▋ | 5606/15000 [25:54:10<42:28:58, 16.28s/it] 37%|███▋ | 5607/15000 [25:54:24<41:11:42, 15.79s/it] 37%|███▋ | 5608/15000 [25:54:39<40:1415000 [25:52:20<39:00:34, 14.94s/it] 37%|███▋ | 5601/15000 [25:52:34<38:52:29, 14.89s/it] 37%|███▋ | 5602/15000 [25:53:11<56:04:51, 21.48s/it] 37%|███▋ | 5603/15000 [25:53:26<50:41:57, 19.42s/it] 37%|███▋ | 5604/15000 [25:53:40<46:56:52, 17.99s/it] 37%|███▋ | 5605/15000 [25:53:55<44:15:09, 16.96s/it] 37%|███▋ | 5606/15000 [25:54:10<42:26:46, 16.27s/it] 37%|███▋ | 5607/15000 [25:54:24<41:08:45, 15.77s/it] 37%|███▋ | 5608/15000 [25:54:39<40:12:22, 15.41s/it] 37%|███▋ | 5609/15000 [25:54:53<39:33:00, 15.16s/it] 37%|███▋ | 5610/15000 [25:55:08<39:05:34, 14.99s/it] 37%|███▋ | 5611/15000 [25:55:23<38:49:57, 14.89s/it] 37%|███▋ | 5612/15000 [25:55:37<38:35:21, 14.80s/it] 37%|███▋ | 5613/15000 [25:55:52<38:31:12, 14.77s/it] 37%|███▋ | 5614/15000 [25:56:29<56:01:09, 21.49s/it] 37%|███▋ | 5615/15000 [25:56:44<50::36, 15.39s/it] 37%|███▋ | 5609/15000 [25:54:53<39:31:06, 15.15s/it] 37%|███▋ | 5610/15000 [25:55:08<39:06:15, 14.99s/it] 37%|███▋ | 5611/15000 [25:55:23<38:44:56, 14.86s/it] 37%|███▋ | 5612/15000 [25:55:37<38:39:27, 14.82s/it] 37%|███▋ | 5613/15000 [25:55:52<38:27:34, 14.75s/it] 37%|███▋ | 5614/15000 [25:56:29<56:03:41, 21.50s/it] 37%|███▋ | 5615/15000 [25:56:44<50:38:03, 19.42s/it] 37%|███▋ | 5616/15000 [25:56:58<46:54:25, 18.00s/it] 37%|███▋ | 5617/15000 [25:57:13<44:15:41, 16.98s/it] 37%|███▋ | 5618/15000 [25:57:28<42:26:23, 16.28s/it] 37%|███▋ | 5619/15000 [25:57:42<41:10:49, 15.80s/it] 37%|███▋ | 5620/15000 [25:57:57<40:16:56, 15.46s/it] 37%|███▋ | 5621/15000 [25:58:12<39:39:33, 15.22s/it] 37%|███▋ | 5622/15000 [25:58:26<39:07:01, 15.02s/it] 37%|███▋ | 5623/15000 [25:58:41<38:52:41, 14.93s/it] 3
{'loss': 0.8221, 'learning_rate': 0.00014234334542574906, 'epoch': 1.07}
{'loss': 0.8221, 'learning_rate': 0.00014234334542574906, 'epoch': 1.07}
<EFBFBD>█▊ | 5692/15000 [26:17:48<38:26:18, 14.87s/it] 38%|███▊ | 5693/15000 [26:18:25<55:32:14, 21.48s/it] 38%|███▊ | 5694/15000 [26:18:39<50:19:12, 19.47s/it] 38%|███▊ | 5695/15000 [26:18:54<46:32:51, 18.01s/it] 38%|███▊ | 5696/15000 [26:19:09<43:52:21, 16.98s/it] 38%|███▊ | 5697/15000 [26:19:23<42:03:41, 16.28s/it] 38%|███▊ | 5698/15000 [26:19:38<40:50:48, 15.81s/it] 38%|███▊ | 5699/15000 [26:19:53<39:58:51, 15.47s/it] 38%|███▊ | 5700/15000 [26:20:07<39:24:24, 15.25s/it] 38%|███▊ | 5700/15000 [26:20:08<39:24:24, 15.25s/it] 38%|███▊ | 5701/15000 [26:20:22<39:07:47, 15.15s/it] 38%|███▊ | 5702/15000 [26:20:37<38:49:02, 15.03s/it] 38%|███▊ | 5703/15000 [26:20:52<38:34:06, 14.93s/it] 38%|███▊ | 5704/15000 [26:21:29<55:41:22, 21.57s/it] 38%|███▊ | 5705/15000 5000 [26:20:08<39:24:51, 15.26s/it] 38%|███▊ | 5700/15000 [26:20:08<39:24:51, 15.26s/it] 38%|███▊ | 5701/15000 [26:20:22<39:01:55, 15.11s/it] 38%|███▊ | 5702/15000 [26:20:37<38:51:02, 15.04s/it] 38%|███▊ | 5703/15000 [26:20:52<38:31:56, 14.92s/it] 38%|███▊ | 5704/15000 [26:21:29<55:41:17, 21.57s/it] 38%|███▊ | 5705/15000 [26:21:44<50:24:31, 19.52s/it] 38%|███▊ | 5706/15000 [26:21:58<46:37:04, 18.06s/it] 38%|███▊ | 5707/15000 [26:22:13<43:54:06, 17.01s/it] 38%|███▊ | 5708/15000 [26:22:27<42:05:53, 16.31s/it] 38%|███▊ | 5709/15000 [26:22:42<40:46:28, 15.80s/it] 38%|███▊ | 5710/15000 [26:22:57<39:50:23, 15.44s/it] 38%|███▊ | 5711/15000 [26:23:11<39:13:12, 15.20s/it] 38%|███▊ | 5712/15000 [26:23:26<38:55:31, 15.09s/it] 38%|███▊ | 5713/15000 [26:23:41<38:35:34, 15000 [26:20:07<39:21:04, 15.23s/it] 38%|███▊ | 5700/15000 [26:20:08<39:21:04, 15.23s/it] 38%|███▊ | 5701/15000 [26:20:22<39:03:56, 15.12s/it] 38%|███▊ | 5702/15000 [26:20:37<38:53:55, 15.06s/it] 38%|███▊ | 5703/15000 [26:20:52<38:29:12, 14.90s/it] 38%|███▊ | 5704/15000 [26:21:29<55:45:32, 21.59s/it] 38%|███▊ | 5705/15000 [26:21:44<50:23:10, 19.51s/it] 38%|███▊ | 5706/15000 [26:21:58<46:37:39, 18.06s/it] 38%|███▊ | 5707/15000 [26:22:13<43:54:31, 17.01s/it] 38%|███▊ | 5708/15000 [26:22:27<42:05:33, 16.31s/it] 38%|███▊ | 5709/15000 [26:22:42<40:50:46, 15.83s/it] 38%|███▊ | 5710/15000 [26:22:57<39:52:55, 15.45s/it] 38%|███▊ | 5711/15000 [26:23:11<39:10:40, 15.18s/it] 38%|███▊ | 5712/15000 [26:23:26<38:55:23, 15.09s/it] 38%|███▊ | 5713/15000 [26:23:41<38:37:35, 1[26:21:44<50:22:04, 19.51s/it] 38%|███▊ | 5706/15000 [26:21:58<46:33:59, 18.04s/it] 38%|███▊ | 5707/15000 [26:22:13<43:55:43, 17.02s/it] 38%|███▊ | 5708/15000 [26:22:27<42:07:46, 16.32s/it] 38%|███▊ | 5709/15000 [26:22:42<40:46:32, 15.80s/it] 38%|███▊ | 5710/15000 [26:22:57<39:49:31, 15.43s/it] 38%|███▊ | 5711/15000 [26:23:11<39:15:33, 15.22s/it] 38%|███▊ | 5712/15000 [26:23:26<38:55:17, 15.09s/it] 38%|███▊ | 5713/15000 [26:23:41<38:36:02, 14.96s/it] 38%|███▊ | 5714/15000 [26:23:55<38:22:09, 14.88s/it] 38%|███▊ | 5715/15000 [26:24:10<38:16:28, 14.84s/it] 38%|███▊ | 5716/15000 [26:24:48<56:05:01, 21.75s/it] 38%|███▊ | 5717/15000 [26:25:03<50:40:04, 19.65s/it] 38%|███▊ | 5718/15000 [26:25:18<46:49:13, 18.16s/it] 38%|███▊ | 5719/15000 [26:25:32<44:02:57, 17.09s/it] 38%|███▊ | 5720/15000 [26:25:47<42:12:37
{'loss': 0.8184, 'learning_rate': 0.00014037757648064018, 'epoch': 1.09}
{'loss': 0.8184, 'learning_rate': 0.00014037757648064018, 'epoch': 1.09}
| 5790/15000 [26:45:17<39:39:36, 15.50s/it] 39%|███▊ | 5791/15000 [26:45:32<39:01:19, 15.25s/it] 39%|███▊ | 5792/15000 [26:45:46<38:28:58, 15.05s/it] 39%|███▊ | 5793/15000 [26:46:01<38:17:30, 14.97s/it] 39%|███▊ | 5794/15000 [26:46:16<37:56:10, 14.83s/it] 39%|███▊ | 5795/15000 [26:46:53<55:18:20, 21.63s/it] 39%|███▊ | 5796/15000 [26:47:08<49:56:01, 19.53s/it] 39%|███▊ | 5797/15000 [26:47:22<46:07:55, 18.05s/it] 39%|███▊ | 5798/15000 [26:47:37<43:25:35, 16.99s/it] 39%|███▊ | 5799/15000 [26:47:52<41:46:36, 16.35s/it] 39%|███▊ | 5800/15000 [26:48:07<40:31:55, 15.86s/it] 39%|███▊ | 5800/15000 [26:48:07<40:31:55, 15.86s/it] 39%|███▊ | 5801/15000 [26:48:21<39:44:27, 15.55s/it] 39%|███▊ | 5802/15000 [26:48:36<39:03:18, 15.29s/it] 39%|███▊ | 5803/15000 [26:48:5 | 5790/15000 [26:45:17<39:37:19, 15.49s/it] 39%|███▊ | 5791/15000 [26:45:32<39:02:55, 15.27s/it] 39%|███▊ | 5792/15000 [26:45:46<38:30:05, 15.05s/it] 39%|███▊ | 5793/15000 [26:46:01<38:19:20, 14.98s/it] 39%|███▊ | 5794/15000 [26:46:16<37:58:21, 14.85s/it] 39%|███▊ | 5795/15000 [26:46:53<55:15:19, 21.61s/it] 39%|███▊ | 5796/15000 [26:47:08<49:56:13, 19.53s/it] 39%|███▊ | 5797/15000 [26:47:22<46:08:34, 18.05s/it] 39%|███▊ | 5798/15000 [26:47:37<43:28:59, 17.01s/it] 39%|███▊ | 5799/15000 [26:47:52<41:48:13, 16.36s/it] 39%|███▊ | 5800/15000 [26:48:07<40:31:39, 15.86s/it] 39%|███▊ | 5800/15000 [26:48:07<40:31:39, 15.86s/it] 39%|███▊ | 5801/15000 [26:48:21<39:44:10, 15.55s/it] 39%|███▊ | 5802/15000 [26:48:36<39:00:14, 15.27s/it] 39%|███▊ | 5803/15000 [26:48:5<> | 5797/15000 [26:47:22<46:07:20, 18.04s/it] 39%|███▊ | 5798/15000 [26:47:37<43:31:28, 17.03s/it] 39%|███▊ | 5799/15000 [26:47:52<41:45:39, 16.34s/it] 39%|███▊ | 5800/15000 [26:48:06<40:31:34, 15.86s/it] 39%|███▊ | 5800/15000 [26:48:07<40:31:34, 15.86s/it] 39%|███▊ | 5801/15000 [26:48:21<39:41:36, 15.53s/it] 39%|███▊ | 5802/15000 [26:48:36<39:02:54, 15.28s/it] 39%|███▊ | 5803/15000 [26:48:51<38:31:49, 15.08s/it] 39%|███▊ | 5804/15000 [26:49:05<38:15:42, 14.98s/it] 39%|███▊ | 5805/15000 [26:49:20<38:06:52, 14.92s/it] 39%|███▊ | 5806/15000 [26:49:35<37:58:29, 14.87s/it] 39%|███▊ | 5807/15000 [26:50:12<54:56:14, 21.51s/it] 39%|███▊ | 5808/15000 [26:50:26<49:33:37, 19.41s/it] 39%|███▊ | 5809/15000 [26:50:41<45:57:37, 18.00s/it] 39%|███▊ | 5810/15000 [26:501<38:35:11, 15.10s/it] 39%|███▊ | 5804/15000 [26:49:05<38:12:38, 14.96s/it] 39%|███▊ | 5805/15000 [26:49:20<38:05:29, 14.91s/it] 39%|███▊ | 5806/15000 [26:49:35<37:58:30, 14.87s/it] 39%|███▊ | 5807/15000 [26:50:12<54:58:30, 21.53s/it] 39%|███▊ | 5808/15000 [26:50:27<49:38:43, 19.44s/it] 39%|███▊ | 5809/15000 [26:50:41<45:55:11, 17.99s/it] 39%|███▊ | 5810/15000 [26:50:56<43:22:37, 16.99s/it] 39%|███▊ | 5811/15000 [26:51:10<41:32:11, 16.27s/it] 39%|███▊ | 5812/15000 [26:51:25<40:18:38, 15.79s/it] 39%|███▉ | 5813/15000 [26:51:40<39:32:19, 15.49s/it] 39%|███▉ | 5814/15000 [26:51:54<38:52:27, 15.23s/it] 39%|███▉ | 5815/15000 [26:52:09<38:26:58, 15.07s/it] 39%|███▉ | 5816/15000 [26:52:24<38:03:48, 14.92s/it] 39%|███▉ | 5817/15000 [26:52:38<37:51:33, 14.84s/it] 39%|███▉ | 5818/15000 [26:53:15<54:43:34, 21.46s
{'loss': 0.8152, 'learning_rate': 0.00013839298417611963, 'epoch': 1.1}
{'loss': 0.8152, 'learning_rate': 0.00013839298417611963, 'epoch': 1.1}
%|███▉ | 5887/15000 [27:12:29<50:05:15, 19.79s/it] 39%|███▉ | 5888/15000 [27:12:43<46:11:07, 18.25s/it] 39%|███▉ | 5889/15000 [27:12:58<43:27:24, 17.17s/it] 39%|███▉ | 5890/15000 [27:13:12<41:30:28, 16.40s/it] 39%|███▉ | 5891/15000 [27:13:27<40:09:33, 15.87s/it] 39%|███▉ | 5892/15000 [27:13:42<39:13:30, 15.50s/it] 39%|███▉ | 5893/15000 [27:13:56<38:38:30, 15.28s/it] 39%|███▉ | 5894/15000 [27:14:11<38:12:19, 15.10s/it] 39%|███▉ | 5895/15000 [27:14:26<37:48:40, 14.95s/it] 39%|███▉ | 5896/15000 [27:14:40<37:33:22, 14.85s/it] 39%|███▉ | 5897/15000 [27:14:55<37:32:10, 14.84s/it] 39%|███▉ | 5898/15000 [27:15:34<55:49:44, 22.08s/it] 39%|███▉ | 5899/15000 [27:15:49<50:16:02, 19.88s/it] 39%|███▉ | 5900/15000 [27:16:04<46:16:50, 18.31s/it] 39%|███▉ | 5900 5895/15000 [27:14:26<37:55:32, 15.00s/it] 39%|███▉ | 5896/15000 [27:14:40<37:34:41, 14.86s/it] 39%|███▉ | 5897/15000 [27:14:55<37:30:42, 14.83s/it] 39%|███▉ | 5898/15000 [27:15:34<55:43:42, 22.04s/it] 39%|███▉ | 5899/15000 [27:15:49<50:18:10, 19.90s/it] 39%|███▉ | 5900/15000 [27:16:04<46:17:42, 18.31s/it] 39%|███▉ | 5900/15000 [27:16:04<46:17:42, 18.31s/it] 39%|███▉ | 5901/15000 [27:16:18<43:36:37, 17.25s/it] 39%|███▉ | 5902/15000 [27:16:33<41:39:30, 16.48s/it] 39%|███▉ | 5903/15000 [27:16:48<40:18:00, 15.95s/it] 39%|███▉ | 5904/15000 [27:17:02<39:21:21, 15.58s/it] 39%|███▉ | 5905/15000 [27:17:17<38:39:43, 15.30s/it] 39%|███▉ | 5906/15000 [27:17:32<38:10:17, 15.11s/it] 39%|███▉ | 5907/15000 [27:17:46<37:47:51, 14.96s/it] 39%|███▉ | 5908/15000 [27:18:01<37:3 5895/15000 [27:14:26<37:50:53, 14.96s/it] 39%|███▉ | 5896/15000 [27:14:40<37:34:15, 14.86s/it] 39%|███▉ | 5897/15000 [27:14:55<37:28:38, 14.82s/it] 39%|███▉ | 5898/15000 [27:15:34<55:47:11, 22.06s/it] 39%|███▉ | 5899/15000 [27:15:49<50:16:48, 19.89s/it] 39%|███▉ | 5900/15000 [27:16:04<46:18:05, 18.32s/it] 39%|███▉ | 5900/15000 [27:16:04<46:18:05, 18.32s/it] 39%|███▉ | 5901/15000 [27:16:18<43:39:18, 17.27s/it] 39%|███▉ | 5902/15000 [27:16:33<41:42:05, 16.50s/it] 39%|███▉ | 5903/15000 [27:16:48<40:16:46, 15.94s/it] 39%|███▉ | 5904/15000 [27:17:03<39:22:38, 15.58s/it] 39%|███▉ | 5905/15000 [27:17:17<38:41:50, 15.32s/it] 39%|███▉ | 5906/15000 [27:17:32<38:06:38, 15.09s/it] 39%|███▉ | 5907/15000 [27:17:46<37:48:38, 14.97s/it] 39%|███▉ | 5908/15000 [27:18:01<37:3/15000 [27:16:04<46:16:50, 18.31s/it] 39%|███▉ | 5901/15000 [27:16:18<43:37:36, 17.26s/it] 39%|███▉ | 5902/15000 [27:16:33<41:40:04, 16.49s/it] 39%|███▉ | 5903/15000 [27:16:48<40:15:29, 15.93s/it] 39%|███▉ | 5904/15000 [27:17:02<39:20:53, 15.57s/it] 39%|███▉ | 5905/15000 [27:17:17<38:36:16, 15.28s/it] 39%|███▉ | 5906/15000 [27:17:32<38:10:31, 15.11s/it] 39%|███▉ | 5907/15000 [27:17:46<37:44:47, 14.94s/it] 39%|███▉ | 5908/15000 [27:18:01<37:37:27, 14.90s/it] 39%|███▉ | 5909/15000 [27:18:40<55:26:33, 21.96s/it] 39%|███▉ | 5910/15000 [27:18:54<49:53:37, 19.76s/it] 39%|███▉ | 5911/15000 [27:19:09<46:01:29, 18.23s/it] 39%|███▉ | 5912/15000 [27:19:24<43:22:29, 17.18s/it] 39%|███▉ | 5913/15000 [27:19:38<41:26:50, 16.42s/it] 39%|███▉ | 5914/15000 [27:19:53<40:05:57, 15.89s/it] 39%|███▉ | 5915/15000 [27:20:08<3
{'loss': 0.8154, 'learning_rate': 0.00013639049369634876, 'epoch': 1.12}
{'loss': 0.8154, 'learning_rate': 0.00013639049369634876, 'epoch': 1.12}
<EFBFBD><EFBFBD>█▉ | 5992/15000 [27:41:36<42:43:36, 17.08s/it] 40%|███▉ | 5993/15000 [27:41:50<40:53:58, 16.35s/it] 40%|███▉ | 5994/15000 [27:42:05<39:36:21, 15.83s/it] 40%|███▉ | 5995/15000 [27:42:20<38:51:13, 15.53s/it] 40%|███▉ | 5996/15000 [27:42:34<38:08:02, 15.25s/it] 40%|███▉ | 5997/15000 [27:42:49<37:45:52, 15.10s/it] 40%|███▉ | 5998/15000 [27:43:04<37:27:43, 14.98s/it] 40%|███▉ | 5999/15000 [27:43:18<37:12:36, 14.88s/it] 40%|████ | 6000/15000 [27:43:57<55:13:01, 22.09s/it] 40%|████ | 6000/15000 [27:43:57<55:13:01, 22.09s/it]Saving model checkpoint to /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-6000
tokenizer config file saved in /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-6000/tokenizer_config.json
Special tokens file saved in /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-6000/special_tokens_map.json
15000 [27:43:57<55:12:06, 22.08s/it] 40%|████ | 6000/15000 [27:43:58<55:12:06, 22.08s/it] 40%|████ | 6001/15000 [27:44:17<53:18:35, 21.33s/it] 40%|████ | 6002/15000 [27:44:32<48:27:05, 19.38s/it] 40%|████ | 6003/15000 [27:44:46<44:56:31, 17.98s/it] 40%|████ | 6004/15000 [27:45:01<42:23:17, 16.96s/it] 40%|████ | 6005/15000 [27:45:16<40:34:52, 16.24s/it] 40%|████ | 6006/15000 [27:45:30<39:23:04, 15.76s/it] 40%|████ | 6007/15000 [27:45:45<38:29:58, 15.41s/it] 40%|████ | 6008/15000 [27:46:00<38:02:12, 15.23s/it] 40%|████ | 6009/15000 [27:46:14<37:37:10, 15.06s/it] 40%|████ | 6010/15000 [27:46:29<37:26:14, 14.99s/it] 40%|████ | 6011/15000 [27:47:08<55:19:35, 22.16s/it] 40%|████ | 6012/15000 [27:47:23<49:38:45, 19.88s/it] 40%|████ | 6013/15000 [27:47:37<45:48:34, 15000 [27:43:57<55:08:32, 22.06s/it] 40%|████ | 6000/15000 [27:43:57<55:08:32, 22.06s/it] 40%|████ | 6001/15000 [27:44:17<53:16:56, 21.32s/it] 40%|████ | 6002/15000 [27:44:32<48:25:40, 19.38s/it] 40%|████ | 6003/15000 [27:44:46<44:57:54, 17.99s/it] 40%|████ | 6004/15000 [27:45:01<42:26:50, 16.99s/it] 40%|████ | 6005/15000 [27:45:16<40:37:22, 16.26s/it] 40%|████ | 6006/15000 [27:45:30<39:24:41, 15.78s/it] 40%|████ | 6007/15000 [27:45:45<38:34:45, 15.44s/it] 40%|████ | 6008/15000 [27:46:00<38:02:59, 15.23s/it] 40%|████ | 6009/15000 [27:46:14<37:36:43, 15.06s/it] 40%|████ | 6010/15000 [27:46:29<37:21:01, 14.96s/it] 40%|████ | 6011/15000 [27:47:08<55:18:19, 22.15s/it] 40%|████ | 6012/15000 [27:47:23<49:41:13, 19.90s/it] 40%|████ | 6013/15000 [27:47:37<45:48:21, 40%|████ | 6001/15000 [27:44:17<53:24:23, 21.36s/it] 40%|████ | 6002/15000 [27:44:32<48:22:36, 19.35s/it] 40%|████ | 6003/15000 [27:44:46<44:54:16, 17.97s/it] 40%|████ | 6004/15000 [27:45:01<42:20:39, 16.95s/it] 40%|████ | 6005/15000 [27:45:16<40:36:36, 16.25s/it] 40%|████ | 6006/15000 [27:45:30<39:21:11, 15.75s/it] 40%|████ | 6007/15000 [27:45:45<38:37:55, 15.46s/it] 40%|████ | 6008/15000 [27:46:00<38:02:25, 15.23s/it] 40%|████ | 6009/15000 [27:46:14<37:37:23, 15.06s/it] 40%|████ | 6010/15000 [27:46:29<37:25:46, 14.99s/it] 40%|████ | 6011/15000 [27:47:08<55:16:46, 22.14s/it] 40%|████ | 6012/15000 [27:47:23<49:41:35, 19.90s/it] 40%|████ | 6013/15000 [27:47:37<45:48:34, 18.35s/it] 40%|████ | 6014/15000 [27:47:52<43:00:13, 17.23s/it] 40%|████ | 6015/15000 [27:48:07<41:02:53, 16.45s/it] 40%|████ 18.35s/it] 40%|████ | 6014/15000 [27:47:52<42:54:40, 17.19s/it] 40%|████ | 6015/15000 [27:48:07<41:09:27, 16.49s/it] 40%|████ | 6016/15000 [27:48:21<39:41:03, 15.90s/it] 40%|████ | 6017/15000 [27:48:36<38:41:22, 15.51s/it] 40%|████ | 6018/15000 [27:48:50<38:00:41, 15.24s/it] 40%|████ | 6019/15000 [27:49:05<37:32:32, 15.05s/it] 40%|████ | 6020/15000 [27:49:20<37:17:19, 14.95s/it] 40%|████ | 6021/15000 [27:49:34<37:04:56, 14.87s/it] 40%|████ | 6022/15000 [27:49:49<36:59:17, 14.83s/it] 40%|████ | 6023/15000 [27:50:28<54:47:08, 21.97s/it] 40%|████ | 6024/15000 [27:50:43<49:23:30, 19.81s/it] 40%|████ | 6025/15000 [27:50:57<45:29:21, 18.25s/it] 40%|████ | 6026/15000 [27:51:12<42:50:53, 17.19s/it] 40%|████ | 6027/15000 [27:51:27<41:00:35, 16.45s/it] 40%|████ | 6028/15000 [27:51:41<39:36:39, 15.89s/it] 40%|<7C><>
{'loss': 0.8127, 'learning_rate': 0.00013437103856932264, 'epoch': 1.14}
{'loss': 0.8127, 'learning_rate': 0.00013437103856932264, 'epoch': 1.14}
| 6090/15000 [28:08:47<36:38:13, 14.80s/it] 41%|████ | 6091/15000 [28:09:25<53:28:33, 21.61s/it] 41%|████ | 6092/15000 [28:09:40<48:18:19, 19.52s/it] 41%|████ | 6093/15000 [28:09:54<44:49:05, 18.11s/it] 41%|████ | 6094/15000 [28:10:09<42:16:17, 17.09s/it] 41%|████ | 6095/15000 [28:10:24<40:30:16, 16.37s/it] 41%|████ | 6096/15000 [28:10:39<39:14:45, 15.87s/it] 41%|████ | 6097/15000 [28:10:53<38:30:03, 15.57s/it] 41%|████ | 6098/15000 [28:11:08<37:50:36, 15.30s/it] 41%|████ | 6099/15000 [28:11:23<37:25:34, 15.14s/it] 41%|████ | 6100/15000 [28:11:37<36:56:29, 14.94s/it] 41%|████ | 6100/15000 [28:11:38<36:56:29, 14.94s/it] 41%|████ | 6101/15000 [28:11:52<36:57:36, 14.95s/it] 41%|████ | 6102/15000 [28:12:30<53:30:25, 21.65s/it] 41%|████ | 6103/15000 [28:12: | 6090/15000 [28:08:47<36:33:35, 14.77s/it] 41%|████ | 6091/15000 [28:09:25<53:28:29, 21.61s/it] 41%|████ | 6092/15000 [28:09:40<48:20:44, 19.54s/it] 41%|████ | 6093/15000 [28:09:54<44:41:23, 18.06s/it] 41%|████ | 6094/15000 [28:10:09<42:14:16, 17.07s/it] 41%|████ | 6095/15000 [28:10:24<40:32:44, 16.39s/it] 41%|████ | 6096/15000 [28:10:39<39:20:04, 15.90s/it] 41%|████ | 6097/15000 [28:10:53<38:25:44, 15.54s/it] 41%|████ | 6098/15000 [28:11:08<37:46:32, 15.28s/it] 41%|████ | 6099/15000 [28:11:23<37:22:11, 15.11s/it] 41%|████ | 6100/15000 [28:11:37<36:59:23, 14.96s/it] 41%|████ | 6100/15000 [28:11:38<36:59:23, 14.96s/it] 41%|████ | 6101/15000 [28:11:52<36:55:26, 14.94s/it] 41%|████ | 6102/15000 [28:12:29<53:31:13, 21.65s/it] 41%|████ | 6103/15000 [28:12:48:20:39, 19.54s/it] 41%|████ | 6093/15000 [28:09:54<44:44:04, 18.08s/it] 41%|████ | 6094/15000 [28:10:09<42:17:42, 17.10s/it] 41%|████ | 6095/15000 [28:10:24<40:31:57, 16.39s/it] 41%|████ | 6096/15000 [28:10:39<39:14:46, 15.87s/it] 41%|████ | 6097/15000 [28:10:53<38:25:22, 15.54s/it] 41%|████ | 6098/15000 [28:11:08<37:50:15, 15.30s/it] 41%|████ | 6099/15000 [28:11:23<37:21:40, 15.11s/it] 41%|████ | 6100/15000 [28:11:37<37:01:33, 14.98s/it] 41%|████ | 6100/15000 [28:11:38<37:01:33, 14.98s/it] 41%|████ | 6101/15000 [28:11:52<36:57:04, 14.95s/it] 41%|████ | 6102/15000 [28:12:29<53:30:39, 21.65s/it] 41%|████ | 6103/15000 [28:12:44<48:22:17, 19.57s/it] 41%|████ | 6104/15000 [28:12:59<44:42:51, 18.09s/it] 41%|████ | 6105/15000 [28:13:14<42:15:39, 17.10s/it] 41%|44<48:23:49, 19.58s/it] 41%|████ | 6104/15000 [28:12:59<44:44:53, 18.11s/it] 41%|████ | 6105/15000 [28:13:14<42:13:56, 17.09s/it] 41%|████ | 6106/15000 [28:13:28<40:27:47, 16.38s/it] 41%|████ | 6107/15000 [28:13:43<39:13:29, 15.88s/it] 41%|████ | 6108/15000 [28:13:58<38:24:34, 15.55s/it] 41%|████ | 6109/15000 [28:14:13<37:49:29, 15.32s/it] 41%|████ | 6110/15000 [28:14:27<37:21:26, 15.13s/it] 41%|████ | 6111/15000 [28:14:42<37:07:09, 15.03s/it] 41%|████ | 6112/15000 [28:14:57<36:51:25, 14.93s/it] 41%|████ | 6113/15000 [28:15:34<53:36:12, 21.71s/it] 41%|████ | 6114/15000 [28:15:49<48:22:01, 19.60s/it] 41%|████ | 6115/15000 [28:16:04<44:39:34, 18.10s/it] 41%|████ | 6116/15000 [28:16:18<42:06:22, 17.06s/it] 41%|████ | 6117/15000 [28:16:33<40:16:08, 16.32s/it] 41%|████ | 6118/15000 [28:16:47<38:57:20, 15.79
{'loss': 0.8118, 'learning_rate': 0.00013233556023167485, 'epoch': 1.16}
{'loss': 0.8118, 'learning_rate': 0.00013233556023167485, 'epoch': 1.16}
<EFBFBD><EFBFBD>██▏ | 6195/15000 [28:38:23<44:34:25, 18.22s/it] 41%|████▏ | 6196/15000 [28:38:38<41:57:37, 17.16s/it] 41%|████▏ | 6197/15000 [28:38:52<40:09:43, 16.42s/it] 41%|████▏ | 6198/15000 [28:39:07<38:50:39, 15.89s/it] 41%|████▏ | 6199/15000 [28:39:21<37:53:18, 15.50s/it] 41%|████▏ | 6200/15000 [28:39:36<37:15:38, 15.24s/it] 41%|████▏ | 6200/15000 [28:39:36<37:15:38, 15.24s/it] 41%|████▏ | 6201/15000 [28:39:51<36:58:05, 15.13s/it] 41%|████▏ | 6202/15000 [28:40:06<36:39:46, 15.00s/it] 41%|████▏ | 6203/15000 [28:40:20<36:18:15, 14.86s/it] 41%|████▏ | 6204/15000 [28:40:58<53:18:16, 21.82s/it] 41%|████▏ | 6205/15000 [28:41:13<48:08:42, 19.71s/it] 41%|████▏ | 6206/15000 [28:41:28<44:34:02, 18.24s/it] 41%|████▏ | 6207/15000 [28:41:43<42:03:34, 17.22s/it] 41%|▖<>██▏ | 6195/15000 [28:38:23<44:33:40, 18.22s/it] 41%|████▏ | 6196/15000 [28:38:38<42:01:18, 17.18s/it] 41%|████▏ | 6197/15000 [28:38:52<40:10:20, 16.43s/it] 41%|████▏ | 6198/15000 [28:39:07<38:51:29, 15.89s/it] 41%|████▏ | 6199/15000 [28:39:22<37:55:38, 15.51s/it] 41%|████▏ | 6200/15000 [28:39:36<37:12:52, 15.22s/it] 41%|████▏ | 6200/15000 [28:39:36<37:12:52, 15.22s/it] 41%|████▏ | 6201/15000 [28:39:51<36:59:46, 15.14s/it] 41%|████▏ | 6202/15000 [28:40:06<36:36:18, 14.98s/it] 41%|████▏ | 6203/15000 [28:40:20<36:20:06, 14.87s/it] 41%|████▏ | 6204/15000 [28:40:58<53:16:56, 21.81s/it] 41%|████▏ | 6205/15000 [28:41:13<48:03:23, 19.67s/it] 41%|████▏ | 6206/15000 [28:41:28<44:34:21, 18.25s/it] 41%|████▏ | 6207/15000 [28:41:43<42:04:20, 17.23s/it] 41%|<7C><>000 [28:38:52<40:07:46, 16.41s/it] 41%|████▏ | 6198/15000 [28:39:07<38:48:37, 15.87s/it] 41%|████▏ | 6199/15000 [28:39:22<37:55:59, 15.52s/it] 41%|████▏ | 6200/15000 [28:39:36<37:18:14, 15.26s/it] 41%|████▏ | 6200/15000 [28:39:36<37:18:14, 15.26s/it] 41%|████▏ | 6201/15000 [28:39:51<36:58:20, 15.13s/it] 41%|████▏ | 6202/15000 [28:40:06<36:33:31, 14.96s/it] 41%|████▏ | 6203/15000 [28:40:20<36:19:33, 14.87s/it] 41%|████▏ | 6204/15000 [28:40:58<53:18:57, 21.82s/it] 41%|████▏ | 6205/15000 [28:41:13<48:10:38, 19.72s/it] 41%|████▏ | 6206/15000 [28:41:28<44:35:36, 18.26s/it] 41%|████▏ | 6207/15000 [28:41:43<42:00:24, 17.20s/it] 41%|████▏ | 6208/15000 [28:41:57<40:08:17, 16.44s/it] 41%|████▏ | 6209/15000 [28:42:12<38:53:19, 15.93s/it] 41%|████▏ | 6210/<2F>███▏ | 6208/15000 [28:41:57<40:11:05, 16.45s/it] 41%|████▏ | 6209/15000 [28:42:12<38:49:46, 15.90s/it] 41%|████▏ | 6210/15000 [28:42:27<37:56:21, 15.54s/it] 41%|████▏ | 6211/15000 [28:42:41<37:20:46, 15.30s/it] 41%|████▏ | 6212/15000 [28:42:56<36:49:43, 15.09s/it] 41%|████▏ | 6213/15000 [28:43:11<36:35:34, 14.99s/it] 41%|████▏ | 6214/15000 [28:43:25<36:19:30, 14.88s/it] 41%|████▏ | 6215/15000 [28:43:40<36:14:04, 14.85s/it] 41%|████▏ | 6216/15000 [28:44:18<52:59:47, 21.72s/it] 41%|████▏ | 6217/15000 [28:44:33<47:55:36, 19.64s/it] 41%|████▏ | 6218/15000 [28:44:47<44:12:31, 18.12s/it] 41%|████▏ | 6219/15000 [28:45:02<41:46:38, 17.13s/it] 41%|████▏ | 6220/15000 [28:45:17<39:55:59, 16.37s/it] 41%|████▏ | 6221/15000 [28:45:32<38:45:22, 15.89s/it] 41%|████▏ | 6222/15000 [28:45:46<37:51:03, 15.52s
{'loss': 0.8108, 'learning_rate': 0.00013028500758979506, 'epoch': 1.18}
{'loss': 0.8108, 'learning_rate': 0.00013028500758979506, 'epoch': 1.18}
<EFBFBD>██▏ | 6297/15000 [29:06:46<44:11:25, 18.28s/it] 42%|████▏ | 6298/15000 [29:07:01<41:32:42, 17.19s/it] 42%|████▏ | 6299/15000 [29:07:16<39:44:41, 16.44s/it] 42%|████▏ | 6300/15000 [29:07:30<38:22:38, 15.88s/it] 42%|████▏ | 6300/15000 [29:07:31<38:22:38, 15.88s/it] 42%|████▏ | 6301/15000 [29:07:45<37:35:24, 15.56s/it] 42%|████▏ | 6302/15000 [29:08:00<36:58:20, 15.30s/it] 42%|████▏ | 6303/15000 [29:08:14<36:27:20, 15.09s/it] 42%|████▏ | 6304/15000 [29:08:29<36:08:19, 14.96s/it] 42%|████▏ | 6305/15000 [29:08:44<35:57:19, 14.89s/it] 42%|████▏ | 6306/15000 [29:08:58<35:46:14, 14.81s/it] 42%|████▏ | 6307/15000 [29:09:38<53:22:29, 22.10s/it] 42%|████▏ | 6308/15000 [29:09:52<47:52:35, 19.83s/it] 42%|████▏ | 6309/15000 [29:10:07<44:09:39, 18.29s/it] 42%|█<>██▏ | 6297/15000 [29:06:47<44:13:03, 18.29s/it] 42%|████▏ | 6298/15000 [29:07:01<41:35:02, 17.20s/it] 42%|████▏ | 6299/15000 [29:07:16<39:41:12, 16.42s/it] 42%|████▏ | 6300/15000 [29:07:31<38:28:04, 15.92s/it] 42%|████▏ | 6300/15000 [29:07:31<38:28:04, 15.92s/it] 42%|████▏ | 6301/15000 [29:07:45<37:31:53, 15.53s/it] 42%|████▏ | 6302/15000 [29:08:00<36:58:50, 15.31s/it] 42%|████▏ | 6303/15000 [29:08:15<36:27:41, 15.09s/it] 42%|████▏ | 6304/15000 [29:08:29<36:07:23, 14.95s/it] 42%|████▏ | 6305/15000 [29:08:44<35:57:26, 14.89s/it] 42%|████▏ | 6306/15000 [29:08:59<35:53:51, 14.86s/it] 42%|████▏ | 6307/15000 [29:09:38<53:17:23, 22.07s/it] 42%|████▏ | 6308/15000 [29:09:52<47:54:22, 19.84s/it] 42%|████▏ | 6309/15000 [29:10:07<44:11:25, 18.30s/it] 42%|█00 [29:07:16<39:37:27, 16.39s/it] 42%|████▏ | 6300/15000 [29:07:30<38:29:25, 15.93s/it] 42%|████▏ | 6300/15000 [29:07:31<38:29:25, 15.93s/it] 42%|████▏ | 6301/15000 [29:07:45<37:33:47, 15.55s/it] 42%|████▏ | 6302/15000 [29:08:00<36:54:55, 15.28s/it] 42%|████▏ | 6303/15000 [29:08:14<36:25:21, 15.08s/it] 42%|████▏ | 6304/15000 [29:08:29<36:09:39, 14.97s/it] 42%|████▏ | 6305/15000 [29:08:44<35:59:24, 14.90s/it] 42%|████▏ | 6306/15000 [29:08:59<35:52:06, 14.85s/it] 42%|████▏ | 6307/15000 [29:09:38<53:18:03, 22.07s/it] 42%|████▏ | 6308/15000 [29:09:52<47:53:21, 19.83s/it] 42%|████▏ | 6309/15000 [29:10:07<44:10:43, 18.30s/it] 42%|████▏ | 6310/15000 [29:10:21<41:29:19, 17.19s/it] 42%|████▏ | 6311/15000 [29:10:36<39:39:39, 16.43s/it] 42%|████▏ | 6312/1███▏ | 6310/15000 [29:10:21<41:30:05, 17.19s/it] 42%|████▏ | 6311/15000 [29:10:36<39:35:59, 16.41s/it] 42%|████▏ | 6312/15000 [29:10:51<38:23:47, 15.91s/it] 42%|████▏ | 6313/15000 [29:11:05<37:28:11, 15.53s/it] 42%|████▏ | 6314/15000 [29:11:20<36:51:27, 15.28s/it] 42%|████▏ | 6315/15000 [29:11:35<36:17:11, 15.04s/it] 42%|████▏ | 6316/15000 [29:11:49<36:00:14, 14.93s/it] 42%|████▏ | 6317/15000 [29:12:04<35:52:37, 14.87s/it] 42%|████▏ | 6318/15000 [29:12:43<53:17:05, 22.09s/it] 42%|████▏ | 6319/15000 [29:12:58<47:52:03, 19.85s/it] 42%|████▏ | 6320/15000 [29:13:12<44:10:40, 18.32s/it] 42%|████▏ | 6321/15000 [29:13:27<41:30:24, 17.22s/it] 42%|████▏ | 6322/15000 [29:13:42<39:40:53, 16.46s/it] 42%|████▏ | 6323/15000 [29:13:56<38:28:41, 15.96s/it] 42%|████▏ | 6324/15000 [29:14:11<37:26:11, 15.53s/
{'loss': 0.8066, 'learning_rate': 0.00012822033657746478, 'epoch': 1.2}
{'loss': 0.8066, 'learning_rate': 0.00012822033657746478, 'epoch': 1.2}
<51:40:39, 21.60s/it] 43%|████▎ | 6387/15000 [29:31:52<46:45:09, 19.54s/it] 43%|████▎ | 6388/15000 [29:32:07<43:14:42, 18.08s/it] 43%|████▎ | 6389/15000 [29:32:21<40:48:17, 17.06s/it] 43%|████▎ | 6390/15000 [29:32:36<39:03:59, 16.33s/it] 43%|████▎ | 6391/15000 [29:32:51<37:55:43, 15.86s/it] 43%|████▎ | 6392/15000 [29:33:05<37:02:03, 15.49s/it] 43%|████▎ | 6393/15000 [29:33:20<36:21:57, 15.21s/it] 43%|████▎ | 6394/15000 [29:33:35<36:02:53, 15.08s/it] 43%|████▎ | 6395/15000 [29:33:49<35:46:12, 14.96s/it] 43%|████▎ | 6396/15000 [29:34:04<35:29:17, 14.85s/it] 43%|████▎ | 6397/15000 [29:34:43<52:30:19, 21.97s/it] 43%|████▎ | 6398/15000 [29:34:57<47:10:43, 19.74s/it] 43%|████▎ | 6399/15000 [29:35:12<43:32:16, 18.22s/it] 43%|████▎ | 6400/15000 [29:35:26<40:56:36, 17.14s/it] ██▎ | 6399/15000 [29:35:12<43:35:35, 18.25s/it] 43%|████▎ | 6400/15000 [29:35:26<40:52:47, 17.11s/it] 43%|████▎ | 6400/15000 [29:35:27<40:52:47, 17.11s/it] 43%|████▎ | 6401/15000 [29:35:41<39:14:20, 16.43s/it] 43%|████▎ | 6402/15000 [29:35:56<37:56:46, 15.89s/it] 43%|████▎ | 6403/15000 [29:36:11<37:03:36, 15.52s/it] 43%|████▎ | 6404/15000 [29:36:25<36:27:43, 15.27s/it] 43%|████▎ | 6405/15000 [29:36:40<35:58:11, 15.07s/it] 43%|████▎ | 6406/15000 [29:36:55<35:44:21, 14.97s/it] 43%|████▎ | 6407/15000 [29:37:09<35:30:03, 14.87s/it] 43%|████▎ | 6408/15000 [29:37:24<35:21:44, 14.82s/it] 43%|████▎ | 6409/15000 [29:38:03<52:34:22, 22.03s/it] 43%|████▎ | 6410/15000 [29:38:17<47:18:30, 19.83s/it] 43%|████▎ | 6411/15000 [29:38:32<43:34:43, 18.27s/it] 43%|█<>██▎ | 6399/15000 [29:35:12<43:36:26, 18.25s/it] 43%|████▎ | 6400/15000 [29:35:26<40:50:30, 17.10s/it] 43%|████▎ | 6400/15000 [29:35:27<40:50:30, 17.10s/it] 43%|████▎ | 6401/15000 [29:35:41<39:17:51, 16.45s/it] 43%|████▎ | 6402/15000 [29:35:56<37:57:12, 15.89s/it] 43%|████▎ | 6403/15000 [29:36:11<37:02:38, 15.51s/it] 43%|████▎ | 6404/15000 [29:36:25<36:24:44, 15.25s/it] 43%|████▎ | 6405/15000 [29:36:40<36:02:07, 15.09s/it] 43%|████▎ | 6406/15000 [29:36:54<35:37:24, 14.92s/it] 43%|████▎ | 6407/15000 [29:37:09<35:33:36, 14.90s/it] 43%|████▎ | 6408/15000 [29:37:24<35:24:26, 14.84s/it] 43%|████▎ | 6409/15000 [29:38:03<52:34:13, 22.03s/it] 43%|████▎ | 6410/15000 [29:38:18<47:22:53, 19.86s/it] 43%|████▎ | 6411/15000 [29:38:32<43:31:54, 18.25s/it] 43%|█<> 43%|████▎ | 6400/15000 [29:35:27<40:56:36, 17.14s/it] 43%|████▎ | 6401/15000 [29:35:41<39:17:26, 16.45s/it] 43%|████▎ | 6402/15000 [29:35:56<37:59:46, 15.91s/it] 43%|████▎ | 6403/15000 [29:36:11<37:04:25, 15.52s/it] 43%|████▎ | 6404/15000 [29:36:25<36:22:37, 15.23s/it] 43%|████▎ | 6405/15000 [29:36:40<35:59:59, 15.08s/it] 43%|████▎ | 6406/15000 [29:36:54<35:41:59, 14.95s/it] 43%|████▎ | 6407/15000 [29:37:09<35:28:24, 14.86s/it] 43%|████▎ | 6408/15000 [29:37:24<35:20:43, 14.81s/it] 43%|████▎ | 6409/15000 [29:38:03<52:34:07, 22.03s/it] 43%|████▎ | 6410/15000 [29:38:17<47:19:32, 19.83s/it] 43%|████▎ | 6411/15000 [29:38:32<43:35:26, 18.27s/it] 43%|████▎ | 6412/15000 [29:38:47<40:59:00, 17.18s/it] 43%|████▎ | 6413/15000 [29:39:01<39:10:54, 16.43s/it] 43%|████▎ | 6414/1
| 6486/15000 [29:59:11<35:19:43, 14.94s/it] 43%|████▎ | 6487/15000 [29:59:26<35:11:00, 14.88s/it] 43%|████▎ | 6488/15000 [30:00:03<50:46:38, 21.48s/it] 43%|████▎ | 6489/15000 [30:00:18<46:00:10, 19.46s/it] 43%|████▎ | 6490/15000 [30:00:32<42:27:45, 17.96s/it] 43%|████▎ | 6491/15000 [30:00:47<40:09:00, 16.99s/it] 43%|████▎ | 6492/15000 [30:01:01<38:29:24, 16.29s/it] 43%|████▎ | 6493/15000 [30:01:16<37:22:57, 15.82s/it] 43%|████▎ | 6494/15000 [30:01:31<36:40:13, 15.52s/it] 43%|████▎ | 6495/15000 [30:01:46<36:07:57, 15.29s/it] 43%|████▎ | 6496/15000 [30:02:01<35:44:35, 15.13s/it] 43%|████▎ | 6497/15000 [30:02:15<35:21:37, 14.97s/it] 43%|████▎ | 6498/15000 [30:02:30<35:15:31, 14.93s/it] 43%|████▎ | 6499/15000 [30:03:07<51:05:11, 21.63s/it] 43%|████▎ | 6500/15000 [30:03:22<46:06:12, 19.53s/it] {'loss': 0.7995, 'learning_rate': 0.00012614250971021657, 'epoch': 1.22}
{'loss': 0.7995, 'learning_rate': 0.00012614250971021657, 'epoch': 1.22}
| 6486/15000 [29:59:11<35:22:43, 14.96s/it] 43%|████▎ | 6487/15000 [29:59:26<35:16:58, 14.92s/it] 43%|████▎ | 6488/15000 [30:00:03<50:44:29, 21.46s/it] 43%|████▎ | 6489/15000 [30:00:18<46:01:20, 19.47s/it] 43%|████▎ | 6490/15000 [30:00:32<42:28:01, 17.96s/it] 43%|████▎ | 6491/15000 [30:00:47<40:09:06, 16.99s/it] 43%|████▎ | 6492/15000 [30:01:02<38:32:11, 16.31s/it] 43%|████▎ | 6493/15000 [30:01:16<37:22:06, 15.81s/it] 43%|████▎ | 6494/15000 [30:01:31<36:35:19, 15.49s/it] 43%|████▎ | 6495/15000 [30:01:46<36:05:14, 15.28s/it] 43%|████▎ | 6496/15000 [30:02:01<35:45:15, 15.14s/it] 43%|████▎ | 6497/15000 [30:02:15<35:24:38, 14.99s/it] 43%|████▎ | 6498/15000 [30:02:30<35:14:13, 14.92s/it] 43%|████▎ | 6499/15000 [30:03:07<51:03:55, 21.63s/it] 43%|████▎ | 6500/15000 [30:03:22<46:08:14, 19.54s/it] 50:48:42, 21.49s/it] 43%|████▎ | 6489/15000 [30:00:18<45:55:21, 19.42s/it] 43%|████▎ | 6490/15000 [30:00:32<42:30:08, 17.98s/it] 43%|████▎ | 6491/15000 [30:00:47<40:10:11, 17.00s/it] 43%|████▎ | 6492/15000 [30:01:02<38:33:09, 16.31s/it] 43%|████▎ | 6493/15000 [30:01:16<37:23:55, 15.83s/it] 43%|████▎ | 6494/15000 [30:01:31<36:39:10, 15.51s/it] 43%|████▎ | 6495/15000 [30:01:46<36:04:20, 15.27s/it] 43%|████▎ | 6496/15000 [30:02:00<35:40:16, 15.10s/it] 43%|████▎ | 6497/15000 [30:02:15<35:27:11, 15.01s/it] 43%|████▎ | 6498/15000 [30:02:30<35:09:18, 14.89s/it] 43%|████▎ | 6499/15000 [30:03:07<51:05:23, 21.64s/it] 43%|████▎ | 6500/15000 [30:03:22<46:04:36, 19.51s/it] 43%|████▎ | 6500/15000 [30:03:22<46:04:36, 19.51s/it] 43%|████▎ | 6501/15000 [30:03:3 43%|████▎ | 6500/15000 [30:03:22<46:08:14, 19.54s/it] 43%|████▎ | 6501/15000 [30:03:37<42:43:28, 18.10s/it] 43%|████▎ | 6502/15000 [30:03:51<40:12:42, 17.03s/it] 43%|████▎ | 6503/15000 [30:04:06<38:37:09, 16.36s/it] 43%|████▎ | 6504/15000 [30:04:21<37:27:42, 15.87s/it] 43%|████▎ | 6505/15000 [30:04:35<36:37:05, 15.52s/it] 43%|████▎ | 6506/15000 [30:04:50<36:02:03, 15.27s/it] 43%|████▎ | 6507/15000 [30:05:05<35:36:01, 15.09s/it] 43%|████▎ | 6508/15000 [30:05:19<35:16:24, 14.95s/it] 43%|████▎ | 6509/15000 [30:05:34<35:03:25, 14.86s/it] 43%|████▎ | 6510/15000 [30:05:49<34:55:30, 14.81s/it] 43%|████▎ | 6511/15000 [30:06:27<51:11:18, 21.71s/it] 43%|████▎ | 6512/15000 [30:06:41<46:09:31, 19.58s/it] 43%|████▎ | 6513/15000 [30:06:56<42:41:49, 18.11s/it] 43%|█<><E29688> 43%|████▎ | 6500/15000 [30:03:22<46:06:12, 19.53s/it] 43%|████▎ | 6501/15000 [30:03:37<42:45:24, 18.11s/it] 43%|████▎ | 6502/15000 [30:03:51<40:12:08, 17.03s/it] 43%|████▎ | 6503/15000 [30:04:06<38:37:48, 16.37s/it] 43%|████▎ | 6504/15000 [30:04:21<37:24:05, 15.85s/it] 43%|████▎ | 6505/15000 [30:04:35<36:40:35, 15.54s/it] 43%|████▎ | 6506/15000 [30:04:50<36:00:22, 15.26s/it] 43%|████▎ | 6507/15000 [30:05:05<35:31:30, 15.06s/it] 43%|████▎ | 6508/15000 [30:05:19<35:14:35, 14.94s/it] 43%|████▎ | 6509/15000 [30:05:34<35:05:42, 14.88s/it] 43%|████▎ | 6510/15000 [30:05:49<34:56:56, 14.82s/it] 43%|████▎ | 6511/15000 [30:06:26<51:10:04, 21.70s/it] 43%|████▎ | 6512/15000 [30:06:41<46:13:01, 19.60s/it] 43%|████▎ | 6513/15000 [30:06:56<42:42:21, 18.11s/it] 43%|█<>
{'loss': 0.8285, 'learning_rate': 0.00012405249563662537, 'epoch': 1.24}
{'loss': 0.8285, 'learning_rate': 0.00012405249563662537, 'epoch': 1.24}
| 6588/15000 [30:27:35<34:47:52, 14.89s/it] 44%|████▍ | 6589/15000 [30:28:11<50:12:19, 21.49s/it] 44%|████▍ | 6590/15000 [30:28:26<45:28:08, 19.46s/it] 44%|████▍ | 6591/15000 [30:28:41<42:01:34, 17.99s/it] 44%|████▍ | 6592/15000 [30:28:55<39:38:45, 16.98s/it] 44%|████▍ | 6593/15000 [30:29:10<38:05:44, 16.31s/it] 44%|████▍ | 6594/15000 [30:29:25<36:54:20, 15.81s/it] 44%|████▍ | 6595/15000 [30:29:40<36:09:30, 15.49s/it] 44%|████▍ | 6596/15000 [30:29:54<35:37:37, 15.26s/it] 44%|████▍ | 6597/15000 [30:30:09<35:09:47, 15.06s/it] 44%|████▍ | 6598/15000 [30:30:24<35:02:53, 15.02s/it] 44%|████▍ | 6599/15000 [30:30:38<34:41:46, 14.87s/it] 44%|████▍ | 6600/15000 [30:31:15<50:02:11, 21.44s/it] 44%|████▍ | 6600/15000 [30:31:15<50:02:11, 21.44s/it] 44%|████▍ | 6588/15000 [30:27:35<34:52:42, 14.93s/it] 44%|████▍ | 6589/15000 [30:28:12<50:15:40, 21.51s/it] 44%|████▍ | 6590/15000 [30:28:26<45:26:33, 19.45s/it] 44%|████▍ | 6591/15000 [30:28:41<42:08:50, 18.04s/it] 44%|████▍ | 6592/15000 [30:28:56<39:42:36, 17.00s/it] 44%|████▍ | 6593/15000 [30:29:10<37:59:44, 16.27s/it] 44%|████▍ | 6594/15000 [30:29:25<36:51:22, 15.78s/it] 44%|████▍ | 6595/15000 [30:29:40<36:11:43, 15.50s/it] 44%|████▍ | 6596/15000 [30:29:54<35:34:33, 15.24s/it] 44%|████▍ | 6597/15000 [30:30:09<35:13:40, 15.09s/it] 44%|████▍ | 6598/15000 [30:30:24<35:01:30, 15.01s/it] 44%|████▍ | 6599/15000 [30:30:38<34:38:41, 14.85s/it] 44%|████▍ | 6600/15000 [30:31:15<50:01:24, 21.44s/it] 44%|████▍ | 6600/15000 [30:31:15<50:01:24, 21.44s/it] 44%|████▍ 5:28:22, 19.47s/it] 44%|████▍ | 6591/15000 [30:28:41<42:02:32, 18.00s/it] 44%|████▍ | 6592/15000 [30:28:55<39:42:09, 17.00s/it] 44%|████▍ | 6593/15000 [30:29:10<38:00:19, 16.27s/it] 44%|████▍ | 6594/15000 [30:29:25<36:56:22, 15.82s/it] 44%|████▍ | 6595/15000 [30:29:39<36:06:35, 15.47s/it] 44%|████▍ | 6596/15000 [30:29:54<35:32:16, 15.22s/it] 44%|████▍ | 6597/15000 [30:30:09<35:14:19, 15.10s/it] 44%|████▍ | 6598/15000 [30:30:24<34:58:58, 14.99s/it] 44%|████▍ | 6599/15000 [30:30:38<34:43:14, 14.88s/it] 44%|████▍ | 6600/15000 [30:31:15<50:04:12, 21.46s/it] 44%|████▍ | 6600/15000 [30:31:15<50:04:12, 21.46s/it] 44%|████▍ | 6601/15000 [30:31:30<45:26:42, 19.48s/it] 44%|████▍ | 6602/15000 [30:31:45<42:03:44, 18.03s/it] 44%|████▍ | 6603/15000 [30:31:59 | 6601/15000 [30:31:30<45:24:17, 19.46s/it] 44%|████▍ | 6602/15000 [30:31:45<42:07:33, 18.06s/it] 44%|████▍ | 6603/15000 [30:31:59<39:40:45, 17.01s/it] 44%|████▍ | 6604/15000 [30:32:14<37:58:04, 16.28s/it] 44%|████▍ | 6605/15000 [30:32:29<36:53:42, 15.82s/it] 44%|████▍ | 6606/15000 [30:32:43<36:07:06, 15.49s/it] 44%|████▍ | 6607/15000 [30:32:58<35:39:14, 15.29s/it] 44%|████▍ | 6608/15000 [30:33:13<35:06:56, 15.06s/it] 44%|████▍ | 6609/15000 [30:33:27<34:51:48, 14.96s/it] 44%|████▍ | 6610/15000 [30:33:42<34:40:57, 14.88s/it] 44%|████▍ | 6611/15000 [30:33:57<34:26:25, 14.78s/it] 44%|████▍ | 6612/15000 [30:34:34<49:56:09, 21.43s/it] 44%|████▍ | 6613/15000 [30:34:48<45:10:08, 19.39s/it] 44%|████▍ | 6614/15000 [30:35:03<41:46:11, 17.93s/it] 44%|████▍ | 6615/15000 [30:35:17<39:32:04, 16.97s/it] 44%|█<><E29688>
{'loss': 0.8375, 'learning_rate': 0.00012195126868674051, 'epoch': 1.25}
{'loss': 0.8375, 'learning_rate': 0.00012195126868674051, 'epoch': 1.25}
| 6690/15000 [30:56:17<49:33:44, 21.47s/it] 45%|████▍ | 6691/15000 [30:56:32<44:56:10, 19.47s/it] 45%|████▍ | 6692/15000 [30:56:47<41:22:48, 17.93s/it] 45%|████▍ | 6693/15000 [30:57:01<39:12:20, 16.99s/it] 45%|████▍ | 6694/15000 [30:57:16<37:40:02, 16.33s/it] 45%|████▍ | 6695/15000 [30:57:31<36:32:55, 15.84s/it] 45%|████▍ | 6696/15000 [30:57:46<35:48:17, 15.52s/it] 45%|████▍ | 6697/15000 [30:58:00<35:11:08, 15.26s/it] 45%|████▍ | 6698/15000 [30:58:15<34:49:25, 15.10s/it] 45%|████▍ | 6699/15000 [30:58:30<34:38:51, 15.03s/it] 45%|████▍ | 6700/15000 [30:58:44<34:20:17, 14.89s/it] 45%|████▍ | 6700/15000 [30:58:45<34:20:17, 14.89s/it] 45%|████▍ | 6701/15000 [30:59:21<49:40:37, 21.55s/it] 45%|████▍ | 6702/15000 [30:59:36<44:53:00, 19.47s/it] 45%|████▍ | 6690/15000 [30:56:17<49:31:41, 21.46s/it] 45%|████▍ | 6691/15000 [30:56:32<44:50:10, 19.43s/it] 45%|████▍ | 6692/15000 [30:56:47<41:29:00, 17.98s/it] 45%|████▍ | 6693/15000 [30:57:01<39:12:11, 16.99s/it] 45%|████▍ | 6694/15000 [30:57:16<37:37:55, 16.31s/it] 45%|████▍ | 6695/15000 [30:57:31<36:32:43, 15.84s/it] 45%|████▍ | 6696/15000 [30:57:46<35:47:32, 15.52s/it] 45%|████▍ | 6697/15000 [30:58:00<35:12:16, 15.26s/it] 45%|████▍ | 6698/15000 [30:58:15<34:49:34, 15.10s/it] 45%|████▍ | 6699/15000 [30:58:30<34:38:45, 15.03s/it] 45%|████▍ | 6700/15000 [30:58:44<34:20:21, 14.89s/it] 45%|████▍ | 6700/15000 [30:58:45<34:20:21, 14.89s/it] 45%|████▍ | 6701/15000 [30:59:21<49:38:07, 21.53s/it] 45%|████▍ | 6702/15000 [30:59:36<44:55:52, 19.49s/it] 45%|████▍ :27:34, 17.97s/it] 45%|████▍ | 6693/15000 [30:57:01<39:11:36, 16.99s/it] 45%|████▍ | 6694/15000 [30:57:16<37:38:33, 16.32s/it] 45%|████▍ | 6695/15000 [30:57:31<36:36:25, 15.87s/it] 45%|████▍ | 6696/15000 [30:57:45<35:43:24, 15.49s/it] 45%|████▍ | 6697/15000 [30:58:00<35:16:20, 15.29s/it] 45%|████▍ | 6698/15000 [30:58:15<34:53:13, 15.13s/it] 45%|████▍ | 6699/15000 [30:58:30<34:33:45, 14.99s/it] 45%|████▍ | 6700/15000 [30:58:44<34:19:19, 14.89s/it] 45%|████▍ | 6700/15000 [30:58:45<34:19:19, 14.89s/it] 45%|████▍ | 6701/15000 [30:59:21<49:40:25, 21.55s/it] 45%|████▍ | 6702/15000 [30:59:36<44:52:52, 19.47s/it] 45%|████▍ | 6703/15000 [30:59:51<41:29:38, 18.00s/it] 45%|████▍ | 6704/15000 [31:00:05<39:08:53, 16.99s/it] 45%|████▍ | 6705/15000 [31:00:20< | 6703/15000 [30:59:51<41:32:44, 18.03s/it] 45%|████▍ | 6704/15000 [31:00:05<39:07:22, 16.98s/it] 45%|████▍ | 6705/15000 [31:00:20<37:31:03, 16.28s/it] 45%|████▍ | 6706/15000 [31:00:35<36:22:59, 15.79s/it] 45%|████▍ | 6707/15000 [31:00:49<35:35:56, 15.45s/it] 45%|████▍ | 6708/15000 [31:01:04<35:07:27, 15.25s/it] 45%|████▍ | 6709/15000 [31:01:19<34:43:06, 15.08s/it] 45%|████▍ | 6710/15000 [31:01:34<34:36:08, 15.03s/it] 45%|████▍ | 6711/15000 [31:01:48<34:20:01, 14.91s/it] 45%|████▍ | 6712/15000 [31:02:26<50:22:11, 21.88s/it] 45%|████▍ | 6713/15000 [31:02:41<45:19:51, 19.69s/it] 45%|████▍ | 6714/15000 [31:02:56<41:52:34, 18.19s/it] 45%|████▍ | 6715/15000 [31:03:10<39:22:46, 17.11s/it] 45%|████▍ | 6716/15000 [31:03:25<37:35:06, 16.33s/it] 45%|████▍ | 6717/15000 [31:03:40<36:31:57, 15.88s/it] 45%|██
{'loss': 0.837, 'learning_rate': 0.000119839808417869, 'epoch': 1.27}
{'loss': 0.837, 'learning_rate': 0.000119839808417869, 'epoch': 1.27}
6792/15000 [31:24:40<44:04:46, 19.33s/it] 45%|████▌ | 6793/15000 [31:24:55<40:58:17, 17.97s/it] 45%|████▌ | 6794/15000 [31:25:09<38:45:49, 17.01s/it] 45%|████▌ | 6795/15000 [31:25:24<37:14:09, 16.34s/it] 45%|████▌ | 6796/15000 [31:25:39<36:06:00, 15.84s/it] 45%|████▌ | 6797/15000 [31:25:53<35:19:18, 15.50s/it] 45%|████▌ | 6798/15000 [31:26:08<34:42:23, 15.23s/it] 45%|████▌ | 6799/15000 [31:26:23<34:20:32, 15.08s/it] 45%|████▌ | 6800/15000 [31:26:37<34:00:10, 14.93s/it] 45%|████▌ | 6800/15000 [31:26:38<34:00:10, 14.93s/it] 45%|████▌ | 6801/15000 [31:26:52<33:55:14, 14.89s/it] 45%|████▌ | 6802/15000 [31:27:28<48:30:20, 21.30s/it] 45%|████▌ | 6803/15000 [31:27:43<43:54:33, 19.28s/it] 45%|████▌ | 6804/15000 [31:27:58<40:45:47, 17.90s/it] 45%|████▌ 6792/15000 [31:24:40<44:03:23, 19.32s/it] 45%|████▌ | 6793/15000 [31:24:55<41:01:50, 18.00s/it] 45%|████▌ | 6794/15000 [31:25:09<38:41:58, 16.98s/it] 45%|████▌ | 6795/15000 [31:25:24<37:12:23, 16.32s/it] 45%|████▌ | 6796/15000 [31:25:39<36:05:22, 15.84s/it] 45%|████▌ | 6797/15000 [31:25:53<35:21:06, 15.51s/it] 45%|████▌ | 6798/15000 [31:26:08<34:40:26, 15.22s/it] 45%|████▌ | 6799/15000 [31:26:23<34:20:14, 15.07s/it] 45%|████▌ | 6800/15000 [31:26:37<34:02:36, 14.95s/it] 45%|████▌ | 6800/15000 [31:26:38<34:02:36, 14.95s/it] 45%|████▌ | 6801/15000 [31:26:52<33:48:50, 14.85s/it] 45%|████▌ | 6802/15000 [31:27:28<48:35:29, 21.34s/it] 45%|████▌ | 6803/15000 [31:27:43<43:55:31, 19.29s/it] 45%|████▌ | 6804/15000 [31:27:58<40:42:00, 17.88s/it] 45%|████▌ 44:51, 17.00s/it] 45%|████▌ | 6795/15000 [31:25:24<37:14:01, 16.34s/it] 45%|████▌ | 6796/15000 [31:25:39<36:05:11, 15.84s/it] 45%|████▌ | 6797/15000 [31:25:53<35:18:08, 15.49s/it] 45%|████▌ | 6798/15000 [31:26:08<34:40:31, 15.22s/it] 45%|████▌ | 6799/15000 [31:26:23<34:19:26, 15.07s/it] 45%|████▌ | 6800/15000 [31:26:37<33:58:00, 14.91s/it] 45%|████▌ | 6800/15000 [31:26:38<33:58:00, 14.91s/it] 45%|████▌ | 6801/15000 [31:26:52<33:52:46, 14.88s/it] 45%|████▌ | 6802/15000 [31:27:28<48:30:44, 21.30s/it] 45%|████▌ | 6803/15000 [31:27:43<43:55:49, 19.29s/it] 45%|████▌ | 6804/15000 [31:27:58<40:44:49, 17.90s/it] 45%|████▌ | 6805/15000 [31:28:12<38:32:12, 16.93s/it] 45%|████▌ | 6806/15000 [31:28:27<37:01:25, 16.27s/it] 45%|████▌ | 6807/15000 [31:28:42<3 | 6805/15000 [31:28:12<38:31:01, 16.92s/it] 45%|████▌ | 6806/15000 [31:28:27<36:59:38, 16.25s/it] 45%|████▌ | 6807/15000 [31:28:42<35:58:23, 15.81s/it] 45%|████▌ | 6808/15000 [31:28:56<35:11:26, 15.46s/it] 45%|████▌ | 6809/15000 [31:29:11<34:40:44, 15.24s/it] 45%|████▌ | 6810/15000 [31:29:26<34:16:34, 15.07s/it] 45%|████▌ | 6811/15000 [31:29:41<34:04:22, 14.98s/it] 45%|████▌ | 6812/15000 [31:29:55<33:48:40, 14.87s/it] 45%|████▌ | 6813/15000 [31:30:32<48:44:08, 21.43s/it] 45%|████▌ | 6814/15000 [31:30:47<44:05:55, 19.39s/it] 45%|████▌ | 6815/15000 [31:31:01<40:54:57, 18.00s/it] 45%|████▌ | 6816/15000 [31:31:16<38:39:27, 17.00s/it] 45%|████▌ | 6817/15000 [31:31:31<37:02:28, 16.30s/it] 45%|████▌ | 6818/15000 [31:31:46<36:04:17, 15.87s/it] 45%|████▌ | 6819/15000 [31:32:00<35:19:28, 15.54s/it] 45%|██<E29688>
{'loss': 0.8353, 'learning_rate': 0.0001177190991579223, 'epoch': 1.29}
{'loss': 0.8353, 'learning_rate': 0.0001177190991579223, 'epoch': 1.29}
6894/15000 [31:53:02<40:34:39, 18.02s/it] 46%|████▌ | 6895/15000 [31:53:16<38:20:14, 17.03s/it] 46%|████▌ | 6896/15000 [31:53:31<36:50:45, 16.37s/it] 46%|████▌ | 6897/15000 [31:53:46<35:39:17, 15.84s/it] 46%|████▌ | 6898/15000 [31:54:00<34:46:43, 15.45s/it] 46%|████▌ | 6899/15000 [31:54:15<34:16:21, 15.23s/it] 46%|████▌ | 6900/15000 [31:54:30<33:54:18, 15.07s/it] 46%|████▌ | 6900/15000 [31:54:30<33:54:18, 15.07s/it] 46%|████▌ | 6901/15000 [31:54:45<33:41:18, 14.97s/it] 46%|████▌ | 6902/15000 [31:54:59<33:28:56, 14.88s/it] 46%|████▌ | 6903/15000 [31:55:36<48:19:56, 21.49s/it] 46%|████▌ | 6904/15000 [31:55:51<43:46:01, 19.46s/it] 46%|████▌ | 6905/15000 [31:56:06<40:35:12, 18.05s/it] 46%|████▌ | 6906/15000 [31:56:20<38:19:57, 17.05s/it] 46%|████▌ 6894/15000 [31:53:02<40:36:42, 18.04s/it] 46%|████▌ | 6895/15000 [31:53:17<38:19:58, 17.03s/it] 46%|████▌ | 6896/15000 [31:53:31<36:47:26, 16.34s/it] 46%|████▌ | 6897/15000 [31:53:46<35:37:15, 15.83s/it] 46%|████▌ | 6898/15000 [31:54:00<34:47:22, 15.46s/it] 46%|████▌ | 6899/15000 [31:54:15<34:15:17, 15.22s/it] 46%|████▌ | 6900/15000 [31:54:30<33:57:18, 15.09s/it] 46%|████▌ | 6900/15000 [31:54:30<33:57:18, 15.09s/it] 46%|████▌ | 6901/15000 [31:54:45<33:43:30, 14.99s/it] 46%|████▌ | 6902/15000 [31:54:59<33:27:58, 14.88s/it] 46%|████▌ | 6903/15000 [31:55:36<48:22:14, 21.51s/it] 46%|████▌ | 6904/15000 [31:55:51<43:47:09, 19.47s/it] 46%|████▌ | 6905/15000 [31:56:06<40:32:03, 18.03s/it] 46%|████▌ | 6906/15000 [31:56:20<38:21:06, 17.06s/it] 46%|████▌ 6:40, 16.34s/it] 46%|████▌ | 6897/15000 [31:53:46<35:34:55, 15.81s/it] 46%|████▌ | 6898/15000 [31:54:00<34:49:22, 15.47s/it] 46%|████▌ | 6899/15000 [31:54:15<34:20:04, 15.26s/it] 46%|████▌ | 6900/15000 [31:54:30<33:57:09, 15.09s/it] 46%|████▌ | 6900/15000 [31:54:30<33:57:09, 15.09s/it] 46%|████▌ | 6901/15000 [31:54:45<33:44:32, 15.00s/it] 46%|████▌ | 6902/15000 [31:54:59<33:28:28, 14.88s/it] 46%|████▌ | 6903/15000 [31:55:36<48:19:08, 21.48s/it] 46%|████▌ | 6904/15000 [31:55:51<43:46:13, 19.46s/it] 46%|████▌ | 6905/15000 [31:56:06<40:35:15, 18.05s/it] 46%|████▌ | 6906/15000 [31:56:20<38:17:15, 17.03s/it] 46%|████▌ | 6907/15000 [31:56:35<36:45:09, 16.35s/it] 46%|████▌ | 6908/15000 [31:56:50<35:37:51, 15.85s/it] 46%|████▌ | 6909/15000 [31:57:05<34| 6907/15000 [31:56:35<36:43:56, 16.34s/it] 46%|████▌ | 6908/15000 [31:56:50<35:36:28, 15.84s/it] 46%|████▌ | 6909/15000 [31:57:05<34:52:05, 15.51s/it] 46%|████▌ | 6910/15000 [31:57:19<34:18:51, 15.27s/it] 46%|████▌ | 6911/15000 [31:57:34<33:54:26, 15.09s/it] 46%|████▌ | 6912/15000 [31:57:49<33:36:05, 14.96s/it] 46%|████▌ | 6913/15000 [31:58:03<33:23:50, 14.87s/it] 46%|████▌ | 6914/15000 [31:58:40<48:13:51, 21.47s/it] 46%|████▌ | 6915/15000 [31:58:55<43:32:43, 19.39s/it] 46%|████▌ | 6916/15000 [31:59:09<40:22:54, 17.98s/it] 46%|████▌ | 6917/15000 [31:59:24<38:12:18, 17.02s/it] 46%|████▌ | 6918/15000 [31:59:39<36:34:20, 16.29s/it] 46%|████▌ | 6919/15000 [31:59:54<35:35:36, 15.86s/it] 46%|████▌ | 6920/15000 [32:00:08<34:52:54, 15.54s/it] 46%|████▌ | 6921/15000 [32:00:23<34:20:57, 15.31s/it] 46%|██<E29688><E29688>
{'loss': 0.833, 'learning_rate': 0.00011559012954653865, 'epoch': 1.31}
{'loss': 0.833, 'learning_rate': 0.00011559012954653865, 'epoch': 1.31}
996/15000 [32:21:24<36:20:01, 16.34s/it] 47%|████▋ | 6997/15000 [32:21:38<35:13:41, 15.85s/it] 47%|████▋ | 6998/15000 [32:21:53<34:23:35, 15.47s/it] 47%|████▋ | 6999/15000 [32:22:08<33:51:02, 15.23s/it] 47%|████▋ | 7000/15000 [32:22:22<33:31:35, 15.09s/it] 47%|████▋ | 7000/15000 [32:22:23<33:31:35, 15.09s/it] 47%|████▋ | 7001/15000 [32:22:37<33:19:28, 15.00s/it] 47%|████▋ | 7002/15000 [32:22:52<33:05:43, 14.90s/it] 47%|████▋ | 7003/15000 [32:23:29<47:41:03, 21.47s/it] 47%|████▋ | 7004/15000 [32:23:43<43:12:01, 19.45s/it] 47%|████▋ | 7005/15000 [32:23:58<40:05:04, 18.05s/it] 47%|████▋ | 7006/15000 [32:24:13<37:56:34, 17.09s/it] 47%|████▋ | 7007/15000 [32:24:28<36:21:59, 16.38s/it] 47%|████▋ | 7008/15000 [32:24:43<35:18:46, 15.91s/it] 47%|████▋ |996/15000 [32:21:24<36:24:20, 16.37s/it] 47%|████▋ | 6997/15000 [32:21:38<35:15:07, 15.86s/it] 47%|████▋ | 6998/15000 [32:21:53<34:25:04, 15.48s/it] 47%|████▋ | 6999/15000 [32:22:08<33:50:03, 15.22s/it] 47%|████▋ | 7000/15000 [32:22:22<33:25:06, 15.04s/it] 47%|████▋ | 7000/15000 [32:22:22<33:25:06, 15.04s/it] 47%|████▋ | 7001/15000 [32:22:37<33:21:29, 15.01s/it] 47%|████▋ | 7002/15000 [32:22:52<33:05:19, 14.89s/it] 47%|████▋ | 7003/15000 [32:23:29<47:40:21, 21.46s/it] 47%|████▋ | 7004/15000 [32:23:43<43:11:44, 19.45s/it] 47%|████▋ | 7005/15000 [32:23:58<40:00:37, 18.02s/it] 47%|████▋ | 7006/15000 [32:24:13<37:53:53, 17.07s/it] 47%|████▋ | 7007/15000 [32:24:28<36:22:07, 16.38s/it] 47%|████▋ | 7008/15000 [32:24:42<35:15:48, 15.88s/it] 47%|████▋ |:18, 15.49s/it] 47%|████▋ | 6999/15000 [32:22:08<33:51:31, 15.23s/it] 47%|████▋ | 7000/15000 [32:22:22<33:27:32, 15.06s/it] 47%|████▋ | 7000/15000 [32:22:22<33:27:32, 15.06s/it] 47%|████▋ | 7001/15000 [32:22:37<33:21:24, 15.01s/it] 47%|████▋ | 7002/15000 [32:22:52<33:03:56, 14.88s/it] 47%|████▋ | 7003/15000 [32:23:29<47:44:01, 21.49s/it] 47%|████▋ | 7004/15000 [32:23:43<43:08:11, 19.42s/it] 47%|████▋ | 7005/15000 [32:23:58<40:03:22, 18.04s/it] 47%|████▋ | 7006/15000 [32:24:13<37:56:26, 17.09s/it] 47%|████▋ | 7007/15000 [32:24:28<36:22:59, 16.39s/it] 47%|████▋ | 7008/15000 [32:24:42<35:17:41, 15.90s/it] 47%|████▋ | 7009/15000 [32:24:57<34:28:05, 15.53s/it] 47%|████▋ | 7010/15000 [32:25:12<33:52:36, 15.26s/it] 47%|████▋ | 7011/15000 [32:25:26<33: 7009/15000 [32:24:57<34:34:38, 15.58s/it] 47%|████▋ | 7010/15000 [32:25:12<33:56:19, 15.29s/it] 47%|████▋ | 7011/15000 [32:25:27<33:30:59, 15.10s/it] 47%|████▋ | 7012/15000 [32:25:41<33:03:23, 14.90s/it] 47%|████▋ | 7013/15000 [32:25:56<32:54:58, 14.84s/it] 47%|████▋ | 7014/15000 [32:26:10<32:54:00, 14.83s/it] 47%|████▋ | 7015/15000 [32:26:48<48:07:50, 21.70s/it] 47%|████▋ | 7016/15000 [32:27:03<43:23:23, 19.56s/it] 47%|████▋ | 7017/15000 [32:27:17<40:04:54, 18.08s/it] 47%|████▋ | 7018/15000 [32:27:32<37:47:14, 17.04s/it] 47%|████▋ | 7019/15000 [32:27:47<36:16:55, 16.37s/it] 47%|████▋ | 7020/15000 [32:28:02<35:14:40, 15.90s/it] 47%|████▋ | 7021/15000 [32:28:16<34:24:27, 15.52s/it] 47%|████▋ | 7022/15000 [32:28:31<33:52:05, 15.28s/it] 47%|████▋ | 7023/15000 [32:28:46<33:31:09, 15.13s/it] 47%|███
{'loss': 0.8337, 'learning_rate': 0.00011345389207419588, 'epoch': 1.33}
{'loss': 0.8337, 'learning_rate': 0.00011345389207419588, 'epoch': 1.33}
98/15000 [32:49:47<34:53:37, 15.90s/it] 47%|████▋ | 7099/15000 [32:50:02<34:04:06, 15.52s/it] 47%|████▋ | 7100/15000 [32:50:16<33:30:22, 15.27s/it] 47%|████▋ | 7100/15000 [32:50:17<33:30:22, 15.27s/it] 47%|████▋ | 7101/15000 [32:50:31<33:12:22, 15.13s/it] 47%|████▋ | 7102/15000 [32:50:46<32:56:17, 15.01s/it] 47%|████▋ | 7103/15000 [32:51:01<32:46:57, 14.94s/it] 47%|████▋ | 7104/15000 [32:51:38<47:13:25, 21.53s/it] 47%|████▋ | 7105/15000 [32:51:52<42:43:06, 19.48s/it] 47%|████▋ | 7106/15000 [32:52:07<39:36:20, 18.06s/it] 47%|████▋ | 7107/15000 [32:52:22<37:20:33, 17.03s/it] 47%|████▋ | 7108/15000 [32:52:36<35:50:17, 16.35s/it] 47%|████▋ | 7109/15000 [32:52:51<34:45:35, 15.86s/it] 47%|████▋ | 7110/15000 [32:53:06<33:58:08, 15.50s/it] 47%|████▋ | 98/15000 [32:49:47<34:54:09, 15.90s/it] 47%|████▋ | 7099/15000 [32:50:02<34:07:28, 15.55s/it] 47%|████▋ | 7100/15000 [32:50:16<33:30:44, 15.27s/it] 47%|████▋ | 7100/15000 [32:50:17<33:30:44, 15.27s/it] 47%|████▋ | 7101/15000 [32:50:31<33:16:51, 15.17s/it] 47%|████▋ | 7102/15000 [32:50:46<32:52:16, 14.98s/it] 47%|████▋ | 7103/15000 [32:51:01<32:43:49, 14.92s/it] 47%|████▋ | 7104/15000 [32:51:38<47:14:31, 21.54s/it] 47%|████▋ | 7105/15000 [32:51:52<42:44:11, 19.49s/it] 47%|████▋ | 7106/15000 [32:52:07<39:37:18, 18.07s/it] 47%|████▋ | 7107/15000 [32:52:22<37:22:27, 17.05s/it] 47%|████▋ | 7108/15000 [32:52:36<35:52:53, 16.37s/it] 47%|████▋ | 7109/15000 [32:52:51<34:45:24, 15.86s/it] 47%|████▋ | 7110/15000 [32:53:06<33:56:45, 15.49s/it] 47%|████▋ | 47, 15.28s/it] 47%|████▋ | 7100/15000 [32:50:17<33:31:47, 15.28s/it] 47%|████▋ | 7101/15000 [32:50:31<33:10:50, 15.12s/it] 47%|████▋ | 7102/15000 [32:50:46<32:55:59, 15.01s/it] 47%|████▋ | 7103/15000 [32:51:01<32:44:45, 14.93s/it] 47%|████▋ | 7104/15000 [32:51:38<47:14:49, 21.54s/it] 47%|████▋ | 7105/15000 [32:51:52<42:45:16, 19.50s/it] 47%|████▋ | 7106/15000 [32:52:07<39:31:25, 18.02s/it] 47%|████▋ | 7107/15000 [32:52:22<37:22:51, 17.05s/it] 47%|████▋ | 7108/15000 [32:52:36<35:51:55, 16.36s/it] 47%|████▋ | 7109/15000 [32:52:51<34:45:20, 15.86s/it] 47%|████▋ | 7110/15000 [32:53:06<33:59:47, 15.51s/it] 47%|████▋ | 7111/15000 [32:53:20<33:27:01, 15.26s/it] 47%|████▋ | 7112/15000 [32:53:35<33:05:37, 15.10s/it] 47%|████▋ | 7113/15000 [32:53:50<32:47111/15000 [32:53:21<33:32:17, 15.30s/it] 47%|████▋ | 7112/15000 [32:53:35<33:00:54, 15.07s/it] 47%|████▋ | 7113/15000 [32:53:50<32:49:55, 14.99s/it] 47%|████▋ | 7114/15000 [32:54:05<32:36:03, 14.88s/it] 47%|████▋ | 7115/15000 [32:54:42<47:08:16, 21.52s/it] 47%|████▋ | 7116/15000 [32:54:56<42:39:12, 19.48s/it] 47%|████▋ | 7117/15000 [32:55:11<39:28:24, 18.03s/it] 47%|████▋ | 7118/15000 [32:55:26<37:17:51, 17.04s/it] 47%|████▋ | 7119/15000 [32:55:40<35:45:48, 16.34s/it] 47%|████▋ | 7120/15000 [32:55:55<34:41:22, 15.85s/it] 47%|████▋ | 7121/15000 [32:56:10<33:58:08, 15.52s/it] 47%|████▋ | 7122/15000 [32:56:25<33:25:28, 15.27s/it] 47%|████▋ | 7123/15000 [32:56:39<33:04:45, 15.12s/it] 47%|████▋ | 7124/15000 [32:56:54<32:46:55, 14.98s/it] 48%|████▊ | 7125/15000 [32:57:09<32:32:11, 14.87s/it] 48%|███<E29688>
{'loss': 0.8302, 'learning_rate': 0.00011131138261952845, 'epoch': 1.35}
t] 48%|████▊ | 7188/15000 [33:14:50<34:20:27, 15.83s/it] 48%|████▊ | 7189/15000 [33:15:04<33:35:01, 15.48s/it] 48%|████▊ | 7190/15000 [33:15:19<33:05:03, 15.25s/it] 48%|████▊ | 7191/15000 [33:15:34<32:45:13, 15.10s/it] 48%|████▊ | 7192/15000 [33:15:48<32:27:19, 14.96s/it] 48%|████▊ | 7193/15000 [33:16:03<32:14:58, 14.87s/it] 48%|████▊ | 7194/15000 [33:16:41<47:23:56, 21.86s/it] 48%|████▊ | 7195/15000 [33:16:56<42:43:42, 19.71s/it] 48%|████▊ | 7196/15000 [33:17:11<39:27:36, 18.20s/it] 48%|████▊ | 7197/15000 [33:17:25<37:10:33, 17.15s/it] 48%|████▊ | 7198/15000 [33:17:40<35:33:10, 16.40s/it] 48%|████▊ | 7199/15000 [33:17:55<34:21:13, 15.85s/it] 48%|████▊ | 7200/15000 [33:18:09<33:33:23, 15.49s/it] 48%|████▊ | 7200/15000 [33:18:09<33:33:23, 15.49s{'loss': 0.8302, 'learning_rate': 0.00011131138261952845, 'epoch': 1.35}
0/15000 [33:18:09<33:31:51, 15.48s/it] 48%|████▊ | 7200/15000 [33:18:10<33:31:51, 15.48s/it] 48%|████▊ | 7201/15000 [33:18:24<33:10:12, 15.31s/it] 48%|████▊ | 7202/15000 [33:18:39<32:38:55, 15.07s/it] 48%|████▊ | 7203/15000 [33:18:53<32:18:38, 14.92s/it] 48%|████▊ | 7204/15000 [33:19:08<32:09:26, 14.85s/it] 48%|████▊ | 7205/15000 [33:19:45<46:35:26, 21.52s/it] 48%|████▊ | 7206/15000 [33:20:00<42:10:15, 19.48s/it] 48%|████▊ | 7207/15000 [33:20:15<39:06:23, 18.07s/it] 48%|████▊ | 7208/15000 [33:20:29<36:57:22, 17.07s/it] 48%|████▊ | 7209/15000 [33:20:44<35:28:32, 16.39s/it] 48%|████▊ | 7210/15000 [33:20:59<34:26:05, 15.91s/it] 48%|████▊ | 7211/15000 [33:21:13<33:33:07, 15.51s/it] 48%|████▊ | 7212/15000 [33:21:28<33:04:18, 15.29s/it] 48%|████▊ | 70/15000 [33:18:09<33:33:56, 15.49s/it] 48%|████▊ | 7200/15000 [33:18:09<33:33:56, 15.49s/it] 48%|████▊ | 7201/15000 [33:18:24<33:08:16, 15.30s/it] 48%|████▊ | 7202/15000 [33:18:39<32:43:52, 15.11s/it] 48%|████▊ | 7203/15000 [33:18:53<32:18:24, 14.92s/it] 48%|████▊ | 7204/15000 [33:19:08<32:08:33, 14.84s/it] 48%|████▊ | 7205/15000 [33:19:45<46:35:05, 21.51s/it] 48%|████▊ | 7206/15000 [33:20:00<42:12:21, 19.49s/it] 48%|████▊ | 7207/15000 [33:20:15<39:04:15, 18.05s/it] 48%|████▊ | 7208/15000 [33:20:29<36:58:46, 17.08s/it] 48%|████▊ | 7209/15000 [33:20:44<35:28:17, 16.39s/it] 48%|████▊ | 7210/15000 [33:20:59<34:24:27, 15.90s/it] 48%|████▊ | 7211/15000 [33:21:14<33:34:37, 15.52s/it] 48%|████▊ | 7212/15000 [33:21:28<33:01:48, 15.27s/it] 48%|████▊ | 7/it] 48%|████▊ | 7201/15000 [33:18:24<33:06:08, 15.28s/it] 48%|████▊ | 7202/15000 [33:18:39<32:39:34, 15.08s/it] 48%|████▊ | 7203/15000 [33:18:53<32:22:01, 14.94s/it] 48%|████▊ | 7204/15000 [33:19:08<32:08:11, 14.84s/it] 48%|████▊ | 7205/15000 [33:19:45<46:39:57, 21.55s/it] 48%|████▊ | 7206/15000 [33:20:00<42:11:51, 19.49s/it] 48%|████▊ | 7207/15000 [33:20:15<39:07:23, 18.07s/it] 48%|████▊ | 7208/15000 [33:20:29<37:00:08, 17.10s/it] 48%|████▊ | 7209/15000 [33:20:44<35:26:17, 16.38s/it] 48%|████▊ | 7210/15000 [33:20:59<34:23:01, 15.89s/it] 48%|████▊ | 7211/15000 [33:21:14<33:36:42, 15.54s/it] 48%|████▊ | 7212/15000 [33:21:28<33:03:05, 15.28s/it] 48%|████▊ | 7213/15000 [33:21:43<32:35:27, 15.07s/it] 48%|████▊ | 7214/15000 [33:21:57<32:19:15, 14.94s/it] 48%|████▊ | 7215/15000 [33:22:12<32:08213/15000 [33:21:43<32:39:31, 15.10s/it] 48%|████▊ | 7214/15000 [33:21:57<32:16:41, 14.92s/it] 48%|████▊ | 7215/15000 [33:22:12<32:12:16, 14.89s/it] 48%|████▊ | 7216/15000 [33:22:49<46:31:32, 21.52s/it] 48%|████▊ | 7217/15000 [33:23:04<42:08:50, 19.50s/it] 48%|████▊ | 7218/15000 [33:23:19<38:59:28, 18.04s/it] 48%|████▊ | 7219/15000 [33:23:33<36:54:47, 17.08s/it] 48%|████▊ | 7220/15000 [33:23:48<35:23:03, 16.37s/it] 48%|████▊ | 7221/15000 [33:24:03<34:13:31, 15.84s/it] 48%|████▊ | 7222/15000 [33:24:17<33:26:35, 15.48s/it] 48%|████▊ | 7223/15000 [33:24:32<32:59:39, 15.27s/it] 48%|████▊ | 7224/15000 [33:24:47<32:35:20, 15.09s/it] 48%|████▊ | 7225/15000 [33:25:02<32:23:02, 14.99s/it] 48%|████▊ | 7226/15000 [33:25:16<32:10:40, 14.90s/it] 48%|████▊ | 7227/15000 [33:25:53<46:27:00, 21.51s/it] 48%|███<E29688><E29688>
42:33<35:34:46, 16.61s/it] 49%|████▊ | 7288/15000 [33:42:47<34:21:24, 16.04s/it] 49%|████▊ | 7289/15000 [33:43:02<33:39:58, 15.72s/it] 49%|████▊ | 7290/15000 [33:43:17<33:01:02, 15.42s/it] 49%|████▊ | 7291/15000 [33:43:32<32:33:44, 15.21s/it] 49%|████▊ | 7292/15000 [33:43:46<32:15:13, 15.06s/it] 49%|████▊ | 7293/15000 [33:44:01<32:04:07, 14.98s/it] 49%|████▊ | 7294/15000 [33:44:16<31:51:46, 14.89s/it] 49%|████▊ | 7295/15000 [33:44:53<45:59:19, 21.49s/it] 49%|████▊ | 7296/15000 [33:45:07<41:36:45, 19.45s/it] 49%|████▊ | 7297/15000 [33:45:22<38:35:18, 18.03s/it] 49%|████▊ | 7298/15000 [33:45:37<36:32:49, 17.08s/it] 49%|████▊ | 7299/15000 [33:45:52<35:14:19, 16.47s/it] 49%|████▊ | 7300/15000 [33:46:07<34:16:05, 16.02s/it] 49%|████▊ | 7300/15000 [3{'loss': 0.8304, 'learning_rate': 0.0001091635999850655, 'epoch': 1.37}
42:32<35:29:09, 16.56s/it] 49%|████▊ | 7288/15000 [33:42:47<34:19:10, 16.02s/it] 49%|████▊ | 7289/15000 [33:43:02<33:38:38, 15.71s/it] 49%|████▊ | 7290/15000 [33:43:17<32:57:36, 15.39s/it] 49%|████▊ | 7291/15000 [33:43:32<32:35:30, 15.22s/it] 49%|████▊ | 7292/15000 [33:43:46<32:16:34, 15.07s/it] 49%|████▊ | 7293/15000 [33:44:01<32:04:00, 14.98s/it] 49%|████▊ | 7294/15000 [33:44:16<31:51:14, 14.88s/it] 49%|████▊ | 7295/15000 [33:44:53<46:00:06, 21.49s/it] 49%|████▊ | 7296/15000 [33:45:07<41:39:34, 19.47s/it] 49%|████▊ | 7297/15000 [33:45:22<38:35:16, 18.03s/it] 49%|████▊ | 7298/15000 [33:45:37<36:34:04, 17.09s/it] 49%|████▊ | 7299/15000 [33:45:52<35:12:23, 16.46s/it] 49%|████▊ | 7300/15000 [33:46:07<34:15:37, 16.02s/it] 49%|████▊ | 7300/15000 [3{'loss': 0.8304, 'learning_rate': 0.0001091635999850655, 'epoch': 1.37}
] 49%|████▊ | 7290/15000 [33:43:17<33:00:39, 15.41s/it] 49%|████▊ | 7291/15000 [33:43:32<32:33:13, 15.20s/it] 49%|████▊ | 7292/15000 [33:43:46<32:13:35, 15.05s/it] 49%|████▊ | 7293/15000 [33:44:01<32:03:29, 14.97s/it] 49%|████▊ | 7294/15000 [33:44:16<31:53:01, 14.90s/it] 49%|████▊ | 7295/15000 [33:44:53<46:00:25, 21.50s/it] 49%|████▊ | 7296/15000 [33:45:07<41:41:43, 19.48s/it] 49%|████▊ | 7297/15000 [33:45:22<38:39:14, 18.06s/it] 49%|████▊ | 7298/15000 [33:45:37<36:30:00, 17.06s/it] 49%|████▊ | 7299/15000 [33:45:52<35:12:45, 16.46s/it] 49%|████▊ | 7300/15000 [33:46:07<34:15:22, 16.02s/it] 49%|████▊ | 7300/15000 [33:46:07<34:15:22, 16.02s/it] 49%|████▊ | 7301/15000 [33:46:22<33:45:36, 15.79s/it] 49%|████▊ | 7302/15000 [33:46:37<33:17:36, 15.57s/3:46:07<34:15:37, 16.02s/it] 49%|████▊ | 7301/15000 [33:46:22<33:45:21, 15.78s/it] 49%|████▊ | 7302/15000 [33:46:37<33:18:24, 15.58s/it] 49%|████▊ | 7303/15000 [33:46:52<33:02:47, 15.46s/it] 49%|████▊ | 7304/15000 [33:47:07<32:40:14, 15.28s/it] 49%|████▊ | 7305/15000 [33:47:22<32:28:14, 15.19s/it] 49%|████▊ | 7306/15000 [33:47:59<46:32:26, 21.78s/it] 49%|████▊ | 7307/15000 [33:48:15<42:13:16, 19.76s/it] 49%|████▊ | 7308/15000 [33:48:30<39:24:54, 18.45s/it] 49%|████▊ | 7309/15000 [33:48:45<37:17:13, 17.45s/it] 49%|████▊ | 7310/15000 [33:49:00<35:33:08, 16.64s/it] 49%|████▊ | 7311/15000 [33:49:14<34:14:57, 16.04s/it] 49%|████▊ | 7312/15000 [33:49:29<33:28:37, 15.68s/it] 49%|████▉ | 7313/15000 [33:49:44<32:51:06, 15.39s/it] 49%|████▉ | 7314/15000 [33:49:59<32:20:19, 15.15s/it] 49%|████▉ | 733:46:07<34:16:05, 16.02s/it] 49%|████▊ | 7301/15000 [33:46:22<33:49:54, 15.82s/it] 49%|████▊ | 7302/15000 [33:46:37<33:18:31, 15.58s/it] 49%|████▊ | 7303/15000 [33:46:53<33:02:37, 15.46s/it] 49%|████▊ | 7304/15000 [33:47:08<32:45:51, 15.33s/it] 49%|████▊ | 7305/15000 [33:47:22<32:28:54, 15.20s/it] 49%|████▊ | 7306/15000 [33:48:00<46:29:41, 21.75s/it] 49%|████▊ | 7307/15000 [33:48:15<42:35:09, 19.93s/it] 49%|████▊ | 7308/15000 [33:48:30<39:19:34, 18.41s/it] 49%|████▊ | 7309/15000 [33:48:45<37:08:37, 17.39s/it] 49%|████▊ | 7310/15000 [33:49:00<35:29:28, 16.61s/it] 49%|████▊ | 7311/15000 [33:49:15<34:16:23, 16.05s/it] 49%|████▊ | 7312/15000 [33:49:29<33:24:23, 15.64s/it] 49%|████▉ | 7313/15000 [33:49:44<32:46:45, 15.35s/it] 49%|████▉ | 7314/15000 [33:49:59<32:17:26, 15.12s/it] 49%|████▉ | 73it] 49%|████▊ | 7303/15000 [33:46:52<33:00:51, 15.44s/it] 49%|████▊ | 7304/15000 [33:47:07<32:41:04, 15.29s/it] 49%|████▊ | 7305/15000 [33:47:22<32:27:55, 15.19s/it] 49%|████▊ | 7306/15000 [33:47:59<46:33:02, 21.78s/it] 49%|████▊ | 7307/15000 [33:48:15<42:16:57, 19.79s/it] 49%|████▊ | 7308/15000 [33:48:30<39:25:00, 18.45s/it] 49%|████▊ | 7309/15000 [33:48:45<37:13:13, 17.42s/it] 49%|████▊ | 7310/15000 [33:49:00<35:32:51, 16.64s/it] 49%|████▊ | 7311/15000 [33:49:15<34:21:46, 16.09s/it] 49%|████▊ | 7312/15000 [33:49:29<33:28:48, 15.68s/it] 49%|████▉ | 7313/15000 [33:49:44<32:48:03, 15.36s/it] 49%|████▉ | 7314/15000 [33:49:59<32:20:43, 15.15s/it] 49%|████▉ | 7315/15000 [33:50:13<32:03:15, 15.02s/it] 49%|████▉ | 7316/15000 [33:50:28<31:50:05, 14.91s/it] 49%|████▉ | 7317/15000 [33:51:05<45:46
{'loss': 0.8324, 'learning_rate': 0.00010701154543160541, 'epoch': 1.38}
{'loss': 0.8324, 'learning_rate': 0.00010701154543160541, 'epoch': 1.38}
0:58<33:38:19, 15.91s/it] 49%|████▉ | 7390/15000 [34:11:13<32:51:06, 15.54s/it] 49%|████▉ | 7391/15000 [34:11:27<32:20:22, 15.30s/it] 49%|████▉ | 7392/15000 [34:11:42<31:55:41, 15.11s/it] 49%|████▉ | 7393/15000 [34:11:57<31:39:24, 14.98s/it] 49%|████▉ | 7394/15000 [34:12:11<31:30:05, 14.91s/it] 49%|████▉ | 7395/15000 [34:12:50<46:29:06, 22.00s/it] 49%|████▉ | 7396/15000 [34:13:05<41:48:52, 19.80s/it] 49%|████▉ | 7397/15000 [34:13:19<38:39:15, 18.30s/it] 49%|████▉ | 7398/15000 [34:13:34<36:16:04, 17.18s/it] 49%|████▉ | 7399/15000 [34:13:49<34:43:29, 16.45s/it] 49%|████▉ | 7400/15000 [34:14:03<33:33:15, 15.89s/it] 49%|████▉ | 7400/15000 [34:14:04<33:33:15, 15.89s/it] 49%|████▉ | 7401/15000 [34:14:18<32:52:04, 15.57s/it] 49%|████▉ | 7402/15000 [340:58<33:36:21, 15.90s/it] 49%|████▉ | 7390/15000 [34:11:13<32:50:05, 15.53s/it] 49%|████▉ | 7391/15000 [34:11:27<32:19:33, 15.29s/it] 49%|████▉ | 7392/15000 [34:11:42<31:57:38, 15.12s/it] 49%|████▉ | 7393/15000 [34:11:57<31:42:54, 15.01s/it] 49%|████▉ | 7394/15000 [34:12:11<31:30:48, 14.92s/it] 49%|████▉ | 7395/15000 [34:12:50<46:27:16, 21.99s/it] 49%|████▉ | 7396/15000 [34:13:05<41:50:34, 19.81s/it] 49%|████▉ | 7397/15000 [34:13:19<38:38:35, 18.30s/it] 49%|████▉ | 7398/15000 [34:13:34<36:20:24, 17.21s/it] 49%|████▉ | 7399/15000 [34:13:49<34:41:24, 16.43s/it] 49%|████▉ | 7400/15000 [34:14:03<33:34:28, 15.90s/it] 49%|████▉ | 7400/15000 [34:14:04<33:34:28, 15.90s/it] 49%|████▉ | 7401/15000 [34:14:18<32:52:20, 15.57s/it] 49%|████▉ | 7402/15000 [34 49%|████▉ | 7392/15000 [34:11:42<31:57:12, 15.12s/it] 49%|████▉ | 7393/15000 [34:11:57<31:42:25, 15.01s/it] 49%|████▉ | 7394/15000 [34:12:11<31:29:31, 14.91s/it] 49%|████▉ | 7395/15000 [34:12:50<46:28:58, 22.00s/it] 49%|████▉ | 7396/15000 [34:13:05<41:51:37, 19.82s/it] 49%|████▉ | 7397/15000 [34:13:19<38:35:45, 18.28s/it] 49%|████▉ | 7398/15000 [34:13:34<36:20:04, 17.21s/it] 49%|████▉ | 7399/15000 [34:13:49<34:41:38, 16.43s/it] 49%|████▉ | 7400/15000 [34:14:03<33:35:41, 15.91s/it] 49%|████▉ | 7400/15000 [34:14:04<33:35:41, 15.91s/it] 49%|████▉ | 7401/15000 [34:14:18<32:53:43, 15.58s/it] 49%|████▉ | 7402/15000 [34:14:33<32:20:08, 15.32s/it] 49%|████▉ | 7403/15000 [34:14:48<31:55:49, 15.13s/it] 49%|████▉ | 7404/15000 [34:15:02<31:38:30, 15.00s/i:14:33<32:19:57, 15.32s/it] 49%|████▉ | 7403/15000 [34:14:48<32:00:06, 15.16s/it] 49%|████▉ | 7404/15000 [34:15:02<31:33:52, 14.96s/it] 49%|████▉ | 7405/15000 [34:15:17<31:30:46, 14.94s/it] 49%|████▉ | 7406/15000 [34:15:55<46:13:46, 21.92s/it] 49%|████▉ | 7407/15000 [34:16:10<41:39:14, 19.75s/it] 49%|████▉ | 7408/15000 [34:16:25<38:28:59, 18.25s/it] 49%|████▉ | 7409/15000 [34:16:39<36:14:49, 17.19s/it] 49%|████▉ | 7410/15000 [34:16:54<34:41:02, 16.45s/it] 49%|████▉ | 7411/15000 [34:17:09<33:35:13, 15.93s/it] 49%|████▉ | 7412/15000 [34:17:24<32:50:55, 15.58s/it] 49%|████▉ | 7413/15000 [34:17:38<32:12:14, 15.28s/it] 49%|████▉ | 7414/15000 [34:17:53<31:51:42, 15.12s/it] 49%|████▉ | 7415/15000 [34:18:08<31:30:09, 14.95s/it] 49%|████▉ | 7416/15000 [34:18:22<31:20:22, 14.88s/it] 49%|████▉ | 74
{'loss': 0.8293, 'learning_rate': 0.00010485622221144484, 'epoch': 1.4}
{'loss': 0.8293, 'learning_rate': 0.00010485622221144484, 'epoch': 1.4}
:20<32:15:11, 15.46s/it] 50%|████▉ | 7492/15000 [34:39:35<31:44:37, 15.22s/it] 50%|████▉ | 7493/15000 [34:39:50<31:22:19, 15.04s/it] 50%|████▉ | 7494/15000 [34:40:04<31:11:59, 14.96s/it] 50%|████▉ | 7495/15000 [34:40:19<31:02:04, 14.89s/it] 50%|████▉ | 7496/15000 [34:40:57<45:10:40, 21.67s/it] 50%|████▉ | 7497/15000 [34:41:11<40:51:19, 19.60s/it] 50%|████▉ | 7498/15000 [34:41:26<37:45:17, 18.12s/it] 50%|████▉ | 7499/15000 [34:41:41<35:32:13, 17.06s/it] 50%|█████ | 7500/15000 [34:41:55<34:01:14, 16.33s/it] 50%|█████ | 7500/15000 [34:41:56<34:01:14, 16.33s/it] 50%|█████ | 7501/15000 [34:42:10<33:07:58, 15.91s/it] 50%|█████ | 7502/15000 [34:42:25<32:20:35, 15.53s/it] 50%|█████ | 7503/15000 [34:42:40<31:47:13, 15.26s/it] 50%|█████ | 7504/15000 [34::20<32:17:57, 15.49s/it] 50%|████▉ | 7492/15000 [34:39:35<31:44:25, 15.22s/it] 50%|████▉ | 7493/15000 [34:39:50<31:25:32, 15.07s/it] 50%|████▉ | 7494/15000 [34:40:04<31:11:10, 14.96s/it] 50%|████▉ | 7495/15000 [34:40:19<31:00:24, 14.87s/it] 50%|████▉ | 7496/15000 [34:40:57<45:12:56, 21.69s/it] 50%|████▉ | 7497/15000 [34:41:11<40:51:10, 19.60s/it] 50%|████▉ | 7498/15000 [34:41:26<37:47:04, 18.13s/it] 50%|████▉ | 7499/15000 [34:41:41<35:31:47, 17.05s/it] 50%|█████ | 7500/15000 [34:41:55<34:00:02, 16.32s/it] 50%|█████ | 7500/15000 [34:41:56<34:00:02, 16.32s/it] 50%|█████ | 7501/15000 [34:42:10<33:04:56, 15.88s/it] 50%|█████ | 7502/15000 [34:42:25<32:17:48, 15.51s/it] 50%|█████ | 7503/15000 [34:42:40<31:47:20, 15.26s/it] 50%|█████ | 7504/15000 [34: 50%|████▉ | 7494/15000 [34:40:04<31:10:10, 14.95s/it] 50%|████▉ | 7495/15000 [34:40:19<30:57:10, 14.85s/it] 50%|████▉ | 7496/15000 [34:40:57<45:14:46, 21.71s/it] 50%|████▉ | 7497/15000 [34:41:11<40:52:28, 19.61s/it] 50%|████▉ | 7498/15000 [34:41:26<37:42:55, 18.10s/it] 50%|████▉ | 7499/15000 [34:41:41<35:31:59, 17.05s/it] 50%|█████ | 7500/15000 [34:41:55<34:00:28, 16.32s/it] 50%|█████ | 7500/15000 [34:41:56<34:00:28, 16.32s/it] 50%|█████ | 7501/15000 [34:42:10<33:03:26, 15.87s/it] 50%|█████ | 7502/15000 [34:42:25<32:20:42, 15.53s/it] 50%|█████ | 7503/15000 [34:42:39<31:46:20, 15.26s/it] 50%|█████ | 7504/15000 [34:42:54<31:23:15, 15.07s/it] 50%|█████ | 7505/15000 [34:43:09<31:11:21, 14.98s/it] 50%|█████ | 7506/15000 [34:43:23<30:59:02, 14.88s/it42:54<31:19:31, 15.04s/it] 50%|█████ | 7505/15000 [34:43:09<31:10:19, 14.97s/it] 50%|█████ | 7506/15000 [34:43:24<31:01:51, 14.91s/it] 50%|█████ | 7507/15000 [34:44:02<45:36:15, 21.91s/it] 50%|█████ | 7508/15000 [34:44:16<41:02:58, 19.72s/it] 50%|█████ | 7509/15000 [34:44:31<37:54:56, 18.22s/it] 50%|█████ | 7510/15000 [34:44:46<35:43:44, 17.17s/it] 50%|█████ | 7511/15000 [34:45:01<34:07:26, 16.40s/it] 50%|█████ | 7512/15000 [34:45:15<32:57:43, 15.85s/it] 50%|█████ | 7513/15000 [34:45:30<32:17:06, 15.52s/it] 50%|█████ | 7514/15000 [34:45:44<31:43:14, 15.25s/it] 50%|█████ | 7515/15000 [34:45:59<31:19:47, 15.07s/it] 50%|█████ | 7516/15000 [34:46:14<31:05:42, 14.96s/it] 50%|█████ | 7517/15000 [34:46:29<30:57:45, 14.90s/it] 50%|█████ | 7518/15000 [34:47:07<45:31:23, 21.90s/it] 50%|█████ | 751
{'loss': 0.8309, 'learning_rate': 0.00010269863510067872, 'epoch': 1.42}
{'loss': 0.8309, 'learning_rate': 0.00010269863510067872, 'epoch': 1.42}
44<31:14:43, 15.19s/it] 51%|█████ | 7594/15000 [35:07:59<30:59:16, 15.06s/it] 51%|█████ | 7595/15000 [35:08:14<30:46:44, 14.96s/it] 51%|█████ | 7596/15000 [35:08:28<30:35:53, 14.88s/it] 51%|█████ | 7597/15000 [35:09:06<44:34:23, 21.68s/it] 51%|█████ | 7598/15000 [35:09:21<40:09:57, 19.53s/it] 51%|█████ | 7599/15000 [35:09:35<37:11:51, 18.09s/it] 51%|█████ | 7600/15000 [35:09:50<34:57:22, 17.01s/it] 51%|█████ | 7600/15000 [35:09:50<34:57:22, 17.01s/it] 51%|█████ | 7601/15000 [35:10:04<33:32:28, 16.32s/it] 51%|█████ | 7602/15000 [35:10:19<32:34:37, 15.85s/it] 51%|█████ | 7603/15000 [35:10:34<31:45:54, 15.46s/it] 51%|█████ | 7604/15000 [35:10:49<31:20:50, 15.26s/it] 51%|█████ | 7605/15000 [35:11:03<31:03:10, 15.12s/it] 51%|█████ | 7606/15000 [35:144<31:17:18, 15.21s/it] 51%|█████ | 7594/15000 [35:07:59<30:59:37, 15.07s/it] 51%|█████ | 7595/15000 [35:08:14<30:46:30, 14.96s/it] 51%|█████ | 7596/15000 [35:08:28<30:34:46, 14.87s/it] 51%|█████ | 7597/15000 [35:09:06<44:31:29, 21.65s/it] 51%|█████ | 7598/15000 [35:09:20<40:06:36, 19.51s/it] 51%|█████ | 7599/15000 [35:09:35<37:14:24, 18.11s/it] 51%|█████ | 7600/15000 [35:09:50<34:58:50, 17.02s/it] 51%|█████ | 7600/15000 [35:09:50<34:58:50, 17.02s/it] 51%|█████ | 7601/15000 [35:10:05<33:36:04, 16.35s/it] 51%|█████ | 7602/15000 [35:10:19<32:32:59, 15.84s/it] 51%|█████ | 7603/15000 [35:10:34<31:51:15, 15.50s/it] 51%|█████ | 7604/15000 [35:10:49<31:18:48, 15.24s/it] 51%|█████ | 7605/15000 [35:11:03<31:00:21, 15.09s/it] 51%|█████ | 7606/15000 [35:151%|█████ | 7596/15000 [35:08:28<30:37:39, 14.89s/it] 51%|█████ | 7597/15000 [35:09:06<44:31:17, 21.65s/it] 51%|█████ | 7598/15000 [35:09:21<40:11:37, 19.55s/it] 51%|█████ | 7599/15000 [35:09:35<37:08:00, 18.06s/it] 51%|█████ | 7600/15000 [35:09:50<35:00:37, 17.03s/it] 51%|█████ | 7600/15000 [35:09:50<35:00:37, 17.03s/it] 51%|█████ | 7601/15000 [35:10:04<33:35:40, 16.35s/it] 51%|█████ | 7602/15000 [35:10:19<32:32:49, 15.84s/it] 51%|█████ | 7603/15000 [35:10:34<31:51:14, 15.50s/it] 51%|█████ | 7604/15000 [35:10:49<31:21:35, 15.26s/it] 51%|█████ | 7605/15000 [35:11:03<31:00:16, 15.09s/it] 51%|█████ | 7606/15000 [35:11:18<30:46:51, 14.99s/it] 51%|█████ | 7607/15000 [35:11:33<30:35:45, 14.90s/it] 51%|█████ | 7608/15000 [35:12:11<45:06:03, 21.96s/it]1:18<30:49:26, 15.01s/it] 51%|█████ | 7607/15000 [35:11:33<30:36:40, 14.91s/it] 51%|█████ | 7608/15000 [35:12:11<45:05:03, 21.96s/it] 51%|█████ | 7609/15000 [35:12:26<40:36:15, 19.78s/it] 51%|█████ | 7610/15000 [35:12:40<37:24:14, 18.22s/it] 51%|█████ | 7611/15000 [35:12:55<35:11:26, 17.15s/it] 51%|█████ | 7612/15000 [35:13:10<33:37:11, 16.38s/it] 51%|█████ | 7613/15000 [35:13:24<32:35:38, 15.88s/it] 51%|█████ | 7614/15000 [35:13:39<31:49:46, 15.51s/it] 51%|█████ | 7615/15000 [35:13:54<31:17:24, 15.25s/it] 51%|█████ | 7616/15000 [35:14:08<30:56:54, 15.09s/it] 51%|█████ | 7617/15000 [35:14:23<30:40:43, 14.96s/it] 51%|█████ | 7618/15000 [35:14:38<30:30:50, 14.88s/it] 51%|█████ | 7619/15000 [35:15:16<44:53:22, 21.89s/it] 51%|█████ | 7620/15000 [35:15:31<40:27:22, 19.73s/it] 51%|█████ | 7621
{'loss': 0.8262, 'learning_rate': 0.00010053978993079045, 'epoch': 1.44}
{'loss': 0.8262, 'learning_rate': 0.00010053978993079045, 'epoch': 1.44}
5/15000 [35:36:06<30:19:37, 14.95s/it] 51%|█████▏ | 7696/15000 [35:36:21<30:12:12, 14.89s/it] 51%|█████▏ | 7697/15000 [35:36:58<43:27:23, 21.42s/it] 51%|█████▏ | 7698/15000 [35:37:12<39:23:19, 19.42s/it] 51%|█████▏ | 7699/15000 [35:37:27<36:31:14, 18.01s/it] 51%|█████▏ | 7700/15000 [35:37:42<34:30:54, 17.02s/it] 51%|█████▏ | 7700/15000 [35:37:42<34:30:54, 17.02s/it] 51%|█████▏ | 7701/15000 [35:37:57<33:13:04, 16.38s/it] 51%|█████▏ | 7702/15000 [35:38:11<32:07:56, 15.85s/it] 51%|█████▏ | 7703/15000 [35:38:26<31:28:40, 15.53s/it] 51%|█████▏ | 7704/15000 [35:38:41<30:54:54, 15.25s/it] 51%|█████▏ | 7705/15000 [35:38:55<30:35:39, 15.10s/it] 51%|█████▏ | 7706/15000 [35:39:10<30:19:00, 14.96s/it] 51%|█████▏ | 7707/15000 [35:39:25<30:08:36, 14.88s/it] 55/15000 [35:36:06<30:23:54, 14.98s/it] 51%|█████▏ | 7696/15000 [35:36:21<30:08:22, 14.86s/it] 51%|█████▏ | 7697/15000 [35:36:58<43:27:18, 21.42s/it] 51%|█████▏ | 7698/15000 [35:37:12<39:24:43, 19.43s/it] 51%|█████▏ | 7699/15000 [35:37:27<36:29:24, 17.99s/it] 51%|█████▏ | 7700/15000 [35:37:42<34:29:57, 17.01s/it] 51%|█████▏ | 7700/15000 [35:37:42<34:29:57, 17.01s/it] 51%|█████▏ | 7701/15000 [35:37:57<33:16:46, 16.41s/it] 51%|█████▏ | 7702/15000 [35:38:11<32:09:54, 15.87s/it] 51%|█████▏ | 7703/15000 [35:38:26<31:27:17, 15.52s/it] 51%|█████▏ | 7704/15000 [35:38:41<30:52:34, 15.24s/it] 51%|█████▏ | 7705/15000 [35:38:55<30:31:19, 15.06s/it] 51%|█████▏ | 7706/15000 [35:39:10<30:21:05, 14.98s/it] 51%|█████▏ | 7707/15000 [35:39:25<30:07:55, 14.87s/it] 530:56, 21.45s/it] 51%|█████▏ | 7698/15000 [35:37:12<39:20:19, 19.39s/it] 51%|█████▏ | 7699/15000 [35:37:27<36:29:38, 17.99s/it] 51%|█████▏ | 7700/15000 [35:37:42<34:32:00, 17.03s/it] 51%|█████▏ | 7700/15000 [35:37:42<34:32:00, 17.03s/it] 51%|█████▏ | 7701/15000 [35:37:57<33:13:18, 16.39s/it] 51%|█████▏ | 7702/15000 [35:38:11<32:12:20, 15.89s/it] 51%|█████▏ | 7703/15000 [35:38:26<31:25:18, 15.50s/it] 51%|█████▏ | 7704/15000 [35:38:41<30:55:05, 15.26s/it] 51%|█████▏ | 7705/15000 [35:38:55<30:33:15, 15.08s/it] 51%|█████▏ | 7706/15000 [35:39:10<30:18:31, 14.96s/it] 51%|█████▏ | 7707/15000 [35:39:25<30:09:34, 14.89s/it] 51%|█████▏ | 7708/15000 [35:39:39<30:02:03, 14.83s/it] 51%|█████▏ | 7709/15000 [35:40:16<43:24:06, 21.43s/it] 51%|█████▏1%|█████▏ | 7708/15000 [35:39:40<30:05:31, 14.86s/it] 51%|█████▏ | 7709/15000 [35:40:16<43:21:28, 21.41s/it] 51%|█████▏ | 7710/15000 [35:40:31<39:15:17, 19.39s/it] 51%|█████▏ | 7711/15000 [35:40:46<36:25:50, 17.99s/it] 51%|█████▏ | 7712/15000 [35:41:00<34:16:19, 16.93s/it] 51%|█████▏ | 7713/15000 [35:41:15<32:54:59, 16.26s/it] 51%|█████▏ | 7714/15000 [35:41:30<31:59:49, 15.81s/it] 51%|█████▏ | 7715/15000 [35:41:44<31:19:40, 15.48s/it] 51%|█████▏ | 7716/15000 [35:41:59<30:46:15, 15.21s/it] 51%|█████▏ | 7717/15000 [35:42:14<30:28:24, 15.06s/it] 51%|█████▏ | 7718/15000 [35:42:28<30:16:10, 14.96s/it] 51%|█████▏ | 7719/15000 [35:42:43<30:09:45, 14.91s/it] 51%|█████▏ | 7720/15000 [35:43:21<44:00:04, 21.76s/it] 51%|█████▏ | 7721/15000 [35:43:36<39:44:32, 19.66s/it] 51%|█████▏ | 77
{'loss': 0.8282, 'learning_rate': 9.838069311974986e-05, 'epoch': 1.46}
{'loss': 0.8282, 'learning_rate': 9.838069311974986e-05, 'epoch': 1.46}
[36:03:47<30:36:31, 15.29s/it] 52%|█████▏ | 7795/15000 [36:04:01<30:14:16, 15.11s/it] 52%|█████▏ | 7796/15000 [36:04:16<29:58:53, 14.98s/it] 52%|█████▏ | 7797/15000 [36:04:31<29:52:07, 14.93s/it] 52%|█████▏ | 7798/15000 [36:05:08<43:05:32, 21.54s/it] 52%|█████▏ | 7799/15000 [36:05:22<38:57:43, 19.48s/it] 52%|█████▏ | 7800/15000 [36:05:37<35:59:16, 17.99s/it] 52%|█████▏ | 7800/15000 [36:05:37<35:59:16, 17.99s/it] 52%|█████▏ | 7801/15000 [36:05:52<34:07:33, 17.07s/it] 52%|█████▏ | 7802/15000 [36:06:06<32:38:28, 16.33s/it] 52%|█████▏ | 7803/15000 [36:06:21<31:41:46, 15.85s/it] 52%|█████▏ | 7804/15000 [36:06:36<30:57:50, 15.49s/it] 52%|█████▏ | 7805/15000 [36:06:51<30:30:53, 15.27s/it] 52%|█████▏ | 7806/15000 [36:07:06<30:16:54, 15.15s/it] 52%|█<><E29688>[36:03:47<30:32:48, 15.26s/it] 52%|█████▏ | 7795/15000 [36:04:01<30:15:30, 15.12s/it] 52%|█████▏ | 7796/15000 [36:04:16<30:00:59, 15.00s/it] 52%|█████▏ | 7797/15000 [36:04:31<29:48:51, 14.90s/it] 52%|█████▏ | 7798/15000 [36:05:08<43:06:33, 21.55s/it] 52%|█████▏ | 7799/15000 [36:05:22<38:55:08, 19.46s/it] 52%|█████▏ | 7800/15000 [36:05:37<36:01:48, 18.02s/it] 52%|█████▏ | 7800/15000 [36:05:37<36:01:48, 18.02s/it] 52%|█████▏ | 7801/15000 [36:05:52<34:05:04, 17.04s/it] 52%|█████▏ | 7802/15000 [36:06:07<32:40:19, 16.34s/it] 52%|█████▏ | 7803/15000 [36:06:21<31:40:13, 15.84s/it] 52%|█████▏ | 7804/15000 [36:06:36<30:57:49, 15.49s/it] 52%|█████▏ | 7805/15000 [36:06:51<30:33:14, 15.29s/it] 52%|█████▏ | 7806/15000 [36:07:05<30:13:28, 15.12s/it] 52%|█<><E29688>4.98s/it] 52%|█████▏ | 7797/15000 [36:04:31<29:50:19, 14.91s/it] 52%|█████▏ | 7798/15000 [36:05:08<43:02:31, 21.52s/it] 52%|█████▏ | 7799/15000 [36:05:22<38:55:38, 19.46s/it] 52%|█████▏ | 7800/15000 [36:05:37<36:01:56, 18.02s/it] 52%|█████▏ | 7800/15000 [36:05:37<36:01:56, 18.02s/it] 52%|█████▏ | 7801/15000 [36:05:52<34:07:36, 17.07s/it] 52%|█████▏ | 7802/15000 [36:06:06<32:40:27, 16.34s/it] 52%|█████▏ | 7803/15000 [36:06:21<31:38:48, 15.83s/it] 52%|█████▏ | 7804/15000 [36:06:36<31:01:51, 15.52s/it] 52%|█████▏ | 7805/15000 [36:06:51<30:33:41, 15.29s/it] 52%|█████▏ | 7806/15000 [36:07:05<30:15:37, 15.14s/it] 52%|█████▏ | 7807/15000 [36:07:20<29:59:21, 15.01s/it] 52%|█████▏ | 7808/15000 [36:07:35<29:47:27, 14.91s/it] 52%|█████▏ | 78<37>███▏ | 7807/15000 [36:07:20<30:04:50, 15.06s/it] 52%|█████▏ | 7808/15000 [36:07:35<29:50:34, 14.94s/it] 52%|█████▏ | 7809/15000 [36:08:12<42:59:14, 21.52s/it] 52%|█████▏ | 7810/15000 [36:08:27<38:52:52, 19.47s/it] 52%|█████▏ | 7811/15000 [36:08:41<35:57:48, 18.01s/it] 52%|█████▏ | 7812/15000 [36:08:56<33:58:34, 17.02s/it] 52%|█████▏ | 7813/15000 [36:09:11<32:35:59, 16.33s/it] 52%|█████▏ | 7814/15000 [36:09:25<31:37:02, 15.84s/it] 52%|█████▏ | 7815/15000 [36:09:40<30:58:45, 15.52s/it] 52%|█████▏ | 7816/15000 [36:09:55<30:28:19, 15.27s/it] 52%|█████▏ | 7817/15000 [36:10:09<30:09:14, 15.11s/it] 52%|█████▏ | 7818/15000 [36:10:24<29:58:28, 15.02s/it] 52%|█████▏ | 7819/15000 [36:10:39<29:48:10, 14.94s/it] 52%|█████▏ | 7820/15000 [36:11:16<43:02:32, 21.58s/it] 52%|█████▏ | 7821/15000
{'loss': 0.8286, 'learning_rate': 9.622235120283769e-05, 'epoch': 1.48}
{'loss': 0.8286, 'learning_rate': 9.622235120283769e-05, 'epoch': 1.48}
6<31:10:18, 15.79s/it] 53%|█████▎ | 7894/15000 [36:31:41<30:38:13, 15.52s/it] 53%|█████▎ | 7895/15000 [36:31:56<30:08:30, 15.27s/it] 53%|█████▎ | 7896/15000 [36:32:10<29:48:21, 15.10s/it] 53%|█████▎ | 7897/15000 [36:32:25<29:32:27, 14.97s/it] 53%|█████▎ | 7898/15000 [36:32:40<29:24:50, 14.91s/it] 53%|█████▎ | 7899/15000 [36:33:16<42:12:05, 21.39s/it] 53%|█████▎ | 7900/15000 [36:33:31<38:11:10, 19.36s/it] 53%|█████▎ | 7900/15000 [36:33:31<38:11:10, 19.36s/it] 53%|█████▎ | 7901/15000 [36:33:46<35:31:46, 18.02s/it] 53%|█████▎ | 7902/15000 [36:34:01<33:36:17, 17.04s/it] 53%|█████▎ | 7903/15000 [36:34:15<32:09:31, 16.31s/it] 53%|█████▎ | 7904/15000 [36:34:30<31:11:49, 15.83s/it] 53%|█████▎ | 7905/15000 [36:34:45<30:35:21, 15.52s/it] 53%|████<E29688>6<31:12:30, 15.81s/it] 53%|█████▎ | 7894/15000 [36:31:41<30:34:36, 15.49s/it] 53%|█████▎ | 7895/15000 [36:31:56<30:11:53, 15.30s/it] 53%|█████▎ | 7896/15000 [36:32:10<29:45:43, 15.08s/it] 53%|█████▎ | 7897/15000 [36:32:25<29:30:04, 14.95s/it] 53%|█████▎ | 7898/15000 [36:32:40<29:25:02, 14.91s/it] 53%|█████▎ | 7899/15000 [36:33:16<42:14:23, 21.41s/it] 53%|█████▎ | 7900/15000 [36:33:31<38:13:18, 19.38s/it] 53%|█████▎ | 7900/15000 [36:33:31<38:13:18, 19.38s/it] 53%|█████▎ | 7901/15000 [36:33:46<35:33:45, 18.03s/it] 53%|█████▎ | 7902/15000 [36:34:00<33:31:08, 17.00s/it] 53%|█████▎ | 7903/15000 [36:34:15<32:10:13, 16.32s/it] 53%|█████▎ | 7904/15000 [36:34:30<31:11:52, 15.83s/it] 53%|█████▎ | 7905/15000 [36:34:45<30:33:56, 15.51s/it] 53%|████<E29688>] 53%|█████▎ | 7896/15000 [36:32:10<29:46:30, 15.09s/it] 53%|█████▎ | 7897/15000 [36:32:25<29:32:46, 14.97s/it] 53%|█████▎ | 7898/15000 [36:32:40<29:21:16, 14.88s/it] 53%|█████▎ | 7899/15000 [36:33:16<42:12:53, 21.40s/it] 53%|█████▎ | 7900/15000 [36:33:31<38:13:18, 19.38s/it] 53%|█████▎ | 7900/15000 [36:33:31<38:13:18, 19.38s/it] 53%|█████▎ | 7901/15000 [36:33:46<35:32:38, 18.02s/it] 53%|█████▎ | 7902/15000 [36:34:00<33:32:26, 17.01s/it] 53%|█████▎ | 7903/15000 [36:34:15<32:11:33, 16.33s/it] 53%|█████▎ | 7904/15000 [36:34:30<31:13:17, 15.84s/it] 53%|█████▎ | 7905/15000 [36:34:45<30:32:52, 15.50s/it] 53%|█████▎ | 7906/15000 [36:34:59<30:04:34, 15.26s/it] 53%|█████▎ | 7907/15000 [36:35:14<29:44:51, 15.10s/it] 53%|█████▎ | 7908/15000<30><30>▎ | 7906/15000 [36:34:59<30:04:27, 15.26s/it] 53%|█████▎ | 7907/15000 [36:35:14<29:45:13, 15.10s/it] 53%|█████▎ | 7908/15000 [36:35:29<29:28:33, 14.96s/it] 53%|█████▎ | 7909/15000 [36:35:43<29:19:08, 14.88s/it] 53%|█████▎ | 7910/15000 [36:36:20<42:21:15, 21.51s/it] 53%|█████▎ | 7911/15000 [36:36:35<38:21:33, 19.48s/it] 53%|█████▎ | 7912/15000 [36:36:50<35:25:49, 18.00s/it] 53%|█████▎ | 7913/15000 [36:37:04<33:29:39, 17.01s/it] 53%|█████▎ | 7914/15000 [36:37:19<32:10:06, 16.34s/it] 53%|█████▎ | 7915/15000 [36:37:34<31:10:03, 15.84s/it] 53%|█████▎ | 7916/15000 [36:37:49<30:31:28, 15.51s/it] 53%|█████▎ | 7917/15000 [36:38:03<29:59:45, 15.25s/it] 53%|█████▎ | 7918/15000 [36:38:18<29:43:33, 15.11s/it] 53%|█████▎ | 7919/15000 [36:38:33<29:29:57, 15.00s/it] 53%|█████▎ | 7920/15000 [36:38:
{'loss': 0.8346, 'learning_rate': 9.406577036341548e-05, 'epoch': 1.5}
{'loss': 0.8346, 'learning_rate': 9.406577036341548e-05, 'epoch': 1.5}
<EFBFBD><EFBFBD>████▎ | 7995/15000 [36:59:52<30:10:24, 15.51s/it] 53%|█████▎ | 7996/15000 [37:00:07<29:39:44, 15.25s/it] 53%|█████▎ | 7997/15000 [37:00:21<29:19:13, 15.07s/it] 53%|█████▎ | 7998/15000 [37:00:36<29:07:22, 14.97s/it] 53%|█████▎ | 7999/15000 [37:00:51<28:58:12, 14.90s/it] 53%|█████▎ | 8000/15000 [37:01:29<42:30:48, 21.86s/it] 53%|█████▎ | 8000/15000 [37:01:29<42:30:48, 21.86s/it]Saving model checkpoint to /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-8000
tokenizer config file saved in /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-8000/tokenizer_config.json
Special tokens file saved in /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-8000/special_tokens_map.json
56, 17.20s/it] 53%|█████▎ | 7993/15000 [36:59:23<31:57:48, 16.42s/it] 53%|█████▎ | 7994/15000 [36:59:37<30:54:00, 15.88s/it] 53%|█████▎ | 7995/15000 [36:59:52<30:14:24, 15.54s/it] 53%|█████▎ | 7996/15000 [37:00:07<29:43:01, 15.27s/it] 53%|█████▎ | 7997/15000 [37:00:21<29:17:35, 15.06s/it] 53%|█████▎ | 7998/15000 [37:00:36<29:06:36, 14.97s/it] 53%|█████▎ | 7999/15000 [37:00:51<28:54:09, 14.86s/it] 53%|█████▎ | 8000/15000 [37:01:29<42:31:58, 21.87s/it] 53%|█████▎ | 8000/15000 [37:01:29<42:31:58, 21.87s/it] 53%|█████▎ | 8001/15000 [37:01:49<41:12:28, 21.20s/it] 53%|█████▎ | 8002/15000 [37:02:04<37:33:39, 19.32s/it] 53%|█████▎ | 8003/15000 [37:02:18<34:49:28, 17.92s/it] 53%|█████▎ | 8004/15000 [37:02:33<32:54:47, 16.94s/it] 53%|█████▎ 11, 17.19s/it] 53%|█████▎ | 7993/15000 [36:59:23<31:54:31, 16.39s/it] 53%|█████▎ | 7994/15000 [36:59:37<30:56:57, 15.90s/it] 53%|█████▎ | 7995/15000 [36:59:52<30:13:29, 15.53s/it] 53%|█████▎ | 7996/15000 [37:00:07<29:40:48, 15.26s/it] 53%|█████▎ | 7997/15000 [37:00:21<29:18:43, 15.07s/it] 53%|█████▎ | 7998/15000 [37:00:36<29:03:16, 14.94s/it] 53%|█████▎ | 7999/15000 [37:00:51<28:57:18, 14.89s/it] 53%|█████▎ | 8000/15000 [37:01:29<42:31:07, 21.87s/it] 53%|█████▎ | 8000/15000 [37:01:29<42:31:07, 21.87s/it] 53%|█████▎ | 8001/15000 [37:01:49<41:15:16, 21.22s/it] 53%|█████▎ | 8002/15000 [37:02:04<37:35:03, 19.33s/it] 53%|█████▎ | 8003/15000 [37:02:18<34:48:47, 17.91s/it] 53%|█████▎ | 8004/15000 [37:02:33<32:50:47, 16.90s/it] 53%|█████▎ 53%|█████▎ | 8001/15000 [37:01:49<41:21:40, 21.27s/it] 53%|█████▎ | 8002/15000 [37:02:03<37:30:23, 19.29s/it] 53%|█████▎ | 8003/15000 [37:02:18<34:47:49, 17.90s/it] 53%|█████▎ | 8004/15000 [37:02:33<32:52:28, 16.92s/it] 53%|█████▎ | 8005/15000 [37:02:47<31:34:40, 16.25s/it] 53%|█████▎ | 8006/15000 [37:03:02<30:41:28, 15.80s/it] 53%|█████▎ | 8007/15000 [37:03:17<29:59:34, 15.44s/it] 53%|█████▎ | 8008/15000 [37:03:31<29:30:41, 15.19s/it] 53%|█████▎ | 8009/15000 [37:03:46<29:11:04, 15.03s/it] 53%|█████▎ | 8010/15000 [37:04:01<28:56:44, 14.91s/it] 53%|█████▎ | 8011/15000 [37:04:37<41:43:20, 21.49s/it] 53%|█████▎ | 8012/15000 [37:04:52<37:45:26, 19.45s/it] 53%|█████▎ | 8013/15000 [37:05:07<35:00:20, 18.04s/it] 53%|█████▎ | 8014/15000 [37:05:22<33:05:50, 17.06s/it] 53%|█████▎ | | 8005/15000 [37:02:47<31:35:49, 16.26s/it] 53%|█████▎ | 8006/15000 [37:03:02<30:41:56, 15.80s/it] 53%|█████▎ | 8007/15000 [37:03:17<29:59:24, 15.44s/it] 53%|█████▎ | 8008/15000 [37:03:31<29:28:21, 15.17s/it] 53%|█████▎ | 8009/15000 [37:03:46<29:15:25, 15.07s/it] 53%|█████▎ | 8010/15000 [37:04:01<28:56:00, 14.90s/it] 53%|█████▎ | 8011/15000 [37:04:37<41:40:16, 21.46s/it] 53%|█████▎ | 8012/15000 [37:04:52<37:45:00, 19.45s/it] 53%|█████▎ | 8013/15000 [37:05:07<35:00:24, 18.04s/it] 53%|█████▎ | 8014/15000 [37:05:22<33:09:14, 17.08s/it] 53%|█████▎ | 8015/15000 [37:05:36<31:43:02, 16.35s/it] 53%|█████▎ | 8016/15000 [37:05:51<30:44:44, 15.85s/it] 53%|█████▎ | 8017/15000 [37:06:06<30:03:34, 15.50s/it] 53%|█████▎ | 8018/15000 [37:06:20<29:34:20, 15.25s/it] 53%|█████▎ | 8019/15000 [37:06:35<29:14
{'loss': 0.8458, 'learning_rate': 9.19119559638596e-05, 'epoch': 1.52}
{'loss': 0.8458, 'learning_rate': 9.19119559638596e-05, 'epoch': 1.52}
00 [37:25:27<28:46:09, 14.98s/it] 54%|█████▍ | 8088/15000 [37:25:41<28:35:29, 14.89s/it] 54%|█████▍ | 8089/15000 [37:26:19<41:31:08, 21.63s/it] 54%|█████▍ | 8090/15000 [37:26:33<37:29:02, 19.53s/it] 54%|█████▍ | 8091/15000 [37:26:48<34:41:43, 18.08s/it] 54%|█████▍ | 8092/15000 [37:27:03<32:46:23, 17.08s/it] 54%|█████▍ | 8093/15000 [37:27:17<31:23:56, 16.37s/it] 54%|█████▍ | 8094/15000 [37:27:32<30:27:43, 15.88s/it] 54%|█████▍ | 8095/15000 [37:27:47<29:42:38, 15.49s/it] 54%|█████▍ | 8096/15000 [37:28:01<29:14:07, 15.24s/it] 54%|█████▍ | 8097/15000 [37:28:16<28:57:52, 15.11s/it] 54%|█████▍ | 8098/15000 [37:28:31<28:45:39, 15.00s/it] 54%|█████▍ | 8099/15000 [37:28:46<28:37:57, 14.94s/it] 54%|█████▍ | 8100/15000 [37:29:24<42:09:03, 21.99s/it] 54%|<7C><>8s/it] 54%|█████▍ | 8092/15000 [37:27:03<32:45:35, 17.07s/it] 54%|█████▍ | 8093/15000 [37:27:17<31:22:50, 16.36s/it] 54%|█████▍ | 8094/15000 [37:27:32<30:22:25, 15.83s/it] 54%|█████▍ | 8095/15000 [37:27:47<29:45:39, 15.52s/it] 54%|█████▍ | 8096/15000 [37:28:01<29:17:31, 15.27s/it] 54%|█████▍ | 8097/15000 [37:28:16<28:58:07, 15.11s/it] 54%|█████▍ | 8098/15000 [37:28:31<28:44:04, 14.99s/it] 54%|█████▍ | 8099/15000 [37:28:46<28:40:34, 14.96s/it] 54%|█████▍ | 8100/15000 [37:29:24<42:04:08, 21.95s/it] 54%|█████▍ | 8100/15000 [37:29:24<42:04:08, 21.95s/it] 54%|█████▍ | 8101/15000 [37:29:39<38:01:26, 19.84s/it] 54%|█████▍ | 8102/15000 [37:29:54<35:03:23, 18.30s/it] 54%|█████▍ | 8103/15000 [37:30:08<32:54:17, 17.18s/it] 54%|█████▍ | 8104/0s/it] 54%|█████▍ | 8092/15000 [37:27:03<32:41:46, 17.04s/it] 54%|█████▍ | 8093/15000 [37:27:17<31:27:03, 16.39s/it] 54%|█████▍ | 8094/15000 [37:27:32<30:24:09, 15.85s/it] 54%|█████▍ | 8095/15000 [37:27:47<29:46:25, 15.52s/it] 54%|█████▍ | 8096/15000 [37:28:01<29:16:30, 15.27s/it] 54%|█████▍ | 8097/15000 [37:28:16<28:58:54, 15.11s/it] 54%|█████▍ | 8098/15000 [37:28:31<28:46:54, 15.01s/it] 54%|█████▍ | 8099/15000 [37:28:46<28:36:56, 14.93s/it] 54%|█████▍ | 8100/15000 [37:29:24<42:04:40, 21.95s/it] 54%|█████▍ | 8100/15000 [37:29:24<42:04:40, 21.95s/it] 54%|█████▍ | 8101/15000 [37:29:39<38:01:34, 19.84s/it] 54%|█████▍ | 8102/15000 [37:29:54<35:04:35, 18.31s/it] 54%|█████▍ | 8103/15000 [37:30:08<32:57:13, 17.20s/it] 54%|█████▍ | 8104/<2F>████▍ | 8100/15000 [37:29:24<42:09:03, 21.99s/it] 54%|█████▍ | 8101/15000 [37:29:39<38:00:30, 19.83s/it] 54%|█████▍ | 8102/15000 [37:29:54<35:02:21, 18.29s/it] 54%|█████▍ | 8103/15000 [37:30:08<32:57:27, 17.20s/it] 54%|█████▍ | 8104/15000 [37:30:23<31:29:36, 16.44s/it] 54%|█████▍ | 8105/15000 [37:30:38<30:28:25, 15.91s/it] 54%|█████▍ | 8106/15000 [37:30:52<29:48:02, 15.56s/it] 54%|█████▍ | 8107/15000 [37:31:07<29:14:56, 15.28s/it] 54%|█████▍ | 8108/15000 [37:31:22<28:58:17, 15.13s/it] 54%|█████▍ | 8109/15000 [37:31:36<28:42:39, 15.00s/it] 54%|█████▍ | 8110/15000 [37:31:51<28:30:01, 14.89s/it] 54%|█████▍ | 8111/15000 [37:32:30<42:07:23, 22.01s/it] 54%|█████▍ | 8112/15000 [37:32:44<37:57:06, 19.84s/it] 54%|█████▍ | 8113/15000 [37:32:59<34:57:41, 18.28s/it] 54%|█████▍ | 8114/15
{'loss': 0.8459, 'learning_rate': 8.976191207687775e-05, 'epoch': 1.53}
{'loss': 0.8459, 'learning_rate': 8.976191207687775e-05, 'epoch': 1.53}
3:09<28:56:23, 15.29s/it] 55%|█████▍ | 8187/15000 [37:53:23<28:37:54, 15.13s/it] 55%|█████▍ | 8188/15000 [37:53:38<28:24:06, 15.01s/it] 55%|█████▍ | 8189/15000 [37:53:53<28:16:51, 14.95s/it] 55%|█████▍ | 8190/15000 [37:54:30<40:44:16, 21.54s/it] 55%|█████▍ | 8191/15000 [37:54:45<36:50:49, 19.48s/it] 55%|█████▍ | 8192/15000 [37:54:59<34:06:53, 18.04s/it] 55%|█████▍ | 8193/15000 [37:55:14<32:09:09, 17.00s/it] 55%|█████▍ | 8194/15000 [37:55:29<30:51:24, 16.32s/it] 55%|█████▍ | 8195/15000 [37:55:43<29:58:42, 15.86s/it] 55%|█████▍ | 8196/15000 [37:55:58<29:21:22, 15.53s/it] 55%|█████▍ | 8197/15000 [37:56:13<28:53:08, 15.29s/it] 55%|█████▍ | 8198/15000 [37:56:28<28:34:08, 15.12s/it] 55%|█████▍ | 8199/15000 [37:56:42<28:20:29, 15.00s/it] 55%|█████▍ | 8200/15000 [37:56:57<28:08:23, 14.90s/it] 55%|█████▍ | 8191/15000 [37:54:45<36:51:51, 19.49s/it] 55%|█████▍ | 8192/15000 [37:54:59<34:07:31, 18.05s/it] 55%|█████▍ | 8193/15000 [37:55:14<32:12:42, 17.04s/it] 55%|█████▍ | 8194/15000 [37:55:29<30:49:17, 16.30s/it] 55%|█████▍ | 8195/15000 [37:55:43<29:56:49, 15.84s/it] 55%|█████▍ | 8196/15000 [37:55:58<29:22:21, 15.54s/it] 55%|█████▍ | 8197/15000 [37:56:13<28:50:21, 15.26s/it] 55%|█████▍ | 8198/15000 [37:56:28<28:34:54, 15.13s/it] 55%|█████▍ | 8199/15000 [37:56:42<28:21:16, 15.01s/it] 55%|█████▍ | 8200/15000 [37:56:57<28:07:53, 14.89s/it] 55%|█████▍ | 8200/15000 [37:56:57<28:07:53, 14.89s/it] 55%|█████▍ | 8201/15000 [37:57:34<40:40:37, 21.54s/it] 55%|█████▍ | 8202/15000 [37:57:49<36:45:58, 19.47s/it] 55%|█████▍ | 8203/15000 [355%|█████▍ | 8191/15000 [37:54:45<36:53:22, 19.50s/it] 55%|█████▍ | 8192/15000 [37:54:59<34:06:25, 18.04s/it] 55%|█████▍ | 8193/15000 [37:55:14<32:12:42, 17.04s/it] 55%|█████▍ | 8194/15000 [37:55:29<30:48:09, 16.29s/it] 55%|█████▍ | 8195/15000 [37:55:43<29:56:33, 15.84s/it] 55%|█████▍ | 8196/15000 [37:55:58<29:21:20, 15.53s/it] 55%|█████▍ | 8197/15000 [37:56:13<28:53:54, 15.29s/it] 55%|█████▍ | 8198/15000 [37:56:28<28:34:20, 15.12s/it] 55%|█████▍ | 8199/15000 [37:56:42<28:19:27, 14.99s/it] 55%|█████▍ | 8200/15000 [37:56:57<28:08:04, 14.89s/it] 55%|█████▍ | 8200/15000 [37:56:57<28:08:04, 14.89s/it] 55%|█████▍ | 8201/15000 [37:57:34<40:41:32, 21.55s/it] 55%|█████▍ | 8202/15000 [37:57:49<36:48:27, 19.49s/it] 55%|█████▍ | 8203/15000 [3 55%|█████▍ | 8200/15000 [37:56:57<28:08:23, 14.90s/it] 55%|█████▍ | 8201/15000 [37:57:34<40:41:53, 21.55s/it] 55%|█████▍ | 8202/15000 [37:57:49<36:47:12, 19.48s/it] 55%|█████▍ | 8203/15000 [37:58:03<34:01:44, 18.02s/it] 55%|█████▍ | 8204/15000 [37:58:18<32:09:47, 17.04s/it] 55%|█████▍ | 8205/15000 [37:58:33<30:49:41, 16.33s/it] 55%|█████▍ | 8206/15000 [37:58:47<29:50:43, 15.81s/it] 55%|█████▍ | 8207/15000 [37:59:02<29:16:45, 15.52s/it] 55%|█████▍ | 8208/15000 [37:59:17<28:49:31, 15.28s/it] 55%|█████▍ | 8209/15000 [37:59:32<28:37:38, 15.18s/it] 55%|█████▍ | 8210/15000 [37:59:47<28:24:16, 15.06s/it] 55%|█████▍ | 8211/15000 [38:00:01<28:11:51, 14.95s/it] 55%|█████▍ | 8212/15000 [38:00:38<40:29:56, 21.48s/it] 55%|█████▍ | 8213/15000 [38:
{'loss': 0.8457, 'learning_rate': 8.7616641017427e-05, 'epoch': 1.55}
{'loss': 0.8457, 'learning_rate': 8.7616641017427e-05, 'epoch': 1.55}
<EFBFBD><EFBFBD>███▌ | 8290/15000 [38:22:25<40:55:49, 21.96s/it] 55%|█████▌ | 8291/15000 [38:22:39<36:49:35, 19.76s/it] 55%|█████▌ | 8292/15000 [38:22:54<34:00:47, 18.25s/it] 55%|█████▌ | 8293/15000 [38:23:09<32:00:10, 17.18s/it] 55%|█████▌ | 8294/15000 [38:23:23<30:34:31, 16.41s/it] 55%|█████▌ | 8295/15000 [38:23:38<29:32:26, 15.86s/it] 55%|█████▌ | 8296/15000 [38:23:52<28:48:36, 15.47s/it] 55%|█████▌ | 8297/15000 [38:24:07<28:27:30, 15.28s/it] 55%|█████▌ | 8298/15000 [38:24:22<28:14:31, 15.17s/it] 55%|█████▌ | 8299/15000 [38:24:37<27:57:26, 15.02s/it] 55%|█████▌ | 8300/15000 [38:24:52<27:46:46, 14.93s/it] 55%|█████▌ | 8300/15000 [38:24:52<27:46:46, 14.93s/it] 55%|█████▌ | 8301/15000 [38:25:06<27:42:39, 14.89s/it] 55%|█████▌ | 8302/15000 [38:25:45<<3C><>███▌ | 8290/15000 [38:22:25<40:56:32, 21.97s/it] 55%|█████▌ | 8291/15000 [38:22:39<36:51:29, 19.78s/it] 55%|█████▌ | 8292/15000 [38:22:54<34:01:35, 18.26s/it] 55%|█████▌ | 8293/15000 [38:23:09<32:01:46, 17.19s/it] 55%|█████▌ | 8294/15000 [38:23:23<30:30:26, 16.38s/it] 55%|█████▌ | 8295/15000 [38:23:38<29:31:45, 15.85s/it] 55%|█████▌ | 8296/15000 [38:23:52<28:52:01, 15.50s/it] 55%|█████▌ | 8297/15000 [38:24:07<28:27:28, 15.28s/it] 55%|█████▌ | 8298/15000 [38:24:22<28:16:08, 15.18s/it] 55%|█████▌ | 8299/15000 [38:24:37<27:57:48, 15.02s/it] 55%|█████▌ | 8300/15000 [38:24:52<27:48:40, 14.94s/it] 55%|█████▌ | 8300/15000 [38:24:52<27:48:40, 14.94s/it] 55%|█████▌ | 8301/15000 [38:25:06<27:39:12, 14.86s/it] 55%|█████▌ | 8302/15000 [38:25:45<<3C><>██▌ | 8300/15000 [38:24:52<27:48:43, 14.94s/it] 55%|█████▌ | 8300/15000 [38:24:52<27:48:43, 14.94s/it] 55%|█████▌ | 8301/15000 [38:25:06<27:39:02, 14.86s/it] 55%|█████▌ | 8302/15000 [38:25:45<40:45:09, 21.90s/it] 55%|█████▌ | 8303/15000 [38:25:59<36:46:30, 19.77s/it] 55%|█████▌ | 8304/15000 [38:26:14<33:56:08, 18.24s/it] 55%|█████▌ | 8305/15000 [38:26:29<32:00:51, 17.21s/it] 55%|█████▌ | 8306/15000 [38:26:43<30:32:45, 16.43s/it] 55%|█████▌ | 8307/15000 [38:26:58<29:34:57, 15.91s/it] 55%|█████▌ | 8308/15000 [38:27:13<28:52:12, 15.53s/it] 55%|█████▌ | 8309/15000 [38:27:27<28:23:42, 15.28s/it] 55%|█████▌ | 8310/15000 [38:27:42<28:09:55, 15.16s/it] 55%|█████▌ | 8311/15000 [38:27:57<27:55:44, 15.03s/it] 55%|█████▌ | 8312/15000 [38:28:12<27:40:46:05, 21.91s/it] 55%|█████▌ | 8303/15000 [38:25:59<36:47:35, 19.78s/it] 55%|█████▌ | 8304/15000 [38:26:14<33:57:48, 18.26s/it] 55%|█████▌ | 8305/15000 [38:26:29<31:56:25, 17.17s/it] 55%|█████▌ | 8306/15000 [38:26:44<30:34:52, 16.45s/it] 55%|█████▌ | 8307/15000 [38:26:58<29:34:53, 15.91s/it] 55%|█████▌ | 8308/15000 [38:27:13<28:49:40, 15.51s/it] 55%|█████▌ | 8309/15000 [38:27:28<28:28:58, 15.32s/it] 55%|█████▌ | 8310/15000 [38:27:42<28:08:10, 15.14s/it] 55%|█████▌ | 8311/15000 [38:27:57<27:54:29, 15.02s/it] 55%|█████▌ | 8312/15000 [38:28:12<27:46:06, 14.95s/it] 55%|█████▌ | 8313/15000 [38:28:50<40:23:19, 21.74s/it] 55%|█████▌ | 8314/15000 [38:29:04<36:35:38, 19.70s/it] 55%|█████▌ | 8315/15000 [38:29:19<33:46:21, 18.19s/it] 55%|█████▌ | 8316/15000 [38:29:34<31:52:16, 17.17s/it] 55%|█
{'loss': 0.8452, 'learning_rate': 8.5477142875451e-05, 'epoch': 1.57}
{'loss': 0.8452, 'learning_rate': 8.5477142875451e-05, 'epoch': 1.57}
█▌ | 8389/15000 [38:49:42<27:33:06, 15.00s/it] 56%|█████▌ | 8390/15000 [38:49:57<27:22:43, 14.91s/it] 56%|█████▌ | 8391/15000 [38:50:34<39:40:59, 21.62s/it] 56%|█████▌ | 8392/15000 [38:50:49<35:53:16, 19.55s/it] 56%|█████▌ | 8393/15000 [38:51:03<33:12:27, 18.09s/it] 56%|█████▌ | 8394/15000 [38:51:18<31:23:45, 17.11s/it] 56%|█████▌ | 8395/15000 [38:51:33<30:01:00, 16.36s/it] 56%|█████▌ | 8396/15000 [38:51:47<29:08:34, 15.89s/it] 56%|█████▌ | 8397/15000 [38:52:02<28:29:52, 15.54s/it] 56%|█████▌ | 8398/15000 [38:52:17<28:05:18, 15.32s/it] 56%|█████▌ | 8399/15000 [38:52:32<27:42:05, 15.11s/it] 56%|█████▌ | 8400/15000 [38:52:46<27:28:33, 14.99s/it] 56%|█████▌ | 8400/15000 [38:52:47<27:28:33, 14.99s/it] 56%|█████▌ | 8401/15000 [38:53:01<27:24:14█▌ | 8389/15000 [38:49:42<27:32:53, 15.00s/it] 56%|█████▌ | 8390/15000 [38:49:57<27:24:52, 14.93s/it] 56%|█████▌ | 8391/15000 [38:50:34<39:38:20, 21.59s/it] 56%|█████▌ | 8392/15000 [38:50:49<35:53:52, 19.56s/it] 56%|█████▌ | 8393/15000 [38:51:03<33:10:17, 18.07s/it] 56%|█████▌ | 8394/15000 [38:51:18<31:22:45, 17.10s/it] 56%|█████▌ | 8395/15000 [38:51:33<30:05:23, 16.40s/it] 56%|█████▌ | 8396/15000 [38:51:47<29:08:42, 15.89s/it] 56%|█████▌ | 8397/15000 [38:52:02<28:28:13, 15.52s/it] 56%|█████▌ | 8398/15000 [38:52:17<28:05:10, 15.32s/it] 56%|█████▌ | 8399/15000 [38:52:32<27:44:43, 15.13s/it] 56%|█████▌ | 8400/15000 [38:52:46<27:27:46, 14.98s/it] 56%|█████▌ | 8400/15000 [38:52:47<27:27:46, 14.98s/it] 56%|█████▌ | 8401/15000 [38:53:01<27:26:04▌ | 8399/15000 [38:52:32<27:45:31, 15.14s/it] 56%|█████▌ | 8400/15000 [38:52:46<27:28:01, 14.98s/it] 56%|█████▌ | 8400/15000 [38:52:46<27:28:01, 14.98s/it] 56%|█████▌ | 8401/15000 [38:53:01<27:24:48, 14.96s/it] 56%|█████▌ | 8402/15000 [38:53:38<39:28:47, 21.54s/it] 56%|█████▌ | 8403/15000 [38:53:53<35:40:19, 19.47s/it] 56%|█████▌ | 8404/15000 [38:54:07<32:58:42, 18.00s/it] 56%|█████▌ | 8405/15000 [38:54:22<31:05:01, 16.97s/it] 56%|█████▌ | 8406/15000 [38:54:36<29:50:19, 16.29s/it] 56%|█████▌ | 8407/15000 [38:54:51<28:58:14, 15.82s/it] 56%|█████▌ | 8408/15000 [38:55:06<28:23:18, 15.50s/it] 56%|█████▌ | 8409/15000 [38:55:21<27:55:56, 15.26s/it] 56%|█████▌ | 8410/15000 [38:55:35<27:31:58, 15.04s/it] 56%|█████▌ | 8411/15000 [38:55:50<27:23:09, 1, 14.95s/it] 56%|█████▌ | 8402/15000 [38:53:38<39:30:17, 21.55s/it] 56%|█████▌ | 8403/15000 [38:53:53<35:39:45, 19.46s/it] 56%|█████▌ | 8404/15000 [38:54:07<32:59:05, 18.00s/it] 56%|█████▌ | 8405/15000 [38:54:22<31:09:05, 17.00s/it] 56%|█████▌ | 8406/15000 [38:54:37<29:49:57, 16.29s/it] 56%|█████▌ | 8407/15000 [38:54:51<28:59:51, 15.83s/it] 56%|█████▌ | 8408/15000 [38:55:06<28:20:27, 15.48s/it] 56%|█████▌ | 8409/15000 [38:55:21<27:55:15, 15.25s/it] 56%|█████▌ | 8410/15000 [38:55:35<27:34:41, 15.07s/it] 56%|█████▌ | 8411/15000 [38:55:50<27:23:14, 14.96s/it] 56%|█████▌ | 8412/15000 [38:56:05<27:14:06, 14.88s/it] 56%|█████▌ | 8413/15000 [38:56:42<39:30:53, 21.60s/it] 56%|█████▌ | 8414/15000 [38:56:57<35:47:32, 19.56s/it] 56%|█████▌ | 8415/15000 [38:57:11<33:03:33, 18.07s/it] 56%|███<E29688><E29688>
| 8488/15000 [39:17:25<27:20:19, 15.11s/it] 57%|█████▋ | 8489/15000 [39:17:39<27:05:08, 14.98s/it] 57%|█████▋ | 8490/15000 [39:17:54<26:55:58, 14.89s/it] 57%|█████▋ | 8491/15000 [39:18:09<26:52:39, 14.87s/it] 57%|█████▋ | 8492/15000 [39:18:48<39:46:22, 22.00s/it] 57%|█████▋ | 8493/15000 [39:19:02<35:49:33, 19.82s/it] 57%|█████▋ | 8494/15000 [39:19:17<33:02:50, 18.29s/it] 57%|█████▋ | 8495/15000 [39:19:32<31:08:04, 17.23s/it] 57%|█████▋ | 8496/15000 [39:19:47<29:45:38, 16.47s/it] 57%|█████▋ | 8497/15000 [39:20:01<28:42:14, 15.89s/it] 57%|█████▋ | 8498/15000 [39:20:16<28:02:30, 15.53s/it] 57%|█████▋ | 8499/15000 [39:20:30<27:36:12, 15.29s/it] 57%|█████▋ | 8500/15000 [39:20:45<27:13:48, 15.08s/it] 57%|█████▋ | 8500/15000 [39:20:45<27:13:48, 15.08s{'loss': 0.84, 'learning_rate': 8.334441504965455e-05, 'epoch': 1.59}
| 8488/15000 [39:17:25<27:21:54, 15.13s/it] 57%|█████▋ | 8489/15000 [39:17:40<27:07:47, 15.00s/it] 57%|█████▋ | 8490/15000 [39:17:54<26:56:21, 14.90s/it] 57%|█████▋ | 8491/15000 [39:18:09<26:49:22, 14.84s/it] 57%|█████▋ | 8492/15000 [39:18:48<39:45:31, 21.99s/it] 57%|█████▋ | 8493/15000 [39:19:02<35:52:35, 19.85s/it] 57%|█████▋ | 8494/15000 [39:19:17<33:04:12, 18.30s/it] 57%|█████▋ | 8495/15000 [39:19:32<31:04:50, 17.20s/it] 57%|█████▋ | 8496/15000 [39:19:46<29:45:25, 16.47s/it] 57%|█████▋ | 8497/15000 [39:20:01<28:42:02, 15.89s/it] 57%|█████▋ | 8498/15000 [39:20:16<28:04:17, 15.54s/it] 57%|█████▋ | 8499/15000 [39:20:30<27:35:03, 15.28s/it] 57%|█████▋ | 8500/15000 [39:20:45<27:13:10, 15.08s/it] 57%|█████▋ | 8500/15000 [39:20:45<27:13:10, 15.08s{'loss': 0.84, 'learning_rate': 8.334441504965455e-05, 'epoch': 1.59}
8498/15000 [39:20:16<28:02:43, 15.53s/it] 57%|█████▋ | 8499/15000 [39:20:30<27:33:13, 15.26s/it] 57%|█████▋ | 8500/15000 [39:20:45<27:12:34, 15.07s/it] 57%|█████▋ | 8500/15000 [39:20:45<27:12:34, 15.07s/it] 57%|█████▋ | 8501/15000 [39:21:00<27:06:21, 15.01s/it] 57%|█████▋ | 8502/15000 [39:21:14<26:53:55, 14.90s/it] 57%|█████▋ | 8503/15000 [39:21:53<39:41:06, 21.99s/it] 57%|█████▋ | 8504/15000 [39:22:08<35:42:55, 19.79s/it] 57%|█████▋ | 8505/15000 [39:22:22<32:57:24, 18.27s/it] 57%|█████▋ | 8506/15000 [39:22:37<31:01:59, 17.20s/it] 57%|█████▋ | 8507/15000 [39:22:52<29:36:41, 16.42s/it] 57%|█████▋ | 8508/15000 [39:23:06<28:42:07, 15.92s/it] 57%|█████▋ | 8509/15000 [39:23:21<28:00:06, 15.53s/it] 57%|█████▋ | 8510/15000 [39:23:36<27:29:20, 15.25s/it/it] 57%|█████▋ | 8501/15000 [39:21:00<27:08:58, 15.04s/it] 57%|█████▋ | 8502/15000 [39:21:15<26:53:41, 14.90s/it] 57%|█████▋ | 8503/15000 [39:21:53<39:34:30, 21.93s/it] 57%|█████▋ | 8504/15000 [39:22:08<35:42:52, 19.79s/it] 57%|█████▋ | 8505/15000 [39:22:22<32:58:25, 18.28s/it] 57%|█████▋ | 8506/15000 [39:22:37<31:00:44, 17.19s/it] 57%|█████▋ | 8507/15000 [39:22:52<29:34:48, 16.40s/it] 57%|█████▋ | 8508/15000 [39:23:06<28:42:26, 15.92s/it] 57%|█████▋ | 8509/15000 [39:23:21<28:00:47, 15.54s/it] 57%|█████▋ | 8510/15000 [39:23:36<27:30:22, 15.26s/it] 57%|█████▋ | 8511/15000 [39:23:50<27:12:15, 15.09s/it] 57%|█████▋ | 8512/15000 [39:24:05<26:58:22, 14.97s/it] 57%|█████▋ | 8513/15000 [39:24:20<26:47:59, 14.87s/it] 57%|█████▋ | 8514/15000 [39:24:58<39:17:06, 21.80s/it] 57%|█████▋ /it] 57%|█████▋ | 8501/15000 [39:21:00<27:04:53, 15.00s/it] 57%|█████▋ | 8502/15000 [39:21:15<26:54:42, 14.91s/it] 57%|█████▋ | 8503/15000 [39:21:53<39:36:53, 21.95s/it] 57%|█████▋ | 8504/15000 [39:22:08<35:41:51, 19.78s/it] 57%|█████▋ | 8505/15000 [39:22:22<33:00:57, 18.30s/it] 57%|█████▋ | 8506/15000 [39:22:37<31:03:09, 17.21s/it] 57%|█████▋ | 8507/15000 [39:22:52<29:35:22, 16.41s/it] 57%|█████▋ | 8508/15000 [39:23:06<28:39:20, 15.89s/it] 57%|█████▋ | 8509/15000 [39:23:21<28:02:25, 15.55s/it] 57%|█████▋ | 8510/15000 [39:23:36<27:29:23, 15.25s/it] 57%|█████▋ | 8511/15000 [39:23:50<27:12:15, 15.09s/it] 57%|█████▋ | 8512/15000 [39:24:05<26:58:50, 14.97s/it] 57%|█████▋ | 8513/15000 [39:24:20<26:50:27, 14.90s/it] 57%|█████▋ | 8514/15000 [39:24:58<39:17:44, 21.81s/it] 57%|█████▋ ] 57%|█████▋ | 8511/15000 [39:23:50<27:10:28, 15.08s/it] 57%|█████▋ | 8512/15000 [39:24:05<26:56:48, 14.95s/it] 57%|█████▋ | 8513/15000 [39:24:20<26:53:10, 14.92s/it] 57%|█████▋ | 8514/15000 [39:24:58<39:19:25, 21.83s/it] 57%|█████▋ | 8515/15000 [39:25:12<35:29:22, 19.70s/it] 57%|█████▋ | 8516/15000 [39:25:27<32:46:15, 18.19s/it] 57%|█████▋ | 8517/15000 [39:25:42<30:50:09, 17.12s/it] 57%|█████▋ | 8518/15000 [39:25:56<29:30:01, 16.38s/it] 57%|█████▋ | 8519/15000 [39:26:11<28:32:31, 15.85s/it] 57%|█████▋ | 8520/15000 [39:26:26<27:49:38, 15.46s/it] 57%|█████▋ | 8521/15000 [39:26:40<27:23:34, 15.22s/it] 57%|█████▋ | 8522/15000 [39:26:55<27:04:38, 15.05s/it] 57%|█████▋ | 8523/15000 [39:27:10<26:51:55, 14.93s/it] 57%|█████▋ | 8524/15000 [39:27:24<26:44:33, 14.87s/it] 57%|█████▋
/15000 [39:45:07<28:21:17, 15.92s/it] 57%|█████▋ | 8588/15000 [39:45:22<27:40:52, 15.54s/it] 57%|█████▋ | 8589/15000 [39:45:37<27:16:21, 15.31s/it] 57%|█████▋ | 8590/15000 [39:45:51<26:51:06, 15.08s/it] 57%|█████▋ | 8591/15000 [39:46:06<26:39:15, 14.97s/it] 57%|█████▋ | 8592/15000 [39:46:21<26:28:03, 14.87s/it] 57%|█████▋ | 8593/15000 [39:46:58<38:28:34, 21.62s/it] 57%|█████▋ | 8594/15000 [39:47:13<34:48:33, 19.56s/it] 57%|█████▋ | 8595/15000 [39:47:27<32:10:10, 18.08s/it] 57%|█████▋ | 8596/15000 [39:47:42<30:22:43, 17.08s/it] 57%|█████▋ | 8597/15000 [39:47:57<29:03:46, 16.34s/it] 57%|█████▋ | 8598/15000 [39:48:12<28:11:44, 15.86s/it] 57%|█████▋ | 8599/15000 [39:48:26<27:35:23, 15.52s/it] 57%|█████▋ | 8600/15000 [39:48:41<27:10:26, 15.29s/it] 57{'loss': 0.8266, 'learning_rate': 8.1219451782533e-05, 'epoch': 1.61}
/15000 [39:45:07<28:22:14, 15.93s/it] 57%|█████▋ | 8588/15000 [39:45:22<27:40:43, 15.54s/it] 57%|█████▋ | 8589/15000 [39:45:37<27:16:31, 15.32s/it] 57%|█████▋ | 8590/15000 [39:45:51<26:51:37, 15.09s/it] 57%|█████▋ | 8591/15000 [39:46:06<26:37:18, 14.95s/it] 57%|█████▋ | 8592/15000 [39:46:21<26:29:23, 14.88s/it] 57%|█████▋ | 8593/15000 [39:46:58<38:27:25, 21.61s/it] 57%|█████▋ | 8594/15000 [39:47:13<34:46:11, 19.54s/it] 57%|█████▋ | 8595/15000 [39:47:28<32:14:10, 18.12s/it] 57%|█████▋ | 8596/15000 [39:47:42<30:20:41, 17.06s/it] 57%|█████▋ | 8597/15000 [39:47:57<29:04:50, 16.35s/it] 57%|█████▋ | 8598/15000 [39:48:12<28:12:26, 15.86s/it] 57%|█████▋ | 8599/15000 [39:48:26<27:35:54, 15.52s/it] 57%|█████▋ | 8600/15000 [39:48:41<27:10:25, 15.29s/it] 57{'loss': 0.8266, 'learning_rate': 8.1219451782533e-05, 'epoch': 1.61}
000 [39:47:57<29:06:12, 16.36s/it] 57%|█████▋ | 8598/15000 [39:48:12<28:12:35, 15.86s/it] 57%|█████▋ | 8599/15000 [39:48:26<27:35:21, 15.52s/it] 57%|█████▋ | 8600/15000 [39:48:41<27:09:52, 15.28s/it] 57%|█████▋ | 8600/15000 [39:48:41<27:09:52, 15.28s/it] 57%|█████▋ | 8601/15000 [39:48:56<26:59:17, 15.18s/it] 57%|█████▋ | 8602/15000 [39:49:11<26:39:37, 15.00s/it] 57%|█████▋ | 8603/15000 [39:49:25<26:29:14, 14.91s/it] 57%|█████▋ | 8604/15000 [39:50:02<38:22:39, 21.60s/it] 57%|█████▋ | 8605/15000 [39:50:17<34:40:56, 19.52s/it] 57%|█████▋ | 8606/15000 [39:50:32<32:05:08, 18.07s/it] 57%|█████▋ | 8607/15000 [39:50:46<30:15:29, 17.04s/it] 57%|█████▋ | 8608/15000 [39:51:01<28:58:58, 16.32s/it] 57%|█████▋ | 8609/15000 [39:51:16<28:06:14, 15.83s/it] 57%|<7C>%|█████▋ | 8600/15000 [39:48:41<27:10:25, 15.29s/it] 57%|█████▋ | 8601/15000 [39:48:56<26:57:32, 15.17s/it] 57%|█████▋ | 8602/15000 [39:49:11<26:43:34, 15.04s/it] 57%|█████▋ | 8603/15000 [39:49:25<26:31:02, 14.92s/it] 57%|█████▋ | 8604/15000 [39:50:02<38:18:13, 21.56s/it] 57%|█████▋ | 8605/15000 [39:50:17<34:39:01, 19.51s/it] 57%|█████▋ | 8606/15000 [39:50:32<32:04:15, 18.06s/it] 57%|█████▋ | 8607/15000 [39:50:46<30:16:47, 17.05s/it] 57%|█████▋ | 8608/15000 [39:51:01<28:58:42, 16.32s/it] 57%|█████▋ | 8609/15000 [39:51:16<28:04:43, 15.82s/it] 57%|█████▋ | 8610/15000 [39:51:30<27:30:05, 15.49s/it] 57%|█████▋ | 8611/15000 [39:51:45<27:08:55, 15.30s/it] 57%|█████▋ | 8612/15000 [39:52:00<26:47:24, 15.10s/it] 57%|█████▋ | 8613/15000 [39:52:15<26:38:24, 15.02s/it] 57%|█████▋ | 8614%|█████▋ | 8600/15000 [39:48:41<27:10:26, 15.29s/it] 57%|█████▋ | 8601/15000 [39:48:56<26:59:50, 15.19s/it] 57%|█████▋ | 8602/15000 [39:49:11<26:42:00, 15.02s/it] 57%|█████▋ | 8603/15000 [39:49:25<26:28:10, 14.90s/it] 57%|█████▋ | 8604/15000 [39:50:02<38:19:00, 21.57s/it] 57%|█████▋ | 8605/15000 [39:50:17<34:39:08, 19.51s/it] 57%|█████▋ | 8606/15000 [39:50:32<32:03:26, 18.05s/it] 57%|█████▋ | 8607/15000 [39:50:46<30:14:28, 17.03s/it] 57%|█████▋ | 8608/15000 [39:51:01<29:01:05, 16.34s/it] 57%|█████▋ | 8609/15000 [39:51:16<28:05:16, 15.82s/it] 57%|█████▋ | 8610/15000 [39:51:30<27:31:10, 15.50s/it] 57%|█████▋ | 8611/15000 [39:51:45<27:06:08, 15.27s/it] 57%|█████▋ | 8612/15000 [39:52:00<26:50:22, 15.13s/it] 57%|█████▋ | 8613/15000 [39:52:15<26:37:04, 15.00s/it] 57%|█████▋ | 8614<31><34>████▋ | 8610/15000 [39:51:31<27:32:28, 15.52s/it] 57%|█████▋ | 8611/15000 [39:51:45<27:06:46, 15.28s/it] 57%|█████▋ | 8612/15000 [39:52:00<26:48:59, 15.11s/it] 57%|█████▋ | 8613/15000 [39:52:15<26:38:29, 15.02s/it] 57%|█████▋ | 8614/15000 [39:52:30<26:30:07, 14.94s/it] 57%|█████▋ | 8615/15000 [39:52:44<26:19:30, 14.84s/it] 57%|█████▋ | 8616/15000 [39:53:21<38:05:36, 21.48s/it] 57%|█████▋ | 8617/15000 [39:53:36<34:29:04, 19.45s/it] 57%|█████▋ | 8618/15000 [39:53:51<31:59:23, 18.04s/it] 57%|█████▋ | 8619/15000 [39:54:05<30:12:25, 17.04s/it] 57%|█████▋ | 8620/15000 [39:54:20<28:57:58, 16.34s/it] 57%|█████▋ | 8621/15000 [39:54:35<28:06:15, 15.86s/it] 57%|█████▋ | 8622/15000 [39:54:49<27:29:10, 15.51s/it] 57%|█████▋ | 8623/15000 [39:55:04<27:06:52, 15.31s/it] 57%|█████▋ | 8624/1
40:12:52<30:01:43, 17.12s/it] 58%|█████▊ | 8687/15000 [40:13:07<28:42:33, 16.37s/it] 58%|█████▊ | 8688/15000 [40:13:21<27:52:43, 15.90s/it] 58%|█████▊ | 8689/15000 [40:13:36<27:14:51, 15.54s/it] 58%|█████▊ | 8690/15000 [40:13:51<26:48:11, 15.29s/it] 58%|█████▊ | 8691/15000 [40:14:05<26:26:45, 15.09s/it] 58%|█████▊ | 8692/15000 [40:14:20<26:10:53, 14.94s/it] 58%|█████▊ | 8693/15000 [40:14:35<26:03:35, 14.87s/it] 58%|█████▊ | 8694/15000 [40:14:49<25:54:51, 14.79s/it] 58%|█████▊ | 8695/15000 [40:15:27<37:42:37, 21.53s/it] 58%|█████▊ | 8696/15000 [40:15:41<34:10:23, 19.52s/it] 58%|█████▊ | 8697/15000 [40:15:56<31:37:36, 18.06s/it] 58%|█████▊ | 8698/15000 [40:16:11<29:51:09, 17.05s/it] 58%|█████▊ | 8699/15000 [40:16:25<28:38:30, 16.36s/it] 58%|█████▊ | 8700/15000 [40:16:40<27:43:55, 15.85s/it] {'loss': 0.8259, 'learning_rate': 7.91032436968725e-05, 'epoch': 1.63}
40:12:52<30:00:49, 17.11s/it] 58%|█████▊ | 8687/15000 [40:13:07<28:43:40, 16.38s/it] 58%|█████▊ | 8688/15000 [40:13:21<27:52:47, 15.90s/it] 58%|█████▊ | 8689/15000 [40:13:36<27:13:17, 15.53s/it] 58%|█████▊ | 8690/15000 [40:13:51<26:51:24, 15.32s/it] 58%|█████▊ | 8691/15000 [40:14:05<26:27:25, 15.10s/it] 58%|█████▊ | 8692/15000 [40:14:20<26:12:52, 14.96s/it] 58%|█████▊ | 8693/15000 [40:14:35<26:02:54, 14.87s/it] 58%|█████▊ | 8694/15000 [40:14:49<25:54:51, 14.79s/it] 58%|█████▊ | 8695/15000 [40:15:27<37:42:14, 21.53s/it] 58%|█████▊ | 8696/15000 [40:15:41<34:09:12, 19.50s/it] 58%|█████▊ | 8697/15000 [40:15:56<31:36:33, 18.05s/it] 58%|█████▊ | 8698/15000 [40:16:11<29:48:09, 17.02s/it] 58%|█████▊ | 8699/15000 [40:16:25<28:35:30, 16.34s/it] 58%|█████▊ | 8700/15000 [40:16:40<27:48:01, 15.89s/it] {'loss': 0.8259, 'learning_rate': 7.91032436968725e-05, 'epoch': 1.63}
15:41<34:09:18, 19.50s/it] 58%|█████▊ | 8697/15000 [40:15:56<31:35:02, 18.04s/it] 58%|█████▊ | 8698/15000 [40:16:11<29:50:32, 17.05s/it] 58%|█████▊ | 8699/15000 [40:16:25<28:35:47, 16.34s/it] 58%|█████▊ | 8700/15000 [40:16:40<27:45:03, 15.86s/it] 58%|█████▊ | 8700/15000 [40:16:40<27:45:03, 15.86s/it] 58%|█████▊ | 8701/15000 [40:16:55<27:18:04, 15.60s/it] 58%|█████▊ | 8702/15000 [40:17:10<26:49:57, 15.34s/it] 58%|█████▊ | 8703/15000 [40:17:24<26:28:07, 15.13s/it] 58%|█████▊ | 8704/15000 [40:17:39<26:09:50, 14.96s/it] 58%|█████▊ | 8705/15000 [40:17:54<26:03:01, 14.90s/it] 58%|█████▊ | 8706/15000 [40:18:31<37:50:14, 21.64s/it] 58%|█████▊ | 8707/15000 [40:18:46<34:09:54, 19.54s/it] 58%|█████▊ | 8708/15000 [40:19:00<31:35:48, 18.08s/it] 58%|███ 58%|█████▊ | 8700/15000 [40:16:40<27:48:01, 15.89s/it] 58%|█████▊ | 8701/15000 [40:16:55<27:16:33, 15.59s/it] 58%|█████▊ | 8702/15000 [40:17:10<26:49:39, 15.33s/it] 58%|█████▊ | 8703/15000 [40:17:25<26:30:35, 15.16s/it] 58%|█████▊ | 8704/15000 [40:17:39<26:11:12, 14.97s/it] 58%|█████▊ | 8705/15000 [40:17:54<26:01:47, 14.89s/it] 58%|█████▊ | 8706/15000 [40:18:31<37:45:45, 21.60s/it] 58%|█████▊ | 8707/15000 [40:18:46<34:12:11, 19.57s/it] 58%|█████▊ | 8708/15000 [40:19:00<31:33:53, 18.06s/it] 58%|█████▊ | 8709/15000 [40:19:15<29:47:18, 17.05s/it] 58%|█████▊ | 8710/15000 [40:19:30<28:34:54, 16.36s/it] 58%|█████▊ | 8711/15000 [40:19:45<27:41:37, 15.85s/it] 58%|█████▊ | 8712/15000 [40:19:59<27:10:35, 15.56s/it] 58%|█████▊ | 8713/15000 [ 58%|█████▊ | 8700/15000 [40:16:40<27:43:55, 15.85s/it] 58%|█████▊ | 8701/15000 [40:16:55<27:15:45, 15.58s/it] 58%|█████▊ | 8702/15000 [40:17:10<26:53:12, 15.37s/it] 58%|█████▊ | 8703/15000 [40:17:25<26:27:32, 15.13s/it] 58%|█████▊ | 8704/15000 [40:17:39<26:07:52, 14.94s/it] 58%|█████▊ | 8705/15000 [40:17:54<26:00:47, 14.88s/it] 58%|█████▊ | 8706/15000 [40:18:31<37:46:21, 21.60s/it] 58%|█████▊ | 8707/15000 [40:18:46<34:12:37, 19.57s/it] 58%|█████▊ | 8708/15000 [40:19:00<31:35:26, 18.07s/it] 58%|█████▊ | 8709/15000 [40:19:15<29:50:48, 17.08s/it] 58%|█████▊ | 8710/15000 [40:19:30<28:34:26, 16.35s/it] 58%|█████▊ | 8711/15000 [40:19:45<27:42:57, 15.87s/it] 58%|█████▊ | 8712/15000 [40:19:59<27:07:49, 15.53s/it] 58%|█████▊ | 8713/15000 [██▊ | 8709/15000 [40:19:15<29:46:43, 17.04s/it] 58%|█████▊ | 8710/15000 [40:19:30<28:32:21, 16.33s/it] 58%|█████▊ | 8711/15000 [40:19:44<27:42:32, 15.86s/it] 58%|█████▊ | 8712/15000 [40:19:59<27:10:01, 15.55s/it] 58%|█████▊ | 8713/15000 [40:20:14<26:44:34, 15.31s/it] 58%|█████▊ | 8714/15000 [40:20:29<26:26:40, 15.14s/it] 58%|█████▊ | 8715/15000 [40:20:43<26:10:05, 14.99s/it] 58%|█████▊ | 8716/15000 [40:20:58<26:02:31, 14.92s/it] 58%|█████▊ | 8717/15000 [40:21:36<37:48:38, 21.66s/it] 58%|█████▊ | 8718/15000 [40:21:50<34:08:50, 19.57s/it] 58%|█████▊ | 8719/15000 [40:22:05<31:32:50, 18.08s/it] 58%|█████▊ | 8720/15000 [40:22:20<29:46:13, 17.07s/it] 58%|█████▊ | 8721/15000 [40:22:34<28:29:41, 16.34s/it] 58%|█████▊ | 8722/15000 [40:22:49<27:39:23, 15.86s/it] 58%|█████▊ | 8723/15000 [40
{'loss': 0.8249, 'learning_rate': 7.699677733393826e-05, 'epoch': 1.65}
{'loss': 0.8249, 'learning_rate': 7.699677733393826e-05, 'epoch': 1.65}
:46:04, 14.95s/it] 59%|█████▊ | 8796/15000 [40:43:43<37:21:44, 21.68s/it] 59%|█████▊ | 8797/15000 [40:43:58<33:46:41, 19.60s/it] 59%|█████▊ | 8798/15000 [40:44:13<31:18:59, 18.18s/it] 59%|█████▊ | 8799/15000 [40:44:27<29:33:18, 17.16s/it] 59%|█████▊ | 8800/15000 [40:44:42<28:26:45, 16.52s/it] 59%|█████▊ | 8800/15000 [40:44:43<28:26:45, 16.52s/it] 59%|█████▊ | 8801/15000 [40:44:57<27:35:10, 16.02s/it] 59%|█████▊ | 8802/15000 [40:45:12<26:52:44, 15.61s/it] 59%|█████▊ | 8803/15000 [40:45:27<26:21:14, 15.31s/it] 59%|█████▊ | 8804/15000 [40:45:41<26:00:41, 15.11s/it] 59%|█████▊ | 8805/15000 [40:45:56<25:48:53, 15.00s/it] 59%|█████▊ | 8806/15000 [40:46:11<25:39:28, 14.91s/it] 59%|█████▊ | 8807/15000 [40:46:48<37:14:58, 21.65s/it] 59%|█████<E29688><E29688>████▊ | 8800/15000 [40:44:42<28:23:49, 16.49s/it] 59%|█████▊ | 8800/15000 [40:44:43<28:23:49, 16.49s/it] 59%|█████▊ | 8801/15000 [40:44:57<27:33:37, 16.01s/it] 59%|█████▊ | 8802/15000 [40:45:12<26:51:23, 15.60s/it] 59%|█████▊ | 8803/15000 [40:45:27<26:20:21, 15.30s/it] 59%|█████▊ | 8804/15000 [40:45:41<26:02:26, 15.13s/it] 59%|█████▊ | 8805/15000 [40:45:56<25:47:14, 14.99s/it] 59%|█████▊ | 8806/15000 [40:46:11<25:41:01, 14.93s/it] 59%|█████▊ | 8807/15000 [40:46:48<37:15:02, 21.65s/it] 59%|█████▊ | 8808/15000 [40:47:03<33:38:01, 19.55s/it] 59%|█████▊ | 8809/15000 [40:47:18<31:13:38, 18.16s/it] 59%|█████▊ | 8810/15000 [40:47:32<29:27:08, 17.13s/it] 59%|█████▊ | 8811/15000 [40:47:47<28:08:36, 16.37s/it] 59%|█████▊ | 8812/15000 [40:48:02████▊ | 8800/15000 [40:44:42<28:24:25, 16.49s/it] 59%|█████▊ | 8800/15000 [40:44:43<28:24:25, 16.49s/it] 59%|█████▊ | 8801/15000 [40:44:57<27:33:05, 16.00s/it] 59%|█████▊ | 8802/15000 [40:45:12<26:51:50, 15.60s/it] 59%|█████▊ | 8803/15000 [40:45:27<26:23:27, 15.33s/it] 59%|█████▊ | 8804/15000 [40:45:41<26:00:32, 15.11s/it] 59%|█████▊ | 8805/15000 [40:45:56<25:47:11, 14.98s/it] 59%|█████▊ | 8806/15000 [40:46:11<25:39:05, 14.91s/it] 59%|█████▊ | 8807/15000 [40:46:48<37:16:25, 21.67s/it] 59%|█████▊ | 8808/15000 [40:47:03<33:40:11, 19.58s/it] 59%|█████▊ | 8809/15000 [40:47:18<31:14:48, 18.17s/it] 59%|█████▊ | 8810/15000 [40:47:32<29:25:20, 17.11s/it] 59%|█████▊ | 8811/15000 [40:47:47<28:09:09, 16.38s/it] 59%|█████▊ | 8812/15000 [40:48:02<30> | 8808/15000 [40:47:03<33:42:27, 19.60s/it] 59%|█████▊ | 8809/15000 [40:47:18<31:12:01, 18.14s/it] 59%|█████▊ | 8810/15000 [40:47:32<29:24:13, 17.10s/it] 59%|█████▊ | 8811/15000 [40:47:47<28:10:33, 16.39s/it] 59%|█████▊ | 8812/15000 [40:48:02<27:16:29, 15.87s/it] 59%|█████▉ | 8813/15000 [40:48:16<26:42:21, 15.54s/it] 59%|█████▉ | 8814/15000 [40:48:31<26:13:27, 15.26s/it] 59%|█████▉ | 8815/15000 [40:48:46<25:57:18, 15.11s/it] 59%|█████▉ | 8816/15000 [40:49:00<25:40:37, 14.95s/it] 59%|█████▉ | 8817/15000 [40:49:15<25:34:31, 14.89s/it] 59%|█████▉ | 8818/15000 [40:49:30<25:25:01, 14.80s/it] 59%|█████▉ | 8819/15000 [40:50:07<36:59:09, 21.54s/it] 59%|█████▉ | 8820/15000 [40:50:22<33:26:29, 19.48s/it] 59%|█████▉ | 8821/15000 [40:50:36<30:56:06, 18.02s/it] 59%|█████▉ | 8822/15000 [40:50:51<2
{'loss': 0.8225, 'learning_rate': 7.490103469356513e-05, 'epoch': 1.67}
{'loss': 0.8225, 'learning_rate': 7.490103469356513e-05, 'epoch': 1.67}
15.15s/it] 59%|█████▉ | 8895/15000 [41:11:02<25:29:49, 15.04s/it] 59%|█████▉ | 8896/15000 [41:11:17<25:23:05, 14.97s/it] 59%|█████▉ | 8897/15000 [41:11:32<25:13:21, 14.88s/it] 59%|█████▉ | 8898/15000 [41:12:10<37:15:01, 21.98s/it] 59%|█████▉ | 8899/15000 [41:12:25<33:32:44, 19.79s/it] 59%|█████▉ | 8900/15000 [41:12:40<30:55:45, 18.25s/it] 59%|█████▉ | 8900/15000 [41:12:40<30:55:45, 18.25s/it] 59%|█████▉ | 8901/15000 [41:12:54<29:15:09, 17.27s/it] 59%|█████▉ | 8902/15000 [41:13:09<27:55:01, 16.48s/it] 59%|█████▉ | 8903/15000 [41:13:24<27:00:43, 15.95s/it] 59%|█████▉ | 8904/15000 [41:13:39<26:23:03, 15.58s/it] 59%|█████▉ | 8905/15000 [41:13:53<25:56:29, 15.32s/it] 59%|█████▉ | 8906/15000 [41:14:08<25:37:08, 15.13s/it] 59%|█████▉ | 8<>█▉ | 8899/15000 [41:12:25<33:35:51, 19.82s/it] 59%|█████▉ | 8900/15000 [41:12:40<30:54:48, 18.24s/it] 59%|█████▉ | 8900/15000 [41:12:40<30:54:48, 18.24s/it] 59%|█████▉ | 8901/15000 [41:12:54<29:14:13, 17.26s/it] 59%|█████▉ | 8902/15000 [41:13:09<27:54:47, 16.48s/it] 59%|█████▉ | 8903/15000 [41:13:24<27:00:46, 15.95s/it] 59%|█████▉ | 8904/15000 [41:13:39<26:24:27, 15.60s/it] 59%|█████▉ | 8905/15000 [41:13:53<25:55:21, 15.31s/it] 59%|█████▉ | 8906/15000 [41:14:08<25:39:46, 15.16s/it] 59%|█████▉ | 8907/15000 [41:14:23<25:23:34, 15.00s/it] 59%|█████▉ | 8908/15000 [41:14:37<25:12:52, 14.90s/it] 59%|█████▉ | 8909/15000 [41:15:16<37:10:32, 21.97s/it] 59%|█████▉ | 8910/15000 [41:15:31<33:31:23, 19.82s/it] 59%|█████▉ | 8911/15000 [41:15:46<31:09:4<>█▉ | 8899/15000 [41:12:25<33:32:43, 19.79s/it] 59%|█████▉ | 8900/15000 [41:12:40<30:53:36, 18.23s/it] 59%|█████▉ | 8900/15000 [41:12:40<30:53:36, 18.23s/it] 59%|█████▉ | 8901/15000 [41:12:54<29:11:20, 17.23s/it] 59%|█████▉ | 8902/15000 [41:13:09<27:57:43, 16.51s/it] 59%|█████▉ | 8903/15000 [41:13:24<27:01:20, 15.96s/it] 59%|█████▉ | 8904/15000 [41:13:39<26:24:05, 15.59s/it] 59%|█████▉ | 8905/15000 [41:13:53<25:56:39, 15.32s/it] 59%|█████▉ | 8906/15000 [41:14:08<25:36:35, 15.13s/it] 59%|█████▉ | 8907/15000 [41:14:23<25:23:49, 15.01s/it] 59%|█████▉ | 8908/15000 [41:14:37<25:15:33, 14.93s/it] 59%|█████▉ | 8909/15000 [41:15:16<37:09:46, 21.96s/it] 59%|█████▉ | 8910/15000 [41:15:31<33:30:05, 19.80s/it] 59%|█████▉ | 8911/15000 [41:15:46<31:11:4907/15000 [41:14:23<25:24:17, 15.01s/it] 59%|█████▉ | 8908/15000 [41:14:37<25:14:41, 14.92s/it] 59%|█████▉ | 8909/15000 [41:15:16<37:08:11, 21.95s/it] 59%|█████▉ | 8910/15000 [41:15:30<33:27:36, 19.78s/it] 59%|█████▉ | 8911/15000 [41:15:46<31:09:47, 18.42s/it] 59%|█████▉ | 8912/15000 [41:16:00<29:13:52, 17.29s/it] 59%|█████▉ | 8913/15000 [41:16:15<27:53:15, 16.49s/it] 59%|█████▉ | 8914/15000 [41:16:30<26:59:09, 15.96s/it] 59%|█████▉ | 8915/15000 [41:16:44<26:20:58, 15.59s/it] 59%|█████▉ | 8916/15000 [41:16:59<25:54:45, 15.33s/it] 59%|█████▉ | 8917/15000 [41:17:14<25:34:37, 15.14s/it] 59%|█████▉ | 8918/15000 [41:17:28<25:19:15, 14.99s/it] 59%|█████▉ | 8919/15000 [41:17:43<25:13:46, 14.94s/it] 59%|█████▉ | 8920/15000 [41:18:21<36:39:43, 21.71s/it] 59%|█████▉ | 8921/15000 [41:18:36<33:06:31,
{'loss': 0.8216, 'learning_rate': 7.281699277636572e-05, 'epoch': 1.68}
{'loss': 0.8216, 'learning_rate': 7.281699277636572e-05, 'epoch': 1.68}
t] 60%|█████▉ | 8994/15000 [41:38:46<25:59:36, 15.58s/it] 60%|█████▉ | 8995/15000 [41:39:01<25:30:20, 15.29s/it] 60%|█████▉ | 8996/15000 [41:39:16<25:12:41, 15.12s/it] 60%|█████▉ | 8997/15000 [41:39:30<25:00:35, 15.00s/it] 60%|█████▉ | 8998/15000 [41:39:45<24:52:36, 14.92s/it] 60%|█████▉ | 8999/15000 [41:40:25<37:18:15, 22.38s/it] 60%|██████ | 9000/15000 [41:40:40<33:28:38, 20.09s/it] 60%|██████ | 9000/15000 [41:40:40<33:28:38, 20.09s/it] 60%|██████ | 9001/15000 [41:40:54<30:52:44, 18.53s/it] 60%|██████ | 9002/15000 [41:41:09<29:01:03, 17.42s/it] 60%|██████ | 9003/15000 [41:41:24<27:40:19, 16.61s/it] 60%|██████ | 9004/15000 [41:41:39<26:41:29, 16.03s/it] 60%|██████ | 9005/15000 [41:41:53<26:00:41, 15.62s/it] 60%|██████ | 9006/1500 | 8998/15000 [41:39:45<24:51:15, 14.91s/it] 60%|█████▉ | 8999/15000 [41:40:25<37:18:14, 22.38s/it] 60%|██████ | 9000/15000 [41:40:40<33:31:06, 20.11s/it] 60%|██████ | 9000/15000 [41:40:40<33:31:06, 20.11s/it] 60%|██████ | 9001/15000 [41:40:55<30:55:06, 18.55s/it] 60%|██████ | 9002/15000 [41:41:09<28:59:18, 17.40s/it] 60%|██████ | 9003/15000 [41:41:24<27:38:16, 16.59s/it] 60%|██████ | 9004/15000 [41:41:39<26:42:44, 16.04s/it] 60%|██████ | 9005/15000 [41:41:54<26:02:33, 15.64s/it] 60%|██████ | 9006/15000 [41:42:08<25:30:02, 15.32s/it] 60%|██████ | 9007/15000 [41:42:23<25:09:05, 15.11s/it] 60%|██████ | 9008/15000 [41:42:37<24:52:41, 14.95s/it] 60%|██████ | 9009/15000 [41:42:52<24:45:37, 14.88s/it] 60%|██████ | 9010/15000 [41:43:31<36:39:33, 22.03 | 8998/15000 [41:39:45<24:52:32, 14.92s/it] 60%|█████▉ | 8999/15000 [41:40:25<37:17:05, 22.37s/it] 60%|██████ | 9000/15000 [41:40:40<33:27:24, 20.07s/it] 60%|██████ | 9000/15000 [41:40:40<33:27:24, 20.07s/it] 60%|██████ | 9001/15000 [41:40:55<30:54:49, 18.55s/it] 60%|██████ | 9002/15000 [41:41:09<29:02:13, 17.43s/it] 60%|██████ | 9003/15000 [41:41:24<27:38:41, 16.60s/it] 60%|██████ | 9004/15000 [41:41:39<26:42:08, 16.03s/it] 60%|██████ | 9005/15000 [41:41:53<25:58:56, 15.60s/it] 60%|██████ | 9006/15000 [41:42:08<25:31:43, 15.33s/it] 60%|██████ | 9007/15000 [41:42:23<25:12:00, 15.14s/it] 60%|██████ | 9008/15000 [41:42:37<24:52:19, 14.94s/it] 60%|██████ | 9009/15000 [41:42:52<24:48:47, 14.91s/it] 60%|██████ | 9010/15000 [41:43:31<36:39:22, 22.030 [41:42:08<25:32:37, 15.34s/it] 60%|██████ | 9007/15000 [41:42:23<25:10:35, 15.12s/it] 60%|██████ | 9008/15000 [41:42:37<24:58:04, 15.00s/it] 60%|██████ | 9009/15000 [41:42:52<24:46:16, 14.89s/it] 60%|██████ | 9010/15000 [41:43:31<36:39:44, 22.03s/it] 60%|██████ | 9011/15000 [41:43:45<32:59:18, 19.83s/it] 60%|██████ | 9012/15000 [41:44:00<30:25:16, 18.29s/it] 60%|██████ | 9013/15000 [41:44:15<28:37:37, 17.21s/it] 60%|██████ | 9014/15000 [41:44:30<27:26:25, 16.50s/it] 60%|██████ | 9015/15000 [41:44:44<26:32:59, 15.97s/it] 60%|██████ | 9016/15000 [41:44:59<25:58:50, 15.63s/it] 60%|██████ | 9017/15000 [41:45:14<25:34:38, 15.39s/it] 60%|██████ | 9018/15000 [41:45:29<25:14:30, 15.19s/it] 60%|██████ | 9019/15000 [41:45:43<24:56:32, 15.01s/it] 60%|██████ | 9020/15000 [41:45:58<24:42:18, 14.87s/
{'loss': 0.8224, 'learning_rate': 7.07456231282686e-05, 'epoch': 1.7}
{'loss': 0.8224, 'learning_rate': 7.07456231282686e-05, 'epoch': 1.7}
██████ | 9093/15000 [42:06:35<26:53:05, 16.38s/it] 61%|██████ | 9094/15000 [42:06:50<25:59:24, 15.84s/it] 61%|██████ | 9095/15000 [42:07:05<25:27:28, 15.52s/it] 61%|██████ | 9096/15000 [42:07:19<25:03:43, 15.28s/it] 61%|██████ | 9097/15000 [42:07:34<24:47:00, 15.11s/it] 61%|██████ | 9098/15000 [42:07:49<24:38:03, 15.03s/it] 61%|██████ | 9099/15000 [42:08:04<24:29:56, 14.95s/it] 61%|██████ | 9100/15000 [42:08:18<24:25:55, 14.91s/it] 61%|██████ | 9100/15000 [42:08:19<24:25:55, 14.91s/it] 61%|██████ | 9101/15000 [42:08:56<35:40:37, 21.77s/it] 61%|██████ | 9102/15000 [42:09:11<32:09:36, 19.63s/it] 61%|██████ | 9103/15000 [42:09:26<29:46:18, 18.18s/it] 61%|██████ | 9104/15000 [42:09:40<28:04:38, 17.14s/it] 61%|██████ | 9105/15000 [42:097/15000 [42:07:34<24:46:45, 15.11s/it] 61%|██████ | 9098/15000 [42:07:49<24:34:59, 14.99s/it] 61%|██████ | 9099/15000 [42:08:04<24:34:57, 15.00s/it] 61%|██████ | 9100/15000 [42:08:18<24:25:58, 14.91s/it] 61%|██████ | 9100/15000 [42:08:19<24:25:58, 14.91s/it] 61%|██████ | 9101/15000 [42:08:56<35:38:18, 21.75s/it] 61%|██████ | 9102/15000 [42:09:11<32:12:31, 19.66s/it] 61%|██████ | 9103/15000 [42:09:26<29:47:04, 18.18s/it] 61%|██████ | 9104/15000 [42:09:40<28:06:07, 17.16s/it] 61%|██████ | 9105/15000 [42:09:55<26:54:32, 16.43s/it] 61%|██████ | 9106/15000 [42:10:10<26:04:59, 15.93s/it] 61%|██████ | 9107/15000 [42:10:25<25:31:12, 15.59s/it] 61%|██████ | 9108/15000 [42:10:40<25:11:08, 15.39s/it] 61%|██████ | 9109/15000 [42:10:55<24:56:57, 15.25s/it] 67/15000 [42:07:34<24:48:49, 15.13s/it] 61%|██████ | 9098/15000 [42:07:49<24:36:03, 15.01s/it] 61%|██████ | 9099/15000 [42:08:04<24:34:06, 14.99s/it] 61%|██████ | 9100/15000 [42:08:18<24:26:34, 14.91s/it] 61%|██████ | 9100/15000 [42:08:19<24:26:34, 14.91s/it] 61%|██████ | 9101/15000 [42:08:56<35:35:15, 21.72s/it] 61%|██████ | 9102/15000 [42:09:11<32:11:03, 19.64s/it] 61%|██████ | 9103/15000 [42:09:26<29:44:22, 18.16s/it] 61%|██████ | 9104/15000 [42:09:40<28:08:08, 17.18s/it] 61%|██████ | 9105/15000 [42:09:55<26:56:40, 16.45s/it] 61%|██████ | 9106/15000 [42:10:10<26:07:57, 15.96s/it] 61%|██████ | 9107/15000 [42:10:25<25:34:01, 15.62s/it] 61%|██████ | 9108/15000 [42:10:40<25:10:09, 15.38s/it] 61%|██████ | 9109/15000 [42:10:55<24:55:38, 15.23s/it] 6:55<26:55:20, 16.44s/it] 61%|██████ | 9106/15000 [42:10:10<26:05:03, 15.93s/it] 61%|██████ | 9107/15000 [42:10:25<25:32:21, 15.60s/it] 61%|██████ | 9108/15000 [42:10:40<25:11:15, 15.39s/it] 61%|██████ | 9109/15000 [42:10:55<24:57:00, 15.25s/it] 61%|██████ | 9110/15000 [42:11:10<24:50:50, 15.19s/it] 61%|██████ | 9111/15000 [42:11:24<24:40:21, 15.08s/it] 61%|██████ | 9112/15000 [42:12:02<35:48:55, 21.90s/it] 61%|██████ | 9113/15000 [42:12:17<32:16:08, 19.73s/it] 61%|██████ | 9114/15000 [42:12:32<29:48:02, 18.23s/it] 61%|██████ | 9115/15000 [42:12:46<28:09:52, 17.23s/it] 61%|██████ | 9116/15000 [42:13:01<26:54:37, 16.46s/it] 61%|██████ | 9117/15000 [42:13:16<26:09:40, 16.01s/it] 61%|██████ | 9118/15000 [42:13:31<25:30:23, 15.61s/it] 61%|██████ | 9119/15000 [42:13:46<25:11:07, 15.42s/it] 61%
{'loss': 0.8218, 'learning_rate': 6.868789138759976e-05, 'epoch': 1.72}
{'loss': 0.8218, 'learning_rate': 6.868789138759976e-05, 'epoch': 1.72}
██████▏ | 9192/15000 [42:34:32<32:18:20, 20.02s/it] 61%|██████▏ | 9193/15000 [42:34:47<29:49:57, 18.49s/it] 61%|██████▏ | 9194/15000 [42:35:02<28:09:11, 17.46s/it] 61%|██████▏ | 9195/15000 [42:35:17<26:54:45, 16.69s/it] 61%|██████▏ | 9196/15000 [42:35:31<26:01:10, 16.14s/it] 61%|██████▏ | 9197/15000 [42:35:46<25:18:52, 15.70s/it] 61%|██████▏ | 9198/15000 [42:36:01<24:47:48, 15.39s/it] 61%|██████▏ | 9199/15000 [42:36:15<24:26:12, 15.16s/it] 61%|██████▏ | 9200/15000 [42:36:30<24:18:57, 15.09s/it] 61%|██████▏ | 9200/15000 [42:36:31<24:18:57, 15.09s/it] 61%|██████▏ | 9201/15000 [42:36:45<24:19:24, 15.10s/it] 61%|██████▏ | 9202/15000 [42:37:23<35:12:59, 21.87s/it] 61%|██████▏ | 9203/15000 [42:37:38<31:42:01, 19.69s/it] 61%|█████<E29688><E29688> | 9196/15000 [42:35:31<25:58:45, 16.11s/it] 61%|██████▏ | 9197/15000 [42:35:46<25:20:19, 15.72s/it] 61%|██████▏ | 9198/15000 [42:36:01<24:47:03, 15.38s/it] 61%|██████▏ | 9199/15000 [42:36:15<24:27:28, 15.18s/it] 61%|██████▏ | 9200/15000 [42:36:30<24:17:59, 15.08s/it] 61%|██████▏ | 9200/15000 [42:36:31<24:17:59, 15.08s/it] 61%|██████▏ | 9201/15000 [42:36:45<24:19:29, 15.10s/it] 61%|██████▏ | 9202/15000 [42:37:23<35:11:37, 21.85s/it] 61%|██████▏ | 9203/15000 [42:37:38<31:45:53, 19.73s/it] 61%|██████▏ | 9204/15000 [42:37:53<29:20:10, 18.22s/it] 61%|██████▏ | 9205/15000 [42:38:08<27:46:15, 17.25s/it] 61%|██████▏ | 9206/15000 [42:38:22<26:32:01, 16.49s/it] 61%|██████▏ | 9207/15000 [42:38:37<25:46:10, 16.01s/it] 61%|██████▏ | 9208/150<35><30> | 9196/15000 [42:35:31<26:00:35, 16.13s/it] 61%|██████▏ | 9197/15000 [42:35:46<25:17:31, 15.69s/it] 61%|██████▏ | 9198/15000 [42:36:01<24:46:03, 15.37s/it] 61%|██████▏ | 9199/15000 [42:36:15<24:28:35, 15.19s/it] 61%|██████▏ | 9200/15000 [42:36:30<24:20:25, 15.11s/it] 61%|██████▏ | 9200/15000 [42:36:31<24:20:25, 15.11s/it] 61%|██████▏ | 9201/15000 [42:36:45<24:16:40, 15.07s/it] 61%|██████▏ | 9202/15000 [42:37:23<35:18:10, 21.92s/it] 61%|██████▏ | 9203/15000 [42:37:38<31:42:53, 19.70s/it] 61%|██████▏ | 9204/15000 [42:37:53<29:20:59, 18.23s/it] 61%|██████▏ | 9205/15000 [42:38:07<27:43:55, 17.23s/it] 61%|██████▏ | 9206/15000 [42:38:22<26:36:26, 16.53s/it] 61%|██████▏ | 9207/15000 [42:38:37<25:46:16, 16.02s/it] 61%|██████▏ | 9208/150█▏ | 9204/15000 [42:37:52<29:20:44, 18.23s/it] 61%|██████▏ | 9205/15000 [42:38:07<27:45:51, 17.25s/it] 61%|██████▏ | 9206/15000 [42:38:22<26:37:30, 16.54s/it] 61%|██████▏ | 9207/15000 [42:38:37<25:44:44, 16.00s/it] 61%|██████▏ | 9208/15000 [42:38:52<25:07:51, 15.62s/it] 61%|██████▏ | 9209/15000 [42:39:06<24:40:23, 15.34s/it] 61%|██████▏ | 9210/15000 [42:39:21<24:20:19, 15.13s/it] 61%|██████▏ | 9211/15000 [42:39:36<24:04:46, 14.97s/it] 61%|██████▏ | 9212/15000 [42:39:50<23:53:38, 14.86s/it] 61%|██████▏ | 9213/15000 [42:40:05<23:50:21, 14.83s/it] 61%|██████▏ | 9214/15000 [42:40:42<34:41:21, 21.58s/it] 61%|██████▏ | 9215/15000 [42:40:57<31:25:45, 19.56s/it] 61%|██████▏ | 9216/15000 [42:41:12<29:03:08, 18.08s/it] 61%|██████▏ | 9217/15000 [42:41:27<27:25:19, 17.07s/it] 61%|█████<E29688>
{'loss': 0.8247, 'learning_rate': 6.664475683491796e-05, 'epoch': 1.74}
288/15000 [43:01:12<24:26:22, 15.40s/it] 62%|██████▏ | 9289/15000 [43:01:27<24:05:53, 15.19s/it] 62%|██████▏ | 9290/15000 [43:01:42<23:52:47, 15.06s/it] 62%|██████▏ | 9291/15000 [43:01:56<23:43:23, 14.96s/it] 62%|██████▏ | 9292/15000 [43:02:35<34:53:49, 22.01s/it] 62%|██████▏ | 9293/15000 [43:02:50<31:30:16, 19.87s/it] 62%|██████▏ | 9294/15000 [43:03:05<29:10:38, 18.41s/it] 62%|██████▏ | 9295/15000 [43:03:19<27:26:11, 17.31s/it] 62%|██████▏ | 9296/15000 [43:03:34<26:11:07, 16.53s/it] 62%|██████▏ | 9297/15000 [43:03:49<25:20:39, 16.00s/it] 62%|██████▏ | 9298/15000 [43:04:03<24:41:56, 15.59s/it] 62%|██████▏ | 9299/15000 [43:04:19<24:25:02, 15.42s/it] 62%|██████▏ | 9300/15000 [43:04:33<24:07:18, 15.23s/it] 62%|██████▏ | 9300/15000 [43:0{'loss': 0.8247, 'learning_rate': 6.664475683491796e-05, 'epoch': 1.74}
<34:52:41, 22.00s/it] 62%|██████▏ | 9293/15000 [43:02:50<31:32:14, 19.89s/it] 62%|██████▏ | 9294/15000 [43:03:05<29:06:57, 18.37s/it] 62%|██████▏ | 9295/15000 [43:03:20<27:29:19, 17.35s/it] 62%|██████▏ | 9296/15000 [43:03:34<26:14:21, 16.56s/it] 62%|██████▏ | 9297/15000 [43:03:49<25:19:56, 15.99s/it] 62%|██████▏ | 9298/15000 [43:04:04<24:42:39, 15.60s/it] 62%|██████▏ | 9299/15000 [43:04:19<24:24:04, 15.41s/it] 62%|██████▏ | 9300/15000 [43:04:33<24:06:44, 15.23s/it] 62%|██████▏ | 9300/15000 [43:04:34<24:06:44, 15.23s/it] 62%|██████▏ | 9301/15000 [43:04:48<23:58:53, 15.15s/it] 62%|██████▏ | 9302/15000 [43:05:03<23:54:10, 15.10s/it] 62%|██████▏ | 9303/15000 [43:05:18<23:45:40, 15.02s/it] 62%|██████▏ | 9304/15000 [43:05:57<35:07:22, 22.2<34:55:22, 22.03s/it] 62%|██████▏ | 9293/15000 [43:02:50<31:31:34, 19.89s/it] 62%|██████▏ | 9294/15000 [43:03:05<29:07:52, 18.38s/it] 62%|██████▏ | 9295/15000 [43:03:19<27:25:55, 17.31s/it] 62%|██████▏ | 9296/15000 [43:03:34<26:13:44, 16.55s/it] 62%|██████▏ | 9297/15000 [43:03:49<25:22:57, 16.02s/it] 62%|██████▏ | 9298/15000 [43:04:04<24:46:33, 15.64s/it] 62%|██████▏ | 9299/15000 [43:04:19<24:22:20, 15.39s/it] 62%|██████▏ | 9300/15000 [43:04:33<24:04:22, 15.20s/it] 62%|██████▏ | 9300/15000 [43:04:34<24:04:22, 15.20s/it] 62%|██████▏ | 9301/15000 [43:04:48<23:57:40, 15.14s/it] 62%|██████▏ | 9302/15000 [43:05:03<23:54:32, 15.11s/it] 62%|██████▏ | 9303/15000 [43:05:18<23:45:41, 15.02s/it] 62%|██████▏ | 9304/15000 [43:05:57<35:08:16, 22.24:34<24:07:18, 15.23s/it] 62%|██████▏ | 9301/15000 [43:04:48<23:59:27, 15.15s/it] 62%|██████▏ | 9302/15000 [43:05:03<23:52:49, 15.09s/it] 62%|██████▏ | 9303/15000 [43:05:18<23:48:41, 15.05s/it] 62%|██████▏ | 9304/15000 [43:05:57<35:08:49, 22.21s/it] 62%|██████▏ | 9305/15000 [43:06:12<31:38:07, 20.00s/it] 62%|██████▏ | 9306/15000 [43:06:27<29:10:19, 18.44s/it] 62%|██████▏ | 9307/15000 [43:06:42<27:31:01, 17.40s/it] 62%|██████▏ | 9308/15000 [43:06:57<26:20:47, 16.66s/it] 62%|██████▏ | 9309/15000 [43:07:11<25:25:33, 16.08s/it] 62%|██████▏ | 9310/15000 [43:07:26<24:45:20, 15.66s/it] 62%|██████▏ | 9311/15000 [43:07:41<24:19:59, 15.40s/it] 62%|██████▏ | 9312/15000 [43:07:56<24:03:56, 15.23s/it] 62%|██████▏ | 9313/15000 [43:08:11<23:58:34, 15.18s/it] 62%|██████▏ | 9314/15000 [43:08:0s/it] 62%|██████▏ | 9305/15000 [43:06:12<31:34:01, 19.95s/it] 62%|██████▏ | 9306/15000 [43:06:27<29:15:19, 18.50s/it] 62%|██████▏ | 9307/15000 [43:06:42<27:31:36, 17.41s/it] 62%|██████▏ | 9308/15000 [43:06:57<26:22:46, 16.68s/it] 62%|██████▏ | 9309/15000 [43:07:11<25:24:23, 16.07s/it] 62%|██████▏ | 9310/15000 [43:07:26<24:40:34, 15.61s/it] 62%|██████▏ | 9311/15000 [43:07:41<24:24:57, 15.45s/it] 62%|██████▏ | 9312/15000 [43:07:56<24:07:00, 15.26s/it] 62%|██████▏ | 9313/15000 [43:08:11<23:58:21, 15.18s/it] 62%|██████▏ | 9314/15000 [43:08:26<23:50:55, 15.10s/it] 62%|██████▏ | 9315/15000 [43:09:05<35:02:17, 22.19s/it] 62%|██████▏ | 9316/15000 [43:09:19<31:30:44, 19.96s/it] 62%|██████▏ | 9317/15000 [43:09:34<28:55:16, 18.32s/it] 62%|██████▏ | 9318/15000 [43:09:49<27:15:59, 17.28
{'loss': 0.8223, 'learning_rate': 6.461717194581393e-05, 'epoch': 1.76}
{'loss': 0.8223, 'learning_rate': 6.461717194581393e-05, 'epoch': 1.76}
██████▎ | 9389/15000 [43:29:33<24:10:57, 15.52s/it] 63%|██████▎ | 9390/15000 [43:29:48<23:52:34, 15.32s/it] 63%|██████▎ | 9391/15000 [43:30:03<23:41:43, 15.21s/it] 63%|██████▎ | 9392/15000 [43:30:17<23:30:00, 15.09s/it] 63%|██████▎ | 9393/15000 [43:30:32<23:18:47, 14.97s/it] 63%|██████▎ | 9394/15000 [43:31:09<33:38:22, 21.60s/it] 63%|██████▎ | 9395/15000 [43:31:24<30:27:25, 19.56s/it] 63%|██████▎ | 9396/15000 [43:31:39<28:15:05, 18.15s/it] 63%|██████▎ | 9397/15000 [43:31:54<26:40:42, 17.14s/it] 63%|██████▎ | 9398/15000 [43:32:08<25:34:39, 16.44s/it] 63%|██████▎ | 9399/15000 [43:32:23<24:48:33, 15.95s/it] 63%|██████▎ | 9400/15000 [43:32:38<24:17:52, 15.62s/it] 63%|██████▎ | 9400/15000 [43:32:38<24:17:52, 15.62s/it] 63%|███████████▎ | 9389/15000 [43:29:33<24:11:34, 15.52s/it] 63%|██████▎ | 9390/15000 [43:29:48<23:51:28, 15.31s/it] 63%|██████▎ | 9391/15000 [43:30:03<23:40:46, 15.20s/it] 63%|██████▎ | 9392/15000 [43:30:17<23:29:02, 15.08s/it] 63%|██████▎ | 9393/15000 [43:30:32<23:15:24, 14.93s/it] 63%|██████▎ | 9394/15000 [43:31:09<33:41:07, 21.63s/it] 63%|██████▎ | 9395/15000 [43:31:24<30:27:29, 19.56s/it] 63%|██████▎ | 9396/15000 [43:31:39<28:13:06, 18.13s/it] 63%|██████▎ | 9397/15000 [43:31:54<26:38:41, 17.12s/it] 63%|██████▎ | 9398/15000 [43:32:08<25:33:27, 16.42s/it] 63%|██████▎ | 9399/15000 [43:32:23<24:50:33, 15.97s/it] 63%|██████▎ | 9400/15000 [43:32:38<24:17:21, 15.61s/it] 63%|██████▎ | 9400/15000 [43:32:38<24:17:21, 15.61s/it] 63%|█████ 16.41s/it] 63%|██████▎ | 9399/15000 [43:32:23<24:49:00, 15.95s/it] 63%|██████▎ | 9400/15000 [43:32:38<24:19:11, 15.63s/it] 63%|██████▎ | 9400/15000 [43:32:38<24:19:11, 15.63s/it] 63%|██████▎ | 9401/15000 [43:32:53<24:03:28, 15.47s/it] 63%|██████▎ | 9402/15000 [43:33:08<23:52:06, 15.35s/it] 63%|██████▎ | 9403/15000 [43:33:23<23:39:41, 15.22s/it] 63%|██████▎ | 9404/15000 [43:33:38<23:30:49, 15.13s/it] 63%|██████▎ | 9405/15000 [43:34:15<33:56:14, 21.84s/it] 63%|██████▎ | 9406/15000 [43:34:30<30:39:34, 19.73s/it] 63%|██████▎ | 9407/15000 [43:34:45<28:23:38, 18.28s/it] 63%|██████▎ | 9408/15000 [43:35:00<26:47:43, 17.25s/it] 63%|██████▎ | 9409/15000 [43:35:15<25:41:53, 16.55s/it] 63%|██████▎ | 9410/15000 [43:35:30<24:51:00, 16.00s/it] 63█▎ | 9401/15000 [43:32:53<24:01:13, 15.44s/it] 63%|██████▎ | 9402/15000 [43:33:08<23:51:22, 15.34s/it] 63%|██████▎ | 9403/15000 [43:33:23<23:37:32, 15.20s/it] 63%|██████▎ | 9404/15000 [43:33:38<23:33:50, 15.16s/it] 63%|██████▎ | 9405/15000 [43:34:16<33:56:44, 21.84s/it] 63%|██████▎ | 9406/15000 [43:34:30<30:38:47, 19.72s/it] 63%|██████▎ | 9407/15000 [43:34:45<28:27:46, 18.32s/it] 63%|██████▎ | 9408/15000 [43:35:00<26:47:20, 17.25s/it] 63%|██████▎ | 9409/15000 [43:35:15<25:42:51, 16.56s/it] 63%|██████▎ | 9410/15000 [43:35:30<24:46:52, 15.96s/it] 63%|██████▎ | 9411/15000 [43:35:44<24:11:33, 15.58s/it] 63%|██████▎ | 9412/15000 [43:35:59<23:44:53, 15.30s/it] 63%|██████▎ | 9413/15000 [43:36:14<23:30:46, 15.15s/it] 63%|██████▎ | 9414/15000 [43:36:29<23:19:13, 15.03s/it] 63%|█████<E29688>
{'loss': 0.8221, 'learning_rate': 6.260608194688206e-05, 'epoch': 1.78}
{'loss': 0.8221, 'learning_rate': 6.260608194688206e-05, 'epoch': 1.78}
<EFBFBD><EFBFBD>██▎ | 9495/15000 [43:59:06<22:36:01, 14.78s/it] 63%|██████▎ | 9496/15000 [43:59:43<32:51:56, 21.50s/it] 63%|██████▎ | 9497/15000 [43:59:58<29:45:55, 19.47s/it] 63%|██████▎ | 9498/15000 [44:00:13<27:35:58, 18.06s/it] 63%|██████▎ | 9499/15000 [44:00:28<26:04:00, 17.06s/it] 63%|██████▎ | 9500/15000 [44:00:42<24:59:21, 16.36s/it] 63%|██████▎ | 9500/15000 [44:00:43<24:59:21, 16.36s/it] 63%|██████▎ | 9501/15000 [44:00:57<24:18:32, 15.91s/it] 63%|██████▎ | 9502/15000 [44:01:12<23:41:55, 15.52s/it] 63%|██████▎ | 9503/15000 [44:01:27<23:21:07, 15.29s/it] 63%|██████▎ | 9504/15000 [44:01:41<23:03:28, 15.10s/it] 63%|██████▎ | 9505/15000 [44:01:56<22:50:23, 14.96s/it] 63%|██████▎ | 9506/15000 [44:02:11<22:43:56, 14.90s/it] 63%|██████▎ |9/15000 [44:00:28<26:03:59, 17.06s/it] 63%|██████▎ | 9500/15000 [44:00:42<24:59:45, 16.36s/it] 63%|██████▎ | 9500/15000 [44:00:43<24:59:45, 16.36s/it] 63%|██████▎ | 9501/15000 [44:00:57<24:19:38, 15.93s/it] 63%|██████▎ | 9502/15000 [44:01:12<23:45:07, 15.55s/it] 63%|██████▎ | 9503/15000 [44:01:27<23:18:51, 15.27s/it] 63%|██████▎ | 9504/15000 [44:01:41<23:04:35, 15.12s/it] 63%|██████▎ | 9505/15000 [44:01:56<22:51:08, 14.97s/it] 63%|██████▎ | 9506/15000 [44:02:11<22:44:00, 14.90s/it] 63%|██████▎ | 9507/15000 [44:02:48<32:59:27, 21.62s/it] 63%|██████▎ | 9508/15000 [44:03:03<29:46:01, 19.51s/it] 63%|██████▎ | 9509/15000 [44:03:17<27:35:24, 18.09s/it] 63%|██████▎ | 9510/15000 [44:03:32<26:02:07, 17.07s/it] 63%|██████▎ | 9511/15000 [44:03:9/15000 [44:00:28<26:03:13, 17.05s/it] 63%|██████▎ | 9500/15000 [44:00:42<25:00:45, 16.37s/it] 63%|██████▎ | 9500/15000 [44:00:43<25:00:45, 16.37s/it] 63%|██████▎ | 9501/15000 [44:00:57<24:21:03, 15.94s/it] 63%|██████▎ | 9502/15000 [44:01:12<23:43:24, 15.53s/it] 63%|██████▎ | 9503/15000 [44:01:26<23:16:39, 15.24s/it] 63%|██████▎ | 9504/15000 [44:01:41<23:04:01, 15.11s/it] 63%|██████▎ | 9505/15000 [44:01:56<22:55:30, 15.02s/it] 63%|██████▎ | 9506/15000 [44:02:11<22:41:48, 14.87s/it] 63%|██████▎ | 9507/15000 [44:02:48<32:58:51, 21.61s/it] 63%|██████▎ | 9508/15000 [44:03:03<29:45:26, 19.51s/it] 63%|██████▎ | 9509/15000 [44:03:17<27:34:37, 18.08s/it] 63%|██████▎ | 9510/15000 [44:03:32<26:02:25, 17.08s/it] 63%|██████▎ | 9511/15000 [44:03: 9507/15000 [44:02:48<32:59:19, 21.62s/it] 63%|██████▎ | 9508/15000 [44:03:03<29:47:54, 19.53s/it] 63%|██████▎ | 9509/15000 [44:03:17<27:37:20, 18.11s/it] 63%|██████▎ | 9510/15000 [44:03:32<25:59:37, 17.05s/it] 63%|██████▎ | 9511/15000 [44:03:47<24:56:27, 16.36s/it] 63%|██████▎ | 9512/15000 [44:04:01<24:12:03, 15.88s/it] 63%|██████▎ | 9513/15000 [44:04:16<23:36:50, 15.49s/it] 63%|██████▎ | 9514/15000 [44:04:31<23:16:55, 15.28s/it] 63%|██████▎ | 9515/15000 [44:04:45<22:58:48, 15.08s/it] 63%|██████▎ | 9516/15000 [44:05:00<22:46:54, 14.96s/it] 63%|██████▎ | 9517/15000 [44:05:15<22:37:14, 14.85s/it] 63%|██████▎ | 9518/15000 [44:05:52<32:54:20, 21.61s/it] 63%|██████▎ | 9519/15000 [44:06:07<29:44:59, 19.54s/it] 63%|██████▎ | 9520/15000 [44:06:22<27:33:09, 18.10s/it] 63%|██████▎ |
{'loss': 0.821, 'learning_rate': 6.061242437507131e-05, 'epoch': 1.8}
{'loss': 0.821, 'learning_rate': 6.061242437507131e-05, 'epoch': 1.8}
[44:26:03<23:57:07, 15.94s/it] 64%|██████▍ | 9592/15000 [44:26:18<23:22:19, 15.56s/it] 64%|██████▍ | 9593/15000 [44:26:33<22:58:37, 15.30s/it] 64%|██████▍ | 9594/15000 [44:26:48<22:41:26, 15.11s/it] 64%|██████▍ | 9595/15000 [44:27:02<22:32:17, 15.01s/it] 64%|██████▍ | 9596/15000 [44:27:17<22:22:23, 14.90s/it] 64%|██████▍ | 9597/15000 [44:27:56<33:16:17, 22.17s/it] 64%|██████▍ | 9598/15000 [44:28:11<29:55:40, 19.94s/it] 64%|██████▍ | 9599/15000 [44:28:25<27:32:58, 18.36s/it] 64%|██████▍ | 9600/15000 [44:28:41<26:10:41, 17.45s/it] 64%|██████▍ | 9600/15000 [44:28:41<26:10:41, 17.45s/it] 64%|██████▍ | 9601/15000 [44:28:56<24:59:49, 16.67s/it] 64%|██████▍ | 9602/15000 [44:29:10<24:08:31, 16.10s/it] 64%|██████▍ | 9603/15000 [44:29:25<23:29 15.01s/it] 64%|██████▍ | 9596/15000 [44:27:17<22:23:52, 14.92s/it] 64%|██████▍ | 9597/15000 [44:27:56<33:17:12, 22.18s/it] 64%|██████▍ | 9598/15000 [44:28:11<29:56:48, 19.96s/it] 64%|██████▍ | 9599/15000 [44:28:26<27:34:58, 18.39s/it] 64%|██████▍ | 9600/15000 [44:28:41<26:09:12, 17.44s/it] 64%|██████▍ | 9600/15000 [44:28:41<26:09:12, 17.44s/it] 64%|██████▍ | 9601/15000 [44:28:56<25:00:21, 16.67s/it] 64%|██████▍ | 9602/15000 [44:29:10<24:06:28, 16.08s/it] 64%|██████▍ | 9603/15000 [44:29:25<23:29:53, 15.67s/it] 64%|██████▍ | 9604/15000 [44:29:40<23:01:54, 15.37s/it] 64%|██████▍ | 9605/15000 [44:29:54<22:42:19, 15.15s/it] 64%|██████▍ | 9606/15000 [44:30:09<22:28:02, 14.99s/it] 64%|██████▍ | 9607/15000 [44:30:24<22:21:56, 14.93s/it] 64 15.02s/it] 64%|██████▍ | 9596/15000 [44:27:17<22:20:39, 14.89s/it] 64%|██████▍ | 9597/15000 [44:27:56<33:17:41, 22.18s/it] 64%|██████▍ | 9598/15000 [44:28:11<29:55:33, 19.94s/it] 64%|██████▍ | 9599/15000 [44:28:26<27:33:21, 18.37s/it] 64%|██████▍ | 9600/15000 [44:28:41<26:09:05, 17.43s/it] 64%|██████▍ | 9600/15000 [44:28:41<26:09:05, 17.43s/it] 64%|██████▍ | 9601/15000 [44:28:56<24:59:05, 16.66s/it] 64%|██████▍ | 9602/15000 [44:29:10<24:08:14, 16.10s/it] 64%|██████▍ | 9603/15000 [44:29:25<23:29:22, 15.67s/it] 64%|██████▍ | 9604/15000 [44:29:40<23:03:29, 15.38s/it] 64%|██████▍ | 9605/15000 [44:29:55<22:45:34, 15.19s/it] 64%|██████▍ | 9606/15000 [44:30:09<22:28:01, 14.99s/it] 64%|██████▍ | 9607/15000 [44:30:24<22:20:15, 14.91s/it] 64:13, 15.67s/it] 64%|██████▍ | 9604/15000 [44:29:40<23:01:31, 15.36s/it] 64%|██████▍ | 9605/15000 [44:29:54<22:43:15, 15.16s/it] 64%|██████▍ | 9606/15000 [44:30:09<22:27:57, 14.99s/it] 64%|██████▍ | 9607/15000 [44:30:24<22:20:51, 14.92s/it] 64%|██████▍ | 9608/15000 [44:31:04<33:46:12, 22.55s/it] 64%|██████▍ | 9609/15000 [44:31:19<30:14:24, 20.19s/it] 64%|██████▍ | 9610/15000 [44:31:34<27:48:28, 18.57s/it] 64%|██████▍ | 9611/15000 [44:31:48<26:05:23, 17.43s/it] 64%|██████▍ | 9612/15000 [44:32:03<24:50:22, 16.60s/it] 64%|██████▍ | 9613/15000 [44:32:18<24:01:09, 16.05s/it] 64%|██████▍ | 9614/15000 [44:32:32<23:22:48, 15.63s/it] 64%|██████▍ | 9615/15000 [44:32:47<22:54:59, 15.32s/it] 64%|██████▍ | 9616/15000 [44:33:02<22:36:22, 15.12s/it] 64%|██████▍ | 9617/15000 [44:33:16<22:25:
{'loss': 0.8219, 'learning_rate': 5.863712864062089e-05, 'epoch': 1.82}
it] 65%|██████▍ | 9688/15000 [44:53:17<28:38:12, 19.41s/it] 65%|██████▍ | 9689/15000 [44:53:32<26:32:32, 17.99s/it] 65%|██████▍ | 9690/15000 [44:53:47<25:03:08, 16.98s/it] 65%|██████▍ | 9691/15000 [44:54:01<24:01:31, 16.29s/it] 65%|██████▍ | 9692/15000 [44:54:16<23:18:06, 15.80s/it] 65%|██████▍ | 9693/15000 [44:54:31<22:46:11, 15.45s/it] 65%|██████▍ | 9694/15000 [44:54:45<22:26:26, 15.23s/it] 65%|██████▍ | 9695/15000 [44:55:00<22:14:29, 15.09s/it] 65%|██████▍ | 9696/15000 [44:55:15<22:02:55, 14.97s/it] 65%|██████▍ | 9697/15000 [44:55:30<21:56:45, 14.90s/it] 65%|██████▍ | 9698/15000 [44:55:44<21:49:59, 14.82s/it] 65%|██████▍ | 9699/15000 [44:56:22<31:48:29, 21.60s/it] 65%|██████▍ | 9700/15000 [44:56:36<28:45:23, 19.53s/it] 65%|██{'loss': 0.8219, 'learning_rate': 5.863712864062089e-05, 'epoch': 1.82}
<EFBFBD><EFBFBD>██▍ | 9692/15000 [44:54:16<23:15:28, 15.77s/it] 65%|██████▍ | 9693/15000 [44:54:31<22:46:23, 15.45s/it] 65%|██████▍ | 9694/15000 [44:54:45<22:26:10, 15.22s/it] 65%|██████▍ | 9695/15000 [44:55:00<22:14:53, 15.10s/it] 65%|██████▍ | 9696/15000 [44:55:15<22:06:09, 15.00s/it] 65%|██████▍ | 9697/15000 [44:55:30<21:59:07, 14.93s/it] 65%|██████▍ | 9698/15000 [44:55:44<21:49:12, 14.82s/it] 65%|██████▍ | 9699/15000 [44:56:22<31:44:55, 21.56s/it] 65%|██████▍ | 9700/15000 [44:56:36<28:42:35, 19.50s/it] 65%|██████▍ | 9700/15000 [44:56:37<28:42:35, 19.50s/it] 65%|██████▍ | 9701/15000 [44:56:51<26:39:21, 18.11s/it] 65%|██████▍ | 9702/15000 [44:57:06<25:09:49, 17.10s/it] 65%|██████▍ | 9703/15000 [44:57:20<24:01:04, 16.32s/it] 65%|██████▍ |<7C><>██▍ | 9692/15000 [44:54:16<23:16:07, 15.78s/it] 65%|██████▍ | 9693/15000 [44:54:31<22:49:27, 15.48s/it] 65%|██████▍ | 9694/15000 [44:54:45<22:27:16, 15.24s/it] 65%|██████▍ | 9695/15000 [44:55:00<22:12:38, 15.07s/it] 65%|██████▍ | 9696/15000 [44:55:15<22:05:35, 15.00s/it] 65%|██████▍ | 9697/15000 [44:55:30<21:56:53, 14.90s/it] 65%|██████▍ | 9698/15000 [44:55:44<21:50:18, 14.83s/it] 65%|██████▍ | 9699/15000 [44:56:22<31:47:06, 21.59s/it] 65%|██████▍ | 9700/15000 [44:56:36<28:42:26, 19.50s/it] 65%|██████▍ | 9700/15000 [44:56:37<28:42:26, 19.50s/it] 65%|██████▍ | 9701/15000 [44:56:51<26:39:43, 18.11s/it] 65%|██████▍ | 9702/15000 [44:57:06<25:12:39, 17.13s/it] 65%|██████▍ | 9703/15000 [44:57:20<24:00:33, 16.32s/it] 65%|██████▍ |████▍ | 9700/15000 [44:56:36<28:45:23, 19.53s/it] 65%|██████▍ | 9701/15000 [44:56:51<26:38:42, 18.10s/it] 65%|██████▍ | 9702/15000 [44:57:06<25:06:35, 17.06s/it] 65%|██████▍ | 9703/15000 [44:57:20<24:00:57, 16.32s/it] 65%|██████▍ | 9704/15000 [44:57:35<23:20:10, 15.86s/it] 65%|██████▍ | 9705/15000 [44:57:50<22:48:21, 15.51s/it] 65%|██████▍ | 9706/15000 [44:58:05<22:29:06, 15.29s/it] 65%|██████▍ | 9707/15000 [44:58:19<22:11:47, 15.10s/it] 65%|██████▍ | 9708/15000 [44:58:34<22:04:22, 15.02s/it] 65%|██████▍ | 9709/15000 [44:58:49<21:56:51, 14.93s/it] 65%|██████▍ | 9710/15000 [44:59:27<32:02:03, 21.80s/it] 65%|██████▍ | 9711/15000 [44:59:41<28:53:06, 19.66s/it] 65%|██████▍ | 9712/15000 [44:59:56<26:41:32, 18.17s/it] 65%|██████▍ | 9713/15000 [45:00:11<25:08:41, 17.12s/it] 65%|██<E29688><E29688> 9704/15000 [44:57:35<23:16:42, 15.82s/it] 65%|██████▍ | 9705/15000 [44:57:50<22:47:39, 15.50s/it] 65%|██████▍ | 9706/15000 [44:58:05<22:27:48, 15.28s/it] 65%|██████▍ | 9707/15000 [44:58:19<22:12:42, 15.11s/it] 65%|██████▍ | 9708/15000 [44:58:34<22:07:21, 15.05s/it] 65%|██████▍ | 9709/15000 [44:58:49<21:55:05, 14.91s/it] 65%|██████▍ | 9710/15000 [44:59:27<32:01:12, 21.79s/it] 65%|██████▍ | 9711/15000 [44:59:41<28:56:45, 19.70s/it] 65%|██████▍ | 9712/15000 [44:59:56<26:39:05, 18.14s/it] 65%|██████▍ | 9713/15000 [45:00:11<25:08:26, 17.12s/it] 65%|██████▍ | 9714/15000 [45:00:25<24:04:25, 16.40s/it] 65%|██████▍ | 9715/15000 [45:00:40<23:15:34, 15.84s/it] 65%|██████▍ | 9716/15000 [45:00:55<22:43:02, 15.48s/it] 65%|██████▍ | 9717/15000 [45:01:09<22:17:34, 15.19s/it] 65%|██████▍ |
[45:20:51<21:25:16, 14.80s/it] 65%|██████▌ | 9789/15000 [45:21:29<31:30:31, 21.77s/it] 65%|██████▌ | 9790/15000 [45:21:44<28:23:00, 19.61s/it] 65%|██████▌ | 9791/15000 [45:21:59<26:13:58, 18.13s/it] 65%|██████▌ | 9792/15000 [45:22:13<24:43:43, 17.09s/it] 65%|██████▌ | 9793/15000 [45:22:28<23:42:31, 16.39s/it] 65%|██████▌ | 9794/15000 [45:22:43<23:00:36, 15.91s/it] 65%|██████▌ | 9795/15000 [45:22:57<22:27:12, 15.53s/it] 65%|██████▌ | 9796/15000 [45:23:12<22:02:41, 15.25s/it] 65%|██████▌ | 9797/15000 [45:23:27<21:46:24, 15.07s/it] 65%|██████▌ | 9798/15000 [45:23:41<21:33:20, 14.92s/it] 65%|██████▌ | 9799/15000 [45:23:56<21:27:31, 14.85s/it] 65%|██████▌ | 9800/15000 [45:24:33<30:59:29, 21.46s/it] 65%|██████▌ | 9800/15000 [45:24:33<30:59{'loss': 0.82, 'learning_rate': 5.668111559378471e-05, 'epoch': 1.83}
{'loss': 0.82, 'learning_rate': 5.668111559378471e-05, 'epoch': 1.83}
[45:20:51<21:27:40, 14.82s/it] 65%|██████▌ | 9789/15000 [45:21:29<31:31:52, 21.78s/it] 65%|██████▌ | 9790/15000 [45:21:44<28:23:38, 19.62s/it] 65%|██████▌ | 9791/15000 [45:21:59<26:13:12, 18.12s/it] 65%|██████▌ | 9792/15000 [45:22:13<24:42:00, 17.07s/it] 65%|██████▌ | 9793/15000 [45:22:28<23:42:50, 16.40s/it] 65%|██████▌ | 9794/15000 [45:22:43<22:57:00, 15.87s/it] 65%|██████▌ | 9795/15000 [45:22:57<22:26:27, 15.52s/it] 65%|██████▌ | 9796/15000 [45:23:12<22:05:45, 15.29s/it] 65%|██████▌ | 9797/15000 [45:23:27<21:46:40, 15.07s/it] 65%|██████▌ | 9798/15000 [45:23:41<21:34:42, 14.93s/it] 65%|██████▌ | 9799/15000 [45:23:56<21:26:46, 14.84s/it] 65%|██████▌ | 9800/15000 [45:24:33<30:59:08, 21.45s/it] 65%|██████▌ | 9800/15000 [45:24:33<30:59<35> | 9798/15000 [45:23:41<21:34:39, 14.93s/it] 65%|██████▌ | 9799/15000 [45:23:56<21:30:45, 14.89s/it] 65%|██████▌ | 9800/15000 [45:24:33<31:00:45, 21.47s/it] 65%|██████▌ | 9800/15000 [45:24:33<31:00:45, 21.47s/it] 65%|██████▌ | 9801/15000 [45:24:48<28:09:30, 19.50s/it] 65%|██████▌ | 9802/15000 [45:25:02<26:03:05, 18.04s/it] 65%|██████▌ | 9803/15000 [45:25:17<24:35:27, 17.03s/it] 65%|██████▌ | 9804/15000 [45:25:32<23:33:10, 16.32s/it] 65%|██████▌ | 9805/15000 [45:25:46<22:50:37, 15.83s/it] 65%|██████▌ | 9806/15000 [45:26:01<22:19:58, 15.48s/it] 65%|██████▌ | 9807/15000 [45:26:16<22:01:44, 15.27s/it] 65%|██████▌ | 9808/15000 [45:26:31<21:45:24, 15.09s/it] 65%|██████▌ | 9809/15000 [45:26:45<21:33:00, 14.95s/it] 65%|██████▌ | 9810/1500:08, 21.45s/it] 65%|██████▌ | 9801/15000 [45:24:48<28:10:35, 19.51s/it] 65%|██████▌ | 9802/15000 [45:25:02<26:03:54, 18.05s/it] 65%|██████▌ | 9803/15000 [45:25:17<24:34:57, 17.03s/it] 65%|██████▌ | 9804/15000 [45:25:32<23:34:48, 16.34s/it] 65%|██████▌ | 9805/15000 [45:25:47<22:51:42, 15.84s/it] 65%|██████▌ | 9806/15000 [45:26:01<22:18:32, 15.46s/it] 65%|██████▌ | 9807/15000 [45:26:16<22:00:18, 15.25s/it] 65%|██████▌ | 9808/15000 [45:26:31<21:45:51, 15.09s/it] 65%|██████▌ | 9809/15000 [45:26:45<21:34:33, 14.96s/it] 65%|██████▌ | 9810/15000 [45:27:00<21:26:00, 14.87s/it] 65%|██████▌ | 9811/15000 [45:27:15<21:21:30, 14.82s/it] 65%|██████▌ | 9812/15000 [45:27:51<30:50:14, 21.40s/it] 65%|██████▌ | 9813/15000 [45:28:06<27:58:10, 19.41s/it] 65%|██████▌ | 9814/15000 [45:28:21<25:56:1:29, 21.46s/it] 65%|██████▌ | 9801/15000 [45:24:48<28:10:24, 19.51s/it] 65%|██████▌ | 9802/15000 [45:25:02<26:02:40, 18.04s/it] 65%|██████▌ | 9803/15000 [45:25:17<24:36:04, 17.04s/it] 65%|██████▌ | 9804/15000 [45:25:32<23:35:22, 16.34s/it] 65%|██████▌ | 9805/15000 [45:25:46<22:49:17, 15.81s/it] 65%|██████▌ | 9806/15000 [45:26:01<22:20:35, 15.49s/it] 65%|██████▌ | 9807/15000 [45:26:16<22:00:50, 15.26s/it] 65%|██████▌ | 9808/15000 [45:26:31<21:49:29, 15.13s/it] 65%|██████▌ | 9809/15000 [45:26:45<21:31:24, 14.93s/it] 65%|██████▌ | 9810/15000 [45:27:00<21:27:24, 14.88s/it] 65%|██████▌ | 9811/15000 [45:27:15<21:22:46, 14.83s/it] 65%|██████▌ | 9812/15000 [45:27:51<30:49:40, 21.39s/it] 65%|██████▌ | 9813/15000 [45:28:06<27:59:13, 19.42s/it] 65%|██████▌ | 9814/15000 [45:28:21<25:56:
{'loss': 0.8193, 'learning_rate': 5.474529709554612e-05, 'epoch': 1.85}
{'loss': 0.8193, 'learning_rate': 5.474529709554612e-05, 'epoch': 1.85}
24:10:29, 17.04s/it] 66%|██████▌ | 9895/15000 [45:50:45<23:08:41, 16.32s/it] 66%|██████▌ | 9896/15000 [45:51:00<22:26:22, 15.83s/it] 66%|██████▌ | 9897/15000 [45:51:15<21:57:05, 15.49s/it] 66%|██████▌ | 9898/15000 [45:51:29<21:34:16, 15.22s/it] 66%|██████▌ | 9899/15000 [45:51:44<21:20:40, 15.06s/it] 66%|██████▌ | 9900/15000 [45:51:59<21:10:33, 14.95s/it] 66%|██████▌ | 9900/15000 [45:51:59<21:10:33, 14.95s/it] 66%|██████▌ | 9901/15000 [45:52:13<21:08:02, 14.92s/it] 66%|██████▌ | 9902/15000 [45:52:51<30:35:19, 21.60s/it] 66%|██████▌ | 9903/15000 [45:53:05<27:38:28, 19.52s/it] 66%|██████▌ | 9904/15000 [45:53:20<25:31:23, 18.03s/it] 66%|██████▌ | 9905/15000 [45:53:34<24:05:34, 17.02s/it] 66%|██████▌ | 9906/15000 [45:53:49<23:05:26, 16.32] 66%|██████▌ | 9899/15000 [45:51:44<21:20:26, 15.06s/it] 66%|██████▌ | 9900/15000 [45:51:59<21:12:41, 14.97s/it] 66%|██████▌ | 9900/15000 [45:51:59<21:12:41, 14.97s/it] 66%|██████▌ | 9901/15000 [45:52:14<21:09:02, 14.93s/it] 66%|██████▌ | 9902/15000 [45:52:51<30:31:48, 21.56s/it] 66%|██████▌ | 9903/15000 [45:53:05<27:38:02, 19.52s/it] 66%|██████▌ | 9904/15000 [45:53:20<25:32:36, 18.04s/it] 66%|██████▌ | 9905/15000 [45:53:35<24:08:17, 17.06s/it] 66%|██████▌ | 9906/15000 [45:53:49<23:02:07, 16.28s/it] 66%|██████▌ | 9907/15000 [45:54:04<22:23:41, 15.83s/it] 66%|██████▌ | 9908/15000 [45:54:18<21:50:03, 15.44s/it] 66%|██████▌ | 9909/15000 [45:54:33<21:28:43, 15.19s/it] 66%|██████▌ | 9910/15000 [45:54:48<21:14:17, 15.02s/it] 66%|██<E29688><E29688>] 66%|██████▌ | 9899/15000 [45:51:44<21:20:40, 15.06s/it] 66%|██████▌ | 9900/15000 [45:51:59<21:11:58, 14.96s/it] 66%|██████▌ | 9900/15000 [45:51:59<21:11:58, 14.96s/it] 66%|██████▌ | 9901/15000 [45:52:13<21:06:06, 14.90s/it] 66%|██████▌ | 9902/15000 [45:52:51<30:34:31, 21.59s/it] 66%|██████▌ | 9903/15000 [45:53:05<27:39:41, 19.54s/it] 66%|██████▌ | 9904/15000 [45:53:20<25:35:17, 18.08s/it] 66%|██████▌ | 9905/15000 [45:53:35<24:05:27, 17.02s/it] 66%|██████▌ | 9906/15000 [45:53:49<23:04:12, 16.30s/it] 66%|██████▌ | 9907/15000 [45:54:04<22:23:33, 15.83s/it] 66%|██████▌ | 9908/15000 [45:54:18<21:49:06, 15.43s/it] 66%|██████▌ | 9909/15000 [45:54:33<21:29:13, 15.19s/it] 66%|██████▌ | 9910/15000 [45:54:48<21:15:22, 15.03s/it] 66%|██<E29688><E29688>s/it] 66%|██████▌ | 9907/15000 [45:54:04<22:21:34, 15.80s/it] 66%|██████▌ | 9908/15000 [45:54:18<21:50:33, 15.44s/it] 66%|██████▌ | 9909/15000 [45:54:33<21:30:39, 15.21s/it] 66%|██████▌ | 9910/15000 [45:54:48<21:13:20, 15.01s/it] 66%|██████▌ | 9911/15000 [45:55:02<21:02:40, 14.89s/it] 66%|██████▌ | 9912/15000 [45:55:17<20:56:28, 14.82s/it] 66%|██████▌ | 9913/15000 [45:55:54<30:21:32, 21.48s/it] 66%|██████▌ | 9914/15000 [45:56:09<27:29:43, 19.46s/it] 66%|██████▌ | 9915/15000 [45:56:23<25:25:54, 18.00s/it] 66%|██████▌ | 9916/15000 [45:56:38<23:59:30, 16.99s/it] 66%|██████▌ | 9917/15000 [45:56:53<23:01:06, 16.30s/it] 66%|██████▌ | 9918/15000 [45:57:07<22:17:48, 15.79s/it] 66%|██████▌ | 9919/15000 [45:57:22<21:48:05, 15.45s/it] 66%|██████▌ | 9920/15000 [45:57:36<21:26:04, 15.19s
{'loss': 0.8199, 'learning_rate': 5.283057559252341e-05, 'epoch': 1.87}
{'loss': 0.8199, 'learning_rate': 5.283057559252341e-05, 'epoch': 1.87}
<EFBFBD><EFBFBD>█████▋ | 9991/15000 [46:17:12<20:38:28, 14.83s/it] 67%|██████▋ | 9992/15000 [46:17:49<30:02:12, 21.59s/it] 67%|██████▋ | 9993/15000 [46:18:03<27:06:00, 19.48s/it] 67%|██████▋ | 9994/15000 [46:18:18<25:05:59, 18.05s/it] 67%|██████▋ | 9995/15000 [46:18:33<23:41:18, 17.04s/it] 67%|██████▋ | 9996/15000 [46:18:47<22:41:23, 16.32s/it] 67%|██████▋ | 9997/15000 [46:19:02<22:01:44, 15.85s/it] 67%|██████▋ | 9998/15000 [46:19:17<21:31:39, 15.49s/it] 67%|██████▋ | 9999/15000 [46:19:32<21:09:38, 15.23s/it] 67%|██████▋ | 10000/15000 [46:19:46<20:53:03, 15.04s/it] 67%|██████▋ | 10000/15000 [46:19:46<20:53:03, 15.04s/it]Saving model checkpoint to /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-10000
tokenizer config file saved in /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-10000/tokenizer_config.json
Special tokens file saved in /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-10000/special_tokens_map.json
<EFBFBD> | 9995/15000 [46:18:33<23:39:29, 17.02s/it] 67%|██████▋ | 9996/15000 [46:18:47<22:40:19, 16.31s/it] 67%|██████▋ | 9997/15000 [46:19:02<22:03:15, 15.87s/it] 67%|██████▋ | 9998/15000 [46:19:17<21:34:15, 15.52s/it] 67%|██████▋ | 9999/15000 [46:19:32<21:09:47, 15.23s/it] 67%|██████▋ | 10000/15000 [46:19:46<20:55:35, 15.07s/it] 67%|██████▋ | 10000/15000 [46:19:46<20:55:35, 15.07s/it] 67%|██████▋ | 10001/15000 [46:20:06<22:47:17, 16.41s/it] 67%|██████▋ | 10002/15000 [46:20:21<22:08:09, 15.94s/it] 67%|██████▋ | 10003/15000 [46:20:57<30:47:30, 22.18s/it] 67%|██████▋ | 10004/15000 [46:21:12<27:39:18, 19.93s/it] 67%|██████▋ | 10005/15000 [46:21:27<25:29:25, 18.37s/it] 67%|██████▋ | 10006/15000 [46:21:41<23:55:56, 17.25s/it] 67%|██████▋ | <20> | 9995/15000 [46:18:33<23:41:45, 17.04s/it] 67%|██████▋ | 9996/15000 [46:18:48<22:41:29, 16.32s/it] 67%|██████▋ | 9997/15000 [46:19:02<22:03:44, 15.88s/it] 67%|██████▋ | 9998/15000 [46:19:17<21:29:14, 15.46s/it] 67%|██████▋ | 9999/15000 [46:19:32<21:08:06, 15.21s/it] 67%|██████▋ | 10000/15000 [46:19:46<20:53:10, 15.04s/it] 67%|██████▋ | 10000/15000 [46:19:46<20:53:10, 15.04s/it] 67%|██████▋ | 10001/15000 [46:20:06<22:48:49, 16.43s/it] 67%|██████▋ | 10002/15000 [46:20:21<22:06:26, 15.92s/it] 67%|██████▋ | 10003/15000 [46:20:57<30:48:59, 22.20s/it] 67%|██████▋ | 10004/15000 [46:21:12<27:41:24, 19.95s/it] 67%|██████▋ | 10005/15000 [46:21:27<25:27:48, 18.35s/it] 67%|██████▋ | 10006/15000 [46:21:41<23:54:14, 17.23s/it] 67%|██████▋ | 67%|██████▋ | 10001/15000 [46:20:06<22:52:00, 16.47s/it] 67%|██████▋ | 10002/15000 [46:20:21<22:05:37, 15.91s/it] 67%|██████▋ | 10003/15000 [46:20:57<30:46:29, 22.17s/it] 67%|██████▋ | 10004/15000 [46:21:12<27:41:15, 19.95s/it] 67%|██████▋ | 10005/15000 [46:21:27<25:28:51, 18.36s/it] 67%|██████▋ | 10006/15000 [46:21:41<23:56:05, 17.25s/it] 67%|██████▋ | 10007/15000 [46:21:56<22:51:26, 16.48s/it] 67%|██████▋ | 10008/15000 [46:22:11<22:06:56, 15.95s/it] 67%|██████▋ | 10009/15000 [46:22:25<21:35:13, 15.57s/it] 67%|██████▋ | 10010/15000 [46:22:40<21:08:43, 15.26s/it] 67%|██████▋ | 10011/15000 [46:22:55<20:54:40, 15.09s/it] 67%|██████▋ | 10012/15000 [46:23:09<20:44:13, 14.97s/it] 67%|██████▋ | 10013/15000 [46:23:24<20:37:20, 14.89s/it] 67%|██████▋ | 10014/15000 [46:23:39<20:32:2410007/15000 [46:21:56<22:50:30, 16.47s/it] 67%|██████▋ | 10008/15000 [46:22:11<22:06:41, 15.95s/it] 67%|██████▋ | 10009/15000 [46:22:26<21:34:33, 15.56s/it] 67%|██████▋ | 10010/15000 [46:22:40<21:10:18, 15.27s/it] 67%|██████▋ | 10011/15000 [46:22:55<20:54:26, 15.09s/it] 67%|██████▋ | 10012/15000 [46:23:10<20:45:29, 14.98s/it] 67%|██████▋ | 10013/15000 [46:23:24<20:34:28, 14.85s/it] 67%|██████▋ | 10014/15000 [46:23:39<20:32:49, 14.84s/it] 67%|██████▋ | 10015/15000 [46:24:16<29:48:44, 21.53s/it] 67%|██████▋ | 10016/15000 [46:24:31<26:57:48, 19.48s/it] 67%|██████▋ | 10017/15000 [46:24:45<24:57:56, 18.04s/it] 67%|██████▋ | 10018/15000 [46:25:00<23:37:15, 17.07s/it] 67%|██████▋ | 10019/15000 [46:25:15<22:34:41, 16.32s/it] 67%|██████▋ | 10020/15000 [46:25:29<21:49:44, 15.78s/it] 67%|████<E29688>
{'loss': 0.8186, 'learning_rate': 5.0937843696263966e-05, 'epoch': 1.89}
{'loss': 0.8186, 'learning_rate': 5.0937843696263966e-05, 'epoch': 1.89}
090/15000 [46:44:50<20:37:17, 15.12s/it] 67%|██████▋ | 10091/15000 [46:45:05<20:28:12, 15.01s/it] 67%|██████▋ | 10092/15000 [46:45:20<20:18:54, 14.90s/it] 67%|██████▋ | 10093/15000 [46:45:35<20:13:52, 14.84s/it] 67%|██████▋ | 10094/15000 [46:46:12<29:16:25, 21.48s/it] 67%|██████▋ | 10095/15000 [46:46:26<26:27:45, 19.42s/it] 67%|██████▋ | 10096/15000 [46:46:41<24:30:39, 17.99s/it] 67%|██████▋ | 10097/15000 [46:46:56<23:09:37, 17.01s/it] 67%|██████▋ | 10098/15000 [46:47:10<22:12:12, 16.31s/it] 67%|██████▋ | 10099/15000 [46:47:25<21:34:30, 15.85s/it] 67%|██████▋ | 10100/15000 [46:47:40<21:06:34, 15.51s/it] 67%|██████▋ | 10100/15000 [46:47:40<21:06:34, 15.51s/it] 67%|██████▋ | 10101/15000 [46:47:54<20:47:12, 15.28s/it] 67%|██████▋ | 101090/15000 [46:44:51<20:38:19, 15.13s/it] 67%|██████▋ | 10091/15000 [46:45:05<20:27:53, 15.01s/it] 67%|██████▋ | 10092/15000 [46:45:20<20:18:57, 14.90s/it] 67%|██████▋ | 10093/15000 [46:45:35<20:14:17, 14.85s/it] 67%|██████▋ | 10094/15000 [46:46:12<29:14:11, 21.45s/it] 67%|██████▋ | 10095/15000 [46:46:26<26:29:47, 19.45s/it] 67%|██████▋ | 10096/15000 [46:46:41<24:29:06, 17.97s/it] 67%|██████▋ | 10097/15000 [46:46:56<23:10:11, 17.01s/it] 67%|██████▋ | 10098/15000 [46:47:10<22:12:22, 16.31s/it] 67%|██████▋ | 10099/15000 [46:47:25<21:32:01, 15.82s/it] 67%|██████▋ | 10100/15000 [46:47:40<21:02:31, 15.46s/it] 67%|██████▋ | 10100/15000 [46:47:40<21:02:31, 15.46s/it] 67%|██████▋ | 10101/15000 [46:47:55<20:51:27, 15.33s/it] 67%|██████▋ | 10117.01s/it] 67%|██████▋ | 10098/15000 [46:47:10<22:11:38, 16.30s/it] 67%|██████▋ | 10099/15000 [46:47:25<21:32:34, 15.82s/it] 67%|██████▋ | 10100/15000 [46:47:40<21:04:18, 15.48s/it] 67%|██████▋ | 10100/15000 [46:47:40<21:04:18, 15.48s/it] 67%|██████▋ | 10101/15000 [46:47:54<20:47:07, 15.27s/it] 67%|██████▋ | 10102/15000 [46:48:09<20:33:38, 15.11s/it] 67%|██████▋ | 10103/15000 [46:48:24<20:24:20, 15.00s/it] 67%|██████▋ | 10104/15000 [46:48:38<20:13:41, 14.87s/it] 67%|██████▋ | 10105/15000 [46:49:15<29:12:04, 21.48s/it] 67%|██████▋ | 10106/15000 [46:49:30<26:24:47, 19.43s/it] 67%|██████▋ | 10107/15000 [46:49:45<24:30:31, 18.03s/it] 67%|██████▋ | 10108/15000 [46:49:59<23:08:31, 17.03s/it] 67%|██████▋ | 10109/15000 [46:50:14<22:10:58, 102/15000 [46:48:09<20:35:40, 15.14s/it] 67%|██████▋ | 10103/15000 [46:48:24<20:21:52, 14.97s/it] 67%|██████▋ | 10104/15000 [46:48:38<20:10:50, 14.84s/it] 67%|██████▋ | 10105/15000 [46:49:15<29:13:33, 21.49s/it] 67%|██████▋ | 10106/15000 [46:49:30<26:23:17, 19.41s/it] 67%|██████▋ | 10107/15000 [46:49:45<24:30:01, 18.03s/it] 67%|██████▋ | 10108/15000 [46:49:59<23:08:30, 17.03s/it] 67%|██████▋ | 10109/15000 [46:50:14<22:12:48, 16.35s/it] 67%|██████▋ | 10110/15000 [46:50:29<21:28:19, 15.81s/it] 67%|██████▋ | 10111/15000 [46:50:44<21:03:25, 15.51s/it] 67%|██████▋ | 10112/15000 [46:50:58<20:39:48, 15.22s/it] 67%|██████▋ | 10113/15000 [46:51:13<20:28:06, 15.08s/it] 67%|██████▋ | 10114/15000 [46:51:28<20:18:39, 14.97s/it] 67%|██████▋ | 10115/15000 [46:51:42<20:13:27, 14.90s/it] 67%|█████<E29688>
{'loss': 0.8218, 'learning_rate': 4.9067983767123736e-05, 'epoch': 1.91}
{'loss': 0.8218, 'learning_rate': 4.9067983767123736e-05, 'epoch': 1.91}
07s/it] 68%|██████▊ | 10193/15000 [47:13:23<19:58:50, 14.96s/it] 68%|██████▊ | 10194/15000 [47:13:37<19:51:28, 14.87s/it] 68%|██████▊ | 10195/15000 [47:14:14<28:36:20, 21.43s/it] 68%|██████▊ | 10196/15000 [47:14:29<25:53:33, 19.40s/it] 68%|██████▊ | 10197/15000 [47:14:43<23:59:43, 17.99s/it] 68%|██████▊ | 10198/15000 [47:14:58<22:38:29, 16.97s/it] 68%|██████▊ | 10199/15000 [47:15:13<21:43:37, 16.29s/it] 68%|██████▊ | 10200/15000 [47:15:27<21:05:47, 15.82s/it] 68%|██████▊ | 10200/15000 [47:15:27<21:05:47, 15.82s/it] 68%|██████▊ | 10201/15000 [47:15:42<20:38:02, 15.48s/it] 68%|██████▊ | 10202/15000 [47:15:57<20:17:16, 15.22s/it] 68%|██████▊ | 10203/15000 [47:16:11<20:04:50, 15.07s/it] 68%|██████▊ | 10204/15000 [47:16:26<19:57:25, 14.9<EFBFBD><EFBFBD> | 10199/15000 [47:15:13<21:42:51, 16.28s/it] 68%|██████▊ | 10200/15000 [47:15:27<21:03:26, 15.79s/it] 68%|██████▊ | 10200/15000 [47:15:27<21:03:26, 15.79s/it] 68%|██████▊ | 10201/15000 [47:15:42<20:40:16, 15.51s/it] 68%|██████▊ | 10202/15000 [47:15:57<20:16:55, 15.22s/it] 68%|██████▊ | 10203/15000 [47:16:11<20:03:52, 15.06s/it] 68%|██████▊ | 10204/15000 [47:16:26<19:56:45, 14.97s/it] 68%|██████▊ | 10205/15000 [47:16:41<19:51:36, 14.91s/it] 68%|██████▊ | 10206/15000 [47:17:18<28:41:46, 21.55s/it] 68%|██████▊ | 10207/15000 [47:17:33<25:59:37, 19.52s/it] 68%|██████▊ | 10208/15000 [47:17:47<23:58:51, 18.02s/it] 68%|██████▊ | 10209/15000 [47:18:02<22:41:29, 17.05s/it] 68%|██████▊ | 10210/15000 [47:18:17<21:45:04, 16.35s/it] 68%|██████▖<E29688> | 10199/15000 [47:15:13<21:42:14, 16.27s/it] 68%|██████▊ | 10200/15000 [47:15:27<21:06:09, 15.83s/it] 68%|██████▊ | 10200/15000 [47:15:27<21:06:09, 15.83s/it] 68%|██████▊ | 10201/15000 [47:15:42<20:38:56, 15.49s/it] 68%|██████▊ | 10202/15000 [47:15:57<20:20:11, 15.26s/it] 68%|██████▊ | 10203/15000 [47:16:11<20:02:25, 15.04s/it] 68%|██████▊ | 10204/15000 [47:16:26<19:56:45, 14.97s/it] 68%|██████▊ | 10205/15000 [47:16:41<19:50:49, 14.90s/it] 68%|██████▊ | 10206/15000 [47:17:18<28:42:41, 21.56s/it] 68%|██████▊ | 10207/15000 [47:17:33<25:59:04, 19.52s/it] 68%|██████▊ | 10208/15000 [47:17:47<24:01:02, 18.04s/it] 68%|██████▊ | 10209/15000 [47:18:02<22:41:45, 17.05s/it] 68%|██████▊ | 10210/15000 [47:18:17<21:45:10, 16.35s/it] 68%|██████<E29688><E29688>8s/it] 68%|██████▊ | 10205/15000 [47:16:41<19:50:25, 14.90s/it] 68%|██████▊ | 10206/15000 [47:17:18<28:43:26, 21.57s/it] 68%|██████▊ | 10207/15000 [47:17:33<25:56:14, 19.48s/it] 68%|██████▊ | 10208/15000 [47:17:47<24:00:32, 18.04s/it] 68%|██████▊ | 10209/15000 [47:18:02<22:41:53, 17.06s/it] 68%|██████▊ | 10210/15000 [47:18:17<21:43:24, 16.33s/it] 68%|██████▊ | 10211/15000 [47:18:31<21:02:20, 15.82s/it] 68%|██████▊ | 10212/15000 [47:18:46<20:35:13, 15.48s/it] 68%|██████▊ | 10213/15000 [47:19:01<20:14:22, 15.22s/it] 68%|██████▊ | 10214/15000 [47:19:15<19:59:34, 15.04s/it] 68%|██████▊ | 10215/15000 [47:19:30<19:50:52, 14.93s/it] 68%|██████▊ | 10216/15000 [47:19:45<19:45:32, 14.87s/it] 68%|██████▊ | 10217/15000 [47:19:59<19:38:11, 14.78s/it] 68%|██████▊ | 10218/15000 [47:20:36<2
{'loss': 0.8182, 'learning_rate': 4.722186750292511e-05, 'epoch': 1.93}
{'loss': 0.8182, 'learning_rate': 4.722186750292511e-05, 'epoch': 1.93}
/it] 69%|██████▊ | 10288/15000 [47:39:57<22:18:14, 17.04s/it] 69%|██████▊ | 10289/15000 [47:40:12<21:20:14, 16.31s/it] 69%|██████▊ | 10290/15000 [47:40:27<20:43:17, 15.84s/it] 69%|██████▊ | 10291/15000 [47:40:42<20:16:20, 15.50s/it] 69%|██████▊ | 10292/15000 [47:40:56<19:56:59, 15.25s/it] 69%|██████▊ | 10293/15000 [47:41:11<19:41:58, 15.07s/it] 69%|██████▊ | 10294/15000 [47:41:26<19:32:08, 14.94s/it] 69%|██████▊ | 10295/15000 [47:41:40<19:26:28, 14.88s/it] 69%|██████▊ | 10296/15000 [47:41:55<19:19:45, 14.79s/it] 69%|██████▊ | 10297/15000 [47:42:32<28:06:19, 21.51s/it] 69%|██████▊ | 10298/15000 [47:42:47<25:22:59, 19.43s/it] 69%|██████▊ | 10299/15000 [47:43:01<23:31:25, 18.01s/it] 69%|██████▊ | 10300/15000 [47:43:16<22:10:50, 16.99s/it] | 10294/15000 [47:41:25<19:29:09, 14.91s/it] 69%|██████▊ | 10295/15000 [47:41:40<19:25:30, 14.86s/it] 69%|██████▊ | 10296/15000 [47:41:55<19:22:31, 14.83s/it] 69%|██████▊ | 10297/15000 [47:42:32<28:05:52, 21.51s/it] 69%|██████▊ | 10298/15000 [47:42:47<25:25:49, 19.47s/it] 69%|██████▊ | 10299/15000 [47:43:01<23:27:36, 17.97s/it] 69%|██████▊ | 10300/15000 [47:43:16<22:11:26, 17.00s/it] 69%|██████▊ | 10300/15000 [47:43:16<22:11:26, 17.00s/it] 69%|██████▊ | 10301/15000 [47:43:31<21:20:47, 16.35s/it] 69%|██████▊ | 10302/15000 [47:43:45<20:36:48, 15.80s/it] 69%|██████▊ | 10303/15000 [47:44:00<20:12:01, 15.48s/it] 69%|██████▊ | 10304/15000 [47:44:15<19:53:16, 15.25s/it] 69%|██████▊ | 10305/15000 [47:44:29<19:40:40, 15.09s/it] 69%|██████▊ | 10294/15000 [47:41:26<19:32:05, 14.94s/it] 69%|██████▊ | 10295/15000 [47:41:40<19:25:17, 14.86s/it] 69%|██████▊ | 10296/15000 [47:41:55<19:21:10, 14.81s/it] 69%|██████▊ | 10297/15000 [47:42:32<28:06:57, 21.52s/it] 69%|██████▊ | 10298/15000 [47:42:47<25:23:51, 19.45s/it] 69%|██████▊ | 10299/15000 [47:43:01<23:30:23, 18.00s/it] 69%|██████▊ | 10300/15000 [47:43:16<22:09:21, 16.97s/it] 69%|██████▊ | 10300/15000 [47:43:16<22:09:21, 16.97s/it] 69%|██████▊ | 10301/15000 [47:43:31<21:22:21, 16.37s/it] 69%|██████▊ | 10302/15000 [47:43:45<20:36:52, 15.80s/it] 69%|██████▊ | 10303/15000 [47:44:00<20:10:18, 15.46s/it] 69%|██████▊ | 10304/15000 [47:44:15<19:51:41, 15.23s/it] 69%|██████▊ | 10305/15000 [47:44:29<19:39:46, 15.08s/it] 69%|██████▊ 69%|██████▊ | 10300/15000 [47:43:16<22:10:50, 16.99s/it] 69%|██████▊ | 10301/15000 [47:43:31<21:19:36, 16.34s/it] 69%|██████▊ | 10302/15000 [47:43:45<20:39:17, 15.83s/it] 69%|██████▊ | 10303/15000 [47:44:00<20:10:29, 15.46s/it] 69%|██████▊ | 10304/15000 [47:44:15<19:54:04, 15.26s/it] 69%|██████▊ | 10305/15000 [47:44:29<19:40:11, 15.08s/it] 69%|██████▊ | 10306/15000 [47:44:44<19:28:37, 14.94s/it] 69%|██████▊ | 10307/15000 [47:44:59<19:23:38, 14.88s/it] 69%|██████▊ | 10308/15000 [47:45:35<27:54:10, 21.41s/it] 69%|██████▊ | 10309/15000 [47:45:50<25:14:00, 19.36s/it] 69%|██████▊ | 10310/15000 [47:46:05<23:23:26, 17.95s/it] 69%|██████▊ | 10311/15000 [47:46:19<22:05:40, 16.96s/it] 69%|██████▊ | 10312/15000 [47:46:34<21:12:27, 16.29s/it] 69%|██████▉ | 10313/15000 [47:46:49<20:3
warnings.warn("The dataset reached end and the iterator is reset to the start.")
9:20:36, 15.01s/it] 69%|██████▉ | 10362/15000 [48:00:16<19:15:55, 14.95s/it] 69%|██████▉ | 10363/15000 [48:00:31<19:09:19, 14.87s/it] 69%|██████▉ | 10364/15000 [48:01:01<25:12:32, 19.58s/it] 69%|██████▉ | 10365/15000 [48:01:16<23:15:17, 18.06s/it] 69%|██████▉ | 10366/15000 [48:01:30<21:54:33, 17.02s/it] 69%|██████▉ | 10367/15000 [48:01:45<21:02:39, 16.35s/it] 69%|██████▉ | 10368/15000 [48:02:00<20:24:55, 15.87s/it] 69%|██████▉ | 10369/15000 [48:02:15<19:53:53, 15.47s/it] 69%|██████▉ | 10370/15000 [48:02:29<19:34:20, 15.22s/it] 69%|██████▉ | 10371/15000 [48:02:44<19:19:03, 15.02s/it] 69%|██████▉ | 10372/15000 [48:02:58<19:10:56, 14.92s/it] 69%|██████▉ | 10373/15000 [48:03:13<19:00:42, 14.79s/it] 69%|██████▉ | 10374/15000 [48:03:28<18:56:12, 14.74s/it] 69%|██████▉ | 10375/150009:23:27, 15.05s/it] 69%|██████▉ | 10362/15000 [48:00:16<19:15:11, 14.94s/it] 69%|██████▉ | 10363/15000 [48:00:31<19:07:32, 14.85s/it] 69%|██████▉ | 10364/15000 [48:01:01<25:12:09, 19.57s/it] 69%|██████▉ | 10365/15000 [48:01:16<23:15:40, 18.07s/it] 69%|██████▉ | 10366/15000 [48:01:30<21:54:09, 17.02s/it] 69%|██████▉ | 10367/15000 [48:01:45<21:01:29, 16.34s/it] 69%|██████▉ | 10368/15000 [48:02:00<20:22:34, 15.84s/it] 69%|██████▉ | 10369/15000 [48:02:14<19:51:48, 15.44s/it] 69%|██████▉ | 10370/15000 [48:02:29<19:33:27, 15.21s/it] 69%|██████▉ | 10371/15000 [48:02:44<19:17:38, 15.01s/it] 69%|██████▉ | 10372/15000 [48:02:58<19:10:36, 14.92s/it] 69%|██████▉ | 10373/15000 [48:03:13<19:03:47, 14.83s/it] 69%|██████▉ | 10374/15000 [48:03:28<18:59:10, 14.78s/it] 69%|██████▉ | 10375/15000 69%|██████▉ | 10364/15000 [48:01:01<25:10:39, 19.55s/it] 69%|██████▉ | 10365/15000 [48:01:16<23:15:57, 18.07s/it] 69%|██████▉ | 10366/15000 [48:01:30<21:56:31, 17.05s/it] 69%|██████▉ | 10367/15000 [48:01:45<21:01:02, 16.33s/it] 69%|██████▉ | 10368/15000 [48:02:00<20:23:31, 15.85s/it] 69%|██████▉ | 10369/15000 [48:02:14<19:52:48, 15.45s/it] 69%|██████▉ | 10370/15000 [48:02:29<19:31:59, 15.19s/it] 69%|██████▉ | 10371/15000 [48:02:44<19:18:54, 15.02s/it] 69%|██████▉ | 10372/15000 [48:02:58<19:10:48, 14.92s/it] 69%|██████▉ | 10373/15000 [48:03:13<19:02:26, 14.81s/it] 69%|██████▉ | 10374/15000 [48:03:28<18:59:41, 14.78s/it] 69%|██████▉ | 10375/15000 [48:03:42<18:56:55, 14.75s/it] 69%|██████▉ | 10376/15000 [48:04:13<25:00:26, 19.47s/it] 69%|██████▉ | 10377/15000 [48:04:28<23:12:57 [48:03:42<18:54:49, 14.72s/it] 69%|██████▉ | 10376/15000 [48:04:13<25:01:48, 19.49s/it] 69%|██████▉ | 10377/15000 [48:04:27<23:10:43, 18.05s/it] 69%|██████▉ | 10378/15000 [48:04:42<21:56:44, 17.09s/it] 69%|██████▉ | 10379/15000 [48:04:57<21:00:13, 16.36s/it] 69%|██████▉ | 10380/15000 [48:05:12<20:18:09, 15.82s/it] 69%|██████▉ | 10381/15000 [48:05:26<19:52:37, 15.49s/it] 69%|██████▉ | 10382/15000 [48:05:41<19:33:47, 15.25s/it] 69%|██████▉ | 10383/15000 [48:05:56<19:19:37, 15.07s/it] 69%|██████▉ | 10384/15000 [48:06:10<19:10:17, 14.95s/it] 69%|██████▉ | 10385/15000 [48:06:25<19:04:24, 14.88s/it] 69%|██████▉ | 10386/15000 [48:06:40<18:57:42, 14.79s/it] 69%|██████▉ | 10387/15000 [48:07:16<27:17:57, 21.30s/it] 69%|██████▉ | 10388/15000 [48:07:31<24:46:57, 19.34s/it] 69%|██████▉
{'loss': 0.8282, 'learning_rate': 4.540035553258619e-05, 'epoch': 1.95}
{'loss': 0.8282, 'learning_rate': 4.540035553258619e-05, 'epoch': 1.95}
10389/15000 [48:07:45<22:55:03, 17.89s/it] 69%|██████▉ | 10390/15000 [48:08:00<21:41:48, 16.94s/it] 69%|██████▉ | 10391/15000 [48:08:15<20:46:22, 16.23s/it] 69%|██████▉ | 10392/15000 [48:08:29<20:09:23, 15.75s/it] 69%|██████▉ | 10393/15000 [48:08:44<19:47:06, 15.46s/it] 69%|██████▉ | 10394/15000 [48:08:59<19:27:34, 15.21s/it] 69%|██████▉ | 10395/15000 [48:09:13<19:15:23, 15.05s/it] 69%|██████▉ | 10396/15000 [48:09:28<19:08:06, 14.96s/it] 69%|██████▉ | 10397/15000 [48:09:43<19:01:11, 14.88s/it] 69%|██████▉ | 10398/15000 [48:10:19<27:20:30, 21.39s/it] 69%|██████▉ | 10399/15000 [48:10:34<24:46:19, 19.38s/it] 69%|██████▉ | 10400/15000 [48:10:49<22:56:31, 17.95s/it] 69%|██████▉ | 10400/15000 [48:10:49<22:56:31, 17.95s/it] 69%|██████▉ | 10389/15000 [48:07:46<22:58:23, 17.94s/it] 69%|██████▉ | 10390/15000 [48:08:00<21:38:52, 16.91s/it] 69%|██████▉ | 10391/15000 [48:08:15<20:46:53, 16.23s/it] 69%|██████▉ | 10392/15000 [48:08:29<20:12:42, 15.79s/it] 69%|██████▉ | 10393/15000 [48:08:44<19:46:42, 15.46s/it] 69%|██████▉ | 10394/15000 [48:08:59<19:28:14, 15.22s/it] 69%|██████▉ | 10395/15000 [48:09:13<19:15:25, 15.05s/it] 69%|██████▉ | 10396/15000 [48:09:28<19:06:14, 14.94s/it] 69%|██████▉ | 10397/15000 [48:09:43<19:01:13, 14.88s/it] 69%|██████▉ | 10398/15000 [48:10:19<27:20:25, 21.39s/it] 69%|██████▉ | 10399/15000 [48:10:34<24:44:48, 19.36s/it] 69%|██████▉ | 10400/15000 [48:10:49<22:57:54, 17.97s/it] 69%|██████▉ | 10400/15000 [48:10:49<22:57:54, 17.97s/it] 69%|██████▉ | :15<20:47:22, 16.24s/it] 69%|██████▉ | 10392/15000 [48:08:29<20:10:42, 15.76s/it] 69%|██████▉ | 10393/15000 [48:08:44<19:47:10, 15.46s/it] 69%|██████▉ | 10394/15000 [48:08:59<19:28:30, 15.22s/it] 69%|██████▉ | 10395/15000 [48:09:13<19:15:38, 15.06s/it] 69%|██████▉ | 10396/15000 [48:09:28<19:07:35, 14.96s/it] 69%|██████▉ | 10397/15000 [48:09:43<18:59:36, 14.85s/it] 69%|██████▉ | 10398/15000 [48:10:19<27:21:00, 21.40s/it] 69%|██████▉ | 10399/15000 [48:10:34<24:46:43, 19.39s/it] 69%|██████▉ | 10400/15000 [48:10:49<22:58:05, 17.98s/it] 69%|██████▉ | 10400/15000 [48:10:49<22:58:05, 17.98s/it] 69%|██████▉ | 10401/15000 [48:11:04<21:46:06, 17.04s/it] 69%|██████▉ | 10402/15000 [48:11:18<20:52:00, 16.34s/it] 69%|██████▉ | 10403/15000 [48:11:10401/15000 [48:11:04<21:46:28, 17.04s/it] 69%|██████▉ | 10402/15000 [48:11:18<20:53:48, 16.36s/it] 69%|██████▉ | 10403/15000 [48:11:33<20:15:06, 15.86s/it] 69%|██████▉ | 10404/15000 [48:11:48<19:48:46, 15.52s/it] 69%|██████▉ | 10405/15000 [48:12:02<19:28:10, 15.25s/it] 69%|██████▉ | 10406/15000 [48:12:17<19:11:47, 15.04s/it] 69%|██████▉ | 10407/15000 [48:12:32<19:05:23, 14.96s/it] 69%|██████▉ | 10408/15000 [48:12:46<18:55:07, 14.83s/it] 69%|██████▉ | 10409/15000 [48:13:01<18:50:15, 14.77s/it] 69%|██████▉ | 10410/15000 [48:13:38<27:11:51, 21.33s/it] 69%|██████▉ | 10411/15000 [48:13:52<24:37:47, 19.32s/it] 69%|██████▉ | 10412/15000 [48:14:07<22:51:37, 17.94s/it] 69%|██████▉ | 10413/15000 [48:14:22<21:34:58, 16.94s/it] 69%|██████▉ | 10414/15000 [48:14:36<20:40:40, 16.23s/it] 69%|████<E29688>
{'loss': 0.8007, 'learning_rate': 4.360429701490934e-05, 'epoch': 1.97}
{'loss': 0.8007, 'learning_rate': 4.360429701490934e-05, 'epoch': 1.97}
<EFBFBD><EFBFBD>▉ | 10498/15000 [48:37:44<18:40:34, 14.93s/it] 70%|██████▉ | 10499/15000 [48:37:59<18:33:22, 14.84s/it] 70%|███████ | 10500/15000 [48:38:35<26:48:37, 21.45s/it] 70%|███████ | 10500/15000 [48:38:36<26:48:37, 21.45s/it] 70%|███████ | 10501/15000 [48:38:50<24:20:50, 19.48s/it] 70%|███████ | 10502/15000 [48:39:05<22:33:48, 18.06s/it] 70%|███████ | 10503/15000 [48:39:20<21:17:32, 17.05s/it] 70%|███████ | 10504/15000 [48:39:34<20:21:01, 16.29s/it] 70%|███████ | 10505/15000 [48:39:49<19:44:42, 15.81s/it] 70%|███████ | 10506/15000 [48:40:04<19:20:37, 15.50s/it] 70%|███████ | 10507/15000 [48:40:18<18:59:09, 15.21s/it] 70%|███████ | 10508/15000 [48:40:33<18:47:12, 15.06s/it] 70%|███████ | 10509/15000 [48:40:48<18:40:57, 14.98s/it] 70%|█████▖<E29688>▉ | 10498/15000 [48:37:44<18:39:17, 14.92s/it] 70%|██████▉ | 10499/15000 [48:37:58<18:33:38, 14.85s/it] 70%|███████ | 10500/15000 [48:38:35<26:49:35, 21.46s/it] 70%|███████ | 10500/15000 [48:38:36<26:49:35, 21.46s/it] 70%|███████ | 10501/15000 [48:38:50<24:19:24, 19.46s/it] 70%|███████ | 10502/15000 [48:39:05<22:32:11, 18.04s/it] 70%|███████ | 10503/15000 [48:39:20<21:17:03, 17.04s/it] 70%|███████ | 10504/15000 [48:39:34<20:21:44, 16.30s/it] 70%|███████ | 10505/15000 [48:39:49<19:47:37, 15.85s/it] 70%|███████ | 10506/15000 [48:40:04<19:17:56, 15.46s/it] 70%|███████ | 10507/15000 [48:40:18<19:01:17, 15.24s/it] 70%|███████ | 10508/15000 [48:40:33<18:47:51, 15.06s/it] 70%|███████ | 10509/15000 [48:40:48<18:40:04, 14.96s/it] 70%|█████<E29688><E29688>00 [48:38:35<26:50:32, 21.47s/it] 70%|███████ | 10500/15000 [48:38:36<26:50:32, 21.47s/it] 70%|███████ | 10501/15000 [48:38:50<24:21:02, 19.48s/it] 70%|███████ | 10502/15000 [48:39:05<22:34:18, 18.07s/it] 70%|███████ | 10503/15000 [48:39:20<21:15:17, 17.02s/it] 70%|███████ | 10504/15000 [48:39:34<20:22:55, 16.32s/it] 70%|███████ | 10505/15000 [48:39:49<19:45:32, 15.82s/it] 70%|███████ | 10506/15000 [48:40:04<19:17:50, 15.46s/it] 70%|███████ | 10507/15000 [48:40:18<18:58:54, 15.21s/it] 70%|███████ | 10508/15000 [48:40:33<18:49:12, 15.08s/it] 70%|███████ | 10509/15000 [48:40:48<18:40:26, 14.97s/it] 70%|███████ | 10510/15000 [48:41:02<18:33:55, 14.89s/it] 70%|███████ | 10511/15000 [48:41:17<18:29:16, 14.83s/it] 70%|███████ | 10512/1500<30>█ | 10510/15000 [48:41:02<18:34:09, 14.89s/it] 70%|███████ | 10511/15000 [48:41:17<18:26:58, 14.80s/it] 70%|███████ | 10512/15000 [48:41:54<26:53:27, 21.57s/it] 70%|███████ | 10513/15000 [48:42:09<24:20:05, 19.52s/it] 70%|███████ | 10514/15000 [48:42:24<22:29:38, 18.05s/it] 70%|███████ | 10515/15000 [48:42:38<21:13:55, 17.04s/it] 70%|███████ | 10516/15000 [48:42:53<20:21:00, 16.34s/it] 70%|███████ | 10517/15000 [48:43:08<19:43:36, 15.84s/it] 70%|███████ | 10518/15000 [48:43:22<19:17:31, 15.50s/it] 70%|███████ | 10519/15000 [48:43:37<18:59:19, 15.26s/it] 70%|███████ | 10520/15000 [48:43:52<18:46:25, 15.09s/it] 70%|███████ | 10521/15000 [48:44:07<18:37:38, 14.97s/it] 70%|███████ | 10522/15000 [48:44:21<18:30:05, 14.87s/it] 70%|███████ | 10523/15000 [48:44:58<26:50:25, 21.58s/it] 70%|█<>
{'loss': 0.7967, 'learning_rate': 4.183452924271776e-05, 'epoch': 1.98}
{'loss': 0.7967, 'learning_rate': 4.183452924271776e-05, 'epoch': 1.98}
<EFBFBD><EFBFBD> | 10593/15000 [49:04:21<22:08:43, 18.09s/it] 71%|███████ | 10594/15000 [49:04:36<20:51:10, 17.04s/it] 71%|███████ | 10595/15000 [49:04:51<20:01:23, 16.36s/it] 71%|███████ | 10596/15000 [49:05:05<19:22:30, 15.84s/it] 71%|███████ | 10597/15000 [49:05:20<18:56:06, 15.48s/it] 71%|███████ | 10598/15000 [49:05:35<18:37:27, 15.23s/it] 71%|███████ | 10599/15000 [49:05:49<18:24:22, 15.06s/it] 71%|███████ | 10600/15000 [49:06:04<18:17:40, 14.97s/it] 71%|███████ | 10600/15000 [49:06:04<18:17:40, 14.97s/it] 71%|███████ | 10601/15000 [49:06:19<18:13:10, 14.91s/it] 71%|███████ | 10602/15000 [49:06:34<18:08:28, 14.85s/it] 71%|███████ | 10603/15000 [49:07:11<26:17:59, 21.53s/it] 71%|███████ | 10604/15000 [49:07:25<23:47:30, 19.48s/it] 71%|██████▖<E29688> | 10593/15000 [49:04:21<22:07:01, 18.07s/it] 71%|███████ | 10594/15000 [49:04:36<20:51:25, 17.04s/it] 71%|███████ | 10595/15000 [49:04:51<20:01:12, 16.36s/it] 71%|███████ | 10596/15000 [49:05:05<19:21:35, 15.83s/it] 71%|███████ | 10597/15000 [49:05:20<18:57:11, 15.50s/it] 71%|███████ | 10598/15000 [49:05:35<18:39:54, 15.26s/it] 71%|███████ | 10599/15000 [49:05:49<18:24:55, 15.06s/it] 71%|███████ | 10600/15000 [49:06:04<18:16:40, 14.95s/it] 71%|███████ | 10600/15000 [49:06:04<18:16:40, 14.95s/it] 71%|███████ | 10601/15000 [49:06:19<18:11:35, 14.89s/it] 71%|███████ | 10602/15000 [49:06:34<18:08:49, 14.85s/it] 71%|███████ | 10603/15000 [49:07:11<26:17:16, 21.52s/it] 71%|███████ | 10604/15000 [49:07:25<23:48:47, 19.50s/it] 71%|██████<E29688><E29688>[49:04:51<19:59:14, 16.33s/it] 71%|███████ | 10596/15000 [49:05:05<19:22:27, 15.84s/it] 71%|███████ | 10597/15000 [49:05:20<18:57:43, 15.50s/it] 71%|███████ | 10598/15000 [49:05:35<18:37:24, 15.23s/it] 71%|███████ | 10599/15000 [49:05:49<18:26:26, 15.08s/it] 71%|███████ | 10600/15000 [49:06:04<18:15:47, 14.94s/it] 71%|███████ | 10600/15000 [49:06:04<18:15:47, 14.94s/it] 71%|███████ | 10601/15000 [49:06:19<18:14:18, 14.93s/it] 71%|███████ | 10602/15000 [49:06:33<18:06:35, 14.82s/it] 71%|███████ | 10603/15000 [49:07:11<26:17:43, 21.53s/it] 71%|███████ | 10604/15000 [49:07:25<23:48:48, 19.50s/it] 71%|███████ | 10605/15000 [49:07:40<22:02:25, 18.05s/it] 71%|███████ | 10606/15000 [49:07:55<20:46:44, 17.02s/it] 71%|███████ | 10607/15000 [<5B> | 10605/15000 [49:07:40<22:03:28, 18.07s/it] 71%|███████ | 10606/15000 [49:07:55<20:47:37, 17.04s/it] 71%|███████ | 10607/15000 [49:08:09<19:55:25, 16.33s/it] 71%|███████ | 10608/15000 [49:08:24<19:15:09, 15.78s/it] 71%|███████ | 10609/15000 [49:08:39<18:50:13, 15.44s/it] 71%|███████ | 10610/15000 [49:08:53<18:36:01, 15.25s/it] 71%|███████ | 10611/15000 [49:09:08<18:23:08, 15.08s/it] 71%|███████ | 10612/15000 [49:09:23<18:13:55, 14.96s/it] 71%|███████ | 10613/15000 [49:09:37<18:04:50, 14.84s/it] 71%|███████ | 10614/15000 [49:10:14<26:10:19, 21.48s/it] 71%|███████ | 10615/15000 [49:10:29<23:39:11, 19.42s/it] 71%|███████ | 10616/15000 [49:10:44<21:55:20, 18.00s/it] 71%|███████ | 10617/15000 [49:10:58<20:40:58, 16.99s/it] 71%|███████ | 10618/15000 [49:11:13<19:48:21, 16.27s/it] 71%|██<E29688>
<EFBFBD><EFBFBD> | 10688/15000 [49:30:36<18:32:46, 15.48s/it] 71%|███████▏ | 10689/15000 [49:30:50<18:12:44, 15.21s/it] 71%|███████▏ | 10690/15000 [49:31:05<17:58:44, 15.02s/it] 71%|███████▏ | 10691/15000 [49:31:19<17:51:14, 14.92s/it] 71%|███████▏ | 10692/15000 [49:31:34<17:48:30, 14.88s/it] 71%|███████▏ | 10693/15000 [49:31:49<17:43:05, 14.81s/it] 71%|███████▏ | 10694/15000 [49:32:26<25:41:50, 21.48s/it] 71%|███████▏ | 10695/15000 [49:32:41<23:15:05, 19.44s/it] 71%|███████▏ | 10696/15000 [49:32:55<21:32:13, 18.01s/it] 71%|███████▏ | 10697/15000 [49:33:10<20:22:26, 17.05s/it] 71%|███████▏ | 10698/15000 [49:33:25<19:32:07, 16.35s/it] 71%|███████▏ | 10699/15000 [49:33:39<18:55:07, 15.84s/it] 71%|███████▏ | 10700/15000 [49:33:54<18:30:42, 15.50s/it] 7{'loss': 0.7962, 'learning_rate': 4.009187725252309e-05, 'epoch': 2.0}
{'loss': 0.7962, 'learning_rate': 4.009187725252309e-05, 'epoch': 2.0}
<EFBFBD><EFBFBD> | 10688/15000 [49:30:36<18:32:02, 15.47s/it] 71%|███████▏ | 10689/15000 [49:30:50<18:13:50, 15.22s/it] 71%|███████▏ | 10690/15000 [49:31:05<18:00:46, 15.05s/it] 71%|███████▏ | 10691/15000 [49:31:19<17:50:32, 14.91s/it] 71%|███████▏ | 10692/15000 [49:31:34<17:48:13, 14.88s/it] 71%|███████▏ | 10693/15000 [49:31:49<17:45:19, 14.84s/it] 71%|███████▏ | 10694/15000 [49:32:26<25:41:12, 21.48s/it] 71%|███████▏ | 10695/15000 [49:32:41<23:16:42, 19.47s/it] 71%|███████▏ | 10696/15000 [49:32:55<21:31:57, 18.01s/it] 71%|███████▏ | 10697/15000 [49:33:10<20:20:18, 17.02s/it] 71%|███████▏ | 10698/15000 [49:33:25<19:31:12, 16.33s/it] 71%|███████▏ | 10699/15000 [49:33:39<18:55:29, 15.84s/it] 71%|███████▏ | 10700/15000 [49:33:54<18:30:15, 15.49s/it] 700 [49:31:05<18:00:07, 15.04s/it] 71%|███████▏ | 10691/15000 [49:31:20<17:53:49, 14.95s/it] 71%|███████▏ | 10692/15000 [49:31:34<17:48:11, 14.88s/it] 71%|███████▏ | 10693/15000 [49:31:49<17:42:33, 14.80s/it] 71%|███████▏ | 10694/15000 [49:32:26<25:43:05, 21.50s/it] 71%|███████▏ | 10695/15000 [49:32:41<23:15:41, 19.45s/it] 71%|███████▏ | 10696/15000 [49:32:55<21:32:19, 18.02s/it] 71%|███████▏ | 10697/15000 [49:33:10<20:22:28, 17.05s/it] 71%|███████▏ | 10698/15000 [49:33:25<19:30:35, 16.33s/it] 71%|███████▏ | 10699/15000 [49:33:39<18:54:13, 15.82s/it] 71%|███████▏ | 10700/15000 [49:33:54<18:29:53, 15.49s/it] 71%|███████▏ | 10700/15000 [49:33:54<18:29:53, 15.49s/it] 71%|███████▏ | 10701/15000 [49:34:09<18:15:38, 15.29s/it] 71%|████1%|███████▏ | 10700/15000 [49:33:54<18:30:15, 15.49s/it] 71%|███████▏ | 10701/15000 [49:34:09<18:14:03, 15.27s/it] 71%|███████▏ | 10702/15000 [49:34:24<18:02:24, 15.11s/it] 71%|███████▏ | 10703/15000 [49:34:38<17:50:10, 14.94s/it] 71%|███████▏ | 10704/15000 [49:34:53<17:44:49, 14.87s/it] 71%|███████▏ | 10705/15000 [49:35:30<25:37:25, 21.48s/it] 71%|███████▏ | 10706/15000 [49:35:44<23:10:45, 19.43s/it] 71%|███████▏ | 10707/15000 [49:35:59<21:29:44, 18.03s/it] 71%|███████▏ | 10708/15000 [49:36:14<20:15:10, 16.99s/it] 71%|███████▏ | 10709/15000 [49:36:28<19:26:53, 16.32s/it] 71%|███████▏ | 10710/15000 [49:36:43<18:53:08, 15.85s/it] 71%|███████▏ | 10711/15000 [49:36:58<18:27:23, 15.49s/it] 71%|███████▏ | 10712/15000 [49:37:13<18:12:57, 15.29s/it] 71%|███████▏ | 107131%|███████▏ | 10700/15000 [49:33:54<18:30:42, 15.50s/it] 71%|███████▏ | 10701/15000 [49:34:09<18:15:56, 15.30s/it] 71%|███████▏ | 10702/15000 [49:34:24<18:02:47, 15.12s/it] 71%|███████▏ | 10703/15000 [49:34:38<17:49:14, 14.93s/it] 71%|███████▏ | 10704/15000 [49:34:53<17:43:21, 14.85s/it] 71%|███████▏ | 10705/15000 [49:35:30<25:39:14, 21.50s/it] 71%|███████▏ | 10706/15000 [49:35:44<23:08:50, 19.41s/it] 71%|███████▏ | 10707/15000 [49:35:59<21:28:11, 18.00s/it] 71%|███████▏ | 10708/15000 [49:36:14<20:15:15, 16.99s/it] 71%|███████▏ | 10709/15000 [49:36:29<19:29:11, 16.35s/it] 71%|███████▏ | 10710/15000 [49:36:43<18:52:54, 15.84s/it] 71%|███████▏ | 10711/15000 [49:36:58<18:29:15, 15.52s/it] 71%|███████▏ | 10712/15000 [49:37:13<18:08:34, 15.23s/it] 71%|███████▏ | 1071
{'loss': 0.7933, 'learning_rate': 3.8377153439907266e-05, 'epoch': 2.02}
{'loss': 0.7933, 'learning_rate': 3.8377153439907266e-05, 'epoch': 2.02}
▏ | 10794/15000 [49:59:52<17:21:23, 14.86s/it] 72%|███████▏ | 10795/15000 [50:00:07<17:19:51, 14.84s/it] 72%|███████▏ | 10796/15000 [50:00:44<25:09:57, 21.55s/it] 72%|███████▏ | 10797/15000 [50:00:59<22:45:56, 19.50s/it] 72%|███████▏ | 10798/15000 [50:01:14<21:06:17, 18.08s/it] 72%|███████▏ | 10799/15000 [50:01:28<19:54:29, 17.06s/it] 72%|███████▏ | 10800/15000 [50:01:43<19:03:36, 16.34s/it] 72%|███████▏ | 10800/15000 [50:01:43<19:03:36, 16.34s/it] 72%|███████▏ | 10801/15000 [50:01:58<18:34:38, 15.93s/it] 72%|███████▏ | 10802/15000 [50:02:13<18:09:32, 15.57s/it] 72%|███████▏ | 10803/15000 [50:02:27<17:51:14, 15.31s/it] 72%|███████▏ | 10804/15000 [50:02:42<17:38:39, 15.14s/it] 72%|███████▏ | 10805/15000 [50:02:57<17:25:33, 14.95s/it] ▏ | 10794/15000 [49:59:52<17:23:01, 14.88s/it] 72%|███████▏ | 10795/15000 [50:00:07<17:20:17, 14.84s/it] 72%|███████▏ | 10796/15000 [50:00:44<25:09:40, 21.55s/it] 72%|███████▏ | 10797/15000 [50:00:59<22:46:30, 19.51s/it] 72%|███████▏ | 10798/15000 [50:01:14<21:06:55, 18.09s/it] 72%|███████▏ | 10799/15000 [50:01:28<19:52:54, 17.04s/it] 72%|███████▏ | 10800/15000 [50:01:43<19:04:03, 16.34s/it] 72%|███████▏ | 10800/15000 [50:01:43<19:04:03, 16.34s/it] 72%|███████▏ | 10801/15000 [50:01:58<18:32:56, 15.90s/it] 72%|███████▏ | 10802/15000 [50:02:13<18:09:14, 15.57s/it] 72%|███████▏ | 10803/15000 [50:02:27<17:51:47, 15.32s/it] 72%|███████▏ | 10804/15000 [50:02:42<17:36:56, 15.11s/it] 72%|███████▏ | 10805/15000 [50:02:57<17:27:34, 14.98s/it] 000 [50:00:44<25:11:13, 21.57s/it] 72%|███████▏ | 10797/15000 [50:00:59<22:47:24, 19.52s/it] 72%|███████▏ | 10798/15000 [50:01:13<21:04:15, 18.05s/it] 72%|███████▏ | 10799/15000 [50:01:28<19:52:23, 17.03s/it] 72%|███████▏ | 10800/15000 [50:01:43<19:04:35, 16.35s/it] 72%|███████▏ | 10800/15000 [50:01:43<19:04:35, 16.35s/it] 72%|███████▏ | 10801/15000 [50:01:58<18:35:40, 15.94s/it] 72%|███████▏ | 10802/15000 [50:02:13<18:10:16, 15.58s/it] 72%|███████▏ | 10803/15000 [50:02:27<17:51:08, 15.31s/it] 72%|███████▏ | 10804/15000 [50:02:42<17:35:54, 15.10s/it] 72%|███████▏ | 10805/15000 [50:02:57<17:26:20, 14.97s/it] 72%|███████▏ | 10806/15000 [50:03:11<17:22:01, 14.91s/it] 72%|███████▏ | 10807/15000 [50:03:49<25:12:47, 21.65s/it] 72%|███<E29688><E29688>72%|███████▏ | 10806/15000 [50:03:11<17:19:26, 14.87s/it] 72%|███████▏ | 10807/15000 [50:03:49<25:11:52, 21.63s/it] 72%|███████▏ | 10808/15000 [50:04:03<22:46:54, 19.56s/it] 72%|███████▏ | 10809/15000 [50:04:18<21:01:11, 18.06s/it] 72%|███████▏ | 10810/15000 [50:04:33<19:49:01, 17.03s/it] 72%|███████▏ | 10811/15000 [50:04:47<18:58:54, 16.31s/it] 72%|███████▏ | 10812/15000 [50:05:02<18:24:05, 15.82s/it] 72%|███████▏ | 10813/15000 [50:05:17<17:59:15, 15.47s/it] 72%|███████▏ | 10814/15000 [50:05:31<17:38:45, 15.18s/it] 72%|███████▏ | 10815/15000 [50:05:46<17:28:56, 15.04s/it] 72%|███████▏ | 10816/15000 [50:06:00<17:20:35, 14.92s/it] 72%|███████▏ | 10817/15000 [50:06:15<17:19:20, 14.91s/it] 72%|███████▏ | 10818/15000 [50:06:30<17:10:47, 14.79s/it] 72%|███████▏ | 108
{'loss': 0.797, 'learning_rate': 3.669115718079702e-05, 'epoch': 2.04}
{'loss': 0.797, 'learning_rate': 3.669115718079702e-05, 'epoch': 2.04}
|███████▎ | 10889/15000 [50:26:28<20:34:41, 18.02s/it] 73%|███████▎ | 10890/15000 [50:26:42<19:24:44, 17.00s/it] 73%|███████▎ | 10891/15000 [50:26:57<18:33:59, 16.27s/it] 73%|███████▎ | 10892/15000 [50:27:12<18:01:15, 15.79s/it] 73%|███████▎ | 10893/15000 [50:27:26<17:35:59, 15.43s/it] 73%|███████▎ | 10894/15000 [50:27:41<17:19:44, 15.19s/it] 73%|███████▎ | 10895/15000 [50:27:56<17:09:48, 15.05s/it] 73%|███████▎ | 10896/15000 [50:28:10<16:59:23, 14.90s/it] 73%|███████▎ | 10897/15000 [50:28:25<16:55:02, 14.84s/it] 73%|███████▎ | 10898/15000 [50:29:02<24:34:40, 21.57s/it] 73%|███████▎ | 10899/15000 [50:29:17<22:14:20, 19.52s/it] 73%|███████▎ | 10900/15000 [50:29:32<20:35:42, 18.08s/it] 73%|███████▎ | 10900/15000 [50:29:32<<3C>▎ | 10900/15000 [50:29:32<20:34:55, 18.07s/it] 73%|███████▎ | 10900/15000 [50:29:32<20:34:55, 18.07s/it] 73%|███████▎ | 10901/15000 [50:29:47<19:30:48, 17.14s/it] 73%|███████▎ | 10902/15000 [50:30:01<18:42:11, 16.43s/it] 73%|███████▎ | 10903/15000 [50:30:16<18:02:14, 15.85s/it] 73%|███████▎ | 10904/15000 [50:30:31<17:37:52, 15.50s/it] 73%|███████▎ | 10905/15000 [50:30:45<17:18:51, 15.22s/it] 73%|███████▎ | 10906/15000 [50:31:00<17:07:25, 15.06s/it] 73%|███████▎ | 10907/15000 [50:31:14<16:55:37, 14.89s/it] 73%|███████▎ | 10908/15000 [50:31:29<16:51:21, 14.83s/it] 73%|███████▎ | 10909/15000 [50:32:06<24:28:54, 21.54s/it] 73%|███████▎ | 10910/15000 [50:32:21<22:10:18, 19.52s/it] 73%|███████▎ | 10911/15000 [50:32:36<20:28:44, 18.03s/it] <0A>▎ | 10900/15000 [50:29:32<20:35:22, 18.08s/it] 73%|███████▎ | 10900/15000 [50:29:32<20:35:22, 18.08s/it] 73%|███████▎ | 10901/15000 [50:29:47<19:31:30, 17.15s/it] 73%|███████▎ | 10902/15000 [50:30:01<18:39:40, 16.39s/it] 73%|███████▎ | 10903/15000 [50:30:16<18:05:35, 15.90s/it] 73%|███████▎ | 10904/15000 [50:30:31<17:37:28, 15.49s/it] 73%|███████▎ | 10905/15000 [50:30:45<17:16:50, 15.19s/it] 73%|███████▎ | 10906/15000 [50:31:00<17:06:55, 15.05s/it] 73%|███████▎ | 10907/15000 [50:31:14<16:57:00, 14.91s/it] 73%|███████▎ | 10908/15000 [50:31:29<16:50:24, 14.82s/it] 73%|███████▎ | 10909/15000 [50:32:06<24:28:27, 21.54s/it] 73%|███████▎ | 10910/15000 [50:32:21<22:09:51, 19.51s/it] 73%|███████▎ | 10911/15000 [50:32:36<20:27:25, 18.01s/it] 20:35:42, 18.08s/it] 73%|███████▎ | 10901/15000 [50:29:47<19:30:23, 17.13s/it] 73%|███████▎ | 10902/15000 [50:30:01<18:40:43, 16.41s/it] 73%|███████▎ | 10903/15000 [50:30:16<18:01:57, 15.85s/it] 73%|███████▎ | 10904/15000 [50:30:31<17:37:49, 15.50s/it] 73%|███████▎ | 10905/15000 [50:30:45<17:18:47, 15.22s/it] 73%|███████▎ | 10906/15000 [50:31:00<17:05:36, 15.03s/it] 73%|███████▎ | 10907/15000 [50:31:14<16:56:29, 14.90s/it] 73%|███████▎ | 10908/15000 [50:31:29<16:51:07, 14.83s/it] 73%|███████▎ | 10909/15000 [50:32:06<24:28:40, 21.54s/it] 73%|███████▎ | 10910/15000 [50:32:21<22:09:22, 19.50s/it] 73%|███████▎ | 10911/15000 [50:32:36<20:29:34, 18.04s/it] 73%|███████▎ | 10912/15000 [50:32:50<19:21:00, 17.04s/it] 73%|███████▎ | 10913/15000 [50:33:05<18:31:22, 16.32s/it] 73%|███
{'loss': 0.7939, 'learning_rate': 3.503467445880789e-05, 'epoch': 2.06}
{'loss': 0.7939, 'learning_rate': 3.503467445880789e-05, 'epoch': 2.06}
17.04s/it] 73%|███████▎ | 10993/15000 [50:55:16<18:08:51, 16.30s/it] 73%|███████▎ | 10994/15000 [50:55:31<17:37:07, 15.83s/it] 73%|███████▎ | 10995/15000 [50:55:45<17:11:46, 15.46s/it] 73%|███████▎ | 10996/15000 [50:56:00<16:56:22, 15.23s/it] 73%|███████▎ | 10997/15000 [50:56:14<16:44:11, 15.05s/it] 73%|███████▎ | 10998/15000 [50:56:29<16:37:46, 14.96s/it] 73%|███████▎ | 10999/15000 [50:56:44<16:30:26, 14.85s/it] 73%|███████▎ | 11000/15000 [50:57:21<24:02:24, 21.64s/it] 73%|███████▎ | 11000/15000 [50:57:21<24:02:24, 21.64s/it] 73%|███████▎ | 11001/15000 [50:57:36<21:44:34, 19.57s/it] 73%|███████▎ | 11002/15000 [50:57:51<20:06:05, 18.10s/it] 73%|███████▎ | 11003/15000 [50:58:05<18:53:52, 17.02s/it] 73%|███████▎ | 11004/ 17.05s/it] 73%|███████▎ | 10993/15000 [50:55:16<18:09:33, 16.31s/it] 73%|███████▎ | 10994/15000 [50:55:31<17:37:06, 15.83s/it] 73%|███████▎ | 10995/15000 [50:55:45<17:11:19, 15.45s/it] 73%|███████▎ | 10996/15000 [50:56:00<16:55:56, 15.22s/it] 73%|███████▎ | 10997/15000 [50:56:15<16:46:09, 15.08s/it] 73%|███████▎ | 10998/15000 [50:56:29<16:37:01, 14.95s/it] 73%|███████▎ | 10999/15000 [50:56:44<16:30:22, 14.85s/it] 73%|███████▎ | 11000/15000 [50:57:21<24:00:51, 21.61s/it] 73%|███████▎ | 11000/15000 [50:57:21<24:00:51, 21.61s/it] 73%|███████▎ | 11001/15000 [50:57:36<21:41:54, 19.53s/it] 73%|███████▎ | 11002/15000 [50:57:51<20:06:55, 18.11s/it] 73%|███████▎ | 11003/15000 [50:58:05<18:55:35, 17.05s/it] 73%|███████▎ | 11004/%|███████▎ | 10995/15000 [50:55:45<17:12:02, 15.46s/it] 73%|███████▎ | 10996/15000 [50:56:00<16:57:23, 15.25s/it] 73%|███████▎ | 10997/15000 [50:56:14<16:44:41, 15.06s/it] 73%|███████▎ | 10998/15000 [50:56:29<16:36:37, 14.94s/it] 73%|███████▎ | 10999/15000 [50:56:44<16:32:08, 14.88s/it] 73%|███████▎ | 11000/15000 [50:57:21<24:00:07, 21.60s/it] 73%|███████▎ | 11000/15000 [50:57:21<24:00:07, 21.60s/it] 73%|███████▎ | 11001/15000 [50:57:36<21:44:22, 19.57s/it] 73%|███████▎ | 11002/15000 [50:57:51<20:04:28, 18.08s/it] 73%|███████▎ | 11003/15000 [50:58:05<18:54:02, 17.02s/it] 73%|███████▎ | 11004/15000 [50:58:20<18:05:49, 16.30s/it] 73%|███████▎ | 11005/15000 [50:58:34<17:31:45, 15.80s/it] 73%|███████▎ | 11006/15000 [50:58:4915000 [50:58:20<18:06:47, 16.32s/it] 73%|███████▎ | 11005/15000 [50:58:34<17:30:06, 15.77s/it] 73%|███████▎ | 11006/15000 [50:58:49<17:09:33, 15.47s/it] 73%|███████▎ | 11007/15000 [50:59:04<16:53:03, 15.22s/it] 73%|███████▎ | 11008/15000 [50:59:18<16:39:51, 15.03s/it] 73%|███████▎ | 11009/15000 [50:59:33<16:35:05, 14.96s/it] 73%|███████▎ | 11010/15000 [50:59:48<16:28:42, 14.87s/it] 73%|███████▎ | 11011/15000 [51:00:03<16:25:55, 14.83s/it] 73%|███████▎ | 11012/15000 [51:00:40<23:51:30, 21.54s/it] 73%|███████▎ | 11013/15000 [51:00:55<21:36:08, 19.51s/it] 73%|███████▎ | 11014/15000 [51:01:09<19:58:30, 18.04s/it] 73%|███████▎ | 11015/15000 [51:01:24<18:49:03, 17.00s/it] 73%|███████▎ | 11016/15000 [51:01:38<18:03:17, 16.31s/it] 73%|███████▎ | 11017/15000 [51:01:53<17:30:25, 15.82s/it
{'loss': 0.7925, 'learning_rate': 3.340847749883191e-05, 'epoch': 2.08}
{'loss': 0.7925, 'learning_rate': 3.340847749883191e-05, 'epoch': 2.08}
00 [51:21:15<16:32:28, 15.22s/it] 74%|███████▍ | 11088/15000 [51:21:30<16:18:48, 15.01s/it] 74%|███████▍ | 11089/15000 [51:21:44<16:11:31, 14.90s/it] 74%|███████▍ | 11090/15000 [51:21:59<16:04:56, 14.81s/it] 74%|███████▍ | 11091/15000 [51:22:36<23:21:37, 21.51s/it] 74%|███████▍ | 11092/15000 [51:22:51<21:07:13, 19.46s/it] 74%|███████▍ | 11093/15000 [51:23:05<19:32:47, 18.01s/it] 74%|███████▍ | 11094/15000 [51:23:20<18:27:54, 17.02s/it] 74%|███████▍ | 11095/15000 [51:23:35<17:42:11, 16.32s/it] 74%|███████▍ | 11096/15000 [51:23:49<17:08:30, 15.81s/it] 74%|███████▍ | 11097/15000 [51:24:04<16:45:14, 15.45s/it] 74%|███████▍ | 11098/15000 [51:24:19<16:29:50, 15.22s/it] 74%|███████▍ | 11099/15000 [51:24:33<16:17:53, 15.04s/it] 74%|███████▍ | 11100/15000 [51:24:48<16:09:50, 14.92s/it] , 15.21s/it] 74%|███████▍ | 11099/15000 [51:24:33<16:17:53, 15.04s/it] 74%|███████▍ | 11100/15000 [51:24:48<16:10:57, 14.94s/it] 74%|███████▍ | 11100/15000 [51:24:48<16:10:57, 14.94s/it] 74%|███████▍ | 11101/15000 [51:25:03<16:07:58, 14.90s/it] 74%|███████▍ | 11102/15000 [51:25:17<16:02:17, 14.81s/it] 74%|███████▍ | 11103/15000 [51:25:54<23:12:34, 21.44s/it] 74%|███████▍ | 11104/15000 [51:26:09<21:01:30, 19.43s/it] 74%|███████▍ | 11105/15000 [51:26:24<19:31:06, 18.04s/it] 74%|███████▍ | 11106/15000 [51:26:39<18:25:38, 17.04s/it] 74%|███████▍ | 11107/15000 [51:26:53<17:37:26, 16.30s/it] 74%|███████▍ | 11108/15000 [51:27:08<17:06:26, 15.82s/it] 74%|███████▍ | 11109/15000 [51:27:22<16:42:55, 15.47s/it] 74%|███████▍ | 11110, 15.18s/it] 74%|███████▍ | 11099/15000 [51:24:33<16:18:22, 15.05s/it] 74%|███████▍ | 11100/15000 [51:24:48<16:09:51, 14.92s/it] 74%|███████▍ | 11100/15000 [51:24:48<16:09:51, 14.92s/it] 74%|███████▍ | 11101/15000 [51:25:03<16:08:54, 14.91s/it] 74%|███████▍ | 11102/15000 [51:25:17<16:00:31, 14.78s/it] 74%|███████▍ | 11103/15000 [51:25:54<23:11:55, 21.43s/it] 74%|███████▍ | 11104/15000 [51:26:09<21:03:04, 19.45s/it] 74%|███████▍ | 11105/15000 [51:26:24<19:27:35, 17.99s/it] 74%|███████▍ | 11106/15000 [51:26:39<18:26:47, 17.05s/it] 74%|███████▍ | 11107/15000 [51:26:53<17:37:18, 16.30s/it] 74%|███████▍ | 11108/15000 [51:27:08<17:07:48, 15.84s/it] 74%|███████▍ | 11109/15000 [51:27:23<16:43:08, 15.47s/it] 74%|███████▍ | 11110 74%|███████▍ | 11100/15000 [51:24:48<16:09:50, 14.92s/it] 74%|███████▍ | 11101/15000 [51:25:03<16:07:28, 14.89s/it] 74%|███████▍ | 11102/15000 [51:25:17<16:02:29, 14.82s/it] 74%|███████▍ | 11103/15000 [51:25:54<23:14:28, 21.47s/it] 74%|███████▍ | 11104/15000 [51:26:09<21:01:33, 19.43s/it] 74%|███████▍ | 11105/15000 [51:26:24<19:29:44, 18.02s/it] 74%|███████▍ | 11106/15000 [51:26:38<18:24:02, 17.01s/it] 74%|███████▍ | 11107/15000 [51:26:53<17:38:45, 16.32s/it] 74%|███████▍ | 11108/15000 [51:27:08<17:06:02, 15.82s/it] 74%|███████▍ | 11109/15000 [51:27:23<16:45:05, 15.50s/it] 74%|███████▍ | 11110/15000 [51:27:37<16:29:50, 15.27s/it] 74%|███████▍ | 11111/15000 [51:27:52<16:17:28, 15.08s/it] 74%|███████▍ | 11112/15000 [51:28:
{'loss': 0.7934, 'learning_rate': 3.1813324407038825e-05, 'epoch': 2.1}
{'loss': 0.7934, 'learning_rate': 3.1813324407038825e-05, 'epoch': 2.1}
▍ | 11191/15000 [51:50:03<15:49:46, 14.96s/it] 75%|███████▍ | 11192/15000 [51:50:18<15:43:18, 14.86s/it] 75%|███████▍ | 11193/15000 [51:50:32<15:40:32, 14.82s/it] 75%|███████▍ | 11194/15000 [51:51:10<22:50:21, 21.60s/it] 75%|███████▍ | 11195/15000 [51:51:24<20:36:59, 19.51s/it] 75%|███████▍ | 11196/15000 [51:51:39<19:03:19, 18.03s/it] 75%|███████▍ | 11197/15000 [51:51:54<17:58:19, 17.01s/it] 75%|███████▍ | 11198/15000 [51:52:08<17:12:08, 16.29s/it] 75%|███████▍ | 11199/15000 [51:52:23<16:42:24, 15.82s/it] 75%|███████▍ | 11200/15000 [51:52:38<16:20:09, 15.48s/it] 75%|███████▍ | 11200/15000 [51:52:38<16:20:09, 15.48s/it] 75%|███████▍ | 11201/15000 [51:52:53<16:07:13, 15.28s/it] 75%|███████▍ | 11202/15000 [51:53:07<15:55:07, 15.09s/it] ▍ | 11191/15000 [51:50:03<15:52:06, 15.00s/it] 75%|███████▍ | 11192/15000 [51:50:18<15:43:51, 14.87s/it] 75%|███████▍ | 11193/15000 [51:50:33<15:41:24, 14.84s/it] 75%|███████▍ | 11194/15000 [51:51:10<22:46:44, 21.55s/it] 75%|███████▍ | 11195/15000 [51:51:24<20:35:58, 19.49s/it] 75%|███████▍ | 11196/15000 [51:51:39<19:02:25, 18.02s/it] 75%|███████▍ | 11197/15000 [51:51:54<17:57:15, 17.00s/it] 75%|███████▍ | 11198/15000 [51:52:08<17:14:35, 16.33s/it] 75%|███████▍ | 11199/15000 [51:52:23<16:40:58, 15.80s/it] 75%|███████▍ | 11200/15000 [51:52:38<16:19:53, 15.47s/it] 75%|███████▍ | 11200/15000 [51:52:38<16:19:53, 15.47s/it] 75%|███████▍ | 11201/15000 [51:52:53<16:09:06, 15.31s/it] 75%|███████▍ | 11202/15000 [51:53:07<15:57:00, 15.12s/it] 000 [51:50:32<15:40:25, 14.82s/it] 75%|███████▍ | 11194/15000 [51:51:10<22:46:29, 21.54s/it] 75%|███████▍ | 11195/15000 [51:51:24<20:34:37, 19.47s/it] 75%|███████▍ | 11196/15000 [51:51:39<19:02:18, 18.02s/it] 75%|███████▍ | 11197/15000 [51:51:54<17:59:39, 17.03s/it] 75%|███████▍ | 11198/15000 [51:52:08<17:13:42, 16.31s/it] 75%|███████▍ | 11199/15000 [51:52:23<16:42:45, 15.83s/it] 75%|███████▍ | 11200/15000 [51:52:38<16:21:11, 15.49s/it] 75%|███████▍ | 11200/15000 [51:52:38<16:21:11, 15.49s/it] 75%|███████▍ | 11201/15000 [51:52:52<16:07:12, 15.28s/it] 75%|███████▍ | 11202/15000 [51:53:07<15:55:43, 15.10s/it] 75%|███████▍ | 11203/15000 [51:53:22<15:46:38, 14.96s/it] 75%|███████▍ | 11204/15000 [51:53:36<15:39:42, 14.85s/it] 75%|███<E29688><E29688>75%|███████▍ | 11203/15000 [51:53:22<15:46:25, 14.96s/it] 75%|███████▍ | 11204/15000 [51:53:36<15:40:02, 14.86s/it] 75%|███████▍ | 11205/15000 [51:54:14<22:49:43, 21.66s/it] 75%|███████▍ | 11206/15000 [51:54:29<20:35:47, 19.54s/it] 75%|███████▍ | 11207/15000 [51:54:43<19:03:05, 18.08s/it] 75%|███████▍ | 11208/15000 [51:54:58<17:57:04, 17.04s/it] 75%|███████▍ | 11209/15000 [51:55:13<17:11:58, 16.33s/it] 75%|███████▍ | 11210/15000 [51:55:27<16:38:59, 15.82s/it] 75%|███████▍ | 11211/15000 [51:55:42<16:17:19, 15.48s/it] 75%|███████▍ | 11212/15000 [51:55:56<16:00:24, 15.21s/it] 75%|███████▍ | 11213/15000 [51:56:11<15:49:49, 15.05s/it] 75%|███████▍ | 11214/15000 [51:56:26<15:42:15, 14.93s/it] 75%|███████▍ | 11215/15000 [51:56:40<15:37:35, 14.86s/it] 75%|███████▍ | 112
{'loss': 0.7916, 'learning_rate': 3.0249958817459722e-05, 'epoch': 2.11}
{'loss': 0.7916, 'learning_rate': 3.0249958817459722e-05, 'epoch': 2.11}
<EFBFBD>▌ | 11297/15000 [52:19:44<20:08:50, 19.59s/it] 75%|███████▌ | 11298/15000 [52:19:58<18:39:07, 18.14s/it] 75%|███████▌ | 11299/15000 [52:20:13<17:31:53, 17.05s/it] 75%|███████▌ | 11300/15000 [52:20:28<16:46:18, 16.32s/it] 75%|███████▌ | 11300/15000 [52:20:28<16:46:18, 16.32s/it] 75%|███████▌ | 11301/15000 [52:20:42<16:18:28, 15.87s/it] 75%|███████▌ | 11302/15000 [52:20:57<15:56:12, 15.51s/it] 75%|███████▌ | 11303/15000 [52:21:12<15:40:37, 15.27s/it] 75%|███████▌ | 11304/15000 [52:21:26<15:28:48, 15.08s/it] 75%|███████▌ | 11305/15000 [52:21:41<15:20:20, 14.94s/it] 75%|███████▌ | 11306/15000 [52:21:56<15:16:34, 14.89s/it] 75%|███████▌ | 11307/15000 [52:22:33<22:10:01, 21.61s/it] 75%|███████▌ | 11308/15000 [52:22:48<20:04:19, 19.57s/it] <0A>▌ | 11297/15000 [52:19:44<20:05:08, 19.53s/it] 75%|███████▌ | 11298/15000 [52:19:58<18:39:16, 18.14s/it] 75%|███████▌ | 11299/15000 [52:20:13<17:31:56, 17.05s/it] 75%|███████▌ | 11300/15000 [52:20:28<16:47:35, 16.34s/it] 75%|███████▌ | 11300/15000 [52:20:28<16:47:35, 16.34s/it] 75%|███████▌ | 11301/15000 [52:20:42<16:18:24, 15.87s/it] 75%|███████▌ | 11302/15000 [52:20:57<15:55:41, 15.51s/it] 75%|███████▌ | 11303/15000 [52:21:12<15:39:21, 15.25s/it] 75%|███████▌ | 11304/15000 [52:21:26<15:28:31, 15.07s/it] 75%|███████▌ | 11305/15000 [52:21:41<15:22:06, 14.97s/it] 75%|███████▌ | 11306/15000 [52:21:56<15:16:16, 14.88s/it] 75%|███████▌ | 11307/15000 [52:22:33<22:10:42, 21.62s/it] 75%|███████▌ | 11308/15000 [52:22:48<20:03:37, 19.56s/it] 5000 [52:20:13<17:31:43, 17.05s/it] 75%|███████▌ | 11300/15000 [52:20:28<16:48:41, 16.36s/it] 75%|███████▌ | 11300/15000 [52:20:28<16:48:41, 16.36s/it] 75%|███████▌ | 11301/15000 [52:20:42<16:18:25, 15.87s/it] 75%|███████▌ | 11302/15000 [52:20:57<15:54:04, 15.48s/it] 75%|███████▌ | 11303/15000 [52:21:12<15:39:49, 15.25s/it] 75%|███████▌ | 11304/15000 [52:21:26<15:29:15, 15.09s/it] 75%|███████▌ | 11305/15000 [52:21:41<15:21:30, 14.96s/it] 75%|███████▌ | 11306/15000 [52:21:56<15:15:26, 14.87s/it] 75%|███████▌ | 11307/15000 [52:22:33<22:11:16, 21.63s/it] 75%|███████▌ | 11308/15000 [52:22:48<20:02:32, 19.54s/it] 75%|███████▌ | 11309/15000 [52:23:02<18:32:11, 18.08s/it] 75%|███████▌ | 11310/15000 [52:23:17<17:28:56, 17.06s/it] 75%|███<E29688> 75%|███████▌ | 11309/15000 [52:23:03<18:32:36, 18.09s/it] 75%|███████▌ | 11310/15000 [52:23:17<17:29:27, 17.06s/it] 75%|███████▌ | 11311/15000 [52:23:32<16:45:26, 16.35s/it] 75%|███████▌ | 11312/15000 [52:23:46<16:10:27, 15.79s/it] 75%|███████▌ | 11313/15000 [52:24:01<15:51:54, 15.49s/it] 75%|███████▌ | 11314/15000 [52:24:16<15:34:35, 15.21s/it] 75%|███████▌ | 11315/15000 [52:24:30<15:20:48, 14.99s/it] 75%|███████▌ | 11316/15000 [52:24:45<15:15:03, 14.90s/it] 75%|███████▌ | 11317/15000 [52:25:00<15:14:43, 14.90s/it] 75%|███████▌ | 11318/15000 [52:25:37<22:07:59, 21.64s/it] 75%|███████▌ | 11319/15000 [52:25:52<20:00:53, 19.57s/it] 75%|███████▌ | 11320/15000 [52:26:07<18:29:45, 18.09s/it] 75%|███████▌ | 11321/15000 [52:26:21<17:24:24, 17.03s/it] 75%|███████▌ | 11
{'loss': 0.7933, 'learning_rate': 2.8719109545317103e-05, 'epoch': 2.13}
{'loss': 0.7933, 'learning_rate': 2.8719109545317103e-05, 'epoch': 2.13}
18.03s/it] 76%|███████▌ | 11390/15000 [52:45:29<17:03:28, 17.01s/it] 76%|███████▌ | 11391/15000 [52:45:43<16:21:03, 16.31s/it] 76%|███████▌ | 11392/15000 [52:45:58<15:50:03, 15.80s/it] 76%|███████▌ | 11393/15000 [52:46:13<15:29:18, 15.46s/it] 76%|███████▌ | 11394/15000 [52:46:27<15:15:12, 15.23s/it] 76%|███████▌ | 11395/15000 [52:46:42<15:03:36, 15.04s/it] 76%|███████▌ | 11396/15000 [52:46:57<14:59:02, 14.97s/it] 76%|███████▌ | 11397/15000 [52:47:11<14:51:05, 14.84s/it] 76%|███████▌ | 11398/15000 [52:47:49<21:39:02, 21.64s/it] 76%|███████▌ | 11399/15000 [52:48:03<19:34:01, 19.56s/it] 76%|███████▌ | 11400/15000 [52:48:18<18:03:47, 18.06s/it] 76%|███████▌ | 11400/15000 [52:48:18<18:03:47, 18.06s/it] 76%|███████▌ | 11401/ 18.03s/it] 76%|███████▌ | 11390/15000 [52:45:29<17:04:59, 17.04s/it] 76%|███████▌ | 11391/15000 [52:45:43<16:20:11, 16.30s/it] 76%|███████▌ | 11392/15000 [52:45:58<15:50:10, 15.80s/it] 76%|███████▌ | 11393/15000 [52:46:13<15:29:50, 15.47s/it] 76%|███████▌ | 11394/15000 [52:46:27<15:14:11, 15.21s/it] 76%|███████▌ | 11395/15000 [52:46:42<15:03:32, 15.04s/it] 76%|███████▌ | 11396/15000 [52:46:57<14:59:45, 14.98s/it] 76%|███████▌ | 11397/15000 [52:47:11<14:51:18, 14.84s/it] 76%|███████▌ | 11398/15000 [52:47:49<21:37:11, 21.61s/it] 76%|███████▌ | 11399/15000 [52:48:03<19:34:14, 19.57s/it] 76%|███████▌ | 11400/15000 [52:48:18<18:03:32, 18.06s/it] 76%|███████▌ | 11400/15000 [52:48:18<18:03:32, 18.06s/it] 76%|███████▌ | 11401/%|███████▌ | 11392/15000 [52:45:58<15:50:28, 15.81s/it] 76%|███████▌ | 11393/15000 [52:46:13<15:30:35, 15.48s/it] 76%|███████▌ | 11394/15000 [52:46:27<15:12:42, 15.19s/it] 76%|███████▌ | 11395/15000 [52:46:42<15:05:10, 15.07s/it] 76%|███████▌ | 11396/15000 [52:46:56<14:57:21, 14.94s/it] 76%|███████▌ | 11397/15000 [52:47:11<14:52:55, 14.87s/it] 76%|███████▌ | 11398/15000 [52:47:49<21:39:21, 21.64s/it] 76%|███████▌ | 11399/15000 [52:48:03<19:31:52, 19.53s/it] 76%|███████▌ | 11400/15000 [52:48:18<18:04:35, 18.08s/it] 76%|███████▌ | 11400/15000 [52:48:18<18:04:35, 18.08s/it] 76%|███████▌ | 11401/15000 [52:48:33<17:06:23, 17.11s/it] 76%|███████▌ | 11402/15000 [52:48:47<16:23:23, 16.40s/it] 76%|███████▌ | 11403/15000 [52:49:0215000 [52:48:33<17:06:19, 17.11s/it] 76%|███████▌ | 11402/15000 [52:48:47<16:22:10, 16.38s/it] 76%|███████▌ | 11403/15000 [52:49:02<15:51:58, 15.88s/it] 76%|███████▌ | 11404/15000 [52:49:17<15:31:30, 15.54s/it] 76%|███████▌ | 11405/15000 [52:49:31<15:13:13, 15.24s/it] 76%|███████▌ | 11406/15000 [52:49:46<15:02:21, 15.06s/it] 76%|███████▌ | 11407/15000 [52:50:01<14:53:30, 14.92s/it] 76%|███████▌ | 11408/15000 [52:50:15<14:49:06, 14.85s/it] 76%|███████▌ | 11409/15000 [52:50:53<21:33:57, 21.62s/it] 76%|███████▌ | 11410/15000 [52:51:07<19:27:58, 19.52s/it] 76%|███████▌ | 11411/15000 [52:51:22<18:01:19, 18.08s/it] 76%|███████▌ | 11412/15000 [52:51:37<16:59:39, 17.05s/it] 76%|███████▌ | 11413/15000 [52:51:51<16:17:09, 16.34s/it] 76%|███████▌ | 11414/15000 [52:52:06<15:45:38, 15.82s/it
{'loss': 0.7905, 'learning_rate': 2.722149024726307e-05, 'epoch': 2.15}
{'loss': 0.7905, 'learning_rate': 2.722149024726307e-05, 'epoch': 2.15}
, 15.46s/it] 77%|███████▋ | 11496/15000 [53:14:46<14:47:27, 15.20s/it] 77%|███████▋ | 11497/15000 [53:15:01<14:39:06, 15.06s/it] 77%|███████▋ | 11498/15000 [53:15:15<14:29:47, 14.90s/it] 77%|███████▋ | 11499/15000 [53:15:30<14:26:56, 14.86s/it] 77%|███████▋ | 11500/15000 [53:16:07<20:57:03, 21.55s/it] 77%|███████▋ | 11500/15000 [53:16:07<20:57:03, 21.55s/it] 77%|███████▋ | 11501/15000 [53:16:22<18:59:47, 19.54s/it] 77%|███████▋ | 11502/15000 [53:16:37<17:35:15, 18.10s/it] 77%|███████▋ | 11503/15000 [53:16:51<16:33:00, 17.04s/it] 77%|███████▋ | 11504/15000 [53:17:06<15:49:37, 16.30s/it] 77%|███████▋ | 11505/15000 [53:17:21<15:23:03, 15.85s/it] 77%|███████▋ | 11506/15000 [53:17:35<15:01:24, 15.48s/it] 77%|███████▋ | 11507, 15.47s/it] 77%|███████▋ | 11496/15000 [53:14:46<14:47:59, 15.21s/it] 77%|███████▋ | 11497/15000 [53:15:01<14:36:42, 15.02s/it] 77%|███████▋ | 11498/15000 [53:15:15<14:29:31, 14.90s/it] 77%|███████▋ | 11499/15000 [53:15:30<14:26:52, 14.86s/it] 77%|███████▋ | 11500/15000 [53:16:07<20:57:02, 21.55s/it] 77%|███████▋ | 11500/15000 [53:16:07<20:57:02, 21.55s/it] 77%|███████▋ | 11501/15000 [53:16:22<18:59:22, 19.54s/it] 77%|███████▋ | 11502/15000 [53:16:37<17:34:04, 18.08s/it] 77%|███████▋ | 11503/15000 [53:16:51<16:34:56, 17.07s/it] 77%|███████▋ | 11504/15000 [53:17:06<15:50:58, 16.32s/it] 77%|███████▋ | 11505/15000 [53:17:21<15:20:43, 15.81s/it] 77%|███████▋ | 11506/15000 [53:17:35<15:02:04, 15.49s/it] 77%|███████▋ | 115077%|███████▋ | 11498/15000 [53:15:15<14:30:14, 14.91s/it] 77%|███████▋ | 11499/15000 [53:15:30<14:25:28, 14.83s/it] 77%|███████▋ | 11500/15000 [53:16:07<20:56:37, 21.54s/it] 77%|███████▋ | 11500/15000 [53:16:07<20:56:37, 21.54s/it] 77%|███████▋ | 11501/15000 [53:16:22<19:00:11, 19.55s/it] 77%|███████▋ | 11502/15000 [53:16:37<17:34:52, 18.09s/it] 77%|███████▋ | 11503/15000 [53:16:51<16:32:57, 17.04s/it] 77%|███████▋ | 11504/15000 [53:17:06<15:51:16, 16.33s/it] 77%|███████▋ | 11505/15000 [53:17:21<15:24:37, 15.87s/it] 77%|███████▋ | 11506/15000 [53:17:35<15:02:23, 15.50s/it] 77%|███████▋ | 11507/15000 [53:17:50<14:46:51, 15.23s/it] 77%|███████▋ | 11508/15000 [53:18:05<14:36:46, 15.06s/it] 77%|███████▋ | 11509/15000 [53:18:1/15000 [53:17:50<14:49:45, 15.28s/it] 77%|███████▋ | 11508/15000 [53:18:05<14:35:19, 15.04s/it] 77%|███████▋ | 11509/15000 [53:18:19<14:28:28, 14.93s/it] 77%|███████▋ | 11510/15000 [53:18:34<14:26:11, 14.89s/it] 77%|███████▋ | 11511/15000 [53:18:49<14:22:55, 14.84s/it] 77%|███████▋ | 11512/15000 [53:19:26<20:55:51, 21.60s/it] 77%|███████▋ | 11513/15000 [53:19:41<18:55:04, 19.53s/it] 77%|███████▋ | 11514/15000 [53:19:56<17:29:06, 18.06s/it] 77%|███████▋ | 11515/15000 [53:20:10<16:29:12, 17.03s/it] 77%|███████▋ | 11516/15000 [53:20:25<15:45:39, 16.29s/it] 77%|███████▋ | 11517/15000 [53:20:39<15:16:39, 15.79s/it] 77%|███████▋ | 11518/15000 [53:20:54<14:56:15, 15.44s/it] 77%|███████▋ | 11519/15000 [53:21:09<14:44:06, 15.24s/it] 77%|███████▋ | 11520/15000 [53:21:23<14:33:36, 15.06s/i
{'loss': 0.7876, 'learning_rate': 2.5757799088684654e-05, 'epoch': 2.17}
▋ | 11588/15000 [53:40:16<14:16:38, 15.06s/it] 77%|███████▋ | 11589/15000 [53:40:30<14:09:40, 14.95s/it] 77%|███████▋ | 11590/15000 [53:40:45<14:02:55, 14.83s/it] 77%|███████▋ | 11591/15000 [53:41:22<20:20:15, 21.48s/it] 77%|███████▋ | 11592/15000 [53:41:37<18:24:04, 19.44s/it] 77%|███████▋ | 11593/15000 [53:41:51<17:02:41, 18.01s/it] 77%|███████▋ | 11594/15000 [53:42:06<16:04:33, 16.99s/it] 77%|███████▋ | 11595/15000 [53:42:21<15:25:35, 16.31s/it] 77%|███████▋ | 11596/15000 [53:42:35<14:56:27, 15.80s/it] 77%|███████▋ | 11597/15000 [53:42:50<14:36:30, 15.45s/it] 77%|███████▋ | 11598/15000 [53:43:05<14:24:34, 15.25s/it] 77%|███████▋ | 11599/15000 [53:43:19<14:15:43, 15.10s/it] 77%|███████▋ | 11600/15000 [53:43:34<14:07:01, 14.95s/it] {'loss': 0.7876, 'learning_rate': 2.5757799088684654e-05, 'epoch': 2.17}
▋ | 11588/15000 [53:40:16<14:17:30, 15.08s/it] 77%|███████▋ | 11589/15000 [53:40:30<14:08:57, 14.93s/it] 77%|███████▋ | 11590/15000 [53:40:45<14:01:41, 14.81s/it] 77%|███████▋ | 11591/15000 [53:41:22<20:19:52, 21.47s/it] 77%|███████▋ | 11592/15000 [53:41:37<18:23:40, 19.43s/it] 77%|███████▋ | 11593/15000 [53:41:51<17:02:38, 18.01s/it] 77%|███████▋ | 11594/15000 [53:42:06<16:03:49, 16.98s/it] 77%|███████▋ | 11595/15000 [53:42:20<15:24:53, 16.30s/it] 77%|███████▋ | 11596/15000 [53:42:35<14:58:09, 15.83s/it] 77%|███████▋ | 11597/15000 [53:42:50<14:38:04, 15.48s/it] 77%|███████▋ | 11598/15000 [53:43:05<14:24:13, 15.24s/it] 77%|███████▋ | 11599/15000 [53:43:19<14:15:03, 15.08s/it] 77%|███████▋ | 11600/15000 [53:43:34<14:05:48, 14.93s/it] 000 [53:40:45<14:02:41, 14.83s/it] 77%|███████▋ | 11591/15000 [53:41:22<20:20:37, 21.48s/it] 77%|███████▋ | 11592/15000 [53:41:37<18:23:28, 19.43s/it] 77%|███████▋ | 11593/15000 [53:41:51<17:02:22, 18.00s/it] 77%|███████▋ | 11594/15000 [53:42:06<16:03:43, 16.98s/it] 77%|███████▋ | 11595/15000 [53:42:20<15:25:16, 16.30s/it] 77%|███████▋ | 11596/15000 [53:42:35<14:57:37, 15.82s/it] 77%|███████▋ | 11597/15000 [53:42:50<14:38:30, 15.49s/it] 77%|███████▋ | 11598/15000 [53:43:05<14:24:34, 15.25s/it] 77%|███████▋ | 11599/15000 [53:43:19<14:14:00, 15.07s/it] 77%|███████▋ | 11600/15000 [53:43:34<14:05:40, 14.92s/it] 77%|███████▋ | 11600/15000 [53:43:34<14:05:40, 14.92s/it] 77%|███████▋ | 11601/15000 [53:43:49<14:04:25, 14.91s/it] 77%|███<E29688><E29688>77%|███████▋ | 11600/15000 [53:43:34<14:05:48, 14.93s/it] 77%|███████▋ | 11601/15000 [53:43:49<14:07:27, 14.96s/it] 77%|███████▋ | 11602/15000 [53:44:26<20:21:09, 21.56s/it] 77%|███████▋ | 11603/15000 [53:44:41<18:25:31, 19.53s/it] 77%|███████▋ | 11604/15000 [53:44:55<17:01:16, 18.04s/it] 77%|███████▋ | 11605/15000 [53:45:10<16:04:30, 17.05s/it] 77%|███████▋ | 11606/15000 [53:45:25<15:22:55, 16.32s/it] 77%|███████▋ | 11607/15000 [53:45:39<14:56:48, 15.86s/it] 77%|███████▋ | 11608/15000 [53:45:54<14:34:26, 15.47s/it] 77%|███████▋ | 11609/15000 [53:46:09<14:20:16, 15.22s/it] 77%|███████▋ | 11610/15000 [53:46:23<14:10:41, 15.06s/it] 77%|███████▋ | 11611/15000 [53:46:38<14:03:02, 14.93s/it] 77%|███████▋ | 11612/15000 [53:46:53<13:58:19, 14.85s/it] 77%|███████▋ | 116177%|███████▋ | 11600/15000 [53:43:34<14:07:01, 14.95s/it] 77%|███████▋ | 11601/15000 [53:43:49<14:05:25, 14.92s/it] 77%|███████▋ | 11602/15000 [53:44:26<20:22:12, 21.58s/it] 77%|███████▋ | 11603/15000 [53:44:41<18:24:47, 19.51s/it] 77%|███████▋ | 11604/15000 [53:44:55<17:01:49, 18.05s/it] 77%|███████▋ | 11605/15000 [53:45:10<16:01:53, 17.00s/it] 77%|███████▋ | 11606/15000 [53:45:25<15:23:30, 16.33s/it] 77%|███████▋ | 11607/15000 [53:45:39<14:57:07, 15.86s/it] 77%|███████▋ | 11608/15000 [53:45:54<14:33:23, 15.45s/it] 77%|███████▋ | 11609/15000 [53:46:09<14:20:06, 15.22s/it] 77%|███████▋ | 11610/15000 [53:46:23<14:11:30, 15.07s/it] 77%|███████▋ | 11611/15000 [53:46:38<14:04:55, 14.96s/it] 77%|███████▋ | 11612/15000 [53:46:53<13:57:40, 14.83s/it] 77%|███████▋ | 116
{'loss': 0.7825, 'learning_rate': 2.432871841823047e-05, 'epoch': 2.19}
{'loss': 0.7825, 'learning_rate': 2.432871841823047e-05, 'epoch': 2.19}
<EFBFBD>▊ | 11694/15000 [54:09:57<17:59:35, 19.59s/it] 78%|███████▊ | 11695/15000 [54:10:12<16:38:03, 18.12s/it] 78%|███████▊ | 11696/15000 [54:10:26<15:41:43, 17.10s/it] 78%|███████▊ | 11697/15000 [54:10:41<15:00:56, 16.37s/it] 78%|███████▊ | 11698/15000 [54:10:56<14:34:05, 15.88s/it] 78%|███████▊ | 11699/15000 [54:11:11<14:13:56, 15.52s/it] 78%|███████▊ | 11700/15000 [54:11:25<14:00:57, 15.29s/it] 78%|███████▊ | 11700/15000 [54:11:25<14:00:57, 15.29s/it] 78%|███████▊ | 11701/15000 [54:11:40<13:52:15, 15.14s/it] 78%|███████▊ | 11702/15000 [54:11:55<13:46:11, 15.03s/it] 78%|███████▊ | 11703/15000 [54:12:09<13:38:41, 14.90s/it] 78%|███████▊ | 11704/15000 [54:12:46<19:42:11, 21.52s/it] 78%|███████▊ | 11705/15000 [54:13:01<17:49:06, 19.47s/it] <0A>▊ | 11694/15000 [54:09:57<18:00:02, 19.60s/it] 78%|███████▊ | 11695/15000 [54:10:12<16:38:43, 18.13s/it] 78%|███████▊ | 11696/15000 [54:10:26<15:42:03, 17.11s/it] 78%|███████▊ | 11697/15000 [54:10:41<15:00:19, 16.35s/it] 78%|███████▊ | 11698/15000 [54:10:56<14:32:03, 15.85s/it] 78%|███████▊ | 11699/15000 [54:11:11<14:14:40, 15.53s/it] 78%|███████▊ | 11700/15000 [54:11:25<13:59:44, 15.27s/it] 78%|███████▊ | 11700/15000 [54:11:25<13:59:44, 15.27s/it] 78%|███████▊ | 11701/15000 [54:11:40<13:52:11, 15.14s/it] 78%|███████▊ | 11702/15000 [54:11:55<13:46:06, 15.03s/it] 78%|███████▊ | 11703/15000 [54:12:09<13:39:15, 14.91s/it] 78%|███████▊ | 11704/15000 [54:12:46<19:42:14, 21.52s/it] 78%|███████▊ | 11705/15000 [54:13:01<17:47:58, 19.45s/it] 5000 [54:10:26<15:41:24, 17.10s/it] 78%|███████▊ | 11697/15000 [54:10:41<14:59:36, 16.34s/it] 78%|███████▊ | 11698/15000 [54:10:56<14:33:31, 15.87s/it] 78%|███████▊ | 11699/15000 [54:11:10<14:12:34, 15.50s/it] 78%|███████▊ | 11700/15000 [54:11:25<13:58:26, 15.24s/it] 78%|███████▊ | 11700/15000 [54:11:25<13:58:26, 15.24s/it] 78%|███████▊ | 11701/15000 [54:11:40<13:53:43, 15.16s/it] 78%|███████▊ | 11702/15000 [54:11:55<13:44:51, 15.01s/it] 78%|███████▊ | 11703/15000 [54:12:09<13:39:31, 14.91s/it] 78%|███████▊ | 11704/15000 [54:12:46<19:41:33, 21.51s/it] 78%|███████▊ | 11705/15000 [54:13:01<17:49:08, 19.47s/it] 78%|███████▊ | 11706/15000 [54:13:16<16:30:38, 18.04s/it] 78%|███████▊ | 11707/15000 [54:13:30<15:35:25, 17.04s/it] 78%|███<E29688> 78%|███████▊ | 11706/15000 [54:13:16<16:28:33, 18.01s/it] 78%|███████▊ | 11707/15000 [54:13:30<15:34:39, 17.03s/it] 78%|███████▊ | 11708/15000 [54:13:45<14:57:10, 16.35s/it] 78%|███████▊ | 11709/15000 [54:14:00<14:30:19, 15.87s/it] 78%|███████▊ | 11710/15000 [54:14:14<14:08:18, 15.47s/it] 78%|███████▊ | 11711/15000 [54:14:29<13:54:39, 15.23s/it] 78%|███████▊ | 11712/15000 [54:14:44<13:46:42, 15.09s/it] 78%|███████▊ | 11713/15000 [54:14:58<13:36:20, 14.90s/it] 78%|███████▊ | 11714/15000 [54:15:13<13:32:45, 14.84s/it] 78%|███████▊ | 11715/15000 [54:15:28<13:30:47, 14.81s/it] 78%|███████▊ | 11716/15000 [54:16:05<19:31:35, 21.41s/it] 78%|███████▊ | 11717/15000 [54:16:19<17:40:48, 19.39s/it] 78%|███████▊ | 11718/15000 [54:16:34<16:24:54, 18.01s/it] 78%|███████▊ | 11
{'loss': 0.815, 'learning_rate': 2.2934914449711087e-05, 'epoch': 2.21}
{'loss': 0.815, 'learning_rate': 2.2934914449711087e-05, 'epoch': 2.21}
%|███████▊ | 11789/15000 [54:36:08<13:49:33, 15.50s/it] 79%|███████▊ | 11790/15000 [54:36:22<13:36:26, 15.26s/it] 79%|███████▊ | 11791/15000 [54:36:37<13:26:45, 15.08s/it] 79%|███████▊ | 11792/15000 [54:36:52<13:21:36, 14.99s/it] 79%|███████▊ | 11793/15000 [54:37:06<13:17:00, 14.91s/it] 79%|███████▊ | 11794/15000 [54:37:43<19:08:53, 21.50s/it] 79%|███████▊ | 11795/15000 [54:37:58<17:20:01, 19.47s/it] 79%|███████▊ | 11796/15000 [54:38:13<16:02:28, 18.02s/it] 79%|███████▊ | 11797/15000 [54:38:27<15:09:30, 17.04s/it] 79%|███████▊ | 11798/15000 [54:38:42<14:32:21, 16.35s/it] 79%|███████▊ | 11799/15000 [54:38:57<14:05:31, 15.85s/it] 79%|███████▊ | 11800/15000 [54:39:11<13:45:40, 15.48s/it] 79%|███████▊ | 11800/15000 [54:39:12<31><32>▊ | 11800/15000 [54:39:11<13:46:00, 15.49s/it] 79%|███████▊ | 11800/15000 [54:39:12<13:46:00, 15.49s/it] 79%|███████▊ | 11801/15000 [54:39:26<13:37:29, 15.33s/it] 79%|███████▊ | 11802/15000 [54:39:41<13:27:17, 15.15s/it] 79%|███████▊ | 11803/15000 [54:39:56<13:21:44, 15.05s/it] 79%|███████▊ | 11804/15000 [54:40:10<13:12:55, 14.89s/it] 79%|███████▊ | 11805/15000 [54:40:47<19:02:17, 21.45s/it] 79%|███████▊ | 11806/15000 [54:41:02<17:14:57, 19.44s/it] 79%|███████▊ | 11807/15000 [54:41:17<15:58:21, 18.01s/it] 79%|███████▊ | 11808/15000 [54:41:31<15:03:31, 16.98s/it] 79%|███████▊ | 11809/15000 [54:41:46<14:25:43, 16.28s/it] 79%|███████▊ | 11810/15000 [54:42:01<14:00:47, 15.81s/it] 79%|███████▊ | 11811/15000 [54:42:15<13:40:56, 15.45s/it]<5D><>▊ | 11800/15000 [54:39:12<13:47:01, 15.51s/it] 79%|███████▊ | 11800/15000 [54:39:12<13:47:01, 15.51s/it] 79%|███████▊ | 11801/15000 [54:39:27<13:38:02, 15.34s/it] 79%|███████▊ | 11802/15000 [54:39:41<13:25:19, 15.11s/it] 79%|███████▊ | 11803/15000 [54:39:56<13:21:09, 15.04s/it] 79%|███████▊ | 11804/15000 [54:40:11<13:13:37, 14.90s/it] 79%|███████▊ | 11805/15000 [54:40:47<19:01:50, 21.44s/it] 79%|███████▊ | 11806/15000 [54:41:02<17:14:52, 19.44s/it] 79%|███████▊ | 11807/15000 [54:41:17<15:57:23, 17.99s/it] 79%|███████▊ | 11808/15000 [54:41:31<15:04:02, 16.99s/it] 79%|███████▊ | 11809/15000 [54:41:46<14:27:25, 16.31s/it] 79%|███████▊ | 11810/15000 [54:42:01<14:00:54, 15.82s/it] 79%|███████▊ | 11811/15000 [54:42:15<13:41:15, 15.45s/it]<13:45:40, 15.48s/it] 79%|███████▊ | 11801/15000 [54:39:26<13:36:32, 15.31s/it] 79%|███████▊ | 11802/15000 [54:39:41<13:27:43, 15.15s/it] 79%|███████▊ | 11803/15000 [54:39:56<13:19:23, 15.00s/it] 79%|███████▊ | 11804/15000 [54:40:10<13:13:03, 14.89s/it] 79%|███████▊ | 11805/15000 [54:40:47<19:02:38, 21.46s/it] 79%|███████▊ | 11806/15000 [54:41:02<17:14:00, 19.42s/it] 79%|███████▊ | 11807/15000 [54:41:17<15:57:33, 17.99s/it] 79%|███████▊ | 11808/15000 [54:41:31<15:03:21, 16.98s/it] 79%|███████▊ | 11809/15000 [54:41:46<14:26:49, 16.30s/it] 79%|███████▊ | 11810/15000 [54:42:01<13:59:20, 15.79s/it] 79%|███████▊ | 11811/15000 [54:42:15<13:41:36, 15.46s/it] 79%|███████▊ | 11812/15000 [54:42:30<13:30:17, 15.25s/it] 79%|███████▉ | 11813/15000 [54:42:45<13:20:54, 15.08s/it] 79%|██<E29688><E29688>
{'loss': 0.8167, 'learning_rate': 2.157703695152109e-05, 'epoch': 2.23}
{'loss': 0.8167, 'learning_rate': 2.157703695152109e-05, 'epoch': 2.23}
, 15.09s/it] 79%|███████▉ | 11893/15000 [55:04:55<12:54:14, 14.95s/it] 79%|███████▉ | 11894/15000 [55:05:09<12:48:31, 14.85s/it] 79%|███████▉ | 11895/15000 [55:05:46<18:23:58, 21.33s/it] 79%|███████▉ | 11896/15000 [55:06:00<16:40:33, 19.34s/it] 79%|███████▉ | 11897/15000 [55:06:15<15:25:22, 17.89s/it] 79%|███████▉ | 11898/15000 [55:06:30<14:34:59, 16.92s/it] 79%|███████▉ | 11899/15000 [55:06:44<14:01:54, 16.29s/it] 79%|███████▉ | 11900/15000 [55:06:59<13:36:20, 15.80s/it] 79%|███████▉ | 11900/15000 [55:06:59<13:36:20, 15.80s/it] 79%|███████▉ | 11901/15000 [55:07:14<13:21:32, 15.52s/it] 79%|███████▉ | 11902/15000 [55:07:28<13:06:28, 15.23s/it] 79%|███████▉ | 11903/15000 [55:07:43<12:58:53, 15.09s/it] 79%|███████▉ | 11904, 15.04s/it] 79%|███████▉ | 11893/15000 [55:04:55<12:53:09, 14.93s/it] 79%|███████▉ | 11894/15000 [55:05:09<12:46:59, 14.82s/it] 79%|███████▉ | 11895/15000 [55:05:46<18:24:42, 21.35s/it] 79%|███████▉ | 11896/15000 [55:06:00<16:40:22, 19.34s/it] 79%|███████▉ | 11897/15000 [55:06:15<15:27:12, 17.93s/it] 79%|███████▉ | 11898/15000 [55:06:30<14:35:40, 16.94s/it] 79%|███████▉ | 11899/15000 [55:06:44<14:02:05, 16.29s/it] 79%|███████▉ | 11900/15000 [55:06:59<13:35:32, 15.78s/it] 79%|███████▉ | 11900/15000 [55:06:59<13:35:32, 15.78s/it] 79%|███████▉ | 11901/15000 [55:07:14<13:21:19, 15.51s/it] 79%|███████▉ | 11902/15000 [55:07:28<13:07:33, 15.25s/it] 79%|███████▉ | 11903/15000 [55:07:43<12:57:31, 15.06s/it] 79%|███████▉ | 119049%|███████▉ | 11895/15000 [55:05:46<18:24:31, 21.34s/it] 79%|███████▉ | 11896/15000 [55:06:00<16:39:18, 19.32s/it] 79%|███████▉ | 11897/15000 [55:06:15<15:27:46, 17.94s/it] 79%|███████▉ | 11898/15000 [55:06:30<14:36:29, 16.95s/it] 79%|███████▉ | 11899/15000 [55:06:44<14:01:33, 16.28s/it] 79%|███████▉ | 11900/15000 [55:06:59<13:35:28, 15.78s/it] 79%|███████▉ | 11900/15000 [55:06:59<13:35:28, 15.78s/it] 79%|███████▉ | 11901/15000 [55:07:14<13:20:33, 15.50s/it] 79%|███████▉ | 11902/15000 [55:07:28<13:08:21, 15.27s/it] 79%|███████▉ | 11903/15000 [55:07:43<12:57:35, 15.06s/it] 79%|███████▉ | 11904/15000 [55:07:58<12:50:29, 14.93s/it] 79%|███████▉ | 11905/15000 [55:08:12<12:47:15, 14.87s/it] 79%|███████▉ | 11906/15000 [55:08:4/15000 [55:07:58<12:50:25, 14.93s/it] 79%|███████▉ | 11905/15000 [55:08:13<12:48:04, 14.89s/it] 79%|███████▉ | 11906/15000 [55:08:49<18:23:04, 21.39s/it] 79%|███████▉ | 11907/15000 [55:09:04<16:39:25, 19.39s/it] 79%|███████▉ | 11908/15000 [55:09:18<15:24:13, 17.93s/it] 79%|███████▉ | 11909/15000 [55:09:33<14:35:09, 16.99s/it] 79%|███████▉ | 11910/15000 [55:09:48<13:57:03, 16.25s/it] 79%|███████▉ | 11911/15000 [55:10:02<13:33:19, 15.80s/it] 79%|███████▉ | 11912/15000 [55:10:17<13:14:00, 15.43s/it] 79%|███████▉ | 11913/15000 [55:10:32<13:02:50, 15.22s/it] 79%|███████▉ | 11914/15000 [55:10:46<12:55:01, 15.07s/it] 79%|███████▉ | 11915/15000 [55:11:01<12:47:49, 14.93s/it] 79%|███████▉ | 11916/15000 [55:11:16<12:43:53, 14.86s/it] 79%|███████▉ | 11917/15000 [55:11:53<18:22:03, 21.45s/i
{'loss': 0.8181, 'learning_rate': 2.025571894372794e-05, 'epoch': 2.25}
000 [55:31:13<14:14:03, 17.01s/it] 80%|███████▉ | 11988/15000 [55:31:28<13:38:29, 16.30s/it] 80%|███████▉ | 11989/15000 [55:31:42<13:14:14, 15.83s/it] 80%|███████▉ | 11990/15000 [55:31:57<12:57:11, 15.49s/it] 80%|███████▉ | 11991/15000 [55:32:12<12:46:17, 15.28s/it] 80%|███████▉ | 11992/15000 [55:32:27<12:37:51, 15.12s/it] 80%|███████▉ | 11993/15000 [55:32:41<12:31:18, 14.99s/it] 80%|███████▉ | 11994/15000 [55:32:56<12:26:11, 14.89s/it] 80%|███████▉ | 11995/15000 [55:33:33<17:55:31, 21.47s/it] 80%|███████▉ | 11996/15000 [55:33:47<16:12:42, 19.43s/it] 80%|███████▉ | 11997/15000 [55:34:02<15:00:43, 18.00s/it] 80%|███████▉ | 11998/15000 [55:34:17<14:09:48, 16.98s/it] 80%|███████▉ | 11999/15000 [55:34:31<13:34:19, 16.28s/it] 80%|████████ | 12000/15000 [55:34:46<13:09:50, 15.80s/it] {'loss': 0.8181, 'learning_rate': 2.025571894372794e-05, 'epoch': 2.25}
80%|████████ | 12000/15000 [55:34:46<13:09:50, 15.80s/it]Saving model checkpoint to /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-12000
tokenizer config file saved in /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-12000/tokenizer_config.json
Special tokens file saved in /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-12000/special_tokens_map.json
5, 17.00s/it] 80%|███████▉ | 11999/15000 [55:34:32<13:35:46, 16.31s/it] 80%|████████ | 12000/15000 [55:34:46<13:09:20, 15.79s/it] 80%|████████ | 12000/15000 [55:34:46<13:09:20, 15.79s/it] 80%|████████ | 12001/15000 [55:35:06<14:06:29, 16.94s/it] 80%|████████ | 12002/15000 [55:35:20<13:34:09, 16.29s/it] 80%|████████ | 12003/15000 [55:35:35<13:09:49, 15.81s/it] 80%|████████ | 12004/15000 [55:35:50<12:52:47, 15.48s/it] 80%|████████ | 12005/15000 [55:36:05<12:40:20, 15.23s/it] 80%|████████ | 12006/15000 [55:36:19<12:32:34, 15.08s/it] 80%|████████ | 12007/15000 [55:36:56<17:57:03, 21.59s/it] 80%|████████ | 12008/15000 [55:37:11<16:12:18, 19.50s/it] 80%|████████ | 12009/15000 [55:37:25<14:56:45, 17.99s/it] 80%|████████ | 12011, 16.98s/it] 80%|███████▉ | 11999/15000 [55:34:31<13:34:59, 16.29s/it] 80%|████████ | 12000/15000 [55:34:46<13:09:38, 15.79s/it] 80%|████████ | 12000/15000 [55:34:46<13:09:38, 15.79s/it] 80%|████████ | 12001/15000 [55:35:06<14:08:29, 16.98s/it] 80%|████████ | 12002/15000 [55:35:21<13:34:53, 16.31s/it] 80%|████████ | 12003/15000 [55:35:35<13:08:53, 15.79s/it] 80%|████████ | 12004/15000 [55:35:50<12:51:33, 15.45s/it] 80%|████████ | 12005/15000 [55:36:04<12:39:56, 15.22s/it] 80%|████████ | 12006/15000 [55:36:19<12:32:48, 15.09s/it] 80%|████████ | 12007/15000 [55:36:56<17:55:39, 21.56s/it] 80%|████████ | 12008/15000 [55:37:11<16:12:50, 19.51s/it] 80%|████████ | 12009/15000 [55:37:25<14:57:31, 18.00s/it] 80%|████████ | 1201 80%|████████ | 12001/15000 [55:35:06<14:09:43, 17.00s/it] 80%|████████ | 12002/15000 [55:35:20<13:33:22, 16.28s/it] 80%|████████ | 12003/15000 [55:35:35<13:08:58, 15.80s/it] 80%|████████ | 12004/15000 [55:35:50<12:51:52, 15.46s/it] 80%|████████ | 12005/15000 [55:36:04<12:40:56, 15.24s/it] 80%|████████ | 12006/15000 [55:36:19<12:32:09, 15.07s/it] 80%|████████ | 12007/15000 [55:36:56<17:56:02, 21.57s/it] 80%|████████ | 12008/15000 [55:37:11<16:11:47, 19.49s/it] 80%|████████ | 12009/15000 [55:37:25<14:58:49, 18.03s/it] 80%|████████ | 12010/15000 [55:37:40<14:08:18, 17.02s/it] 80%|████████ | 12011/15000 [55:37:55<13:32:53, 16.32s/it] 80%|████████ | 12012/15000 [55:38:09<13:07:46, 15.82s/it] 80%|████████ | 12013/15000 [55:38:24<12:50:28, 15.48s/it] 80%|████████ | 120/15000 [55:37:40<14:08:58, 17.04s/it] 80%|████████ | 12011/15000 [55:37:55<13:33:07, 16.32s/it] 80%|████████ | 12012/15000 [55:38:09<13:08:38, 15.84s/it] 80%|████████ | 12013/15000 [55:38:24<12:48:55, 15.45s/it] 80%|████████ | 12014/15000 [55:38:39<12:39:13, 15.26s/it] 80%|████████ | 12015/15000 [55:38:53<12:29:28, 15.06s/it] 80%|████████ | 12016/15000 [55:39:08<12:23:36, 14.95s/it] 80%|████████ | 12017/15000 [55:39:23<12:18:15, 14.85s/it] 80%|████████ | 12018/15000 [55:39:59<17:44:15, 21.41s/it] 80%|████████ | 12019/15000 [55:40:14<16:03:19, 19.39s/it] 80%|████████ | 12020/15000 [55:40:28<14:51:02, 17.94s/it] 80%|████████ | 12021/15000 [55:40:43<14:02:52, 16.98s/it] 80%|████████ | 12022/15000 [55:40:58<13:27:50, 16.28s/it] 80%|████████ | 12023/15000 [55:41:12<13:02:39, 15.77s/
{'loss': 0.8173, 'learning_rate': 1.897157640296825e-05, 'epoch': 2.26}
{'loss': 0.8173, 'learning_rate': 1.897157640296825e-05, 'epoch': 2.26}
<EFBFBD>█ | 12091/15000 [56:00:02<12:28:24, 15.44s/it] 81%|████████ | 12092/15000 [56:00:17<12:16:40, 15.20s/it] 81%|████████ | 12093/15000 [56:00:31<12:08:43, 15.04s/it] 81%|████████ | 12094/15000 [56:00:46<12:04:18, 14.95s/it] 81%|████████ | 12095/15000 [56:01:01<11:59:24, 14.86s/it] 81%|████████ | 12096/15000 [56:01:37<17:17:07, 21.43s/it] 81%|████████ | 12097/15000 [56:01:52<15:39:04, 19.41s/it] 81%|████████ | 12098/15000 [56:02:07<14:29:09, 17.97s/it] 81%|████████ | 12099/15000 [56:02:21<13:40:33, 16.97s/it] 81%|████████ | 12100/15000 [56:02:36<13:06:19, 16.27s/it] 81%|████████ | 12100/15000 [56:02:36<13:06:19, 16.27s/it] 81%|████████ | 12101/15000 [56:02:51<12:47:15, 15.88s/it] 81%|████████ | 12102/15000 [56:03:06<12:29:04, 15.51s/it] <0A>█ | 12091/15000 [56:00:02<12:29:15, 15.45s/it] 81%|████████ | 12092/15000 [56:00:16<12:15:14, 15.17s/it] 81%|████████ | 12093/15000 [56:00:31<12:08:55, 15.04s/it] 81%|████████ | 12094/15000 [56:00:46<12:04:05, 14.95s/it] 81%|████████ | 12095/15000 [56:01:01<11:59:16, 14.86s/it] 81%|████████ | 12096/15000 [56:01:37<17:18:10, 21.45s/it] 81%|████████ | 12097/15000 [56:01:52<15:38:04, 19.39s/it] 81%|████████ | 12098/15000 [56:02:07<14:28:29, 17.96s/it] 81%|████████ | 12099/15000 [56:02:21<13:42:10, 17.00s/it] 81%|████████ | 12100/15000 [56:02:36<13:07:56, 16.30s/it] 81%|████████ | 12100/15000 [56:02:36<13:07:56, 16.30s/it] 81%|████████ | 12101/15000 [56:02:51<12:46:01, 15.85s/it] 81%|████████ | 12102/15000 [56:03:06<12:28:32, 15.50s/it] ██ | 12095/15000 [56:01:00<11:57:56, 14.83s/it] 81%|████████ | 12096/15000 [56:01:37<17:17:52, 21.44s/it] 81%|████████ | 12097/15000 [56:01:52<15:37:59, 19.39s/it] 81%|████████ | 12098/15000 [56:02:07<14:29:19, 17.97s/it] 81%|████████ | 12099/15000 [56:02:21<13:41:23, 16.99s/it] 81%|████████ | 12100/15000 [56:02:36<13:06:21, 16.27s/it] 81%|████████ | 12100/15000 [56:02:36<13:06:21, 16.27s/it] 81%|████████ | 12101/15000 [56:02:51<12:46:20, 15.86s/it] 81%|████████ | 12102/15000 [56:03:05<12:28:34, 15.50s/it] 81%|████████ | 12103/15000 [56:03:20<12:14:45, 15.22s/it] 81%|████████ | 12104/15000 [56:03:35<12:06:07, 15.04s/it] 81%|████████ | 12105/15000 [56:03:49<12:02:39, 14.98s/it] 81%|████████ | 12106/15000 [56:04:04<11:58:13, 14.89s/it 81%|████████ | 12103/15000 [56:03:20<12:15:12, 15.23s/it] 81%|████████ | 12104/15000 [56:03:35<12:05:42, 15.04s/it] 81%|████████ | 12105/15000 [56:03:50<12:02:37, 14.98s/it] 81%|████████ | 12106/15000 [56:04:04<11:57:25, 14.87s/it] 81%|████████ | 12107/15000 [56:04:41<17:18:11, 21.53s/it] 81%|████████ | 12108/15000 [56:04:56<15:36:18, 19.43s/it] 81%|████████ | 12109/15000 [56:05:11<14:28:16, 18.02s/it] 81%|████████ | 12110/15000 [56:05:25<13:39:41, 17.02s/it] 81%|████████ | 12111/15000 [56:05:40<13:04:16, 16.29s/it] 81%|████████ | 12112/15000 [56:05:54<12:40:29, 15.80s/it] 81%|████████ | 12113/15000 [56:06:09<12:24:44, 15.48s/it] 81%|████████ | 12114/15000 [56:06:24<12:11:24, 15.21s/it] 81%|████████ | 12115/15000 [56:06:38<12:04:12, 15.06s/it] 81%|████████ | 12
{'loss': 0.8158, 'learning_rate': 1.772520797528988e-05, 'epoch': 2.28}
{'loss': 0.8158, 'learning_rate': 1.772520797528988e-05, 'epoch': 2.28}
<EFBFBD><EFBFBD>███████▏ | 12197/15000 [56:29:40<16:39:24, 21.39s/it] 81%|████████▏ | 12198/15000 [56:29:55<15:06:32, 19.41s/it] 81%|████████▏ | 12199/15000 [56:30:10<14:00:52, 18.01s/it] 81%|████████▏ | 12200/15000 [56:30:24<13:14:40, 17.03s/it] 81%|████████▏ | 12200/15000 [56:30:25<13:14:40, 17.03s/it] 81%|████████▏ | 12201/15000 [56:30:39<12:43:58, 16.38s/it] 81%|████████▏ | 12202/15000 [56:30:54<12:19:11, 15.85s/it] 81%|████████▏ | 12203/15000 [56:31:09<12:02:28, 15.50s/it] 81%|████████▏ | 12204/15000 [56:31:23<11:49:25, 15.22s/it] 81%|████████▏ | 12205/15000 [56:31:38<11:41:22, 15.06s/it] 81%|████████▏ | 12206/15000 [56:31:53<11:36:49, 14.96s/it] 81%|████████▏ | 12207/15000 [56:32:07<11:33:37, 14.90s/it] 81%|████████▏ <20><>███████▏ | 12197/15000 [56:29:40<16:40:47, 21.42s/it] 81%|████████▏ | 12198/15000 [56:29:55<15:06:14, 19.41s/it] 81%|████████▏ | 12199/15000 [56:30:10<14:00:38, 18.01s/it] 81%|████████▏ | 12200/15000 [56:30:24<13:13:25, 17.00s/it] 81%|████████▏ | 12200/15000 [56:30:25<13:13:25, 17.00s/it] 81%|████████▏ | 12201/15000 [56:30:39<12:42:53, 16.35s/it] 81%|████████▏ | 12202/15000 [56:30:54<12:20:06, 15.87s/it] 81%|████████▏ | 12203/15000 [56:31:09<12:03:21, 15.52s/it] 81%|████████▏ | 12204/15000 [56:31:23<11:48:19, 15.20s/it] 81%|████████▏ | 12205/15000 [56:31:38<11:41:28, 15.06s/it] 81%|████████▏ | 12206/15000 [56:31:53<11:37:10, 14.97s/it] 81%|████████▏ | 12207/15000 [56:32:07<11:33:08, 14.89s/it] 81%|████████▏ it] 81%|████████▏ | 12200/15000 [56:30:25<13:13:23, 17.00s/it] 81%|████████▏ | 12201/15000 [56:30:39<12:44:12, 16.38s/it] 81%|████████▏ | 12202/15000 [56:30:54<12:20:45, 15.88s/it] 81%|████████▏ | 12203/15000 [56:31:09<12:01:36, 15.48s/it] 81%|████████▏ | 12204/15000 [56:31:23<11:50:00, 15.24s/it] 81%|████████▏ | 12205/15000 [56:31:38<11:41:54, 15.07s/it] 81%|████████▏ | 12206/15000 [56:31:53<11:37:17, 14.97s/it] 81%|████████▏ | 12207/15000 [56:32:07<11:33:07, 14.89s/it] 81%|████████▏ | 12208/15000 [56:32:44<16:33:43, 21.36s/it] 81%|████████▏ | 12209/15000 [56:32:58<14:58:51, 19.32s/it] 81%|████████▏ | 12210/15000 [56:33:13<13:53:55, 17.93s/it] 81%|████████▏ | 12211/15000 [56:33:28<13:08:32, 16.96s/it] 81%|██████| 12208/15000 [56:32:44<16:35:53, 21.40s/it] 81%|████████▏ | 12209/15000 [56:32:58<14:59:25, 19.34s/it] 81%|████████▏ | 12210/15000 [56:33:13<13:53:37, 17.93s/it] 81%|████████▏ | 12211/15000 [56:33:28<13:07:18, 16.94s/it] 81%|████████▏ | 12212/15000 [56:33:42<12:35:58, 16.27s/it] 81%|████████▏ | 12213/15000 [56:33:57<12:14:27, 15.81s/it] 81%|████████▏ | 12214/15000 [56:34:12<11:58:42, 15.48s/it] 81%|████████▏ | 12215/15000 [56:34:26<11:45:59, 15.21s/it] 81%|████████▏ | 12216/15000 [56:34:41<11:38:04, 15.04s/it] 81%|████████▏ | 12217/15000 [56:34:56<11:33:18, 14.95s/it] 81%|████████▏ | 12218/15000 [56:35:11<11:29:52, 14.88s/it] 81%|████████▏ | 12219/15000 [56:35:47<16:31:17, 21.39s/it] 81%|████████▏ | 12220/15000 [56:36:02<14:57:03, 19.36s/it] 81%|████████▏ | 12221/1
{'loss': 0.8173, 'learning_rate': 1.65171946970729e-05, 'epoch': 2.3}
{'loss': 0.8173, 'learning_rate': 1.65171946970729e-05, 'epoch': 2.3}
████████▏ | 12291/15000 [56:55:37<11:54:33, 15.83s/it] 82%|████████▏ | 12292/15000 [56:55:52<11:39:06, 15.49s/it] 82%|████████▏ | 12293/15000 [56:56:06<11:28:36, 15.26s/it] 82%|████████▏ | 12294/15000 [56:56:21<11:20:35, 15.09s/it] 82%|████████▏ | 12295/15000 [56:56:36<11:13:57, 14.95s/it] 82%|████████▏ | 12296/15000 [56:56:50<11:10:35, 14.88s/it] 82%|████████▏ | 12297/15000 [56:57:05<11:08:52, 14.85s/it] 82%|████████▏ | 12298/15000 [56:57:42<16:06:01, 21.45s/it] 82%|████████▏ | 12299/15000 [56:57:57<14:33:04, 19.39s/it] 82%|████████▏ | 12300/15000 [56:58:11<13:28:48, 17.97s/it] 82%|████████▏ | 12300/15000 [56:58:11<13:28:48, 17.97s/it] 82%|████████▏ | 12301/15000 [56:58:26<12:43:35, 16.97s/it] 82%|████████▏<E29688>█▏ | 12300/15000 [56:58:11<13:27:53, 17.95s/it] 82%|████████▏ | 12300/15000 [56:58:12<13:27:53, 17.95s/it] 82%|████████▏ | 12301/15000 [56:58:26<12:45:36, 17.02s/it] 82%|████████▏ | 12302/15000 [56:58:41<12:11:41, 16.27s/it] 82%|████████▏ | 12303/15000 [56:58:55<11:50:21, 15.80s/it] 82%|████████▏ | 12304/15000 [56:59:10<11:33:35, 15.44s/it] 82%|████████▏ | 12305/15000 [56:59:25<11:24:39, 15.24s/it] 82%|████████▏ | 12306/15000 [56:59:40<11:18:01, 15.10s/it] 82%|████████▏ | 12307/15000 [56:59:54<11:11:31, 14.96s/it] 82%|████████▏ | 12308/15000 [57:00:09<11:06:42, 14.86s/it] 82%|████████▏ | 12309/15000 [57:00:46<16:04:23, 21.50s/it] 82%|████████▏ | 12310/15000 [57:01:00<14:32:13, 19.45s/it] 82%|████████▏ | 12311/15000 [57:0<>█▏ | 12300/15000 [56:58:11<13:29:34, 17.99s/it] 82%|████████▏ | 12300/15000 [56:58:11<13:29:34, 17.99s/it] 82%|████████▏ | 12301/15000 [56:58:26<12:44:52, 17.00s/it] 82%|████████▏ | 12302/15000 [56:58:41<12:11:59, 16.28s/it] 82%|████████▏ | 12303/15000 [56:58:55<11:51:40, 15.83s/it] 82%|████████▏ | 12304/15000 [56:59:10<11:34:11, 15.45s/it] 82%|████████▏ | 12305/15000 [56:59:25<11:24:57, 15.25s/it] 82%|████████▏ | 12306/15000 [56:59:39<11:16:31, 15.07s/it] 82%|████████▏ | 12307/15000 [56:59:54<11:11:33, 14.96s/it] 82%|████████▏ | 12308/15000 [57:00:09<11:06:07, 14.85s/it] 82%|████████▏ | 12309/15000 [57:00:46<16:03:38, 21.49s/it] 82%|████████▏ | 12310/15000 [57:01:00<14:31:28, 19.44s/it] 82%|████████▏ | 12311/15000 [57:0 | 12302/15000 [56:58:41<12:12:46, 16.30s/it] 82%|████████▏ | 12303/15000 [56:58:55<11:51:32, 15.83s/it] 82%|████████▏ | 12304/15000 [56:59:10<11:35:28, 15.48s/it] 82%|████████▏ | 12305/15000 [56:59:25<11:24:27, 15.24s/it] 82%|████████▏ | 12306/15000 [56:59:39<11:16:47, 15.07s/it] 82%|████████▏ | 12307/15000 [56:59:54<11:10:26, 14.94s/it] 82%|████████▏ | 12308/15000 [57:00:09<11:07:05, 14.87s/it] 82%|████████▏ | 12309/15000 [57:00:46<16:03:38, 21.49s/it] 82%|████████▏ | 12310/15000 [57:01:00<14:32:18, 19.46s/it] 82%|████████▏ | 12311/15000 [57:01:15<13:28:15, 18.03s/it] 82%|████████▏ | 12312/15000 [57:01:30<12:42:11, 17.01s/it] 82%|████████▏ | 12313/15000 [57:01:44<12:11:16, 16.33s/it] 82%|████████▏ | 12314/15000 [57:01:59<11:47:13, 15.80s/it] 82%|████████▏ | 12315/
{'loss': 0.814, 'learning_rate': 1.534809972415998e-05, 'epoch': 2.32}
{'loss': 0.814, 'learning_rate': 1.534809972415998e-05, 'epoch': 2.32}
12390/15000 [57:23:10<12:19:12, 16.99s/it] 83%|████████▎ | 12391/15000 [57:23:25<11:49:06, 16.31s/it] 83%|████████▎ | 12392/15000 [57:23:40<11:29:08, 15.85s/it] 83%|████████▎ | 12393/15000 [57:23:54<11:12:57, 15.49s/it] 83%|████████▎ | 12394/15000 [57:24:09<11:01:12, 15.22s/it] 83%|████████▎ | 12395/15000 [57:24:24<10:55:28, 15.10s/it] 83%|████████▎ | 12396/15000 [57:24:38<10:47:49, 14.93s/it] 83%|████████▎ | 12397/15000 [57:24:53<10:45:31, 14.88s/it] 83%|████████▎ | 12398/15000 [57:25:30<15:28:19, 21.41s/it] 83%|████████▎ | 12399/15000 [57:25:44<13:59:01, 19.35s/it] 83%|████████▎ | 12400/15000 [57:25:59<12:59:07, 17.98s/it] 83%|████████▎ | 12400/15000 [57:25:59<12:59:07, 17.98s/it] 83%|████████▎ | 12401/15000 [57:26:14<12:1 12390/15000 [57:23:10<12:19:30, 17.00s/it] 83%|████████▎ | 12391/15000 [57:23:25<11:49:30, 16.32s/it] 83%|████████▎ | 12392/15000 [57:23:40<11:27:53, 15.83s/it] 83%|████████▎ | 12393/15000 [57:23:54<11:13:05, 15.49s/it] 83%|████████▎ | 12394/15000 [57:24:09<11:03:37, 15.28s/it] 83%|████████▎ | 12395/15000 [57:24:24<10:53:34, 15.05s/it] 83%|████████▎ | 12396/15000 [57:24:38<10:48:40, 14.95s/it] 83%|████████▎ | 12397/15000 [57:24:53<10:44:48, 14.86s/it] 83%|████████▎ | 12398/15000 [57:25:30<15:27:56, 21.40s/it] 83%|████████▎ | 12399/15000 [57:25:44<13:59:17, 19.36s/it] 83%|████████▎ | 12400/15000 [57:25:59<12:58:36, 17.97s/it] 83%|████████▎ | 12400/15000 [57:25:59<12:58:36, 17.97s/it] 83%|████████▎ | 12401/15000 [57:26:14<12:1<><31>█▎ | 12394/15000 [57:24:09<11:01:50, 15.24s/it] 83%|████████▎ | 12395/15000 [57:24:24<10:53:49, 15.06s/it] 83%|████████▎ | 12396/15000 [57:24:38<10:48:34, 14.94s/it] 83%|████████▎ | 12397/15000 [57:24:53<10:45:35, 14.88s/it] 83%|████████▎ | 12398/15000 [57:25:30<15:27:52, 21.40s/it] 83%|████████▎ | 12399/15000 [57:25:44<13:59:57, 19.38s/it] 83%|████████▎ | 12400/15000 [57:25:59<12:58:56, 17.98s/it] 83%|████████▎ | 12400/15000 [57:25:59<12:58:56, 17.98s/it] 83%|████████▎ | 12401/15000 [57:26:14<12:17:15, 17.02s/it] 83%|████████▎ | 12402/15000 [57:26:28<11:46:59, 16.33s/it] 83%|████████▎ | 12403/15000 [57:26:43<11:25:40, 15.84s/it] 83%|████████▎ | 12404/15000 [57:26:58<11:09:10, 15.47s/it] 83%|████████▎ | 12405/15000 [57:8:22, 17.05s/it] 83%|████████▎ | 12402/15000 [57:26:29<11:47:21, 16.34s/it] 83%|████████▎ | 12403/15000 [57:26:43<11:25:21, 15.83s/it] 83%|████████▎ | 12404/15000 [57:26:58<11:09:08, 15.47s/it] 83%|████████▎ | 12405/15000 [57:27:12<10:58:23, 15.22s/it] 83%|████████▎ | 12406/15000 [57:27:27<10:48:59, 15.01s/it] 83%|████████▎ | 12407/15000 [57:27:42<10:43:45, 14.90s/it] 83%|████████▎ | 12408/15000 [57:27:56<10:41:53, 14.86s/it] 83%|████████▎ | 12409/15000 [57:28:11<10:40:06, 14.82s/it] 83%|████████▎ | 12410/15000 [57:28:48<15:20:13, 21.32s/it] 83%|████████▎ | 12411/15000 [57:29:02<13:51:34, 19.27s/it] 83%|████████▎ | 12412/15000 [57:29:17<12:52:08, 17.90s/it] 83%|████████▎ | 12413/15000 [57:29:31<12:10:21, 16.94s/it] 83%|████████▎ | 12414/15000 [57:29:46<11:38:37, 16.
{'loss': 0.816, 'learning_rate': 1.4218468069322578e-05, 'epoch': 2.34}
{'loss': 0.816, 'learning_rate': 1.4218468069322578e-05, 'epoch': 2.34}
:40<11:00:42, 15.81s/it] 83%|████████▎ | 12494/15000 [57:51:55<10:47:44, 15.51s/it] 83%|████████▎ | 12495/15000 [57:52:10<10:36:17, 15.24s/it] 83%|████████▎ | 12496/15000 [57:52:25<10:30:30, 15.11s/it] 83%|████████▎ | 12497/15000 [57:52:39<10:24:51, 14.98s/it] 83%|████████▎ | 12498/15000 [57:52:54<10:19:45, 14.86s/it] 83%|████████▎ | 12499/15000 [57:53:31<14:56:05, 21.50s/it] 83%|████████▎ | 12500/15000 [57:53:45<13:29:22, 19.43s/it] 83%|████████▎ | 12500/15000 [57:53:46<13:29:22, 19.43s/it] 83%|████████▎ | 12501/15000 [57:54:00<12:32:40, 18.07s/it] 83%|████████▎ | 12502/15000 [57:54:15<11:49:39, 17.05s/it] 83%|████████▎ | 12503/15000 [57:54:30<11:20:32, 16.35s/it] 83%|████████▎ | 12504/15000 [57:54:44<10:58:21, 15.83s/it] 8:40<11:00:46, 15.81s/it] 83%|████████▎ | 12494/15000 [57:51:55<10:48:30, 15.53s/it] 83%|████████▎ | 12495/15000 [57:52:10<10:35:55, 15.23s/it] 83%|████████▎ | 12496/15000 [57:52:25<10:31:01, 15.12s/it] 83%|████████▎ | 12497/15000 [57:52:39<10:24:19, 14.97s/it] 83%|████████▎ | 12498/15000 [57:52:54<10:20:16, 14.87s/it] 83%|████████▎ | 12499/15000 [57:53:31<14:54:15, 21.45s/it] 83%|████████▎ | 12500/15000 [57:53:45<13:29:32, 19.43s/it] 83%|████████▎ | 12500/15000 [57:53:46<13:29:32, 19.43s/it] 83%|████████▎ | 12501/15000 [57:54:00<12:34:00, 18.10s/it] 83%|████████▎ | 12502/15000 [57:54:15<11:50:41, 17.07s/it] 83%|████████▎ | 12503/15000 [57:54:30<11:19:49, 16.34s/it] 83%|████████▎ | 12504/15000 [57:54:44<10:58:51, 15.84s/it] 8000 [57:52:39<10:23:14, 14.94s/it] 83%|████████▎ | 12498/15000 [57:52:54<10:21:01, 14.89s/it] 83%|████████▎ | 12499/15000 [57:53:31<14:56:01, 21.50s/it] 83%|████████▎ | 12500/15000 [57:53:45<13:30:13, 19.45s/it] 83%|████████▎ | 12500/15000 [57:53:46<13:30:13, 19.45s/it] 83%|████████▎ | 12501/15000 [57:54:00<12:33:21, 18.09s/it] 83%|████████▎ | 12502/15000 [57:54:15<11:50:46, 17.07s/it] 83%|████████▎ | 12503/15000 [57:54:30<11:19:57, 16.34s/it] 83%|████████▎ | 12504/15000 [57:54:44<10:59:27, 15.85s/it] 83%|████████▎ | 12505/15000 [57:54:59<10:44:39, 15.50s/it] 83%|████████▎ | 12506/15000 [57:55:14<10:34:29, 15.26s/it] 83%|████████▎ | 12507/15000 [57:55:28<10:26:17, 15.07s/it] 83%|████████▎ | 12508/15000 [57:55:43<10:22:18, 14.3%|████████▎ | 12505/15000 [57:54:59<10:43:57, 15.49s/it] 83%|████████▎ | 12506/15000 [57:55:14<10:34:55, 15.27s/it] 83%|████████▎ | 12507/15000 [57:55:29<10:28:12, 15.12s/it] 83%|████████▎ | 12508/15000 [57:55:43<10:21:16, 14.96s/it] 83%|████████▎ | 12509/15000 [57:55:58<10:19:04, 14.91s/it] 83%|████████▎ | 12510/15000 [57:56:35<14:53:08, 21.52s/it] 83%|████████▎ | 12511/15000 [57:56:50<13:27:04, 19.46s/it] 83%|████████▎ | 12512/15000 [57:57:04<12:26:12, 18.00s/it] 83%|████████▎ | 12513/15000 [57:57:19<11:45:28, 17.02s/it] 83%|████████▎ | 12514/15000 [57:57:34<11:16:34, 16.33s/it] 83%|████████▎ | 12515/15000 [57:57:48<10:55:25, 15.83s/it] 83%|████████▎ | 12516/15000 [57:58:03<10:40:10, 15.46s/it] 83%|████████▎ | 12517/15000 [57:58:18<10:31:26, 15.26s/it] 83%|██
{'loss': 0.8186, 'learning_rate': 1.3128826348184887e-05, 'epoch': 2.36}
{'loss': 0.8186, 'learning_rate': 1.3128826348184887e-05, 'epoch': 2.36}
/it] 84%|████████▍ | 12597/15000 [58:20:25<10:02:15, 15.04s/it] 84%|████████▍ | 12598/15000 [58:20:40<9:56:07, 14.89s/it] 84%|████████▍ | 12599/15000 [58:20:54<9:52:48, 14.81s/it] 84%|████████▍ | 12600/15000 [58:21:31<14:18:24, 21.46s/it] 84%|████████▍ | 12600/15000 [58:21:31<14:18:24, 21.46s/it] 84%|████████▍ | 12601/15000 [58:21:46<12:58:17, 19.47s/it] 84%|████████▍ | 12602/15000 [58:22:01<12:00:51, 18.04s/it] 84%|████████▍ | 12603/15000 [58:22:15<11:18:15, 16.98s/it] 84%|████████▍ | 12604/15000 [58:22:30<10:50:20, 16.29s/it] 84%|████████▍ | 12605/15000 [58:22:45<10:30:38, 15.80s/it] 84%|████████▍ | 12606/15000 [58:22:59<10:16:20, 15.45s/it] 84%|████████▍ | 12607/15000 [58:23:14<10:07:57, 15.24s/it] 84%|██████/it] 84%|████████▍ | 12597/15000 [58:20:25<10:00:47, 15.00s/it] 84%|████████▍ | 12598/15000 [58:20:40<9:55:48, 14.88s/it] 84%|████████▍ | 12599/15000 [58:20:54<9:53:28, 14.83s/it] 84%|████████▍ | 12600/15000 [58:21:31<14:17:53, 21.45s/it] 84%|████████▍ | 12600/15000 [58:21:31<14:17:53, 21.45s/it] 84%|████████▍ | 12601/15000 [58:21:46<12:58:00, 19.46s/it] 84%|████████▍ | 12602/15000 [58:22:01<12:01:31, 18.05s/it] 84%|████████▍ | 12603/15000 [58:22:15<11:19:45, 17.02s/it] 84%|████████▍ | 12604/15000 [58:22:30<10:48:55, 16.25s/it] 84%|████████▍ | 12605/15000 [58:22:45<10:31:14, 15.81s/it] 84%|████████▍ | 12606/15000 [58:22:59<10:17:58, 15.49s/it] 84%|████████▍ | 12607/15000 [58:23:14<10:07:51, 15.24s/it] 84%|██████8, 21.47s/it] 84%|████████▍ | 12600/15000 [58:21:31<14:18:58, 21.47s/it] 84%|████████▍ | 12601/15000 [58:21:46<12:58:48, 19.48s/it] 84%|████████▍ | 12602/15000 [58:22:01<12:01:03, 18.04s/it] 84%|████████▍ | 12603/15000 [58:22:15<11:19:35, 17.01s/it] 84%|████████▍ | 12604/15000 [58:22:30<10:49:17, 16.26s/it] 84%|████████▍ | 12605/15000 [58:22:45<10:30:51, 15.80s/it] 84%|████████▍ | 12606/15000 [58:22:59<10:17:37, 15.48s/it] 84%|████████▍ | 12607/15000 [58:23:14<10:08:20, 15.25s/it] 84%|████████▍ | 12608/15000 [58:23:29<10:02:15, 15.11s/it] 84%|████████▍ | 12609/15000 [58:23:43<9:57:39, 15.00s/it] 84%|████████▍ | 12610/15000 [58:23:58<9:53:18, 14.89s/it] 84%|████████▍ | 12611/15000 [58:24:35<14:18:30, 21.56s/it] 84%|█████▍ | 12608/15000 [58:23:29<10:01:38, 15.09s/it] 84%|████████▍ | 12609/15000 [58:23:43<9:57:05, 14.98s/it] 84%|████████▍ | 12610/15000 [58:23:58<9:54:55, 14.94s/it] 84%|████████▍ | 12611/15000 [58:24:35<14:18:23, 21.56s/it] 84%|████████▍ | 12612/15000 [58:24:50<12:56:14, 19.50s/it] 84%|████████▍ | 12613/15000 [58:25:05<11:58:26, 18.06s/it] 84%|████████▍ | 12614/15000 [58:25:19<11:17:03, 17.03s/it] 84%|████████▍ | 12615/15000 [58:25:34<10:49:29, 16.34s/it] 84%|████████▍ | 12616/15000 [58:25:49<10:28:10, 15.81s/it] 84%|████████▍ | 12617/15000 [58:26:03<10:15:35, 15.50s/it] 84%|████████▍ | 12618/15000 [58:26:18<10:05:04, 15.24s/it] 84%|████████▍ | 12619/15000 [58:26:33<9:56:51, 15.04s/it] 84%|████████▍ | 12620/15000 [58:26:47<9:52:45, 14.94s/it] 84%|████████▍ |
{'loss': 0.8146, 'learning_rate': 1.2079682533724379e-05, 'epoch': 2.38}
{'loss': 0.8146, 'learning_rate': 1.2079682533724379e-05, 'epoch': 2.38}
████▍ | 12691/15000 [58:46:46<11:32:46, 18.00s/it] 85%|████████▍ | 12692/15000 [58:47:01<10:55:19, 17.04s/it] 85%|████████▍ | 12693/15000 [58:47:16<10:27:55, 16.33s/it] 85%|████████▍ | 12694/15000 [58:47:31<10:08:56, 15.84s/it] 85%|████████▍ | 12695/15000 [58:47:45<9:55:57, 15.51s/it] 85%|████████▍ | 12696/15000 [58:48:00<9:45:10, 15.24s/it] 85%|████████▍ | 12697/15000 [58:48:15<9:38:17, 15.07s/it] 85%|████████▍ | 12698/15000 [58:48:29<9:33:53, 14.96s/it] 85%|████████▍ | 12699/15000 [58:48:44<9:30:48, 14.88s/it] 85%|████████▍ | 12700/15000 [58:48:59<9:28:30, 14.83s/it] 85%|████████▍ | 12700/15000 [58:48:59<9:28:30, 14.83s/it] 85%|████████▍ | 12701/15000 [58:49:36<13:45:21, 21.54s/it] 85%|████████▍ | 12702/15000 [58:/15000 [58:48:59<9:27:48, 14.81s/it] 85%|████████▍ | 12700/15000 [58:48:59<9:27:48, 14.81s/it] 85%|████████▍ | 12701/15000 [58:49:36<13:44:42, 21.52s/it] 85%|████████▍ | 12702/15000 [58:49:51<12:25:57, 19.48s/it] 85%|████████▍ | 12703/15000 [58:50:05<11:31:08, 18.05s/it] 85%|████████▍ | 12704/15000 [58:50:20<10:50:41, 17.00s/it] 85%|████████▍ | 12705/15000 [58:50:35<10:24:09, 16.32s/it] 85%|████████▍ | 12706/15000 [58:50:49<10:05:06, 15.83s/it] 85%|████████▍ | 12707/15000 [58:51:04<9:49:59, 15.44s/it] 85%|████████▍ | 12708/15000 [58:51:19<9:43:25, 15.27s/it] 85%|████████▍ | 12709/15000 [58:51:34<9:36:59, 15.11s/it] 85%|████████▍ | 12710/15000 [58:51:48<9:31:23, 14.97s/it] 85%|████████▍ | 12711/15000 [58:52:03<9:26:08, 14.84s//15000 [58:48:59<9:27:49, 14.81s/it] 85%|████████▍ | 12700/15000 [58:48:59<9:27:49, 14.81s/it] 85%|████████▍ | 12701/15000 [58:49:36<13:44:25, 21.52s/it] 85%|████████▍ | 12702/15000 [58:49:51<12:26:10, 19.48s/it] 85%|████████▍ | 12703/15000 [58:50:05<11:30:55, 18.05s/it] 85%|████████▍ | 12704/15000 [58:50:20<10:51:33, 17.03s/it] 85%|████████▍ | 12705/15000 [58:50:35<10:23:57, 16.31s/it] 85%|████████▍ | 12706/15000 [58:50:49<10:05:59, 15.85s/it] 85%|████████▍ | 12707/15000 [58:51:04<9:50:53, 15.46s/it] 85%|████████▍ | 12708/15000 [58:51:19<9:42:36, 15.25s/it] 85%|████████▍ | 12709/15000 [58:51:33<9:35:55, 15.08s/it] 85%|████████▍ | 12710/15000 [58:51:48<9:31:37, 14.98s/it] 85%|████████▍ | 12711/15000 [58:52:03<9:26:56, 14.86s/49:51<12:25:10, 19.46s/it] 85%|████████▍ | 12703/15000 [58:50:05<11:30:30, 18.04s/it] 85%|████████▍ | 12704/15000 [58:50:20<10:51:19, 17.02s/it] 85%|████████▍ | 12705/15000 [58:50:35<10:24:36, 16.33s/it] 85%|████████▍ | 12706/15000 [58:50:49<10:04:41, 15.82s/it] 85%|████████▍ | 12707/15000 [58:51:04<9:51:24, 15.48s/it] 85%|████████▍ | 12708/15000 [58:51:19<9:42:42, 15.25s/it] 85%|████████▍ | 12709/15000 [58:51:33<9:36:36, 15.10s/it] 85%|████████▍ | 12710/15000 [58:51:48<9:30:34, 14.95s/it] 85%|████████▍ | 12711/15000 [58:52:03<9:26:54, 14.86s/it] 85%|████████▍ | 12712/15000 [58:52:40<13:39:43, 21.50s/it] 85%|████████▍ | 12713/15000 [58:52:54<12:20:18, 19.42s/it] 85%|████████▍ | 12714/15000 [58:53:09<11:25:37, 18.00s/it] 85%|████████▍ | 12715/15000 [58:53:24<10:47:1
{'loss': 0.8176, 'learning_rate': 1.1071525719463095e-05, 'epoch': 2.4}
{'loss': 0.8176, 'learning_rate': 1.1071525719463095e-05, 'epoch': 2.4}
<EFBFBD>█████▌ | 12791/15000 [59:14:32<11:53:24, 19.38s/it] 85%|████████▌ | 12792/15000 [59:14:47<11:00:57, 17.96s/it] 85%|████████▌ | 12793/15000 [59:15:02<10:24:46, 16.99s/it] 85%|████████▌ | 12794/15000 [59:15:16<9:59:14, 16.30s/it] 85%|████████▌ | 12795/15000 [59:15:31<9:40:03, 15.78s/it] 85%|████████▌ | 12796/15000 [59:15:46<9:27:12, 15.44s/it] 85%|████████▌ | 12797/15000 [59:16:00<9:19:36, 15.24s/it] 85%|████████▌ | 12798/15000 [59:16:15<9:13:58, 15.09s/it] 85%|████████▌ | 12799/15000 [59:16:30<9:09:33, 14.98s/it] 85%|████████▌ | 12800/15000 [59:16:45<9:06:09, 14.90s/it] 85%|████████▌ | 12800/15000 [59:16:45<9:06:09, 14.90s/it] 85%|████████▌ | 12801/15000 [59:17:22<13:10:01, 21.56s/it] 85%|████████▌ | 12802/15000 [<5B>█████▌ | 12791/15000 [59:14:32<11:53:50, 19.39s/it] 85%|████████▌ | 12792/15000 [59:14:47<11:01:29, 17.98s/it] 85%|████████▌ | 12793/15000 [59:15:02<10:23:23, 16.95s/it] 85%|████████▌ | 12794/15000 [59:15:16<9:58:35, 16.28s/it] 85%|████████▌ | 12795/15000 [59:15:31<9:40:29, 15.80s/it] 85%|████████▌ | 12796/15000 [59:15:46<9:28:19, 15.47s/it] 85%|████████▌ | 12797/15000 [59:16:00<9:19:24, 15.24s/it] 85%|████████▌ | 12798/15000 [59:16:15<9:14:34, 15.11s/it] 85%|████████▌ | 12799/15000 [59:16:30<9:08:36, 14.96s/it] 85%|████████▌ | 12800/15000 [59:16:45<9:06:03, 14.89s/it] 85%|████████▌ | 12800/15000 [59:16:45<9:06:03, 14.89s/it] 85%|████████▌ | 12801/15000 [59:17:22<13:10:39, 21.57s/it] 85%|████████▌ | 12802/15000 [|████████▌ | 12795/15000 [59:15:31<9:40:33, 15.80s/it] 85%|████████▌ | 12796/15000 [59:15:46<9:28:10, 15.47s/it] 85%|████████▌ | 12797/15000 [59:16:00<9:20:17, 15.26s/it] 85%|████████▌ | 12798/15000 [59:16:15<9:14:23, 15.11s/it] 85%|████████▌ | 12799/15000 [59:16:30<9:09:43, 14.99s/it] 85%|████████▌ | 12800/15000 [59:16:44<9:05:05, 14.87s/it] 85%|████████▌ | 12800/15000 [59:16:45<9:05:05, 14.87s/it] 85%|████████▌ | 12801/15000 [59:17:22<13:10:10, 21.56s/it] 85%|████████▌ | 12802/15000 [59:17:36<11:54:23, 19.50s/it] 85%|████████▌ | 12803/15000 [59:17:51<11:00:52, 18.05s/it] 85%|████████▌ | 12804/15000 [59:18:06<10:23:05, 17.02s/it] 85%|████████▌ | 12805/15000 [59:18:20<9:57:45, 16.34s/it] 85%|████████▌ | 128059:17:36<11:54:29, 19.50s/it] 85%|████████▌ | 12803/15000 [59:17:51<11:01:10, 18.06s/it] 85%|████████▌ | 12804/15000 [59:18:06<10:23:59, 17.05s/it] 85%|████████▌ | 12805/15000 [59:18:20<9:56:27, 16.30s/it] 85%|████████▌ | 12806/15000 [59:18:35<9:38:50, 15.83s/it] 85%|████████▌ | 12807/15000 [59:18:50<9:26:43, 15.51s/it] 85%|████████▌ | 12808/15000 [59:19:04<9:17:08, 15.25s/it] 85%|████████▌ | 12809/15000 [59:19:19<9:11:13, 15.10s/it] 85%|████████▌ | 12810/15000 [59:19:34<9:06:51, 14.98s/it] 85%|████████▌ | 12811/15000 [59:19:48<9:01:56, 14.85s/it] 85%|████████▌ | 12812/15000 [59:20:25<13:02:57, 21.47s/it] 85%|████████▌ | 12813/15000 [59:20:41<11:53:32, 19.58s/it] 85%|████████▌ | 12814/15000 [59:20:55<10:59:15, 18.09s/it] 85%|████████▌ | 12815/15000 [59:21:10<10:21:
{'loss': 0.8143, 'learning_rate': 1.010482589146048e-05, 'epoch': 2.41}
{'loss': 0.8143, 'learning_rate': 1.010482589146048e-05, 'epoch': 2.41}
<EFBFBD>█████▌ | 12895/15000 [59:43:19<9:30:13, 16.25s/it] 86%|████████▌ | 12896/15000 [59:43:33<9:13:24, 15.78s/it] 86%|████████▌ | 12897/15000 [59:43:48<9:01:11, 15.44s/it] 86%|████████▌ | 12898/15000 [59:44:03<8:53:11, 15.22s/it] 86%|████████▌ | 12899/15000 [59:44:17<8:48:20, 15.09s/it] 86%|████████▌ | 12900/15000 [59:44:32<8:42:05, 14.92s/it] 86%|████████▌ | 12900/15000 [59:44:32<8:42:05, 14.92s/it] 86%|████████▌ | 12901/15000 [59:44:47<8:41:48, 14.92s/it] 86%|████████▌ | 12902/15000 [59:45:24<12:29:41, 21.44s/it] 86%|████████▌ | 12903/15000 [59:45:38<11:19:14, 19.43s/it] 86%|████████▌ | 12904/15000 [59:45:53<10:29:16, 18.01s/it] 86%|████████▌ | 12905/15000 [59:46:08<9:53:21, 16.99s/it] 86%|████████▌ | 12906/15000 [5<>█████▌ | 12895/15000 [59:43:19<9:31:10, 16.28s/it] 86%|████████▌ | 12896/15000 [59:43:33<9:12:09, 15.75s/it] 86%|████████▌ | 12897/15000 [59:43:48<9:02:02, 15.46s/it] 86%|████████▌ | 12898/15000 [59:44:03<8:52:18, 15.19s/it] 86%|████████▌ | 12899/15000 [59:44:17<8:47:07, 15.05s/it] 86%|████████▌ | 12900/15000 [59:44:32<8:41:57, 14.91s/it] 86%|████████▌ | 12900/15000 [59:44:32<8:41:57, 14.91s/it] 86%|████████▌ | 12901/15000 [59:44:47<8:42:09, 14.93s/it] 86%|████████▌ | 12902/15000 [59:45:23<12:29:06, 21.42s/it] 86%|████████▌ | 12903/15000 [59:45:38<11:18:57, 19.43s/it] 86%|████████▌ | 12904/15000 [59:45:53<10:29:12, 18.01s/it] 86%|████████▌ | 12905/15000 [59:46:08<9:52:42, 16.98s/it] 86%|████████▌ | 12906/15000 [5███████▌ | 12899/15000 [59:44:17<8:47:15, 15.06s/it] 86%|████████▌ | 12900/15000 [59:44:32<8:43:25, 14.96s/it] 86%|████████▌ | 12900/15000 [59:44:32<8:43:25, 14.96s/it] 86%|████████▌ | 12901/15000 [59:44:47<8:41:51, 14.92s/it] 86%|████████▌ | 12902/15000 [59:45:23<12:29:11, 21.43s/it] 86%|████████▌ | 12903/15000 [59:45:38<11:17:52, 19.40s/it] 86%|████████▌ | 12904/15000 [59:45:53<10:27:59, 17.98s/it] 86%|████████▌ | 12905/15000 [59:46:08<9:53:34, 17.00s/it] 86%|████████▌ | 12906/15000 [59:46:22<9:29:25, 16.32s/it] 86%|████████▌ | 12907/15000 [59:46:37<9:11:51, 15.82s/it] 86%|████████▌ | 12908/15000 [59:46:52<8:59:01, 15.46s/it] 86%|████████▌ | 12909/15000 [59:47:06<8:50:30, 15.22s/it] 86%|████████▌ | 12910/1509:46:22<9:28:48, 16.30s/it] 86%|████████▌ | 12907/15000 [59:46:37<9:10:57, 15.79s/it] 86%|████████▌ | 12908/15000 [59:46:52<9:00:03, 15.49s/it] 86%|████████▌ | 12909/15000 [59:47:06<8:51:02, 15.24s/it] 86%|████████▌ | 12910/15000 [59:47:21<8:44:09, 15.05s/it] 86%|████████▌ | 12911/15000 [59:47:36<8:39:18, 14.92s/it] 86%|████████▌ | 12912/15000 [59:47:50<8:37:16, 14.86s/it] 86%|████████▌ | 12913/15000 [59:48:27<12:24:57, 21.42s/it] 86%|████████▌ | 12914/15000 [59:48:42<11:15:31, 19.43s/it] 86%|████████▌ | 12915/15000 [59:48:56<10:24:55, 17.98s/it] 86%|████████▌ | 12916/15000 [59:49:11<9:50:39, 17.01s/it] 86%|████████▌ | 12917/15000 [59:49:26<9:25:58, 16.30s/it] 86%|████████▌ | 12918/15000 [59:49:40<9:08:24, 15.80s/it] 86%|████████▌ | 12919/15000 [59:49:55<8:56:31, 1
{'loss': 0.8161, 'learning_rate': 9.180033709213454e-06, 'epoch': 2.43}
{'loss': 0.8161, 'learning_rate': 9.180033709213454e-06, 'epoch': 2.43}
87%|████████▋ | 12990/15000 [60:09:31<8:17:57, 14.86s/it] 87%|████████▋ | 12991/15000 [60:10:07<11:54:13, 21.33s/it] 87%|████████▋ | 12992/15000 [60:10:22<10:47:08, 19.34s/it] 87%|████████▋ | 12993/15000 [60:10:37<9:59:53, 17.93s/it] 87%|████████▋ | 12994/15000 [60:10:51<9:26:40, 16.95s/it] 87%|████████▋ | 12995/15000 [60:11:06<9:04:31, 16.30s/it] 87%|████████▋ | 12996/15000 [60:11:21<8:47:33, 15.80s/it] 87%|████████▋ | 12997/15000 [60:11:35<8:36:11, 15.46s/it] 87%|████████▋ | 12998/15000 [60:11:50<8:28:41, 15.25s/it] 87%|████████▋ | 12999/15000 [60:12:05<8:21:38, 15.04s/it] 87%|████████▋ | 13000/15000 [60:12:19<8:17:36, 14.93s/it] 87%|████████▋ | 13000/15000 [60:12:20<8:17:36, 14.93s/it] 87%|████████▋ | 13<31><33>█▋ | 12999/15000 [60:12:05<8:23:15, 15.09s/it] 87%|████████▋ | 13000/15000 [60:12:20<8:17:57, 14.94s/it] 87%|████████▋ | 13000/15000 [60:12:20<8:17:57, 14.94s/it] 87%|████████▋ | 13001/15000 [60:12:34<8:16:50, 14.91s/it] 87%|████████▋ | 13002/15000 [60:12:49<8:14:03, 14.84s/it] 87%|████████▋ | 13003/15000 [60:13:26<11:50:10, 21.34s/it] 87%|████████▋ | 13004/15000 [60:13:40<10:41:58, 19.30s/it] 87%|████████▋ | 13005/15000 [60:13:55<9:56:12, 17.93s/it] 87%|████████▋ | 13006/15000 [60:14:10<9:23:19, 16.95s/it] 87%|████████▋ | 13007/15000 [60:14:24<8:59:52, 16.25s/it] 87%|████████▋ | 13008/15000 [60:14:39<8:44:30, 15.80s/it] 87%|████████▋ | 13009/15000 [60:14:54<8:33:04, 15.46s/it] 87%|████████▋ | 13010/15000 [60:15:08<8:24<32><34>█▋ | 12999/15000 [60:12:05<8:22:35, 15.07s/it] 87%|████████▋ | 13000/15000 [60:12:20<8:18:09, 14.94s/it] 87%|████████▋ | 13000/15000 [60:12:20<8:18:09, 14.94s/it] 87%|████████▋ | 13001/15000 [60:12:34<8:15:55, 14.89s/it] 87%|████████▋ | 13002/15000 [60:12:49<8:14:57, 14.86s/it] 87%|████████▋ | 13003/15000 [60:13:26<11:49:33, 21.32s/it] 87%|████████▋ | 13004/15000 [60:13:40<10:42:16, 19.31s/it] 87%|████████▋ | 13005/15000 [60:13:55<9:55:59, 17.92s/it] 87%|████████▋ | 13006/15000 [60:14:09<9:22:58, 16.94s/it] 87%|████████▋ | 13007/15000 [60:14:24<8:59:17, 16.24s/it] 87%|████████▋ | 13008/15000 [60:14:39<8:44:40, 15.80s/it] 87%|████████▋ | 13009/15000 [60:14:54<8:33:31, 15.48s/it] 87%|████████▋ | 13010/15000 [60:15:08<8:24001/15000 [60:12:34<8:16:37, 14.91s/it] 87%|████████▋ | 13002/15000 [60:12:49<8:15:01, 14.87s/it] 87%|████████▋ | 13003/15000 [60:13:25<11:49:10, 21.31s/it] 87%|████████▋ | 13004/15000 [60:13:40<10:42:19, 19.31s/it] 87%|████████▋ | 13005/15000 [60:13:55<9:56:11, 17.93s/it] 87%|████████▋ | 13006/15000 [60:14:09<9:22:44, 16.93s/it] 87%|████████▋ | 13007/15000 [60:14:24<9:00:42, 16.28s/it] 87%|████████▋ | 13008/15000 [60:14:39<8:44:07, 15.79s/it] 87%|████████▋ | 13009/15000 [60:14:53<8:33:03, 15.46s/it] 87%|████████▋ | 13010/15000 [60:15:08<8:25:02, 15.23s/it] 87%|████████▋ | 13011/15000 [60:15:23<8:18:53, 15.05s/it] 87%|████████▋ | 13012/15000 [60:15:38<8:15:38, 14.96s/it] 87%|████████▋ | 13013/15000 [60:15:52<8:12:48, 14.88s/it] 87%|████████▋ | 13014/15000 [60:16:29
{'loss': 0.8164, 'learning_rate': 8.297580295566575e-06, 'epoch': 2.45}
{'loss': 0.8164, 'learning_rate': 8.297580295566575e-06, 'epoch': 2.45}
<EFBFBD><EFBFBD>█▋ | 13090/15000 [60:37:17<7:55:39, 14.94s/it] 87%|████████▋ | 13091/15000 [60:37:31<7:52:56, 14.86s/it] 87%|████████▋ | 13092/15000 [60:38:08<11:23:44, 21.50s/it] 87%|████████▋ | 13093/15000 [60:38:23<10:17:21, 19.42s/it] 87%|████████▋ | 13094/15000 [60:38:38<9:31:40, 18.00s/it] 87%|████████▋ | 13095/15000 [60:38:52<9:01:04, 17.04s/it] 87%|████████▋ | 13096/15000 [60:39:07<8:36:22, 16.27s/it] 87%|████████▋ | 13097/15000 [60:39:22<8:20:01, 15.77s/it] 87%|████████▋ | 13098/15000 [60:39:36<8:10:03, 15.46s/it] 87%|████████▋ | 13099/15000 [60:39:51<8:01:54, 15.21s/it] 87%|████████▋ | 13100/15000 [60:40:06<7:56:59, 15.06s/it] 87%|████████▋ | 13100/15000 [60:40:06<7:56:59, 15.06s/it] 87%|████████▋ | 13101/15000 [60:40:20<7:53<35><33>█▋ | 13090/15000 [60:37:17<7:55:28, 14.94s/it] 87%|████████▋ | 13091/15000 [60:37:31<7:53:46, 14.89s/it] 87%|████████▋ | 13092/15000 [60:38:08<11:23:35, 21.50s/it] 87%|████████▋ | 13093/15000 [60:38:23<10:17:06, 19.42s/it] 87%|████████▋ | 13094/15000 [60:38:38<9:32:31, 18.02s/it] 87%|████████▋ | 13095/15000 [60:38:52<9:00:25, 17.02s/it] 87%|████████▋ | 13096/15000 [60:39:07<8:37:24, 16.30s/it] 87%|████████▋ | 13097/15000 [60:39:22<8:20:18, 15.77s/it] 87%|████████▋ | 13098/15000 [60:39:36<8:09:21, 15.44s/it] 87%|████████▋ | 13099/15000 [60:39:51<8:02:33, 15.23s/it] 87%|████████▋ | 13100/15000 [60:40:06<7:56:30, 15.05s/it] 87%|████████▋ | 13100/15000 [60:40:06<7:56:30, 15.05s/it] 87%|████████▋ | 13101/15000 [60:40:20<7:54<35><34>███▋ | 13094/15000 [60:38:38<9:32:03, 18.01s/it] 87%|████████▋ | 13095/15000 [60:38:52<8:59:04, 16.98s/it] 87%|████████▋ | 13096/15000 [60:39:07<8:36:42, 16.28s/it] 87%|████████▋ | 13097/15000 [60:39:21<8:20:12, 15.77s/it] 87%|████████▋ | 13098/15000 [60:39:36<8:10:08, 15.46s/it] 87%|████████▋ | 13099/15000 [60:39:51<8:02:32, 15.23s/it] 87%|████████▋ | 13100/15000 [60:40:06<7:57:00, 15.06s/it] 87%|████████▋ | 13100/15000 [60:40:06<7:57:00, 15.06s/it] 87%|████████▋ | 13101/15000 [60:40:20<7:54:53, 15.00s/it] 87%|████████▋ | 13102/15000 [60:40:35<7:51:46, 14.91s/it] 87%|████████▋ | 13103/15000 [60:41:12<11:19:48, 21.50s/it] 87%|████████▋ | 13104/15000 [60:41:27<10:14:04, 19.43s/it] 87%|████████▋ | 13105/15000 [60:41:4:48, 14.97s/it] 87%|████████▋ | 13102/15000 [60:40:35<7:51:21, 14.90s/it] 87%|████████▋ | 13103/15000 [60:41:12<11:19:57, 21.51s/it] 87%|████████▋ | 13104/15000 [60:41:27<10:14:36, 19.45s/it] 87%|████████▋ | 13105/15000 [60:41:41<9:28:46, 18.01s/it] 87%|████████▋ | 13106/15000 [60:41:56<8:58:22, 17.06s/it] 87%|████████▋ | 13107/15000 [60:42:11<8:35:14, 16.33s/it] 87%|████████▋ | 13108/15000 [60:42:25<8:19:03, 15.83s/it] 87%|████████▋ | 13109/15000 [60:42:40<8:08:14, 15.49s/it] 87%|████████▋ | 13110/15000 [60:42:55<7:59:56, 15.24s/it] 87%|████████▋ | 13111/15000 [60:43:09<7:54:31, 15.07s/it] 87%|████████▋ | 13112/15000 [60:43:24<7:50:02, 14.94s/it] 87%|████████▋ | 13113/15000 [60:43:39<7:47:25, 14.86s/it] 87%|████████▋ | 13114/15000 [60:43:54<7:45:54, 14.82s/it] 87
{'loss': 0.8264, 'learning_rate': 7.457877035729588e-06, 'epoch': 2.47}
{'loss': 0.8264, 'learning_rate': 7.457877035729588e-06, 'epoch': 2.47}
[61:06:26<9:46:24, 19.48s/it] 88%|████████▊ | 13195/15000 [61:06:40<9:01:46, 18.01s/it] 88%|████████▊ | 13196/15000 [61:06:55<8:31:44, 17.02s/it] 88%|████████▊ | 13197/15000 [61:07:10<8:11:05, 16.34s/it] 88%|████████▊ | 13198/15000 [61:07:24<7:54:42, 15.81s/it] 88%|████████▊ | 13199/15000 [61:07:39<7:44:37, 15.48s/it] 88%|████████▊ | 13200/15000 [61:07:54<7:36:21, 15.21s/it] 88%|████████▊ | 13200/15000 [61:07:54<7:36:21, 15.21s/it] 88%|████████▊ | 13201/15000 [61:08:08<7:32:12, 15.08s/it] 88%|████████▊ | 13202/15000 [61:08:23<7:29:23, 15.00s/it] 88%|████████▊ | 13203/15000 [61:08:38<7:26:45, 14.92s/it] 88%|████████▊ | 13204/15000 [61:09:15<10:44:24, 21.53s/it] 88%|████████▊ | 13205/15000 [61:09:29<9:42:09, 19.46s/it] 88%|<7C> [61:06:26<9:46:25, 19.48s/it] 88%|████████▊ | 13195/15000 [61:06:40<9:02:12, 18.02s/it] 88%|████████▊ | 13196/15000 [61:06:55<8:32:01, 17.03s/it] 88%|████████▊ | 13197/15000 [61:07:09<8:09:23, 16.29s/it] 88%|████████▊ | 13198/15000 [61:07:24<7:56:06, 15.85s/it] 88%|████████▊ | 13199/15000 [61:07:39<7:45:02, 15.49s/it] 88%|████████▊ | 13200/15000 [61:07:54<7:36:35, 15.22s/it] 88%|████████▊ | 13200/15000 [61:07:54<7:36:35, 15.22s/it] 88%|████████▊ | 13201/15000 [61:08:08<7:31:41, 15.06s/it] 88%|████████▊ | 13202/15000 [61:08:23<7:29:03, 14.99s/it] 88%|████████▊ | 13203/15000 [61:08:38<7:26:27, 14.91s/it] 88%|████████▊ | 13204/15000 [61:09:15<10:45:07, 21.55s/it] 88%|████████▊ | 13205/15000 [61:09:29<9:42:55, 19.48s/it] 88%|<7C>15000 [61:07:24<7:54:58, 15.81s/it] 88%|████████▊ | 13199/15000 [61:07:39<7:45:02, 15.49s/it] 88%|████████▊ | 13200/15000 [61:07:53<7:36:33, 15.22s/it] 88%|████████▊ | 13200/15000 [61:07:54<7:36:33, 15.22s/it] 88%|████████▊ | 13201/15000 [61:08:08<7:33:09, 15.11s/it] 88%|████████▊ | 13202/15000 [61:08:23<7:29:40, 15.01s/it] 88%|████████▊ | 13203/15000 [61:08:38<7:25:40, 14.88s/it] 88%|████████▊ | 13204/15000 [61:09:15<10:44:19, 21.53s/it] 88%|████████▊ | 13205/15000 [61:09:29<9:42:45, 19.48s/it] 88%|████████▊ | 13206/15000 [61:09:44<8:59:44, 18.05s/it] 88%|████████▊ | 13207/15000 [61:09:59<8:29:37, 17.05s/it] 88%|████████▊ | 13208/15000 [61:10:13<8:07:30, 16.32s/it] 88%|████████▊ | 13209/15000 [61:10:28<7:52:05, 15.82s/it] 8<><38>███████▊ | 13206/15000 [61:09:44<8:58:45, 18.02s/it] 88%|████████▊ | 13207/15000 [61:09:59<8:29:04, 17.04s/it] 88%|████████▊ | 13208/15000 [61:10:14<8:08:09, 16.34s/it] 88%|████████▊ | 13209/15000 [61:10:28<7:52:05, 15.82s/it] 88%|████████▊ | 13210/15000 [61:10:43<7:41:59, 15.49s/it] 88%|████████▊ | 13211/15000 [61:10:58<7:35:05, 15.26s/it] 88%|████████▊ | 13212/15000 [61:11:12<7:29:24, 15.08s/it] 88%|████████▊ | 13213/15000 [61:11:27<7:26:30, 14.99s/it] 88%|████████▊ | 13214/15000 [61:11:42<7:23:55, 14.91s/it] 88%|████████▊ | 13215/15000 [61:12:19<10:40:05, 21.52s/it] 88%|████████▊ | 13216/15000 [61:12:33<9:37:58, 19.44s/it] 88%|████████▊ | 13217/15000 [61:12:48<8:55:14, 18.01s/it] 88%|████████▊ | 13218/15000 [61:13:03<8:25:57, 17.04s/it] 88%|███████
{'loss': 0.8354, 'learning_rate': 6.661315385496425e-06, 'epoch': 2.49}
{'loss': 0.8354, 'learning_rate': 6.661315385496425e-06, 'epoch': 2.49}
1:32:39<7:14:21, 15.23s/it] 89%|████████▊ | 13290/15000 [61:32:54<7:09:53, 15.08s/it] 89%|████████▊ | 13291/15000 [61:33:08<7:05:31, 14.94s/it] 89%|████████▊ | 13292/15000 [61:33:23<7:02:54, 14.86s/it] 89%|████████▊ | 13293/15000 [61:33:37<7:00:56, 14.80s/it] 89%|████████▊ | 13294/15000 [61:34:14<10:10:09, 21.46s/it] 89%|████████▊ | 13295/15000 [61:34:29<9:11:51, 19.42s/it] 89%|████████▊ | 13296/15000 [61:34:44<8:30:41, 17.98s/it] 89%|████████▊ | 13297/15000 [61:34:59<8:02:42, 17.01s/it] 89%|████████▊ | 13298/15000 [61:35:13<7:42:38, 16.31s/it] 89%|████████▊ | 13299/15000 [61:35:28<7:28:24, 15.82s/it] 89%|████████▊ | 13300/15000 [61:35:43<7:18:16, 15.47s/it] 89%|████████▊ | 13300/15000 [61:35:43<7:18:16, 15.47s/it] 89%|█<><E29688>t] 89%|████████▊ | 13299/15000 [61:35:28<7:28:13, 15.81s/it] 89%|████████▊ | 13300/15000 [61:35:43<7:18:40, 15.48s/it] 89%|████████▊ | 13300/15000 [61:35:43<7:18:40, 15.48s/it] 89%|████████▊ | 13301/15000 [61:35:58<7:14:22, 15.34s/it] 89%|████████▊ | 13302/15000 [61:36:12<7:06:51, 15.08s/it] 89%|████████▊ | 13303/15000 [61:36:27<7:05:13, 15.03s/it] 89%|████████▊ | 13304/15000 [61:36:42<7:01:53, 14.93s/it] 89%|████████▊ | 13305/15000 [61:37:19<10:08:46, 21.55s/it] 89%|████████▊ | 13306/15000 [61:37:33<9:08:59, 19.44s/it] 89%|████████▊ | 13307/15000 [61:37:48<8:29:05, 18.04s/it] 89%|████████▊ | 13308/15000 [61:38:03<8:00:01, 17.02s/it] 89%|████████▊ | 13309/15000 [61:38:17<7:40:03, 16.32s/it] 89%|████████▊ | t] 89%|████████▊ | 13299/15000 [61:35:28<7:28:13, 15.81s/it] 89%|████████▊ | 13300/15000 [61:35:43<7:18:55, 15.49s/it] 89%|████████▊ | 13300/15000 [61:35:43<7:18:55, 15.49s/it] 89%|████████▊ | 13301/15000 [61:35:58<7:14:53, 15.36s/it] 89%|████████▊ | 13302/15000 [61:36:12<7:07:10, 15.09s/it] 89%|████████▊ | 13303/15000 [61:36:27<7:04:33, 15.01s/it] 89%|████████▊ | 13304/15000 [61:36:42<7:01:53, 14.93s/it] 89%|████████▊ | 13305/15000 [61:37:19<10:07:57, 21.52s/it] 89%|████████▊ | 13306/15000 [61:37:33<9:09:19, 19.46s/it] 89%|████████▊ | 13307/15000 [61:37:48<8:29:00, 18.04s/it] 89%|████████▊ | 13308/15000 [61:38:03<7:59:41, 17.01s/it] 89%|████████▊ | 13309/15000 [61:38:17<7:39:45, 16.31s/it] 89%|████████▊ | <20>██████▊ | 13301/15000 [61:35:58<7:13:52, 15.32s/it] 89%|████████▊ | 13302/15000 [61:36:12<7:08:14, 15.13s/it] 89%|████████▊ | 13303/15000 [61:36:27<7:04:33, 15.01s/it] 89%|████████▊ | 13304/15000 [61:36:42<7:00:57, 14.89s/it] 89%|████████▊ | 13305/15000 [61:37:19<10:08:33, 21.54s/it] 89%|████████▊ | 13306/15000 [61:37:33<9:09:32, 19.46s/it] 89%|████████▊ | 13307/15000 [61:37:48<8:28:48, 18.03s/it] 89%|████████▊ | 13308/15000 [61:38:03<8:00:00, 17.02s/it] 89%|████████▊ | 13309/15000 [61:38:17<7:40:06, 16.33s/it] 89%|████████▊ | 13310/15000 [61:38:32<7:25:48, 15.83s/it] 89%|████████▊ | 13311/15000 [61:38:47<7:14:56, 15.45s/it] 89%|████████▊ | 13312/15000 [61:39:01<7:08:47, 15.24s/it] 89%|████████▉ | 13313/15000 [61:39:16<7:03:19, 15.06s/it] 89%|████████<E29688>
{'loss': 0.8357, 'learning_rate': 5.908266688755049e-06, 'epoch': 2.51}
{'loss': 0.8357, 'learning_rate': 5.908266688755049e-06, 'epoch': 2.51}
████▉ | 13390/15000 [62:00:41<6:48:01, 15.21s/it] 89%|████████▉ | 13391/15000 [62:00:56<6:44:03, 15.07s/it] 89%|████████▉ | 13392/15000 [62:01:10<6:40:50, 14.96s/it] 89%|████████▉ | 13393/15000 [62:01:25<6:38:14, 14.87s/it] 89%|████████▉ | 13394/15000 [62:02:02<9:35:18, 21.49s/it] 89%|████████▉ | 13395/15000 [62:02:17<8:40:11, 19.45s/it] 89%|████████▉ | 13396/15000 [62:02:31<8:00:58, 17.99s/it] 89%|████████▉ | 13397/15000 [62:02:46<7:34:10, 17.00s/it] 89%|████████▉ | 13398/15000 [62:03:01<7:14:10, 16.26s/it] 89%|████████▉ | 13399/15000 [62:03:15<7:00:52, 15.77s/it] 89%|████████▉ | 13400/15000 [62:03:30<6:51:04, 15.42s/it] 89%|████████▉ | 13400/15000 [62:03:30<6:51:04, 15.42s/it] 89%|████████▉ | 13401/15000 [62:03:45<████▉ | 13390/15000 [62:00:41<6:48:08, 15.21s/it] 89%|████████▉ | 13391/15000 [62:00:56<6:44:17, 15.08s/it] 89%|████████▉ | 13392/15000 [62:01:10<6:40:23, 14.94s/it] 89%|████████▉ | 13393/15000 [62:01:25<6:38:05, 14.86s/it] 89%|████████▉ | 13394/15000 [62:02:02<9:35:13, 21.49s/it] 89%|████████▉ | 13395/15000 [62:02:17<8:40:27, 19.46s/it] 89%|████████▉ | 13396/15000 [62:02:31<8:00:51, 17.99s/it] 89%|████████▉ | 13397/15000 [62:02:46<7:34:17, 17.00s/it] 89%|████████▉ | 13398/15000 [62:03:01<7:15:19, 16.30s/it] 89%|████████▉ | 13399/15000 [62:03:15<7:00:38, 15.76s/it] 89%|████████▉ | 13400/15000 [62:03:30<6:50:09, 15.38s/it] 89%|████████▉ | 13400/15000 [62:03:30<6:50:09, 15.38s/it] 89%|████████▉ | 13401/15000 [62:03:45<<3C>█████▉ | 13394/15000 [62:02:02<9:35:05, 21.49s/it] 89%|████████▉ | 13395/15000 [62:02:17<8:40:09, 19.45s/it] 89%|████████▉ | 13396/15000 [62:02:31<8:01:34, 18.01s/it] 89%|████████▉ | 13397/15000 [62:02:46<7:33:25, 16.97s/it] 89%|████████▉ | 13398/15000 [62:03:00<7:14:28, 16.27s/it] 89%|████████▉ | 13399/15000 [62:03:15<7:00:08, 15.75s/it] 89%|████████▉ | 13400/15000 [62:03:30<6:50:37, 15.40s/it] 89%|████████▉ | 13400/15000 [62:03:30<6:50:37, 15.40s/it] 89%|████████▉ | 13401/15000 [62:03:44<6:46:23, 15.25s/it] 89%|████████▉ | 13402/15000 [62:03:59<6:40:36, 15.04s/it] 89%|████████▉ | 13403/15000 [62:04:14<6:37:53, 14.95s/it] 89%|████████▉ | 13404/15000 [62:04:28<6:35:26, 14.87s/it] 89%|████████▉ | 13405/15000 [62:046:45:51, 15.23s/it] 89%|████████▉ | 13402/15000 [62:03:59<6:40:52, 15.05s/it] 89%|████████▉ | 13403/15000 [62:04:14<6:37:30, 14.93s/it] 89%|████████▉ | 13404/15000 [62:04:28<6:35:03, 14.85s/it] 89%|████████▉ | 13405/15000 [62:04:43<6:32:47, 14.78s/it] 89%|████████▉ | 13406/15000 [62:05:20<9:28:35, 21.40s/it] 89%|████████▉ | 13407/15000 [62:05:35<8:34:44, 19.39s/it] 89%|████████▉ | 13408/15000 [62:05:49<7:56:36, 17.96s/it] 89%|████████▉ | 13409/15000 [62:06:04<7:30:05, 16.97s/it] 89%|████████▉ | 13410/15000 [62:06:18<7:10:23, 16.24s/it] 89%|████████▉ | 13411/15000 [62:06:33<6:57:36, 15.77s/it] 89%|████████▉ | 13412/15000 [62:06:48<6:49:47, 15.48s/it] 89%|████████▉ | 13413/15000 [62:07:03<6:43:18, 15.25s/it] 89%|████████▉ | 13414/15000 [62:07:17<6:39:49, 15.13s/it] 8
{'loss': 0.8341, 'learning_rate': 5.199082004372957e-06, 'epoch': 2.53}
{'loss': 0.8341, 'learning_rate': 5.199082004372957e-06, 'epoch': 2.53}
, 14.87s/it] 90%|████████▉ | 13495/15000 [62:30:03<8:55:28, 21.35s/it] 90%|████████▉ | 13496/15000 [62:30:17<8:03:28, 19.29s/it] 90%|████████▉ | 13497/15000 [62:30:32<7:29:22, 17.94s/it] 90%|████████▉ | 13498/15000 [62:30:47<7:04:28, 16.96s/it] 90%|████████▉ | 13499/15000 [62:31:01<6:47:48, 16.30s/it] 90%|█████████ | 13500/15000 [62:31:16<6:35:48, 15.83s/it] 90%|█████████ | 13500/15000 [62:31:16<6:35:48, 15.83s/it] 90%|█████████ | 13501/15000 [62:31:31<6:28:10, 15.54s/it] 90%|█████████ | 13502/15000 [62:31:46<6:21:26, 15.28s/it] 90%|█████████ | 13503/15000 [62:32:00<6:18:31, 15.17s/it] 90%|█████████ | 13504/15000 [62:32:15<6:14:57, 15.04s/it] 90%|█████████ | 13505/15000 [62:32:30<6:12:18, 14.94s/it] 90%|███████<E29688>, 14.87s/it] 90%|████████▉ | 13495/15000 [62:30:02<8:54:47, 21.32s/it] 90%|████████▉ | 13496/15000 [62:30:17<8:04:02, 19.31s/it] 90%|████████▉ | 13497/15000 [62:30:32<7:29:39, 17.95s/it] 90%|████████▉ | 13498/15000 [62:30:46<7:04:24, 16.95s/it] 90%|████████▉ | 13499/15000 [62:31:01<6:47:41, 16.30s/it] 90%|█████████ | 13500/15000 [62:31:16<6:35:59, 15.84s/it] 90%|█████████ | 13500/15000 [62:31:16<6:35:59, 15.84s/it] 90%|█████████ | 13501/15000 [62:31:31<6:29:20, 15.58s/it] 90%|█████████ | 13502/15000 [62:31:46<6:22:16, 15.31s/it] 90%|█████████ | 13503/15000 [62:32:00<6:17:30, 15.13s/it] 90%|█████████ | 13504/15000 [62:32:15<6:14:15, 15.01s/it] 90%|█████████ | 13505/15000 [62:32:30<6:11:42, 14.92s/it] 90%|███████<E29688>5:23, 16.99s/it] 90%|████████▉ | 13499/15000 [62:31:01<6:47:42, 16.30s/it] 90%|█████████ | 13500/15000 [62:31:16<6:34:36, 15.78s/it] 90%|█████████ | 13500/15000 [62:31:16<6:34:36, 15.78s/it] 90%|█████████ | 13501/15000 [62:31:31<6:29:28, 15.59s/it] 90%|█████████ | 13502/15000 [62:31:46<6:22:14, 15.31s/it] 90%|█████████ | 13503/15000 [62:32:00<6:17:21, 15.12s/it] 90%|█████████ | 13504/15000 [62:32:15<6:14:57, 15.04s/it] 90%|█████████ | 13505/15000 [62:32:30<6:12:13, 14.94s/it] 90%|█████████ | 13506/15000 [62:33:06<8:53:43, 21.43s/it] 90%|█████████ | 13507/15000 [62:33:21<8:02:38, 19.40s/it] 90%|█████████ | 13508/15000 [62:33:36<7:26:45, 17.97s/it] 90%|█████████ | 13509/15000 [62:33:50<7:01:23, 16.96s/it] 90%|██████<E29688><E29688>█ | 13506/15000 [62:33:06<8:53:37, 21.43s/it] 90%|█████████ | 13507/15000 [62:33:21<8:03:15, 19.42s/it] 90%|█████████ | 13508/15000 [62:33:36<7:26:47, 17.97s/it] 90%|█████████ | 13509/15000 [62:33:50<7:01:51, 16.98s/it] 90%|█████████ | 13510/15000 [62:34:05<6:43:57, 16.27s/it] 90%|█████████ | 13511/15000 [62:34:20<6:32:02, 15.80s/it] 90%|█████████ | 13512/15000 [62:34:34<6:23:32, 15.47s/it] 90%|█████████ | 13513/15000 [62:34:49<6:17:10, 15.22s/it] 90%|█████████ | 13514/15000 [62:35:04<6:13:13, 15.07s/it] 90%|█████████ | 13515/15000 [62:35:19<6:10:55, 14.99s/it] 90%|█████████ | 13516/15000 [62:35:33<6:07:44, 14.87s/it] 90%|█████████ | 13517/15000 [62:36:10<8:47:37, 21.35s/it] 90%|█████████ | 13518/15000 [62:36:24<7:56:46, 19.30s/it] 90%|█████████ | 13519/15000 [6
{'loss': 0.8358, 'learning_rate': 4.534091942539475e-06, 'epoch': 2.55}
{'loss': 0.8358, 'learning_rate': 4.534091942539475e-06, 'epoch': 2.55}
<EFBFBD>████████ | 13590/15000 [62:56:18<6:03:56, 15.49s/it] 91%|█████████ | 13591/15000 [62:56:32<5:58:04, 15.25s/it] 91%|█████████ | 13592/15000 [62:56:47<5:53:28, 15.06s/it] 91%|█████████ | 13593/15000 [62:57:02<5:50:13, 14.94s/it] 91%|█████████ | 13594/15000 [62:57:16<5:47:47, 14.84s/it] 91%|█████████ | 13595/15000 [62:57:53<8:23:04, 21.48s/it] 91%|█████████ | 13596/15000 [62:58:08<7:33:41, 19.39s/it] 91%|█████████ | 13597/15000 [62:58:23<7:00:59, 18.00s/it] 91%|█████████ | 13598/15000 [62:58:37<6:36:54, 16.99s/it] 91%|█████████ | 13599/15000 [62:58:52<6:20:28, 16.29s/it] 91%|█████████ | 13600/15000 [62:59:06<6:08:59, 15.81s/it] 91%|█████████ | 13600/15000 [62:59:07<6:08:59, 15.81s/it] 91%|█████████ | 13601/15000 13599/15000 [62:58:52<6:20:06, 16.28s/it] 91%|█████████ | 13600/15000 [62:59:07<6:08:45, 15.80s/it] 91%|█████████ | 13600/15000 [62:59:07<6:08:45, 15.80s/it] 91%|█████████ | 13601/15000 [62:59:21<6:01:52, 15.52s/it] 91%|█████████ | 13602/15000 [62:59:36<5:56:04, 15.28s/it] 91%|█████████ | 13603/15000 [62:59:51<5:51:56, 15.12s/it] 91%|█████████ | 13604/15000 [63:00:06<5:48:55, 15.00s/it] 91%|█████████ | 13605/15000 [63:00:20<5:46:22, 14.90s/it] 91%|█████████ | 13606/15000 [63:00:35<5:44:35, 14.83s/it] 91%|█████████ | 13607/15000 [63:01:12<8:17:26, 21.43s/it] 91%|█████████ | 13608/15000 [63:01:26<7:30:24, 19.41s/it] 91%|█████████ | 13609/15000 [63:01:41<6:57:47, 18.02s/it] 91%|█████████ | 13610/15000 [63:01:56<6:34:12, 17.02s/i 13599/15000 [62:58:52<6:20:09, 16.28s/it] 91%|█████████ | 13600/15000 [62:59:07<6:08:46, 15.80s/it] 91%|█████████ | 13600/15000 [62:59:07<6:08:46, 15.80s/it] 91%|█████████ | 13601/15000 [62:59:21<6:02:01, 15.53s/it] 91%|█████████ | 13602/15000 [62:59:36<5:55:53, 15.27s/it] 91%|█████████ | 13603/15000 [62:59:51<5:52:15, 15.13s/it] 91%|█████████ | 13604/15000 [63:00:05<5:48:15, 14.97s/it] 91%|█████████ | 13605/15000 [63:00:20<5:46:16, 14.89s/it] 91%|█████████ | 13606/15000 [63:00:35<5:43:59, 14.81s/it] 91%|█████████ | 13607/15000 [63:01:12<8:17:07, 21.41s/it] 91%|█████████ | 13608/15000 [63:01:26<7:30:23, 19.41s/it] 91%|█████████ | 13609/15000 [63:01:41<6:57:32, 18.01s/it] 91%|█████████ | 13610/15000 [63:01:56<6:34:45, 17.04s/i[62:59:21<6:02:19, 15.54s/it] 91%|█████████ | 13602/15000 [62:59:36<5:55:47, 15.27s/it] 91%|█████████ | 13603/15000 [62:59:51<5:51:46, 15.11s/it] 91%|█████████ | 13604/15000 [63:00:05<5:48:40, 14.99s/it] 91%|█████████ | 13605/15000 [63:00:20<5:46:30, 14.90s/it] 91%|█████████ | 13606/15000 [63:00:35<5:44:35, 14.83s/it] 91%|█████████ | 13607/15000 [63:01:12<8:17:30, 21.43s/it] 91%|█████████ | 13608/15000 [63:01:26<7:30:44, 19.43s/it] 91%|█████████ | 13609/15000 [63:01:41<6:57:28, 18.01s/it] 91%|█████████ | 13610/15000 [63:01:56<6:33:48, 17.00s/it] 91%|█████████ | 13611/15000 [63:02:10<6:17:18, 16.30s/it] 91%|█████████ | 13612/15000 [63:02:25<6:06:29, 15.84s/it] 91%|█████████ | 13613/15000 [63:02:40<5:57:47, 15.48s/it] 91%|█████████ | 13614/15000 [63:02:54<5:51:47, 15.
{'loss': 0.8264, 'learning_rate': 3.913606510640644e-06, 'epoch': 2.56}
{'loss': 0.8264, 'learning_rate': 3.913606510640644e-06, 'epoch': 2.56}
4:06<5:45:42, 15.83s/it] 91%|█████████▏| 13691/15000 [63:24:20<5:36:44, 15.43s/it] 91%|█████████▏| 13692/15000 [63:24:35<5:31:46, 15.22s/it] 91%|█████████▏| 13693/15000 [63:24:50<5:28:25, 15.08s/it] 91%|█████████▏| 13694/15000 [63:25:04<5:24:53, 14.93s/it] 91%|█████████▏| 13695/15000 [63:25:19<5:23:44, 14.88s/it] 91%|█████████▏| 13696/15000 [63:25:56<7:49:38, 21.61s/it] 91%|█████████▏| 13697/15000 [63:26:11<7:03:26, 19.50s/it] 91%|█████████▏| 13698/15000 [63:26:25<6:32:02, 18.07s/it] 91%|█████████▏| 13699/15000 [63:26:40<6:09:39, 17.05s/it] 91%|█████████▏| 13700/15000 [63:26:55<5:53:49, 16.33s/it] 91%|█████████▏| 13700/15000 [63:26:55<5:53:49, 16.33s/it] 91%|█████████▏| 13701/15000 [63:27:10<5:43:52, 154:05<5:45:01, 15.80s/it] 91%|█████████▏| 13691/15000 [63:24:20<5:36:41, 15.43s/it] 91%|█████████▏| 13692/15000 [63:24:35<5:31:35, 15.21s/it] 91%|█████████▏| 13693/15000 [63:24:49<5:27:38, 15.04s/it] 91%|█████████▏| 13694/15000 [63:25:04<5:25:41, 14.96s/it] 91%|█████████▏| 13695/15000 [63:25:19<5:23:30, 14.87s/it] 91%|█████████▏| 13696/15000 [63:25:56<7:49:33, 21.61s/it] 91%|█████████▏| 13697/15000 [63:26:11<7:04:05, 19.53s/it] 91%|█████████▏| 13698/15000 [63:26:25<6:31:22, 18.04s/it] 91%|█████████▏| 13699/15000 [63:26:40<6:09:32, 17.04s/it] 91%|█████████▏| 13700/15000 [63:26:55<5:53:38, 16.32s/it] 91%|█████████▏| 13700/15000 [63:26:55<5:53:38, 16.32s/it] 91%|█████████▏| 13701/15000 [63:27:10<5:45:01, 15/15000 [63:25:04<5:25:35, 14.96s/it] 91%|█████████▏| 13695/15000 [63:25:19<5:24:04, 14.90s/it] 91%|█████████▏| 13696/15000 [63:25:56<7:48:47, 21.57s/it] 91%|█████████▏| 13697/15000 [63:26:11<7:03:29, 19.50s/it] 91%|█████████▏| 13698/15000 [63:26:25<6:31:32, 18.04s/it] 91%|█████████▏| 13699/15000 [63:26:40<6:09:35, 17.04s/it] 91%|█████████▏| 13700/15000 [63:26:55<5:53:43, 16.33s/it] 91%|█████████▏| 13700/15000 [63:26:55<5:53:43, 16.33s/it] 91%|█████████▏| 13701/15000 [63:27:10<5:44:16, 15.90s/it] 91%|█████████▏| 13702/15000 [63:27:24<5:35:31, 15.51s/it] 91%|█████████▏| 13703/15000 [63:27:39<5:29:43, 15.25s/it] 91%|█████████▏| 13704/15000 [63:27:54<5:25:37, 15.08s/it] 91%|█████████▏| 13705/15000 [63:28:08.94s/it] 91%|█████████▏| 13702/15000 [63:27:24<5:35:42, 15.52s/it] 91%|█████████▏| 13703/15000 [63:27:39<5:29:46, 15.26s/it] 91%|█████████▏| 13704/15000 [63:27:53<5:24:38, 15.03s/it] 91%|█████████▏| 13705/15000 [63:28:08<5:22:44, 14.95s/it] 91%|█████████▏| 13706/15000 [63:28:23<5:20:49, 14.88s/it] 91%|█████████▏| 13707/15000 [63:28:38<5:19:21, 14.82s/it] 91%|█████████▏| 13708/15000 [63:29:15<7:44:38, 21.58s/it] 91%|█████████▏| 13709/15000 [63:29:30<6:59:26, 19.49s/it] 91%|█████████▏| 13710/15000 [63:29:44<6:27:45, 18.04s/it] 91%|█████████▏| 13711/15000 [63:29:59<6:06:13, 17.05s/it] 91%|█████████▏| 13712/15000 [63:30:14<5:50:25, 16.32s/it] 91%|█████████▏| 13713/15000 [63:30:28<5:39:39, 15.84s/it] 91%|█████████▏| 13714/15000 [63:30:43<5:31:44
{'loss': 0.8142, 'learning_rate': 3.3379149687388867e-06, 'epoch': 2.58}
{'loss': 0.8142, 'learning_rate': 3.3379149687388867e-06, 'epoch': 2.58}
[63:52:24<5:19:07, 15.85s/it] 92%|█████████▏| 13793/15000 [63:52:39<5:11:59, 15.51s/it] 92%|█████████▏| 13794/15000 [63:52:54<5:06:26, 15.25s/it] 92%|█████████▏| 13795/15000 [63:53:08<5:02:34, 15.07s/it] 92%|█████████▏| 13796/15000 [63:53:23<4:59:44, 14.94s/it] 92%|█████████▏| 13797/15000 [63:53:37<4:57:43, 14.85s/it] 92%|█████████▏| 13798/15000 [63:54:16<7:19:52, 21.96s/it] 92%|█████████▏| 13799/15000 [63:54:31<6:35:49, 19.77s/it] 92%|█████████▏| 13800/15000 [63:54:45<6:04:27, 18.22s/it] 92%|█████████▏| 13800/15000 [63:54:46<6:04:27, 18.22s/it] 92%|█████████▏| 13801/15000 [63:55:00<5:44:34, 17.24s/it] 92%|█████████▏| 13802/15000 [63:55:15<5:28:25, 16.45s/it] 92%|█████████▏| 13803/15000 [63:55:29<5:16:5[63:52:24<5:19:28, 15.87s/it] 92%|█████████▏| 13793/15000 [63:52:39<5:11:51, 15.50s/it] 92%|█████████▏| 13794/15000 [63:52:54<5:06:39, 15.26s/it] 92%|█████████▏| 13795/15000 [63:53:08<5:02:36, 15.07s/it] 92%|█████████▏| 13796/15000 [63:53:23<5:00:00, 14.95s/it] 92%|█████████▏| 13797/15000 [63:53:37<4:57:59, 14.86s/it] 92%|█████████▏| 13798/15000 [63:54:16<7:20:15, 21.98s/it] 92%|█████████▏| 13799/15000 [63:54:31<6:35:01, 19.74s/it] 92%|█████████▏| 13800/15000 [63:54:45<6:05:02, 18.25s/it] 92%|█████████▏| 13800/15000 [63:54:46<6:05:02, 18.25s/it] 92%|█████████▏| 13801/15000 [63:55:00<5:43:59, 17.21s/it] 92%|█████████▏| 13802/15000 [63:55:15<5:28:12, 16.44s/it] 92%|█████████▏| 13803/15000 [63:55:29<5:17:313796/15000 [63:53:23<4:59:51, 14.94s/it] 92%|█████████▏| 13797/15000 [63:53:37<4:58:02, 14.86s/it] 92%|█████████▏| 13798/15000 [63:54:16<7:20:10, 21.97s/it] 92%|█████████▏| 13799/15000 [63:54:31<6:35:30, 19.76s/it] 92%|█████████▏| 13800/15000 [63:54:45<6:05:29, 18.27s/it] 92%|█████████▏| 13800/15000 [63:54:46<6:05:29, 18.27s/it] 92%|█████████▏| 13801/15000 [63:55:00<5:43:45, 17.20s/it] 92%|█████████▏| 13802/15000 [63:55:15<5:28:08, 16.43s/it] 92%|█████████▏| 13803/15000 [63:55:29<5:17:02, 15.89s/it] 92%|█████████▏| 13804/15000 [63:55:44<5:09:36, 15.53s/it] 92%|█████████▏| 13805/15000 [63:55:59<5:03:59, 15.26s/it] 92%|█████████▏| 13806/15000 [63:56:13<5:00:22, 15.09s/it] 92%|█████████▏| 13807/15000 [63:3, 15.88s/it] 92%|█████████▏| 13804/15000 [63:55:44<5:09:32, 15.53s/it] 92%|█████████▏| 13805/15000 [63:55:59<5:04:28, 15.29s/it] 92%|█████████▏| 13806/15000 [63:56:13<5:00:10, 15.08s/it] 92%|█████████▏| 13807/15000 [63:56:28<4:57:13, 14.95s/it] 92%|█████████▏| 13808/15000 [63:56:43<4:55:01, 14.85s/it] 92%|█████████▏| 13809/15000 [63:57:20<7:06:02, 21.46s/it] 92%|█████████▏| 13810/15000 [63:57:34<6:26:03, 19.47s/it] 92%|█████████▏| 13811/15000 [63:57:49<5:56:07, 17.97s/it] 92%|█████████▏| 13812/15000 [63:58:04<5:36:23, 16.99s/it] 92%|█████████▏| 13813/15000 [63:58:18<5:22:58, 16.33s/it] 92%|█████████▏| 13814/15000 [63:58:33<5:11:21, 15.75s/it] 92%|█████████▏| 13815/15000 [63:58:48<5:05:17, 15.46s/it] 92%|█████████▏| 13816/15000 [63:59:02<5:
{'loss': 0.8155, 'learning_rate': 2.8072856947248037e-06, 'epoch': 2.6}
{'loss': 0.8155, 'learning_rate': 2.8072856947248037e-06, 'epoch': 2.6}
5000 [64:20:43<4:45:07, 15.47s/it] 93%|█████████▎| 13895/15000 [64:20:58<4:40:45, 15.24s/it] 93%|█████████▎| 13896/15000 [64:21:13<4:37:35, 15.09s/it] 93%|█████████▎| 13897/15000 [64:21:28<4:35:27, 14.98s/it] 93%|█████████▎| 13898/15000 [64:21:42<4:33:26, 14.89s/it] 93%|█████████▎| 13899/15000 [64:22:20<6:36:21, 21.60s/it] 93%|█████████▎| 13900/15000 [64:22:34<5:57:44, 19.51s/it] 93%|█████████▎| 13900/15000 [64:22:34<5:57:44, 19.51s/it] 93%|█████████▎| 13901/15000 [64:22:49<5:32:24, 18.15s/it] 93%|█████████▎| 13902/15000 [64:23:04<5:12:02, 17.05s/it] 93%|█████████▎| 13903/15000 [64:23:18<4:58:32, 16.33s/it] 93%|█████████▎| 13904/15000 [64:23:33<4:49:18, 15.84s/it] 93%|█████████▎| 13905/15000 [64:23:48<45000 [64:20:43<4:45:33, 15.49s/it] 93%|█████████▎| 13895/15000 [64:20:58<4:40:38, 15.24s/it] 93%|█████████▎| 13896/15000 [64:21:13<4:37:33, 15.08s/it] 93%|█████████▎| 13897/15000 [64:21:28<4:35:09, 14.97s/it] 93%|█████████▎| 13898/15000 [64:21:42<4:33:46, 14.91s/it] 93%|█████████▎| 13899/15000 [64:22:20<6:36:21, 21.60s/it] 93%|█████████▎| 13900/15000 [64:22:34<5:57:47, 19.52s/it] 93%|█████████▎| 13900/15000 [64:22:34<5:57:47, 19.52s/it] 93%|█████████▎| 13901/15000 [64:22:49<5:31:39, 18.11s/it] 93%|█████████▎| 13902/15000 [64:23:04<5:12:18, 17.07s/it] 93%|█████████▎| 13903/15000 [64:23:18<4:58:52, 16.35s/it] 93%|█████████▎| 13904/15000 [64:23:33<4:49:20, 15.84s/it] 93%|█████████▎| 13905/15000 [64:23:48<4▎| 13898/15000 [64:21:42<4:33:46, 14.91s/it] 93%|█████████▎| 13899/15000 [64:22:19<6:36:18, 21.60s/it] 93%|█████████▎| 13900/15000 [64:22:34<5:58:08, 19.54s/it] 93%|█████████▎| 13900/15000 [64:22:34<5:58:08, 19.54s/it] 93%|█████████▎| 13901/15000 [64:22:49<5:31:24, 18.09s/it] 93%|█████████▎| 13902/15000 [64:23:04<5:12:14, 17.06s/it] 93%|█████████▎| 13903/15000 [64:23:18<4:58:52, 16.35s/it] 93%|█████████▎| 13904/15000 [64:23:33<4:49:20, 15.84s/it] 93%|█████████▎| 13905/15000 [64:23:48<4:43:03, 15.51s/it] 93%|█████████▎| 13906/15000 [64:24:02<4:37:37, 15.23s/it] 93%|█████████▎| 13907/15000 [64:24:17<4:34:23, 15.06s/it] 93%|█████████▎| 13908/15000 [64:24:32<4:31:40, 14.93s/it] 93%|█████████▎| 13909/15000:43:06, 15.51s/it] 93%|█████████▎| 13906/15000 [64:24:02<4:37:55, 15.24s/it] 93%|█████████▎| 13907/15000 [64:24:17<4:34:03, 15.04s/it] 93%|█████████▎| 13908/15000 [64:24:32<4:31:46, 14.93s/it] 93%|█████████▎| 13909/15000 [64:24:46<4:30:18, 14.87s/it] 93%|█████████▎| 13910/15000 [64:25:01<4:29:12, 14.82s/it] 93%|█████████▎| 13911/15000 [64:25:38<6:32:24, 21.62s/it] 93%|█████████▎| 13912/15000 [64:25:53<5:53:55, 19.52s/it] 93%|█████████▎| 13913/15000 [64:26:08<5:27:11, 18.06s/it] 93%|█████████▎| 13914/15000 [64:26:22<5:08:42, 17.06s/it] 93%|█████████▎| 13915/15000 [64:26:37<4:55:11, 16.32s/it] 93%|█████████▎| 13916/15000 [64:26:52<4:46:03, 15.83s/it] 93%|█████████▎| 13917/15000 [64:27:06<4:39:53, 15.51s/it] 93%|█████████▎| 13918/15000 [64:27:
{'loss': 0.8142, 'learning_rate': 2.3219660592038285e-06, 'epoch': 2.62}
{'loss': 0.8142, 'learning_rate': 2.3219660592038285e-06, 'epoch': 2.62}
<EFBFBD><EFBFBD>█▎| 14000/15000 [64:50:00<4:07:45, 14.87s/it] 93%|█████████▎| 14000/15000 [64:50:01<4:07:45, 14.87s/it]Saving model checkpoint to /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-14000
tokenizer config file saved in /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-14000/tokenizer_config.json
Special tokens file saved in /leonardo_work/IscrC_fineNLP/llamantino_chat/UltraChat/train/results/checkpoint-14000/special_tokens_map.json
996/15000 [64:49:02<4:19:12, 15.49s/it] 93%|█████████▎| 13997/15000 [64:49:16<4:14:59, 15.25s/it] 93%|█████████▎| 13998/15000 [64:49:31<4:11:52, 15.08s/it] 93%|█████████▎| 13999/15000 [64:49:46<4:09:18, 14.94s/it] 93%|█████████▎| 14000/15000 [64:50:01<4:08:19, 14.90s/it] 93%|█████████▎| 14000/15000 [64:50:01<4:08:19, 14.90s/it] 93%|█████████▎| 14001/15000 [64:50:42<6:20:00, 22.82s/it] 93%|█████████▎| 14002/15000 [64:50:57<5:39:19, 20.40s/it] 93%|█████████▎| 14003/15000 [64:51:11<5:10:40, 18.70s/it] 93%|█████████▎| 14004/15000 [64:51:26<4:50:03, 17.47s/it] 93%|█████████▎| 14005/15000 [64:51:41<4:35:47, 16.63s/it] 93%|█████████▎| 14006/15000 [64:51:55<4:25:48, 16.04s/it] 93%|█████████▎| 14007/15000 [64:52996/15000 [64:49:02<4:19:10, 15.49s/it] 93%|█████████▎| 13997/15000 [64:49:16<4:15:03, 15.26s/it] 93%|█████████▎| 13998/15000 [64:49:31<4:11:59, 15.09s/it] 93%|█████████▎| 13999/15000 [64:49:46<4:09:25, 14.95s/it] 93%|█████████▎| 14000/15000 [64:50:00<4:07:38, 14.86s/it] 93%|█████████▎| 14000/15000 [64:50:01<4:07:38, 14.86s/it] 93%|█████████▎| 14001/15000 [64:50:42<6:19:59, 22.82s/it] 93%|█████████▎| 14002/15000 [64:50:57<5:39:41, 20.42s/it] 93%|█████████▎| 14003/15000 [64:51:11<5:10:39, 18.70s/it] 93%|█████████▎| 14004/15000 [64:51:26<4:50:08, 17.48s/it] 93%|█████████▎| 14005/15000 [64:51:41<4:35:43, 16.63s/it] 93%|█████████▎| 14006/15000 [64:51:55<4:25:36, 16.03s/it] 93%|█████████▎| 14007/15000 [64:52 93%|█████████▎| 14001/15000 [64:50:42<6:20:41, 22.86s/it] 93%|█████████▎| 14002/15000 [64:50:57<5:39:05, 20.39s/it] 93%|█████████▎| 14003/15000 [64:51:11<5:10:33, 18.69s/it] 93%|█████████▎| 14004/15000 [64:51:26<4:50:04, 17.47s/it] 93%|█████████▎| 14005/15000 [64:51:40<4:35:20, 16.60s/it] 93%|█████████▎| 14006/15000 [64:51:55<4:25:57, 16.05s/it] 93%|█████████▎| 14007/15000 [64:52:10<4:18:12, 15.60s/it] 93%|█████████▎| 14008/15000 [64:52:25<4:13:38, 15.34s/it] 93%|█████████▎| 14009/15000 [64:52:39<4:09:32, 15.11s/it] 93%|█████████▎| 14010/15000 [64:52:54<4:06:54, 14.96s/it] 93%|█████████▎| 14011/15000 [64:53:08<4:05:26, 14.89s/it] 93%|█████████▎| 14012/15000 [64:53:46<5:56:06, 21.63s/it] 93%|█████████▎| 14013/15000 [64:54:00<5:21:28, 19.54s/:10<4:18:17, 15.61s/it] 93%|█████████▎| 14008/15000 [64:52:25<4:13:30, 15.33s/it] 93%|█████████▎| 14009/15000 [64:52:39<4:09:52, 15.13s/it] 93%|█████████▎| 14010/15000 [64:52:54<4:07:26, 15.00s/it] 93%|█████████▎| 14011/15000 [64:53:09<4:05:15, 14.88s/it] 93%|█████████▎| 14012/15000 [64:53:46<5:55:58, 21.62s/it] 93%|█████████▎| 14013/15000 [64:54:01<5:21:25, 19.54s/it] 93%|█████████▎| 14014/15000 [64:54:15<4:56:20, 18.03s/it] 93%|█████████▎| 14015/15000 [64:54:30<4:39:29, 17.03s/it] 93%|█████████▎| 14016/15000 [64:54:44<4:27:40, 16.32s/it] 93%|█████████▎| 14017/15000 [64:54:59<4:18:56, 15.81s/it] 93%|█████████▎| 14018/15000 [64:55:14<4:12:59, 15.46s/it] 93%|█████████▎| 14019/15000 [64:55:28<4:09:21, 15.25s/it] 93%|█████████▎| 14020/15000 [6
{'loss': 0.8113, 'learning_rate': 1.882182310176095e-06, 'epoch': 2.64}
{'loss': 0.8113, 'learning_rate': 1.882182310176095e-06, 'epoch': 2.64}
1<5:24:36, 21.43s/it] 94%|█████████▍| 14092/15000 [65:15:55<4:53:23, 19.39s/it] 94%|█████████▍| 14093/15000 [65:16:10<4:31:43, 17.97s/it] 94%|█████████▍| 14094/15000 [65:16:25<4:16:57, 17.02s/it] 94%|█████████▍| 14095/15000 [65:16:40<4:06:02, 16.31s/it] 94%|█████████▍| 14096/15000 [65:16:54<3:58:18, 15.82s/it] 94%|█████████▍| 14097/15000 [65:17:09<3:53:18, 15.50s/it] 94%|█████████▍| 14098/15000 [65:17:24<3:49:33, 15.27s/it] 94%|█████████▍| 14099/15000 [65:17:38<3:46:37, 15.09s/it] 94%|█████████▍| 14100/15000 [65:17:53<3:44:07, 14.94s/it] 94%|█████████▍| 14100/15000 [65:17:53<3:44:07, 14.94s/it] 94%|█████████▍| 14101/15000 [65:18:08<3:43:33, 14.92s/it] 94%|█████████▍| 14102/15000 [65:18:45<5:22:48, 21.57<EFBFBD>| 14098/15000 [65:17:24<3:49:06, 15.24s/it] 94%|█████████▍| 14099/15000 [65:17:38<3:46:55, 15.11s/it] 94%|█████████▍| 14100/15000 [65:17:53<3:44:17, 14.95s/it] 94%|█████████▍| 14100/15000 [65:17:53<3:44:17, 14.95s/it] 94%|█████████▍| 14101/15000 [65:18:08<3:43:34, 14.92s/it] 94%|█████████▍| 14102/15000 [65:18:45<5:23:27, 21.61s/it] 94%|█████████▍| 14103/15000 [65:19:00<4:51:34, 19.50s/it] 94%|█████████▍| 14104/15000 [65:19:14<4:29:29, 18.05s/it] 94%|█████████▍| 14105/15000 [65:19:29<4:13:24, 16.99s/it] 94%|█████████▍| 14106/15000 [65:19:44<4:02:48, 16.30s/it] 94%|█████████▍| 14107/15000 [65:19:58<3:55:19, 15.81s/it] 94%|█████████▍| 14108/15000 [65:20:13<3:50:14, 15.49s/it] 94%|█████████▍| 14109/15000 [<5B>| 14098/15000 [65:17:24<3:49:23, 15.26s/it] 94%|█████████▍| 14099/15000 [65:17:38<3:46:31, 15.09s/it] 94%|█████████▍| 14100/15000 [65:17:53<3:44:16, 14.95s/it] 94%|█████████▍| 14100/15000 [65:17:53<3:44:16, 14.95s/it] 94%|█████████▍| 14101/15000 [65:18:08<3:43:18, 14.90s/it] 94%|█████████▍| 14102/15000 [65:18:45<5:23:18, 21.60s/it] 94%|█████████▍| 14103/15000 [65:19:00<4:51:26, 19.49s/it] 94%|█████████▍| 14104/15000 [65:19:14<4:29:49, 18.07s/it] 94%|█████████▍| 14105/15000 [65:19:29<4:13:42, 17.01s/it] 94%|█████████▍| 14106/15000 [65:19:44<4:02:58, 16.31s/it] 94%|█████████▍| 14107/15000 [65:19:58<3:55:14, 15.81s/it] 94%|█████████▍| 14108/15000 [65:20:13<3:49:58, 15.47s/it] 94%|█████████▍| 14109/15000 [s/it] 94%|█████████▍| 14103/15000 [65:19:00<4:51:33, 19.50s/it] 94%|█████████▍| 14104/15000 [65:19:14<4:29:27, 18.04s/it] 94%|█████████▍| 14105/15000 [65:19:29<4:13:45, 17.01s/it] 94%|█████████▍| 14106/15000 [65:19:44<4:03:10, 16.32s/it] 94%|█████████▍| 14107/15000 [65:19:58<3:55:42, 15.84s/it] 94%|█████████▍| 14108/15000 [65:20:13<3:50:06, 15.48s/it] 94%|█████████▍| 14109/15000 [65:20:28<3:46:12, 15.23s/it] 94%|█████████▍| 14110/15000 [65:20:42<3:43:36, 15.08s/it] 94%|█████████▍| 14111/15000 [65:20:57<3:41:09, 14.93s/it] 94%|█████████▍| 14112/15000 [65:21:12<3:39:51, 14.86s/it] 94%|█████████▍| 14113/15000 [65:21:26<3:39:15, 14.83s/it] 94%|█████████▍| 14114/15000 [65:22:03<5:17:35, 21.51s/it] 94%|█████████▍| 14115/15000 [65:22:18<4:47:00, 1
{'loss': 0.812, 'learning_rate': 1.488139467563354e-06, 'epoch': 2.66}
{'loss': 0.812, 'learning_rate': 1.488139467563354e-06, 'epoch': 2.66}
:44:00<4:49:58, 21.56s/it] 95%|█████████▍| 14194/15000 [65:44:15<4:21:40, 19.48s/it] 95%|█████████▍| 14195/15000 [65:44:30<4:01:48, 18.02s/it] 95%|█████████▍| 14196/15000 [65:44:44<3:48:00, 17.02s/it] 95%|█████████▍| 14197/15000 [65:44:59<3:38:22, 16.32s/it] 95%|█████████▍| 14198/15000 [65:45:14<3:31:35, 15.83s/it] 95%|█████████▍| 14199/15000 [65:45:28<3:26:01, 15.43s/it] 95%|█████████▍| 14200/15000 [65:45:43<3:22:37, 15.20s/it] 95%|█████████▍| 14200/15000 [65:45:43<3:22:37, 15.20s/it] 95%|█████████▍| 14201/15000 [65:45:58<3:21:09, 15.11s/it] 95%|█████████▍| 14202/15000 [65:46:13<3:19:14, 14.98s/it] 95%|█████████▍| 14203/15000 [65:46:27<3:17:53, 14.90s/it] 95%|█████████▍| 14204/15000 [65:47:04<4:45:41, █▍| 14200/15000 [65:45:43<3:22:29, 15.19s/it] 95%|█████████▍| 14200/15000 [65:45:43<3:22:29, 15.19s/it] 95%|█████████▍| 14201/15000 [65:45:58<3:20:58, 15.09s/it] 95%|█████████▍| 14202/15000 [65:46:12<3:18:48, 14.95s/it] 95%|█████████▍| 14203/15000 [65:46:27<3:17:40, 14.88s/it] 95%|█████████▍| 14204/15000 [65:47:04<4:45:28, 21.52s/it] 95%|█████████▍| 14205/15000 [65:47:19<4:17:59, 19.47s/it] 95%|█████████▍| 14206/15000 [65:47:34<3:58:46, 18.04s/it] 95%|█████████▍| 14207/15000 [65:47:48<3:45:18, 17.05s/it] 95%|█████████▍| 14208/15000 [65:48:03<3:35:03, 16.29s/it] 95%|█████████▍| 14209/15000 [65:48:18<3:28:32, 15.82s/it] 95%|█████████▍| 14210/15000 [65:48:32<3:23:44, 15.47s/it] 95%|█████████▍| 14211/15█▍| 14200/15000 [65:45:43<3:22:58, 15.22s/it] 95%|█████████▍| 14200/15000 [65:45:43<3:22:58, 15.22s/it] 95%|█████████▍| 14201/15000 [65:45:58<3:21:09, 15.11s/it] 95%|█████████▍| 14202/15000 [65:46:13<3:19:12, 14.98s/it] 95%|█████████▍| 14203/15000 [65:46:27<3:17:37, 14.88s/it] 95%|█████████▍| 14204/15000 [65:47:04<4:45:15, 21.50s/it] 95%|█████████▍| 14205/15000 [65:47:19<4:17:51, 19.46s/it] 95%|█████████▍| 14206/15000 [65:47:34<3:58:37, 18.03s/it] 95%|█████████▍| 14207/15000 [65:47:48<3:44:53, 17.02s/it] 95%|█████████▍| 14208/15000 [65:48:03<3:35:06, 16.30s/it] 95%|█████████▍| 14209/15000 [65:48:18<3:28:35, 15.82s/it] 95%|█████████▍| 14210/15000 [65:48:32<3:23:30, 15.46s/it] 95%|█████████▍| 14211/1521.54s/it] 95%|█████████▍| 14205/15000 [65:47:19<4:17:53, 19.46s/it] 95%|█████████▍| 14206/15000 [65:47:34<3:58:30, 18.02s/it] 95%|█████████▍| 14207/15000 [65:47:48<3:44:41, 17.00s/it] 95%|█████████▍| 14208/15000 [65:48:03<3:35:28, 16.32s/it] 95%|█████████▍| 14209/15000 [65:48:17<3:28:20, 15.80s/it] 95%|█████████▍| 14210/15000 [65:48:32<3:23:46, 15.48s/it] 95%|█████████▍| 14211/15000 [65:48:47<3:20:22, 15.24s/it] 95%|█████████▍| 14212/15000 [65:49:02<3:17:51, 15.06s/it] 95%|█████████▍| 14213/15000 [65:49:16<3:16:26, 14.98s/it] 95%|█████████▍| 14214/15000 [65:49:31<3:15:24, 14.92s/it] 95%|█████████▍| 14215/15000 [65:50:08<4:40:31, 21.44s/it] 95%|█████████▍| 14216/15000 [65:50:22<4:13:53, 19.43s/it] 95%|█████████▍| 14217/15000 [65:50:37<3:55:
<EFBFBD><EFBFBD>█▌| 14289/15000 [66:10:28<3:03:30, 15.49s/it] 95%|█████████▌| 14290/15000 [66:10:43<3:00:16, 15.23s/it] 95%|█████████▌| 14291/15000 [66:10:58<2:58:13, 15.08s/it] 95%|█████████▌| 14292/15000 [66:11:12<2:56:09, 14.93s/it] 95%|█████████▌| 14293/15000 [66:11:27<2:54:25, 14.80s/it] 95%|█████████▌| 14294/15000 [66:12:04<4:13:09, 21.51s/it] 95%|█████████▌| 14295/15000 [66:12:19<3:49:02, 19.49s/it] 95%|█████████▌| 14296/15000 [66:12:33<3:31:48, 18.05s/it] 95%|█████████▌| 14297/15000 [66:12:48<3:19:37, 17.04s/it] 95%|█████████▌| 14298/15000 [66:13:03<3:11:02, 16.33s/it] 95%|█████████▌| 14299/15000 [66:13:17<3:05:09, 15.85s/it] 95%|█████████▌| 14300/15000 [66:13:32<3:00:59, 15.51s/it] 95%|█████████▌| 14300/{'loss': 0.8139, 'learning_rate': 1.1400212276321376e-06, 'epoch': 2.68}
<EFBFBD><EFBFBD>█▌| 14289/15000 [66:10:28<3:03:31, 15.49s/it] 95%|█████████▌| 14290/15000 [66:10:43<3:00:32, 15.26s/it] 95%|█████████▌| 14291/15000 [66:10:58<2:58:17, 15.09s/it] 95%|█████████▌| 14292/15000 [66:11:12<2:56:00, 14.92s/it] 95%|█████████▌| 14293/15000 [66:11:27<2:54:34, 14.81s/it] 95%|█████████▌| 14294/15000 [66:12:04<4:13:14, 21.52s/it] 95%|█████████▌| 14295/15000 [66:12:19<3:49:04, 19.50s/it] 95%|█████████▌| 14296/15000 [66:12:33<3:31:36, 18.03s/it] 95%|█████████▌| 14297/15000 [66:12:48<3:19:46, 17.05s/it] 95%|█████████▌| 14298/15000 [66:13:03<3:10:57, 16.32s/it] 95%|█████████▌| 14299/15000 [66:13:17<3:05:12, 15.85s/it] 95%|█████████▌| 14300/15000 [66:13:32<3:00:44, 15.49s/it] 95%|█████████▌| 14300/{'loss': 0.8139, 'learning_rate': 1.1400212276321376e-06, 'epoch': 2.68}
0 [66:12:19<3:49:06, 19.50s/it] 95%|█████████▌| 14296/15000 [66:12:33<3:31:46, 18.05s/it] 95%|█████████▌| 14297/15000 [66:12:48<3:19:24, 17.02s/it] 95%|█████████▌| 14298/15000 [66:13:03<3:11:12, 16.34s/it] 95%|█████████▌| 14299/15000 [66:13:17<3:05:17, 15.86s/it] 95%|█████████▌| 14300/15000 [66:13:32<3:00:48, 15.50s/it] 95%|█████████▌| 14300/15000 [66:13:32<3:00:48, 15.50s/it] 95%|█████████▌| 14301/15000 [66:13:47<2:58:20, 15.31s/it] 95%|█████████▌| 14302/15000 [66:14:01<2:55:14, 15.06s/it] 95%|█████████▌| 14303/15000 [66:14:16<2:53:48, 14.96s/it] 95%|█████████▌| 14304/15000 [66:14:31<2:52:17, 14.85s/it] 95%|█████████▌| 14305/15000 [66:14:45<2:51:18, 14.79s/it] 95%|█████████▌| 14306/15000 [66:15:23<4:0815000 [66:13:32<3:00:59, 15.51s/it] 95%|█████████▌| 14301/15000 [66:13:47<2:58:15, 15.30s/it] 95%|█████████▌| 14302/15000 [66:14:01<2:55:28, 15.08s/it] 95%|█████████▌| 14303/15000 [66:14:16<2:53:52, 14.97s/it] 95%|█████████▌| 14304/15000 [66:14:31<2:52:21, 14.86s/it] 95%|█████████▌| 14305/15000 [66:14:46<2:51:41, 14.82s/it] 95%|█████████▌| 14306/15000 [66:15:23<4:08:32, 21.49s/it] 95%|█████████▌| 14307/15000 [66:15:37<3:44:33, 19.44s/it] 95%|█████████▌| 14308/15000 [66:15:52<3:27:56, 18.03s/it] 95%|█████████▌| 14309/15000 [66:16:07<3:16:06, 17.03s/it] 95%|█████████▌| 14310/15000 [66:16:21<3:07:23, 16.29s/it] 95%|█████████▌| 14311/15000 [66:16:36<3:02:08, 15.86s/it] 95%|█████████▌| 14312/15000 [66:16:51<2:57:20, 15.47s/it] 95%|█████████▌| 14315000 [66:13:32<3:00:44, 15.49s/it] 95%|█████████▌| 14301/15000 [66:13:47<2:58:25, 15.32s/it] 95%|█████████▌| 14302/15000 [66:14:02<2:55:42, 15.10s/it] 95%|█████████▌| 14303/15000 [66:14:16<2:53:28, 14.93s/it] 95%|█████████▌| 14304/15000 [66:14:31<2:52:30, 14.87s/it] 95%|█████████▌| 14305/15000 [66:14:45<2:51:25, 14.80s/it] 95%|█████████▌| 14306/15000 [66:15:23<4:08:44, 21.51s/it] 95%|█████████▌| 14307/15000 [66:15:37<3:44:47, 19.46s/it] 95%|█████████▌| 14308/15000 [66:15:52<3:27:33, 18.00s/it] 95%|█████████▌| 14309/15000 [66:16:07<3:15:48, 17.00s/it] 95%|█████████▌| 14310/15000 [66:16:21<3:07:38, 16.32s/it] 95%|█████████▌| 14311/15000 [66:16:36<3:02:01, 15.85s/it] 95%|█████████▌| 14312/15000 [66:16:51<2:57:33, 15.48s/it] 95%|█████████▌| 143:48, 21.51s/it] 95%|█████████▌| 14307/15000 [66:15:37<3:44:51, 19.47s/it] 95%|█████████▌| 14308/15000 [66:15:52<3:27:50, 18.02s/it] 95%|█████████▌| 14309/15000 [66:16:07<3:15:59, 17.02s/it] 95%|█████████▌| 14310/15000 [66:16:21<3:07:43, 16.32s/it] 95%|█████████▌| 14311/15000 [66:16:36<3:01:58, 15.85s/it] 95%|█████████▌| 14312/15000 [66:16:51<2:57:40, 15.49s/it] 95%|█████████▌| 14313/15000 [66:17:05<2:54:17, 15.22s/it] 95%|█████████▌| 14314/15000 [66:17:20<2:51:52, 15.03s/it] 95%|█████████▌| 14315/15000 [66:17:35<2:50:35, 14.94s/it] 95%|█████████▌| 14316/15000 [66:17:49<2:49:32, 14.87s/it] 95%|█████████▌| 14317/15000 [66:18:26<4:05:04, 21.53s/it] 95%|█████████▌| 14318/15000 [66:18:41<3:41:27, 19.48s/it] 95%|█████████▌| 14319/15000 [66:18:56<
{'loss': 0.8132, 'learning_rate': 8.379898773574924e-07, 'epoch': 2.7}
{'loss': 0.8132, 'learning_rate': 8.379898773574924e-07, 'epoch': 2.7}
<EFBFBD>███▌| 14391/15000 [66:38:47<2:37:05, 15.48s/it] 96%|█████████▌| 14392/15000 [66:39:02<2:34:25, 15.24s/it] 96%|█████████▌| 14393/15000 [66:39:17<2:32:16, 15.05s/it] 96%|█████████▌| 14394/15000 [66:39:31<2:31:14, 14.97s/it] 96%|█████████▌| 14395/15000 [66:39:46<2:30:13, 14.90s/it] 96%|█████████▌| 14396/15000 [66:40:23<3:37:12, 21.58s/it] 96%|█████████▌| 14397/15000 [66:40:38<3:16:07, 19.51s/it] 96%|█████████▌| 14398/15000 [66:40:52<3:00:40, 18.01s/it] 96%|█████████▌| 14399/15000 [66:41:07<2:50:41, 17.04s/it] 96%|█████████▌| 14400/15000 [66:41:22<2:43:13, 16.32s/it] 96%|█████████▌| 14400/15000 [66:41:22<2:43:13, 16.32s/it] 96%|█████████▌| 14401/15000 [66:41:37<2:38:43, 15.90s/it] 96%|█████████▌| 1<>███▌| 14391/15000 [66:38:47<2:36:58, 15.47s/it] 96%|█████████▌| 14392/15000 [66:39:02<2:34:08, 15.21s/it] 96%|█████████▌| 14393/15000 [66:39:17<2:32:30, 15.07s/it] 96%|█████████▌| 14394/15000 [66:39:31<2:31:12, 14.97s/it] 96%|█████████▌| 14395/15000 [66:39:46<2:30:03, 14.88s/it] 96%|█████████▌| 14396/15000 [66:40:23<3:37:10, 21.57s/it] 96%|█████████▌| 14397/15000 [66:40:38<3:16:07, 19.52s/it] 96%|█████████▌| 14398/15000 [66:40:52<3:00:45, 18.02s/it] 96%|█████████▌| 14399/15000 [66:41:07<2:50:45, 17.05s/it] 96%|█████████▌| 14400/15000 [66:41:22<2:43:10, 16.32s/it] 96%|█████████▌| 14400/15000 [66:41:22<2:43:10, 16.32s/it] 96%|█████████▌| 14401/15000 [66:41:37<2:38:40, 15.89s/it] 96%|█████████▌| 1/15000 [66:40:38<3:15:55, 19.49s/it] 96%|█████████▌| 14398/15000 [66:40:52<3:01:04, 18.05s/it] 96%|█████████▌| 14399/15000 [66:41:07<2:50:14, 17.00s/it] 96%|█████████▌| 14400/15000 [66:41:22<2:43:13, 16.32s/it] 96%|█████████▌| 14400/15000 [66:41:22<2:43:13, 16.32s/it] 96%|█████████▌| 14401/15000 [66:41:37<2:38:54, 15.92s/it] 96%|█████████▌| 14402/15000 [66:41:51<2:34:42, 15.52s/it] 96%|█████████▌| 14403/15000 [66:42:06<2:32:11, 15.29s/it] 96%|█████████▌| 14404/15000 [66:42:21<2:29:53, 15.09s/it] 96%|█████████▌| 14405/15000 [66:42:35<2:28:14, 14.95s/it] 96%|█████████▌| 14406/15000 [66:42:50<2:27:07, 14.86s/it] 96%|█████████▌| 14407/15000 [66:43:27<3:32:57, 21.55s/it] 96%|█████████▌| 14408/15000 [66:43:424402/15000 [66:41:51<2:34:44, 15.53s/it] 96%|█████████▌| 14403/15000 [66:42:06<2:32:10, 15.29s/it] 96%|█████████▌| 14404/15000 [66:42:21<2:30:09, 15.12s/it] 96%|█████████▌| 14405/15000 [66:42:35<2:28:12, 14.95s/it] 96%|█████████▌| 14406/15000 [66:42:50<2:26:43, 14.82s/it] 96%|█████████▌| 14407/15000 [66:43:27<3:32:47, 21.53s/it] 96%|█████████▌| 14408/15000 [66:43:42<3:12:11, 19.48s/it] 96%|█████████▌| 14409/15000 [66:43:56<2:57:31, 18.02s/it] 96%|█████████▌| 14410/15000 [66:44:11<2:47:21, 17.02s/it] 96%|█████████▌| 14411/15000 [66:44:26<2:40:18, 16.33s/it] 96%|█████████▌| 14412/15000 [66:44:41<2:35:03, 15.82s/it] 96%|█████████▌| 14413/15000 [66:44:55<2:31:18, 15.47s/it] 96%|█████████▌| 14414/15000 [66:45:10<2:28:45, 15.23s/it] 96%|█████████<E29688><E29688>
{'loss': 0.8164, 'learning_rate': 5.821862187675775e-07, 'epoch': 2.71}
{'loss': 0.8164, 'learning_rate': 5.821862187675775e-07, 'epoch': 2.71}
█████▋| 14493/15000 [67:07:05<2:08:33, 15.21s/it] 97%|█████████▋| 14494/15000 [67:07:20<2:06:55, 15.05s/it] 97%|█████████▋| 14495/15000 [67:07:35<2:05:46, 14.94s/it] 97%|█████████▋| 14496/15000 [67:07:49<2:04:47, 14.86s/it] 97%|█████████▋| 14497/15000 [67:08:26<2:59:31, 21.41s/it] 97%|█████████▋| 14498/15000 [67:08:41<2:42:26, 19.41s/it] 97%|█████████▋| 14499/15000 [67:08:55<2:30:13, 17.99s/it] 97%|█████████▋| 14500/15000 [67:09:10<2:21:34, 16.99s/it] 97%|█████████▋| 14500/15000 [67:09:10<2:21:34, 16.99s/it] 97%|█████████▋| 14501/15000 [67:09:25<2:16:00, 16.35s/it] 97%|█████████▋| 14502/15000 [67:09:40<2:11:26, 15.84s/it] 97%|█████████▋| 14503/15000 [67:09:54<2:08:23, 15.50s/it] 97%|█████████<E29688>█████▋| 14493/15000 [67:07:05<2:08:55, 15.26s/it] 97%|█████████▋| 14494/15000 [67:07:20<2:06:45, 15.03s/it] 97%|█████████▋| 14495/15000 [67:07:35<2:05:42, 14.94s/it] 97%|█████████▋| 14496/15000 [67:07:49<2:04:58, 14.88s/it] 97%|█████████▋| 14497/15000 [67:08:26<2:59:34, 21.42s/it] 97%|█████████▋| 14498/15000 [67:08:41<2:42:29, 19.42s/it] 97%|█████████▋| 14499/15000 [67:08:55<2:30:10, 17.98s/it] 97%|█████████▋| 14500/15000 [67:09:10<2:21:31, 16.98s/it] 97%|█████████▋| 14500/15000 [67:09:10<2:21:31, 16.98s/it] 97%|█████████▋| 14501/15000 [67:09:25<2:15:58, 16.35s/it] 97%|█████████▋| 14502/15000 [67:09:39<2:11:16, 15.82s/it] 97%|█████████▋| 14503/15000 [67:09:54<2:08:06, 15.47s/it] 97%|█████████<E29688>14499/15000 [67:08:55<2:30:23, 18.01s/it] 97%|█████████▋| 14500/15000 [67:09:10<2:21:38, 17.00s/it] 97%|█████████▋| 14500/15000 [67:09:10<2:21:38, 17.00s/it] 97%|█████████▋| 14501/15000 [67:09:25<2:15:38, 16.31s/it] 97%|█████████▋| 14502/15000 [67:09:39<2:11:25, 15.83s/it] 97%|█████████▋| 14503/15000 [67:09:54<2:08:21, 15.50s/it] 97%|█████████▋| 14504/15000 [67:10:09<2:06:13, 15.27s/it] 97%|█████████▋| 14505/15000 [67:10:23<2:04:12, 15.05s/it] 97%|█████████▋| 14506/15000 [67:10:38<2:03:00, 14.94s/it] 97%|█████████▋| 14507/15000 [67:10:53<2:02:01, 14.85s/it] 97%|█████████▋| 14508/15000 [67:11:07<2:01:23, 14.80s/it] 97%|█████████▋| 14509/15000 [67:11:44<2:55:27, 21.44s/it] 97%|█████████▋| 14510/15000 [67:<3A><>| 14504/15000 [67:10:09<2:06:17, 15.28s/it] 97%|█████████▋| 14505/15000 [67:10:24<2:04:29, 15.09s/it] 97%|█████████▋| 14506/15000 [67:10:38<2:02:58, 14.94s/it] 97%|█████████▋| 14507/15000 [67:10:53<2:02:11, 14.87s/it] 97%|█████████▋| 14508/15000 [67:11:08<2:01:20, 14.80s/it] 97%|█████████▋| 14509/15000 [67:11:45<2:55:29, 21.44s/it] 97%|█████████▋| 14510/15000 [67:11:59<2:38:37, 19.42s/it] 97%|█████████▋| 14511/15000 [67:12:14<2:26:39, 17.99s/it] 97%|█████████▋| 14512/15000 [67:12:29<2:18:11, 16.99s/it] 97%|█████████▋| 14513/15000 [67:12:43<2:12:17, 16.30s/it] 97%|█████████▋| 14514/15000 [67:12:58<2:07:58, 15.80s/it] 97%|█████████▋| 14515/15000 [67:13:13<2:05:04, 15.47s/it] 97%|█████████▋| 14516/15000 [67:13:27<2:02:49, 15.23s/it] 97%|████████
{'loss': 0.8144, 'learning_rate': 3.727295033040035e-07, 'epoch': 2.73}
{'loss': 0.8144, 'learning_rate': 3.727295033040035e-07, 'epoch': 2.73}
| 14588/15000 [67:33:42<2:28:24, 21.61s/it] 97%|█████████▋| 14589/15000 [67:33:56<2:13:53, 19.55s/it] 97%|█████████▋| 14590/15000 [67:34:11<2:03:35, 18.09s/it] 97%|█████████▋| 14591/15000 [67:34:26<1:56:13, 17.05s/it] 97%|█████████▋| 14592/15000 [67:34:40<1:51:06, 16.34s/it] 97%|█████████▋| 14593/15000 [67:34:55<1:47:23, 15.83s/it] 97%|█████████▋| 14594/15000 [67:35:10<1:44:31, 15.45s/it] 97%|█████████▋| 14595/15000 [67:35:24<1:42:47, 15.23s/it] 97%|█████████▋| 14596/15000 [67:35:39<1:41:23, 15.06s/it] 97%|█████████▋| 14597/15000 [67:35:54<1:40:21, 14.94s/it] 97%|█████████▋| 14598/15000 [67:36:08<1:39:29, 14.85s/it] 97%|█████████▋| 14599/15000 [67:36:47<2:26:14, 21.88s/it] 97%|█████████▋| 14600/15000 [67:37:01<2:11:39, 19.75s/it] <20><>██████▋| 14595/15000 [67:35:24<1:42:49, 15.23s/it] 97%|█████████▋| 14596/15000 [67:35:39<1:41:20, 15.05s/it] 97%|█████████▋| 14597/15000 [67:35:54<1:40:10, 14.92s/it] 97%|█████████▋| 14598/15000 [67:36:08<1:39:26, 14.84s/it] 97%|█████████▋| 14599/15000 [67:36:47<2:26:22, 21.90s/it] 97%|█████████▋| 14600/15000 [67:37:01<2:11:22, 19.71s/it] 97%|█████████▋| 14600/15000 [67:37:02<2:11:22, 19.71s/it] 97%|█████████▋| 14601/15000 [67:37:16<2:01:22, 18.25s/it] 97%|█████████▋| 14602/15000 [67:37:31<1:54:12, 17.22s/it] 97%|█████████▋| 14603/15000 [67:37:46<1:48:48, 16.44s/it] 97%|█████████▋| 14604/15000 [67:38:00<1:45:08, 15.93s/it] 97%|█████████▋| 14605/15000 [67:38:15<1:42:21, 15.55s/it] 97%|███████▖<E29688>██████▋| 14595/15000 [67:35:24<1:42:48, 15.23s/it] 97%|█████████▋| 14596/15000 [67:35:39<1:41:29, 15.07s/it] 97%|█████████▋| 14597/15000 [67:35:54<1:40:25, 14.95s/it] 97%|█████████▋| 14598/15000 [67:36:08<1:39:34, 14.86s/it] 97%|█████████▋| 14599/15000 [67:36:47<2:26:13, 21.88s/it] 97%|█████████▋| 14600/15000 [67:37:01<2:11:35, 19.74s/it] 97%|█████████▋| 14600/15000 [67:37:02<2:11:35, 19.74s/it] 97%|█████████▋| 14601/15000 [67:37:16<2:01:18, 18.24s/it] 97%|█████████▋| 14602/15000 [67:37:31<1:54:02, 17.19s/it] 97%|█████████▋| 14603/15000 [67:37:46<1:48:47, 16.44s/it] 97%|█████████▋| 14604/15000 [67:38:00<1:45:01, 15.91s/it] 97%|█████████▋| 14605/15000 [67:38:15<1:42:23, 15.55s/it] 97%|███████<E29688><E29688> 97%|█████████▋| 14600/15000 [67:37:01<2:11:39, 19.75s/it] 97%|█████████▋| 14601/15000 [67:37:16<2:01:30, 18.27s/it] 97%|█████████▋| 14602/15000 [67:37:31<1:54:05, 17.20s/it] 97%|█████████▋| 14603/15000 [67:37:46<1:48:48, 16.45s/it] 97%|█████████▋| 14604/15000 [67:38:00<1:45:03, 15.92s/it] 97%|█████████▋| 14605/15000 [67:38:15<1:42:15, 15.53s/it] 97%|█████████▋| 14606/15000 [67:38:30<1:40:18, 15.28s/it] 97%|█████████▋| 14607/15000 [67:38:44<1:38:52, 15.10s/it] 97%|█████████▋| 14608/15000 [67:38:59<1:37:40, 14.95s/it] 97%|█████████▋| 14609/15000 [67:39:14<1:36:55, 14.87s/it] 97%|█████████▋| 14610/15000 [67:39:51<2:19:50, 21.52s/it] 97%|█████████▋| 14611/15000 [67:40:05<2:06:03, 19.44s/it] 97%|█████████▋| 14612/1500
{'loss': 0.815, 'learning_rate': 2.0971737622883515e-07, 'epoch': 2.75}
{'loss': 0.815, 'learning_rate': 2.0971737622883515e-07, 'epoch': 2.75}
<EFBFBD><EFBFBD>▊| 14690/15000 [68:02:01<1:40:55, 19.53s/it] 98%|█████████▊| 14691/15000 [68:02:16<1:33:06, 18.08s/it] 98%|█████████▊| 14692/15000 [68:02:31<1:27:34, 17.06s/it] 98%|█████████▊| 14693/15000 [68:02:45<1:23:34, 16.33s/it] 98%|█████████▊| 14694/15000 [68:03:00<1:20:51, 15.86s/it] 98%|█████████▊| 14695/15000 [68:03:15<1:18:50, 15.51s/it] 98%|█████████▊| 14696/15000 [68:03:29<1:17:27, 15.29s/it] 98%|█████████▊| 14697/15000 [68:03:44<1:16:07, 15.07s/it] 98%|█████████▊| 14698/15000 [68:03:59<1:15:23, 14.98s/it] 98%|█████████▊| 14699/15000 [68:04:13<1:14:39, 14.88s/it] 98%|█████████▊| 14700/15000 [68:04:51<1:47:59, 21.60s/it] 98%|█████████▊| 14700/15000 [68:04:51<1:47:59, 21.60s/it] 98%|█████████▊| 14701/150<35>████████▊| 14697/15000 [68:03:44<1:16:25, 15.13s/it] 98%|█████████▊| 14698/15000 [68:03:59<1:15:14, 14.95s/it] 98%|█████████▊| 14699/15000 [68:04:13<1:14:43, 14.89s/it] 98%|█████████▊| 14700/15000 [68:04:51<1:48:11, 21.64s/it] 98%|█████████▊| 14700/15000 [68:04:51<1:48:11, 21.64s/it] 98%|█████████▊| 14701/15000 [68:05:06<1:37:31, 19.57s/it] 98%|█████████▊| 14702/15000 [68:05:20<1:29:56, 18.11s/it] 98%|█████████▊| 14703/15000 [68:05:35<1:24:31, 17.08s/it] 98%|█████████▊| 14704/15000 [68:05:50<1:20:51, 16.39s/it] 98%|█████████▊| 14705/15000 [68:06:04<1:18:08, 15.89s/it] 98%|█████████▊| 14706/15000 [68:06:19<1:15:53, 15.49s/it] 98%|█████████▊| 14707/15000 [68:06:33<1:14:12, 15.20s/it] 98%|██████<E29688>████████▊| 14697/15000 [68:03:44<1:16:13, 15.10s/it] 98%|█████████▊| 14698/15000 [68:03:59<1:15:14, 14.95s/it] 98%|█████████▊| 14699/15000 [68:04:13<1:14:30, 14.85s/it] 98%|█████████▊| 14700/15000 [68:04:51<1:48:03, 21.61s/it] 98%|█████████▊| 14700/15000 [68:04:51<1:48:03, 21.61s/it] 98%|█████████▊| 14701/15000 [68:05:06<1:37:43, 19.61s/it] 98%|█████████▊| 14702/15000 [68:05:20<1:29:53, 18.10s/it] 98%|█████████▊| 14703/15000 [68:05:35<1:24:32, 17.08s/it] 98%|█████████▊| 14704/15000 [68:05:50<1:20:50, 16.39s/it] 98%|█████████▊| 14705/15000 [68:06:04<1:18:13, 15.91s/it] 98%|█████████▊| 14706/15000 [68:06:19<1:15:54, 15.49s/it] 98%|█████████▊| 14707/15000 [68:06:34<1:14:23, 15.23s/it] 98%|██████00 [68:05:05<1:37:32, 19.57s/it] 98%|█████████▊| 14702/15000 [68:05:20<1:29:59, 18.12s/it] 98%|█████████▊| 14703/15000 [68:05:35<1:24:38, 17.10s/it] 98%|█████████▊| 14704/15000 [68:05:50<1:20:45, 16.37s/it] 98%|█████████▊| 14705/15000 [68:06:04<1:17:59, 15.86s/it] 98%|█████████▊| 14706/15000 [68:06:19<1:15:51, 15.48s/it] 98%|█████████▊| 14707/15000 [68:06:34<1:14:23, 15.23s/it] 98%|█████████▊| 14708/15000 [68:06:48<1:13:20, 15.07s/it] 98%|█████████▊| 14709/15000 [68:07:03<1:12:28, 14.94s/it] 98%|█████████▊| 14710/15000 [68:07:17<1:11:45, 14.85s/it] 98%|█████████▊| 14711/15000 [68:07:32<1:11:07, 14.77s/it] 98%|█████████▊| 14712/15000 [68:08:09<1:42:59, 21.46s/it] 98%|█████████▊| 14713/15000 [68:08:24<1:32:47, 19.40s/it] 98%|█████████▊| 14714
{'loss': 0.8131, 'learning_rate': 9.32258311039269e-08, 'epoch': 2.77}
{'loss': 0.8131, 'learning_rate': 9.32258311039269e-08, 'epoch': 2.77}
:19<1:07:31, 19.48s/it] 99%|█████████▊| 14793/15000 [68:30:34<1:02:11, 18.03s/it] 99%|█████████▊| 14794/15000 [68:30:48<58:22, 17.00s/it] 99%|█████████▊| 14795/15000 [68:31:03<55:35, 16.27s/it] 99%|█████████▊| 14796/15000 [68:31:17<53:40, 15.79s/it] 99%|█████████▊| 14797/15000 [68:31:32<52:14, 15.44s/it] 99%|█████████▊| 14798/15000 [68:31:47<51:13, 15.21s/it] 99%|█████████▊| 14799/15000 [68:32:01<50:26, 15.06s/it] 99%|█████████▊| 14800/15000 [68:32:16<49:46, 14.93s/it] 99%|█████████▊| 14800/15000 [68:32:16<49:46, 14.93s/it] 99%|█████████▊| 14801/15000 [68:32:31<49:22, 14.89s/it] 99%|█████████▊| 14802/15000 [68:33:08<1:11:15, 21.59s/it] 99%|█████████▊| 14803/15000 [68:33:23<1:04:05, 19.52s/it] 99%|█<><E29688>99/15000 [68:32:01<50:20, 15.03s/it] 99%|█████████▊| 14800/15000 [68:32:16<49:46, 14.93s/it] 99%|█████████▊| 14800/15000 [68:32:16<49:46, 14.93s/it] 99%|█████████▊| 14801/15000 [68:32:31<49:24, 14.90s/it] 99%|█████████▊| 14802/15000 [68:33:08<1:11:14, 21.59s/it] 99%|█████████▊| 14803/15000 [68:33:23<1:04:07, 19.53s/it] 99%|█████████▊| 14804/15000 [68:33:38<59:03, 18.08s/it] 99%|█████████▊| 14805/15000 [68:33:52<55:24, 17.05s/it] 99%|█████████▊| 14806/15000 [68:34:07<52:48, 16.33s/it] 99%|█████████▊| 14807/15000 [68:34:22<50:56, 15.84s/it] 99%|█████████▊| 14808/15000 [68:34:36<49:27, 15.45s/it] 99%|█████████▊| 14809/15000 [68:34:51<48:30, 15.24s/it] 99%|█████████▊| 14810/15000 [68:35:06<47:44, 15.08s/it]99/15000 [68:32:02<50:26, 15.06s/it] 99%|█████████▊| 14800/15000 [68:32:16<49:43, 14.92s/it] 99%|█████████▊| 14800/15000 [68:32:16<49:43, 14.92s/it] 99%|█████████▊| 14801/15000 [68:32:31<49:25, 14.90s/it] 99%|█████████▊| 14802/15000 [68:33:08<1:11:06, 21.55s/it] 99%|█████████▊| 14803/15000 [68:33:23<1:04:06, 19.52s/it] 99%|█████████▊| 14804/15000 [68:33:38<59:00, 18.06s/it] 99%|█████████▊| 14805/15000 [68:33:52<55:24, 17.05s/it] 99%|█████████▊| 14806/15000 [68:34:07<52:51, 16.35s/it] 99%|█████████▊| 14807/15000 [68:34:21<50:50, 15.81s/it] 99%|█████████▊| 14808/15000 [68:34:36<49:34, 15.49s/it] 99%|█████████▊| 14809/15000 [68:34:51<48:31, 15.24s/it] 99%|█████████▊| 14810/15000 [68:35:06<47:45, 15.08s/it]<5D>███████▊| 14804/15000 [68:33:38<59:04, 18.09s/it] 99%|█████████▊| 14805/15000 [68:33:52<55:19, 17.02s/it] 99%|█████████▊| 14806/15000 [68:34:07<52:44, 16.31s/it] 99%|█████████▊| 14807/15000 [68:34:21<50:53, 15.82s/it] 99%|█████████▊| 14808/15000 [68:34:36<49:36, 15.50s/it] 99%|█████████▊| 14809/15000 [68:34:51<48:33, 15.26s/it] 99%|█████████▊| 14810/15000 [68:35:05<47:40, 15.06s/it] 99%|█████████▊| 14811/15000 [68:35:20<47:05, 14.95s/it] 99%|█████████▊| 14812/15000 [68:35:35<46:31, 14.85s/it] 99%|█████████▉| 14813/15000 [68:36:12<1:07:20, 21.61s/it] 99%|█████████▉| 14814/15000 [68:36:27<1:00:29, 19.51s/it] 99%|█████████▉| 14815/15000 [68:36:41<55:41, 18.06s/it] 99%|█████████▉| 14816/15000 [68:36:56<52:19, 17.06s/it] 99%|██████<E29688>
{'loss': 0.8154, 'learning_rate': 2.3309174364027907e-08, 'epoch': 2.79}
{'loss': 0.8154, 'learning_rate': 2.3309174364027907e-08, 'epoch': 2.79}
68:57:17<27:26, 14.97s/it] 99%|█████████▉| 14891/15000 [68:57:32<27:04, 14.90s/it] 99%|█████████▉| 14892/15000 [68:58:09<38:44, 21.52s/it] 99%|█████████▉| 14893/15000 [68:58:24<34:46, 19.50s/it] 99%|█████████▉| 14894/15000 [68:58:38<31:53, 18.06s/it] 99%|█████████▉| 14895/15000 [68:58:53<29:47, 17.02s/it] 99%|█████████▉| 14896/15000 [68:59:08<28:20, 16.35s/it] 99%|█████████▉| 14897/15000 [68:59:22<27:09, 15.82s/it] 99%|█████████▉| 14898/15000 [68:59:37<26:22, 15.52s/it] 99%|█████████▉| 14899/15000 [68:59:52<25:41, 15.26s/it] 99%|█████████▉| 14900/15000 [69:00:07<25:09, 15.10s/it] 99%|█████████▉| 14900/15000 [69:00:07<25:09, 15.10s/it] 99%|█████████▉| 14901/15000 [69:00:21<24:44, 15.00s/it] 99%|███<E29688>68:57:17<27:24, 14.95s/it] 99%|█████████▉| 14891/15000 [68:57:32<27:07, 14.93s/it] 99%|█████████▉| 14892/15000 [68:58:09<38:48, 21.56s/it] 99%|█████████▉| 14893/15000 [68:58:24<34:43, 19.47s/it] 99%|█████████▉| 14894/15000 [68:58:38<31:55, 18.08s/it] 99%|█████████▉| 14895/15000 [68:58:53<29:48, 17.03s/it] 99%|█████████▉| 14896/15000 [68:59:08<28:18, 16.33s/it] 99%|█████████▉| 14897/15000 [68:59:22<27:09, 15.82s/it] 99%|█████████▉| 14898/15000 [68:59:37<26:22, 15.51s/it] 99%|█████████▉| 14899/15000 [68:59:52<25:42, 15.27s/it] 99%|█████████▉| 14900/15000 [69:00:07<25:11, 15.11s/it] 99%|█████████▉| 14900/15000 [69:00:07<25:11, 15.11s/it] 99%|█████████▉| 14901/15000 [69:00:21<24:46, 15.01s/it] 99%|███<E29688>█████████▉| 14897/15000 [68:59:22<27:10, 15.83s/it] 99%|█████████▉| 14898/15000 [68:59:37<26:22, 15.51s/it] 99%|█████████▉| 14899/15000 [68:59:52<25:41, 15.26s/it] 99%|█████████▉| 14900/15000 [69:00:06<25:07, 15.08s/it] 99%|█████████▉| 14900/15000 [69:00:07<25:07, 15.08s/it] 99%|█████████▉| 14901/15000 [69:00:21<24:45, 15.01s/it] 99%|█████████▉| 14902/15000 [69:00:36<24:21, 14.91s/it] 99%|█████████▉| 14903/15000 [69:00:51<23:58, 14.83s/it] 99%|█████████▉| 14904/15000 [69:01:28<34:23, 21.49s/it] 99%|█████████▉| 14905/15000 [69:01:42<30:48, 19.46s/it] 99%|█████████▉| 14906/15000 [69:01:57<28:11, 18.00s/it] 99%|█████████▉| 14907/15000 [69:02:12<26:21, 17.01s/it] 99%|█████████▉| 14908/1500<30><30>█████▉| 14902/15000 [69:00:36<24:20, 14.91s/it] 99%|█████████▉| 14903/15000 [69:00:51<23:58, 14.83s/it] 99%|█████████▉| 14904/15000 [69:01:28<34:22, 21.48s/it] 99%|█████████▉| 14905/15000 [69:01:42<30:44, 19.42s/it] 99%|█████████▉| 14906/15000 [69:01:57<28:13, 18.02s/it] 99%|█████████▉| 14907/15000 [69:02:12<26:20, 16.99s/it] 99%|█████████▉| 14908/15000 [69:02:26<25:01, 16.32s/it] 99%|█████████▉| 14909/15000 [69:02:41<24:02, 15.85s/it] 99%|█████████▉| 14910/15000 [69:02:56<23:12, 15.48s/it] 99%|█████████▉| 14911/15000 [69:03:10<22:32, 15.20s/it] 99%|█████████▉| 14912/15000 [69:03:25<22:04, 15.05s/it] 99%|█████████▉| 14913/15000 [69:03:40<21:38, 14.93s/it] 99%|█████████▉| 14914/15000 [69:03:54<21:16, 14.85s/it] 99%|█████████▉|
<EFBFBD>███▉| 14995/15000 [69:26:43<01:37, 19.53s/it] 100%|█████████▉| 14996/15000 [69:26:57<01:12, 18.06s/it] 100%|█████████▉| 14997/15000 [69:27:12<00:51, 17.02s/it] 100%|█████████▉| 14998/15000 [69:27:27<00:32, 16.37s/it] 100%|█████████▉| 14999/15000 [69:27:41<00:15, 15.80s/it] 100%|██████████| 15000/15000 [69:27:56<00:00, 15.51s/it] 100%|██████████| 15000/15000 [69:27:56<00:00, 15.51s/it]
Training completed. Do not forget to share your model on huggingface.co/models =)
{'loss': 0.8134, 'learning_rate': 0.0, 'epoch': 2.81}
<EFBFBD>███▉| 14995/15000 [69:26:43<01:37, 19.51s/it] 100%|█████████▉| 14996/15000 [69:26:57<01:12, 18.04s/it] 100%|█████████▉| 14997/15000 [69:27:12<00:51, 17.02s/it] 100%|█████████▉| 14998/15000 [69:27:27<00:32, 16.37s/it] 100%|█████████▉| 14999/15000 [69:27:42<00:15, 15.85s/it] 100%|██████████| 15000/15000 [69:27:56<00:00, 15.48s/it] 100%|██████████| 15000/15000 [69:27:56<00:00, 15.48s/it]
Training completed. Do not forget to share your model on huggingface.co/models =)
{'loss': 0.8134, 'learning_rate': 0.0, 'epoch': 2.81}
<EFBFBD>▉| 14988/15000 [69:24:37<03:09, 15.80s/it] 100%|█████████▉| 14989/15000 [69:24:52<02:49, 15.45s/it] 100%|█████████▉| 14990/15000 [69:25:07<02:32, 15.21s/it] 100%|█████████▉| 14991/15000 [69:25:21<02:15, 15.04s/it] 100%|█████████▉| 14992/15000 [69:25:36<01:59, 14.98s/it] 100%|█████████▉| 14993/15000 [69:25:51<01:44, 14.90s/it] 100%|█████████▉| 14994/15000 [69:26:28<02:09, 21.55s/it] 100%|█████████▉| 14995/15000 [69:26:43<01:37, 19.52s/it] 100%|█████████▉| 14996/15000 [69:26:57<01:12, 18.05s/it] 100%|█████████▉| 14997/15000 [69:27:12<00:51, 17.07s/it] 100%|█████████▉| 14998/15000 [69:27:27<00:32, 16.35s/it] 100%|█████████▉| 14999/15000 [69:27:41<00:15, 15.83s/it] 100%|██████████| 15000/15000 [69:27:56<00:00, 15.50s/it] 100%|██████████| 15000/15000 [69:27:56<00:00, 15.50s/it]
Training completed. Do not forget to share your model on huggingface.co/models =)
{'train_runtime': 250081.6545, 'train_samples_per_second': 5.758, 'train_steps_per_second': 0.06, 'train_loss': 0.8493305440266927, 'epoch': 2.81}
{'train_runtime': 250082.0071, 'train_samples_per_second': 5.758, 'train_steps_per_second': 0.06, 'train_loss': 0.8493305440266927, 'epoch': 2.81}
{'train_runtime': 250081.6132, 'train_samples_per_second': 5.758, 'train_steps_per_second': 0.06, 'train_loss': 0.8493305440266927, 'epoch': 2.81}
Saving last checkpoint of the model...
Saving last checkpoint of the model...
Saving last checkpoint of the model...
Saving last checkpoint of the model...
Saving last checkpoint of the model...
Saving last checkpoint of the model...
Saving last checkpoint of the model...
100%|██████████| 15000/15000 [69:27:57<00:00, 15.48s/it] 100%|██████████| 15000/15000 [69:27:57<00:00, 16.67s/it]
Saving last checkpoint of the model...
Saving last checkpoint of the model...
Saving last checkpoint of the model...
Saving last checkpoint of the model...
100%|██████████| 15000/15000 [69:27:57<00:00, 15.51s/it] 100%|██████████| 15000/15000 [69:27:57<00:00, 16.67s/it]
Saving last checkpoint of the model...
100%|██████████| 15000/15000 [69:27:57<00:00, 15.50s/it] 100%|██████████| 15000/15000 [69:27:57<00:00, 16.67s/it]
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/config.json
Model config LlamaConfig {
"_name_or_path": "/leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}
loading weights file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/model.safetensors.index.json
Instantiating LlamaForCausalLM model under default dtype torch.float16.
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/config.json
Model config LlamaConfig {
"_name_or_path": "/leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}
loading weights file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/model.safetensors.index.json
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/config.json
Model config LlamaConfig {
"_name_or_path": "/leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 32000
}
Instantiating LlamaForCausalLM model under default dtype torch.float16.
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}
loading weights file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/model.safetensors.index.json
Instantiating LlamaForCausalLM model under default dtype torch.float16.
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.31.0"
}
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 33%|███▎ | 1/3 [00:21<00:43, 21.68s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [00:21<00:43, 21.82s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [00:21<00:43, 21.85s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [00:21<00:43, 21.83s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:42<00:21, 21.32s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:43<00:21, 21.46s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:43<00:21, 21.49s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:43<00:21, 21.47s/it] Loading checkpoint shards: 100%|██████████| 3/3 [00:55<00:00, 17.57s/it] Loading checkpoint shards: 100%|██████████| 3/3 [00:55<00:00, 18.63s/it]
Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 33%|███▎ | 1/3 [00:21<00:43, 21.65s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [00:21<00:43, 21.81s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [00:21<00:43, 21.89s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [00:21<00:43, 21.84s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:42<00:21, 21.40s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:43<00:21, 21.51s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:43<00:21, 21.48s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:43<00:21, 21.48s/it] Loading checkpoint shards: 100%|██████████| 3/3 [00:55<00:00, 17.60s/it Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 0%| | 0/3 [00:00<?, ?it/s] Loading checkpoint shards: 33%|███▎ | 1/3 [00:21<00:43, 21.51s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [00:21<00:43, 21.81s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [00:21<00:43, 21.81s/it] Loading checkpoint shards: 33%|███▎ | 1/3 [00:21<00:43, 21.86s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:42<00:21, 21.33s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:43<00:21, 21.49s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:43<00:21, 21.46s/it] Loading checkpoint shards: 67%|██████▋ | 2/3 [00:43<00:21, 21.53s/it] Loading checkpoint shards: 100%|██████████| 3/3 [00:55<00:00, 17.53s/it] Loading checkpoint shards: 100%|██████████| 3/3 [00:55<00:00, 18.65s/it]
] Loading checkpoint shards: 100%|██████████| 3/3 [00:55<00:00, 18.64s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 17.62s/it] Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 18.71s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 17.60s/it] Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 18.67s/it]
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 17.63s/it] Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 18.68s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 17.60s/it] Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 18.68s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 17.62s/it] Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 18.70s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 17.63s/it] Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 18.69s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 17.62s/it] Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 18.70s/it]
Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 17.65s/it] Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 18.69s/it]
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 17.63s/it] Loading checkpoint shards: 100%|██████████| 3/3 [00:56<00:00, 18.70s/it]
All model checkpoint weights were used when initializing LlamaForCausalLM.
All the weights of LlamaForCausalLM were initialized from the model checkpoint at /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA.
If your task is similar to the task the model of the checkpoint was trained on, you can already use LlamaForCausalLM for predictions without further training.
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/generation_config.json
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/generation_config.json
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}
loading configuration file /leonardo_work/IscrC_fineNLP/llamantino_chat/13B_MODELS_final/Llamantino-2-13b-chat-hf-ITA/generation_config.json
Generate config GenerationConfig {
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"temperature": 0.9,
"top_p": 0.6,
"transformers_version": "4.31.0"
}
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
Assigning <pad> to the pad_token key of the tokenizer
Configuration saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/config.json
Configuration saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/generation_config.json
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
Assigning <pad> to the pad_token key of the tokenizer
Configuration saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/config.json
Configuration saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/generation_config.json
loading file tokenizer.model
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
Assigning <pad> to the pad_token key of the tokenizer
Configuration saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/config.json
Configuration saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/generation_config.json
The model is bigger than the maximum size per checkpoint (10GB) and is going to be split in 3 checkpoint shards. You can find where each parameters has been saved in the index located at Llamantino-2-13b-chat-hf-ITA_UltraB_final/model.safetensors.index.json.
Configuration saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/config.json
Configuration saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/generation_config.json
The model is bigger than the maximum size per checkpoint (10GB) and is going to be split in 3 checkpoint shards. You can find where each parameters has been saved in the index located at Llamantino-2-13b-chat-hf-ITA_UltraB_final/model.safetensors.index.json.
Configuration saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/config.json
Configuration saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/generation_config.json
The model is bigger than the maximum size per checkpoint (10GB) and is going to be split in 3 checkpoint shards. You can find where each parameters has been saved in the index located at Llamantino-2-13b-chat-hf-ITA_UltraB_final/model.safetensors.index.json.
Configuration saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/config.json
Configuration saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/generation_config.json
The model is bigger than the maximum size per checkpoint (10GB) and is going to be split in 3 checkpoint shards. You can find where each parameters has been saved in the index located at Llamantino-2-13b-chat-hf-ITA_UltraB_final/pytorch_model.bin.index.json.
tokenizer config file saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/tokenizer_config.json
Special tokens file saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/special_tokens_map.json
INFO:torch.distributed.elastic.agent.server.api:[default] worker group successfully finished. Waiting 300 seconds for other agents to finish.
INFO:torch.distributed.elastic.agent.server.api:Local worker group finished (SUCCEEDED). Waiting 300 seconds for other agents to finish
The model is bigger than the maximum size per checkpoint (10GB) and is going to be split in 3 checkpoint shards. You can find where each parameters has been saved in the index located at Llamantino-2-13b-chat-hf-ITA_UltraB_final/pytorch_model.bin.index.json.
tokenizer config file saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/tokenizer_config.json
Special tokens file saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/special_tokens_map.json
INFO:torch.distributed.elastic.agent.server.api:[default] worker group successfully finished. Waiting 300 seconds for other agents to finish.
INFO:torch.distributed.elastic.agent.server.api:Local worker group finished (SUCCEEDED). Waiting 300 seconds for other agents to finish
The model is bigger than the maximum size per checkpoint (10GB) and is going to be split in 3 checkpoint shards. You can find where each parameters has been saved in the index located at Llamantino-2-13b-chat-hf-ITA_UltraB_final/pytorch_model.bin.index.json.
tokenizer config file saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/tokenizer_config.json
Special tokens file saved in Llamantino-2-13b-chat-hf-ITA_UltraB_final/special_tokens_map.json
INFO:torch.distributed.elastic.agent.server.api:[default] worker group successfully finished. Waiting 300 seconds for other agents to finish.
INFO:torch.distributed.elastic.agent.server.api:Local worker group finished (SUCCEEDED). Waiting 300 seconds for other agents to finish
INFO:torch.distributed.elastic.agent.server.api:Done waiting for other agents. Elapsed: 0.0009827613830566406 seconds
INFO:torch.distributed.elastic.agent.server.api:Done waiting for other agents. Elapsed: 48.7719452381134 seconds
INFO:torch.distributed.elastic.agent.server.api:Done waiting for other agents. Elapsed: 38.99942111968994 seconds
Reference in New Issue Copy Permalink