初始化项目,由ModelHub XC社区提供模型
Model: DCAgent/a1-stack_pytest_gpt5mini Source: Original Platform
This commit is contained in:
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
60
README.md
Normal file
60
README.md
Normal file
@@ -0,0 +1,60 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
base_model: Qwen/Qwen3-8B
|
||||
tags:
|
||||
- llama-factory
|
||||
- full
|
||||
- generated_from_trainer
|
||||
model-index:
|
||||
- name: sft_a1_stack_pytest_gpt5mini__Qwen3-8B
|
||||
results: []
|
||||
---
|
||||
|
||||
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
||||
should probably proofread and complete it, then remove this comment. -->
|
||||
|
||||
# sft_a1_stack_pytest_gpt5mini__Qwen3-8B
|
||||
|
||||
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--exp_rpt_stack-pytest-gpt5mini_glm_4.7_traces_jupiter/snapshots/8f5962e22355e85ad49717a49e9a3821a1db506e_thinking_preprocessed dataset.
|
||||
|
||||
## Model description
|
||||
|
||||
More information needed
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
More information needed
|
||||
|
||||
## Training and evaluation data
|
||||
|
||||
More information needed
|
||||
|
||||
## Training procedure
|
||||
|
||||
### Training hyperparameters
|
||||
|
||||
The following hyperparameters were used during training:
|
||||
- learning_rate: 4e-05
|
||||
- train_batch_size: 1
|
||||
- eval_batch_size: 8
|
||||
- seed: 42
|
||||
- distributed_type: multi-GPU
|
||||
- num_devices: 16
|
||||
- total_train_batch_size: 16
|
||||
- total_eval_batch_size: 128
|
||||
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
||||
- lr_scheduler_type: cosine
|
||||
- lr_scheduler_warmup_ratio: 0.1
|
||||
- num_epochs: 7.0
|
||||
|
||||
### Training results
|
||||
|
||||
|
||||
|
||||
### Framework versions
|
||||
|
||||
- Transformers 4.57.6
|
||||
- Pytorch 2.9.1+cu130
|
||||
- Datasets 4.7.0
|
||||
- Tokenizers 0.22.2
|
||||
28
added_tokens.json
Normal file
28
added_tokens.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"</think>": 151668,
|
||||
"</tool_call>": 151658,
|
||||
"</tool_response>": 151666,
|
||||
"<think>": 151667,
|
||||
"<tool_call>": 151657,
|
||||
"<tool_response>": 151665,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
16
all_results.json
Normal file
16
all_results.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"achieved_tflops_per_gpu": 0.0036901022213999698,
|
||||
"achieved_tflops_per_gpu_theoretical": 596.2712030568775,
|
||||
"epoch": 7.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.19432786107063293,
|
||||
"mfu_percent": 0.0002607846092862169,
|
||||
"mfu_percent_theoretical": 42.13930763652845,
|
||||
"total_flos": 1055465597173760.0,
|
||||
"train_loss": 0.21853318925887819,
|
||||
"train_runtime": 17876.6321,
|
||||
"train_samples_per_second": 2.818,
|
||||
"train_steps_per_second": 0.176,
|
||||
"valid_targets_mean": 4280.6,
|
||||
"valid_targets_min": 315
|
||||
}
|
||||
89
chat_template.jinja
Normal file
89
chat_template.jinja
Normal file
@@ -0,0 +1,89 @@
|
||||
{%- if tools %}
|
||||
{{- '<|im_start|>system\n' }}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- messages[0].content + '\n\n' }}
|
||||
{%- endif %}
|
||||
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
||||
{%- for tool in tools %}
|
||||
{{- "\n" }}
|
||||
{{- tool | tojson }}
|
||||
{%- endfor %}
|
||||
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
||||
{%- else %}
|
||||
{%- if messages[0].role == 'system' %}
|
||||
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
||||
{%- for message in messages[::-1] %}
|
||||
{%- set index = (messages|length - 1) - loop.index0 %}
|
||||
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
||||
{%- set ns.multi_step_tool = false %}
|
||||
{%- set ns.last_query_index = index %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- for message in messages %}
|
||||
{%- if message.content is string %}
|
||||
{%- set content = message.content %}
|
||||
{%- else %}
|
||||
{%- set content = '' %}
|
||||
{%- endif %}
|
||||
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
||||
{%- elif message.role == "assistant" %}
|
||||
{%- set reasoning_content = '' %}
|
||||
{%- if message.reasoning_content is string %}
|
||||
{%- set reasoning_content = message.reasoning_content %}
|
||||
{%- else %}
|
||||
{%- if '</think>' in content %}
|
||||
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
||||
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- if loop.index0 > ns.last_query_index %}
|
||||
{%- if loop.last or (not loop.last and reasoning_content) %}
|
||||
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- else %}
|
||||
{{- '<|im_start|>' + message.role + '\n' + content }}
|
||||
{%- endif %}
|
||||
{%- if message.tool_calls %}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- if (loop.first and content) or (not loop.first) %}
|
||||
{{- '\n' }}
|
||||
{%- endif %}
|
||||
{%- if tool_call.function %}
|
||||
{%- set tool_call = tool_call.function %}
|
||||
{%- endif %}
|
||||
{{- '<tool_call>\n{"name": "' }}
|
||||
{{- tool_call.name }}
|
||||
{{- '", "arguments": ' }}
|
||||
{%- if tool_call.arguments is string %}
|
||||
{{- tool_call.arguments }}
|
||||
{%- else %}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{%- endif %}
|
||||
{{- '}\n</tool_call>' }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- elif message.role == "tool" %}
|
||||
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
||||
{{- '<|im_start|>user' }}
|
||||
{%- endif %}
|
||||
{{- '\n<tool_response>\n' }}
|
||||
{{- content }}
|
||||
{{- '\n</tool_response>' }}
|
||||
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
||||
{{- '<|im_end|>\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|im_start|>assistant\n' }}
|
||||
{%- if enable_thinking is defined and enable_thinking is false %}
|
||||
{{- '<think>\n\n</think>\n\n' }}
|
||||
{%- endif %}
|
||||
{%- endif %}
|
||||
68
config.json
Normal file
68
config.json
Normal file
@@ -0,0 +1,68 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 151645,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 12288,
|
||||
"layer_types": [
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention",
|
||||
"full_attention"
|
||||
],
|
||||
"max_position_embeddings": 40960,
|
||||
"max_window_layers": 36,
|
||||
"model_type": "qwen3",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 36,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 151643,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 151936
|
||||
}
|
||||
12
generation_config.json
Normal file
12
generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"temperature": 0.6,
|
||||
"top_k": 20,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:116e14d209a4ba2675a47381c896a223bf36216028beeb34adc0d77280e9ca17
|
||||
size 4902257696
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:107e0dc5ac94456ead3e19aa1101d092f0522db45c53005a9c403aa37a0a48f5
|
||||
size 4915960368
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8c0081d9fc9227f8aeba35271cfcf378950048c9837cc046070f19ef8d542aef
|
||||
size 4983068496
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c0df90418ec224611840c5871bec381420be527f2d440b5f51346b1114bc6744
|
||||
size 1580230264
|
||||
407
model.safetensors.index.json
Normal file
407
model.safetensors.index.json
Normal file
@@ -0,0 +1,407 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 308224,
|
||||
"total_size": 16381470720
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00004-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
12
run_summary.json
Normal file
12
run_summary.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"agent_name": "8f5962e22355e85ad49717a49e9a3821a1db506e_thinking_preprocessed",
|
||||
"training_start": null,
|
||||
"training_end": null,
|
||||
"created_by": "raoof1",
|
||||
"base_model_name": "Qwen/Qwen3-8B",
|
||||
"dataset_name": "/e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--exp_rpt_stack-pytest-gpt5mini_glm_4.7_traces_jupiter/snapshots/8f5962e22355e85ad49717a49e9a3821a1db506e_thinking_preprocessed",
|
||||
"training_type": "SFT",
|
||||
"training_parameters": "https://huggingface.co/DCAgent/a1-stack_pytest_gpt5mini/blob/main/config.json",
|
||||
"wandb_link": null,
|
||||
"traces_location_s3": null
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
BIN
tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
240
tokenizer_config.json
Normal file
240
tokenizer_config.json
Normal file
@@ -0,0 +1,240 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151665": {
|
||||
"content": "<tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151666": {
|
||||
"content": "</tool_response>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151667": {
|
||||
"content": "<think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151668": {
|
||||
"content": "</think>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "right",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
16
train_results.json
Normal file
16
train_results.json
Normal file
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"achieved_tflops_per_gpu": 0.0036901022213999698,
|
||||
"achieved_tflops_per_gpu_theoretical": 596.2712030568775,
|
||||
"epoch": 7.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.19432786107063293,
|
||||
"mfu_percent": 0.0002607846092862169,
|
||||
"mfu_percent_theoretical": 42.13930763652845,
|
||||
"total_flos": 1055465597173760.0,
|
||||
"train_loss": 0.21853318925887819,
|
||||
"train_runtime": 17876.6321,
|
||||
"train_samples_per_second": 2.818,
|
||||
"train_steps_per_second": 0.176,
|
||||
"valid_targets_mean": 4280.6,
|
||||
"valid_targets_min": 315
|
||||
}
|
||||
631
trainer_log.jsonl
Normal file
631
trainer_log.jsonl
Normal file
@@ -0,0 +1,631 @@
|
||||
{"current_steps": 5, "total_steps": 3150, "loss": 0.6676, "lr": 5.07936507936508e-07, "epoch": 0.011111111111111112, "percentage": 0.16, "elapsed_time": "0:00:37", "remaining_time": "6:32:03"}
|
||||
{"current_steps": 10, "total_steps": 3150, "loss": 0.658, "lr": 1.142857142857143e-06, "epoch": 0.022222222222222223, "percentage": 0.32, "elapsed_time": "0:01:06", "remaining_time": "5:46:16"}
|
||||
{"current_steps": 15, "total_steps": 3150, "loss": 0.6536, "lr": 1.777777777777778e-06, "epoch": 0.03333333333333333, "percentage": 0.48, "elapsed_time": "0:01:36", "remaining_time": "5:35:55"}
|
||||
{"current_steps": 20, "total_steps": 3150, "loss": 0.6353, "lr": 2.412698412698413e-06, "epoch": 0.044444444444444446, "percentage": 0.63, "elapsed_time": "0:02:11", "remaining_time": "5:42:23"}
|
||||
{"current_steps": 25, "total_steps": 3150, "loss": 0.5386, "lr": 3.047619047619048e-06, "epoch": 0.05555555555555555, "percentage": 0.79, "elapsed_time": "0:02:45", "remaining_time": "5:44:42"}
|
||||
{"current_steps": 30, "total_steps": 3150, "loss": 0.5029, "lr": 3.6825396825396833e-06, "epoch": 0.06666666666666667, "percentage": 0.95, "elapsed_time": "0:03:17", "remaining_time": "5:41:39"}
|
||||
{"current_steps": 35, "total_steps": 3150, "loss": 0.4468, "lr": 4.317460317460318e-06, "epoch": 0.07777777777777778, "percentage": 1.11, "elapsed_time": "0:03:46", "remaining_time": "5:36:12"}
|
||||
{"current_steps": 40, "total_steps": 3150, "loss": 0.4331, "lr": 4.952380952380953e-06, "epoch": 0.08888888888888889, "percentage": 1.27, "elapsed_time": "0:04:16", "remaining_time": "5:31:50"}
|
||||
{"current_steps": 45, "total_steps": 3150, "loss": 0.4438, "lr": 5.5873015873015876e-06, "epoch": 0.1, "percentage": 1.43, "elapsed_time": "0:04:46", "remaining_time": "5:29:53"}
|
||||
{"current_steps": 50, "total_steps": 3150, "loss": 0.4316, "lr": 6.222222222222223e-06, "epoch": 0.1111111111111111, "percentage": 1.59, "elapsed_time": "0:05:14", "remaining_time": "5:25:00"}
|
||||
{"current_steps": 55, "total_steps": 3150, "loss": 0.4538, "lr": 6.857142857142858e-06, "epoch": 0.12222222222222222, "percentage": 1.75, "elapsed_time": "0:05:45", "remaining_time": "5:23:58"}
|
||||
{"current_steps": 60, "total_steps": 3150, "loss": 0.3969, "lr": 7.492063492063493e-06, "epoch": 0.13333333333333333, "percentage": 1.9, "elapsed_time": "0:06:15", "remaining_time": "5:22:25"}
|
||||
{"current_steps": 65, "total_steps": 3150, "loss": 0.3905, "lr": 8.126984126984128e-06, "epoch": 0.14444444444444443, "percentage": 2.06, "elapsed_time": "0:06:42", "remaining_time": "5:18:00"}
|
||||
{"current_steps": 70, "total_steps": 3150, "loss": 0.3874, "lr": 8.761904761904763e-06, "epoch": 0.15555555555555556, "percentage": 2.22, "elapsed_time": "0:07:12", "remaining_time": "5:17:22"}
|
||||
{"current_steps": 75, "total_steps": 3150, "loss": 0.356, "lr": 9.396825396825398e-06, "epoch": 0.16666666666666666, "percentage": 2.38, "elapsed_time": "0:07:38", "remaining_time": "5:13:16"}
|
||||
{"current_steps": 80, "total_steps": 3150, "loss": 0.3536, "lr": 1.0031746031746033e-05, "epoch": 0.17777777777777778, "percentage": 2.54, "elapsed_time": "0:08:06", "remaining_time": "5:11:27"}
|
||||
{"current_steps": 85, "total_steps": 3150, "loss": 0.3733, "lr": 1.0666666666666667e-05, "epoch": 0.18888888888888888, "percentage": 2.7, "elapsed_time": "0:08:39", "remaining_time": "5:11:55"}
|
||||
{"current_steps": 90, "total_steps": 3150, "loss": 0.34, "lr": 1.1301587301587302e-05, "epoch": 0.2, "percentage": 2.86, "elapsed_time": "0:09:04", "remaining_time": "5:08:28"}
|
||||
{"current_steps": 95, "total_steps": 3150, "loss": 0.3612, "lr": 1.1936507936507937e-05, "epoch": 0.2111111111111111, "percentage": 3.02, "elapsed_time": "0:09:29", "remaining_time": "5:05:29"}
|
||||
{"current_steps": 100, "total_steps": 3150, "loss": 0.3496, "lr": 1.2571428571428572e-05, "epoch": 0.2222222222222222, "percentage": 3.17, "elapsed_time": "0:09:59", "remaining_time": "5:04:44"}
|
||||
{"current_steps": 105, "total_steps": 3150, "loss": 0.3417, "lr": 1.3206349206349206e-05, "epoch": 0.23333333333333334, "percentage": 3.33, "elapsed_time": "0:10:25", "remaining_time": "5:02:11"}
|
||||
{"current_steps": 110, "total_steps": 3150, "loss": 0.3631, "lr": 1.3841269841269843e-05, "epoch": 0.24444444444444444, "percentage": 3.49, "elapsed_time": "0:10:55", "remaining_time": "5:02:03"}
|
||||
{"current_steps": 115, "total_steps": 3150, "loss": 0.33, "lr": 1.4476190476190478e-05, "epoch": 0.25555555555555554, "percentage": 3.65, "elapsed_time": "0:11:30", "remaining_time": "5:03:40"}
|
||||
{"current_steps": 120, "total_steps": 3150, "loss": 0.3383, "lr": 1.5111111111111112e-05, "epoch": 0.26666666666666666, "percentage": 3.81, "elapsed_time": "0:12:02", "remaining_time": "5:04:02"}
|
||||
{"current_steps": 125, "total_steps": 3150, "loss": 0.3198, "lr": 1.5746031746031745e-05, "epoch": 0.2777777777777778, "percentage": 3.97, "elapsed_time": "0:12:32", "remaining_time": "5:03:32"}
|
||||
{"current_steps": 130, "total_steps": 3150, "loss": 0.302, "lr": 1.6380952380952384e-05, "epoch": 0.28888888888888886, "percentage": 4.13, "elapsed_time": "0:13:02", "remaining_time": "5:02:59"}
|
||||
{"current_steps": 135, "total_steps": 3150, "loss": 0.3243, "lr": 1.7015873015873018e-05, "epoch": 0.3, "percentage": 4.29, "elapsed_time": "0:13:32", "remaining_time": "5:02:26"}
|
||||
{"current_steps": 140, "total_steps": 3150, "loss": 0.2979, "lr": 1.7650793650793653e-05, "epoch": 0.3111111111111111, "percentage": 4.44, "elapsed_time": "0:14:05", "remaining_time": "5:02:50"}
|
||||
{"current_steps": 145, "total_steps": 3150, "loss": 0.3149, "lr": 1.8285714285714288e-05, "epoch": 0.32222222222222224, "percentage": 4.6, "elapsed_time": "0:14:33", "remaining_time": "5:01:33"}
|
||||
{"current_steps": 150, "total_steps": 3150, "loss": 0.3226, "lr": 1.8920634920634923e-05, "epoch": 0.3333333333333333, "percentage": 4.76, "elapsed_time": "0:15:02", "remaining_time": "5:00:46"}
|
||||
{"current_steps": 155, "total_steps": 3150, "loss": 0.3088, "lr": 1.9555555555555557e-05, "epoch": 0.34444444444444444, "percentage": 4.92, "elapsed_time": "0:15:31", "remaining_time": "4:59:56"}
|
||||
{"current_steps": 160, "total_steps": 3150, "loss": 0.3173, "lr": 2.0190476190476192e-05, "epoch": 0.35555555555555557, "percentage": 5.08, "elapsed_time": "0:16:00", "remaining_time": "4:59:12"}
|
||||
{"current_steps": 165, "total_steps": 3150, "loss": 0.3187, "lr": 2.082539682539683e-05, "epoch": 0.36666666666666664, "percentage": 5.24, "elapsed_time": "0:16:30", "remaining_time": "4:58:35"}
|
||||
{"current_steps": 170, "total_steps": 3150, "loss": 0.2887, "lr": 2.146031746031746e-05, "epoch": 0.37777777777777777, "percentage": 5.4, "elapsed_time": "0:16:58", "remaining_time": "4:57:42"}
|
||||
{"current_steps": 175, "total_steps": 3150, "loss": 0.3388, "lr": 2.20952380952381e-05, "epoch": 0.3888888888888889, "percentage": 5.56, "elapsed_time": "0:17:24", "remaining_time": "4:56:01"}
|
||||
{"current_steps": 180, "total_steps": 3150, "loss": 0.3079, "lr": 2.273015873015873e-05, "epoch": 0.4, "percentage": 5.71, "elapsed_time": "0:17:53", "remaining_time": "4:55:06"}
|
||||
{"current_steps": 185, "total_steps": 3150, "loss": 0.3189, "lr": 2.336507936507937e-05, "epoch": 0.4111111111111111, "percentage": 5.87, "elapsed_time": "0:18:19", "remaining_time": "4:53:41"}
|
||||
{"current_steps": 190, "total_steps": 3150, "loss": 0.3086, "lr": 2.4e-05, "epoch": 0.4222222222222222, "percentage": 6.03, "elapsed_time": "0:18:47", "remaining_time": "4:52:46"}
|
||||
{"current_steps": 195, "total_steps": 3150, "loss": 0.3016, "lr": 2.463492063492064e-05, "epoch": 0.43333333333333335, "percentage": 6.19, "elapsed_time": "0:19:15", "remaining_time": "4:51:47"}
|
||||
{"current_steps": 200, "total_steps": 3150, "loss": 0.3146, "lr": 2.526984126984127e-05, "epoch": 0.4444444444444444, "percentage": 6.35, "elapsed_time": "0:19:44", "remaining_time": "4:51:11"}
|
||||
{"current_steps": 205, "total_steps": 3150, "loss": 0.3152, "lr": 2.5904761904761908e-05, "epoch": 0.45555555555555555, "percentage": 6.51, "elapsed_time": "0:20:12", "remaining_time": "4:50:13"}
|
||||
{"current_steps": 210, "total_steps": 3150, "loss": 0.3122, "lr": 2.653968253968254e-05, "epoch": 0.4666666666666667, "percentage": 6.67, "elapsed_time": "0:20:40", "remaining_time": "4:49:28"}
|
||||
{"current_steps": 215, "total_steps": 3150, "loss": 0.3154, "lr": 2.7174603174603178e-05, "epoch": 0.4777777777777778, "percentage": 6.83, "elapsed_time": "0:21:12", "remaining_time": "4:49:26"}
|
||||
{"current_steps": 220, "total_steps": 3150, "loss": 0.28, "lr": 2.780952380952381e-05, "epoch": 0.4888888888888889, "percentage": 6.98, "elapsed_time": "0:21:43", "remaining_time": "4:49:17"}
|
||||
{"current_steps": 225, "total_steps": 3150, "loss": 0.3075, "lr": 2.8444444444444447e-05, "epoch": 0.5, "percentage": 7.14, "elapsed_time": "0:22:11", "remaining_time": "4:48:23"}
|
||||
{"current_steps": 230, "total_steps": 3150, "loss": 0.2884, "lr": 2.9079365079365082e-05, "epoch": 0.5111111111111111, "percentage": 7.3, "elapsed_time": "0:22:44", "remaining_time": "4:48:49"}
|
||||
{"current_steps": 235, "total_steps": 3150, "loss": 0.2937, "lr": 2.9714285714285717e-05, "epoch": 0.5222222222222223, "percentage": 7.46, "elapsed_time": "0:23:11", "remaining_time": "4:47:36"}
|
||||
{"current_steps": 240, "total_steps": 3150, "loss": 0.2914, "lr": 3.034920634920635e-05, "epoch": 0.5333333333333333, "percentage": 7.62, "elapsed_time": "0:23:38", "remaining_time": "4:46:37"}
|
||||
{"current_steps": 245, "total_steps": 3150, "loss": 0.308, "lr": 3.098412698412699e-05, "epoch": 0.5444444444444444, "percentage": 7.78, "elapsed_time": "0:24:03", "remaining_time": "4:45:20"}
|
||||
{"current_steps": 250, "total_steps": 3150, "loss": 0.2811, "lr": 3.161904761904762e-05, "epoch": 0.5555555555555556, "percentage": 7.94, "elapsed_time": "0:24:33", "remaining_time": "4:44:48"}
|
||||
{"current_steps": 255, "total_steps": 3150, "loss": 0.2898, "lr": 3.225396825396826e-05, "epoch": 0.5666666666666667, "percentage": 8.1, "elapsed_time": "0:25:00", "remaining_time": "4:43:51"}
|
||||
{"current_steps": 260, "total_steps": 3150, "loss": 0.2962, "lr": 3.288888888888889e-05, "epoch": 0.5777777777777777, "percentage": 8.25, "elapsed_time": "0:25:28", "remaining_time": "4:43:12"}
|
||||
{"current_steps": 265, "total_steps": 3150, "loss": 0.298, "lr": 3.352380952380953e-05, "epoch": 0.5888888888888889, "percentage": 8.41, "elapsed_time": "0:25:58", "remaining_time": "4:42:46"}
|
||||
{"current_steps": 270, "total_steps": 3150, "loss": 0.2903, "lr": 3.415873015873016e-05, "epoch": 0.6, "percentage": 8.57, "elapsed_time": "0:26:23", "remaining_time": "4:41:27"}
|
||||
{"current_steps": 275, "total_steps": 3150, "loss": 0.2766, "lr": 3.47936507936508e-05, "epoch": 0.6111111111111112, "percentage": 8.73, "elapsed_time": "0:26:54", "remaining_time": "4:41:23"}
|
||||
{"current_steps": 280, "total_steps": 3150, "loss": 0.28, "lr": 3.542857142857143e-05, "epoch": 0.6222222222222222, "percentage": 8.89, "elapsed_time": "0:27:25", "remaining_time": "4:41:07"}
|
||||
{"current_steps": 285, "total_steps": 3150, "loss": 0.2958, "lr": 3.606349206349207e-05, "epoch": 0.6333333333333333, "percentage": 9.05, "elapsed_time": "0:27:54", "remaining_time": "4:40:30"}
|
||||
{"current_steps": 290, "total_steps": 3150, "loss": 0.3008, "lr": 3.66984126984127e-05, "epoch": 0.6444444444444445, "percentage": 9.21, "elapsed_time": "0:28:20", "remaining_time": "4:39:29"}
|
||||
{"current_steps": 295, "total_steps": 3150, "loss": 0.2685, "lr": 3.733333333333334e-05, "epoch": 0.6555555555555556, "percentage": 9.37, "elapsed_time": "0:28:52", "remaining_time": "4:39:30"}
|
||||
{"current_steps": 300, "total_steps": 3150, "loss": 0.2869, "lr": 3.796825396825397e-05, "epoch": 0.6666666666666666, "percentage": 9.52, "elapsed_time": "0:29:26", "remaining_time": "4:39:38"}
|
||||
{"current_steps": 305, "total_steps": 3150, "loss": 0.2635, "lr": 3.860317460317461e-05, "epoch": 0.6777777777777778, "percentage": 9.68, "elapsed_time": "0:29:59", "remaining_time": "4:39:44"}
|
||||
{"current_steps": 310, "total_steps": 3150, "loss": 0.2679, "lr": 3.923809523809524e-05, "epoch": 0.6888888888888889, "percentage": 9.84, "elapsed_time": "0:30:25", "remaining_time": "4:38:45"}
|
||||
{"current_steps": 315, "total_steps": 3150, "loss": 0.2778, "lr": 3.9873015873015876e-05, "epoch": 0.7, "percentage": 10.0, "elapsed_time": "0:30:52", "remaining_time": "4:37:55"}
|
||||
{"current_steps": 320, "total_steps": 3150, "loss": 0.2757, "lr": 3.999980352246968e-05, "epoch": 0.7111111111111111, "percentage": 10.16, "elapsed_time": "0:31:27", "remaining_time": "4:38:14"}
|
||||
{"current_steps": 325, "total_steps": 3150, "loss": 0.2866, "lr": 3.9999005339118864e-05, "epoch": 0.7222222222222222, "percentage": 10.32, "elapsed_time": "0:31:56", "remaining_time": "4:37:39"}
|
||||
{"current_steps": 330, "total_steps": 3150, "loss": 0.2852, "lr": 3.9997593194586953e-05, "epoch": 0.7333333333333333, "percentage": 10.48, "elapsed_time": "0:32:29", "remaining_time": "4:37:38"}
|
||||
{"current_steps": 335, "total_steps": 3150, "loss": 0.2799, "lr": 3.99955671322262e-05, "epoch": 0.7444444444444445, "percentage": 10.63, "elapsed_time": "0:33:00", "remaining_time": "4:37:23"}
|
||||
{"current_steps": 340, "total_steps": 3150, "loss": 0.2922, "lr": 3.999292721423588e-05, "epoch": 0.7555555555555555, "percentage": 10.79, "elapsed_time": "0:33:32", "remaining_time": "4:37:10"}
|
||||
{"current_steps": 345, "total_steps": 3150, "loss": 0.2837, "lr": 3.998967352166037e-05, "epoch": 0.7666666666666667, "percentage": 10.95, "elapsed_time": "0:33:59", "remaining_time": "4:36:19"}
|
||||
{"current_steps": 350, "total_steps": 3150, "loss": 0.2983, "lr": 3.998580615438671e-05, "epoch": 0.7777777777777778, "percentage": 11.11, "elapsed_time": "0:34:28", "remaining_time": "4:35:45"}
|
||||
{"current_steps": 355, "total_steps": 3150, "loss": 0.2885, "lr": 3.998132523114146e-05, "epoch": 0.7888888888888889, "percentage": 11.27, "elapsed_time": "0:34:56", "remaining_time": "4:35:03"}
|
||||
{"current_steps": 360, "total_steps": 3150, "loss": 0.2716, "lr": 3.9976230889487107e-05, "epoch": 0.8, "percentage": 11.43, "elapsed_time": "0:35:26", "remaining_time": "4:34:42"}
|
||||
{"current_steps": 365, "total_steps": 3150, "loss": 0.2772, "lr": 3.997052328581783e-05, "epoch": 0.8111111111111111, "percentage": 11.59, "elapsed_time": "0:35:56", "remaining_time": "4:34:13"}
|
||||
{"current_steps": 370, "total_steps": 3150, "loss": 0.277, "lr": 3.99642025953547e-05, "epoch": 0.8222222222222222, "percentage": 11.75, "elapsed_time": "0:36:26", "remaining_time": "4:33:46"}
|
||||
{"current_steps": 375, "total_steps": 3150, "loss": 0.2786, "lr": 3.9957269012140306e-05, "epoch": 0.8333333333333334, "percentage": 11.9, "elapsed_time": "0:36:54", "remaining_time": "4:33:05"}
|
||||
{"current_steps": 380, "total_steps": 3150, "loss": 0.2705, "lr": 3.9949722749032755e-05, "epoch": 0.8444444444444444, "percentage": 12.06, "elapsed_time": "0:37:24", "remaining_time": "4:32:38"}
|
||||
{"current_steps": 385, "total_steps": 3150, "loss": 0.2908, "lr": 3.994156403769922e-05, "epoch": 0.8555555555555555, "percentage": 12.22, "elapsed_time": "0:37:54", "remaining_time": "4:32:17"}
|
||||
{"current_steps": 390, "total_steps": 3150, "loss": 0.2549, "lr": 3.993279312860876e-05, "epoch": 0.8666666666666667, "percentage": 12.38, "elapsed_time": "0:38:18", "remaining_time": "4:31:05"}
|
||||
{"current_steps": 395, "total_steps": 3150, "loss": 0.2673, "lr": 3.9923410291024636e-05, "epoch": 0.8777777777777778, "percentage": 12.54, "elapsed_time": "0:38:46", "remaining_time": "4:30:24"}
|
||||
{"current_steps": 400, "total_steps": 3150, "loss": 0.2625, "lr": 3.991341581299609e-05, "epoch": 0.8888888888888888, "percentage": 12.7, "elapsed_time": "0:39:19", "remaining_time": "4:30:22"}
|
||||
{"current_steps": 405, "total_steps": 3150, "loss": 0.2851, "lr": 3.990281000134946e-05, "epoch": 0.9, "percentage": 12.86, "elapsed_time": "0:39:52", "remaining_time": "4:30:12"}
|
||||
{"current_steps": 410, "total_steps": 3150, "loss": 0.281, "lr": 3.989159318167875e-05, "epoch": 0.9111111111111111, "percentage": 13.02, "elapsed_time": "0:40:23", "remaining_time": "4:29:57"}
|
||||
{"current_steps": 415, "total_steps": 3150, "loss": 0.258, "lr": 3.9879765698335705e-05, "epoch": 0.9222222222222223, "percentage": 13.17, "elapsed_time": "0:40:50", "remaining_time": "4:29:12"}
|
||||
{"current_steps": 420, "total_steps": 3150, "loss": 0.2765, "lr": 3.986732791441915e-05, "epoch": 0.9333333333333333, "percentage": 13.33, "elapsed_time": "0:41:23", "remaining_time": "4:29:03"}
|
||||
{"current_steps": 425, "total_steps": 3150, "loss": 0.2613, "lr": 3.985428021176391e-05, "epoch": 0.9444444444444444, "percentage": 13.49, "elapsed_time": "0:41:51", "remaining_time": "4:28:23"}
|
||||
{"current_steps": 430, "total_steps": 3150, "loss": 0.2607, "lr": 3.984062299092904e-05, "epoch": 0.9555555555555556, "percentage": 13.65, "elapsed_time": "0:42:17", "remaining_time": "4:27:34"}
|
||||
{"current_steps": 435, "total_steps": 3150, "loss": 0.2771, "lr": 3.982635667118557e-05, "epoch": 0.9666666666666667, "percentage": 13.81, "elapsed_time": "0:42:42", "remaining_time": "4:26:35"}
|
||||
{"current_steps": 440, "total_steps": 3150, "loss": 0.2749, "lr": 3.981148169050361e-05, "epoch": 0.9777777777777777, "percentage": 13.97, "elapsed_time": "0:43:10", "remaining_time": "4:25:58"}
|
||||
{"current_steps": 445, "total_steps": 3150, "loss": 0.3032, "lr": 3.97959985055389e-05, "epoch": 0.9888888888888889, "percentage": 14.13, "elapsed_time": "0:43:37", "remaining_time": "4:25:11"}
|
||||
{"current_steps": 450, "total_steps": 3150, "loss": 0.2528, "lr": 3.97799075916188e-05, "epoch": 1.0, "percentage": 14.29, "elapsed_time": "0:44:02", "remaining_time": "4:24:16"}
|
||||
{"current_steps": 455, "total_steps": 3150, "loss": 0.2498, "lr": 3.976320944272773e-05, "epoch": 1.011111111111111, "percentage": 14.44, "elapsed_time": "0:44:32", "remaining_time": "4:23:48"}
|
||||
{"current_steps": 460, "total_steps": 3150, "loss": 0.2431, "lr": 3.9745904571491916e-05, "epoch": 1.0222222222222221, "percentage": 14.6, "elapsed_time": "0:44:59", "remaining_time": "4:23:08"}
|
||||
{"current_steps": 465, "total_steps": 3150, "loss": 0.2631, "lr": 3.972799350916375e-05, "epoch": 1.0333333333333334, "percentage": 14.76, "elapsed_time": "0:45:30", "remaining_time": "4:22:44"}
|
||||
{"current_steps": 470, "total_steps": 3150, "loss": 0.2568, "lr": 3.970947680560543e-05, "epoch": 1.0444444444444445, "percentage": 14.92, "elapsed_time": "0:45:56", "remaining_time": "4:21:55"}
|
||||
{"current_steps": 475, "total_steps": 3150, "loss": 0.2522, "lr": 3.969035502927208e-05, "epoch": 1.0555555555555556, "percentage": 15.08, "elapsed_time": "0:46:22", "remaining_time": "4:21:08"}
|
||||
{"current_steps": 480, "total_steps": 3150, "loss": 0.2625, "lr": 3.967062876719433e-05, "epoch": 1.0666666666666667, "percentage": 15.24, "elapsed_time": "0:46:54", "remaining_time": "4:20:52"}
|
||||
{"current_steps": 485, "total_steps": 3150, "loss": 0.275, "lr": 3.965029862496023e-05, "epoch": 1.0777777777777777, "percentage": 15.4, "elapsed_time": "0:47:22", "remaining_time": "4:20:21"}
|
||||
{"current_steps": 490, "total_steps": 3150, "loss": 0.274, "lr": 3.962936522669674e-05, "epoch": 1.0888888888888888, "percentage": 15.56, "elapsed_time": "0:47:54", "remaining_time": "4:20:02"}
|
||||
{"current_steps": 495, "total_steps": 3150, "loss": 0.2376, "lr": 3.960782921505052e-05, "epoch": 1.1, "percentage": 15.71, "elapsed_time": "0:48:23", "remaining_time": "4:19:35"}
|
||||
{"current_steps": 500, "total_steps": 3150, "loss": 0.2534, "lr": 3.9585691251168205e-05, "epoch": 1.1111111111111112, "percentage": 15.87, "elapsed_time": "0:48:51", "remaining_time": "4:18:57"}
|
||||
{"current_steps": 505, "total_steps": 3150, "loss": 0.246, "lr": 3.9562952014676116e-05, "epoch": 1.1222222222222222, "percentage": 16.03, "elapsed_time": "0:49:20", "remaining_time": "4:18:28"}
|
||||
{"current_steps": 510, "total_steps": 3150, "loss": 0.25, "lr": 3.95396122036594e-05, "epoch": 1.1333333333333333, "percentage": 16.19, "elapsed_time": "0:49:47", "remaining_time": "4:17:43"}
|
||||
{"current_steps": 515, "total_steps": 3150, "loss": 0.271, "lr": 3.951567253464058e-05, "epoch": 1.1444444444444444, "percentage": 16.35, "elapsed_time": "0:50:18", "remaining_time": "4:17:25"}
|
||||
{"current_steps": 520, "total_steps": 3150, "loss": 0.2305, "lr": 3.949113374255759e-05, "epoch": 1.1555555555555554, "percentage": 16.51, "elapsed_time": "0:50:49", "remaining_time": "4:17:01"}
|
||||
{"current_steps": 525, "total_steps": 3150, "loss": 0.2423, "lr": 3.946599658074117e-05, "epoch": 1.1666666666666667, "percentage": 16.67, "elapsed_time": "0:51:15", "remaining_time": "4:16:17"}
|
||||
{"current_steps": 530, "total_steps": 3150, "loss": 0.2753, "lr": 3.94402618208918e-05, "epoch": 1.1777777777777778, "percentage": 16.83, "elapsed_time": "0:51:42", "remaining_time": "4:15:37"}
|
||||
{"current_steps": 535, "total_steps": 3150, "loss": 0.2515, "lr": 3.9413930253055925e-05, "epoch": 1.1888888888888889, "percentage": 16.98, "elapsed_time": "0:52:14", "remaining_time": "4:15:22"}
|
||||
{"current_steps": 540, "total_steps": 3150, "loss": 0.2423, "lr": 3.938700268560179e-05, "epoch": 1.2, "percentage": 17.14, "elapsed_time": "0:52:45", "remaining_time": "4:14:58"}
|
||||
{"current_steps": 545, "total_steps": 3150, "loss": 0.2473, "lr": 3.935947994519455e-05, "epoch": 1.211111111111111, "percentage": 17.3, "elapsed_time": "0:53:14", "remaining_time": "4:14:29"}
|
||||
{"current_steps": 550, "total_steps": 3150, "loss": 0.2797, "lr": 3.933136287677095e-05, "epoch": 1.2222222222222223, "percentage": 17.46, "elapsed_time": "0:53:44", "remaining_time": "4:14:02"}
|
||||
{"current_steps": 555, "total_steps": 3150, "loss": 0.251, "lr": 3.9302652343513325e-05, "epoch": 1.2333333333333334, "percentage": 17.62, "elapsed_time": "0:54:11", "remaining_time": "4:13:20"}
|
||||
{"current_steps": 560, "total_steps": 3150, "loss": 0.2386, "lr": 3.927334922682319e-05, "epoch": 1.2444444444444445, "percentage": 17.78, "elapsed_time": "0:54:39", "remaining_time": "4:12:47"}
|
||||
{"current_steps": 565, "total_steps": 3150, "loss": 0.2414, "lr": 3.924345442629405e-05, "epoch": 1.2555555555555555, "percentage": 17.94, "elapsed_time": "0:55:07", "remaining_time": "4:12:12"}
|
||||
{"current_steps": 570, "total_steps": 3150, "loss": 0.239, "lr": 3.9212968859683924e-05, "epoch": 1.2666666666666666, "percentage": 18.1, "elapsed_time": "0:55:33", "remaining_time": "4:11:26"}
|
||||
{"current_steps": 575, "total_steps": 3150, "loss": 0.249, "lr": 3.918189346288708e-05, "epoch": 1.2777777777777777, "percentage": 18.25, "elapsed_time": "0:56:01", "remaining_time": "4:10:52"}
|
||||
{"current_steps": 580, "total_steps": 3150, "loss": 0.2513, "lr": 3.9150229189905325e-05, "epoch": 1.2888888888888888, "percentage": 18.41, "elapsed_time": "0:56:25", "remaining_time": "4:10:01"}
|
||||
{"current_steps": 585, "total_steps": 3150, "loss": 0.2594, "lr": 3.911797701281872e-05, "epoch": 1.3, "percentage": 18.57, "elapsed_time": "0:56:49", "remaining_time": "4:09:07"}
|
||||
{"current_steps": 590, "total_steps": 3150, "loss": 0.2598, "lr": 3.9085137921755765e-05, "epoch": 1.3111111111111111, "percentage": 18.73, "elapsed_time": "0:57:19", "remaining_time": "4:08:43"}
|
||||
{"current_steps": 595, "total_steps": 3150, "loss": 0.2528, "lr": 3.9051712924862926e-05, "epoch": 1.3222222222222222, "percentage": 18.89, "elapsed_time": "0:57:49", "remaining_time": "4:08:17"}
|
||||
{"current_steps": 600, "total_steps": 3150, "loss": 0.2529, "lr": 3.901770304827379e-05, "epoch": 1.3333333333333333, "percentage": 19.05, "elapsed_time": "0:58:14", "remaining_time": "4:07:31"}
|
||||
{"current_steps": 605, "total_steps": 3150, "loss": 0.2753, "lr": 3.898310933607746e-05, "epoch": 1.3444444444444446, "percentage": 19.21, "elapsed_time": "0:58:41", "remaining_time": "4:06:53"}
|
||||
{"current_steps": 610, "total_steps": 3150, "loss": 0.2389, "lr": 3.8947932850286585e-05, "epoch": 1.3555555555555556, "percentage": 19.37, "elapsed_time": "0:59:10", "remaining_time": "4:06:24"}
|
||||
{"current_steps": 615, "total_steps": 3150, "loss": 0.2505, "lr": 3.891217467080472e-05, "epoch": 1.3666666666666667, "percentage": 19.52, "elapsed_time": "0:59:39", "remaining_time": "4:05:55"}
|
||||
{"current_steps": 620, "total_steps": 3150, "loss": 0.2465, "lr": 3.887583589539315e-05, "epoch": 1.3777777777777778, "percentage": 19.68, "elapsed_time": "1:00:06", "remaining_time": "4:05:15"}
|
||||
{"current_steps": 625, "total_steps": 3150, "loss": 0.2529, "lr": 3.883891763963723e-05, "epoch": 1.3888888888888888, "percentage": 19.84, "elapsed_time": "1:00:38", "remaining_time": "4:04:58"}
|
||||
{"current_steps": 630, "total_steps": 3150, "loss": 0.2341, "lr": 3.880142103691213e-05, "epoch": 1.4, "percentage": 20.0, "elapsed_time": "1:01:04", "remaining_time": "4:04:17"}
|
||||
{"current_steps": 635, "total_steps": 3150, "loss": 0.2561, "lr": 3.876334723834802e-05, "epoch": 1.411111111111111, "percentage": 20.16, "elapsed_time": "1:01:28", "remaining_time": "4:03:27"}
|
||||
{"current_steps": 640, "total_steps": 3150, "loss": 0.2496, "lr": 3.872469741279475e-05, "epoch": 1.4222222222222223, "percentage": 20.32, "elapsed_time": "1:01:59", "remaining_time": "4:03:06"}
|
||||
{"current_steps": 645, "total_steps": 3150, "loss": 0.2535, "lr": 3.868547274678595e-05, "epoch": 1.4333333333333333, "percentage": 20.48, "elapsed_time": "1:02:27", "remaining_time": "4:02:32"}
|
||||
{"current_steps": 650, "total_steps": 3150, "loss": 0.2524, "lr": 3.864567444450263e-05, "epoch": 1.4444444444444444, "percentage": 20.63, "elapsed_time": "1:02:53", "remaining_time": "4:01:53"}
|
||||
{"current_steps": 655, "total_steps": 3150, "loss": 0.2434, "lr": 3.8605303727736186e-05, "epoch": 1.4555555555555555, "percentage": 20.79, "elapsed_time": "1:03:23", "remaining_time": "4:01:28"}
|
||||
{"current_steps": 660, "total_steps": 3150, "loss": 0.2638, "lr": 3.856436183585089e-05, "epoch": 1.4666666666666668, "percentage": 20.95, "elapsed_time": "1:03:53", "remaining_time": "4:01:02"}
|
||||
{"current_steps": 665, "total_steps": 3150, "loss": 0.2584, "lr": 3.8522850025745885e-05, "epoch": 1.4777777777777779, "percentage": 21.11, "elapsed_time": "1:04:23", "remaining_time": "4:00:37"}
|
||||
{"current_steps": 670, "total_steps": 3150, "loss": 0.2516, "lr": 3.8480769571816535e-05, "epoch": 1.488888888888889, "percentage": 21.27, "elapsed_time": "1:04:53", "remaining_time": "4:00:10"}
|
||||
{"current_steps": 675, "total_steps": 3150, "loss": 0.2382, "lr": 3.843812176591535e-05, "epoch": 1.5, "percentage": 21.43, "elapsed_time": "1:05:20", "remaining_time": "3:59:35"}
|
||||
{"current_steps": 680, "total_steps": 3150, "loss": 0.2391, "lr": 3.8394907917312314e-05, "epoch": 1.511111111111111, "percentage": 21.59, "elapsed_time": "1:05:50", "remaining_time": "3:59:10"}
|
||||
{"current_steps": 685, "total_steps": 3150, "loss": 0.2412, "lr": 3.835112935265468e-05, "epoch": 1.5222222222222221, "percentage": 21.75, "elapsed_time": "1:06:19", "remaining_time": "3:58:40"}
|
||||
{"current_steps": 690, "total_steps": 3150, "loss": 0.2358, "lr": 3.830678741592625e-05, "epoch": 1.5333333333333332, "percentage": 21.9, "elapsed_time": "1:06:46", "remaining_time": "3:58:03"}
|
||||
{"current_steps": 695, "total_steps": 3150, "loss": 0.262, "lr": 3.826188346840611e-05, "epoch": 1.5444444444444443, "percentage": 22.06, "elapsed_time": "1:07:17", "remaining_time": "3:57:40"}
|
||||
{"current_steps": 700, "total_steps": 3150, "loss": 0.2439, "lr": 3.8216418888626864e-05, "epoch": 1.5555555555555556, "percentage": 22.22, "elapsed_time": "1:07:46", "remaining_time": "3:57:13"}
|
||||
{"current_steps": 705, "total_steps": 3150, "loss": 0.2569, "lr": 3.817039507233227e-05, "epoch": 1.5666666666666667, "percentage": 22.38, "elapsed_time": "1:08:15", "remaining_time": "3:56:41"}
|
||||
{"current_steps": 710, "total_steps": 3150, "loss": 0.2376, "lr": 3.812381343243444e-05, "epoch": 1.5777777777777777, "percentage": 22.54, "elapsed_time": "1:08:44", "remaining_time": "3:56:14"}
|
||||
{"current_steps": 715, "total_steps": 3150, "loss": 0.238, "lr": 3.807667539897041e-05, "epoch": 1.588888888888889, "percentage": 22.7, "elapsed_time": "1:09:13", "remaining_time": "3:55:45"}
|
||||
{"current_steps": 720, "total_steps": 3150, "loss": 0.2585, "lr": 3.8028982419058304e-05, "epoch": 1.6, "percentage": 22.86, "elapsed_time": "1:09:42", "remaining_time": "3:55:15"}
|
||||
{"current_steps": 725, "total_steps": 3150, "loss": 0.2473, "lr": 3.798073595685283e-05, "epoch": 1.6111111111111112, "percentage": 23.02, "elapsed_time": "1:10:15", "remaining_time": "3:55:00"}
|
||||
{"current_steps": 730, "total_steps": 3150, "loss": 0.2523, "lr": 3.793193749350042e-05, "epoch": 1.6222222222222222, "percentage": 23.17, "elapsed_time": "1:10:42", "remaining_time": "3:54:25"}
|
||||
{"current_steps": 735, "total_steps": 3150, "loss": 0.2593, "lr": 3.788258852709367e-05, "epoch": 1.6333333333333333, "percentage": 23.33, "elapsed_time": "1:11:14", "remaining_time": "3:54:05"}
|
||||
{"current_steps": 740, "total_steps": 3150, "loss": 0.2193, "lr": 3.7832690572625417e-05, "epoch": 1.6444444444444444, "percentage": 23.49, "elapsed_time": "1:11:44", "remaining_time": "3:53:40"}
|
||||
{"current_steps": 745, "total_steps": 3150, "loss": 0.2603, "lr": 3.77822451619422e-05, "epoch": 1.6555555555555554, "percentage": 23.65, "elapsed_time": "1:12:17", "remaining_time": "3:53:21"}
|
||||
{"current_steps": 750, "total_steps": 3150, "loss": 0.2438, "lr": 3.773125384369723e-05, "epoch": 1.6666666666666665, "percentage": 23.81, "elapsed_time": "1:12:44", "remaining_time": "3:52:47"}
|
||||
{"current_steps": 755, "total_steps": 3150, "loss": 0.2519, "lr": 3.7679718183302856e-05, "epoch": 1.6777777777777778, "percentage": 23.97, "elapsed_time": "1:13:17", "remaining_time": "3:52:29"}
|
||||
{"current_steps": 760, "total_steps": 3150, "loss": 0.261, "lr": 3.762763976288252e-05, "epoch": 1.6888888888888889, "percentage": 24.13, "elapsed_time": "1:13:42", "remaining_time": "3:51:47"}
|
||||
{"current_steps": 765, "total_steps": 3150, "loss": 0.2604, "lr": 3.757502018122215e-05, "epoch": 1.7, "percentage": 24.29, "elapsed_time": "1:14:10", "remaining_time": "3:51:15"}
|
||||
{"current_steps": 770, "total_steps": 3150, "loss": 0.2734, "lr": 3.7521861053721104e-05, "epoch": 1.7111111111111112, "percentage": 24.44, "elapsed_time": "1:14:35", "remaining_time": "3:50:34"}
|
||||
{"current_steps": 775, "total_steps": 3150, "loss": 0.2436, "lr": 3.74681640123426e-05, "epoch": 1.7222222222222223, "percentage": 24.6, "elapsed_time": "1:15:01", "remaining_time": "3:49:56"}
|
||||
{"current_steps": 780, "total_steps": 3150, "loss": 0.2469, "lr": 3.741393070556355e-05, "epoch": 1.7333333333333334, "percentage": 24.76, "elapsed_time": "1:15:27", "remaining_time": "3:49:16"}
|
||||
{"current_steps": 785, "total_steps": 3150, "loss": 0.2451, "lr": 3.7359162798324015e-05, "epoch": 1.7444444444444445, "percentage": 24.92, "elapsed_time": "1:15:55", "remaining_time": "3:48:43"}
|
||||
{"current_steps": 790, "total_steps": 3150, "loss": 0.2645, "lr": 3.7303861971976074e-05, "epoch": 1.7555555555555555, "percentage": 25.08, "elapsed_time": "1:16:21", "remaining_time": "3:48:07"}
|
||||
{"current_steps": 795, "total_steps": 3150, "loss": 0.2541, "lr": 3.724802992423218e-05, "epoch": 1.7666666666666666, "percentage": 25.24, "elapsed_time": "1:16:52", "remaining_time": "3:47:44"}
|
||||
{"current_steps": 800, "total_steps": 3150, "loss": 0.2563, "lr": 3.719166836911309e-05, "epoch": 1.7777777777777777, "percentage": 25.4, "elapsed_time": "1:17:21", "remaining_time": "3:47:14"}
|
||||
{"current_steps": 805, "total_steps": 3150, "loss": 0.2532, "lr": 3.713477903689518e-05, "epoch": 1.7888888888888888, "percentage": 25.56, "elapsed_time": "1:17:49", "remaining_time": "3:46:41"}
|
||||
{"current_steps": 810, "total_steps": 3150, "loss": 0.2542, "lr": 3.707736367405741e-05, "epoch": 1.8, "percentage": 25.71, "elapsed_time": "1:18:16", "remaining_time": "3:46:07"}
|
||||
{"current_steps": 815, "total_steps": 3150, "loss": 0.2443, "lr": 3.701942404322764e-05, "epoch": 1.8111111111111111, "percentage": 25.87, "elapsed_time": "1:18:46", "remaining_time": "3:45:41"}
|
||||
{"current_steps": 820, "total_steps": 3150, "loss": 0.2468, "lr": 3.696096192312852e-05, "epoch": 1.8222222222222222, "percentage": 26.03, "elapsed_time": "1:19:16", "remaining_time": "3:45:16"}
|
||||
{"current_steps": 825, "total_steps": 3150, "loss": 0.2688, "lr": 3.690197910852294e-05, "epoch": 1.8333333333333335, "percentage": 26.19, "elapsed_time": "1:19:44", "remaining_time": "3:44:44"}
|
||||
{"current_steps": 830, "total_steps": 3150, "loss": 0.235, "lr": 3.684247741015888e-05, "epoch": 1.8444444444444446, "percentage": 26.35, "elapsed_time": "1:20:10", "remaining_time": "3:44:05"}
|
||||
{"current_steps": 835, "total_steps": 3150, "loss": 0.2482, "lr": 3.678245865471383e-05, "epoch": 1.8555555555555556, "percentage": 26.51, "elapsed_time": "1:20:38", "remaining_time": "3:43:34"}
|
||||
{"current_steps": 840, "total_steps": 3150, "loss": 0.2437, "lr": 3.672192468473872e-05, "epoch": 1.8666666666666667, "percentage": 26.67, "elapsed_time": "1:21:07", "remaining_time": "3:43:06"}
|
||||
{"current_steps": 845, "total_steps": 3150, "loss": 0.2422, "lr": 3.666087735860138e-05, "epoch": 1.8777777777777778, "percentage": 26.83, "elapsed_time": "1:21:33", "remaining_time": "3:42:28"}
|
||||
{"current_steps": 850, "total_steps": 3150, "loss": 0.2504, "lr": 3.6599318550429415e-05, "epoch": 1.8888888888888888, "percentage": 26.98, "elapsed_time": "1:22:02", "remaining_time": "3:41:59"}
|
||||
{"current_steps": 855, "total_steps": 3150, "loss": 0.2358, "lr": 3.653725015005275e-05, "epoch": 1.9, "percentage": 27.14, "elapsed_time": "1:22:28", "remaining_time": "3:41:23"}
|
||||
{"current_steps": 860, "total_steps": 3150, "loss": 0.2466, "lr": 3.6474674062945573e-05, "epoch": 1.911111111111111, "percentage": 27.3, "elapsed_time": "1:22:59", "remaining_time": "3:41:00"}
|
||||
{"current_steps": 865, "total_steps": 3150, "loss": 0.242, "lr": 3.6411592210167834e-05, "epoch": 1.9222222222222223, "percentage": 27.46, "elapsed_time": "1:23:28", "remaining_time": "3:40:31"}
|
||||
{"current_steps": 870, "total_steps": 3150, "loss": 0.2441, "lr": 3.6348006528306295e-05, "epoch": 1.9333333333333333, "percentage": 27.62, "elapsed_time": "1:23:54", "remaining_time": "3:39:52"}
|
||||
{"current_steps": 875, "total_steps": 3150, "loss": 0.2349, "lr": 3.628391896941505e-05, "epoch": 1.9444444444444444, "percentage": 27.78, "elapsed_time": "1:24:22", "remaining_time": "3:39:21"}
|
||||
{"current_steps": 880, "total_steps": 3150, "loss": 0.2662, "lr": 3.621933150095561e-05, "epoch": 1.9555555555555557, "percentage": 27.94, "elapsed_time": "1:24:47", "remaining_time": "3:38:44"}
|
||||
{"current_steps": 885, "total_steps": 3150, "loss": 0.2681, "lr": 3.615424610573651e-05, "epoch": 1.9666666666666668, "percentage": 28.1, "elapsed_time": "1:25:12", "remaining_time": "3:38:04"}
|
||||
{"current_steps": 890, "total_steps": 3150, "loss": 0.2466, "lr": 3.608866478185245e-05, "epoch": 1.9777777777777779, "percentage": 28.25, "elapsed_time": "1:25:43", "remaining_time": "3:37:40"}
|
||||
{"current_steps": 895, "total_steps": 3150, "loss": 0.235, "lr": 3.602258954262287e-05, "epoch": 1.988888888888889, "percentage": 28.41, "elapsed_time": "1:26:10", "remaining_time": "3:37:07"}
|
||||
{"current_steps": 900, "total_steps": 3150, "loss": 0.248, "lr": 3.595602241653028e-05, "epoch": 2.0, "percentage": 28.57, "elapsed_time": "1:26:41", "remaining_time": "3:36:42"}
|
||||
{"current_steps": 905, "total_steps": 3150, "loss": 0.2363, "lr": 3.588896544715787e-05, "epoch": 2.011111111111111, "percentage": 28.73, "elapsed_time": "1:27:09", "remaining_time": "3:36:12"}
|
||||
{"current_steps": 910, "total_steps": 3150, "loss": 0.2403, "lr": 3.5821420693126834e-05, "epoch": 2.022222222222222, "percentage": 28.89, "elapsed_time": "1:27:47", "remaining_time": "3:36:05"}
|
||||
{"current_steps": 915, "total_steps": 3150, "loss": 0.2336, "lr": 3.575339022803313e-05, "epoch": 2.033333333333333, "percentage": 29.05, "elapsed_time": "1:28:16", "remaining_time": "3:35:36"}
|
||||
{"current_steps": 920, "total_steps": 3150, "loss": 0.2199, "lr": 3.5684876140383875e-05, "epoch": 2.0444444444444443, "percentage": 29.21, "elapsed_time": "1:28:42", "remaining_time": "3:35:02"}
|
||||
{"current_steps": 925, "total_steps": 3150, "loss": 0.2174, "lr": 3.561588053353319e-05, "epoch": 2.0555555555555554, "percentage": 29.37, "elapsed_time": "1:29:09", "remaining_time": "3:34:26"}
|
||||
{"current_steps": 930, "total_steps": 3150, "loss": 0.22, "lr": 3.554640552561761e-05, "epoch": 2.066666666666667, "percentage": 29.52, "elapsed_time": "1:29:36", "remaining_time": "3:33:53"}
|
||||
{"current_steps": 935, "total_steps": 3150, "loss": 0.2297, "lr": 3.5476453249491125e-05, "epoch": 2.077777777777778, "percentage": 29.68, "elapsed_time": "1:30:09", "remaining_time": "3:33:35"}
|
||||
{"current_steps": 940, "total_steps": 3150, "loss": 0.2005, "lr": 3.5406025852659626e-05, "epoch": 2.088888888888889, "percentage": 29.84, "elapsed_time": "1:30:38", "remaining_time": "3:33:05"}
|
||||
{"current_steps": 945, "total_steps": 3150, "loss": 0.2129, "lr": 3.533512549721503e-05, "epoch": 2.1, "percentage": 30.0, "elapsed_time": "1:31:01", "remaining_time": "3:32:24"}
|
||||
{"current_steps": 950, "total_steps": 3150, "loss": 0.2176, "lr": 3.5263754359768896e-05, "epoch": 2.111111111111111, "percentage": 30.16, "elapsed_time": "1:31:32", "remaining_time": "3:31:59"}
|
||||
{"current_steps": 955, "total_steps": 3150, "loss": 0.2184, "lr": 3.5191914631385565e-05, "epoch": 2.1222222222222222, "percentage": 30.32, "elapsed_time": "1:31:59", "remaining_time": "3:31:25"}
|
||||
{"current_steps": 960, "total_steps": 3150, "loss": 0.2139, "lr": 3.511960851751496e-05, "epoch": 2.1333333333333333, "percentage": 30.48, "elapsed_time": "1:32:27", "remaining_time": "3:30:55"}
|
||||
{"current_steps": 965, "total_steps": 3150, "loss": 0.231, "lr": 3.504683823792483e-05, "epoch": 2.1444444444444444, "percentage": 30.63, "elapsed_time": "1:32:59", "remaining_time": "3:30:32"}
|
||||
{"current_steps": 970, "total_steps": 3150, "loss": 0.2194, "lr": 3.49736060266326e-05, "epoch": 2.1555555555555554, "percentage": 30.79, "elapsed_time": "1:33:27", "remaining_time": "3:30:01"}
|
||||
{"current_steps": 975, "total_steps": 3150, "loss": 0.2077, "lr": 3.489991413183686e-05, "epoch": 2.1666666666666665, "percentage": 30.95, "elapsed_time": "1:33:52", "remaining_time": "3:29:24"}
|
||||
{"current_steps": 980, "total_steps": 3150, "loss": 0.2232, "lr": 3.482576481584824e-05, "epoch": 2.1777777777777776, "percentage": 31.11, "elapsed_time": "1:34:19", "remaining_time": "3:28:51"}
|
||||
{"current_steps": 985, "total_steps": 3150, "loss": 0.2094, "lr": 3.4751160355020034e-05, "epoch": 2.188888888888889, "percentage": 31.27, "elapsed_time": "1:34:48", "remaining_time": "3:28:23"}
|
||||
{"current_steps": 990, "total_steps": 3150, "loss": 0.2195, "lr": 3.467610303967829e-05, "epoch": 2.2, "percentage": 31.43, "elapsed_time": "1:35:18", "remaining_time": "3:27:56"}
|
||||
{"current_steps": 995, "total_steps": 3150, "loss": 0.248, "lr": 3.4600595174051496e-05, "epoch": 2.2111111111111112, "percentage": 31.59, "elapsed_time": "1:35:53", "remaining_time": "3:27:41"}
|
||||
{"current_steps": 1000, "total_steps": 3150, "loss": 0.2202, "lr": 3.452463907619986e-05, "epoch": 2.2222222222222223, "percentage": 31.75, "elapsed_time": "1:36:22", "remaining_time": "3:27:12"}
|
||||
{"current_steps": 1005, "total_steps": 3150, "loss": 0.2321, "lr": 3.444823707794414e-05, "epoch": 2.2333333333333334, "percentage": 31.9, "elapsed_time": "1:36:50", "remaining_time": "3:26:41"}
|
||||
{"current_steps": 1010, "total_steps": 3150, "loss": 0.2199, "lr": 3.437139152479403e-05, "epoch": 2.2444444444444445, "percentage": 32.06, "elapsed_time": "1:37:14", "remaining_time": "3:26:02"}
|
||||
{"current_steps": 1015, "total_steps": 3150, "loss": 0.2146, "lr": 3.429410477587619e-05, "epoch": 2.2555555555555555, "percentage": 32.22, "elapsed_time": "1:37:45", "remaining_time": "3:25:37"}
|
||||
{"current_steps": 1020, "total_steps": 3150, "loss": 0.2155, "lr": 3.4216379203861785e-05, "epoch": 2.2666666666666666, "percentage": 32.38, "elapsed_time": "1:38:16", "remaining_time": "3:25:13"}
|
||||
{"current_steps": 1025, "total_steps": 3150, "loss": 0.2394, "lr": 3.41382171948937e-05, "epoch": 2.2777777777777777, "percentage": 32.54, "elapsed_time": "1:38:42", "remaining_time": "3:24:37"}
|
||||
{"current_steps": 1030, "total_steps": 3150, "loss": 0.2265, "lr": 3.405962114851324e-05, "epoch": 2.2888888888888888, "percentage": 32.7, "elapsed_time": "1:39:10", "remaining_time": "3:24:07"}
|
||||
{"current_steps": 1035, "total_steps": 3150, "loss": 0.2384, "lr": 3.398059347758647e-05, "epoch": 2.3, "percentage": 32.86, "elapsed_time": "1:39:41", "remaining_time": "3:23:42"}
|
||||
{"current_steps": 1040, "total_steps": 3150, "loss": 0.2424, "lr": 3.3901136608230166e-05, "epoch": 2.311111111111111, "percentage": 33.02, "elapsed_time": "1:40:10", "remaining_time": "3:23:13"}
|
||||
{"current_steps": 1045, "total_steps": 3150, "loss": 0.2259, "lr": 3.38212529797373e-05, "epoch": 2.3222222222222224, "percentage": 33.17, "elapsed_time": "1:40:39", "remaining_time": "3:22:46"}
|
||||
{"current_steps": 1050, "total_steps": 3150, "loss": 0.2182, "lr": 3.374094504450218e-05, "epoch": 2.3333333333333335, "percentage": 33.33, "elapsed_time": "1:41:07", "remaining_time": "3:22:14"}
|
||||
{"current_steps": 1055, "total_steps": 3150, "loss": 0.2289, "lr": 3.366021526794517e-05, "epoch": 2.3444444444444446, "percentage": 33.49, "elapsed_time": "1:41:37", "remaining_time": "3:21:47"}
|
||||
{"current_steps": 1060, "total_steps": 3150, "loss": 0.2224, "lr": 3.357906612843697e-05, "epoch": 2.3555555555555556, "percentage": 33.65, "elapsed_time": "1:42:04", "remaining_time": "3:21:16"}
|
||||
{"current_steps": 1065, "total_steps": 3150, "loss": 0.2298, "lr": 3.349750011722256e-05, "epoch": 2.3666666666666667, "percentage": 33.81, "elapsed_time": "1:42:36", "remaining_time": "3:20:52"}
|
||||
{"current_steps": 1070, "total_steps": 3150, "loss": 0.2292, "lr": 3.3415519738344686e-05, "epoch": 2.3777777777777778, "percentage": 33.97, "elapsed_time": "1:43:07", "remaining_time": "3:20:28"}
|
||||
{"current_steps": 1075, "total_steps": 3150, "loss": 0.2184, "lr": 3.333312750856703e-05, "epoch": 2.388888888888889, "percentage": 34.13, "elapsed_time": "1:43:35", "remaining_time": "3:19:56"}
|
||||
{"current_steps": 1080, "total_steps": 3150, "loss": 0.2296, "lr": 3.3250325957296936e-05, "epoch": 2.4, "percentage": 34.29, "elapsed_time": "1:44:08", "remaining_time": "3:19:35"}
|
||||
{"current_steps": 1085, "total_steps": 3150, "loss": 0.2226, "lr": 3.3167117626507726e-05, "epoch": 2.411111111111111, "percentage": 34.44, "elapsed_time": "1:44:37", "remaining_time": "3:19:06"}
|
||||
{"current_steps": 1090, "total_steps": 3150, "loss": 0.2285, "lr": 3.308350507066069e-05, "epoch": 2.422222222222222, "percentage": 34.6, "elapsed_time": "1:45:03", "remaining_time": "3:18:33"}
|
||||
{"current_steps": 1095, "total_steps": 3150, "loss": 0.2117, "lr": 3.2999490856626674e-05, "epoch": 2.4333333333333336, "percentage": 34.76, "elapsed_time": "1:45:29", "remaining_time": "3:17:58"}
|
||||
{"current_steps": 1100, "total_steps": 3150, "loss": 0.2399, "lr": 3.291507756360725e-05, "epoch": 2.4444444444444446, "percentage": 34.92, "elapsed_time": "1:45:54", "remaining_time": "3:17:22"}
|
||||
{"current_steps": 1105, "total_steps": 3150, "loss": 0.224, "lr": 3.283026778305554e-05, "epoch": 2.4555555555555557, "percentage": 35.08, "elapsed_time": "1:46:26", "remaining_time": "3:16:58"}
|
||||
{"current_steps": 1110, "total_steps": 3150, "loss": 0.2317, "lr": 3.2745064118596696e-05, "epoch": 2.466666666666667, "percentage": 35.24, "elapsed_time": "1:46:51", "remaining_time": "3:16:22"}
|
||||
{"current_steps": 1115, "total_steps": 3150, "loss": 0.232, "lr": 3.265946918594793e-05, "epoch": 2.477777777777778, "percentage": 35.4, "elapsed_time": "1:47:15", "remaining_time": "3:15:45"}
|
||||
{"current_steps": 1120, "total_steps": 3150, "loss": 0.2217, "lr": 3.257348561283822e-05, "epoch": 2.488888888888889, "percentage": 35.56, "elapsed_time": "1:47:41", "remaining_time": "3:15:11"}
|
||||
{"current_steps": 1125, "total_steps": 3150, "loss": 0.2144, "lr": 3.248711603892765e-05, "epoch": 2.5, "percentage": 35.71, "elapsed_time": "1:48:10", "remaining_time": "3:14:42"}
|
||||
{"current_steps": 1130, "total_steps": 3150, "loss": 0.2476, "lr": 3.240036311572635e-05, "epoch": 2.511111111111111, "percentage": 35.87, "elapsed_time": "1:48:33", "remaining_time": "3:14:02"}
|
||||
{"current_steps": 1135, "total_steps": 3150, "loss": 0.2188, "lr": 3.2313229506513167e-05, "epoch": 2.522222222222222, "percentage": 36.03, "elapsed_time": "1:49:00", "remaining_time": "3:13:31"}
|
||||
{"current_steps": 1140, "total_steps": 3150, "loss": 0.2431, "lr": 3.22257178862538e-05, "epoch": 2.533333333333333, "percentage": 36.19, "elapsed_time": "1:49:34", "remaining_time": "3:13:11"}
|
||||
{"current_steps": 1145, "total_steps": 3150, "loss": 0.2299, "lr": 3.213783094151873e-05, "epoch": 2.5444444444444443, "percentage": 36.35, "elapsed_time": "1:50:00", "remaining_time": "3:12:38"}
|
||||
{"current_steps": 1150, "total_steps": 3150, "loss": 0.2235, "lr": 3.204957137040079e-05, "epoch": 2.5555555555555554, "percentage": 36.51, "elapsed_time": "1:50:33", "remaining_time": "3:12:16"}
|
||||
{"current_steps": 1155, "total_steps": 3150, "loss": 0.2182, "lr": 3.196094188243224e-05, "epoch": 2.5666666666666664, "percentage": 36.67, "elapsed_time": "1:50:56", "remaining_time": "3:11:38"}
|
||||
{"current_steps": 1160, "total_steps": 3150, "loss": 0.2195, "lr": 3.187194519850167e-05, "epoch": 2.5777777777777775, "percentage": 36.83, "elapsed_time": "1:51:23", "remaining_time": "3:11:05"}
|
||||
{"current_steps": 1165, "total_steps": 3150, "loss": 0.2326, "lr": 3.17825840507704e-05, "epoch": 2.588888888888889, "percentage": 36.98, "elapsed_time": "1:51:53", "remaining_time": "3:10:38"}
|
||||
{"current_steps": 1170, "total_steps": 3150, "loss": 0.2191, "lr": 3.169286118258867e-05, "epoch": 2.6, "percentage": 37.14, "elapsed_time": "1:52:22", "remaining_time": "3:10:10"}
|
||||
{"current_steps": 1175, "total_steps": 3150, "loss": 0.2194, "lr": 3.1602779348411354e-05, "epoch": 2.611111111111111, "percentage": 37.3, "elapsed_time": "1:52:48", "remaining_time": "3:09:37"}
|
||||
{"current_steps": 1180, "total_steps": 3150, "loss": 0.2224, "lr": 3.151234131371348e-05, "epoch": 2.6222222222222222, "percentage": 37.46, "elapsed_time": "1:53:16", "remaining_time": "3:09:06"}
|
||||
{"current_steps": 1185, "total_steps": 3150, "loss": 0.2231, "lr": 3.142154985490523e-05, "epoch": 2.6333333333333333, "percentage": 37.62, "elapsed_time": "1:53:42", "remaining_time": "3:08:33"}
|
||||
{"current_steps": 1190, "total_steps": 3150, "loss": 0.2079, "lr": 3.1330407759246805e-05, "epoch": 2.6444444444444444, "percentage": 37.78, "elapsed_time": "1:54:09", "remaining_time": "3:08:01"}
|
||||
{"current_steps": 1195, "total_steps": 3150, "loss": 0.2062, "lr": 3.1238917824762794e-05, "epoch": 2.6555555555555554, "percentage": 37.94, "elapsed_time": "1:54:40", "remaining_time": "3:07:37"}
|
||||
{"current_steps": 1200, "total_steps": 3150, "loss": 0.2228, "lr": 3.1147082860156275e-05, "epoch": 2.6666666666666665, "percentage": 38.1, "elapsed_time": "1:55:12", "remaining_time": "3:07:12"}
|
||||
{"current_steps": 1205, "total_steps": 3150, "loss": 0.2108, "lr": 3.105490568472266e-05, "epoch": 2.677777777777778, "percentage": 38.25, "elapsed_time": "1:55:36", "remaining_time": "3:06:37"}
|
||||
{"current_steps": 1210, "total_steps": 3150, "loss": 0.2333, "lr": 3.0962389128263025e-05, "epoch": 2.688888888888889, "percentage": 38.41, "elapsed_time": "1:56:07", "remaining_time": "3:06:11"}
|
||||
{"current_steps": 1215, "total_steps": 3150, "loss": 0.2199, "lr": 3.086953603099736e-05, "epoch": 2.7, "percentage": 38.57, "elapsed_time": "1:56:35", "remaining_time": "3:05:40"}
|
||||
{"current_steps": 1220, "total_steps": 3150, "loss": 0.2182, "lr": 3.077634924347728e-05, "epoch": 2.7111111111111112, "percentage": 38.73, "elapsed_time": "1:57:02", "remaining_time": "3:05:08"}
|
||||
{"current_steps": 1225, "total_steps": 3150, "loss": 0.2293, "lr": 3.068283162649858e-05, "epoch": 2.7222222222222223, "percentage": 38.89, "elapsed_time": "1:57:28", "remaining_time": "3:04:36"}
|
||||
{"current_steps": 1230, "total_steps": 3150, "loss": 0.216, "lr": 3.0588986051013355e-05, "epoch": 2.7333333333333334, "percentage": 39.05, "elapsed_time": "1:57:58", "remaining_time": "3:04:09"}
|
||||
{"current_steps": 1235, "total_steps": 3150, "loss": 0.2231, "lr": 3.049481539804192e-05, "epoch": 2.7444444444444445, "percentage": 39.21, "elapsed_time": "1:58:25", "remaining_time": "3:03:37"}
|
||||
{"current_steps": 1240, "total_steps": 3150, "loss": 0.2201, "lr": 3.0400322558584308e-05, "epoch": 2.7555555555555555, "percentage": 39.37, "elapsed_time": "1:58:51", "remaining_time": "3:03:04"}
|
||||
{"current_steps": 1245, "total_steps": 3150, "loss": 0.2444, "lr": 3.0305510433531568e-05, "epoch": 2.7666666666666666, "percentage": 39.52, "elapsed_time": "1:59:20", "remaining_time": "3:02:35"}
|
||||
{"current_steps": 1250, "total_steps": 3150, "loss": 0.2227, "lr": 3.0210381933576654e-05, "epoch": 2.7777777777777777, "percentage": 39.68, "elapsed_time": "1:59:50", "remaining_time": "3:02:09"}
|
||||
{"current_steps": 1255, "total_steps": 3150, "loss": 0.2268, "lr": 3.0114939979125135e-05, "epoch": 2.7888888888888888, "percentage": 39.84, "elapsed_time": "2:00:22", "remaining_time": "3:01:46"}
|
||||
{"current_steps": 1260, "total_steps": 3150, "loss": 0.2216, "lr": 3.001918750020547e-05, "epoch": 2.8, "percentage": 40.0, "elapsed_time": "2:00:46", "remaining_time": "3:01:09"}
|
||||
{"current_steps": 1265, "total_steps": 3150, "loss": 0.2121, "lr": 2.992312743637911e-05, "epoch": 2.811111111111111, "percentage": 40.16, "elapsed_time": "2:01:11", "remaining_time": "3:00:35"}
|
||||
{"current_steps": 1270, "total_steps": 3150, "loss": 0.2065, "lr": 2.982676273665023e-05, "epoch": 2.822222222222222, "percentage": 40.32, "elapsed_time": "2:01:41", "remaining_time": "3:00:08"}
|
||||
{"current_steps": 1275, "total_steps": 3150, "loss": 0.2301, "lr": 2.97300963593752e-05, "epoch": 2.8333333333333335, "percentage": 40.48, "elapsed_time": "2:02:09", "remaining_time": "2:59:39"}
|
||||
{"current_steps": 1280, "total_steps": 3150, "loss": 0.2155, "lr": 2.9633131272171768e-05, "epoch": 2.8444444444444446, "percentage": 40.63, "elapsed_time": "2:02:34", "remaining_time": "2:59:05"}
|
||||
{"current_steps": 1285, "total_steps": 3150, "loss": 0.2136, "lr": 2.953587045182795e-05, "epoch": 2.8555555555555556, "percentage": 40.79, "elapsed_time": "2:03:03", "remaining_time": "2:58:36"}
|
||||
{"current_steps": 1290, "total_steps": 3150, "loss": 0.2263, "lr": 2.943831688421066e-05, "epoch": 2.8666666666666667, "percentage": 40.95, "elapsed_time": "2:03:27", "remaining_time": "2:58:00"}
|
||||
{"current_steps": 1295, "total_steps": 3150, "loss": 0.2254, "lr": 2.9340473564174003e-05, "epoch": 2.8777777777777778, "percentage": 41.11, "elapsed_time": "2:03:51", "remaining_time": "2:57:25"}
|
||||
{"current_steps": 1300, "total_steps": 3150, "loss": 0.2347, "lr": 2.9242343495467396e-05, "epoch": 2.888888888888889, "percentage": 41.27, "elapsed_time": "2:04:22", "remaining_time": "2:57:00"}
|
||||
{"current_steps": 1305, "total_steps": 3150, "loss": 0.2228, "lr": 2.9143929690643292e-05, "epoch": 2.9, "percentage": 41.43, "elapsed_time": "2:04:54", "remaining_time": "2:56:36"}
|
||||
{"current_steps": 1310, "total_steps": 3150, "loss": 0.2322, "lr": 2.9045235170964754e-05, "epoch": 2.911111111111111, "percentage": 41.59, "elapsed_time": "2:05:22", "remaining_time": "2:56:05"}
|
||||
{"current_steps": 1315, "total_steps": 3150, "loss": 0.2247, "lr": 2.8946262966312652e-05, "epoch": 2.9222222222222225, "percentage": 41.75, "elapsed_time": "2:05:52", "remaining_time": "2:55:38"}
|
||||
{"current_steps": 1320, "total_steps": 3150, "loss": 0.2268, "lr": 2.8847016115092686e-05, "epoch": 2.9333333333333336, "percentage": 41.9, "elapsed_time": "2:06:19", "remaining_time": "2:55:08"}
|
||||
{"current_steps": 1325, "total_steps": 3150, "loss": 0.2085, "lr": 2.8747497664142075e-05, "epoch": 2.9444444444444446, "percentage": 42.06, "elapsed_time": "2:06:46", "remaining_time": "2:54:36"}
|
||||
{"current_steps": 1330, "total_steps": 3150, "loss": 0.2251, "lr": 2.8647710668636053e-05, "epoch": 2.9555555555555557, "percentage": 42.22, "elapsed_time": "2:07:12", "remaining_time": "2:54:04"}
|
||||
{"current_steps": 1335, "total_steps": 3150, "loss": 0.2159, "lr": 2.8547658191994054e-05, "epoch": 2.966666666666667, "percentage": 42.38, "elapsed_time": "2:07:37", "remaining_time": "2:53:31"}
|
||||
{"current_steps": 1340, "total_steps": 3150, "loss": 0.2165, "lr": 2.844734330578567e-05, "epoch": 2.977777777777778, "percentage": 42.54, "elapsed_time": "2:08:06", "remaining_time": "2:53:02"}
|
||||
{"current_steps": 1345, "total_steps": 3150, "loss": 0.2223, "lr": 2.834676908963636e-05, "epoch": 2.988888888888889, "percentage": 42.7, "elapsed_time": "2:08:33", "remaining_time": "2:52:31"}
|
||||
{"current_steps": 1350, "total_steps": 3150, "loss": 0.2423, "lr": 2.824593863113291e-05, "epoch": 3.0, "percentage": 42.86, "elapsed_time": "2:09:01", "remaining_time": "2:52:02"}
|
||||
{"current_steps": 1355, "total_steps": 3150, "loss": 0.1906, "lr": 2.814485502572863e-05, "epoch": 3.011111111111111, "percentage": 43.02, "elapsed_time": "2:09:26", "remaining_time": "2:51:28"}
|
||||
{"current_steps": 1360, "total_steps": 3150, "loss": 0.2145, "lr": 2.804352137664835e-05, "epoch": 3.022222222222222, "percentage": 43.17, "elapsed_time": "2:09:57", "remaining_time": "2:51:03"}
|
||||
{"current_steps": 1365, "total_steps": 3150, "loss": 0.1982, "lr": 2.7941940794793122e-05, "epoch": 3.033333333333333, "percentage": 43.33, "elapsed_time": "2:10:24", "remaining_time": "2:50:32"}
|
||||
{"current_steps": 1370, "total_steps": 3150, "loss": 0.1881, "lr": 2.7840116398644742e-05, "epoch": 3.0444444444444443, "percentage": 43.49, "elapsed_time": "2:10:50", "remaining_time": "2:49:59"}
|
||||
{"current_steps": 1375, "total_steps": 3150, "loss": 0.195, "lr": 2.7738051314169993e-05, "epoch": 3.0555555555555554, "percentage": 43.65, "elapsed_time": "2:11:20", "remaining_time": "2:49:33"}
|
||||
{"current_steps": 1380, "total_steps": 3150, "loss": 0.1936, "lr": 2.7635748674724702e-05, "epoch": 3.066666666666667, "percentage": 43.81, "elapsed_time": "2:11:45", "remaining_time": "2:48:59"}
|
||||
{"current_steps": 1385, "total_steps": 3150, "loss": 0.1928, "lr": 2.7533211620957532e-05, "epoch": 3.077777777777778, "percentage": 43.97, "elapsed_time": "2:12:07", "remaining_time": "2:48:22"}
|
||||
{"current_steps": 1390, "total_steps": 3150, "loss": 0.2061, "lr": 2.743044330071356e-05, "epoch": 3.088888888888889, "percentage": 44.13, "elapsed_time": "2:12:32", "remaining_time": "2:47:48"}
|
||||
{"current_steps": 1395, "total_steps": 3150, "loss": 0.1965, "lr": 2.7327446868937664e-05, "epoch": 3.1, "percentage": 44.29, "elapsed_time": "2:12:57", "remaining_time": "2:47:16"}
|
||||
{"current_steps": 1400, "total_steps": 3150, "loss": 0.1885, "lr": 2.7224225487577637e-05, "epoch": 3.111111111111111, "percentage": 44.44, "elapsed_time": "2:13:27", "remaining_time": "2:46:49"}
|
||||
{"current_steps": 1405, "total_steps": 3150, "loss": 0.2004, "lr": 2.712078232548714e-05, "epoch": 3.1222222222222222, "percentage": 44.6, "elapsed_time": "2:13:57", "remaining_time": "2:46:22"}
|
||||
{"current_steps": 1410, "total_steps": 3150, "loss": 0.2093, "lr": 2.7017120558328395e-05, "epoch": 3.1333333333333333, "percentage": 44.76, "elapsed_time": "2:14:26", "remaining_time": "2:45:54"}
|
||||
{"current_steps": 1415, "total_steps": 3150, "loss": 0.2034, "lr": 2.6913243368474734e-05, "epoch": 3.1444444444444444, "percentage": 44.92, "elapsed_time": "2:14:51", "remaining_time": "2:45:20"}
|
||||
{"current_steps": 1420, "total_steps": 3150, "loss": 0.2028, "lr": 2.680915394491286e-05, "epoch": 3.1555555555555554, "percentage": 45.08, "elapsed_time": "2:15:19", "remaining_time": "2:44:52"}
|
||||
{"current_steps": 1425, "total_steps": 3150, "loss": 0.2088, "lr": 2.6704855483144973e-05, "epoch": 3.1666666666666665, "percentage": 45.24, "elapsed_time": "2:15:47", "remaining_time": "2:44:23"}
|
||||
{"current_steps": 1430, "total_steps": 3150, "loss": 0.211, "lr": 2.6600351185090637e-05, "epoch": 3.1777777777777776, "percentage": 45.4, "elapsed_time": "2:16:16", "remaining_time": "2:43:54"}
|
||||
{"current_steps": 1435, "total_steps": 3150, "loss": 0.1992, "lr": 2.649564425898853e-05, "epoch": 3.188888888888889, "percentage": 45.56, "elapsed_time": "2:16:43", "remaining_time": "2:43:23"}
|
||||
{"current_steps": 1440, "total_steps": 3150, "loss": 0.1933, "lr": 2.6390737919297925e-05, "epoch": 3.2, "percentage": 45.71, "elapsed_time": "2:17:11", "remaining_time": "2:42:54"}
|
||||
{"current_steps": 1445, "total_steps": 3150, "loss": 0.2036, "lr": 2.6285635386599983e-05, "epoch": 3.2111111111111112, "percentage": 45.87, "elapsed_time": "2:17:35", "remaining_time": "2:42:21"}
|
||||
{"current_steps": 1450, "total_steps": 3150, "loss": 0.2114, "lr": 2.618033988749895e-05, "epoch": 3.2222222222222223, "percentage": 46.03, "elapsed_time": "2:18:04", "remaining_time": "2:41:53"}
|
||||
{"current_steps": 1455, "total_steps": 3150, "loss": 0.2106, "lr": 2.6074854654523023e-05, "epoch": 3.2333333333333334, "percentage": 46.19, "elapsed_time": "2:18:30", "remaining_time": "2:41:21"}
|
||||
{"current_steps": 1460, "total_steps": 3150, "loss": 0.199, "lr": 2.596918292602518e-05, "epoch": 3.2444444444444445, "percentage": 46.35, "elapsed_time": "2:18:59", "remaining_time": "2:40:53"}
|
||||
{"current_steps": 1465, "total_steps": 3150, "loss": 0.1997, "lr": 2.586332794608371e-05, "epoch": 3.2555555555555555, "percentage": 46.51, "elapsed_time": "2:19:26", "remaining_time": "2:40:22"}
|
||||
{"current_steps": 1470, "total_steps": 3150, "loss": 0.1956, "lr": 2.5757292964402653e-05, "epoch": 3.2666666666666666, "percentage": 46.67, "elapsed_time": "2:19:53", "remaining_time": "2:39:52"}
|
||||
{"current_steps": 1475, "total_steps": 3150, "loss": 0.193, "lr": 2.5651081236212045e-05, "epoch": 3.2777777777777777, "percentage": 46.83, "elapsed_time": "2:20:19", "remaining_time": "2:39:20"}
|
||||
{"current_steps": 1480, "total_steps": 3150, "loss": 0.1966, "lr": 2.5544696022167945e-05, "epoch": 3.2888888888888888, "percentage": 46.98, "elapsed_time": "2:20:48", "remaining_time": "2:38:52"}
|
||||
{"current_steps": 1485, "total_steps": 3150, "loss": 0.2198, "lr": 2.5438140588252367e-05, "epoch": 3.3, "percentage": 47.14, "elapsed_time": "2:21:12", "remaining_time": "2:38:19"}
|
||||
{"current_steps": 1490, "total_steps": 3150, "loss": 0.1837, "lr": 2.5331418205672988e-05, "epoch": 3.311111111111111, "percentage": 47.3, "elapsed_time": "2:21:41", "remaining_time": "2:37:51"}
|
||||
{"current_steps": 1495, "total_steps": 3150, "loss": 0.208, "lr": 2.522453215076277e-05, "epoch": 3.3222222222222224, "percentage": 47.46, "elapsed_time": "2:22:06", "remaining_time": "2:37:19"}
|
||||
{"current_steps": 1500, "total_steps": 3150, "loss": 0.2122, "lr": 2.511748570487932e-05, "epoch": 3.3333333333333335, "percentage": 47.62, "elapsed_time": "2:22:33", "remaining_time": "2:36:49"}
|
||||
{"current_steps": 1505, "total_steps": 3150, "loss": 0.1975, "lr": 2.5010282154304193e-05, "epoch": 3.3444444444444446, "percentage": 47.78, "elapsed_time": "2:23:13", "remaining_time": "2:36:33"}
|
||||
{"current_steps": 1510, "total_steps": 3150, "loss": 0.2019, "lr": 2.4902924790142004e-05, "epoch": 3.3555555555555556, "percentage": 47.94, "elapsed_time": "2:23:37", "remaining_time": "2:35:59"}
|
||||
{"current_steps": 1515, "total_steps": 3150, "loss": 0.2145, "lr": 2.479541690821935e-05, "epoch": 3.3666666666666667, "percentage": 48.1, "elapsed_time": "2:24:06", "remaining_time": "2:35:31"}
|
||||
{"current_steps": 1520, "total_steps": 3150, "loss": 0.1977, "lr": 2.4687761808983693e-05, "epoch": 3.3777777777777778, "percentage": 48.25, "elapsed_time": "2:24:33", "remaining_time": "2:35:01"}
|
||||
{"current_steps": 1525, "total_steps": 3150, "loss": 0.1974, "lr": 2.457996279740199e-05, "epoch": 3.388888888888889, "percentage": 48.41, "elapsed_time": "2:25:07", "remaining_time": "2:34:38"}
|
||||
{"current_steps": 1530, "total_steps": 3150, "loss": 0.1913, "lr": 2.4472023182859257e-05, "epoch": 3.4, "percentage": 48.57, "elapsed_time": "2:25:39", "remaining_time": "2:34:14"}
|
||||
{"current_steps": 1535, "total_steps": 3150, "loss": 0.199, "lr": 2.4363946279056947e-05, "epoch": 3.411111111111111, "percentage": 48.73, "elapsed_time": "2:26:10", "remaining_time": "2:33:48"}
|
||||
{"current_steps": 1540, "total_steps": 3150, "loss": 0.215, "lr": 2.4255735403911243e-05, "epoch": 3.422222222222222, "percentage": 48.89, "elapsed_time": "2:26:38", "remaining_time": "2:33:18"}
|
||||
{"current_steps": 1545, "total_steps": 3150, "loss": 0.215, "lr": 2.4147393879451205e-05, "epoch": 3.4333333333333336, "percentage": 49.05, "elapsed_time": "2:27:05", "remaining_time": "2:32:48"}
|
||||
{"current_steps": 1550, "total_steps": 3150, "loss": 0.2036, "lr": 2.4038925031716755e-05, "epoch": 3.4444444444444446, "percentage": 49.21, "elapsed_time": "2:27:28", "remaining_time": "2:32:13"}
|
||||
{"current_steps": 1555, "total_steps": 3150, "loss": 0.2151, "lr": 2.3930332190656604e-05, "epoch": 3.4555555555555557, "percentage": 49.37, "elapsed_time": "2:27:54", "remaining_time": "2:31:42"}
|
||||
{"current_steps": 1560, "total_steps": 3150, "loss": 0.1986, "lr": 2.382161869002599e-05, "epoch": 3.466666666666667, "percentage": 49.52, "elapsed_time": "2:28:22", "remaining_time": "2:31:14"}
|
||||
{"current_steps": 1565, "total_steps": 3150, "loss": 0.2006, "lr": 2.371278786728436e-05, "epoch": 3.477777777777778, "percentage": 49.68, "elapsed_time": "2:28:49", "remaining_time": "2:30:43"}
|
||||
{"current_steps": 1570, "total_steps": 3150, "loss": 0.1948, "lr": 2.3603843063492892e-05, "epoch": 3.488888888888889, "percentage": 49.84, "elapsed_time": "2:29:18", "remaining_time": "2:30:15"}
|
||||
{"current_steps": 1575, "total_steps": 3150, "loss": 0.1965, "lr": 2.3494787623211954e-05, "epoch": 3.5, "percentage": 50.0, "elapsed_time": "2:29:42", "remaining_time": "2:29:42"}
|
||||
{"current_steps": 1580, "total_steps": 3150, "loss": 0.1973, "lr": 2.3385624894398387e-05, "epoch": 3.511111111111111, "percentage": 50.16, "elapsed_time": "2:30:10", "remaining_time": "2:29:13"}
|
||||
{"current_steps": 1585, "total_steps": 3150, "loss": 0.2111, "lr": 2.3276358228302757e-05, "epoch": 3.522222222222222, "percentage": 50.32, "elapsed_time": "2:30:36", "remaining_time": "2:28:42"}
|
||||
{"current_steps": 1590, "total_steps": 3150, "loss": 0.191, "lr": 2.316699097936646e-05, "epoch": 3.533333333333333, "percentage": 50.48, "elapsed_time": "2:31:00", "remaining_time": "2:28:09"}
|
||||
{"current_steps": 1595, "total_steps": 3150, "loss": 0.1971, "lr": 2.305752650511874e-05, "epoch": 3.5444444444444443, "percentage": 50.63, "elapsed_time": "2:31:28", "remaining_time": "2:27:40"}
|
||||
{"current_steps": 1600, "total_steps": 3150, "loss": 0.2015, "lr": 2.2947968166073627e-05, "epoch": 3.5555555555555554, "percentage": 50.79, "elapsed_time": "2:31:57", "remaining_time": "2:27:12"}
|
||||
{"current_steps": 1605, "total_steps": 3150, "loss": 0.1917, "lr": 2.2838319325626746e-05, "epoch": 3.5666666666666664, "percentage": 50.95, "elapsed_time": "2:32:30", "remaining_time": "2:26:48"}
|
||||
{"current_steps": 1610, "total_steps": 3150, "loss": 0.1995, "lr": 2.2728583349952094e-05, "epoch": 3.5777777777777775, "percentage": 51.11, "elapsed_time": "2:32:59", "remaining_time": "2:26:20"}
|
||||
{"current_steps": 1615, "total_steps": 3150, "loss": 0.2028, "lr": 2.2618763607898666e-05, "epoch": 3.588888888888889, "percentage": 51.27, "elapsed_time": "2:33:28", "remaining_time": "2:25:52"}
|
||||
{"current_steps": 1620, "total_steps": 3150, "loss": 0.1992, "lr": 2.250886347088707e-05, "epoch": 3.6, "percentage": 51.43, "elapsed_time": "2:34:01", "remaining_time": "2:25:28"}
|
||||
{"current_steps": 1625, "total_steps": 3150, "loss": 0.1865, "lr": 2.2398886312805996e-05, "epoch": 3.611111111111111, "percentage": 51.59, "elapsed_time": "2:34:27", "remaining_time": "2:24:57"}
|
||||
{"current_steps": 1630, "total_steps": 3150, "loss": 0.213, "lr": 2.228883550990864e-05, "epoch": 3.6222222222222222, "percentage": 51.75, "elapsed_time": "2:34:56", "remaining_time": "2:24:28"}
|
||||
{"current_steps": 1635, "total_steps": 3150, "loss": 0.203, "lr": 2.2178714440709084e-05, "epoch": 3.6333333333333333, "percentage": 51.9, "elapsed_time": "2:35:25", "remaining_time": "2:24:00"}
|
||||
{"current_steps": 1640, "total_steps": 3150, "loss": 0.2106, "lr": 2.206852648587853e-05, "epoch": 3.6444444444444444, "percentage": 52.06, "elapsed_time": "2:35:56", "remaining_time": "2:23:34"}
|
||||
{"current_steps": 1645, "total_steps": 3150, "loss": 0.2239, "lr": 2.1958275028141566e-05, "epoch": 3.6555555555555554, "percentage": 52.22, "elapsed_time": "2:36:28", "remaining_time": "2:23:09"}
|
||||
{"current_steps": 1650, "total_steps": 3150, "loss": 0.192, "lr": 2.1847963452172283e-05, "epoch": 3.6666666666666665, "percentage": 52.38, "elapsed_time": "2:36:54", "remaining_time": "2:22:38"}
|
||||
{"current_steps": 1655, "total_steps": 3150, "loss": 0.2014, "lr": 2.173759514449037e-05, "epoch": 3.677777777777778, "percentage": 52.54, "elapsed_time": "2:37:25", "remaining_time": "2:22:12"}
|
||||
{"current_steps": 1660, "total_steps": 3150, "loss": 0.1981, "lr": 2.1627173493357167e-05, "epoch": 3.688888888888889, "percentage": 52.7, "elapsed_time": "2:37:54", "remaining_time": "2:21:44"}
|
||||
{"current_steps": 1665, "total_steps": 3150, "loss": 0.2009, "lr": 2.1516701888671633e-05, "epoch": 3.7, "percentage": 52.86, "elapsed_time": "2:38:21", "remaining_time": "2:21:14"}
|
||||
{"current_steps": 1670, "total_steps": 3150, "loss": 0.2019, "lr": 2.1406183721866274e-05, "epoch": 3.7111111111111112, "percentage": 53.02, "elapsed_time": "2:38:44", "remaining_time": "2:20:40"}
|
||||
{"current_steps": 1675, "total_steps": 3150, "loss": 0.2024, "lr": 2.1295622385803036e-05, "epoch": 3.7222222222222223, "percentage": 53.17, "elapsed_time": "2:39:08", "remaining_time": "2:20:08"}
|
||||
{"current_steps": 1680, "total_steps": 3150, "loss": 0.1978, "lr": 2.118502127466916e-05, "epoch": 3.7333333333333334, "percentage": 53.33, "elapsed_time": "2:39:37", "remaining_time": "2:19:40"}
|
||||
{"current_steps": 1685, "total_steps": 3150, "loss": 0.198, "lr": 2.1074383783872932e-05, "epoch": 3.7444444444444445, "percentage": 53.49, "elapsed_time": "2:40:06", "remaining_time": "2:19:12"}
|
||||
{"current_steps": 1690, "total_steps": 3150, "loss": 0.1994, "lr": 2.0963713309939516e-05, "epoch": 3.7555555555555555, "percentage": 53.65, "elapsed_time": "2:40:36", "remaining_time": "2:18:44"}
|
||||
{"current_steps": 1695, "total_steps": 3150, "loss": 0.2008, "lr": 2.0853013250406616e-05, "epoch": 3.7666666666666666, "percentage": 53.81, "elapsed_time": "2:41:05", "remaining_time": "2:18:16"}
|
||||
{"current_steps": 1700, "total_steps": 3150, "loss": 0.2006, "lr": 2.0742287003720207e-05, "epoch": 3.7777777777777777, "percentage": 53.97, "elapsed_time": "2:41:31", "remaining_time": "2:17:46"}
|
||||
{"current_steps": 1705, "total_steps": 3150, "loss": 0.1906, "lr": 2.063153796913022e-05, "epoch": 3.7888888888888888, "percentage": 54.13, "elapsed_time": "2:41:59", "remaining_time": "2:17:17"}
|
||||
{"current_steps": 1710, "total_steps": 3150, "loss": 0.2013, "lr": 2.0520769546586133e-05, "epoch": 3.8, "percentage": 54.29, "elapsed_time": "2:42:26", "remaining_time": "2:16:47"}
|
||||
{"current_steps": 1715, "total_steps": 3150, "loss": 0.2127, "lr": 2.040998513663265e-05, "epoch": 3.811111111111111, "percentage": 54.44, "elapsed_time": "2:42:55", "remaining_time": "2:16:19"}
|
||||
{"current_steps": 1720, "total_steps": 3150, "loss": 0.2227, "lr": 2.0299188140305276e-05, "epoch": 3.822222222222222, "percentage": 54.6, "elapsed_time": "2:43:24", "remaining_time": "2:15:51"}
|
||||
{"current_steps": 1725, "total_steps": 3150, "loss": 0.2102, "lr": 2.0188381959025905e-05, "epoch": 3.8333333333333335, "percentage": 54.76, "elapsed_time": "2:43:52", "remaining_time": "2:15:22"}
|
||||
{"current_steps": 1730, "total_steps": 3150, "loss": 0.2154, "lr": 2.007756999449841e-05, "epoch": 3.8444444444444446, "percentage": 54.92, "elapsed_time": "2:44:23", "remaining_time": "2:14:56"}
|
||||
{"current_steps": 1735, "total_steps": 3150, "loss": 0.2082, "lr": 1.9966755648604214e-05, "epoch": 3.8555555555555556, "percentage": 55.08, "elapsed_time": "2:44:52", "remaining_time": "2:14:28"}
|
||||
{"current_steps": 1740, "total_steps": 3150, "loss": 0.1974, "lr": 1.985594232329783e-05, "epoch": 3.8666666666666667, "percentage": 55.24, "elapsed_time": "2:45:21", "remaining_time": "2:14:00"}
|
||||
{"current_steps": 1745, "total_steps": 3150, "loss": 0.2088, "lr": 1.9745133420502465e-05, "epoch": 3.8777777777777778, "percentage": 55.4, "elapsed_time": "2:45:58", "remaining_time": "2:13:38"}
|
||||
{"current_steps": 1750, "total_steps": 3150, "loss": 0.2074, "lr": 1.963433234200553e-05, "epoch": 3.888888888888889, "percentage": 55.56, "elapsed_time": "2:46:24", "remaining_time": "2:13:07"}
|
||||
{"current_steps": 1755, "total_steps": 3150, "loss": 0.2047, "lr": 1.9523542489354256e-05, "epoch": 3.9, "percentage": 55.71, "elapsed_time": "2:46:52", "remaining_time": "2:12:39"}
|
||||
{"current_steps": 1760, "total_steps": 3150, "loss": 0.1936, "lr": 1.941276726375122e-05, "epoch": 3.911111111111111, "percentage": 55.87, "elapsed_time": "2:47:19", "remaining_time": "2:12:08"}
|
||||
{"current_steps": 1765, "total_steps": 3150, "loss": 0.2063, "lr": 1.930201006594999e-05, "epoch": 3.9222222222222225, "percentage": 56.03, "elapsed_time": "2:47:47", "remaining_time": "2:11:39"}
|
||||
{"current_steps": 1770, "total_steps": 3150, "loss": 0.1942, "lr": 1.9191274296150636e-05, "epoch": 3.9333333333333336, "percentage": 56.19, "elapsed_time": "2:48:18", "remaining_time": "2:11:13"}
|
||||
{"current_steps": 1775, "total_steps": 3150, "loss": 0.2072, "lr": 1.9080563353895468e-05, "epoch": 3.9444444444444446, "percentage": 56.35, "elapsed_time": "2:48:45", "remaining_time": "2:10:43"}
|
||||
{"current_steps": 1780, "total_steps": 3150, "loss": 0.2059, "lr": 1.8969880637964523e-05, "epoch": 3.9555555555555557, "percentage": 56.51, "elapsed_time": "2:49:14", "remaining_time": "2:10:15"}
|
||||
{"current_steps": 1785, "total_steps": 3150, "loss": 0.1871, "lr": 1.885922954627137e-05, "epoch": 3.966666666666667, "percentage": 56.67, "elapsed_time": "2:49:45", "remaining_time": "2:09:49"}
|
||||
{"current_steps": 1790, "total_steps": 3150, "loss": 0.1983, "lr": 1.874861347575867e-05, "epoch": 3.977777777777778, "percentage": 56.83, "elapsed_time": "2:50:14", "remaining_time": "2:09:20"}
|
||||
{"current_steps": 1795, "total_steps": 3150, "loss": 0.2081, "lr": 1.8638035822294e-05, "epoch": 3.988888888888889, "percentage": 56.98, "elapsed_time": "2:50:39", "remaining_time": "2:08:49"}
|
||||
{"current_steps": 1800, "total_steps": 3150, "loss": 0.21, "lr": 1.8527499980565505e-05, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "2:51:04", "remaining_time": "2:08:18"}
|
||||
{"current_steps": 1805, "total_steps": 3150, "loss": 0.1853, "lr": 1.841700934397776e-05, "epoch": 4.011111111111111, "percentage": 57.3, "elapsed_time": "2:51:33", "remaining_time": "2:07:50"}
|
||||
{"current_steps": 1810, "total_steps": 3150, "loss": 0.1936, "lr": 1.8306567304547537e-05, "epoch": 4.022222222222222, "percentage": 57.46, "elapsed_time": "2:52:02", "remaining_time": "2:07:22"}
|
||||
{"current_steps": 1815, "total_steps": 3150, "loss": 0.1789, "lr": 1.8196177252799715e-05, "epoch": 4.033333333333333, "percentage": 57.62, "elapsed_time": "2:52:30", "remaining_time": "2:06:53"}
|
||||
{"current_steps": 1820, "total_steps": 3150, "loss": 0.1887, "lr": 1.8085842577663152e-05, "epoch": 4.044444444444444, "percentage": 57.78, "elapsed_time": "2:52:59", "remaining_time": "2:06:25"}
|
||||
{"current_steps": 1825, "total_steps": 3150, "loss": 0.1874, "lr": 1.797556666636669e-05, "epoch": 4.055555555555555, "percentage": 57.94, "elapsed_time": "2:53:25", "remaining_time": "2:05:54"}
|
||||
{"current_steps": 1830, "total_steps": 3150, "loss": 0.2079, "lr": 1.786535290433512e-05, "epoch": 4.066666666666666, "percentage": 58.1, "elapsed_time": "2:53:54", "remaining_time": "2:05:26"}
|
||||
{"current_steps": 1835, "total_steps": 3150, "loss": 0.1778, "lr": 1.775520467508531e-05, "epoch": 4.0777777777777775, "percentage": 58.25, "elapsed_time": "2:54:22", "remaining_time": "2:04:57"}
|
||||
{"current_steps": 1840, "total_steps": 3150, "loss": 0.1968, "lr": 1.7645125360122254e-05, "epoch": 4.088888888888889, "percentage": 58.41, "elapsed_time": "2:54:45", "remaining_time": "2:04:25"}
|
||||
{"current_steps": 1845, "total_steps": 3150, "loss": 0.1791, "lr": 1.7535118338835358e-05, "epoch": 4.1, "percentage": 58.57, "elapsed_time": "2:55:12", "remaining_time": "2:03:55"}
|
||||
{"current_steps": 1850, "total_steps": 3150, "loss": 0.1687, "lr": 1.7425186988394586e-05, "epoch": 4.111111111111111, "percentage": 58.73, "elapsed_time": "2:55:41", "remaining_time": "2:03:27"}
|
||||
{"current_steps": 1855, "total_steps": 3150, "loss": 0.1957, "lr": 1.7315334683646898e-05, "epoch": 4.122222222222222, "percentage": 58.89, "elapsed_time": "2:56:11", "remaining_time": "2:02:59"}
|
||||
{"current_steps": 1860, "total_steps": 3150, "loss": 0.1756, "lr": 1.7205564797012523e-05, "epoch": 4.133333333333334, "percentage": 59.05, "elapsed_time": "2:56:38", "remaining_time": "2:02:30"}
|
||||
{"current_steps": 1865, "total_steps": 3150, "loss": 0.1809, "lr": 1.709588069838154e-05, "epoch": 4.144444444444445, "percentage": 59.21, "elapsed_time": "2:57:05", "remaining_time": "2:02:00"}
|
||||
{"current_steps": 1870, "total_steps": 3150, "loss": 0.1936, "lr": 1.698628575501034e-05, "epoch": 4.155555555555556, "percentage": 59.37, "elapsed_time": "2:57:35", "remaining_time": "2:01:33"}
|
||||
{"current_steps": 1875, "total_steps": 3150, "loss": 0.1717, "lr": 1.6876783331418298e-05, "epoch": 4.166666666666667, "percentage": 59.52, "elapsed_time": "2:58:04", "remaining_time": "2:01:05"}
|
||||
{"current_steps": 1880, "total_steps": 3150, "loss": 0.1774, "lr": 1.6767376789284463e-05, "epoch": 4.177777777777778, "percentage": 59.68, "elapsed_time": "2:58:32", "remaining_time": "2:00:36"}
|
||||
{"current_steps": 1885, "total_steps": 3150, "loss": 0.1899, "lr": 1.6658069487344375e-05, "epoch": 4.188888888888889, "percentage": 59.84, "elapsed_time": "2:58:59", "remaining_time": "2:00:06"}
|
||||
{"current_steps": 1890, "total_steps": 3150, "loss": 0.1972, "lr": 1.6548864781286922e-05, "epoch": 4.2, "percentage": 60.0, "elapsed_time": "2:59:30", "remaining_time": "1:59:40"}
|
||||
{"current_steps": 1895, "total_steps": 3150, "loss": 0.1757, "lr": 1.643976602365136e-05, "epoch": 4.211111111111111, "percentage": 60.16, "elapsed_time": "3:00:01", "remaining_time": "1:59:13"}
|
||||
{"current_steps": 1900, "total_steps": 3150, "loss": 0.185, "lr": 1.6330776563724354e-05, "epoch": 4.222222222222222, "percentage": 60.32, "elapsed_time": "3:00:26", "remaining_time": "1:58:42"}
|
||||
{"current_steps": 1905, "total_steps": 3150, "loss": 0.1838, "lr": 1.62218997474372e-05, "epoch": 4.233333333333333, "percentage": 60.48, "elapsed_time": "3:01:00", "remaining_time": "1:58:17"}
|
||||
{"current_steps": 1910, "total_steps": 3150, "loss": 0.1772, "lr": 1.6113138917263048e-05, "epoch": 4.2444444444444445, "percentage": 60.63, "elapsed_time": "3:01:29", "remaining_time": "1:57:49"}
|
||||
{"current_steps": 1915, "total_steps": 3150, "loss": 0.1867, "lr": 1.6004497412114354e-05, "epoch": 4.2555555555555555, "percentage": 60.79, "elapsed_time": "3:01:58", "remaining_time": "1:57:21"}
|
||||
{"current_steps": 1920, "total_steps": 3150, "loss": 0.1749, "lr": 1.5895978567240314e-05, "epoch": 4.266666666666667, "percentage": 60.95, "elapsed_time": "3:02:26", "remaining_time": "1:56:52"}
|
||||
{"current_steps": 1925, "total_steps": 3150, "loss": 0.1762, "lr": 1.578758571412455e-05, "epoch": 4.277777777777778, "percentage": 61.11, "elapsed_time": "3:02:55", "remaining_time": "1:56:24"}
|
||||
{"current_steps": 1930, "total_steps": 3150, "loss": 0.1811, "lr": 1.5679322180382725e-05, "epoch": 4.288888888888889, "percentage": 61.27, "elapsed_time": "3:03:22", "remaining_time": "1:55:55"}
|
||||
{"current_steps": 1935, "total_steps": 3150, "loss": 0.1788, "lr": 1.5571191289660517e-05, "epoch": 4.3, "percentage": 61.43, "elapsed_time": "3:03:49", "remaining_time": "1:55:25"}
|
||||
{"current_steps": 1940, "total_steps": 3150, "loss": 0.1761, "lr": 1.5463196361531463e-05, "epoch": 4.311111111111111, "percentage": 61.59, "elapsed_time": "3:04:14", "remaining_time": "1:54:54"}
|
||||
{"current_steps": 1945, "total_steps": 3150, "loss": 0.1777, "lr": 1.5355340711395154e-05, "epoch": 4.322222222222222, "percentage": 61.75, "elapsed_time": "3:04:39", "remaining_time": "1:54:24"}
|
||||
{"current_steps": 1950, "total_steps": 3150, "loss": 0.1931, "lr": 1.5247627650375356e-05, "epoch": 4.333333333333333, "percentage": 61.9, "elapsed_time": "3:05:06", "remaining_time": "1:53:55"}
|
||||
{"current_steps": 1955, "total_steps": 3150, "loss": 0.2096, "lr": 1.5140060485218448e-05, "epoch": 4.344444444444444, "percentage": 62.06, "elapsed_time": "3:05:35", "remaining_time": "1:53:26"}
|
||||
{"current_steps": 1960, "total_steps": 3150, "loss": 0.1768, "lr": 1.5032642518191842e-05, "epoch": 4.355555555555555, "percentage": 62.22, "elapsed_time": "3:06:02", "remaining_time": "1:52:57"}
|
||||
{"current_steps": 1965, "total_steps": 3150, "loss": 0.2015, "lr": 1.4925377046982642e-05, "epoch": 4.366666666666666, "percentage": 62.38, "elapsed_time": "3:06:26", "remaining_time": "1:52:25"}
|
||||
{"current_steps": 1970, "total_steps": 3150, "loss": 0.1876, "lr": 1.4818267364596382e-05, "epoch": 4.377777777777778, "percentage": 62.54, "elapsed_time": "3:06:54", "remaining_time": "1:51:57"}
|
||||
{"current_steps": 1975, "total_steps": 3150, "loss": 0.1753, "lr": 1.4711316759255963e-05, "epoch": 4.388888888888889, "percentage": 62.7, "elapsed_time": "3:07:21", "remaining_time": "1:51:27"}
|
||||
{"current_steps": 1980, "total_steps": 3150, "loss": 0.1748, "lr": 1.4604528514300657e-05, "epoch": 4.4, "percentage": 62.86, "elapsed_time": "3:07:53", "remaining_time": "1:51:01"}
|
||||
{"current_steps": 1985, "total_steps": 3150, "loss": 0.1876, "lr": 1.449790590808537e-05, "epoch": 4.411111111111111, "percentage": 63.02, "elapsed_time": "3:08:21", "remaining_time": "1:50:32"}
|
||||
{"current_steps": 1990, "total_steps": 3150, "loss": 0.193, "lr": 1.4391452213879949e-05, "epoch": 4.4222222222222225, "percentage": 63.17, "elapsed_time": "3:08:50", "remaining_time": "1:50:04"}
|
||||
{"current_steps": 1995, "total_steps": 3150, "loss": 0.1718, "lr": 1.428517069976872e-05, "epoch": 4.433333333333334, "percentage": 63.33, "elapsed_time": "3:09:16", "remaining_time": "1:49:34"}
|
||||
{"current_steps": 2000, "total_steps": 3150, "loss": 0.1935, "lr": 1.4179064628550139e-05, "epoch": 4.444444444444445, "percentage": 63.49, "elapsed_time": "3:09:41", "remaining_time": "1:49:04"}
|
||||
{"current_steps": 2005, "total_steps": 3150, "loss": 0.1766, "lr": 1.4073137257636664e-05, "epoch": 4.455555555555556, "percentage": 63.65, "elapsed_time": "3:10:09", "remaining_time": "1:48:35"}
|
||||
{"current_steps": 2010, "total_steps": 3150, "loss": 0.1843, "lr": 1.3967391838954692e-05, "epoch": 4.466666666666667, "percentage": 63.81, "elapsed_time": "3:10:34", "remaining_time": "1:48:05"}
|
||||
{"current_steps": 2015, "total_steps": 3150, "loss": 0.1783, "lr": 1.3861831618844797e-05, "epoch": 4.477777777777778, "percentage": 63.97, "elapsed_time": "3:11:04", "remaining_time": "1:47:37"}
|
||||
{"current_steps": 2020, "total_steps": 3150, "loss": 0.1791, "lr": 1.3756459837962006e-05, "epoch": 4.488888888888889, "percentage": 64.13, "elapsed_time": "3:11:31", "remaining_time": "1:47:08"}
|
||||
{"current_steps": 2025, "total_steps": 3150, "loss": 0.1829, "lr": 1.3651279731176364e-05, "epoch": 4.5, "percentage": 64.29, "elapsed_time": "3:11:57", "remaining_time": "1:46:38"}
|
||||
{"current_steps": 2030, "total_steps": 3150, "loss": 0.1912, "lr": 1.354629452747357e-05, "epoch": 4.511111111111111, "percentage": 64.44, "elapsed_time": "3:12:28", "remaining_time": "1:46:11"}
|
||||
{"current_steps": 2035, "total_steps": 3150, "loss": 0.1752, "lr": 1.3441507449855914e-05, "epoch": 4.522222222222222, "percentage": 64.6, "elapsed_time": "3:13:00", "remaining_time": "1:45:44"}
|
||||
{"current_steps": 2040, "total_steps": 3150, "loss": 0.1881, "lr": 1.3336921715243269e-05, "epoch": 4.533333333333333, "percentage": 64.76, "elapsed_time": "3:13:29", "remaining_time": "1:45:17"}
|
||||
{"current_steps": 2045, "total_steps": 3150, "loss": 0.1904, "lr": 1.323254053437438e-05, "epoch": 4.544444444444444, "percentage": 64.92, "elapsed_time": "3:13:57", "remaining_time": "1:44:48"}
|
||||
{"current_steps": 2050, "total_steps": 3150, "loss": 0.1996, "lr": 1.3128367111708263e-05, "epoch": 4.555555555555555, "percentage": 65.08, "elapsed_time": "3:14:25", "remaining_time": "1:44:19"}
|
||||
{"current_steps": 2055, "total_steps": 3150, "loss": 0.1724, "lr": 1.3024404645325852e-05, "epoch": 4.566666666666666, "percentage": 65.24, "elapsed_time": "3:14:55", "remaining_time": "1:43:51"}
|
||||
{"current_steps": 2060, "total_steps": 3150, "loss": 0.1794, "lr": 1.2920656326831802e-05, "epoch": 4.5777777777777775, "percentage": 65.4, "elapsed_time": "3:15:23", "remaining_time": "1:43:23"}
|
||||
{"current_steps": 2065, "total_steps": 3150, "loss": 0.1744, "lr": 1.2817125341256533e-05, "epoch": 4.588888888888889, "percentage": 65.56, "elapsed_time": "3:15:52", "remaining_time": "1:42:54"}
|
||||
{"current_steps": 2070, "total_steps": 3150, "loss": 0.1768, "lr": 1.271381486695841e-05, "epoch": 4.6, "percentage": 65.71, "elapsed_time": "3:16:21", "remaining_time": "1:42:26"}
|
||||
{"current_steps": 2075, "total_steps": 3150, "loss": 0.1756, "lr": 1.2610728075526226e-05, "epoch": 4.611111111111111, "percentage": 65.87, "elapsed_time": "3:16:51", "remaining_time": "1:41:59"}
|
||||
{"current_steps": 2080, "total_steps": 3150, "loss": 0.1832, "lr": 1.250786813168176e-05, "epoch": 4.622222222222222, "percentage": 66.03, "elapsed_time": "3:17:14", "remaining_time": "1:41:28"}
|
||||
{"current_steps": 2085, "total_steps": 3150, "loss": 0.1854, "lr": 1.2405238193182711e-05, "epoch": 4.633333333333333, "percentage": 66.19, "elapsed_time": "3:17:39", "remaining_time": "1:40:57"}
|
||||
{"current_steps": 2090, "total_steps": 3150, "loss": 0.1766, "lr": 1.2302841410725664e-05, "epoch": 4.644444444444445, "percentage": 66.35, "elapsed_time": "3:18:06", "remaining_time": "1:40:28"}
|
||||
{"current_steps": 2095, "total_steps": 3150, "loss": 0.1981, "lr": 1.2200680927849447e-05, "epoch": 4.655555555555556, "percentage": 66.51, "elapsed_time": "3:18:33", "remaining_time": "1:39:59"}
|
||||
{"current_steps": 2100, "total_steps": 3150, "loss": 0.1958, "lr": 1.2098759880838562e-05, "epoch": 4.666666666666667, "percentage": 66.67, "elapsed_time": "3:18:59", "remaining_time": "1:39:29"}
|
||||
{"current_steps": 2105, "total_steps": 3150, "loss": 0.1859, "lr": 1.1997081398626951e-05, "epoch": 4.677777777777778, "percentage": 66.83, "elapsed_time": "3:19:23", "remaining_time": "1:38:59"}
|
||||
{"current_steps": 2110, "total_steps": 3150, "loss": 0.1842, "lr": 1.18956486027019e-05, "epoch": 4.688888888888889, "percentage": 66.98, "elapsed_time": "3:19:51", "remaining_time": "1:38:30"}
|
||||
{"current_steps": 2115, "total_steps": 3150, "loss": 0.1725, "lr": 1.179446460700824e-05, "epoch": 4.7, "percentage": 67.14, "elapsed_time": "3:20:21", "remaining_time": "1:38:02"}
|
||||
{"current_steps": 2120, "total_steps": 3150, "loss": 0.1854, "lr": 1.1693532517852723e-05, "epoch": 4.711111111111111, "percentage": 67.3, "elapsed_time": "3:20:51", "remaining_time": "1:37:35"}
|
||||
{"current_steps": 2125, "total_steps": 3150, "loss": 0.1834, "lr": 1.1592855433808694e-05, "epoch": 4.722222222222222, "percentage": 67.46, "elapsed_time": "3:21:21", "remaining_time": "1:37:07"}
|
||||
{"current_steps": 2130, "total_steps": 3150, "loss": 0.2116, "lr": 1.1492436445620925e-05, "epoch": 4.733333333333333, "percentage": 67.62, "elapsed_time": "3:21:50", "remaining_time": "1:36:39"}
|
||||
{"current_steps": 2135, "total_steps": 3150, "loss": 0.1792, "lr": 1.1392278636110779e-05, "epoch": 4.7444444444444445, "percentage": 67.78, "elapsed_time": "3:22:17", "remaining_time": "1:36:10"}
|
||||
{"current_steps": 2140, "total_steps": 3150, "loss": 0.1839, "lr": 1.1292385080081517e-05, "epoch": 4.7555555555555555, "percentage": 67.94, "elapsed_time": "3:22:46", "remaining_time": "1:35:41"}
|
||||
{"current_steps": 2145, "total_steps": 3150, "loss": 0.1866, "lr": 1.1192758844223936e-05, "epoch": 4.766666666666667, "percentage": 68.1, "elapsed_time": "3:23:14", "remaining_time": "1:35:13"}
|
||||
{"current_steps": 2150, "total_steps": 3150, "loss": 0.181, "lr": 1.1093402987022213e-05, "epoch": 4.777777777777778, "percentage": 68.25, "elapsed_time": "3:23:42", "remaining_time": "1:34:44"}
|
||||
{"current_steps": 2155, "total_steps": 3150, "loss": 0.1763, "lr": 1.0994320558660027e-05, "epoch": 4.788888888888889, "percentage": 68.41, "elapsed_time": "3:24:12", "remaining_time": "1:34:17"}
|
||||
{"current_steps": 2160, "total_steps": 3150, "loss": 0.1867, "lr": 1.0895514600926885e-05, "epoch": 4.8, "percentage": 68.57, "elapsed_time": "3:24:39", "remaining_time": "1:33:47"}
|
||||
{"current_steps": 2165, "total_steps": 3150, "loss": 0.1975, "lr": 1.0796988147124767e-05, "epoch": 4.811111111111111, "percentage": 68.73, "elapsed_time": "3:25:13", "remaining_time": "1:33:22"}
|
||||
{"current_steps": 2170, "total_steps": 3150, "loss": 0.1794, "lr": 1.0698744221974992e-05, "epoch": 4.822222222222222, "percentage": 68.89, "elapsed_time": "3:25:41", "remaining_time": "1:32:53"}
|
||||
{"current_steps": 2175, "total_steps": 3150, "loss": 0.1856, "lr": 1.0600785841525387e-05, "epoch": 4.833333333333333, "percentage": 69.05, "elapsed_time": "3:26:09", "remaining_time": "1:32:24"}
|
||||
{"current_steps": 2180, "total_steps": 3150, "loss": 0.1986, "lr": 1.050311601305765e-05, "epoch": 4.844444444444444, "percentage": 69.21, "elapsed_time": "3:26:37", "remaining_time": "1:31:56"}
|
||||
{"current_steps": 2185, "total_steps": 3150, "loss": 0.1882, "lr": 1.0405737734995083e-05, "epoch": 4.855555555555555, "percentage": 69.37, "elapsed_time": "3:27:05", "remaining_time": "1:31:27"}
|
||||
{"current_steps": 2190, "total_steps": 3150, "loss": 0.188, "lr": 1.0308653996810464e-05, "epoch": 4.866666666666667, "percentage": 69.52, "elapsed_time": "3:27:35", "remaining_time": "1:30:59"}
|
||||
{"current_steps": 2195, "total_steps": 3150, "loss": 0.1697, "lr": 1.0211867778934367e-05, "epoch": 4.877777777777778, "percentage": 69.68, "elapsed_time": "3:28:03", "remaining_time": "1:30:31"}
|
||||
{"current_steps": 2200, "total_steps": 3150, "loss": 0.1694, "lr": 1.0115382052663585e-05, "epoch": 4.888888888888889, "percentage": 69.84, "elapsed_time": "3:28:29", "remaining_time": "1:30:01"}
|
||||
{"current_steps": 2205, "total_steps": 3150, "loss": 0.1868, "lr": 1.0019199780069964e-05, "epoch": 4.9, "percentage": 70.0, "elapsed_time": "3:28:58", "remaining_time": "1:29:33"}
|
||||
{"current_steps": 2210, "total_steps": 3150, "loss": 0.178, "lr": 9.923323913909432e-06, "epoch": 4.911111111111111, "percentage": 70.16, "elapsed_time": "3:29:25", "remaining_time": "1:29:04"}
|
||||
{"current_steps": 2215, "total_steps": 3150, "loss": 0.1885, "lr": 9.827757397531373e-06, "epoch": 4.9222222222222225, "percentage": 70.32, "elapsed_time": "3:29:52", "remaining_time": "1:28:35"}
|
||||
{"current_steps": 2220, "total_steps": 3150, "loss": 0.1855, "lr": 9.732503164788251e-06, "epoch": 4.933333333333334, "percentage": 70.48, "elapsed_time": "3:30:21", "remaining_time": "1:28:07"}
|
||||
{"current_steps": 2225, "total_steps": 3150, "loss": 0.1875, "lr": 9.637564139945576e-06, "epoch": 4.944444444444445, "percentage": 70.63, "elapsed_time": "3:30:53", "remaining_time": "1:27:40"}
|
||||
{"current_steps": 2230, "total_steps": 3150, "loss": 0.1849, "lr": 9.542943237592087e-06, "epoch": 4.955555555555556, "percentage": 70.79, "elapsed_time": "3:31:21", "remaining_time": "1:27:11"}
|
||||
{"current_steps": 2235, "total_steps": 3150, "loss": 0.1765, "lr": 9.448643362550289e-06, "epoch": 4.966666666666667, "percentage": 70.95, "elapsed_time": "3:31:51", "remaining_time": "1:26:44"}
|
||||
{"current_steps": 2240, "total_steps": 3150, "loss": 0.187, "lr": 9.354667409787293e-06, "epoch": 4.977777777777778, "percentage": 71.11, "elapsed_time": "3:32:13", "remaining_time": "1:26:13"}
|
||||
{"current_steps": 2245, "total_steps": 3150, "loss": 0.1891, "lr": 9.261018264325934e-06, "epoch": 4.988888888888889, "percentage": 71.27, "elapsed_time": "3:32:41", "remaining_time": "1:25:44"}
|
||||
{"current_steps": 2250, "total_steps": 3150, "loss": 0.1883, "lr": 9.16769880115619e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "3:33:06", "remaining_time": "1:25:14"}
|
||||
{"current_steps": 2255, "total_steps": 3150, "loss": 0.1815, "lr": 9.074711885146928e-06, "epoch": 5.011111111111111, "percentage": 71.59, "elapsed_time": "3:33:33", "remaining_time": "1:24:45"}
|
||||
{"current_steps": 2260, "total_steps": 3150, "loss": 0.1665, "lr": 8.982060370957953e-06, "epoch": 5.022222222222222, "percentage": 71.75, "elapsed_time": "3:34:01", "remaining_time": "1:24:17"}
|
||||
{"current_steps": 2265, "total_steps": 3150, "loss": 0.1649, "lr": 8.889747102952388e-06, "epoch": 5.033333333333333, "percentage": 71.9, "elapsed_time": "3:34:26", "remaining_time": "1:23:47"}
|
||||
{"current_steps": 2270, "total_steps": 3150, "loss": 0.1776, "lr": 8.79777491510932e-06, "epoch": 5.044444444444444, "percentage": 72.06, "elapsed_time": "3:34:52", "remaining_time": "1:23:17"}
|
||||
{"current_steps": 2275, "total_steps": 3150, "loss": 0.1773, "lr": 8.706146630936833e-06, "epoch": 5.055555555555555, "percentage": 72.22, "elapsed_time": "3:35:20", "remaining_time": "1:22:49"}
|
||||
{"current_steps": 2280, "total_steps": 3150, "loss": 0.1678, "lr": 8.6148650633853e-06, "epoch": 5.066666666666666, "percentage": 72.38, "elapsed_time": "3:35:49", "remaining_time": "1:22:21"}
|
||||
{"current_steps": 2285, "total_steps": 3150, "loss": 0.1669, "lr": 8.523933014761038e-06, "epoch": 5.0777777777777775, "percentage": 72.54, "elapsed_time": "3:36:17", "remaining_time": "1:21:52"}
|
||||
{"current_steps": 2290, "total_steps": 3150, "loss": 0.1639, "lr": 8.43335327664027e-06, "epoch": 5.088888888888889, "percentage": 72.7, "elapsed_time": "3:36:48", "remaining_time": "1:21:25"}
|
||||
{"current_steps": 2295, "total_steps": 3150, "loss": 0.1781, "lr": 8.343128629783457e-06, "epoch": 5.1, "percentage": 72.86, "elapsed_time": "3:37:19", "remaining_time": "1:20:57"}
|
||||
{"current_steps": 2300, "total_steps": 3150, "loss": 0.1854, "lr": 8.253261844049883e-06, "epoch": 5.111111111111111, "percentage": 73.02, "elapsed_time": "3:37:45", "remaining_time": "1:20:28"}
|
||||
{"current_steps": 2305, "total_steps": 3150, "loss": 0.1897, "lr": 8.163755678312651e-06, "epoch": 5.122222222222222, "percentage": 73.17, "elapsed_time": "3:38:18", "remaining_time": "1:20:01"}
|
||||
{"current_steps": 2310, "total_steps": 3150, "loss": 0.156, "lr": 8.074612880373972e-06, "epoch": 5.133333333333334, "percentage": 73.33, "elapsed_time": "3:38:45", "remaining_time": "1:19:32"}
|
||||
{"current_steps": 2315, "total_steps": 3150, "loss": 0.1589, "lr": 7.985836186880836e-06, "epoch": 5.144444444444445, "percentage": 73.49, "elapsed_time": "3:39:08", "remaining_time": "1:19:02"}
|
||||
{"current_steps": 2320, "total_steps": 3150, "loss": 0.1688, "lr": 7.897428323240961e-06, "epoch": 5.155555555555556, "percentage": 73.65, "elapsed_time": "3:39:41", "remaining_time": "1:18:35"}
|
||||
{"current_steps": 2325, "total_steps": 3150, "loss": 0.1821, "lr": 7.809392003539142e-06, "epoch": 5.166666666666667, "percentage": 73.81, "elapsed_time": "3:40:12", "remaining_time": "1:18:08"}
|
||||
{"current_steps": 2330, "total_steps": 3150, "loss": 0.1841, "lr": 7.72172993045393e-06, "epoch": 5.177777777777778, "percentage": 73.97, "elapsed_time": "3:40:40", "remaining_time": "1:17:39"}
|
||||
{"current_steps": 2335, "total_steps": 3150, "loss": 0.1689, "lr": 7.634444795174671e-06, "epoch": 5.188888888888889, "percentage": 74.13, "elapsed_time": "3:41:06", "remaining_time": "1:17:10"}
|
||||
{"current_steps": 2340, "total_steps": 3150, "loss": 0.1751, "lr": 7.547539277318861e-06, "epoch": 5.2, "percentage": 74.29, "elapsed_time": "3:41:39", "remaining_time": "1:16:43"}
|
||||
{"current_steps": 2345, "total_steps": 3150, "loss": 0.1714, "lr": 7.461016044849918e-06, "epoch": 5.211111111111111, "percentage": 74.44, "elapsed_time": "3:42:07", "remaining_time": "1:16:15"}
|
||||
{"current_steps": 2350, "total_steps": 3150, "loss": 0.1691, "lr": 7.374877753995224e-06, "epoch": 5.222222222222222, "percentage": 74.6, "elapsed_time": "3:42:37", "remaining_time": "1:15:47"}
|
||||
{"current_steps": 2355, "total_steps": 3150, "loss": 0.1797, "lr": 7.289127049164648e-06, "epoch": 5.233333333333333, "percentage": 74.76, "elapsed_time": "3:43:10", "remaining_time": "1:15:20"}
|
||||
{"current_steps": 2360, "total_steps": 3150, "loss": 0.1611, "lr": 7.203766562869303e-06, "epoch": 5.2444444444444445, "percentage": 74.92, "elapsed_time": "3:43:40", "remaining_time": "1:14:52"}
|
||||
{"current_steps": 2365, "total_steps": 3150, "loss": 0.1703, "lr": 7.118798915640779e-06, "epoch": 5.2555555555555555, "percentage": 75.08, "elapsed_time": "3:44:05", "remaining_time": "1:14:22"}
|
||||
{"current_steps": 2370, "total_steps": 3150, "loss": 0.1767, "lr": 7.03422671595065e-06, "epoch": 5.266666666666667, "percentage": 75.24, "elapsed_time": "3:44:33", "remaining_time": "1:13:54"}
|
||||
{"current_steps": 2375, "total_steps": 3150, "loss": 0.1724, "lr": 6.950052560130414e-06, "epoch": 5.277777777777778, "percentage": 75.4, "elapsed_time": "3:45:03", "remaining_time": "1:13:26"}
|
||||
{"current_steps": 2380, "total_steps": 3150, "loss": 0.1574, "lr": 6.866279032291792e-06, "epoch": 5.288888888888889, "percentage": 75.56, "elapsed_time": "3:45:31", "remaining_time": "1:12:57"}
|
||||
{"current_steps": 2385, "total_steps": 3150, "loss": 0.1664, "lr": 6.782908704247404e-06, "epoch": 5.3, "percentage": 75.71, "elapsed_time": "3:45:57", "remaining_time": "1:12:28"}
|
||||
{"current_steps": 2390, "total_steps": 3150, "loss": 0.1673, "lr": 6.699944135431788e-06, "epoch": 5.311111111111111, "percentage": 75.87, "elapsed_time": "3:46:28", "remaining_time": "1:12:01"}
|
||||
{"current_steps": 2395, "total_steps": 3150, "loss": 0.1614, "lr": 6.617387872822842e-06, "epoch": 5.322222222222222, "percentage": 76.03, "elapsed_time": "3:46:55", "remaining_time": "1:11:32"}
|
||||
{"current_steps": 2400, "total_steps": 3150, "loss": 0.1807, "lr": 6.535242450863632e-06, "epoch": 5.333333333333333, "percentage": 76.19, "elapsed_time": "3:47:23", "remaining_time": "1:11:03"}
|
||||
{"current_steps": 2405, "total_steps": 3150, "loss": 0.1784, "lr": 6.453510391384606e-06, "epoch": 5.344444444444444, "percentage": 76.35, "elapsed_time": "3:47:53", "remaining_time": "1:10:35"}
|
||||
{"current_steps": 2410, "total_steps": 3150, "loss": 0.1619, "lr": 6.372194203526121e-06, "epoch": 5.355555555555555, "percentage": 76.51, "elapsed_time": "3:48:23", "remaining_time": "1:10:07"}
|
||||
{"current_steps": 2415, "total_steps": 3150, "loss": 0.178, "lr": 6.2912963836614916e-06, "epoch": 5.366666666666666, "percentage": 76.67, "elapsed_time": "3:48:51", "remaining_time": "1:09:39"}
|
||||
{"current_steps": 2420, "total_steps": 3150, "loss": 0.1758, "lr": 6.210819415320253e-06, "epoch": 5.377777777777778, "percentage": 76.83, "elapsed_time": "3:49:21", "remaining_time": "1:09:11"}
|
||||
{"current_steps": 2425, "total_steps": 3150, "loss": 0.1663, "lr": 6.130765769112024e-06, "epoch": 5.388888888888889, "percentage": 76.98, "elapsed_time": "3:49:44", "remaining_time": "1:08:41"}
|
||||
{"current_steps": 2430, "total_steps": 3150, "loss": 0.18, "lr": 6.051137902650575e-06, "epoch": 5.4, "percentage": 77.14, "elapsed_time": "3:50:14", "remaining_time": "1:08:13"}
|
||||
{"current_steps": 2435, "total_steps": 3150, "loss": 0.171, "lr": 5.9719382604784405e-06, "epoch": 5.411111111111111, "percentage": 77.3, "elapsed_time": "3:50:41", "remaining_time": "1:07:44"}
|
||||
{"current_steps": 2440, "total_steps": 3150, "loss": 0.1698, "lr": 5.893169273991825e-06, "epoch": 5.4222222222222225, "percentage": 77.46, "elapsed_time": "3:51:11", "remaining_time": "1:07:16"}
|
||||
{"current_steps": 2445, "total_steps": 3150, "loss": 0.1745, "lr": 5.8148333613659945e-06, "epoch": 5.433333333333334, "percentage": 77.62, "elapsed_time": "3:51:42", "remaining_time": "1:06:48"}
|
||||
{"current_steps": 2450, "total_steps": 3150, "loss": 0.172, "lr": 5.736932927481016e-06, "epoch": 5.444444444444445, "percentage": 77.78, "elapsed_time": "3:52:08", "remaining_time": "1:06:19"}
|
||||
{"current_steps": 2455, "total_steps": 3150, "loss": 0.1701, "lr": 5.659470363847956e-06, "epoch": 5.455555555555556, "percentage": 77.94, "elapsed_time": "3:52:38", "remaining_time": "1:05:51"}
|
||||
{"current_steps": 2460, "total_steps": 3150, "loss": 0.1689, "lr": 5.5824480485354315e-06, "epoch": 5.466666666666667, "percentage": 78.1, "elapsed_time": "3:53:06", "remaining_time": "1:05:23"}
|
||||
{"current_steps": 2465, "total_steps": 3150, "loss": 0.1842, "lr": 5.505868346096623e-06, "epoch": 5.477777777777778, "percentage": 78.25, "elapsed_time": "3:53:36", "remaining_time": "1:04:54"}
|
||||
{"current_steps": 2470, "total_steps": 3150, "loss": 0.161, "lr": 5.429733607496674e-06, "epoch": 5.488888888888889, "percentage": 78.41, "elapsed_time": "3:53:59", "remaining_time": "1:04:25"}
|
||||
{"current_steps": 2475, "total_steps": 3150, "loss": 0.1734, "lr": 5.354046170040537e-06, "epoch": 5.5, "percentage": 78.57, "elapsed_time": "3:54:28", "remaining_time": "1:03:56"}
|
||||
{"current_steps": 2480, "total_steps": 3150, "loss": 0.1707, "lr": 5.278808357301186e-06, "epoch": 5.511111111111111, "percentage": 78.73, "elapsed_time": "3:54:59", "remaining_time": "1:03:29"}
|
||||
{"current_steps": 2485, "total_steps": 3150, "loss": 0.1756, "lr": 5.204022479048325e-06, "epoch": 5.522222222222222, "percentage": 78.89, "elapsed_time": "3:55:25", "remaining_time": "1:03:00"}
|
||||
{"current_steps": 2490, "total_steps": 3150, "loss": 0.1748, "lr": 5.129690831177425e-06, "epoch": 5.533333333333333, "percentage": 79.05, "elapsed_time": "3:55:51", "remaining_time": "1:02:31"}
|
||||
{"current_steps": 2495, "total_steps": 3150, "loss": 0.1791, "lr": 5.055815695639303e-06, "epoch": 5.544444444444444, "percentage": 79.21, "elapsed_time": "3:56:18", "remaining_time": "1:02:02"}
|
||||
{"current_steps": 2500, "total_steps": 3150, "loss": 0.1607, "lr": 4.982399340370017e-06, "epoch": 5.555555555555555, "percentage": 79.37, "elapsed_time": "3:56:46", "remaining_time": "1:01:33"}
|
||||
{"current_steps": 2505, "total_steps": 3150, "loss": 0.1647, "lr": 4.909444019221274e-06, "epoch": 5.566666666666666, "percentage": 79.52, "elapsed_time": "3:57:15", "remaining_time": "1:01:05"}
|
||||
{"current_steps": 2510, "total_steps": 3150, "loss": 0.1613, "lr": 4.836951971891215e-06, "epoch": 5.5777777777777775, "percentage": 79.68, "elapsed_time": "3:57:42", "remaining_time": "1:00:36"}
|
||||
{"current_steps": 2515, "total_steps": 3150, "loss": 0.1777, "lr": 4.764925423855669e-06, "epoch": 5.588888888888889, "percentage": 79.84, "elapsed_time": "3:58:10", "remaining_time": "1:00:08"}
|
||||
{"current_steps": 2520, "total_steps": 3150, "loss": 0.1817, "lr": 4.693366586299824e-06, "epoch": 5.6, "percentage": 80.0, "elapsed_time": "3:58:34", "remaining_time": "0:59:38"}
|
||||
{"current_steps": 2525, "total_steps": 3150, "loss": 0.1782, "lr": 4.622277656050369e-06, "epoch": 5.611111111111111, "percentage": 80.16, "elapsed_time": "3:59:03", "remaining_time": "0:59:10"}
|
||||
{"current_steps": 2530, "total_steps": 3150, "loss": 0.1786, "lr": 4.551660815508012e-06, "epoch": 5.622222222222222, "percentage": 80.32, "elapsed_time": "3:59:33", "remaining_time": "0:58:42"}
|
||||
{"current_steps": 2535, "total_steps": 3150, "loss": 0.1732, "lr": 4.481518232580515e-06, "epoch": 5.633333333333333, "percentage": 80.48, "elapsed_time": "3:59:58", "remaining_time": "0:58:13"}
|
||||
{"current_steps": 2540, "total_steps": 3150, "loss": 0.182, "lr": 4.411852060616115e-06, "epoch": 5.644444444444445, "percentage": 80.63, "elapsed_time": "4:00:28", "remaining_time": "0:57:44"}
|
||||
{"current_steps": 2545, "total_steps": 3150, "loss": 0.1792, "lr": 4.342664438337447e-06, "epoch": 5.655555555555556, "percentage": 80.79, "elapsed_time": "4:00:56", "remaining_time": "0:57:16"}
|
||||
{"current_steps": 2550, "total_steps": 3150, "loss": 0.1726, "lr": 4.273957489775862e-06, "epoch": 5.666666666666667, "percentage": 80.95, "elapsed_time": "4:01:25", "remaining_time": "0:56:48"}
|
||||
{"current_steps": 2555, "total_steps": 3150, "loss": 0.1761, "lr": 4.205733324206216e-06, "epoch": 5.677777777777778, "percentage": 81.11, "elapsed_time": "4:01:51", "remaining_time": "0:56:19"}
|
||||
{"current_steps": 2560, "total_steps": 3150, "loss": 0.1731, "lr": 4.137994036082138e-06, "epoch": 5.688888888888889, "percentage": 81.27, "elapsed_time": "4:02:19", "remaining_time": "0:55:50"}
|
||||
{"current_steps": 2565, "total_steps": 3150, "loss": 0.1744, "lr": 4.070741704971726e-06, "epoch": 5.7, "percentage": 81.43, "elapsed_time": "4:02:48", "remaining_time": "0:55:22"}
|
||||
{"current_steps": 2570, "total_steps": 3150, "loss": 0.1849, "lr": 4.003978395493682e-06, "epoch": 5.711111111111111, "percentage": 81.59, "elapsed_time": "4:03:18", "remaining_time": "0:54:54"}
|
||||
{"current_steps": 2575, "total_steps": 3150, "loss": 0.1776, "lr": 3.937706157253971e-06, "epoch": 5.722222222222222, "percentage": 81.75, "elapsed_time": "4:03:47", "remaining_time": "0:54:26"}
|
||||
{"current_steps": 2580, "total_steps": 3150, "loss": 0.1722, "lr": 3.871927024782838e-06, "epoch": 5.733333333333333, "percentage": 81.9, "elapsed_time": "4:04:14", "remaining_time": "0:53:57"}
|
||||
{"current_steps": 2585, "total_steps": 3150, "loss": 0.1705, "lr": 3.80664301747242e-06, "epoch": 5.7444444444444445, "percentage": 82.06, "elapsed_time": "4:04:46", "remaining_time": "0:53:30"}
|
||||
{"current_steps": 2590, "total_steps": 3150, "loss": 0.1747, "lr": 3.741856139514706e-06, "epoch": 5.7555555555555555, "percentage": 82.22, "elapsed_time": "4:05:13", "remaining_time": "0:53:01"}
|
||||
{"current_steps": 2595, "total_steps": 3150, "loss": 0.1621, "lr": 3.677568379840011e-06, "epoch": 5.766666666666667, "percentage": 82.38, "elapsed_time": "4:05:39", "remaining_time": "0:52:32"}
|
||||
{"current_steps": 2600, "total_steps": 3150, "loss": 0.1793, "lr": 3.613781712055935e-06, "epoch": 5.777777777777778, "percentage": 82.54, "elapsed_time": "4:06:10", "remaining_time": "0:52:04"}
|
||||
{"current_steps": 2605, "total_steps": 3150, "loss": 0.1806, "lr": 3.5504980943867538e-06, "epoch": 5.788888888888889, "percentage": 82.7, "elapsed_time": "4:06:33", "remaining_time": "0:51:35"}
|
||||
{"current_steps": 2610, "total_steps": 3150, "loss": 0.1811, "lr": 3.487719469613331e-06, "epoch": 5.8, "percentage": 82.86, "elapsed_time": "4:06:59", "remaining_time": "0:51:06"}
|
||||
{"current_steps": 2615, "total_steps": 3150, "loss": 0.1714, "lr": 3.4254477650134367e-06, "epoch": 5.811111111111111, "percentage": 83.02, "elapsed_time": "4:07:24", "remaining_time": "0:50:37"}
|
||||
{"current_steps": 2620, "total_steps": 3150, "loss": 0.17, "lr": 3.3636848923026257e-06, "epoch": 5.822222222222222, "percentage": 83.17, "elapsed_time": "4:07:50", "remaining_time": "0:50:08"}
|
||||
{"current_steps": 2625, "total_steps": 3150, "loss": 0.1702, "lr": 3.30243274757549e-06, "epoch": 5.833333333333333, "percentage": 83.33, "elapsed_time": "4:08:21", "remaining_time": "0:49:40"}
|
||||
{"current_steps": 2630, "total_steps": 3150, "loss": 0.1661, "lr": 3.2416932112475207e-06, "epoch": 5.844444444444444, "percentage": 83.49, "elapsed_time": "4:08:49", "remaining_time": "0:49:11"}
|
||||
{"current_steps": 2635, "total_steps": 3150, "loss": 0.1538, "lr": 3.1814681479973154e-06, "epoch": 5.855555555555555, "percentage": 83.65, "elapsed_time": "4:09:17", "remaining_time": "0:48:43"}
|
||||
{"current_steps": 2640, "total_steps": 3150, "loss": 0.1756, "lr": 3.121759406709386e-06, "epoch": 5.866666666666667, "percentage": 83.81, "elapsed_time": "4:09:45", "remaining_time": "0:48:15"}
|
||||
{"current_steps": 2645, "total_steps": 3150, "loss": 0.1785, "lr": 3.062568820417353e-06, "epoch": 5.877777777777778, "percentage": 83.97, "elapsed_time": "4:10:11", "remaining_time": "0:47:46"}
|
||||
{"current_steps": 2650, "total_steps": 3150, "loss": 0.1781, "lr": 3.003898206247704e-06, "epoch": 5.888888888888889, "percentage": 84.13, "elapsed_time": "4:10:37", "remaining_time": "0:47:17"}
|
||||
{"current_steps": 2655, "total_steps": 3150, "loss": 0.1633, "lr": 2.9457493653639856e-06, "epoch": 5.9, "percentage": 84.29, "elapsed_time": "4:11:09", "remaining_time": "0:46:49"}
|
||||
{"current_steps": 2660, "total_steps": 3150, "loss": 0.1798, "lr": 2.8881240829115453e-06, "epoch": 5.911111111111111, "percentage": 84.44, "elapsed_time": "4:11:33", "remaining_time": "0:46:20"}
|
||||
{"current_steps": 2665, "total_steps": 3150, "loss": 0.1798, "lr": 2.8310241279626784e-06, "epoch": 5.9222222222222225, "percentage": 84.6, "elapsed_time": "4:12:04", "remaining_time": "0:45:52"}
|
||||
{"current_steps": 2670, "total_steps": 3150, "loss": 0.1904, "lr": 2.774451253462356e-06, "epoch": 5.933333333333334, "percentage": 84.76, "elapsed_time": "4:12:32", "remaining_time": "0:45:24"}
|
||||
{"current_steps": 2675, "total_steps": 3150, "loss": 0.1661, "lr": 2.718407196174391e-06, "epoch": 5.944444444444445, "percentage": 84.92, "elapsed_time": "4:13:03", "remaining_time": "0:44:56"}
|
||||
{"current_steps": 2680, "total_steps": 3150, "loss": 0.1681, "lr": 2.6628936766281375e-06, "epoch": 5.955555555555556, "percentage": 85.08, "elapsed_time": "4:13:27", "remaining_time": "0:44:27"}
|
||||
{"current_steps": 2685, "total_steps": 3150, "loss": 0.1678, "lr": 2.607912399065646e-06, "epoch": 5.966666666666667, "percentage": 85.24, "elapsed_time": "4:13:58", "remaining_time": "0:43:58"}
|
||||
{"current_steps": 2690, "total_steps": 3150, "loss": 0.1679, "lr": 2.5534650513893787e-06, "epoch": 5.977777777777778, "percentage": 85.4, "elapsed_time": "4:14:25", "remaining_time": "0:43:30"}
|
||||
{"current_steps": 2695, "total_steps": 3150, "loss": 0.1566, "lr": 2.4995533051103448e-06, "epoch": 5.988888888888889, "percentage": 85.56, "elapsed_time": "4:14:54", "remaining_time": "0:43:02"}
|
||||
{"current_steps": 2700, "total_steps": 3150, "loss": 0.1719, "lr": 2.446178815296838e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "4:15:21", "remaining_time": "0:42:33"}
|
||||
{"current_steps": 2705, "total_steps": 3150, "loss": 0.1704, "lr": 2.393343220523581e-06, "epoch": 6.011111111111111, "percentage": 85.87, "elapsed_time": "4:15:53", "remaining_time": "0:42:05"}
|
||||
{"current_steps": 2710, "total_steps": 3150, "loss": 0.1615, "lr": 2.3410481428214602e-06, "epoch": 6.022222222222222, "percentage": 86.03, "elapsed_time": "4:16:18", "remaining_time": "0:41:36"}
|
||||
{"current_steps": 2715, "total_steps": 3150, "loss": 0.1599, "lr": 2.2892951876276983e-06, "epoch": 6.033333333333333, "percentage": 86.19, "elapsed_time": "4:16:45", "remaining_time": "0:41:08"}
|
||||
{"current_steps": 2720, "total_steps": 3150, "loss": 0.168, "lr": 2.2380859437365855e-06, "epoch": 6.044444444444444, "percentage": 86.35, "elapsed_time": "4:17:12", "remaining_time": "0:40:39"}
|
||||
{"current_steps": 2725, "total_steps": 3150, "loss": 0.1584, "lr": 2.187421983250695e-06, "epoch": 6.055555555555555, "percentage": 86.51, "elapsed_time": "4:17:39", "remaining_time": "0:40:11"}
|
||||
{"current_steps": 2730, "total_steps": 3150, "loss": 0.156, "lr": 2.1373048615326385e-06, "epoch": 6.066666666666666, "percentage": 86.67, "elapsed_time": "4:18:07", "remaining_time": "0:39:42"}
|
||||
{"current_steps": 2735, "total_steps": 3150, "loss": 0.1625, "lr": 2.0877361171572953e-06, "epoch": 6.0777777777777775, "percentage": 86.83, "elapsed_time": "4:18:37", "remaining_time": "0:39:14"}
|
||||
{"current_steps": 2740, "total_steps": 3150, "loss": 0.1607, "lr": 2.0387172718645853e-06, "epoch": 6.088888888888889, "percentage": 86.98, "elapsed_time": "4:19:05", "remaining_time": "0:38:46"}
|
||||
{"current_steps": 2745, "total_steps": 3150, "loss": 0.153, "lr": 1.990249830512756e-06, "epoch": 6.1, "percentage": 87.14, "elapsed_time": "4:19:34", "remaining_time": "0:38:17"}
|
||||
{"current_steps": 2750, "total_steps": 3150, "loss": 0.1524, "lr": 1.942335281032188e-06, "epoch": 6.111111111111111, "percentage": 87.3, "elapsed_time": "4:20:05", "remaining_time": "0:37:49"}
|
||||
{"current_steps": 2755, "total_steps": 3150, "loss": 0.1562, "lr": 1.8949750943797051e-06, "epoch": 6.122222222222222, "percentage": 87.46, "elapsed_time": "4:20:33", "remaining_time": "0:37:21"}
|
||||
{"current_steps": 2760, "total_steps": 3150, "loss": 0.1582, "lr": 1.8481707244934232e-06, "epoch": 6.133333333333334, "percentage": 87.62, "elapsed_time": "4:21:00", "remaining_time": "0:36:52"}
|
||||
{"current_steps": 2765, "total_steps": 3150, "loss": 0.1642, "lr": 1.8019236082481063e-06, "epoch": 6.144444444444445, "percentage": 87.78, "elapsed_time": "4:21:29", "remaining_time": "0:36:24"}
|
||||
{"current_steps": 2770, "total_steps": 3150, "loss": 0.1602, "lr": 1.7562351654110776e-06, "epoch": 6.155555555555556, "percentage": 87.94, "elapsed_time": "4:21:57", "remaining_time": "0:35:56"}
|
||||
{"current_steps": 2775, "total_steps": 3150, "loss": 0.1553, "lr": 1.711106798598603e-06, "epoch": 6.166666666666667, "percentage": 88.1, "elapsed_time": "4:22:28", "remaining_time": "0:35:28"}
|
||||
{"current_steps": 2780, "total_steps": 3150, "loss": 0.1843, "lr": 1.6665398932328615e-06, "epoch": 6.177777777777778, "percentage": 88.25, "elapsed_time": "4:23:01", "remaining_time": "0:35:00"}
|
||||
{"current_steps": 2785, "total_steps": 3150, "loss": 0.1653, "lr": 1.6225358174993866e-06, "epoch": 6.188888888888889, "percentage": 88.41, "elapsed_time": "4:23:31", "remaining_time": "0:34:32"}
|
||||
{"current_steps": 2790, "total_steps": 3150, "loss": 0.1695, "lr": 1.5790959223050761e-06, "epoch": 6.2, "percentage": 88.57, "elapsed_time": "4:23:55", "remaining_time": "0:34:03"}
|
||||
{"current_steps": 2795, "total_steps": 3150, "loss": 0.1601, "lr": 1.5362215412367198e-06, "epoch": 6.211111111111111, "percentage": 88.73, "elapsed_time": "4:24:20", "remaining_time": "0:33:34"}
|
||||
{"current_steps": 2800, "total_steps": 3150, "loss": 0.1853, "lr": 1.493913990520066e-06, "epoch": 6.222222222222222, "percentage": 88.89, "elapsed_time": "4:24:50", "remaining_time": "0:33:06"}
|
||||
{"current_steps": 2805, "total_steps": 3150, "loss": 0.1676, "lr": 1.4521745689793942e-06, "epoch": 6.233333333333333, "percentage": 89.05, "elapsed_time": "4:25:17", "remaining_time": "0:32:37"}
|
||||
{"current_steps": 2810, "total_steps": 3150, "loss": 0.1707, "lr": 1.4110045579976638e-06, "epoch": 6.2444444444444445, "percentage": 89.21, "elapsed_time": "4:25:45", "remaining_time": "0:32:09"}
|
||||
{"current_steps": 2815, "total_steps": 3150, "loss": 0.1773, "lr": 1.3704052214771513e-06, "epoch": 6.2555555555555555, "percentage": 89.37, "elapsed_time": "4:26:10", "remaining_time": "0:31:40"}
|
||||
{"current_steps": 2820, "total_steps": 3150, "loss": 0.171, "lr": 1.3303778058006844e-06, "epoch": 6.266666666666667, "percentage": 89.52, "elapsed_time": "4:26:37", "remaining_time": "0:31:12"}
|
||||
{"current_steps": 2825, "total_steps": 3150, "loss": 0.1814, "lr": 1.2909235397933429e-06, "epoch": 6.277777777777778, "percentage": 89.68, "elapsed_time": "4:27:11", "remaining_time": "0:30:44"}
|
||||
{"current_steps": 2830, "total_steps": 3150, "loss": 0.1513, "lr": 1.2520436346847498e-06, "epoch": 6.288888888888889, "percentage": 89.84, "elapsed_time": "4:27:42", "remaining_time": "0:30:16"}
|
||||
{"current_steps": 2835, "total_steps": 3150, "loss": 0.158, "lr": 1.213739284071891e-06, "epoch": 6.3, "percentage": 90.0, "elapsed_time": "4:28:12", "remaining_time": "0:29:48"}
|
||||
{"current_steps": 2840, "total_steps": 3150, "loss": 0.1702, "lr": 1.176011663882466e-06, "epoch": 6.311111111111111, "percentage": 90.16, "elapsed_time": "4:28:35", "remaining_time": "0:29:19"}
|
||||
{"current_steps": 2845, "total_steps": 3150, "loss": 0.1691, "lr": 1.1388619323387884e-06, "epoch": 6.322222222222222, "percentage": 90.32, "elapsed_time": "4:29:03", "remaining_time": "0:28:50"}
|
||||
{"current_steps": 2850, "total_steps": 3150, "loss": 0.1712, "lr": 1.1022912299222387e-06, "epoch": 6.333333333333333, "percentage": 90.48, "elapsed_time": "4:29:33", "remaining_time": "0:28:22"}
|
||||
{"current_steps": 2855, "total_steps": 3150, "loss": 0.1607, "lr": 1.0663006793382214e-06, "epoch": 6.344444444444444, "percentage": 90.63, "elapsed_time": "4:30:02", "remaining_time": "0:27:54"}
|
||||
{"current_steps": 2860, "total_steps": 3150, "loss": 0.1641, "lr": 1.0308913854817425e-06, "epoch": 6.355555555555555, "percentage": 90.79, "elapsed_time": "4:30:34", "remaining_time": "0:27:26"}
|
||||
{"current_steps": 2865, "total_steps": 3150, "loss": 0.1729, "lr": 9.960644354034544e-07, "epoch": 6.366666666666666, "percentage": 90.95, "elapsed_time": "4:31:01", "remaining_time": "0:26:57"}
|
||||
{"current_steps": 2870, "total_steps": 3150, "loss": 0.168, "lr": 9.618208982763045e-07, "epoch": 6.377777777777778, "percentage": 91.11, "elapsed_time": "4:31:28", "remaining_time": "0:26:29"}
|
||||
{"current_steps": 2875, "total_steps": 3150, "loss": 0.1904, "lr": 9.281618253626967e-07, "epoch": 6.388888888888889, "percentage": 91.27, "elapsed_time": "4:31:55", "remaining_time": "0:26:00"}
|
||||
{"current_steps": 2880, "total_steps": 3150, "loss": 0.157, "lr": 8.950882499822322e-07, "epoch": 6.4, "percentage": 91.43, "elapsed_time": "4:32:22", "remaining_time": "0:25:32"}
|
||||
{"current_steps": 2885, "total_steps": 3150, "loss": 0.1604, "lr": 8.626011874799723e-07, "epoch": 6.411111111111111, "percentage": 91.59, "elapsed_time": "4:32:48", "remaining_time": "0:25:03"}
|
||||
{"current_steps": 2890, "total_steps": 3150, "loss": 0.1563, "lr": 8.307016351952857e-07, "epoch": 6.4222222222222225, "percentage": 91.75, "elapsed_time": "4:33:13", "remaining_time": "0:24:34"}
|
||||
{"current_steps": 2895, "total_steps": 3150, "loss": 0.1768, "lr": 7.993905724312156e-07, "epoch": 6.433333333333334, "percentage": 91.9, "elapsed_time": "4:33:39", "remaining_time": "0:24:06"}
|
||||
{"current_steps": 2900, "total_steps": 3150, "loss": 0.1773, "lr": 7.686689604244191e-07, "epoch": 6.444444444444445, "percentage": 92.06, "elapsed_time": "4:34:07", "remaining_time": "0:23:37"}
|
||||
{"current_steps": 2905, "total_steps": 3150, "loss": 0.1605, "lr": 7.385377423156592e-07, "epoch": 6.455555555555556, "percentage": 92.22, "elapsed_time": "4:34:34", "remaining_time": "0:23:09"}
|
||||
{"current_steps": 2910, "total_steps": 3150, "loss": 0.1654, "lr": 7.0899784312086e-07, "epoch": 6.466666666666667, "percentage": 92.38, "elapsed_time": "4:35:03", "remaining_time": "0:22:41"}
|
||||
{"current_steps": 2915, "total_steps": 3150, "loss": 0.1767, "lr": 6.800501697026817e-07, "epoch": 6.477777777777778, "percentage": 92.54, "elapsed_time": "4:35:33", "remaining_time": "0:22:12"}
|
||||
{"current_steps": 2920, "total_steps": 3150, "loss": 0.169, "lr": 6.516956107427241e-07, "epoch": 6.488888888888889, "percentage": 92.7, "elapsed_time": "4:35:56", "remaining_time": "0:21:44"}
|
||||
{"current_steps": 2925, "total_steps": 3150, "loss": 0.1661, "lr": 6.239350367141872e-07, "epoch": 6.5, "percentage": 92.86, "elapsed_time": "4:36:24", "remaining_time": "0:21:15"}
|
||||
{"current_steps": 2930, "total_steps": 3150, "loss": 0.1734, "lr": 5.967692998552088e-07, "epoch": 6.511111111111111, "percentage": 93.02, "elapsed_time": "4:36:51", "remaining_time": "0:20:47"}
|
||||
{"current_steps": 2935, "total_steps": 3150, "loss": 0.1708, "lr": 5.701992341426499e-07, "epoch": 6.522222222222222, "percentage": 93.17, "elapsed_time": "4:37:17", "remaining_time": "0:20:18"}
|
||||
{"current_steps": 2940, "total_steps": 3150, "loss": 0.1612, "lr": 5.442256552665326e-07, "epoch": 6.533333333333333, "percentage": 93.33, "elapsed_time": "4:37:44", "remaining_time": "0:19:50"}
|
||||
{"current_steps": 2945, "total_steps": 3150, "loss": 0.15, "lr": 5.188493606049672e-07, "epoch": 6.544444444444444, "percentage": 93.49, "elapsed_time": "4:38:10", "remaining_time": "0:19:21"}
|
||||
{"current_steps": 2950, "total_steps": 3150, "loss": 0.1615, "lr": 4.940711291996891e-07, "epoch": 6.555555555555555, "percentage": 93.65, "elapsed_time": "4:38:39", "remaining_time": "0:18:53"}
|
||||
{"current_steps": 2955, "total_steps": 3150, "loss": 0.1593, "lr": 4.698917217321408e-07, "epoch": 6.566666666666666, "percentage": 93.81, "elapsed_time": "4:39:05", "remaining_time": "0:18:25"}
|
||||
{"current_steps": 2960, "total_steps": 3150, "loss": 0.1577, "lr": 4.4631188050011654e-07, "epoch": 6.5777777777777775, "percentage": 93.97, "elapsed_time": "4:39:35", "remaining_time": "0:17:56"}
|
||||
{"current_steps": 2965, "total_steps": 3150, "loss": 0.163, "lr": 4.2333232939498094e-07, "epoch": 6.588888888888889, "percentage": 94.13, "elapsed_time": "4:40:04", "remaining_time": "0:17:28"}
|
||||
{"current_steps": 2970, "total_steps": 3150, "loss": 0.1624, "lr": 4.009537738794289e-07, "epoch": 6.6, "percentage": 94.29, "elapsed_time": "4:40:26", "remaining_time": "0:16:59"}
|
||||
{"current_steps": 2975, "total_steps": 3150, "loss": 0.1744, "lr": 3.791769009658497e-07, "epoch": 6.611111111111111, "percentage": 94.44, "elapsed_time": "4:40:55", "remaining_time": "0:16:31"}
|
||||
{"current_steps": 2980, "total_steps": 3150, "loss": 0.1696, "lr": 3.5800237919522363e-07, "epoch": 6.622222222222222, "percentage": 94.6, "elapsed_time": "4:41:19", "remaining_time": "0:16:02"}
|
||||
{"current_steps": 2985, "total_steps": 3150, "loss": 0.1768, "lr": 3.3743085861659643e-07, "epoch": 6.633333333333333, "percentage": 94.76, "elapsed_time": "4:41:49", "remaining_time": "0:15:34"}
|
||||
{"current_steps": 2990, "total_steps": 3150, "loss": 0.164, "lr": 3.1746297076713504e-07, "epoch": 6.644444444444445, "percentage": 94.92, "elapsed_time": "4:42:19", "remaining_time": "0:15:06"}
|
||||
{"current_steps": 2995, "total_steps": 3150, "loss": 0.1715, "lr": 2.9809932865271893e-07, "epoch": 6.655555555555556, "percentage": 95.08, "elapsed_time": "4:42:49", "remaining_time": "0:14:38"}
|
||||
{"current_steps": 3000, "total_steps": 3150, "loss": 0.1637, "lr": 2.793405267291505e-07, "epoch": 6.666666666666667, "percentage": 95.24, "elapsed_time": "4:43:21", "remaining_time": "0:14:10"}
|
||||
{"current_steps": 3005, "total_steps": 3150, "loss": 0.168, "lr": 2.6118714088386954e-07, "epoch": 6.677777777777778, "percentage": 95.4, "elapsed_time": "4:43:57", "remaining_time": "0:13:42"}
|
||||
{"current_steps": 3010, "total_steps": 3150, "loss": 0.166, "lr": 2.436397284183123e-07, "epoch": 6.688888888888889, "percentage": 95.56, "elapsed_time": "4:44:28", "remaining_time": "0:13:13"}
|
||||
{"current_steps": 3015, "total_steps": 3150, "loss": 0.164, "lr": 2.2669882803076916e-07, "epoch": 6.7, "percentage": 95.71, "elapsed_time": "4:44:57", "remaining_time": "0:12:45"}
|
||||
{"current_steps": 3020, "total_steps": 3150, "loss": 0.158, "lr": 2.1036495979986692e-07, "epoch": 6.711111111111111, "percentage": 95.87, "elapsed_time": "4:45:27", "remaining_time": "0:12:17"}
|
||||
{"current_steps": 3025, "total_steps": 3150, "loss": 0.1565, "lr": 1.9463862516859277e-07, "epoch": 6.722222222222222, "percentage": 96.03, "elapsed_time": "4:45:58", "remaining_time": "0:11:49"}
|
||||
{"current_steps": 3030, "total_steps": 3150, "loss": 0.165, "lr": 1.7952030692891086e-07, "epoch": 6.733333333333333, "percentage": 96.19, "elapsed_time": "4:46:29", "remaining_time": "0:11:20"}
|
||||
{"current_steps": 3035, "total_steps": 3150, "loss": 0.1747, "lr": 1.6501046920692986e-07, "epoch": 6.7444444444444445, "percentage": 96.35, "elapsed_time": "4:46:58", "remaining_time": "0:10:52"}
|
||||
{"current_steps": 3040, "total_steps": 3150, "loss": 0.1509, "lr": 1.511095574486543e-07, "epoch": 6.7555555555555555, "percentage": 96.51, "elapsed_time": "4:47:28", "remaining_time": "0:10:24"}
|
||||
{"current_steps": 3045, "total_steps": 3150, "loss": 0.1729, "lr": 1.378179984063177e-07, "epoch": 6.766666666666667, "percentage": 96.67, "elapsed_time": "4:47:57", "remaining_time": "0:09:55"}
|
||||
{"current_steps": 3050, "total_steps": 3150, "loss": 0.1819, "lr": 1.2513620012528427e-07, "epoch": 6.777777777777778, "percentage": 96.83, "elapsed_time": "4:48:29", "remaining_time": "0:09:27"}
|
||||
{"current_steps": 3055, "total_steps": 3150, "loss": 0.1764, "lr": 1.1306455193150323e-07, "epoch": 6.788888888888889, "percentage": 96.98, "elapsed_time": "4:48:56", "remaining_time": "0:08:59"}
|
||||
{"current_steps": 3060, "total_steps": 3150, "loss": 0.1801, "lr": 1.0160342441957626e-07, "epoch": 6.8, "percentage": 97.14, "elapsed_time": "4:49:24", "remaining_time": "0:08:30"}
|
||||
{"current_steps": 3065, "total_steps": 3150, "loss": 0.1676, "lr": 9.07531694413688e-08, "epoch": 6.811111111111111, "percentage": 97.3, "elapsed_time": "4:49:53", "remaining_time": "0:08:02"}
|
||||
{"current_steps": 3070, "total_steps": 3150, "loss": 0.1707, "lr": 8.051412009521864e-08, "epoch": 6.822222222222222, "percentage": 97.46, "elapsed_time": "4:50:28", "remaining_time": "0:07:34"}
|
||||
{"current_steps": 3075, "total_steps": 3150, "loss": 0.165, "lr": 7.08865907156997e-08, "epoch": 6.833333333333333, "percentage": 97.62, "elapsed_time": "4:50:58", "remaining_time": "0:07:05"}
|
||||
{"current_steps": 3080, "total_steps": 3150, "loss": 0.1729, "lr": 6.187087686397641e-08, "epoch": 6.844444444444444, "percentage": 97.78, "elapsed_time": "4:51:27", "remaining_time": "0:06:37"}
|
||||
{"current_steps": 3085, "total_steps": 3150, "loss": 0.1649, "lr": 5.3467255318726544e-08, "epoch": 6.855555555555555, "percentage": 97.94, "elapsed_time": "4:51:55", "remaining_time": "0:06:09"}
|
||||
{"current_steps": 3090, "total_steps": 3150, "loss": 0.1566, "lr": 4.567598406765461e-08, "epoch": 6.866666666666667, "percentage": 98.1, "elapsed_time": "4:52:22", "remaining_time": "0:05:40"}
|
||||
{"current_steps": 3095, "total_steps": 3150, "loss": 0.1783, "lr": 3.84973022995605e-08, "epoch": 6.877777777777778, "percentage": 98.25, "elapsed_time": "4:52:47", "remaining_time": "0:05:12"}
|
||||
{"current_steps": 3100, "total_steps": 3150, "loss": 0.1655, "lr": 3.193143039700086e-08, "epoch": 6.888888888888889, "percentage": 98.41, "elapsed_time": "4:53:13", "remaining_time": "0:04:43"}
|
||||
{"current_steps": 3105, "total_steps": 3150, "loss": 0.1659, "lr": 2.597856992952341e-08, "epoch": 6.9, "percentage": 98.57, "elapsed_time": "4:53:41", "remaining_time": "0:04:15"}
|
||||
{"current_steps": 3110, "total_steps": 3150, "loss": 0.1642, "lr": 2.063890364748078e-08, "epoch": 6.911111111111111, "percentage": 98.73, "elapsed_time": "4:54:11", "remaining_time": "0:03:47"}
|
||||
{"current_steps": 3115, "total_steps": 3150, "loss": 0.169, "lr": 1.5912595476414993e-08, "epoch": 6.9222222222222225, "percentage": 98.89, "elapsed_time": "4:54:37", "remaining_time": "0:03:18"}
|
||||
{"current_steps": 3120, "total_steps": 3150, "loss": 0.1611, "lr": 1.1799790512030395e-08, "epoch": 6.933333333333334, "percentage": 99.05, "elapsed_time": "4:55:08", "remaining_time": "0:02:50"}
|
||||
{"current_steps": 3125, "total_steps": 3150, "loss": 0.1635, "lr": 8.300615015734981e-09, "epoch": 6.944444444444445, "percentage": 99.21, "elapsed_time": "4:55:32", "remaining_time": "0:02:21"}
|
||||
{"current_steps": 3130, "total_steps": 3150, "loss": 0.1727, "lr": 5.415176410765721e-09, "epoch": 6.955555555555556, "percentage": 99.37, "elapsed_time": "4:56:01", "remaining_time": "0:01:53"}
|
||||
{"current_steps": 3135, "total_steps": 3150, "loss": 0.1711, "lr": 3.1435632788956448e-09, "epoch": 6.966666666666667, "percentage": 99.52, "elapsed_time": "4:56:24", "remaining_time": "0:01:25"}
|
||||
{"current_steps": 3140, "total_steps": 3150, "loss": 0.1593, "lr": 1.4858453577071275e-09, "epoch": 6.977777777777778, "percentage": 99.68, "elapsed_time": "4:56:51", "remaining_time": "0:00:56"}
|
||||
{"current_steps": 3145, "total_steps": 3150, "loss": 0.1676, "lr": 4.4207353845360234e-10, "epoch": 6.988888888888889, "percentage": 99.84, "elapsed_time": "4:57:18", "remaining_time": "0:00:28"}
|
||||
{"current_steps": 3150, "total_steps": 3150, "loss": 0.1667, "lr": 1.2279864494146865e-11, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "4:57:46", "remaining_time": "0:00:00"}
|
||||
{"current_steps": 3150, "total_steps": 3150, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "4:57:55", "remaining_time": "0:00:00"}
|
||||
6977
trainer_state.json
Normal file
6977
trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:98706dc12c6d5749e8473a8f4cc9c017503195cef4076a03da6a8be13508412f
|
||||
size 8593
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 43 KiB |
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user