初始化项目,由ModelHub XC社区提供模型
Model: DCAgent/a1-bugsinpy 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_bugsinpy__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_bugsinpy__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_bugsinpy-v4_10k_glm_4.7_traces_jupiter/snapshots/e66806e73ed8080c8c5a014f15c36968c2256f81_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": 0.005310423151959063,
|
||||
"achieved_tflops_per_gpu_theoretical": 704.6841490672189,
|
||||
"epoch": 7.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.21552443504333496,
|
||||
"mfu_percent": 0.00037529492239993375,
|
||||
"mfu_percent_theoretical": 49.800999934079066,
|
||||
"total_flos": 1717709353779200.0,
|
||||
"train_loss": 0.15650485047922919,
|
||||
"train_runtime": 20216.2486,
|
||||
"train_samples_per_second": 3.333,
|
||||
"train_steps_per_second": 0.208,
|
||||
"valid_targets_mean": 5110.8,
|
||||
"valid_targets_min": 529
|
||||
}
|
||||
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 sha256:22bf8d56dbf9f931651abfe032448f6fbee6649fa3c892d63f802bca3861d33b
|
||||
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 sha256:42e420904723d0768371dd5ab3576d27416f6a98cfc884a3456822c4b1fd8a55
|
||||
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 sha256:6001245735d591ec2195f728db3866591c6bf1279c19227cd26afa6743b19b3b
|
||||
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:cb8314b9ab5b155b56145cce2de10acf66b23c9a3fa903c5cd96b463cc3c0096
|
||||
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": "e66806e73ed8080c8c5a014f15c36968c2256f81_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_bugsinpy-v4_10k_glm_4.7_traces_jupiter/snapshots/e66806e73ed8080c8c5a014f15c36968c2256f81_thinking_preprocessed",
|
||||
"training_type": "SFT",
|
||||
"training_parameters": "https://huggingface.co/DCAgent/a1-bugsinpy/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
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
||||
size 11422654
|
||||
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": 0.005310423151959063,
|
||||
"achieved_tflops_per_gpu_theoretical": 704.6841490672189,
|
||||
"epoch": 7.0,
|
||||
"loss_nan_ranks": 0,
|
||||
"loss_rank_avg": 0.21552443504333496,
|
||||
"mfu_percent": 0.00037529492239993375,
|
||||
"mfu_percent_theoretical": 49.800999934079066,
|
||||
"total_flos": 1717709353779200.0,
|
||||
"train_loss": 0.15650485047922919,
|
||||
"train_runtime": 20216.2486,
|
||||
"train_samples_per_second": 3.333,
|
||||
"train_steps_per_second": 0.208,
|
||||
"valid_targets_mean": 5110.8,
|
||||
"valid_targets_min": 529
|
||||
}
|
||||
903
trainer_log.jsonl
Normal file
903
trainer_log.jsonl
Normal file
@@ -0,0 +1,903 @@
|
||||
{"current_steps": 5, "total_steps": 4214, "loss": 0.881, "lr": 3.791469194312797e-07, "epoch": 0.008305647840531562, "percentage": 0.12, "elapsed_time": "0:00:39", "remaining_time": "9:19:50"}
|
||||
{"current_steps": 10, "total_steps": 4214, "loss": 0.8879, "lr": 8.530805687203792e-07, "epoch": 0.016611295681063124, "percentage": 0.24, "elapsed_time": "0:01:20", "remaining_time": "9:20:51"}
|
||||
{"current_steps": 15, "total_steps": 4214, "loss": 0.864, "lr": 1.3270142180094788e-06, "epoch": 0.024916943521594685, "percentage": 0.36, "elapsed_time": "0:01:54", "remaining_time": "8:53:47"}
|
||||
{"current_steps": 20, "total_steps": 4214, "loss": 0.823, "lr": 1.8009478672985784e-06, "epoch": 0.03322259136212625, "percentage": 0.47, "elapsed_time": "0:02:34", "remaining_time": "9:00:40"}
|
||||
{"current_steps": 25, "total_steps": 4214, "loss": 0.7812, "lr": 2.2748815165876777e-06, "epoch": 0.04152823920265781, "percentage": 0.59, "elapsed_time": "0:03:10", "remaining_time": "8:50:43"}
|
||||
{"current_steps": 30, "total_steps": 4214, "loss": 0.7246, "lr": 2.7488151658767775e-06, "epoch": 0.04983388704318937, "percentage": 0.71, "elapsed_time": "0:03:49", "remaining_time": "8:52:20"}
|
||||
{"current_steps": 35, "total_steps": 4214, "loss": 0.6784, "lr": 3.222748815165877e-06, "epoch": 0.05813953488372093, "percentage": 0.83, "elapsed_time": "0:04:27", "remaining_time": "8:52:00"}
|
||||
{"current_steps": 40, "total_steps": 4214, "loss": 0.6538, "lr": 3.6966824644549766e-06, "epoch": 0.0664451827242525, "percentage": 0.95, "elapsed_time": "0:05:06", "remaining_time": "8:53:54"}
|
||||
{"current_steps": 45, "total_steps": 4214, "loss": 0.6216, "lr": 4.170616113744076e-06, "epoch": 0.07475083056478406, "percentage": 1.07, "elapsed_time": "0:05:44", "remaining_time": "8:51:33"}
|
||||
{"current_steps": 50, "total_steps": 4214, "loss": 0.6023, "lr": 4.644549763033176e-06, "epoch": 0.08305647840531562, "percentage": 1.19, "elapsed_time": "0:06:24", "remaining_time": "8:53:28"}
|
||||
{"current_steps": 55, "total_steps": 4214, "loss": 0.5834, "lr": 5.118483412322275e-06, "epoch": 0.09136212624584718, "percentage": 1.31, "elapsed_time": "0:07:05", "remaining_time": "8:56:05"}
|
||||
{"current_steps": 60, "total_steps": 4214, "loss": 0.5935, "lr": 5.592417061611375e-06, "epoch": 0.09966777408637874, "percentage": 1.42, "elapsed_time": "0:07:45", "remaining_time": "8:57:23"}
|
||||
{"current_steps": 65, "total_steps": 4214, "loss": 0.4977, "lr": 6.066350710900475e-06, "epoch": 0.1079734219269103, "percentage": 1.54, "elapsed_time": "0:08:21", "remaining_time": "8:53:38"}
|
||||
{"current_steps": 70, "total_steps": 4214, "loss": 0.5678, "lr": 6.5402843601895735e-06, "epoch": 0.11627906976744186, "percentage": 1.66, "elapsed_time": "0:09:01", "remaining_time": "8:53:53"}
|
||||
{"current_steps": 75, "total_steps": 4214, "loss": 0.5062, "lr": 7.014218009478674e-06, "epoch": 0.12458471760797342, "percentage": 1.78, "elapsed_time": "0:09:41", "remaining_time": "8:55:17"}
|
||||
{"current_steps": 80, "total_steps": 4214, "loss": 0.5583, "lr": 7.488151658767773e-06, "epoch": 0.132890365448505, "percentage": 1.9, "elapsed_time": "0:10:15", "remaining_time": "8:49:46"}
|
||||
{"current_steps": 85, "total_steps": 4214, "loss": 0.525, "lr": 7.962085308056872e-06, "epoch": 0.14119601328903655, "percentage": 2.02, "elapsed_time": "0:10:53", "remaining_time": "8:49:18"}
|
||||
{"current_steps": 90, "total_steps": 4214, "loss": 0.4729, "lr": 8.436018957345973e-06, "epoch": 0.14950166112956811, "percentage": 2.14, "elapsed_time": "0:11:33", "remaining_time": "8:49:46"}
|
||||
{"current_steps": 95, "total_steps": 4214, "loss": 0.4614, "lr": 8.909952606635071e-06, "epoch": 0.15780730897009967, "percentage": 2.25, "elapsed_time": "0:12:10", "remaining_time": "8:47:31"}
|
||||
{"current_steps": 100, "total_steps": 4214, "loss": 0.4938, "lr": 9.383886255924171e-06, "epoch": 0.16611295681063123, "percentage": 2.37, "elapsed_time": "0:12:50", "remaining_time": "8:48:18"}
|
||||
{"current_steps": 105, "total_steps": 4214, "loss": 0.4798, "lr": 9.85781990521327e-06, "epoch": 0.1744186046511628, "percentage": 2.49, "elapsed_time": "0:13:31", "remaining_time": "8:49:00"}
|
||||
{"current_steps": 110, "total_steps": 4214, "loss": 0.4378, "lr": 1.033175355450237e-05, "epoch": 0.18272425249169436, "percentage": 2.61, "elapsed_time": "0:14:07", "remaining_time": "8:47:09"}
|
||||
{"current_steps": 115, "total_steps": 4214, "loss": 0.4762, "lr": 1.080568720379147e-05, "epoch": 0.19102990033222592, "percentage": 2.73, "elapsed_time": "0:14:48", "remaining_time": "8:47:50"}
|
||||
{"current_steps": 120, "total_steps": 4214, "loss": 0.4477, "lr": 1.127962085308057e-05, "epoch": 0.19933554817275748, "percentage": 2.85, "elapsed_time": "0:15:26", "remaining_time": "8:46:53"}
|
||||
{"current_steps": 125, "total_steps": 4214, "loss": 0.4323, "lr": 1.1753554502369669e-05, "epoch": 0.20764119601328904, "percentage": 2.97, "elapsed_time": "0:16:03", "remaining_time": "8:45:30"}
|
||||
{"current_steps": 130, "total_steps": 4214, "loss": 0.4285, "lr": 1.2227488151658769e-05, "epoch": 0.2159468438538206, "percentage": 3.08, "elapsed_time": "0:16:38", "remaining_time": "8:42:49"}
|
||||
{"current_steps": 135, "total_steps": 4214, "loss": 0.4342, "lr": 1.270142180094787e-05, "epoch": 0.22425249169435216, "percentage": 3.2, "elapsed_time": "0:17:18", "remaining_time": "8:43:05"}
|
||||
{"current_steps": 140, "total_steps": 4214, "loss": 0.4234, "lr": 1.3175355450236968e-05, "epoch": 0.23255813953488372, "percentage": 3.32, "elapsed_time": "0:17:57", "remaining_time": "8:42:33"}
|
||||
{"current_steps": 145, "total_steps": 4214, "loss": 0.4093, "lr": 1.3649289099526068e-05, "epoch": 0.24086378737541528, "percentage": 3.44, "elapsed_time": "0:18:31", "remaining_time": "8:39:42"}
|
||||
{"current_steps": 150, "total_steps": 4214, "loss": 0.407, "lr": 1.4123222748815166e-05, "epoch": 0.24916943521594684, "percentage": 3.56, "elapsed_time": "0:19:10", "remaining_time": "8:39:41"}
|
||||
{"current_steps": 155, "total_steps": 4214, "loss": 0.4041, "lr": 1.4597156398104267e-05, "epoch": 0.2574750830564784, "percentage": 3.68, "elapsed_time": "0:19:50", "remaining_time": "8:39:32"}
|
||||
{"current_steps": 160, "total_steps": 4214, "loss": 0.3964, "lr": 1.5071090047393367e-05, "epoch": 0.26578073089701, "percentage": 3.8, "elapsed_time": "0:20:25", "remaining_time": "8:37:43"}
|
||||
{"current_steps": 165, "total_steps": 4214, "loss": 0.3991, "lr": 1.5545023696682465e-05, "epoch": 0.27408637873754155, "percentage": 3.92, "elapsed_time": "0:21:04", "remaining_time": "8:37:22"}
|
||||
{"current_steps": 170, "total_steps": 4214, "loss": 0.3569, "lr": 1.6018957345971565e-05, "epoch": 0.2823920265780731, "percentage": 4.03, "elapsed_time": "0:21:41", "remaining_time": "8:36:02"}
|
||||
{"current_steps": 175, "total_steps": 4214, "loss": 0.389, "lr": 1.6492890995260666e-05, "epoch": 0.29069767441860467, "percentage": 4.15, "elapsed_time": "0:22:23", "remaining_time": "8:36:51"}
|
||||
{"current_steps": 180, "total_steps": 4214, "loss": 0.3985, "lr": 1.6966824644549766e-05, "epoch": 0.29900332225913623, "percentage": 4.27, "elapsed_time": "0:23:05", "remaining_time": "8:37:23"}
|
||||
{"current_steps": 185, "total_steps": 4214, "loss": 0.404, "lr": 1.7440758293838863e-05, "epoch": 0.3073089700996678, "percentage": 4.39, "elapsed_time": "0:23:43", "remaining_time": "8:36:31"}
|
||||
{"current_steps": 190, "total_steps": 4214, "loss": 0.3717, "lr": 1.7914691943127963e-05, "epoch": 0.31561461794019935, "percentage": 4.51, "elapsed_time": "0:24:22", "remaining_time": "8:36:16"}
|
||||
{"current_steps": 195, "total_steps": 4214, "loss": 0.3762, "lr": 1.8388625592417063e-05, "epoch": 0.3239202657807309, "percentage": 4.63, "elapsed_time": "0:24:58", "remaining_time": "8:34:40"}
|
||||
{"current_steps": 5, "total_steps": 4214, "loss": 0.8811, "lr": 3.791469194312797e-07, "epoch": 0.008305647840531562, "percentage": 0.12, "elapsed_time": "0:00:39", "remaining_time": "9:12:34"}
|
||||
{"current_steps": 10, "total_steps": 4214, "loss": 0.8878, "lr": 8.530805687203792e-07, "epoch": 0.016611295681063124, "percentage": 0.24, "elapsed_time": "0:01:19", "remaining_time": "9:16:54"}
|
||||
{"current_steps": 15, "total_steps": 4214, "loss": 0.8641, "lr": 1.3270142180094788e-06, "epoch": 0.024916943521594685, "percentage": 0.36, "elapsed_time": "0:01:54", "remaining_time": "8:53:23"}
|
||||
{"current_steps": 20, "total_steps": 4214, "loss": 0.823, "lr": 1.8009478672985784e-06, "epoch": 0.03322259136212625, "percentage": 0.47, "elapsed_time": "0:02:34", "remaining_time": "9:01:16"}
|
||||
{"current_steps": 25, "total_steps": 4214, "loss": 0.7812, "lr": 2.2748815165876777e-06, "epoch": 0.04152823920265781, "percentage": 0.59, "elapsed_time": "0:03:10", "remaining_time": "8:51:28"}
|
||||
{"current_steps": 30, "total_steps": 4214, "loss": 0.7247, "lr": 2.7488151658767775e-06, "epoch": 0.04983388704318937, "percentage": 0.71, "elapsed_time": "0:03:49", "remaining_time": "8:53:29"}
|
||||
{"current_steps": 35, "total_steps": 4214, "loss": 0.6785, "lr": 3.222748815165877e-06, "epoch": 0.05813953488372093, "percentage": 0.83, "elapsed_time": "0:04:28", "remaining_time": "8:53:28"}
|
||||
{"current_steps": 40, "total_steps": 4214, "loss": 0.6538, "lr": 3.6966824644549766e-06, "epoch": 0.0664451827242525, "percentage": 0.95, "elapsed_time": "0:05:07", "remaining_time": "8:55:39"}
|
||||
{"current_steps": 45, "total_steps": 4214, "loss": 0.6216, "lr": 4.170616113744076e-06, "epoch": 0.07475083056478406, "percentage": 1.07, "elapsed_time": "0:05:44", "remaining_time": "8:52:12"}
|
||||
{"current_steps": 50, "total_steps": 4214, "loss": 0.6023, "lr": 4.644549763033176e-06, "epoch": 0.08305647840531562, "percentage": 1.19, "elapsed_time": "0:06:25", "remaining_time": "8:54:23"}
|
||||
{"current_steps": 55, "total_steps": 4214, "loss": 0.5833, "lr": 5.118483412322275e-06, "epoch": 0.09136212624584718, "percentage": 1.31, "elapsed_time": "0:07:06", "remaining_time": "8:56:54"}
|
||||
{"current_steps": 60, "total_steps": 4214, "loss": 0.5933, "lr": 5.592417061611375e-06, "epoch": 0.09966777408637874, "percentage": 1.42, "elapsed_time": "0:07:46", "remaining_time": "8:58:18"}
|
||||
{"current_steps": 65, "total_steps": 4214, "loss": 0.4975, "lr": 6.066350710900475e-06, "epoch": 0.1079734219269103, "percentage": 1.54, "elapsed_time": "0:08:23", "remaining_time": "8:55:17"}
|
||||
{"current_steps": 70, "total_steps": 4214, "loss": 0.5674, "lr": 6.5402843601895735e-06, "epoch": 0.11627906976744186, "percentage": 1.66, "elapsed_time": "0:09:02", "remaining_time": "8:55:30"}
|
||||
{"current_steps": 75, "total_steps": 4214, "loss": 0.5059, "lr": 7.014218009478674e-06, "epoch": 0.12458471760797342, "percentage": 1.78, "elapsed_time": "0:09:44", "remaining_time": "8:57:18"}
|
||||
{"current_steps": 80, "total_steps": 4214, "loss": 0.5583, "lr": 7.488151658767773e-06, "epoch": 0.132890365448505, "percentage": 1.9, "elapsed_time": "0:10:17", "remaining_time": "8:51:49"}
|
||||
{"current_steps": 85, "total_steps": 4214, "loss": 0.5252, "lr": 7.962085308056872e-06, "epoch": 0.14119601328903655, "percentage": 2.02, "elapsed_time": "0:10:56", "remaining_time": "8:51:17"}
|
||||
{"current_steps": 90, "total_steps": 4214, "loss": 0.4731, "lr": 8.436018957345973e-06, "epoch": 0.14950166112956811, "percentage": 2.14, "elapsed_time": "0:11:36", "remaining_time": "8:52:06"}
|
||||
{"current_steps": 95, "total_steps": 4214, "loss": 0.4619, "lr": 8.909952606635071e-06, "epoch": 0.15780730897009967, "percentage": 2.25, "elapsed_time": "0:12:13", "remaining_time": "8:50:02"}
|
||||
{"current_steps": 100, "total_steps": 4214, "loss": 0.4944, "lr": 9.383886255924171e-06, "epoch": 0.16611295681063123, "percentage": 2.37, "elapsed_time": "0:12:54", "remaining_time": "8:51:04"}
|
||||
{"current_steps": 105, "total_steps": 4214, "loss": 0.4805, "lr": 9.85781990521327e-06, "epoch": 0.1744186046511628, "percentage": 2.49, "elapsed_time": "0:13:35", "remaining_time": "8:51:50"}
|
||||
{"current_steps": 110, "total_steps": 4214, "loss": 0.4385, "lr": 1.033175355450237e-05, "epoch": 0.18272425249169436, "percentage": 2.61, "elapsed_time": "0:14:12", "remaining_time": "8:49:53"}
|
||||
{"current_steps": 115, "total_steps": 4214, "loss": 0.4766, "lr": 1.080568720379147e-05, "epoch": 0.19102990033222592, "percentage": 2.73, "elapsed_time": "0:14:53", "remaining_time": "8:50:34"}
|
||||
{"current_steps": 120, "total_steps": 4214, "loss": 0.4478, "lr": 1.127962085308057e-05, "epoch": 0.19933554817275748, "percentage": 2.85, "elapsed_time": "0:15:30", "remaining_time": "8:49:17"}
|
||||
{"current_steps": 125, "total_steps": 4214, "loss": 0.4324, "lr": 1.1753554502369669e-05, "epoch": 0.20764119601328904, "percentage": 2.97, "elapsed_time": "0:16:07", "remaining_time": "8:47:33"}
|
||||
{"current_steps": 130, "total_steps": 4214, "loss": 0.4287, "lr": 1.2227488151658769e-05, "epoch": 0.2159468438538206, "percentage": 3.08, "elapsed_time": "0:16:42", "remaining_time": "8:44:56"}
|
||||
{"current_steps": 135, "total_steps": 4214, "loss": 0.4347, "lr": 1.270142180094787e-05, "epoch": 0.22425249169435216, "percentage": 3.2, "elapsed_time": "0:17:22", "remaining_time": "8:44:52"}
|
||||
{"current_steps": 140, "total_steps": 4214, "loss": 0.4241, "lr": 1.3175355450236968e-05, "epoch": 0.23255813953488372, "percentage": 3.32, "elapsed_time": "0:18:01", "remaining_time": "8:44:40"}
|
||||
{"current_steps": 145, "total_steps": 4214, "loss": 0.4099, "lr": 1.3649289099526068e-05, "epoch": 0.24086378737541528, "percentage": 3.44, "elapsed_time": "0:18:35", "remaining_time": "8:41:50"}
|
||||
{"current_steps": 150, "total_steps": 4214, "loss": 0.4078, "lr": 1.4123222748815166e-05, "epoch": 0.24916943521594684, "percentage": 3.56, "elapsed_time": "0:19:15", "remaining_time": "8:41:39"}
|
||||
{"current_steps": 155, "total_steps": 4214, "loss": 0.4048, "lr": 1.4597156398104267e-05, "epoch": 0.2574750830564784, "percentage": 3.68, "elapsed_time": "0:19:54", "remaining_time": "8:41:14"}
|
||||
{"current_steps": 160, "total_steps": 4214, "loss": 0.3972, "lr": 1.5071090047393367e-05, "epoch": 0.26578073089701, "percentage": 3.8, "elapsed_time": "0:20:30", "remaining_time": "8:39:33"}
|
||||
{"current_steps": 165, "total_steps": 4214, "loss": 0.3999, "lr": 1.5545023696682465e-05, "epoch": 0.27408637873754155, "percentage": 3.92, "elapsed_time": "0:21:09", "remaining_time": "8:39:01"}
|
||||
{"current_steps": 170, "total_steps": 4214, "loss": 0.3574, "lr": 1.6018957345971565e-05, "epoch": 0.2823920265780731, "percentage": 4.03, "elapsed_time": "0:21:46", "remaining_time": "8:37:59"}
|
||||
{"current_steps": 175, "total_steps": 4214, "loss": 0.3895, "lr": 1.6492890995260666e-05, "epoch": 0.29069767441860467, "percentage": 4.15, "elapsed_time": "0:22:28", "remaining_time": "8:38:45"}
|
||||
{"current_steps": 180, "total_steps": 4214, "loss": 0.399, "lr": 1.6966824644549766e-05, "epoch": 0.29900332225913623, "percentage": 4.27, "elapsed_time": "0:23:09", "remaining_time": "8:39:09"}
|
||||
{"current_steps": 185, "total_steps": 4214, "loss": 0.4045, "lr": 1.7440758293838863e-05, "epoch": 0.3073089700996678, "percentage": 4.39, "elapsed_time": "0:23:48", "remaining_time": "8:38:40"}
|
||||
{"current_steps": 190, "total_steps": 4214, "loss": 0.3721, "lr": 1.7914691943127963e-05, "epoch": 0.31561461794019935, "percentage": 4.51, "elapsed_time": "0:24:28", "remaining_time": "8:38:28"}
|
||||
{"current_steps": 195, "total_steps": 4214, "loss": 0.3764, "lr": 1.8388625592417063e-05, "epoch": 0.3239202657807309, "percentage": 4.63, "elapsed_time": "0:25:04", "remaining_time": "8:36:57"}
|
||||
{"current_steps": 200, "total_steps": 4214, "loss": 0.3629, "lr": 1.8862559241706163e-05, "epoch": 0.33222591362126247, "percentage": 4.75, "elapsed_time": "0:25:41", "remaining_time": "8:35:39"}
|
||||
{"current_steps": 205, "total_steps": 4214, "loss": 0.3494, "lr": 1.9336492890995263e-05, "epoch": 0.34053156146179403, "percentage": 4.86, "elapsed_time": "0:26:22", "remaining_time": "8:35:43"}
|
||||
{"current_steps": 210, "total_steps": 4214, "loss": 0.3906, "lr": 1.9810426540284364e-05, "epoch": 0.3488372093023256, "percentage": 4.98, "elapsed_time": "0:27:03", "remaining_time": "8:35:52"}
|
||||
{"current_steps": 215, "total_steps": 4214, "loss": 0.3761, "lr": 2.0284360189573464e-05, "epoch": 0.35714285714285715, "percentage": 5.1, "elapsed_time": "0:27:38", "remaining_time": "8:34:14"}
|
||||
{"current_steps": 220, "total_steps": 4214, "loss": 0.3829, "lr": 2.075829383886256e-05, "epoch": 0.3654485049833887, "percentage": 5.22, "elapsed_time": "0:28:19", "remaining_time": "8:34:09"}
|
||||
{"current_steps": 225, "total_steps": 4214, "loss": 0.3438, "lr": 2.123222748815166e-05, "epoch": 0.37375415282392027, "percentage": 5.34, "elapsed_time": "0:28:54", "remaining_time": "8:32:35"}
|
||||
{"current_steps": 230, "total_steps": 4214, "loss": 0.3626, "lr": 2.170616113744076e-05, "epoch": 0.38205980066445183, "percentage": 5.46, "elapsed_time": "0:29:30", "remaining_time": "8:31:12"}
|
||||
{"current_steps": 235, "total_steps": 4214, "loss": 0.3792, "lr": 2.2180094786729858e-05, "epoch": 0.3903654485049834, "percentage": 5.58, "elapsed_time": "0:30:12", "remaining_time": "8:31:27"}
|
||||
{"current_steps": 240, "total_steps": 4214, "loss": 0.3837, "lr": 2.265402843601896e-05, "epoch": 0.39867109634551495, "percentage": 5.7, "elapsed_time": "0:30:51", "remaining_time": "8:30:51"}
|
||||
{"current_steps": 245, "total_steps": 4214, "loss": 0.3504, "lr": 2.3127962085308058e-05, "epoch": 0.4069767441860465, "percentage": 5.81, "elapsed_time": "0:31:28", "remaining_time": "8:29:56"}
|
||||
{"current_steps": 250, "total_steps": 4214, "loss": 0.3596, "lr": 2.360189573459716e-05, "epoch": 0.4152823920265781, "percentage": 5.93, "elapsed_time": "0:32:06", "remaining_time": "8:29:00"}
|
||||
{"current_steps": 255, "total_steps": 4214, "loss": 0.3568, "lr": 2.407582938388626e-05, "epoch": 0.42358803986710963, "percentage": 6.05, "elapsed_time": "0:32:43", "remaining_time": "8:28:09"}
|
||||
{"current_steps": 260, "total_steps": 4214, "loss": 0.3261, "lr": 2.4549763033175355e-05, "epoch": 0.4318936877076412, "percentage": 6.17, "elapsed_time": "0:33:19", "remaining_time": "8:26:50"}
|
||||
{"current_steps": 265, "total_steps": 4214, "loss": 0.3618, "lr": 2.502369668246446e-05, "epoch": 0.44019933554817275, "percentage": 6.29, "elapsed_time": "0:33:59", "remaining_time": "8:26:26"}
|
||||
{"current_steps": 270, "total_steps": 4214, "loss": 0.3555, "lr": 2.5497630331753556e-05, "epoch": 0.4485049833887043, "percentage": 6.41, "elapsed_time": "0:34:35", "remaining_time": "8:25:11"}
|
||||
{"current_steps": 275, "total_steps": 4214, "loss": 0.3597, "lr": 2.597156398104266e-05, "epoch": 0.4568106312292359, "percentage": 6.53, "elapsed_time": "0:35:16", "remaining_time": "8:25:10"}
|
||||
{"current_steps": 280, "total_steps": 4214, "loss": 0.3431, "lr": 2.6445497630331756e-05, "epoch": 0.46511627906976744, "percentage": 6.64, "elapsed_time": "0:35:48", "remaining_time": "8:23:09"}
|
||||
{"current_steps": 285, "total_steps": 4214, "loss": 0.3382, "lr": 2.6919431279620853e-05, "epoch": 0.473421926910299, "percentage": 6.76, "elapsed_time": "0:36:26", "remaining_time": "8:22:29"}
|
||||
{"current_steps": 290, "total_steps": 4214, "loss": 0.3349, "lr": 2.7393364928909956e-05, "epoch": 0.48172757475083056, "percentage": 6.88, "elapsed_time": "0:36:57", "remaining_time": "8:20:05"}
|
||||
{"current_steps": 295, "total_steps": 4214, "loss": 0.3714, "lr": 2.7867298578199053e-05, "epoch": 0.4900332225913621, "percentage": 7.0, "elapsed_time": "0:37:36", "remaining_time": "8:19:38"}
|
||||
{"current_steps": 300, "total_steps": 4214, "loss": 0.3394, "lr": 2.8341232227488157e-05, "epoch": 0.4983388704318937, "percentage": 7.12, "elapsed_time": "0:38:17", "remaining_time": "8:19:29"}
|
||||
{"current_steps": 305, "total_steps": 4214, "loss": 0.3324, "lr": 2.8815165876777254e-05, "epoch": 0.5066445182724253, "percentage": 7.24, "elapsed_time": "0:38:56", "remaining_time": "8:19:10"}
|
||||
{"current_steps": 310, "total_steps": 4214, "loss": 0.3459, "lr": 2.928909952606635e-05, "epoch": 0.5149501661129569, "percentage": 7.36, "elapsed_time": "0:39:36", "remaining_time": "8:18:48"}
|
||||
{"current_steps": 315, "total_steps": 4214, "loss": 0.3422, "lr": 2.9763033175355454e-05, "epoch": 0.5232558139534884, "percentage": 7.48, "elapsed_time": "0:40:17", "remaining_time": "8:18:49"}
|
||||
{"current_steps": 320, "total_steps": 4214, "loss": 0.3609, "lr": 3.023696682464455e-05, "epoch": 0.53156146179402, "percentage": 7.59, "elapsed_time": "0:40:53", "remaining_time": "8:17:38"}
|
||||
{"current_steps": 325, "total_steps": 4214, "loss": 0.3545, "lr": 3.0710900473933654e-05, "epoch": 0.5398671096345515, "percentage": 7.71, "elapsed_time": "0:41:29", "remaining_time": "8:16:31"}
|
||||
{"current_steps": 330, "total_steps": 4214, "loss": 0.3252, "lr": 3.1184834123222755e-05, "epoch": 0.5481727574750831, "percentage": 7.83, "elapsed_time": "0:42:04", "remaining_time": "8:15:16"}
|
||||
{"current_steps": 335, "total_steps": 4214, "loss": 0.3366, "lr": 3.165876777251185e-05, "epoch": 0.5564784053156147, "percentage": 7.95, "elapsed_time": "0:42:39", "remaining_time": "8:14:00"}
|
||||
{"current_steps": 340, "total_steps": 4214, "loss": 0.3175, "lr": 3.213270142180095e-05, "epoch": 0.5647840531561462, "percentage": 8.07, "elapsed_time": "0:43:18", "remaining_time": "8:13:32"}
|
||||
{"current_steps": 345, "total_steps": 4214, "loss": 0.3065, "lr": 3.260663507109005e-05, "epoch": 0.5730897009966778, "percentage": 8.19, "elapsed_time": "0:43:57", "remaining_time": "8:12:54"}
|
||||
{"current_steps": 350, "total_steps": 4214, "loss": 0.3191, "lr": 3.308056872037915e-05, "epoch": 0.5813953488372093, "percentage": 8.31, "elapsed_time": "0:44:33", "remaining_time": "8:11:51"}
|
||||
{"current_steps": 355, "total_steps": 4214, "loss": 0.3192, "lr": 3.355450236966825e-05, "epoch": 0.5897009966777409, "percentage": 8.42, "elapsed_time": "0:45:11", "remaining_time": "8:11:11"}
|
||||
{"current_steps": 360, "total_steps": 4214, "loss": 0.3299, "lr": 3.402843601895735e-05, "epoch": 0.5980066445182725, "percentage": 8.54, "elapsed_time": "0:45:48", "remaining_time": "8:10:24"}
|
||||
{"current_steps": 365, "total_steps": 4214, "loss": 0.3199, "lr": 3.450236966824645e-05, "epoch": 0.606312292358804, "percentage": 8.66, "elapsed_time": "0:46:27", "remaining_time": "8:09:54"}
|
||||
{"current_steps": 370, "total_steps": 4214, "loss": 0.3269, "lr": 3.497630331753555e-05, "epoch": 0.6146179401993356, "percentage": 8.78, "elapsed_time": "0:46:57", "remaining_time": "8:07:47"}
|
||||
{"current_steps": 375, "total_steps": 4214, "loss": 0.335, "lr": 3.545023696682465e-05, "epoch": 0.6229235880398671, "percentage": 8.9, "elapsed_time": "0:47:34", "remaining_time": "8:07:01"}
|
||||
{"current_steps": 380, "total_steps": 4214, "loss": 0.3737, "lr": 3.592417061611375e-05, "epoch": 0.6312292358803987, "percentage": 9.02, "elapsed_time": "0:48:14", "remaining_time": "8:06:43"}
|
||||
{"current_steps": 385, "total_steps": 4214, "loss": 0.3323, "lr": 3.639810426540284e-05, "epoch": 0.6395348837209303, "percentage": 9.14, "elapsed_time": "0:48:57", "remaining_time": "8:06:50"}
|
||||
{"current_steps": 390, "total_steps": 4214, "loss": 0.3433, "lr": 3.687203791469195e-05, "epoch": 0.6478405315614618, "percentage": 9.25, "elapsed_time": "0:49:32", "remaining_time": "8:05:44"}
|
||||
{"current_steps": 395, "total_steps": 4214, "loss": 0.3154, "lr": 3.7345971563981044e-05, "epoch": 0.6561461794019934, "percentage": 9.37, "elapsed_time": "0:50:12", "remaining_time": "8:05:22"}
|
||||
{"current_steps": 400, "total_steps": 4214, "loss": 0.3271, "lr": 3.781990521327015e-05, "epoch": 0.6644518272425249, "percentage": 9.49, "elapsed_time": "0:50:57", "remaining_time": "8:05:53"}
|
||||
{"current_steps": 405, "total_steps": 4214, "loss": 0.3152, "lr": 3.8293838862559244e-05, "epoch": 0.6727574750830565, "percentage": 9.61, "elapsed_time": "0:51:35", "remaining_time": "8:05:08"}
|
||||
{"current_steps": 410, "total_steps": 4214, "loss": 0.3257, "lr": 3.8767772511848344e-05, "epoch": 0.6810631229235881, "percentage": 9.73, "elapsed_time": "0:52:12", "remaining_time": "8:04:24"}
|
||||
{"current_steps": 415, "total_steps": 4214, "loss": 0.3103, "lr": 3.9241706161137444e-05, "epoch": 0.6893687707641196, "percentage": 9.85, "elapsed_time": "0:52:53", "remaining_time": "8:04:10"}
|
||||
{"current_steps": 420, "total_steps": 4214, "loss": 0.2992, "lr": 3.9715639810426545e-05, "epoch": 0.6976744186046512, "percentage": 9.97, "elapsed_time": "0:53:29", "remaining_time": "8:03:11"}
|
||||
{"current_steps": 425, "total_steps": 4214, "loss": 0.3226, "lr": 3.999997254490316e-05, "epoch": 0.7059800664451827, "percentage": 10.09, "elapsed_time": "0:54:04", "remaining_time": "8:02:02"}
|
||||
{"current_steps": 430, "total_steps": 4214, "loss": 0.3225, "lr": 3.999966367592929e-05, "epoch": 0.7142857142857143, "percentage": 10.2, "elapsed_time": "0:54:41", "remaining_time": "8:01:18"}
|
||||
{"current_steps": 435, "total_steps": 4214, "loss": 0.3277, "lr": 3.9999011624428174e-05, "epoch": 0.7225913621262459, "percentage": 10.32, "elapsed_time": "0:55:18", "remaining_time": "8:00:31"}
|
||||
{"current_steps": 440, "total_steps": 4214, "loss": 0.3141, "lr": 3.999801640158863e-05, "epoch": 0.7308970099667774, "percentage": 10.44, "elapsed_time": "0:55:54", "remaining_time": "7:59:32"}
|
||||
{"current_steps": 445, "total_steps": 4214, "loss": 0.3214, "lr": 3.9996678024488105e-05, "epoch": 0.739202657807309, "percentage": 10.56, "elapsed_time": "0:56:31", "remaining_time": "7:58:44"}
|
||||
{"current_steps": 450, "total_steps": 4214, "loss": 0.3261, "lr": 3.9994996516092365e-05, "epoch": 0.7475083056478405, "percentage": 10.68, "elapsed_time": "0:57:09", "remaining_time": "7:58:07"}
|
||||
{"current_steps": 455, "total_steps": 4214, "loss": 0.3039, "lr": 3.999297190525511e-05, "epoch": 0.7558139534883721, "percentage": 10.8, "elapsed_time": "0:57:47", "remaining_time": "7:57:28"}
|
||||
{"current_steps": 460, "total_steps": 4214, "loss": 0.3033, "lr": 3.999060422671747e-05, "epoch": 0.7641196013289037, "percentage": 10.92, "elapsed_time": "0:58:25", "remaining_time": "7:56:45"}
|
||||
{"current_steps": 465, "total_steps": 4214, "loss": 0.31, "lr": 3.9987893521107434e-05, "epoch": 0.7724252491694352, "percentage": 11.03, "elapsed_time": "0:58:58", "remaining_time": "7:55:32"}
|
||||
{"current_steps": 470, "total_steps": 4214, "loss": 0.3246, "lr": 3.9984839834939116e-05, "epoch": 0.7807308970099668, "percentage": 11.15, "elapsed_time": "0:59:32", "remaining_time": "7:54:17"}
|
||||
{"current_steps": 475, "total_steps": 4214, "loss": 0.3051, "lr": 3.9981443220611995e-05, "epoch": 0.7890365448504983, "percentage": 11.27, "elapsed_time": "1:00:08", "remaining_time": "7:53:27"}
|
||||
{"current_steps": 480, "total_steps": 4214, "loss": 0.3299, "lr": 3.9977703736409967e-05, "epoch": 0.7973421926910299, "percentage": 11.39, "elapsed_time": "1:00:50", "remaining_time": "7:53:14"}
|
||||
{"current_steps": 485, "total_steps": 4214, "loss": 0.3149, "lr": 3.997362144650041e-05, "epoch": 0.8056478405315615, "percentage": 11.51, "elapsed_time": "1:01:30", "remaining_time": "7:52:55"}
|
||||
{"current_steps": 490, "total_steps": 4214, "loss": 0.2939, "lr": 3.996919642093302e-05, "epoch": 0.813953488372093, "percentage": 11.63, "elapsed_time": "1:01:58", "remaining_time": "7:51:00"}
|
||||
{"current_steps": 495, "total_steps": 4214, "loss": 0.296, "lr": 3.996442873563866e-05, "epoch": 0.8222591362126246, "percentage": 11.75, "elapsed_time": "1:02:37", "remaining_time": "7:50:27"}
|
||||
{"current_steps": 500, "total_steps": 4214, "loss": 0.3114, "lr": 3.995931847242801e-05, "epoch": 0.8305647840531561, "percentage": 11.87, "elapsed_time": "1:03:15", "remaining_time": "7:49:50"}
|
||||
{"current_steps": 505, "total_steps": 4214, "loss": 0.3039, "lr": 3.99538657189902e-05, "epoch": 0.8388704318936877, "percentage": 11.98, "elapsed_time": "1:03:51", "remaining_time": "7:49:02"}
|
||||
{"current_steps": 510, "total_steps": 4214, "loss": 0.3126, "lr": 3.9948070568891284e-05, "epoch": 0.8471760797342193, "percentage": 12.1, "elapsed_time": "1:04:29", "remaining_time": "7:48:25"}
|
||||
{"current_steps": 515, "total_steps": 4214, "loss": 0.2974, "lr": 3.994193312157265e-05, "epoch": 0.8554817275747508, "percentage": 12.22, "elapsed_time": "1:04:59", "remaining_time": "7:46:45"}
|
||||
{"current_steps": 520, "total_steps": 4214, "loss": 0.3333, "lr": 3.9935453482349304e-05, "epoch": 0.8637873754152824, "percentage": 12.34, "elapsed_time": "1:05:40", "remaining_time": "7:46:34"}
|
||||
{"current_steps": 525, "total_steps": 4214, "loss": 0.3043, "lr": 3.992863176240806e-05, "epoch": 0.872093023255814, "percentage": 12.46, "elapsed_time": "1:06:15", "remaining_time": "7:45:31"}
|
||||
{"current_steps": 530, "total_steps": 4214, "loss": 0.3047, "lr": 3.992146807880565e-05, "epoch": 0.8803986710963455, "percentage": 12.58, "elapsed_time": "1:06:48", "remaining_time": "7:44:24"}
|
||||
{"current_steps": 535, "total_steps": 4214, "loss": 0.3031, "lr": 3.9913962554466683e-05, "epoch": 0.8887043189368771, "percentage": 12.7, "elapsed_time": "1:07:20", "remaining_time": "7:43:03"}
|
||||
{"current_steps": 540, "total_steps": 4214, "loss": 0.3131, "lr": 3.9906115318181565e-05, "epoch": 0.8970099667774086, "percentage": 12.81, "elapsed_time": "1:07:59", "remaining_time": "7:42:32"}
|
||||
{"current_steps": 545, "total_steps": 4214, "loss": 0.314, "lr": 3.9897926504604294e-05, "epoch": 0.9053156146179402, "percentage": 12.93, "elapsed_time": "1:08:36", "remaining_time": "7:41:52"}
|
||||
{"current_steps": 550, "total_steps": 4214, "loss": 0.3079, "lr": 3.9889396254250106e-05, "epoch": 0.9136212624584718, "percentage": 13.05, "elapsed_time": "1:09:10", "remaining_time": "7:40:52"}
|
||||
{"current_steps": 555, "total_steps": 4214, "loss": 0.3002, "lr": 3.9880524713493105e-05, "epoch": 0.9219269102990033, "percentage": 13.17, "elapsed_time": "1:09:48", "remaining_time": "7:40:15"}
|
||||
{"current_steps": 560, "total_steps": 4214, "loss": 0.31, "lr": 3.9871312034563754e-05, "epoch": 0.9302325581395349, "percentage": 13.29, "elapsed_time": "1:10:29", "remaining_time": "7:39:54"}
|
||||
{"current_steps": 565, "total_steps": 4214, "loss": 0.2937, "lr": 3.9861758375546216e-05, "epoch": 0.9385382059800664, "percentage": 13.41, "elapsed_time": "1:11:10", "remaining_time": "7:39:43"}
|
||||
{"current_steps": 570, "total_steps": 4214, "loss": 0.3288, "lr": 3.9851863900375703e-05, "epoch": 0.946843853820598, "percentage": 13.53, "elapsed_time": "1:11:47", "remaining_time": "7:39:00"}
|
||||
{"current_steps": 575, "total_steps": 4214, "loss": 0.3197, "lr": 3.984162877883562e-05, "epoch": 0.9551495016611296, "percentage": 13.64, "elapsed_time": "1:12:19", "remaining_time": "7:37:42"}
|
||||
{"current_steps": 580, "total_steps": 4214, "loss": 0.3078, "lr": 3.983105318655465e-05, "epoch": 0.9634551495016611, "percentage": 13.76, "elapsed_time": "1:13:01", "remaining_time": "7:37:30"}
|
||||
{"current_steps": 585, "total_steps": 4214, "loss": 0.2998, "lr": 3.982013730500379e-05, "epoch": 0.9717607973421927, "percentage": 13.88, "elapsed_time": "1:13:40", "remaining_time": "7:37:03"}
|
||||
{"current_steps": 590, "total_steps": 4214, "loss": 0.3069, "lr": 3.980888132149316e-05, "epoch": 0.9800664451827242, "percentage": 14.0, "elapsed_time": "1:14:16", "remaining_time": "7:36:11"}
|
||||
{"current_steps": 595, "total_steps": 4214, "loss": 0.3172, "lr": 3.979728542916886e-05, "epoch": 0.9883720930232558, "percentage": 14.12, "elapsed_time": "1:14:53", "remaining_time": "7:35:29"}
|
||||
{"current_steps": 600, "total_steps": 4214, "loss": 0.3179, "lr": 3.978534982700962e-05, "epoch": 0.9966777408637874, "percentage": 14.24, "elapsed_time": "1:15:34", "remaining_time": "7:35:12"}
|
||||
{"current_steps": 605, "total_steps": 4214, "loss": 0.3144, "lr": 3.977307471982339e-05, "epoch": 1.004983388704319, "percentage": 14.36, "elapsed_time": "1:16:09", "remaining_time": "7:34:19"}
|
||||
{"current_steps": 610, "total_steps": 4214, "loss": 0.292, "lr": 3.976046031824382e-05, "epoch": 1.0132890365448506, "percentage": 14.48, "elapsed_time": "1:16:48", "remaining_time": "7:33:48"}
|
||||
{"current_steps": 615, "total_steps": 4214, "loss": 0.3018, "lr": 3.974750683872667e-05, "epoch": 1.021594684385382, "percentage": 14.59, "elapsed_time": "1:17:23", "remaining_time": "7:32:53"}
|
||||
{"current_steps": 620, "total_steps": 4214, "loss": 0.3134, "lr": 3.9734214503546066e-05, "epoch": 1.0299003322259137, "percentage": 14.71, "elapsed_time": "1:18:02", "remaining_time": "7:32:26"}
|
||||
{"current_steps": 625, "total_steps": 4214, "loss": 0.2892, "lr": 3.97205835407907e-05, "epoch": 1.0382059800664452, "percentage": 14.83, "elapsed_time": "1:18:44", "remaining_time": "7:32:10"}
|
||||
{"current_steps": 630, "total_steps": 4214, "loss": 0.2922, "lr": 3.970661418435993e-05, "epoch": 1.0465116279069768, "percentage": 14.95, "elapsed_time": "1:19:18", "remaining_time": "7:31:12"}
|
||||
{"current_steps": 635, "total_steps": 4214, "loss": 0.2945, "lr": 3.969230667395971e-05, "epoch": 1.0548172757475083, "percentage": 15.07, "elapsed_time": "1:19:54", "remaining_time": "7:30:22"}
|
||||
{"current_steps": 640, "total_steps": 4214, "loss": 0.2903, "lr": 3.967766125509858e-05, "epoch": 1.06312292358804, "percentage": 15.19, "elapsed_time": "1:20:33", "remaining_time": "7:29:51"}
|
||||
{"current_steps": 645, "total_steps": 4214, "loss": 0.3032, "lr": 3.966267817908335e-05, "epoch": 1.0714285714285714, "percentage": 15.31, "elapsed_time": "1:21:12", "remaining_time": "7:29:21"}
|
||||
{"current_steps": 650, "total_steps": 4214, "loss": 0.3034, "lr": 3.964735770301482e-05, "epoch": 1.079734219269103, "percentage": 15.42, "elapsed_time": "1:21:51", "remaining_time": "7:28:51"}
|
||||
{"current_steps": 655, "total_steps": 4214, "loss": 0.2716, "lr": 3.963170008978342e-05, "epoch": 1.0880398671096345, "percentage": 15.54, "elapsed_time": "1:22:31", "remaining_time": "7:28:22"}
|
||||
{"current_steps": 660, "total_steps": 4214, "loss": 0.3064, "lr": 3.961570560806461e-05, "epoch": 1.0963455149501662, "percentage": 15.66, "elapsed_time": "1:23:12", "remaining_time": "7:28:05"}
|
||||
{"current_steps": 665, "total_steps": 4214, "loss": 0.3268, "lr": 3.959937453231436e-05, "epoch": 1.1046511627906976, "percentage": 15.78, "elapsed_time": "1:23:49", "remaining_time": "7:27:22"}
|
||||
{"current_steps": 670, "total_steps": 4214, "loss": 0.2681, "lr": 3.9582707142764356e-05, "epoch": 1.1129568106312293, "percentage": 15.9, "elapsed_time": "1:24:27", "remaining_time": "7:26:44"}
|
||||
{"current_steps": 675, "total_steps": 4214, "loss": 0.2995, "lr": 3.9565703725417266e-05, "epoch": 1.1212624584717608, "percentage": 16.02, "elapsed_time": "1:25:02", "remaining_time": "7:25:52"}
|
||||
{"current_steps": 680, "total_steps": 4214, "loss": 0.3132, "lr": 3.9548364572041774e-05, "epoch": 1.1295681063122924, "percentage": 16.14, "elapsed_time": "1:25:40", "remaining_time": "7:25:15"}
|
||||
{"current_steps": 685, "total_steps": 4214, "loss": 0.2832, "lr": 3.9530689980167615e-05, "epoch": 1.1378737541528239, "percentage": 16.26, "elapsed_time": "1:26:13", "remaining_time": "7:24:12"}
|
||||
{"current_steps": 690, "total_steps": 4214, "loss": 0.3025, "lr": 3.951268025308043e-05, "epoch": 1.1461794019933556, "percentage": 16.37, "elapsed_time": "1:26:44", "remaining_time": "7:23:02"}
|
||||
{"current_steps": 695, "total_steps": 4214, "loss": 0.313, "lr": 3.949433569981661e-05, "epoch": 1.154485049833887, "percentage": 16.49, "elapsed_time": "1:27:20", "remaining_time": "7:22:16"}
|
||||
{"current_steps": 700, "total_steps": 4214, "loss": 0.2859, "lr": 3.9475656635157954e-05, "epoch": 1.1627906976744187, "percentage": 16.61, "elapsed_time": "1:27:58", "remaining_time": "7:21:35"}
|
||||
{"current_steps": 705, "total_steps": 4214, "loss": 0.3013, "lr": 3.9456643379626284e-05, "epoch": 1.1710963455149501, "percentage": 16.73, "elapsed_time": "1:28:38", "remaining_time": "7:21:10"}
|
||||
{"current_steps": 710, "total_steps": 4214, "loss": 0.2911, "lr": 3.943729625947794e-05, "epoch": 1.1794019933554818, "percentage": 16.85, "elapsed_time": "1:29:12", "remaining_time": "7:20:16"}
|
||||
{"current_steps": 715, "total_steps": 4214, "loss": 0.2879, "lr": 3.941761560669818e-05, "epoch": 1.1877076411960132, "percentage": 16.97, "elapsed_time": "1:29:50", "remaining_time": "7:19:41"}
|
||||
{"current_steps": 720, "total_steps": 4214, "loss": 0.3014, "lr": 3.9397601758995493e-05, "epoch": 1.196013289036545, "percentage": 17.09, "elapsed_time": "1:30:32", "remaining_time": "7:19:24"}
|
||||
{"current_steps": 725, "total_steps": 4214, "loss": 0.2933, "lr": 3.93772550597958e-05, "epoch": 1.2043189368770764, "percentage": 17.2, "elapsed_time": "1:31:09", "remaining_time": "7:18:41"}
|
||||
{"current_steps": 730, "total_steps": 4214, "loss": 0.2932, "lr": 3.935657585823655e-05, "epoch": 1.212624584717608, "percentage": 17.32, "elapsed_time": "1:31:51", "remaining_time": "7:18:23"}
|
||||
{"current_steps": 735, "total_steps": 4214, "loss": 0.284, "lr": 3.9335564509160746e-05, "epoch": 1.2209302325581395, "percentage": 17.44, "elapsed_time": "1:32:30", "remaining_time": "7:17:53"}
|
||||
{"current_steps": 740, "total_steps": 4214, "loss": 0.2991, "lr": 3.931422137311084e-05, "epoch": 1.2292358803986712, "percentage": 17.56, "elapsed_time": "1:33:08", "remaining_time": "7:17:15"}
|
||||
{"current_steps": 745, "total_steps": 4214, "loss": 0.291, "lr": 3.929254681632257e-05, "epoch": 1.2375415282392026, "percentage": 17.68, "elapsed_time": "1:33:46", "remaining_time": "7:16:39"}
|
||||
{"current_steps": 750, "total_steps": 4214, "loss": 0.2932, "lr": 3.927054121071864e-05, "epoch": 1.2458471760797343, "percentage": 17.8, "elapsed_time": "1:34:24", "remaining_time": "7:16:02"}
|
||||
{"current_steps": 755, "total_steps": 4214, "loss": 0.3035, "lr": 3.924820493390236e-05, "epoch": 1.2541528239202657, "percentage": 17.92, "elapsed_time": "1:35:04", "remaining_time": "7:15:36"}
|
||||
{"current_steps": 760, "total_steps": 4214, "loss": 0.2823, "lr": 3.9225538369151185e-05, "epoch": 1.2624584717607974, "percentage": 18.04, "elapsed_time": "1:35:39", "remaining_time": "7:14:42"}
|
||||
{"current_steps": 765, "total_steps": 4214, "loss": 0.2953, "lr": 3.92025419054101e-05, "epoch": 1.2707641196013288, "percentage": 18.15, "elapsed_time": "1:36:16", "remaining_time": "7:14:02"}
|
||||
{"current_steps": 770, "total_steps": 4214, "loss": 0.2837, "lr": 3.9179215937284965e-05, "epoch": 1.2790697674418605, "percentage": 18.27, "elapsed_time": "1:36:51", "remaining_time": "7:13:11"}
|
||||
{"current_steps": 775, "total_steps": 4214, "loss": 0.2947, "lr": 3.915556086503576e-05, "epoch": 1.287375415282392, "percentage": 18.39, "elapsed_time": "1:37:26", "remaining_time": "7:12:25"}
|
||||
{"current_steps": 780, "total_steps": 4214, "loss": 0.2759, "lr": 3.913157709456966e-05, "epoch": 1.2956810631229236, "percentage": 18.51, "elapsed_time": "1:38:07", "remaining_time": "7:11:59"}
|
||||
{"current_steps": 785, "total_steps": 4214, "loss": 0.2707, "lr": 3.910726503743415e-05, "epoch": 1.303986710963455, "percentage": 18.63, "elapsed_time": "1:38:38", "remaining_time": "7:10:54"}
|
||||
{"current_steps": 790, "total_steps": 4214, "loss": 0.2812, "lr": 3.90826251108099e-05, "epoch": 1.3122923588039868, "percentage": 18.75, "elapsed_time": "1:39:13", "remaining_time": "7:10:04"}
|
||||
{"current_steps": 795, "total_steps": 4214, "loss": 0.2885, "lr": 3.905765773750364e-05, "epoch": 1.3205980066445182, "percentage": 18.87, "elapsed_time": "1:39:49", "remaining_time": "7:09:19"}
|
||||
{"current_steps": 800, "total_steps": 4214, "loss": 0.2878, "lr": 3.903236334594089e-05, "epoch": 1.3289036544850499, "percentage": 18.98, "elapsed_time": "1:40:26", "remaining_time": "7:08:37"}
|
||||
{"current_steps": 805, "total_steps": 4214, "loss": 0.2736, "lr": 3.900674237015859e-05, "epoch": 1.3372093023255813, "percentage": 19.1, "elapsed_time": "1:40:57", "remaining_time": "7:07:30"}
|
||||
{"current_steps": 810, "total_steps": 4214, "loss": 0.3039, "lr": 3.898079524979772e-05, "epoch": 1.345514950166113, "percentage": 19.22, "elapsed_time": "1:41:37", "remaining_time": "7:07:03"}
|
||||
{"current_steps": 815, "total_steps": 4214, "loss": 0.2961, "lr": 3.895452243009567e-05, "epoch": 1.3538205980066444, "percentage": 19.34, "elapsed_time": "1:42:12", "remaining_time": "7:06:15"}
|
||||
{"current_steps": 820, "total_steps": 4214, "loss": 0.308, "lr": 3.8927924361878655e-05, "epoch": 1.3621262458471761, "percentage": 19.46, "elapsed_time": "1:42:54", "remaining_time": "7:05:57"}
|
||||
{"current_steps": 825, "total_steps": 4214, "loss": 0.2937, "lr": 3.890100150155397e-05, "epoch": 1.3704318936877076, "percentage": 19.58, "elapsed_time": "1:43:30", "remaining_time": "7:05:10"}
|
||||
{"current_steps": 830, "total_steps": 4214, "loss": 0.2986, "lr": 3.887375431110214e-05, "epoch": 1.3787375415282392, "percentage": 19.7, "elapsed_time": "1:44:02", "remaining_time": "7:04:11"}
|
||||
{"current_steps": 835, "total_steps": 4214, "loss": 0.2859, "lr": 3.884618325806901e-05, "epoch": 1.3870431893687707, "percentage": 19.81, "elapsed_time": "1:44:37", "remaining_time": "7:03:22"}
|
||||
{"current_steps": 840, "total_steps": 4214, "loss": 0.3001, "lr": 3.881828881555773e-05, "epoch": 1.3953488372093024, "percentage": 19.93, "elapsed_time": "1:45:15", "remaining_time": "7:02:45"}
|
||||
{"current_steps": 845, "total_steps": 4214, "loss": 0.2839, "lr": 3.87900714622206e-05, "epoch": 1.4036544850498338, "percentage": 20.05, "elapsed_time": "1:45:52", "remaining_time": "7:02:07"}
|
||||
{"current_steps": 850, "total_steps": 4214, "loss": 0.3031, "lr": 3.87615316822509e-05, "epoch": 1.4119601328903655, "percentage": 20.17, "elapsed_time": "1:46:27", "remaining_time": "7:01:17"}
|
||||
{"current_steps": 855, "total_steps": 4214, "loss": 0.2909, "lr": 3.873266996537456e-05, "epoch": 1.420265780730897, "percentage": 20.29, "elapsed_time": "1:47:04", "remaining_time": "7:00:39"}
|
||||
{"current_steps": 860, "total_steps": 4214, "loss": 0.3143, "lr": 3.870348680684175e-05, "epoch": 1.4285714285714286, "percentage": 20.41, "elapsed_time": "1:47:45", "remaining_time": "7:00:16"}
|
||||
{"current_steps": 865, "total_steps": 4214, "loss": 0.2921, "lr": 3.867398270741839e-05, "epoch": 1.43687707641196, "percentage": 20.53, "elapsed_time": "1:48:17", "remaining_time": "6:59:16"}
|
||||
{"current_steps": 870, "total_steps": 4214, "loss": 0.2776, "lr": 3.864415817337757e-05, "epoch": 1.4451827242524917, "percentage": 20.65, "elapsed_time": "1:48:53", "remaining_time": "6:58:31"}
|
||||
{"current_steps": 875, "total_steps": 4214, "loss": 0.2888, "lr": 3.861401371649085e-05, "epoch": 1.4534883720930232, "percentage": 20.76, "elapsed_time": "1:49:32", "remaining_time": "6:58:00"}
|
||||
{"current_steps": 880, "total_steps": 4214, "loss": 0.2923, "lr": 3.8583549854019466e-05, "epoch": 1.4617940199335548, "percentage": 20.88, "elapsed_time": "1:50:06", "remaining_time": "6:57:08"}
|
||||
{"current_steps": 885, "total_steps": 4214, "loss": 0.286, "lr": 3.855276710870547e-05, "epoch": 1.4700996677740865, "percentage": 21.0, "elapsed_time": "1:50:45", "remaining_time": "6:56:37"}
|
||||
{"current_steps": 890, "total_steps": 4214, "loss": 0.2736, "lr": 3.852166600876277e-05, "epoch": 1.478405315614618, "percentage": 21.12, "elapsed_time": "1:51:26", "remaining_time": "6:56:11"}
|
||||
{"current_steps": 895, "total_steps": 4214, "loss": 0.2828, "lr": 3.8490247087868035e-05, "epoch": 1.4867109634551494, "percentage": 21.24, "elapsed_time": "1:52:03", "remaining_time": "6:55:32"}
|
||||
{"current_steps": 900, "total_steps": 4214, "loss": 0.2736, "lr": 3.845851088515159e-05, "epoch": 1.495016611295681, "percentage": 21.36, "elapsed_time": "1:52:40", "remaining_time": "6:54:55"}
|
||||
{"current_steps": 905, "total_steps": 4214, "loss": 0.2921, "lr": 3.8426457945188065e-05, "epoch": 1.5033222591362128, "percentage": 21.48, "elapsed_time": "1:53:19", "remaining_time": "6:54:20"}
|
||||
{"current_steps": 910, "total_steps": 4214, "loss": 0.3223, "lr": 3.839408881798719e-05, "epoch": 1.5116279069767442, "percentage": 21.59, "elapsed_time": "1:53:54", "remaining_time": "6:53:33"}
|
||||
{"current_steps": 915, "total_steps": 4214, "loss": 0.2618, "lr": 3.8361404058984236e-05, "epoch": 1.5199335548172757, "percentage": 21.71, "elapsed_time": "1:54:26", "remaining_time": "6:52:38"}
|
||||
{"current_steps": 920, "total_steps": 4214, "loss": 0.2628, "lr": 3.832840422903054e-05, "epoch": 1.5282392026578073, "percentage": 21.83, "elapsed_time": "1:55:01", "remaining_time": "6:51:49"}
|
||||
{"current_steps": 925, "total_steps": 4214, "loss": 0.3064, "lr": 3.829508989438389e-05, "epoch": 1.536544850498339, "percentage": 21.95, "elapsed_time": "1:55:41", "remaining_time": "6:51:20"}
|
||||
{"current_steps": 930, "total_steps": 4214, "loss": 0.2862, "lr": 3.826146162669876e-05, "epoch": 1.5448504983388704, "percentage": 22.07, "elapsed_time": "1:56:18", "remaining_time": "6:50:43"}
|
||||
{"current_steps": 935, "total_steps": 4214, "loss": 0.2945, "lr": 3.822752000301656e-05, "epoch": 1.553156146179402, "percentage": 22.19, "elapsed_time": "1:56:54", "remaining_time": "6:49:58"}
|
||||
{"current_steps": 940, "total_steps": 4214, "loss": 0.2878, "lr": 3.819326560575569e-05, "epoch": 1.5614617940199336, "percentage": 22.31, "elapsed_time": "1:57:33", "remaining_time": "6:49:27"}
|
||||
{"current_steps": 945, "total_steps": 4214, "loss": 0.3047, "lr": 3.815869902270157e-05, "epoch": 1.5697674418604652, "percentage": 22.43, "elapsed_time": "1:58:11", "remaining_time": "6:48:52"}
|
||||
{"current_steps": 950, "total_steps": 4214, "loss": 0.2896, "lr": 3.8123820846996536e-05, "epoch": 1.5780730897009967, "percentage": 22.54, "elapsed_time": "1:58:47", "remaining_time": "6:48:10"}
|
||||
{"current_steps": 955, "total_steps": 4214, "loss": 0.3049, "lr": 3.808863167712967e-05, "epoch": 1.5863787375415281, "percentage": 22.66, "elapsed_time": "1:59:25", "remaining_time": "6:47:34"}
|
||||
{"current_steps": 960, "total_steps": 4214, "loss": 0.2882, "lr": 3.805313211692655e-05, "epoch": 1.5946843853820598, "percentage": 22.78, "elapsed_time": "2:00:01", "remaining_time": "6:46:48"}
|
||||
{"current_steps": 965, "total_steps": 4214, "loss": 0.2721, "lr": 3.801732277553885e-05, "epoch": 1.6029900332225915, "percentage": 22.9, "elapsed_time": "2:00:35", "remaining_time": "6:46:01"}
|
||||
{"current_steps": 970, "total_steps": 4214, "loss": 0.2847, "lr": 3.7981204267433935e-05, "epoch": 1.611295681063123, "percentage": 23.02, "elapsed_time": "2:01:15", "remaining_time": "6:45:30"}
|
||||
{"current_steps": 975, "total_steps": 4214, "loss": 0.2831, "lr": 3.794477721238425e-05, "epoch": 1.6196013289036544, "percentage": 23.14, "elapsed_time": "2:01:53", "remaining_time": "6:44:54"}
|
||||
{"current_steps": 980, "total_steps": 4214, "loss": 0.2875, "lr": 3.7908042235456753e-05, "epoch": 1.627906976744186, "percentage": 23.26, "elapsed_time": "2:02:32", "remaining_time": "6:44:22"}
|
||||
{"current_steps": 985, "total_steps": 4214, "loss": 0.273, "lr": 3.787099996700216e-05, "epoch": 1.6362126245847177, "percentage": 23.37, "elapsed_time": "2:03:04", "remaining_time": "6:43:26"}
|
||||
{"current_steps": 990, "total_steps": 4214, "loss": 0.3144, "lr": 3.783365104264413e-05, "epoch": 1.6445182724252492, "percentage": 23.49, "elapsed_time": "2:03:46", "remaining_time": "6:43:03"}
|
||||
{"current_steps": 995, "total_steps": 4214, "loss": 0.2777, "lr": 3.779599610326833e-05, "epoch": 1.6528239202657806, "percentage": 23.61, "elapsed_time": "2:04:24", "remaining_time": "6:42:29"}
|
||||
{"current_steps": 1000, "total_steps": 4214, "loss": 0.2922, "lr": 3.775803579501151e-05, "epoch": 1.6611295681063123, "percentage": 23.73, "elapsed_time": "2:05:01", "remaining_time": "6:41:50"}
|
||||
{"current_steps": 1005, "total_steps": 4214, "loss": 0.2714, "lr": 3.771977076925034e-05, "epoch": 1.669435215946844, "percentage": 23.85, "elapsed_time": "2:05:36", "remaining_time": "6:41:05"}
|
||||
{"current_steps": 1010, "total_steps": 4214, "loss": 0.2713, "lr": 3.7681201682590286e-05, "epoch": 1.6777408637873754, "percentage": 23.97, "elapsed_time": "2:06:09", "remaining_time": "6:40:14"}
|
||||
{"current_steps": 1015, "total_steps": 4214, "loss": 0.286, "lr": 3.7642329196854295e-05, "epoch": 1.6860465116279069, "percentage": 24.09, "elapsed_time": "2:06:46", "remaining_time": "6:39:33"}
|
||||
{"current_steps": 1020, "total_steps": 4214, "loss": 0.2903, "lr": 3.760315397907149e-05, "epoch": 1.6943521594684385, "percentage": 24.21, "elapsed_time": "2:07:23", "remaining_time": "6:38:54"}
|
||||
{"current_steps": 1025, "total_steps": 4214, "loss": 0.3102, "lr": 3.756367670146567e-05, "epoch": 1.7026578073089702, "percentage": 24.32, "elapsed_time": "2:08:03", "remaining_time": "6:38:23"}
|
||||
{"current_steps": 1030, "total_steps": 4214, "loss": 0.2809, "lr": 3.752389804144384e-05, "epoch": 1.7109634551495017, "percentage": 24.44, "elapsed_time": "2:08:38", "remaining_time": "6:37:41"}
|
||||
{"current_steps": 1035, "total_steps": 4214, "loss": 0.2844, "lr": 3.748381868158452e-05, "epoch": 1.719269102990033, "percentage": 24.56, "elapsed_time": "2:09:15", "remaining_time": "6:37:01"}
|
||||
{"current_steps": 1040, "total_steps": 4214, "loss": 0.2557, "lr": 3.7443439309626085e-05, "epoch": 1.7275747508305648, "percentage": 24.68, "elapsed_time": "2:09:45", "remaining_time": "6:36:00"}
|
||||
{"current_steps": 1045, "total_steps": 4214, "loss": 0.2801, "lr": 3.740276061845493e-05, "epoch": 1.7358803986710964, "percentage": 24.8, "elapsed_time": "2:10:21", "remaining_time": "6:35:18"}
|
||||
{"current_steps": 1050, "total_steps": 4214, "loss": 0.2936, "lr": 3.7361783306093596e-05, "epoch": 1.744186046511628, "percentage": 24.92, "elapsed_time": "2:11:02", "remaining_time": "6:34:53"}
|
||||
{"current_steps": 1055, "total_steps": 4214, "loss": 0.283, "lr": 3.732050807568878e-05, "epoch": 1.7524916943521593, "percentage": 25.04, "elapsed_time": "2:11:40", "remaining_time": "6:34:15"}
|
||||
{"current_steps": 1060, "total_steps": 4214, "loss": 0.2715, "lr": 3.7278935635499285e-05, "epoch": 1.760797342192691, "percentage": 25.15, "elapsed_time": "2:12:16", "remaining_time": "6:33:33"}
|
||||
{"current_steps": 1065, "total_steps": 4214, "loss": 0.3126, "lr": 3.723706669888388e-05, "epoch": 1.7691029900332227, "percentage": 25.27, "elapsed_time": "2:12:58", "remaining_time": "6:33:09"}
|
||||
{"current_steps": 1070, "total_steps": 4214, "loss": 0.2857, "lr": 3.7194901984289e-05, "epoch": 1.7774086378737541, "percentage": 25.39, "elapsed_time": "2:13:34", "remaining_time": "6:32:28"}
|
||||
{"current_steps": 1075, "total_steps": 4214, "loss": 0.2708, "lr": 3.715244221523649e-05, "epoch": 1.7857142857142856, "percentage": 25.51, "elapsed_time": "2:14:06", "remaining_time": "6:31:36"}
|
||||
{"current_steps": 1080, "total_steps": 4214, "loss": 0.2869, "lr": 3.710968812031114e-05, "epoch": 1.7940199335548173, "percentage": 25.63, "elapsed_time": "2:14:46", "remaining_time": "6:31:07"}
|
||||
{"current_steps": 1085, "total_steps": 4214, "loss": 0.265, "lr": 3.7066640433148205e-05, "epoch": 1.802325581395349, "percentage": 25.75, "elapsed_time": "2:15:21", "remaining_time": "6:30:21"}
|
||||
{"current_steps": 1090, "total_steps": 4214, "loss": 0.2784, "lr": 3.7023299892420814e-05, "epoch": 1.8106312292358804, "percentage": 25.87, "elapsed_time": "2:15:56", "remaining_time": "6:29:37"}
|
||||
{"current_steps": 1095, "total_steps": 4214, "loss": 0.2754, "lr": 3.697966724182729e-05, "epoch": 1.8189368770764118, "percentage": 25.98, "elapsed_time": "2:16:27", "remaining_time": "6:28:40"}
|
||||
{"current_steps": 1100, "total_steps": 4214, "loss": 0.2593, "lr": 3.6935743230078364e-05, "epoch": 1.8272425249169435, "percentage": 26.1, "elapsed_time": "2:17:01", "remaining_time": "6:27:53"}
|
||||
{"current_steps": 1105, "total_steps": 4214, "loss": 0.274, "lr": 3.689152861088441e-05, "epoch": 1.8355481727574752, "percentage": 26.22, "elapsed_time": "2:17:38", "remaining_time": "6:27:15"}
|
||||
{"current_steps": 1110, "total_steps": 4214, "loss": 0.2948, "lr": 3.6847024142942414e-05, "epoch": 1.8438538205980066, "percentage": 26.34, "elapsed_time": "2:18:16", "remaining_time": "6:26:39"}
|
||||
{"current_steps": 1115, "total_steps": 4214, "loss": 0.2784, "lr": 3.6802230589923e-05, "epoch": 1.852159468438538, "percentage": 26.46, "elapsed_time": "2:18:58", "remaining_time": "6:26:15"}
|
||||
{"current_steps": 1120, "total_steps": 4214, "loss": 0.2872, "lr": 3.6757148720457336e-05, "epoch": 1.8604651162790697, "percentage": 26.58, "elapsed_time": "2:19:35", "remaining_time": "6:25:36"}
|
||||
{"current_steps": 1125, "total_steps": 4214, "loss": 0.273, "lr": 3.671177930812392e-05, "epoch": 1.8687707641196014, "percentage": 26.7, "elapsed_time": "2:20:06", "remaining_time": "6:24:43"}
|
||||
{"current_steps": 1130, "total_steps": 4214, "loss": 0.2951, "lr": 3.6666123131435336e-05, "epoch": 1.8770764119601329, "percentage": 26.82, "elapsed_time": "2:20:49", "remaining_time": "6:24:19"}
|
||||
{"current_steps": 1135, "total_steps": 4214, "loss": 0.2766, "lr": 3.6620180973824846e-05, "epoch": 1.8853820598006643, "percentage": 26.93, "elapsed_time": "2:21:28", "remaining_time": "6:23:46"}
|
||||
{"current_steps": 1140, "total_steps": 4214, "loss": 0.2817, "lr": 3.657395362363301e-05, "epoch": 1.893687707641196, "percentage": 27.05, "elapsed_time": "2:22:01", "remaining_time": "6:22:58"}
|
||||
{"current_steps": 1145, "total_steps": 4214, "loss": 0.2794, "lr": 3.65274418740941e-05, "epoch": 1.9019933554817277, "percentage": 27.17, "elapsed_time": "2:22:39", "remaining_time": "6:22:22"}
|
||||
{"current_steps": 1150, "total_steps": 4214, "loss": 0.2979, "lr": 3.648064652332253e-05, "epoch": 1.910299003322259, "percentage": 27.29, "elapsed_time": "2:23:17", "remaining_time": "6:21:47"}
|
||||
{"current_steps": 1155, "total_steps": 4214, "loss": 0.2534, "lr": 3.643356837429914e-05, "epoch": 1.9186046511627906, "percentage": 27.41, "elapsed_time": "2:23:52", "remaining_time": "6:21:04"}
|
||||
{"current_steps": 1160, "total_steps": 4214, "loss": 0.2735, "lr": 3.6386208234857424e-05, "epoch": 1.9269102990033222, "percentage": 27.53, "elapsed_time": "2:24:29", "remaining_time": "6:20:23"}
|
||||
{"current_steps": 1165, "total_steps": 4214, "loss": 0.297, "lr": 3.633856691766966e-05, "epoch": 1.935215946843854, "percentage": 27.65, "elapsed_time": "2:25:04", "remaining_time": "6:19:41"}
|
||||
{"current_steps": 1170, "total_steps": 4214, "loss": 0.2866, "lr": 3.629064524023298e-05, "epoch": 1.9435215946843853, "percentage": 27.76, "elapsed_time": "2:25:39", "remaining_time": "6:18:58"}
|
||||
{"current_steps": 1175, "total_steps": 4214, "loss": 0.2814, "lr": 3.624244402485533e-05, "epoch": 1.9518272425249168, "percentage": 27.88, "elapsed_time": "2:26:20", "remaining_time": "6:18:28"}
|
||||
{"current_steps": 1180, "total_steps": 4214, "loss": 0.2928, "lr": 3.6193964098641365e-05, "epoch": 1.9601328903654485, "percentage": 28.0, "elapsed_time": "2:26:58", "remaining_time": "6:17:54"}
|
||||
{"current_steps": 1185, "total_steps": 4214, "loss": 0.2775, "lr": 3.614520629347825e-05, "epoch": 1.9684385382059801, "percentage": 28.12, "elapsed_time": "2:27:36", "remaining_time": "6:17:18"}
|
||||
{"current_steps": 1190, "total_steps": 4214, "loss": 0.3039, "lr": 3.60961714460214e-05, "epoch": 1.9767441860465116, "percentage": 28.24, "elapsed_time": "2:28:14", "remaining_time": "6:16:42"}
|
||||
{"current_steps": 1195, "total_steps": 4214, "loss": 0.2819, "lr": 3.604686039768011e-05, "epoch": 1.985049833887043, "percentage": 28.36, "elapsed_time": "2:28:49", "remaining_time": "6:15:58"}
|
||||
{"current_steps": 1200, "total_steps": 4214, "loss": 0.2931, "lr": 3.599727399460312e-05, "epoch": 1.9933554817275747, "percentage": 28.48, "elapsed_time": "2:29:26", "remaining_time": "6:15:20"}
|
||||
{"current_steps": 1205, "total_steps": 4214, "loss": 0.2755, "lr": 3.594741308766408e-05, "epoch": 2.0016611295681064, "percentage": 28.6, "elapsed_time": "2:29:58", "remaining_time": "6:14:29"}
|
||||
{"current_steps": 1210, "total_steps": 4214, "loss": 0.2719, "lr": 3.589727853244699e-05, "epoch": 2.009966777408638, "percentage": 28.71, "elapsed_time": "2:30:34", "remaining_time": "6:13:50"}
|
||||
{"current_steps": 1215, "total_steps": 4214, "loss": 0.2684, "lr": 3.584687118923149e-05, "epoch": 2.0182724252491693, "percentage": 28.83, "elapsed_time": "2:31:14", "remaining_time": "6:13:18"}
|
||||
{"current_steps": 1220, "total_steps": 4214, "loss": 0.2704, "lr": 3.5796191922978094e-05, "epoch": 2.026578073089701, "percentage": 28.95, "elapsed_time": "2:31:55", "remaining_time": "6:12:49"}
|
||||
{"current_steps": 1225, "total_steps": 4214, "loss": 0.2878, "lr": 3.574524160331335e-05, "epoch": 2.0348837209302326, "percentage": 29.07, "elapsed_time": "2:32:31", "remaining_time": "6:12:09"}
|
||||
{"current_steps": 1230, "total_steps": 4214, "loss": 0.2771, "lr": 3.569402110451494e-05, "epoch": 2.043189368770764, "percentage": 29.19, "elapsed_time": "2:33:11", "remaining_time": "6:11:37"}
|
||||
{"current_steps": 1235, "total_steps": 4214, "loss": 0.2515, "lr": 3.564253130549666e-05, "epoch": 2.0514950166112955, "percentage": 29.31, "elapsed_time": "2:33:50", "remaining_time": "6:11:05"}
|
||||
{"current_steps": 1240, "total_steps": 4214, "loss": 0.2568, "lr": 3.559077308979332e-05, "epoch": 2.0598006644518274, "percentage": 29.43, "elapsed_time": "2:34:28", "remaining_time": "6:10:29"}
|
||||
{"current_steps": 1245, "total_steps": 4214, "loss": 0.267, "lr": 3.553874734554565e-05, "epoch": 2.068106312292359, "percentage": 29.54, "elapsed_time": "2:35:02", "remaining_time": "6:09:44"}
|
||||
{"current_steps": 1250, "total_steps": 4214, "loss": 0.2657, "lr": 3.548645496548495e-05, "epoch": 2.0764119601328903, "percentage": 29.66, "elapsed_time": "2:35:35", "remaining_time": "6:08:56"}
|
||||
{"current_steps": 1255, "total_steps": 4214, "loss": 0.2633, "lr": 3.543389684691788e-05, "epoch": 2.0847176079734218, "percentage": 29.78, "elapsed_time": "2:36:09", "remaining_time": "6:08:12"}
|
||||
{"current_steps": 1260, "total_steps": 4214, "loss": 0.247, "lr": 3.5381073891711e-05, "epoch": 2.0930232558139537, "percentage": 29.9, "elapsed_time": "2:36:46", "remaining_time": "6:07:32"}
|
||||
{"current_steps": 1265, "total_steps": 4214, "loss": 0.3065, "lr": 3.532798700627532e-05, "epoch": 2.101328903654485, "percentage": 30.02, "elapsed_time": "2:37:29", "remaining_time": "6:07:09"}
|
||||
{"current_steps": 1270, "total_steps": 4214, "loss": 0.268, "lr": 3.5274637101550737e-05, "epoch": 2.1096345514950166, "percentage": 30.14, "elapsed_time": "2:38:05", "remaining_time": "6:06:29"}
|
||||
{"current_steps": 1275, "total_steps": 4214, "loss": 0.2742, "lr": 3.522102509299039e-05, "epoch": 2.117940199335548, "percentage": 30.26, "elapsed_time": "2:38:43", "remaining_time": "6:05:51"}
|
||||
{"current_steps": 1280, "total_steps": 4214, "loss": 0.2704, "lr": 3.516715190054499e-05, "epoch": 2.12624584717608, "percentage": 30.37, "elapsed_time": "2:39:15", "remaining_time": "6:05:03"}
|
||||
{"current_steps": 1285, "total_steps": 4214, "loss": 0.2662, "lr": 3.511301844864699e-05, "epoch": 2.1345514950166113, "percentage": 30.49, "elapsed_time": "2:39:55", "remaining_time": "6:04:31"}
|
||||
{"current_steps": 1290, "total_steps": 4214, "loss": 0.2863, "lr": 3.505862566619476e-05, "epoch": 2.142857142857143, "percentage": 30.61, "elapsed_time": "2:40:31", "remaining_time": "6:03:51"}
|
||||
{"current_steps": 1295, "total_steps": 4214, "loss": 0.2631, "lr": 3.5003974486536614e-05, "epoch": 2.1511627906976742, "percentage": 30.73, "elapsed_time": "2:41:07", "remaining_time": "6:03:10"}
|
||||
{"current_steps": 1300, "total_steps": 4214, "loss": 0.2947, "lr": 3.4949065847454835e-05, "epoch": 2.159468438538206, "percentage": 30.85, "elapsed_time": "2:41:49", "remaining_time": "6:02:43"}
|
||||
{"current_steps": 1305, "total_steps": 4214, "loss": 0.2679, "lr": 3.4893900691149525e-05, "epoch": 2.1677740863787376, "percentage": 30.97, "elapsed_time": "2:42:26", "remaining_time": "6:02:05"}
|
||||
{"current_steps": 1310, "total_steps": 4214, "loss": 0.2637, "lr": 3.48384799642225e-05, "epoch": 2.176079734219269, "percentage": 31.09, "elapsed_time": "2:43:04", "remaining_time": "6:01:30"}
|
||||
{"current_steps": 1315, "total_steps": 4214, "loss": 0.2645, "lr": 3.478280461766101e-05, "epoch": 2.1843853820598005, "percentage": 31.21, "elapsed_time": "2:43:43", "remaining_time": "6:00:56"}
|
||||
{"current_steps": 1320, "total_steps": 4214, "loss": 0.2796, "lr": 3.4726875606821416e-05, "epoch": 2.1926910299003324, "percentage": 31.32, "elapsed_time": "2:44:19", "remaining_time": "6:00:16"}
|
||||
{"current_steps": 1325, "total_steps": 4214, "loss": 0.269, "lr": 3.467069389141284e-05, "epoch": 2.200996677740864, "percentage": 31.44, "elapsed_time": "2:44:55", "remaining_time": "5:59:35"}
|
||||
{"current_steps": 1330, "total_steps": 4214, "loss": 0.2559, "lr": 3.461426043548063e-05, "epoch": 2.2093023255813953, "percentage": 31.56, "elapsed_time": "2:45:32", "remaining_time": "5:58:57"}
|
||||
{"current_steps": 1335, "total_steps": 4214, "loss": 0.2987, "lr": 3.455757620738989e-05, "epoch": 2.2176079734219267, "percentage": 31.68, "elapsed_time": "2:46:13", "remaining_time": "5:58:29"}
|
||||
{"current_steps": 1340, "total_steps": 4214, "loss": 0.279, "lr": 3.4500642179808785e-05, "epoch": 2.2259136212624586, "percentage": 31.8, "elapsed_time": "2:46:52", "remaining_time": "5:57:54"}
|
||||
{"current_steps": 1345, "total_steps": 4214, "loss": 0.2701, "lr": 3.444345932969193e-05, "epoch": 2.23421926910299, "percentage": 31.92, "elapsed_time": "2:47:27", "remaining_time": "5:57:12"}
|
||||
{"current_steps": 1350, "total_steps": 4214, "loss": 0.2696, "lr": 3.438602863826359e-05, "epoch": 2.2425249169435215, "percentage": 32.04, "elapsed_time": "2:48:06", "remaining_time": "5:56:39"}
|
||||
{"current_steps": 1355, "total_steps": 4214, "loss": 0.2823, "lr": 3.43283510910008e-05, "epoch": 2.250830564784053, "percentage": 32.15, "elapsed_time": "2:48:40", "remaining_time": "5:55:54"}
|
||||
{"current_steps": 1360, "total_steps": 4214, "loss": 0.2723, "lr": 3.427042767761655e-05, "epoch": 2.259136212624585, "percentage": 32.27, "elapsed_time": "2:49:21", "remaining_time": "5:55:23"}
|
||||
{"current_steps": 1365, "total_steps": 4214, "loss": 0.2719, "lr": 3.421225939204271e-05, "epoch": 2.2674418604651163, "percentage": 32.39, "elapsed_time": "2:49:55", "remaining_time": "5:54:40"}
|
||||
{"current_steps": 1370, "total_steps": 4214, "loss": 0.2843, "lr": 3.415384723241302e-05, "epoch": 2.2757475083056478, "percentage": 32.51, "elapsed_time": "2:50:30", "remaining_time": "5:53:57"}
|
||||
{"current_steps": 1375, "total_steps": 4214, "loss": 0.2613, "lr": 3.4095192201045984e-05, "epoch": 2.284053156146179, "percentage": 32.63, "elapsed_time": "2:51:09", "remaining_time": "5:53:24"}
|
||||
{"current_steps": 1380, "total_steps": 4214, "loss": 0.2476, "lr": 3.403629530442761e-05, "epoch": 2.292358803986711, "percentage": 32.75, "elapsed_time": "2:51:47", "remaining_time": "5:52:46"}
|
||||
{"current_steps": 1385, "total_steps": 4214, "loss": 0.2667, "lr": 3.397715755319419e-05, "epoch": 2.3006644518272426, "percentage": 32.87, "elapsed_time": "2:52:21", "remaining_time": "5:52:04"}
|
||||
{"current_steps": 1390, "total_steps": 4214, "loss": 0.2769, "lr": 3.3917779962114935e-05, "epoch": 2.308970099667774, "percentage": 32.99, "elapsed_time": "2:52:52", "remaining_time": "5:51:13"}
|
||||
{"current_steps": 1395, "total_steps": 4214, "loss": 0.2536, "lr": 3.385816355007455e-05, "epoch": 2.3172757475083055, "percentage": 33.1, "elapsed_time": "2:53:27", "remaining_time": "5:50:31"}
|
||||
{"current_steps": 1400, "total_steps": 4214, "loss": 0.2815, "lr": 3.3798309340055806e-05, "epoch": 2.3255813953488373, "percentage": 33.22, "elapsed_time": "2:54:06", "remaining_time": "5:49:57"}
|
||||
{"current_steps": 1405, "total_steps": 4214, "loss": 0.2819, "lr": 3.373821835912192e-05, "epoch": 2.333887043189369, "percentage": 33.34, "elapsed_time": "2:54:46", "remaining_time": "5:49:25"}
|
||||
{"current_steps": 1410, "total_steps": 4214, "loss": 0.2718, "lr": 3.3677891638398975e-05, "epoch": 2.3421926910299002, "percentage": 33.46, "elapsed_time": "2:55:25", "remaining_time": "5:48:51"}
|
||||
{"current_steps": 1415, "total_steps": 4214, "loss": 0.2888, "lr": 3.361733021305819e-05, "epoch": 2.350498338870432, "percentage": 33.58, "elapsed_time": "2:56:04", "remaining_time": "5:48:17"}
|
||||
{"current_steps": 1420, "total_steps": 4214, "loss": 0.2824, "lr": 3.3556535122298194e-05, "epoch": 2.3588039867109636, "percentage": 33.7, "elapsed_time": "2:56:44", "remaining_time": "5:47:45"}
|
||||
{"current_steps": 1425, "total_steps": 4214, "loss": 0.2688, "lr": 3.349550740932717e-05, "epoch": 2.367109634551495, "percentage": 33.82, "elapsed_time": "2:57:23", "remaining_time": "5:47:12"}
|
||||
{"current_steps": 1430, "total_steps": 4214, "loss": 0.2694, "lr": 3.343424812134498e-05, "epoch": 2.3754152823920265, "percentage": 33.93, "elapsed_time": "2:57:57", "remaining_time": "5:46:28"}
|
||||
{"current_steps": 1435, "total_steps": 4214, "loss": 0.2736, "lr": 3.337275830952515e-05, "epoch": 2.383720930232558, "percentage": 34.05, "elapsed_time": "2:58:34", "remaining_time": "5:45:49"}
|
||||
{"current_steps": 1440, "total_steps": 4214, "loss": 0.2488, "lr": 3.3311039028996886e-05, "epoch": 2.39202657807309, "percentage": 34.17, "elapsed_time": "2:59:08", "remaining_time": "5:45:05"}
|
||||
{"current_steps": 1445, "total_steps": 4214, "loss": 0.2722, "lr": 3.324909133882692e-05, "epoch": 2.4003322259136213, "percentage": 34.29, "elapsed_time": "2:59:44", "remaining_time": "5:44:25"}
|
||||
{"current_steps": 1450, "total_steps": 4214, "loss": 0.2547, "lr": 3.318691630200138e-05, "epoch": 2.4086378737541527, "percentage": 34.41, "elapsed_time": "3:00:17", "remaining_time": "5:43:40"}
|
||||
{"current_steps": 1455, "total_steps": 4214, "loss": 0.2618, "lr": 3.312451498540751e-05, "epoch": 2.4169435215946846, "percentage": 34.53, "elapsed_time": "3:00:54", "remaining_time": "5:43:02"}
|
||||
{"current_steps": 1460, "total_steps": 4214, "loss": 0.2834, "lr": 3.306188845981541e-05, "epoch": 2.425249169435216, "percentage": 34.65, "elapsed_time": "3:01:30", "remaining_time": "5:42:21"}
|
||||
{"current_steps": 1465, "total_steps": 4214, "loss": 0.2919, "lr": 3.2999037799859604e-05, "epoch": 2.4335548172757475, "percentage": 34.77, "elapsed_time": "3:02:07", "remaining_time": "5:41:45"}
|
||||
{"current_steps": 1470, "total_steps": 4214, "loss": 0.253, "lr": 3.2935964084020646e-05, "epoch": 2.441860465116279, "percentage": 34.88, "elapsed_time": "3:02:43", "remaining_time": "5:41:05"}
|
||||
{"current_steps": 1475, "total_steps": 4214, "loss": 0.2562, "lr": 3.2872668394606596e-05, "epoch": 2.4501661129568104, "percentage": 35.0, "elapsed_time": "3:03:19", "remaining_time": "5:40:25"}
|
||||
{"current_steps": 1480, "total_steps": 4214, "loss": 0.2574, "lr": 3.280915181773445e-05, "epoch": 2.4584717607973423, "percentage": 35.12, "elapsed_time": "3:03:50", "remaining_time": "5:39:37"}
|
||||
{"current_steps": 1485, "total_steps": 4214, "loss": 0.2725, "lr": 3.274541544331151e-05, "epoch": 2.4667774086378738, "percentage": 35.24, "elapsed_time": "3:04:26", "remaining_time": "5:38:56"}
|
||||
{"current_steps": 1490, "total_steps": 4214, "loss": 0.2768, "lr": 3.2681460365016664e-05, "epoch": 2.475083056478405, "percentage": 35.36, "elapsed_time": "3:05:05", "remaining_time": "5:38:23"}
|
||||
{"current_steps": 1495, "total_steps": 4214, "loss": 0.2814, "lr": 3.261728768028166e-05, "epoch": 2.483388704318937, "percentage": 35.48, "elapsed_time": "3:05:44", "remaining_time": "5:37:48"}
|
||||
{"current_steps": 1500, "total_steps": 4214, "loss": 0.2609, "lr": 3.255289849027218e-05, "epoch": 2.4916943521594686, "percentage": 35.6, "elapsed_time": "3:06:25", "remaining_time": "5:37:18"}
|
||||
{"current_steps": 1505, "total_steps": 4214, "loss": 0.2659, "lr": 3.248829389986908e-05, "epoch": 2.5, "percentage": 35.71, "elapsed_time": "3:07:12", "remaining_time": "5:36:57"}
|
||||
{"current_steps": 1510, "total_steps": 4214, "loss": 0.262, "lr": 3.2423475017649324e-05, "epoch": 2.5083056478405314, "percentage": 35.83, "elapsed_time": "3:07:44", "remaining_time": "5:36:11"}
|
||||
{"current_steps": 1515, "total_steps": 4214, "loss": 0.2514, "lr": 3.235844295586702e-05, "epoch": 2.516611295681063, "percentage": 35.95, "elapsed_time": "3:08:18", "remaining_time": "5:35:28"}
|
||||
{"current_steps": 1520, "total_steps": 4214, "loss": 0.2742, "lr": 3.229319883043428e-05, "epoch": 2.524916943521595, "percentage": 36.07, "elapsed_time": "3:08:55", "remaining_time": "5:34:51"}
|
||||
{"current_steps": 1525, "total_steps": 4214, "loss": 0.2607, "lr": 3.2227743760902125e-05, "epoch": 2.5332225913621262, "percentage": 36.19, "elapsed_time": "3:09:34", "remaining_time": "5:34:15"}
|
||||
{"current_steps": 1530, "total_steps": 4214, "loss": 0.2813, "lr": 3.2162078870441273e-05, "epoch": 2.5415282392026577, "percentage": 36.31, "elapsed_time": "3:10:18", "remaining_time": "5:33:50"}
|
||||
{"current_steps": 1535, "total_steps": 4214, "loss": 0.2759, "lr": 3.20962052858228e-05, "epoch": 2.5498338870431896, "percentage": 36.43, "elapsed_time": "3:10:52", "remaining_time": "5:33:07"}
|
||||
{"current_steps": 1540, "total_steps": 4214, "loss": 0.2679, "lr": 3.203012413739889e-05, "epoch": 2.558139534883721, "percentage": 36.54, "elapsed_time": "3:11:30", "remaining_time": "5:32:31"}
|
||||
{"current_steps": 1545, "total_steps": 4214, "loss": 0.2605, "lr": 3.196383655908338e-05, "epoch": 2.5664451827242525, "percentage": 36.66, "elapsed_time": "3:12:06", "remaining_time": "5:31:51"}
|
||||
{"current_steps": 1550, "total_steps": 4214, "loss": 0.2768, "lr": 3.1897343688332334e-05, "epoch": 2.574750830564784, "percentage": 36.78, "elapsed_time": "3:12:40", "remaining_time": "5:31:08"}
|
||||
{"current_steps": 1555, "total_steps": 4214, "loss": 0.2777, "lr": 3.183064666612451e-05, "epoch": 2.5830564784053154, "percentage": 36.9, "elapsed_time": "3:13:21", "remaining_time": "5:30:37"}
|
||||
{"current_steps": 1560, "total_steps": 4214, "loss": 0.2576, "lr": 3.176374663694179e-05, "epoch": 2.5913621262458473, "percentage": 37.02, "elapsed_time": "3:13:53", "remaining_time": "5:29:51"}
|
||||
{"current_steps": 1565, "total_steps": 4214, "loss": 0.2748, "lr": 3.169664474874953e-05, "epoch": 2.5996677740863787, "percentage": 37.14, "elapsed_time": "3:14:31", "remaining_time": "5:29:15"}
|
||||
{"current_steps": 1570, "total_steps": 4214, "loss": 0.2654, "lr": 3.162934215297687e-05, "epoch": 2.60797342192691, "percentage": 37.26, "elapsed_time": "3:15:11", "remaining_time": "5:28:43"}
|
||||
{"current_steps": 1575, "total_steps": 4214, "loss": 0.2636, "lr": 3.156184000449697e-05, "epoch": 2.616279069767442, "percentage": 37.38, "elapsed_time": "3:15:50", "remaining_time": "5:28:09"}
|
||||
{"current_steps": 1580, "total_steps": 4214, "loss": 0.2738, "lr": 3.1494139461607214e-05, "epoch": 2.6245847176079735, "percentage": 37.49, "elapsed_time": "3:16:26", "remaining_time": "5:27:29"}
|
||||
{"current_steps": 1585, "total_steps": 4214, "loss": 0.2592, "lr": 3.142624168600931e-05, "epoch": 2.632890365448505, "percentage": 37.61, "elapsed_time": "3:17:04", "remaining_time": "5:26:53"}
|
||||
{"current_steps": 1590, "total_steps": 4214, "loss": 0.2567, "lr": 3.135814784278934e-05, "epoch": 2.6411960132890364, "percentage": 37.73, "elapsed_time": "3:17:42", "remaining_time": "5:26:17"}
|
||||
{"current_steps": 1595, "total_steps": 4214, "loss": 0.2699, "lr": 3.128985910039784e-05, "epoch": 2.649501661129568, "percentage": 37.85, "elapsed_time": "3:18:23", "remaining_time": "5:25:45"}
|
||||
{"current_steps": 1600, "total_steps": 4214, "loss": 0.2721, "lr": 3.122137663062966e-05, "epoch": 2.6578073089700998, "percentage": 37.97, "elapsed_time": "3:18:59", "remaining_time": "5:25:06"}
|
||||
{"current_steps": 1605, "total_steps": 4214, "loss": 0.2682, "lr": 3.115270160860392e-05, "epoch": 2.666112956810631, "percentage": 38.09, "elapsed_time": "3:19:35", "remaining_time": "5:24:26"}
|
||||
{"current_steps": 1505, "total_steps": 4214, "loss": 0.2583, "lr": 3.248829389986908e-05, "epoch": 2.5, "percentage": 35.71, "elapsed_time": "0:00:44", "remaining_time": "0:01:19"}
|
||||
{"current_steps": 1510, "total_steps": 4214, "loss": 0.2612, "lr": 3.2423475017649324e-05, "epoch": 2.5083056478405314, "percentage": 35.83, "elapsed_time": "0:01:27", "remaining_time": "0:02:36"}
|
||||
{"current_steps": 1515, "total_steps": 4214, "loss": 0.2619, "lr": 3.235844295586702e-05, "epoch": 2.516611295681063, "percentage": 35.95, "elapsed_time": "0:02:08", "remaining_time": "0:03:49"}
|
||||
{"current_steps": 1520, "total_steps": 4214, "loss": 0.2635, "lr": 3.229319883043428e-05, "epoch": 2.524916943521595, "percentage": 36.07, "elapsed_time": "0:02:46", "remaining_time": "0:04:55"}
|
||||
{"current_steps": 1525, "total_steps": 4214, "loss": 0.2823, "lr": 3.2227743760902125e-05, "epoch": 2.5332225913621262, "percentage": 36.19, "elapsed_time": "0:03:24", "remaining_time": "0:06:01"}
|
||||
{"current_steps": 1530, "total_steps": 4214, "loss": 0.2766, "lr": 3.2162078870441273e-05, "epoch": 2.5415282392026577, "percentage": 36.31, "elapsed_time": "0:04:02", "remaining_time": "0:07:05"}
|
||||
{"current_steps": 1535, "total_steps": 4214, "loss": 0.2451, "lr": 3.20962052858228e-05, "epoch": 2.5498338870431896, "percentage": 36.43, "elapsed_time": "0:04:39", "remaining_time": "0:08:07"}
|
||||
{"current_steps": 1540, "total_steps": 4214, "loss": 0.2571, "lr": 3.203012413739889e-05, "epoch": 2.558139534883721, "percentage": 36.54, "elapsed_time": "0:05:13", "remaining_time": "0:09:03"}
|
||||
{"current_steps": 1545, "total_steps": 4214, "loss": 0.2464, "lr": 3.196383655908338e-05, "epoch": 2.5664451827242525, "percentage": 36.66, "elapsed_time": "0:05:55", "remaining_time": "0:10:13"}
|
||||
{"current_steps": 1550, "total_steps": 4214, "loss": 0.2434, "lr": 3.1897343688332334e-05, "epoch": 2.574750830564784, "percentage": 36.78, "elapsed_time": "0:06:33", "remaining_time": "0:11:16"}
|
||||
{"current_steps": 1555, "total_steps": 4214, "loss": 0.2404, "lr": 3.183064666612451e-05, "epoch": 2.5830564784053154, "percentage": 36.9, "elapsed_time": "0:07:08", "remaining_time": "0:12:12"}
|
||||
{"current_steps": 1560, "total_steps": 4214, "loss": 0.2544, "lr": 3.176374663694179e-05, "epoch": 2.5913621262458473, "percentage": 37.02, "elapsed_time": "0:07:50", "remaining_time": "0:13:20"}
|
||||
{"current_steps": 1565, "total_steps": 4214, "loss": 0.2615, "lr": 3.169664474874953e-05, "epoch": 2.5996677740863787, "percentage": 37.14, "elapsed_time": "0:08:26", "remaining_time": "0:14:17"}
|
||||
{"current_steps": 1570, "total_steps": 4214, "loss": 0.2451, "lr": 3.162934215297687e-05, "epoch": 2.60797342192691, "percentage": 37.26, "elapsed_time": "0:09:05", "remaining_time": "0:15:18"}
|
||||
{"current_steps": 1575, "total_steps": 4214, "loss": 0.2659, "lr": 3.156184000449697e-05, "epoch": 2.616279069767442, "percentage": 37.38, "elapsed_time": "0:09:38", "remaining_time": "0:16:09"}
|
||||
{"current_steps": 1580, "total_steps": 4214, "loss": 0.2766, "lr": 3.1494139461607214e-05, "epoch": 2.6245847176079735, "percentage": 37.49, "elapsed_time": "0:10:16", "remaining_time": "0:17:07"}
|
||||
{"current_steps": 1585, "total_steps": 4214, "loss": 0.2802, "lr": 3.142624168600931e-05, "epoch": 2.632890365448505, "percentage": 37.61, "elapsed_time": "0:10:57", "remaining_time": "0:18:10"}
|
||||
{"current_steps": 1590, "total_steps": 4214, "loss": 0.2816, "lr": 3.135814784278934e-05, "epoch": 2.6411960132890364, "percentage": 37.73, "elapsed_time": "0:11:36", "remaining_time": "0:19:09"}
|
||||
{"current_steps": 1595, "total_steps": 4214, "loss": 0.2581, "lr": 3.128985910039784e-05, "epoch": 2.649501661129568, "percentage": 37.85, "elapsed_time": "0:12:13", "remaining_time": "0:20:04"}
|
||||
{"current_steps": 1600, "total_steps": 4214, "loss": 0.2515, "lr": 3.122137663062966e-05, "epoch": 2.6578073089700998, "percentage": 37.97, "elapsed_time": "0:12:56", "remaining_time": "0:21:08"}
|
||||
{"current_steps": 1605, "total_steps": 4214, "loss": 0.2586, "lr": 3.115270160860392e-05, "epoch": 2.666112956810631, "percentage": 38.09, "elapsed_time": "0:13:38", "remaining_time": "0:22:11"}
|
||||
{"current_steps": 1610, "total_steps": 4214, "loss": 0.255, "lr": 3.108383521274381e-05, "epoch": 2.6744186046511627, "percentage": 38.21, "elapsed_time": "0:14:18", "remaining_time": "0:23:08"}
|
||||
{"current_steps": 1615, "total_steps": 4214, "loss": 0.2514, "lr": 3.10147786247564e-05, "epoch": 2.6827242524916945, "percentage": 38.32, "elapsed_time": "0:14:55", "remaining_time": "0:24:00"}
|
||||
{"current_steps": 1620, "total_steps": 4214, "loss": 0.2508, "lr": 3.094553302961232e-05, "epoch": 2.691029900332226, "percentage": 38.44, "elapsed_time": "0:15:39", "remaining_time": "0:25:05"}
|
||||
{"current_steps": 1625, "total_steps": 4214, "loss": 0.2386, "lr": 3.087609961552549e-05, "epoch": 2.6993355481727574, "percentage": 38.56, "elapsed_time": "0:16:13", "remaining_time": "0:25:50"}
|
||||
{"current_steps": 1630, "total_steps": 4214, "loss": 0.2602, "lr": 3.080647957393266e-05, "epoch": 2.707641196013289, "percentage": 38.68, "elapsed_time": "0:16:48", "remaining_time": "0:26:38"}
|
||||
{"current_steps": 1635, "total_steps": 4214, "loss": 0.2632, "lr": 3.073667409947301e-05, "epoch": 2.7159468438538203, "percentage": 38.8, "elapsed_time": "0:17:27", "remaining_time": "0:27:32"}
|
||||
{"current_steps": 1640, "total_steps": 4214, "loss": 0.2625, "lr": 3.066668438996764e-05, "epoch": 2.7242524916943522, "percentage": 38.92, "elapsed_time": "0:18:05", "remaining_time": "0:28:23"}
|
||||
{"current_steps": 1645, "total_steps": 4214, "loss": 0.2565, "lr": 3.0596511646399005e-05, "epoch": 2.7325581395348837, "percentage": 39.04, "elapsed_time": "0:18:42", "remaining_time": "0:29:12"}
|
||||
{"current_steps": 1650, "total_steps": 4214, "loss": 0.2562, "lr": 3.052615707289035e-05, "epoch": 2.740863787375415, "percentage": 39.16, "elapsed_time": "0:19:19", "remaining_time": "0:30:02"}
|
||||
{"current_steps": 1655, "total_steps": 4214, "loss": 0.2744, "lr": 3.0455621876684987e-05, "epoch": 2.749169435215947, "percentage": 39.27, "elapsed_time": "0:20:02", "remaining_time": "0:31:00"}
|
||||
{"current_steps": 1660, "total_steps": 4214, "loss": 0.2315, "lr": 3.03849072681256e-05, "epoch": 2.7574750830564785, "percentage": 39.39, "elapsed_time": "0:20:38", "remaining_time": "0:31:45"}
|
||||
{"current_steps": 1665, "total_steps": 4214, "loss": 0.2484, "lr": 3.0314014460633515e-05, "epoch": 2.76578073089701, "percentage": 39.51, "elapsed_time": "0:21:16", "remaining_time": "0:32:34"}
|
||||
{"current_steps": 1670, "total_steps": 4214, "loss": 0.2632, "lr": 3.0242944670687825e-05, "epoch": 2.7740863787375414, "percentage": 39.63, "elapsed_time": "0:21:51", "remaining_time": "0:33:17"}
|
||||
{"current_steps": 1675, "total_steps": 4214, "loss": 0.2604, "lr": 3.017169911780453e-05, "epoch": 2.782392026578073, "percentage": 39.75, "elapsed_time": "0:22:28", "remaining_time": "0:34:03"}
|
||||
{"current_steps": 1680, "total_steps": 4214, "loss": 0.2446, "lr": 3.010027902451566e-05, "epoch": 2.7906976744186047, "percentage": 39.87, "elapsed_time": "0:23:06", "remaining_time": "0:34:50"}
|
||||
{"current_steps": 1685, "total_steps": 4214, "loss": 0.2693, "lr": 3.0028685616348205e-05, "epoch": 2.799003322259136, "percentage": 39.99, "elapsed_time": "0:23:48", "remaining_time": "0:35:43"}
|
||||
{"current_steps": 1690, "total_steps": 4214, "loss": 0.2499, "lr": 2.9956920121803174e-05, "epoch": 2.8073089700996676, "percentage": 40.1, "elapsed_time": "0:24:28", "remaining_time": "0:36:32"}
|
||||
{"current_steps": 1695, "total_steps": 4214, "loss": 0.2508, "lr": 2.988498377233446e-05, "epoch": 2.8156146179401995, "percentage": 40.22, "elapsed_time": "0:24:58", "remaining_time": "0:37:07"}
|
||||
{"current_steps": 1700, "total_steps": 4214, "loss": 0.2549, "lr": 2.981287780232774e-05, "epoch": 2.823920265780731, "percentage": 40.34, "elapsed_time": "0:25:41", "remaining_time": "0:38:00"}
|
||||
{"current_steps": 1705, "total_steps": 4214, "loss": 0.2436, "lr": 2.9740603449079253e-05, "epoch": 2.8322259136212624, "percentage": 40.46, "elapsed_time": "0:26:19", "remaining_time": "0:38:43"}
|
||||
{"current_steps": 1710, "total_steps": 4214, "loss": 0.2523, "lr": 2.966816195277463e-05, "epoch": 2.840531561461794, "percentage": 40.58, "elapsed_time": "0:26:57", "remaining_time": "0:39:28"}
|
||||
{"current_steps": 1715, "total_steps": 4214, "loss": 0.2562, "lr": 2.9595554556467557e-05, "epoch": 2.8488372093023253, "percentage": 40.7, "elapsed_time": "0:27:34", "remaining_time": "0:40:10"}
|
||||
{"current_steps": 1720, "total_steps": 4214, "loss": 0.2503, "lr": 2.952278250605847e-05, "epoch": 2.857142857142857, "percentage": 40.82, "elapsed_time": "0:28:08", "remaining_time": "0:40:48"}
|
||||
{"current_steps": 1725, "total_steps": 4214, "loss": 0.262, "lr": 2.9449847050273193e-05, "epoch": 2.8654485049833887, "percentage": 40.93, "elapsed_time": "0:28:48", "remaining_time": "0:41:33"}
|
||||
{"current_steps": 1730, "total_steps": 4214, "loss": 0.2555, "lr": 2.9376749440641457e-05, "epoch": 2.87375415282392, "percentage": 41.05, "elapsed_time": "0:29:24", "remaining_time": "0:42:13"}
|
||||
{"current_steps": 1735, "total_steps": 4214, "loss": 0.2493, "lr": 2.930349093147548e-05, "epoch": 2.882059800664452, "percentage": 41.17, "elapsed_time": "0:29:56", "remaining_time": "0:42:47"}
|
||||
{"current_steps": 1740, "total_steps": 4214, "loss": 0.2558, "lr": 2.9230072779848418e-05, "epoch": 2.8903654485049834, "percentage": 41.29, "elapsed_time": "0:30:30", "remaining_time": "0:43:22"}
|
||||
{"current_steps": 1745, "total_steps": 4214, "loss": 0.2634, "lr": 2.9156496245572802e-05, "epoch": 2.898671096345515, "percentage": 41.41, "elapsed_time": "0:31:07", "remaining_time": "0:44:02"}
|
||||
{"current_steps": 1750, "total_steps": 4214, "loss": 0.266, "lr": 2.90827625911789e-05, "epoch": 2.9069767441860463, "percentage": 41.53, "elapsed_time": "0:31:47", "remaining_time": "0:44:45"}
|
||||
{"current_steps": 1755, "total_steps": 4214, "loss": 0.2537, "lr": 2.9008873081893096e-05, "epoch": 2.915282392026578, "percentage": 41.65, "elapsed_time": "0:32:23", "remaining_time": "0:45:22"}
|
||||
{"current_steps": 1760, "total_steps": 4214, "loss": 0.2478, "lr": 2.8934828985616122e-05, "epoch": 2.9235880398671097, "percentage": 41.77, "elapsed_time": "0:33:01", "remaining_time": "0:46:02"}
|
||||
{"current_steps": 1765, "total_steps": 4214, "loss": 0.2539, "lr": 2.8860631572901367e-05, "epoch": 2.931893687707641, "percentage": 41.88, "elapsed_time": "0:33:42", "remaining_time": "0:46:46"}
|
||||
{"current_steps": 1770, "total_steps": 4214, "loss": 0.2523, "lr": 2.8786282116933003e-05, "epoch": 2.940199335548173, "percentage": 42.0, "elapsed_time": "0:34:24", "remaining_time": "0:47:30"}
|
||||
{"current_steps": 1775, "total_steps": 4214, "loss": 0.2697, "lr": 2.8711781893504204e-05, "epoch": 2.9485049833887045, "percentage": 42.12, "elapsed_time": "0:35:00", "remaining_time": "0:48:05"}
|
||||
{"current_steps": 1780, "total_steps": 4214, "loss": 0.2688, "lr": 2.8637132180995215e-05, "epoch": 2.956810631229236, "percentage": 42.24, "elapsed_time": "0:35:35", "remaining_time": "0:48:40"}
|
||||
{"current_steps": 1785, "total_steps": 4214, "loss": 0.2649, "lr": 2.8562334260351425e-05, "epoch": 2.9651162790697674, "percentage": 42.36, "elapsed_time": "0:36:18", "remaining_time": "0:49:24"}
|
||||
{"current_steps": 1790, "total_steps": 4214, "loss": 0.2467, "lr": 2.8487389415061392e-05, "epoch": 2.973421926910299, "percentage": 42.48, "elapsed_time": "0:36:56", "remaining_time": "0:50:01"}
|
||||
{"current_steps": 1795, "total_steps": 4214, "loss": 0.2707, "lr": 2.8412298931134805e-05, "epoch": 2.9817275747508307, "percentage": 42.6, "elapsed_time": "0:37:34", "remaining_time": "0:50:37"}
|
||||
{"current_steps": 1800, "total_steps": 4214, "loss": 0.255, "lr": 2.833706409708045e-05, "epoch": 2.990033222591362, "percentage": 42.71, "elapsed_time": "0:38:12", "remaining_time": "0:51:14"}
|
||||
{"current_steps": 1805, "total_steps": 4214, "loss": 0.2685, "lr": 2.8261686203884035e-05, "epoch": 2.9983388704318936, "percentage": 42.83, "elapsed_time": "0:38:51", "remaining_time": "0:51:51"}
|
||||
{"current_steps": 1810, "total_steps": 4214, "loss": 0.2552, "lr": 2.8186166544986123e-05, "epoch": 3.006644518272425, "percentage": 42.95, "elapsed_time": "0:39:28", "remaining_time": "0:52:26"}
|
||||
{"current_steps": 1815, "total_steps": 4214, "loss": 0.2578, "lr": 2.811050641625988e-05, "epoch": 3.014950166112957, "percentage": 43.07, "elapsed_time": "0:40:08", "remaining_time": "0:53:03"}
|
||||
{"current_steps": 1820, "total_steps": 4214, "loss": 0.244, "lr": 2.803470711598884e-05, "epoch": 3.0232558139534884, "percentage": 43.19, "elapsed_time": "0:40:45", "remaining_time": "0:53:37"}
|
||||
{"current_steps": 1825, "total_steps": 4214, "loss": 0.2673, "lr": 2.795876994484464e-05, "epoch": 3.03156146179402, "percentage": 43.31, "elapsed_time": "0:41:21", "remaining_time": "0:54:08"}
|
||||
{"current_steps": 1830, "total_steps": 4214, "loss": 0.2572, "lr": 2.788269620586472e-05, "epoch": 3.0398671096345513, "percentage": 43.43, "elapsed_time": "0:41:57", "remaining_time": "0:54:40"}
|
||||
{"current_steps": 1835, "total_steps": 4214, "loss": 0.2642, "lr": 2.780648720442992e-05, "epoch": 3.048172757475083, "percentage": 43.55, "elapsed_time": "0:42:37", "remaining_time": "0:55:15"}
|
||||
{"current_steps": 1840, "total_steps": 4214, "loss": 0.2557, "lr": 2.7730144248242132e-05, "epoch": 3.0564784053156147, "percentage": 43.66, "elapsed_time": "0:43:12", "remaining_time": "0:55:44"}
|
||||
{"current_steps": 1845, "total_steps": 4214, "loss": 0.2416, "lr": 2.7653668647301797e-05, "epoch": 3.064784053156146, "percentage": 43.78, "elapsed_time": "0:43:46", "remaining_time": "0:56:12"}
|
||||
{"current_steps": 1850, "total_steps": 4214, "loss": 0.287, "lr": 2.7577061713885494e-05, "epoch": 3.0730897009966776, "percentage": 43.9, "elapsed_time": "0:44:24", "remaining_time": "0:56:44"}
|
||||
{"current_steps": 1855, "total_steps": 4214, "loss": 0.2625, "lr": 2.7500324762523387e-05, "epoch": 3.0813953488372094, "percentage": 44.02, "elapsed_time": "0:45:02", "remaining_time": "0:57:16"}
|
||||
{"current_steps": 1860, "total_steps": 4214, "loss": 0.2692, "lr": 2.7423459109976648e-05, "epoch": 3.089700996677741, "percentage": 44.14, "elapsed_time": "0:45:39", "remaining_time": "0:57:46"}
|
||||
{"current_steps": 1865, "total_steps": 4214, "loss": 0.2351, "lr": 2.7346466075214917e-05, "epoch": 3.0980066445182723, "percentage": 44.26, "elapsed_time": "0:46:16", "remaining_time": "0:58:17"}
|
||||
{"current_steps": 1870, "total_steps": 4214, "loss": 0.2642, "lr": 2.7269346979393608e-05, "epoch": 3.106312292358804, "percentage": 44.38, "elapsed_time": "0:46:51", "remaining_time": "0:58:44"}
|
||||
{"current_steps": 1875, "total_steps": 4214, "loss": 0.2618, "lr": 2.71921031458313e-05, "epoch": 3.1146179401993357, "percentage": 44.49, "elapsed_time": "0:47:27", "remaining_time": "0:59:12"}
|
||||
{"current_steps": 1880, "total_steps": 4214, "loss": 0.2478, "lr": 2.7114735899986966e-05, "epoch": 3.122923588039867, "percentage": 44.61, "elapsed_time": "0:48:06", "remaining_time": "0:59:43"}
|
||||
{"current_steps": 1885, "total_steps": 4214, "loss": 0.2646, "lr": 2.7037246569437287e-05, "epoch": 3.1312292358803986, "percentage": 44.73, "elapsed_time": "0:48:42", "remaining_time": "1:00:11"}
|
||||
{"current_steps": 1890, "total_steps": 4214, "loss": 0.2459, "lr": 2.6959636483853843e-05, "epoch": 3.13953488372093, "percentage": 44.85, "elapsed_time": "0:49:22", "remaining_time": "1:00:42"}
|
||||
{"current_steps": 1895, "total_steps": 4214, "loss": 0.2435, "lr": 2.688190697498029e-05, "epoch": 3.147840531561462, "percentage": 44.97, "elapsed_time": "0:50:01", "remaining_time": "1:01:13"}
|
||||
{"current_steps": 1900, "total_steps": 4214, "loss": 0.2512, "lr": 2.680405937660952e-05, "epoch": 3.1561461794019934, "percentage": 45.09, "elapsed_time": "0:50:40", "remaining_time": "1:01:42"}
|
||||
{"current_steps": 1905, "total_steps": 4214, "loss": 0.2559, "lr": 2.6726095024560782e-05, "epoch": 3.164451827242525, "percentage": 45.21, "elapsed_time": "0:51:18", "remaining_time": "1:02:11"}
|
||||
{"current_steps": 1910, "total_steps": 4214, "loss": 0.2422, "lr": 2.6648015256656727e-05, "epoch": 3.1727574750830563, "percentage": 45.33, "elapsed_time": "0:51:49", "remaining_time": "1:02:30"}
|
||||
{"current_steps": 1915, "total_steps": 4214, "loss": 0.2506, "lr": 2.6569821412700498e-05, "epoch": 3.181063122923588, "percentage": 45.44, "elapsed_time": "0:52:33", "remaining_time": "1:03:05"}
|
||||
{"current_steps": 1920, "total_steps": 4214, "loss": 0.2498, "lr": 2.6491514834452713e-05, "epoch": 3.1893687707641196, "percentage": 45.56, "elapsed_time": "0:53:09", "remaining_time": "1:03:30"}
|
||||
{"current_steps": 1925, "total_steps": 4214, "loss": 0.242, "lr": 2.6413096865608426e-05, "epoch": 3.197674418604651, "percentage": 45.68, "elapsed_time": "0:53:47", "remaining_time": "1:03:58"}
|
||||
{"current_steps": 1930, "total_steps": 4214, "loss": 0.2546, "lr": 2.633456885177412e-05, "epoch": 3.2059800664451825, "percentage": 45.8, "elapsed_time": "0:54:26", "remaining_time": "1:04:25"}
|
||||
{"current_steps": 1935, "total_steps": 4214, "loss": 0.2497, "lr": 2.6255932140444546e-05, "epoch": 3.2142857142857144, "percentage": 45.92, "elapsed_time": "0:55:05", "remaining_time": "1:04:53"}
|
||||
{"current_steps": 1940, "total_steps": 4214, "loss": 0.2471, "lr": 2.6177188080979675e-05, "epoch": 3.222591362126246, "percentage": 46.04, "elapsed_time": "0:55:44", "remaining_time": "1:05:19"}
|
||||
{"current_steps": 1945, "total_steps": 4214, "loss": 0.2231, "lr": 2.609833802458149e-05, "epoch": 3.2308970099667773, "percentage": 46.16, "elapsed_time": "0:56:20", "remaining_time": "1:05:43"}
|
||||
{"current_steps": 1950, "total_steps": 4214, "loss": 0.2534, "lr": 2.601938332427083e-05, "epoch": 3.2392026578073088, "percentage": 46.27, "elapsed_time": "0:56:57", "remaining_time": "1:06:07"}
|
||||
{"current_steps": 1955, "total_steps": 4214, "loss": 0.2651, "lr": 2.594032533486415e-05, "epoch": 3.2475083056478407, "percentage": 46.39, "elapsed_time": "0:57:39", "remaining_time": "1:06:37"}
|
||||
{"current_steps": 1960, "total_steps": 4214, "loss": 0.2619, "lr": 2.58611654129503e-05, "epoch": 3.255813953488372, "percentage": 46.51, "elapsed_time": "0:58:14", "remaining_time": "1:06:58"}
|
||||
{"current_steps": 1965, "total_steps": 4214, "loss": 0.2426, "lr": 2.578190491686722e-05, "epoch": 3.2641196013289036, "percentage": 46.63, "elapsed_time": "0:58:53", "remaining_time": "1:07:24"}
|
||||
{"current_steps": 1970, "total_steps": 4214, "loss": 0.2687, "lr": 2.5702545206678658e-05, "epoch": 3.2724252491694354, "percentage": 46.75, "elapsed_time": "0:59:28", "remaining_time": "1:07:45"}
|
||||
{"current_steps": 1975, "total_steps": 4214, "loss": 0.2612, "lr": 2.5623087644150792e-05, "epoch": 3.280730897009967, "percentage": 46.87, "elapsed_time": "1:00:05", "remaining_time": "1:08:07"}
|
||||
{"current_steps": 1980, "total_steps": 4214, "loss": 0.265, "lr": 2.5543533592728924e-05, "epoch": 3.2890365448504983, "percentage": 46.99, "elapsed_time": "1:00:42", "remaining_time": "1:08:29"}
|
||||
{"current_steps": 1985, "total_steps": 4214, "loss": 0.2617, "lr": 2.5463884417514024e-05, "epoch": 3.29734219269103, "percentage": 47.1, "elapsed_time": "1:01:18", "remaining_time": "1:08:50"}
|
||||
{"current_steps": 1990, "total_steps": 4214, "loss": 0.2506, "lr": 2.538414148523933e-05, "epoch": 3.3056478405315612, "percentage": 47.22, "elapsed_time": "1:01:56", "remaining_time": "1:09:13"}
|
||||
{"current_steps": 1995, "total_steps": 4214, "loss": 0.2647, "lr": 2.5304306164246916e-05, "epoch": 3.313953488372093, "percentage": 47.34, "elapsed_time": "1:02:33", "remaining_time": "1:09:34"}
|
||||
{"current_steps": 2000, "total_steps": 4214, "loss": 0.2579, "lr": 2.522437982446417e-05, "epoch": 3.3222591362126246, "percentage": 47.46, "elapsed_time": "1:03:10", "remaining_time": "1:09:56"}
|
||||
{"current_steps": 2005, "total_steps": 4214, "loss": 0.2537, "lr": 2.5144363837380324e-05, "epoch": 3.330564784053156, "percentage": 47.58, "elapsed_time": "1:03:53", "remaining_time": "1:10:23"}
|
||||
{"current_steps": 2010, "total_steps": 4214, "loss": 0.2549, "lr": 2.5064259576022904e-05, "epoch": 3.338870431893688, "percentage": 47.7, "elapsed_time": "1:04:26", "remaining_time": "1:10:39"}
|
||||
{"current_steps": 2015, "total_steps": 4214, "loss": 0.266, "lr": 2.4984068414934162e-05, "epoch": 3.3471760797342194, "percentage": 47.82, "elapsed_time": "1:05:06", "remaining_time": "1:11:03"}
|
||||
{"current_steps": 2020, "total_steps": 4214, "loss": 0.2599, "lr": 2.4903791730147502e-05, "epoch": 3.355481727574751, "percentage": 47.94, "elapsed_time": "1:05:48", "remaining_time": "1:11:28"}
|
||||
{"current_steps": 2025, "total_steps": 4214, "loss": 0.2624, "lr": 2.4823430899163877e-05, "epoch": 3.3637873754152823, "percentage": 48.05, "elapsed_time": "1:06:25", "remaining_time": "1:11:48"}
|
||||
{"current_steps": 2030, "total_steps": 4214, "loss": 0.2546, "lr": 2.4742987300928114e-05, "epoch": 3.3720930232558137, "percentage": 48.17, "elapsed_time": "1:07:04", "remaining_time": "1:12:10"}
|
||||
{"current_steps": 2035, "total_steps": 4214, "loss": 0.2723, "lr": 2.46624623158053e-05, "epoch": 3.3803986710963456, "percentage": 48.29, "elapsed_time": "1:07:40", "remaining_time": "1:12:27"}
|
||||
{"current_steps": 2040, "total_steps": 4214, "loss": 0.2618, "lr": 2.458185732555707e-05, "epoch": 3.388704318936877, "percentage": 48.41, "elapsed_time": "1:08:18", "remaining_time": "1:12:47"}
|
||||
{"current_steps": 2045, "total_steps": 4214, "loss": 0.2363, "lr": 2.450117371331789e-05, "epoch": 3.3970099667774085, "percentage": 48.53, "elapsed_time": "1:08:53", "remaining_time": "1:13:04"}
|
||||
{"current_steps": 2050, "total_steps": 4214, "loss": 0.2657, "lr": 2.4420412863571347e-05, "epoch": 3.4053156146179404, "percentage": 48.65, "elapsed_time": "1:09:34", "remaining_time": "1:13:26"}
|
||||
{"current_steps": 2055, "total_steps": 4214, "loss": 0.2446, "lr": 2.4339576162126362e-05, "epoch": 3.413621262458472, "percentage": 48.77, "elapsed_time": "1:10:08", "remaining_time": "1:13:41"}
|
||||
{"current_steps": 2060, "total_steps": 4214, "loss": 0.2524, "lr": 2.4258664996093443e-05, "epoch": 3.4219269102990033, "percentage": 48.88, "elapsed_time": "1:10:40", "remaining_time": "1:13:53"}
|
||||
{"current_steps": 2065, "total_steps": 4214, "loss": 0.2793, "lr": 2.4177680753860857e-05, "epoch": 3.4302325581395348, "percentage": 49.0, "elapsed_time": "1:11:21", "remaining_time": "1:14:15"}
|
||||
{"current_steps": 2070, "total_steps": 4214, "loss": 0.2618, "lr": 2.4096624825070814e-05, "epoch": 3.438538205980066, "percentage": 49.12, "elapsed_time": "1:11:56", "remaining_time": "1:14:31"}
|
||||
{"current_steps": 2075, "total_steps": 4214, "loss": 0.2438, "lr": 2.4015498600595635e-05, "epoch": 3.446843853820598, "percentage": 49.24, "elapsed_time": "1:12:35", "remaining_time": "1:14:49"}
|
||||
{"current_steps": 2080, "total_steps": 4214, "loss": 0.2619, "lr": 2.3934303472513864e-05, "epoch": 3.4551495016611296, "percentage": 49.36, "elapsed_time": "1:13:17", "remaining_time": "1:15:12"}
|
||||
{"current_steps": 2085, "total_steps": 4214, "loss": 0.2566, "lr": 2.385304083408639e-05, "epoch": 3.463455149501661, "percentage": 49.48, "elapsed_time": "1:13:57", "remaining_time": "1:15:30"}
|
||||
{"current_steps": 2090, "total_steps": 4214, "loss": 0.2462, "lr": 2.377171207973255e-05, "epoch": 3.471760797342193, "percentage": 49.6, "elapsed_time": "1:14:36", "remaining_time": "1:15:49"}
|
||||
{"current_steps": 2095, "total_steps": 4214, "loss": 0.2533, "lr": 2.3690318605006173e-05, "epoch": 3.4800664451827243, "percentage": 49.72, "elapsed_time": "1:15:17", "remaining_time": "1:16:09"}
|
||||
{"current_steps": 2100, "total_steps": 4214, "loss": 0.2693, "lr": 2.3608861806571674e-05, "epoch": 3.488372093023256, "percentage": 49.83, "elapsed_time": "1:15:52", "remaining_time": "1:16:23"}
|
||||
{"current_steps": 2105, "total_steps": 4214, "loss": 0.2368, "lr": 2.3527343082180053e-05, "epoch": 3.4966777408637872, "percentage": 49.95, "elapsed_time": "1:16:28", "remaining_time": "1:16:36"}
|
||||
{"current_steps": 2110, "total_steps": 4214, "loss": 0.2538, "lr": 2.3445763830644924e-05, "epoch": 3.5049833887043187, "percentage": 50.07, "elapsed_time": "1:17:03", "remaining_time": "1:16:50"}
|
||||
{"current_steps": 2115, "total_steps": 4214, "loss": 0.2483, "lr": 2.3364125451818515e-05, "epoch": 3.5132890365448506, "percentage": 50.19, "elapsed_time": "1:17:37", "remaining_time": "1:17:02"}
|
||||
{"current_steps": 2120, "total_steps": 4214, "loss": 0.2496, "lr": 2.3282429346567635e-05, "epoch": 3.521594684385382, "percentage": 50.31, "elapsed_time": "1:18:12", "remaining_time": "1:17:14"}
|
||||
{"current_steps": 2125, "total_steps": 4214, "loss": 0.2599, "lr": 2.3200676916749658e-05, "epoch": 3.5299003322259135, "percentage": 50.43, "elapsed_time": "1:18:53", "remaining_time": "1:17:32"}
|
||||
{"current_steps": 2130, "total_steps": 4214, "loss": 0.2786, "lr": 2.3118869565188448e-05, "epoch": 3.5382059800664454, "percentage": 50.55, "elapsed_time": "1:19:35", "remaining_time": "1:17:52"}
|
||||
{"current_steps": 2135, "total_steps": 4214, "loss": 0.271, "lr": 2.3037008695650292e-05, "epoch": 3.546511627906977, "percentage": 50.66, "elapsed_time": "1:20:16", "remaining_time": "1:18:10"}
|
||||
{"current_steps": 2140, "total_steps": 4214, "loss": 0.2557, "lr": 2.295509571281981e-05, "epoch": 3.5548172757475083, "percentage": 50.78, "elapsed_time": "1:20:51", "remaining_time": "1:18:21"}
|
||||
{"current_steps": 2145, "total_steps": 4214, "loss": 0.253, "lr": 2.287313202227588e-05, "epoch": 3.5631229235880397, "percentage": 50.9, "elapsed_time": "1:21:34", "remaining_time": "1:18:41"}
|
||||
{"current_steps": 2150, "total_steps": 4214, "loss": 0.2475, "lr": 2.279111903046745e-05, "epoch": 3.571428571428571, "percentage": 51.02, "elapsed_time": "1:22:17", "remaining_time": "1:18:59"}
|
||||
{"current_steps": 2155, "total_steps": 4214, "loss": 0.2388, "lr": 2.2709058144689498e-05, "epoch": 3.579734219269103, "percentage": 51.14, "elapsed_time": "1:22:58", "remaining_time": "1:19:16"}
|
||||
{"current_steps": 2160, "total_steps": 4214, "loss": 0.2581, "lr": 2.26269507730588e-05, "epoch": 3.5880398671096345, "percentage": 51.26, "elapsed_time": "1:23:37", "remaining_time": "1:19:30"}
|
||||
{"current_steps": 2165, "total_steps": 4214, "loss": 0.2764, "lr": 2.2544798324489814e-05, "epoch": 3.596345514950166, "percentage": 51.38, "elapsed_time": "1:24:16", "remaining_time": "1:19:45"}
|
||||
{"current_steps": 2170, "total_steps": 4214, "loss": 0.2541, "lr": 2.2462602208670496e-05, "epoch": 3.604651162790698, "percentage": 51.5, "elapsed_time": "1:24:54", "remaining_time": "1:19:58"}
|
||||
{"current_steps": 2175, "total_steps": 4214, "loss": 0.2677, "lr": 2.23803638360381e-05, "epoch": 3.6129568106312293, "percentage": 51.61, "elapsed_time": "1:25:34", "remaining_time": "1:20:13"}
|
||||
{"current_steps": 2180, "total_steps": 4214, "loss": 0.2391, "lr": 2.229808461775498e-05, "epoch": 3.6212624584717608, "percentage": 51.73, "elapsed_time": "1:26:09", "remaining_time": "1:20:23"}
|
||||
{"current_steps": 2185, "total_steps": 4214, "loss": 0.2525, "lr": 2.221576596568439e-05, "epoch": 3.629568106312292, "percentage": 51.85, "elapsed_time": "1:26:49", "remaining_time": "1:20:37"}
|
||||
{"current_steps": 2190, "total_steps": 4214, "loss": 0.2594, "lr": 2.2133409292366234e-05, "epoch": 3.6378737541528237, "percentage": 51.97, "elapsed_time": "1:27:28", "remaining_time": "1:20:50"}
|
||||
{"current_steps": 2195, "total_steps": 4214, "loss": 0.242, "lr": 2.2051016010992834e-05, "epoch": 3.6461794019933556, "percentage": 52.09, "elapsed_time": "1:28:00", "remaining_time": "1:20:56"}
|
||||
{"current_steps": 2200, "total_steps": 4214, "loss": 0.2728, "lr": 2.1968587535384697e-05, "epoch": 3.654485049833887, "percentage": 52.21, "elapsed_time": "1:28:36", "remaining_time": "1:21:07"}
|
||||
{"current_steps": 2205, "total_steps": 4214, "loss": 0.252, "lr": 2.1886125279966238e-05, "epoch": 3.6627906976744184, "percentage": 52.33, "elapsed_time": "1:29:14", "remaining_time": "1:21:18"}
|
||||
{"current_steps": 2210, "total_steps": 4214, "loss": 0.2358, "lr": 2.1803630659741516e-05, "epoch": 3.6710963455149503, "percentage": 52.44, "elapsed_time": "1:29:50", "remaining_time": "1:21:27"}
|
||||
{"current_steps": 2215, "total_steps": 4214, "loss": 0.242, "lr": 2.172110509026994e-05, "epoch": 3.679401993355482, "percentage": 52.56, "elapsed_time": "1:30:26", "remaining_time": "1:21:37"}
|
||||
{"current_steps": 2220, "total_steps": 4214, "loss": 0.2298, "lr": 2.1638549987641996e-05, "epoch": 3.6877076411960132, "percentage": 52.68, "elapsed_time": "1:31:00", "remaining_time": "1:21:44"}
|
||||
{"current_steps": 2225, "total_steps": 4214, "loss": 0.2346, "lr": 2.155596676845496e-05, "epoch": 3.6960132890365447, "percentage": 52.8, "elapsed_time": "1:31:33", "remaining_time": "1:21:50"}
|
||||
{"current_steps": 2230, "total_steps": 4214, "loss": 0.2551, "lr": 2.1473356849788538e-05, "epoch": 3.704318936877076, "percentage": 52.92, "elapsed_time": "1:32:16", "remaining_time": "1:22:05"}
|
||||
{"current_steps": 2235, "total_steps": 4214, "loss": 0.2622, "lr": 2.139072164918061e-05, "epoch": 3.712624584717608, "percentage": 53.04, "elapsed_time": "1:32:54", "remaining_time": "1:22:16"}
|
||||
{"current_steps": 2240, "total_steps": 4214, "loss": 0.2674, "lr": 2.1308062584602865e-05, "epoch": 3.7209302325581395, "percentage": 53.16, "elapsed_time": "1:33:30", "remaining_time": "1:22:24"}
|
||||
{"current_steps": 2245, "total_steps": 4214, "loss": 0.2674, "lr": 2.1225381074436493e-05, "epoch": 3.729235880398671, "percentage": 53.27, "elapsed_time": "1:34:07", "remaining_time": "1:22:32"}
|
||||
{"current_steps": 2250, "total_steps": 4214, "loss": 0.2556, "lr": 2.114267853744783e-05, "epoch": 3.737541528239203, "percentage": 53.39, "elapsed_time": "1:34:45", "remaining_time": "1:22:42"}
|
||||
{"current_steps": 2255, "total_steps": 4214, "loss": 0.2435, "lr": 2.1059956392764022e-05, "epoch": 3.7458471760797343, "percentage": 53.51, "elapsed_time": "1:35:26", "remaining_time": "1:22:55"}
|
||||
{"current_steps": 2260, "total_steps": 4214, "loss": 0.2439, "lr": 2.097721605984868e-05, "epoch": 3.7541528239202657, "percentage": 53.63, "elapsed_time": "1:36:00", "remaining_time": "1:23:00"}
|
||||
{"current_steps": 2265, "total_steps": 4214, "loss": 0.2592, "lr": 2.08944589584775e-05, "epoch": 3.762458471760797, "percentage": 53.75, "elapsed_time": "1:36:37", "remaining_time": "1:23:09"}
|
||||
{"current_steps": 2270, "total_steps": 4214, "loss": 0.2402, "lr": 2.0811686508713918e-05, "epoch": 3.770764119601329, "percentage": 53.87, "elapsed_time": "1:37:14", "remaining_time": "1:23:16"}
|
||||
{"current_steps": 2275, "total_steps": 4214, "loss": 0.2263, "lr": 2.0728900130884755e-05, "epoch": 3.7790697674418605, "percentage": 53.99, "elapsed_time": "1:37:50", "remaining_time": "1:23:23"}
|
||||
{"current_steps": 2280, "total_steps": 4214, "loss": 0.2583, "lr": 2.0646101245555812e-05, "epoch": 3.787375415282392, "percentage": 54.11, "elapsed_time": "1:38:26", "remaining_time": "1:23:30"}
|
||||
{"current_steps": 2285, "total_steps": 4214, "loss": 0.2637, "lr": 2.0563291273507517e-05, "epoch": 3.795681063122924, "percentage": 54.22, "elapsed_time": "1:39:06", "remaining_time": "1:23:39"}
|
||||
{"current_steps": 2290, "total_steps": 4214, "loss": 0.2478, "lr": 2.0480471635710538e-05, "epoch": 3.8039867109634553, "percentage": 54.34, "elapsed_time": "1:39:44", "remaining_time": "1:23:48"}
|
||||
{"current_steps": 2295, "total_steps": 4214, "loss": 0.265, "lr": 2.0397643753301403e-05, "epoch": 3.8122923588039868, "percentage": 54.46, "elapsed_time": "1:40:26", "remaining_time": "1:23:58"}
|
||||
{"current_steps": 2300, "total_steps": 4214, "loss": 0.2582, "lr": 2.031480904755812e-05, "epoch": 3.820598006644518, "percentage": 54.58, "elapsed_time": "1:41:01", "remaining_time": "1:24:03"}
|
||||
{"current_steps": 2305, "total_steps": 4214, "loss": 0.2554, "lr": 2.0231968939875766e-05, "epoch": 3.8289036544850497, "percentage": 54.7, "elapsed_time": "1:41:42", "remaining_time": "1:24:14"}
|
||||
{"current_steps": 2310, "total_steps": 4214, "loss": 0.2305, "lr": 2.014912485174213e-05, "epoch": 3.8372093023255816, "percentage": 54.82, "elapsed_time": "1:42:16", "remaining_time": "1:24:17"}
|
||||
{"current_steps": 2315, "total_steps": 4214, "loss": 0.259, "lr": 2.0066278204713282e-05, "epoch": 3.845514950166113, "percentage": 54.94, "elapsed_time": "1:42:58", "remaining_time": "1:24:28"}
|
||||
{"current_steps": 2320, "total_steps": 4214, "loss": 0.2644, "lr": 1.9983430420389222e-05, "epoch": 3.8538205980066444, "percentage": 55.05, "elapsed_time": "1:43:30", "remaining_time": "1:24:30"}
|
||||
{"current_steps": 2325, "total_steps": 4214, "loss": 0.265, "lr": 1.9900582920389458e-05, "epoch": 3.8621262458471763, "percentage": 55.17, "elapsed_time": "1:44:08", "remaining_time": "1:24:36"}
|
||||
{"current_steps": 2330, "total_steps": 4214, "loss": 0.2457, "lr": 1.981773712632861e-05, "epoch": 3.870431893687708, "percentage": 55.29, "elapsed_time": "1:44:48", "remaining_time": "1:24:44"}
|
||||
{"current_steps": 2335, "total_steps": 4214, "loss": 0.2343, "lr": 1.973489445979204e-05, "epoch": 3.8787375415282392, "percentage": 55.41, "elapsed_time": "1:45:22", "remaining_time": "1:24:47"}
|
||||
{"current_steps": 2340, "total_steps": 4214, "loss": 0.2455, "lr": 1.965205634231142e-05, "epoch": 3.8870431893687707, "percentage": 55.53, "elapsed_time": "1:45:54", "remaining_time": "1:24:49"}
|
||||
{"current_steps": 2345, "total_steps": 4214, "loss": 0.2563, "lr": 1.95692241953404e-05, "epoch": 3.895348837209302, "percentage": 55.65, "elapsed_time": "1:46:30", "remaining_time": "1:24:53"}
|
||||
{"current_steps": 2350, "total_steps": 4214, "loss": 0.2643, "lr": 1.9486399440230142e-05, "epoch": 3.903654485049834, "percentage": 55.77, "elapsed_time": "1:47:09", "remaining_time": "1:25:00"}
|
||||
{"current_steps": 2355, "total_steps": 4214, "loss": 0.2252, "lr": 1.940358349820499e-05, "epoch": 3.9119601328903655, "percentage": 55.89, "elapsed_time": "1:47:42", "remaining_time": "1:25:01"}
|
||||
{"current_steps": 2360, "total_steps": 4214, "loss": 0.2562, "lr": 1.9320777790338068e-05, "epoch": 3.920265780730897, "percentage": 56.0, "elapsed_time": "1:48:17", "remaining_time": "1:25:04"}
|
||||
{"current_steps": 2365, "total_steps": 4214, "loss": 0.2414, "lr": 1.9237983737526855e-05, "epoch": 3.928571428571429, "percentage": 56.12, "elapsed_time": "1:48:52", "remaining_time": "1:25:07"}
|
||||
{"current_steps": 2370, "total_steps": 4214, "loss": 0.2414, "lr": 1.9155202760468868e-05, "epoch": 3.9368770764119603, "percentage": 56.24, "elapsed_time": "1:49:26", "remaining_time": "1:25:09"}
|
||||
{"current_steps": 2375, "total_steps": 4214, "loss": 0.2575, "lr": 1.907243627963723e-05, "epoch": 3.9451827242524917, "percentage": 56.36, "elapsed_time": "1:50:06", "remaining_time": "1:25:15"}
|
||||
{"current_steps": 2380, "total_steps": 4214, "loss": 0.2966, "lr": 1.898968571525634e-05, "epoch": 3.953488372093023, "percentage": 56.48, "elapsed_time": "1:50:47", "remaining_time": "1:25:22"}
|
||||
{"current_steps": 2385, "total_steps": 4214, "loss": 0.2584, "lr": 1.890695248727746e-05, "epoch": 3.9617940199335546, "percentage": 56.6, "elapsed_time": "1:51:26", "remaining_time": "1:25:27"}
|
||||
{"current_steps": 2390, "total_steps": 4214, "loss": 0.2479, "lr": 1.882423801535438e-05, "epoch": 3.9700996677740865, "percentage": 56.72, "elapsed_time": "1:52:01", "remaining_time": "1:25:30"}
|
||||
{"current_steps": 2395, "total_steps": 4214, "loss": 0.251, "lr": 1.8741543718819028e-05, "epoch": 3.978405315614618, "percentage": 56.83, "elapsed_time": "1:52:40", "remaining_time": "1:25:34"}
|
||||
{"current_steps": 2400, "total_steps": 4214, "loss": 0.2429, "lr": 1.8658871016657173e-05, "epoch": 3.9867109634551494, "percentage": 56.95, "elapsed_time": "1:53:18", "remaining_time": "1:25:38"}
|
||||
{"current_steps": 2405, "total_steps": 4214, "loss": 0.2748, "lr": 1.8576221327484002e-05, "epoch": 3.9950166112956813, "percentage": 57.07, "elapsed_time": "1:53:59", "remaining_time": "1:25:44"}
|
||||
{"current_steps": 2410, "total_steps": 4214, "loss": 0.2367, "lr": 1.8493596069519813e-05, "epoch": 4.003322259136213, "percentage": 57.19, "elapsed_time": "1:54:33", "remaining_time": "1:25:45"}
|
||||
{"current_steps": 2415, "total_steps": 4214, "loss": 0.2538, "lr": 1.8410996660565714e-05, "epoch": 4.011627906976744, "percentage": 57.31, "elapsed_time": "1:55:14", "remaining_time": "1:25:51"}
|
||||
{"current_steps": 2420, "total_steps": 4214, "loss": 0.2423, "lr": 1.8328424517979222e-05, "epoch": 4.019933554817276, "percentage": 57.43, "elapsed_time": "1:55:52", "remaining_time": "1:25:54"}
|
||||
{"current_steps": 2425, "total_steps": 4214, "loss": 0.2408, "lr": 1.8245881058649993e-05, "epoch": 4.028239202657807, "percentage": 57.55, "elapsed_time": "1:56:26", "remaining_time": "1:25:54"}
|
||||
{"current_steps": 2430, "total_steps": 4214, "loss": 0.2335, "lr": 1.816336769897549e-05, "epoch": 4.0365448504983386, "percentage": 57.66, "elapsed_time": "1:57:00", "remaining_time": "1:25:54"}
|
||||
{"current_steps": 2435, "total_steps": 4214, "loss": 0.2614, "lr": 1.80808858548367e-05, "epoch": 4.04485049833887, "percentage": 57.78, "elapsed_time": "1:57:41", "remaining_time": "1:25:58"}
|
||||
{"current_steps": 2440, "total_steps": 4214, "loss": 0.2398, "lr": 1.79984369415738e-05, "epoch": 4.053156146179402, "percentage": 57.9, "elapsed_time": "1:58:22", "remaining_time": "1:26:03"}
|
||||
{"current_steps": 2445, "total_steps": 4214, "loss": 0.2347, "lr": 1.7916022373961908e-05, "epoch": 4.061461794019934, "percentage": 58.02, "elapsed_time": "1:58:57", "remaining_time": "1:26:04"}
|
||||
{"current_steps": 2450, "total_steps": 4214, "loss": 0.2678, "lr": 1.7833643566186772e-05, "epoch": 4.069767441860465, "percentage": 58.14, "elapsed_time": "1:59:36", "remaining_time": "1:26:07"}
|
||||
{"current_steps": 2455, "total_steps": 4214, "loss": 0.2606, "lr": 1.775130193182056e-05, "epoch": 4.078073089700997, "percentage": 58.26, "elapsed_time": "2:00:13", "remaining_time": "1:26:08"}
|
||||
{"current_steps": 2460, "total_steps": 4214, "loss": 0.2508, "lr": 1.7668998883797522e-05, "epoch": 4.086378737541528, "percentage": 58.38, "elapsed_time": "2:00:47", "remaining_time": "1:26:07"}
|
||||
{"current_steps": 2465, "total_steps": 4214, "loss": 0.2549, "lr": 1.7586735834389813e-05, "epoch": 4.09468438538206, "percentage": 58.5, "elapsed_time": "2:01:27", "remaining_time": "1:26:11"}
|
||||
{"current_steps": 2470, "total_steps": 4214, "loss": 0.2455, "lr": 1.750451419518322e-05, "epoch": 4.102990033222591, "percentage": 58.61, "elapsed_time": "2:02:09", "remaining_time": "1:26:15"}
|
||||
{"current_steps": 2475, "total_steps": 4214, "loss": 0.2493, "lr": 1.742233537705299e-05, "epoch": 4.1112956810631225, "percentage": 58.73, "elapsed_time": "2:02:51", "remaining_time": "1:26:19"}
|
||||
{"current_steps": 2480, "total_steps": 4214, "loss": 0.2395, "lr": 1.734020079013954e-05, "epoch": 4.119601328903655, "percentage": 58.85, "elapsed_time": "2:03:26", "remaining_time": "1:26:18"}
|
||||
{"current_steps": 2485, "total_steps": 4214, "loss": 0.2673, "lr": 1.725811184382433e-05, "epoch": 4.127906976744186, "percentage": 58.97, "elapsed_time": "2:04:07", "remaining_time": "1:26:21"}
|
||||
{"current_steps": 2490, "total_steps": 4214, "loss": 0.2426, "lr": 1.7176069946705654e-05, "epoch": 4.136212624584718, "percentage": 59.09, "elapsed_time": "2:04:40", "remaining_time": "1:26:19"}
|
||||
{"current_steps": 2495, "total_steps": 4214, "loss": 0.2249, "lr": 1.7094076506574465e-05, "epoch": 4.144518272425249, "percentage": 59.21, "elapsed_time": "2:05:14", "remaining_time": "1:26:17"}
|
||||
{"current_steps": 2500, "total_steps": 4214, "loss": 0.2338, "lr": 1.7012132930390225e-05, "epoch": 4.152823920265781, "percentage": 59.33, "elapsed_time": "2:05:48", "remaining_time": "1:26:15"}
|
||||
{"current_steps": 2505, "total_steps": 4214, "loss": 0.2568, "lr": 1.6930240624256742e-05, "epoch": 4.161129568106312, "percentage": 59.44, "elapsed_time": "2:06:28", "remaining_time": "1:26:16"}
|
||||
{"current_steps": 2510, "total_steps": 4214, "loss": 0.2329, "lr": 1.68484009933981e-05, "epoch": 4.1694352159468435, "percentage": 59.56, "elapsed_time": "2:07:04", "remaining_time": "1:26:16"}
|
||||
{"current_steps": 2515, "total_steps": 4214, "loss": 0.2476, "lr": 1.6766615442134462e-05, "epoch": 4.177740863787376, "percentage": 59.68, "elapsed_time": "2:07:41", "remaining_time": "1:26:15"}
|
||||
{"current_steps": 2520, "total_steps": 4214, "loss": 0.2342, "lr": 1.6684885373858048e-05, "epoch": 4.186046511627907, "percentage": 59.8, "elapsed_time": "2:08:15", "remaining_time": "1:26:13"}
|
||||
{"current_steps": 2525, "total_steps": 4214, "loss": 0.2666, "lr": 1.6603212191009003e-05, "epoch": 4.194352159468439, "percentage": 59.92, "elapsed_time": "2:08:51", "remaining_time": "1:26:11"}
|
||||
{"current_steps": 2530, "total_steps": 4214, "loss": 0.2426, "lr": 1.6521597295051367e-05, "epoch": 4.20265780730897, "percentage": 60.04, "elapsed_time": "2:09:27", "remaining_time": "1:26:10"}
|
||||
{"current_steps": 2535, "total_steps": 4214, "loss": 0.2458, "lr": 1.6440042086449e-05, "epoch": 4.210963455149502, "percentage": 60.16, "elapsed_time": "2:10:03", "remaining_time": "1:26:08"}
|
||||
{"current_steps": 2540, "total_steps": 4214, "loss": 0.2379, "lr": 1.6358547964641556e-05, "epoch": 4.219269102990033, "percentage": 60.28, "elapsed_time": "2:10:39", "remaining_time": "1:26:06"}
|
||||
{"current_steps": 2545, "total_steps": 4214, "loss": 0.2419, "lr": 1.6277116328020503e-05, "epoch": 4.2275747508305646, "percentage": 60.39, "elapsed_time": "2:11:12", "remaining_time": "1:26:02"}
|
||||
{"current_steps": 2550, "total_steps": 4214, "loss": 0.2369, "lr": 1.619574857390507e-05, "epoch": 4.235880398671096, "percentage": 60.51, "elapsed_time": "2:11:46", "remaining_time": "1:25:59"}
|
||||
{"current_steps": 2555, "total_steps": 4214, "loss": 0.2433, "lr": 1.611444609851831e-05, "epoch": 4.2441860465116275, "percentage": 60.63, "elapsed_time": "2:12:26", "remaining_time": "1:25:59"}
|
||||
{"current_steps": 2560, "total_steps": 4214, "loss": 0.2112, "lr": 1.603321029696313e-05, "epoch": 4.25249169435216, "percentage": 60.75, "elapsed_time": "2:13:02", "remaining_time": "1:25:57"}
|
||||
{"current_steps": 2565, "total_steps": 4214, "loss": 0.2588, "lr": 1.5952042563198364e-05, "epoch": 4.260797342192691, "percentage": 60.87, "elapsed_time": "2:13:45", "remaining_time": "1:25:59"}
|
||||
{"current_steps": 2570, "total_steps": 4214, "loss": 0.2444, "lr": 1.5870944290014833e-05, "epoch": 4.269102990033223, "percentage": 60.99, "elapsed_time": "2:14:20", "remaining_time": "1:25:56"}
|
||||
{"current_steps": 2575, "total_steps": 4214, "loss": 0.2212, "lr": 1.578991686901145e-05, "epoch": 4.277408637873754, "percentage": 61.11, "elapsed_time": "2:14:55", "remaining_time": "1:25:52"}
|
||||
{"current_steps": 2580, "total_steps": 4214, "loss": 0.2168, "lr": 1.5708961690571344e-05, "epoch": 4.285714285714286, "percentage": 61.22, "elapsed_time": "2:15:30", "remaining_time": "1:25:49"}
|
||||
{"current_steps": 2585, "total_steps": 4214, "loss": 0.2501, "lr": 1.562808014383803e-05, "epoch": 4.294019933554817, "percentage": 61.34, "elapsed_time": "2:16:05", "remaining_time": "1:25:45"}
|
||||
{"current_steps": 2590, "total_steps": 4214, "loss": 0.2436, "lr": 1.5547273616691515e-05, "epoch": 4.3023255813953485, "percentage": 61.46, "elapsed_time": "2:16:44", "remaining_time": "1:25:44"}
|
||||
{"current_steps": 2595, "total_steps": 4214, "loss": 0.2076, "lr": 1.546654349572453e-05, "epoch": 4.310631229235881, "percentage": 61.58, "elapsed_time": "2:17:19", "remaining_time": "1:25:40"}
|
||||
{"current_steps": 2600, "total_steps": 4214, "loss": 0.2432, "lr": 1.5385891166218723e-05, "epoch": 4.318936877076412, "percentage": 61.7, "elapsed_time": "2:17:59", "remaining_time": "1:25:39"}
|
||||
{"current_steps": 2605, "total_steps": 4214, "loss": 0.2439, "lr": 1.5305318012120872e-05, "epoch": 4.327242524916944, "percentage": 61.82, "elapsed_time": "2:18:38", "remaining_time": "1:25:37"}
|
||||
{"current_steps": 2610, "total_steps": 4214, "loss": 0.2386, "lr": 1.5224825416019165e-05, "epoch": 4.335548172757475, "percentage": 61.94, "elapsed_time": "2:19:16", "remaining_time": "1:25:35"}
|
||||
{"current_steps": 2615, "total_steps": 4214, "loss": 0.2265, "lr": 1.5144414759119444e-05, "epoch": 4.343853820598007, "percentage": 62.06, "elapsed_time": "2:19:50", "remaining_time": "1:25:30"}
|
||||
{"current_steps": 2620, "total_steps": 4214, "loss": 0.2381, "lr": 1.5064087421221551e-05, "epoch": 4.352159468438538, "percentage": 62.17, "elapsed_time": "2:20:23", "remaining_time": "1:25:24"}
|
||||
{"current_steps": 2625, "total_steps": 4214, "loss": 0.239, "lr": 1.4983844780695603e-05, "epoch": 4.3604651162790695, "percentage": 62.29, "elapsed_time": "2:21:05", "remaining_time": "1:25:24"}
|
||||
{"current_steps": 2630, "total_steps": 4214, "loss": 0.249, "lr": 1.4903688214458356e-05, "epoch": 4.368770764119601, "percentage": 62.41, "elapsed_time": "2:21:41", "remaining_time": "1:25:20"}
|
||||
{"current_steps": 2635, "total_steps": 4214, "loss": 0.2382, "lr": 1.4823619097949584e-05, "epoch": 4.377076411960133, "percentage": 62.53, "elapsed_time": "2:22:21", "remaining_time": "1:25:18"}
|
||||
{"current_steps": 2640, "total_steps": 4214, "loss": 0.2392, "lr": 1.4743638805108495e-05, "epoch": 4.385382059800665, "percentage": 62.65, "elapsed_time": "2:23:00", "remaining_time": "1:25:15"}
|
||||
{"current_steps": 2645, "total_steps": 4214, "loss": 0.2469, "lr": 1.4663748708350114e-05, "epoch": 4.393687707641196, "percentage": 62.77, "elapsed_time": "2:23:40", "remaining_time": "1:25:13"}
|
||||
{"current_steps": 2650, "total_steps": 4214, "loss": 0.2577, "lr": 1.4583950178541755e-05, "epoch": 4.401993355481728, "percentage": 62.89, "elapsed_time": "2:24:19", "remaining_time": "1:25:10"}
|
||||
{"current_steps": 2655, "total_steps": 4214, "loss": 0.2588, "lr": 1.4504244584979494e-05, "epoch": 4.410299003322259, "percentage": 63.0, "elapsed_time": "2:24:55", "remaining_time": "1:25:05"}
|
||||
{"current_steps": 2660, "total_steps": 4214, "loss": 0.2321, "lr": 1.4424633295364701e-05, "epoch": 4.4186046511627906, "percentage": 63.12, "elapsed_time": "2:25:30", "remaining_time": "1:25:00"}
|
||||
{"current_steps": 2665, "total_steps": 4214, "loss": 0.2515, "lr": 1.4345117675780511e-05, "epoch": 4.426910299003322, "percentage": 63.24, "elapsed_time": "2:26:09", "remaining_time": "1:24:57"}
|
||||
{"current_steps": 2670, "total_steps": 4214, "loss": 0.2611, "lr": 1.4265699090668436e-05, "epoch": 4.4352159468438535, "percentage": 63.36, "elapsed_time": "2:26:50", "remaining_time": "1:24:55"}
|
||||
{"current_steps": 2675, "total_steps": 4214, "loss": 0.2474, "lr": 1.4186378902804939e-05, "epoch": 4.443521594684386, "percentage": 63.48, "elapsed_time": "2:27:27", "remaining_time": "1:24:50"}
|
||||
{"current_steps": 2680, "total_steps": 4214, "loss": 0.2252, "lr": 1.4107158473278024e-05, "epoch": 4.451827242524917, "percentage": 63.6, "elapsed_time": "2:27:59", "remaining_time": "1:24:42"}
|
||||
{"current_steps": 2685, "total_steps": 4214, "loss": 0.2532, "lr": 1.402803916146392e-05, "epoch": 4.460132890365449, "percentage": 63.72, "elapsed_time": "2:28:42", "remaining_time": "1:24:41"}
|
||||
{"current_steps": 2690, "total_steps": 4214, "loss": 0.2571, "lr": 1.3949022325003714e-05, "epoch": 4.46843853820598, "percentage": 63.83, "elapsed_time": "2:29:18", "remaining_time": "1:24:35"}
|
||||
{"current_steps": 2695, "total_steps": 4214, "loss": 0.2232, "lr": 1.3870109319780105e-05, "epoch": 4.476744186046512, "percentage": 63.95, "elapsed_time": "2:29:56", "remaining_time": "1:24:30"}
|
||||
{"current_steps": 2700, "total_steps": 4214, "loss": 0.2475, "lr": 1.3791301499894082e-05, "epoch": 4.485049833887043, "percentage": 64.07, "elapsed_time": "2:30:28", "remaining_time": "1:24:22"}
|
||||
{"current_steps": 2705, "total_steps": 4214, "loss": 0.2627, "lr": 1.371260021764173e-05, "epoch": 4.4933554817275745, "percentage": 64.19, "elapsed_time": "2:31:04", "remaining_time": "1:24:16"}
|
||||
{"current_steps": 2710, "total_steps": 4214, "loss": 0.2479, "lr": 1.3634006823490993e-05, "epoch": 4.501661129568106, "percentage": 64.31, "elapsed_time": "2:31:43", "remaining_time": "1:24:12"}
|
||||
{"current_steps": 2715, "total_steps": 4214, "loss": 0.2567, "lr": 1.3555522666058549e-05, "epoch": 4.509966777408637, "percentage": 64.43, "elapsed_time": "2:32:24", "remaining_time": "1:24:09"}
|
||||
{"current_steps": 2720, "total_steps": 4214, "loss": 0.2443, "lr": 1.3477149092086612e-05, "epoch": 4.51827242524917, "percentage": 64.55, "elapsed_time": "2:33:04", "remaining_time": "1:24:04"}
|
||||
{"current_steps": 2725, "total_steps": 4214, "loss": 0.2493, "lr": 1.3398887446419849e-05, "epoch": 4.526578073089701, "percentage": 64.67, "elapsed_time": "2:33:40", "remaining_time": "1:23:58"}
|
||||
{"current_steps": 2730, "total_steps": 4214, "loss": 0.2604, "lr": 1.3320739071982325e-05, "epoch": 4.534883720930233, "percentage": 64.78, "elapsed_time": "2:34:18", "remaining_time": "1:23:52"}
|
||||
{"current_steps": 2735, "total_steps": 4214, "loss": 0.2454, "lr": 1.3242705309754414e-05, "epoch": 4.543189368770764, "percentage": 64.9, "elapsed_time": "2:34:56", "remaining_time": "1:23:47"}
|
||||
{"current_steps": 2740, "total_steps": 4214, "loss": 0.2435, "lr": 1.3164787498749822e-05, "epoch": 4.5514950166112955, "percentage": 65.02, "elapsed_time": "2:35:29", "remaining_time": "1:23:39"}
|
||||
{"current_steps": 2745, "total_steps": 4214, "loss": 0.2296, "lr": 1.3086986975992585e-05, "epoch": 4.559800664451827, "percentage": 65.14, "elapsed_time": "2:36:04", "remaining_time": "1:23:31"}
|
||||
{"current_steps": 2750, "total_steps": 4214, "loss": 0.2451, "lr": 1.3009305076494176e-05, "epoch": 4.568106312292358, "percentage": 65.26, "elapsed_time": "2:36:35", "remaining_time": "1:23:22"}
|
||||
{"current_steps": 2755, "total_steps": 4214, "loss": 0.2517, "lr": 1.2931743133230525e-05, "epoch": 4.576411960132891, "percentage": 65.38, "elapsed_time": "2:37:09", "remaining_time": "1:23:13"}
|
||||
{"current_steps": 2760, "total_steps": 4214, "loss": 0.2398, "lr": 1.2854302477119204e-05, "epoch": 4.584717607973422, "percentage": 65.5, "elapsed_time": "2:37:42", "remaining_time": "1:23:04"}
|
||||
{"current_steps": 2765, "total_steps": 4214, "loss": 0.2385, "lr": 1.2776984436996553e-05, "epoch": 4.593023255813954, "percentage": 65.61, "elapsed_time": "2:38:20", "remaining_time": "1:22:58"}
|
||||
{"current_steps": 2770, "total_steps": 4214, "loss": 0.2507, "lr": 1.2699790339594923e-05, "epoch": 4.601328903654485, "percentage": 65.73, "elapsed_time": "2:38:53", "remaining_time": "1:22:49"}
|
||||
{"current_steps": 2775, "total_steps": 4214, "loss": 0.2615, "lr": 1.2622721509519846e-05, "epoch": 4.6096345514950166, "percentage": 65.85, "elapsed_time": "2:39:33", "remaining_time": "1:22:44"}
|
||||
{"current_steps": 2780, "total_steps": 4214, "loss": 0.2388, "lr": 1.2545779269227358e-05, "epoch": 4.617940199335548, "percentage": 65.97, "elapsed_time": "2:40:12", "remaining_time": "1:22:38"}
|
||||
{"current_steps": 2785, "total_steps": 4214, "loss": 0.2393, "lr": 1.2468964939001278e-05, "epoch": 4.6262458471760795, "percentage": 66.09, "elapsed_time": "2:40:49", "remaining_time": "1:22:31"}
|
||||
{"current_steps": 2790, "total_steps": 4214, "loss": 0.2322, "lr": 1.2392279836930583e-05, "epoch": 4.634551495016611, "percentage": 66.21, "elapsed_time": "2:41:26", "remaining_time": "1:22:24"}
|
||||
{"current_steps": 2795, "total_steps": 4214, "loss": 0.2489, "lr": 1.231572527888675e-05, "epoch": 4.642857142857143, "percentage": 66.33, "elapsed_time": "2:42:02", "remaining_time": "1:22:16"}
|
||||
{"current_steps": 2800, "total_steps": 4214, "loss": 0.2273, "lr": 1.2239302578501198e-05, "epoch": 4.651162790697675, "percentage": 66.45, "elapsed_time": "2:42:39", "remaining_time": "1:22:08"}
|
||||
{"current_steps": 2805, "total_steps": 4214, "loss": 0.2276, "lr": 1.2163013047142768e-05, "epoch": 4.659468438538206, "percentage": 66.56, "elapsed_time": "2:43:16", "remaining_time": "1:22:00"}
|
||||
{"current_steps": 2810, "total_steps": 4214, "loss": 0.2654, "lr": 1.2086857993895174e-05, "epoch": 4.667774086378738, "percentage": 66.68, "elapsed_time": "2:43:56", "remaining_time": "1:21:54"}
|
||||
{"current_steps": 2815, "total_steps": 4214, "loss": 0.2324, "lr": 1.2010838725534573e-05, "epoch": 4.676079734219269, "percentage": 66.8, "elapsed_time": "2:44:32", "remaining_time": "1:21:46"}
|
||||
{"current_steps": 2820, "total_steps": 4214, "loss": 0.2529, "lr": 1.1934956546507124e-05, "epoch": 4.6843853820598005, "percentage": 66.92, "elapsed_time": "2:45:08", "remaining_time": "1:21:38"}
|
||||
{"current_steps": 2825, "total_steps": 4214, "loss": 0.2593, "lr": 1.185921275890664e-05, "epoch": 4.692691029900332, "percentage": 67.04, "elapsed_time": "2:45:50", "remaining_time": "1:21:32"}
|
||||
{"current_steps": 2830, "total_steps": 4214, "loss": 0.2383, "lr": 1.1783608662452185e-05, "epoch": 4.700996677740864, "percentage": 67.16, "elapsed_time": "2:46:26", "remaining_time": "1:21:23"}
|
||||
{"current_steps": 2835, "total_steps": 4214, "loss": 0.2521, "lr": 1.1708145554465828e-05, "epoch": 4.709302325581396, "percentage": 67.28, "elapsed_time": "2:47:01", "remaining_time": "1:21:14"}
|
||||
{"current_steps": 2840, "total_steps": 4214, "loss": 0.2444, "lr": 1.1632824729850346e-05, "epoch": 4.717607973421927, "percentage": 67.39, "elapsed_time": "2:47:41", "remaining_time": "1:21:07"}
|
||||
{"current_steps": 2845, "total_steps": 4214, "loss": 0.2635, "lr": 1.155764748106702e-05, "epoch": 4.725913621262459, "percentage": 67.51, "elapsed_time": "2:48:21", "remaining_time": "1:21:00"}
|
||||
{"current_steps": 2850, "total_steps": 4214, "loss": 0.2442, "lr": 1.148261509811346e-05, "epoch": 4.73421926910299, "percentage": 67.63, "elapsed_time": "2:48:59", "remaining_time": "1:20:52"}
|
||||
{"current_steps": 2855, "total_steps": 4214, "loss": 0.2377, "lr": 1.1407728868501442e-05, "epoch": 4.7425249169435215, "percentage": 67.75, "elapsed_time": "2:49:34", "remaining_time": "1:20:43"}
|
||||
{"current_steps": 2860, "total_steps": 4214, "loss": 0.223, "lr": 1.1332990077234874e-05, "epoch": 4.750830564784053, "percentage": 67.87, "elapsed_time": "2:50:13", "remaining_time": "1:20:35"}
|
||||
{"current_steps": 2865, "total_steps": 4214, "loss": 0.2331, "lr": 1.1258400006787675e-05, "epoch": 4.759136212624584, "percentage": 67.99, "elapsed_time": "2:50:53", "remaining_time": "1:20:27"}
|
||||
{"current_steps": 2870, "total_steps": 4214, "loss": 0.2325, "lr": 1.1183959937081804e-05, "epoch": 4.767441860465116, "percentage": 68.11, "elapsed_time": "2:51:30", "remaining_time": "1:20:18"}
|
||||
{"current_steps": 2875, "total_steps": 4214, "loss": 0.2508, "lr": 1.1109671145465315e-05, "epoch": 4.775747508305648, "percentage": 68.22, "elapsed_time": "2:52:14", "remaining_time": "1:20:13"}
|
||||
{"current_steps": 2880, "total_steps": 4214, "loss": 0.2468, "lr": 1.1035534906690399e-05, "epoch": 4.78405315614618, "percentage": 68.34, "elapsed_time": "2:52:53", "remaining_time": "1:20:04"}
|
||||
{"current_steps": 2885, "total_steps": 4214, "loss": 0.2311, "lr": 1.0961552492891552e-05, "epoch": 4.792358803986711, "percentage": 68.46, "elapsed_time": "2:53:29", "remaining_time": "1:19:55"}
|
||||
{"current_steps": 2890, "total_steps": 4214, "loss": 0.2291, "lr": 1.08877251735637e-05, "epoch": 4.8006644518272426, "percentage": 68.58, "elapsed_time": "2:54:07", "remaining_time": "1:19:46"}
|
||||
{"current_steps": 2895, "total_steps": 4214, "loss": 0.2435, "lr": 1.081405421554044e-05, "epoch": 4.808970099667774, "percentage": 68.7, "elapsed_time": "2:54:43", "remaining_time": "1:19:36"}
|
||||
{"current_steps": 2900, "total_steps": 4214, "loss": 0.2292, "lr": 1.074054088297232e-05, "epoch": 4.8172757475083055, "percentage": 68.82, "elapsed_time": "2:55:15", "remaining_time": "1:19:24"}
|
||||
{"current_steps": 2905, "total_steps": 4214, "loss": 0.2391, "lr": 1.0667186437305115e-05, "epoch": 4.825581395348837, "percentage": 68.94, "elapsed_time": "2:55:55", "remaining_time": "1:19:16"}
|
||||
{"current_steps": 2910, "total_steps": 4214, "loss": 0.2334, "lr": 1.059399213725818e-05, "epoch": 4.833887043189369, "percentage": 69.06, "elapsed_time": "2:56:28", "remaining_time": "1:19:04"}
|
||||
{"current_steps": 2915, "total_steps": 4214, "loss": 0.2422, "lr": 1.0520959238802902e-05, "epoch": 4.842192691029901, "percentage": 69.17, "elapsed_time": "2:57:03", "remaining_time": "1:18:54"}
|
||||
{"current_steps": 2920, "total_steps": 4214, "loss": 0.2563, "lr": 1.044808899514107e-05, "epoch": 4.850498338870432, "percentage": 69.29, "elapsed_time": "2:57:40", "remaining_time": "1:18:44"}
|
||||
{"current_steps": 2925, "total_steps": 4214, "loss": 0.241, "lr": 1.0375382656683439e-05, "epoch": 4.858803986710964, "percentage": 69.41, "elapsed_time": "2:58:14", "remaining_time": "1:18:33"}
|
||||
{"current_steps": 2930, "total_steps": 4214, "loss": 0.2522, "lr": 1.0302841471028228e-05, "epoch": 4.867109634551495, "percentage": 69.53, "elapsed_time": "2:58:53", "remaining_time": "1:18:23"}
|
||||
{"current_steps": 2935, "total_steps": 4214, "loss": 0.238, "lr": 1.0230466682939755e-05, "epoch": 4.8754152823920265, "percentage": 69.65, "elapsed_time": "2:59:25", "remaining_time": "1:18:11"}
|
||||
{"current_steps": 2940, "total_steps": 4214, "loss": 0.2388, "lr": 1.0158259534327032e-05, "epoch": 4.883720930232558, "percentage": 69.77, "elapsed_time": "3:00:04", "remaining_time": "1:18:02"}
|
||||
{"current_steps": 2945, "total_steps": 4214, "loss": 0.2415, "lr": 1.0086221264222478e-05, "epoch": 4.892026578073089, "percentage": 69.89, "elapsed_time": "3:00:42", "remaining_time": "1:17:52"}
|
||||
{"current_steps": 2950, "total_steps": 4214, "loss": 0.2864, "lr": 1.0014353108760657e-05, "epoch": 4.900332225913621, "percentage": 70.0, "elapsed_time": "3:01:23", "remaining_time": "1:17:43"}
|
||||
{"current_steps": 2955, "total_steps": 4214, "loss": 0.2537, "lr": 9.942656301157081e-06, "epoch": 4.908637873754153, "percentage": 70.12, "elapsed_time": "3:02:04", "remaining_time": "1:17:34"}
|
||||
{"current_steps": 2960, "total_steps": 4214, "loss": 0.2488, "lr": 9.871132071687013e-06, "epoch": 4.916943521594685, "percentage": 70.24, "elapsed_time": "3:02:41", "remaining_time": "1:17:23"}
|
||||
{"current_steps": 2965, "total_steps": 4214, "loss": 0.2333, "lr": 9.799781647664382e-06, "epoch": 4.925249169435216, "percentage": 70.36, "elapsed_time": "3:03:13", "remaining_time": "1:17:11"}
|
||||
{"current_steps": 2970, "total_steps": 4214, "loss": 0.265, "lr": 9.728606253420711e-06, "epoch": 4.9335548172757475, "percentage": 70.48, "elapsed_time": "3:03:46", "remaining_time": "1:16:58"}
|
||||
{"current_steps": 2975, "total_steps": 4214, "loss": 0.2408, "lr": 9.65760711028414e-06, "epoch": 4.941860465116279, "percentage": 70.6, "elapsed_time": "3:04:21", "remaining_time": "1:16:46"}
|
||||
{"current_steps": 2980, "total_steps": 4214, "loss": 0.2512, "lr": 9.586785436558414e-06, "epoch": 4.95016611295681, "percentage": 70.72, "elapsed_time": "3:05:00", "remaining_time": "1:16:36"}
|
||||
{"current_steps": 2985, "total_steps": 4214, "loss": 0.2322, "lr": 9.516142447502012e-06, "epoch": 4.958471760797342, "percentage": 70.84, "elapsed_time": "3:05:34", "remaining_time": "1:16:24"}
|
||||
{"current_steps": 2990, "total_steps": 4214, "loss": 0.221, "lr": 9.445679355307308e-06, "epoch": 4.966777408637874, "percentage": 70.95, "elapsed_time": "3:06:07", "remaining_time": "1:16:11"}
|
||||
{"current_steps": 2995, "total_steps": 4214, "loss": 0.2475, "lr": 9.375397369079733e-06, "epoch": 4.975083056478406, "percentage": 71.07, "elapsed_time": "3:06:42", "remaining_time": "1:15:59"}
|
||||
{"current_steps": 3000, "total_steps": 4214, "loss": 0.2345, "lr": 9.305297694817046e-06, "epoch": 4.983388704318937, "percentage": 71.19, "elapsed_time": "3:07:18", "remaining_time": "1:15:47"}
|
||||
{"current_steps": 3005, "total_steps": 4214, "loss": 0.2251, "lr": 9.235381535388638e-06, "epoch": 4.9916943521594686, "percentage": 71.31, "elapsed_time": "3:08:03", "remaining_time": "1:15:39"}
|
||||
{"current_steps": 3010, "total_steps": 4214, "loss": 0.2315, "lr": 9.16565009051491e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "3:08:41", "remaining_time": "1:15:28"}
|
||||
{"current_steps": 3015, "total_steps": 4214, "loss": 0.2281, "lr": 9.096104556746654e-06, "epoch": 5.0083056478405314, "percentage": 71.55, "elapsed_time": "3:09:16", "remaining_time": "1:15:16"}
|
||||
{"current_steps": 3020, "total_steps": 4214, "loss": 0.2289, "lr": 9.026746127444532e-06, "epoch": 5.016611295681063, "percentage": 71.67, "elapsed_time": "3:09:49", "remaining_time": "1:15:03"}
|
||||
{"current_steps": 3025, "total_steps": 4214, "loss": 0.2229, "lr": 8.957575992758622e-06, "epoch": 5.024916943521594, "percentage": 71.78, "elapsed_time": "3:10:30", "remaining_time": "1:14:52"}
|
||||
{"current_steps": 3030, "total_steps": 4214, "loss": 0.2318, "lr": 8.888595339607961e-06, "epoch": 5.033222591362127, "percentage": 71.9, "elapsed_time": "3:11:09", "remaining_time": "1:14:41"}
|
||||
{"current_steps": 3035, "total_steps": 4214, "loss": 0.2395, "lr": 8.819805351660189e-06, "epoch": 5.041528239202658, "percentage": 72.02, "elapsed_time": "3:11:43", "remaining_time": "1:14:28"}
|
||||
{"current_steps": 3040, "total_steps": 4214, "loss": 0.2174, "lr": 8.751207209311268e-06, "epoch": 5.04983388704319, "percentage": 72.14, "elapsed_time": "3:12:23", "remaining_time": "1:14:17"}
|
||||
{"current_steps": 3045, "total_steps": 4214, "loss": 0.2037, "lr": 8.682802089665166e-06, "epoch": 5.058139534883721, "percentage": 72.26, "elapsed_time": "3:12:56", "remaining_time": "1:14:04"}
|
||||
{"current_steps": 3050, "total_steps": 4214, "loss": 0.2231, "lr": 8.614591166513732e-06, "epoch": 5.0664451827242525, "percentage": 72.38, "elapsed_time": "3:13:33", "remaining_time": "1:13:52"}
|
||||
{"current_steps": 3055, "total_steps": 4214, "loss": 0.2445, "lr": 8.54657561031649e-06, "epoch": 5.074750830564784, "percentage": 72.5, "elapsed_time": "3:14:13", "remaining_time": "1:13:41"}
|
||||
{"current_steps": 3060, "total_steps": 4214, "loss": 0.2279, "lr": 8.478756588180584e-06, "epoch": 5.083056478405315, "percentage": 72.62, "elapsed_time": "3:14:47", "remaining_time": "1:13:27"}
|
||||
{"current_steps": 3065, "total_steps": 4214, "loss": 0.2422, "lr": 8.411135263840767e-06, "epoch": 5.091362126245847, "percentage": 72.73, "elapsed_time": "3:15:22", "remaining_time": "1:13:14"}
|
||||
{"current_steps": 3070, "total_steps": 4214, "loss": 0.2077, "lr": 8.343712797639392e-06, "epoch": 5.099667774086379, "percentage": 72.85, "elapsed_time": "3:15:58", "remaining_time": "1:13:01"}
|
||||
{"current_steps": 3075, "total_steps": 4214, "loss": 0.2174, "lr": 8.276490346506534e-06, "epoch": 5.107973421926911, "percentage": 72.97, "elapsed_time": "3:16:31", "remaining_time": "1:12:47"}
|
||||
{"current_steps": 3080, "total_steps": 4214, "loss": 0.2351, "lr": 8.209469063940117e-06, "epoch": 5.116279069767442, "percentage": 73.09, "elapsed_time": "3:17:07", "remaining_time": "1:12:34"}
|
||||
{"current_steps": 3085, "total_steps": 4214, "loss": 0.2474, "lr": 8.142650099986147e-06, "epoch": 5.1245847176079735, "percentage": 73.21, "elapsed_time": "3:17:40", "remaining_time": "1:12:20"}
|
||||
{"current_steps": 3090, "total_steps": 4214, "loss": 0.2048, "lr": 8.07603460121895e-06, "epoch": 5.132890365448505, "percentage": 73.33, "elapsed_time": "3:18:18", "remaining_time": "1:12:08"}
|
||||
{"current_steps": 3095, "total_steps": 4214, "loss": 0.2278, "lr": 8.009623710721497e-06, "epoch": 5.141196013289036, "percentage": 73.45, "elapsed_time": "3:18:52", "remaining_time": "1:11:54"}
|
||||
{"current_steps": 3100, "total_steps": 4214, "loss": 0.24, "lr": 7.943418568065831e-06, "epoch": 5.149501661129568, "percentage": 73.56, "elapsed_time": "3:19:27", "remaining_time": "1:11:40"}
|
||||
{"current_steps": 3105, "total_steps": 4214, "loss": 0.2227, "lr": 7.877420309293454e-06, "epoch": 5.157807308970099, "percentage": 73.68, "elapsed_time": "3:20:00", "remaining_time": "1:11:26"}
|
||||
{"current_steps": 3110, "total_steps": 4214, "loss": 0.2431, "lr": 7.811630066895874e-06, "epoch": 5.166112956810632, "percentage": 73.8, "elapsed_time": "3:20:36", "remaining_time": "1:11:12"}
|
||||
{"current_steps": 3115, "total_steps": 4214, "loss": 0.2382, "lr": 7.746048969795153e-06, "epoch": 5.174418604651163, "percentage": 73.92, "elapsed_time": "3:21:16", "remaining_time": "1:11:00"}
|
||||
{"current_steps": 3120, "total_steps": 4214, "loss": 0.221, "lr": 7.680678143324558e-06, "epoch": 5.1827242524916945, "percentage": 74.04, "elapsed_time": "3:21:52", "remaining_time": "1:10:47"}
|
||||
{"current_steps": 3125, "total_steps": 4214, "loss": 0.2365, "lr": 7.615518709209217e-06, "epoch": 5.191029900332226, "percentage": 74.16, "elapsed_time": "3:22:37", "remaining_time": "1:10:36"}
|
||||
{"current_steps": 3130, "total_steps": 4214, "loss": 0.2303, "lr": 7.5505717855468985e-06, "epoch": 5.1993355481727574, "percentage": 74.28, "elapsed_time": "3:23:12", "remaining_time": "1:10:22"}
|
||||
{"current_steps": 3135, "total_steps": 4214, "loss": 0.2547, "lr": 7.485838486788803e-06, "epoch": 5.207641196013289, "percentage": 74.39, "elapsed_time": "3:23:54", "remaining_time": "1:10:10"}
|
||||
{"current_steps": 3140, "total_steps": 4214, "loss": 0.2305, "lr": 7.421319923720478e-06, "epoch": 5.21594684385382, "percentage": 74.51, "elapsed_time": "3:24:31", "remaining_time": "1:09:57"}
|
||||
{"current_steps": 3145, "total_steps": 4214, "loss": 0.2414, "lr": 7.357017203442711e-06, "epoch": 5.224252491694352, "percentage": 74.63, "elapsed_time": "3:25:10", "remaining_time": "1:09:44"}
|
||||
{"current_steps": 3150, "total_steps": 4214, "loss": 0.2318, "lr": 7.292931429352561e-06, "epoch": 5.232558139534884, "percentage": 74.75, "elapsed_time": "3:25:49", "remaining_time": "1:09:31"}
|
||||
{"current_steps": 3155, "total_steps": 4214, "loss": 0.2337, "lr": 7.229063701124406e-06, "epoch": 5.240863787375416, "percentage": 74.87, "elapsed_time": "3:26:27", "remaining_time": "1:09:17"}
|
||||
{"current_steps": 3160, "total_steps": 4214, "loss": 0.2483, "lr": 7.16541511469111e-06, "epoch": 5.249169435215947, "percentage": 74.99, "elapsed_time": "3:27:07", "remaining_time": "1:09:05"}
|
||||
{"current_steps": 3165, "total_steps": 4214, "loss": 0.2311, "lr": 7.10198676222517e-06, "epoch": 5.2574750830564785, "percentage": 75.11, "elapsed_time": "3:27:45", "remaining_time": "1:08:51"}
|
||||
{"current_steps": 3170, "total_steps": 4214, "loss": 0.23, "lr": 7.038779732119996e-06, "epoch": 5.26578073089701, "percentage": 75.23, "elapsed_time": "3:28:19", "remaining_time": "1:08:36"}
|
||||
{"current_steps": 3175, "total_steps": 4214, "loss": 0.2415, "lr": 6.975795108971257e-06, "epoch": 5.274086378737541, "percentage": 75.34, "elapsed_time": "3:29:03", "remaining_time": "1:08:24"}
|
||||
{"current_steps": 3180, "total_steps": 4214, "loss": 0.2386, "lr": 6.9130339735582295e-06, "epoch": 5.282392026578073, "percentage": 75.46, "elapsed_time": "3:29:38", "remaining_time": "1:08:09"}
|
||||
{"current_steps": 3185, "total_steps": 4214, "loss": 0.2289, "lr": 6.850497402825267e-06, "epoch": 5.290697674418604, "percentage": 75.58, "elapsed_time": "3:30:13", "remaining_time": "1:07:55"}
|
||||
{"current_steps": 3190, "total_steps": 4214, "loss": 0.227, "lr": 6.7881864698633515e-06, "epoch": 5.299003322259137, "percentage": 75.7, "elapsed_time": "3:30:51", "remaining_time": "1:07:41"}
|
||||
{"current_steps": 3195, "total_steps": 4214, "loss": 0.2222, "lr": 6.726102243891619e-06, "epoch": 5.307308970099668, "percentage": 75.82, "elapsed_time": "3:31:30", "remaining_time": "1:07:27"}
|
||||
{"current_steps": 3200, "total_steps": 4214, "loss": 0.2322, "lr": 6.664245790239079e-06, "epoch": 5.3156146179401995, "percentage": 75.94, "elapsed_time": "3:32:05", "remaining_time": "1:07:12"}
|
||||
{"current_steps": 3205, "total_steps": 4214, "loss": 0.2509, "lr": 6.6026181703262785e-06, "epoch": 5.323920265780731, "percentage": 76.06, "elapsed_time": "3:32:38", "remaining_time": "1:06:56"}
|
||||
{"current_steps": 3210, "total_steps": 4214, "loss": 0.2437, "lr": 6.541220441647107e-06, "epoch": 5.332225913621262, "percentage": 76.17, "elapsed_time": "3:33:16", "remaining_time": "1:06:42"}
|
||||
{"current_steps": 3215, "total_steps": 4214, "loss": 0.2325, "lr": 6.4800536577506846e-06, "epoch": 5.340531561461794, "percentage": 76.29, "elapsed_time": "3:33:54", "remaining_time": "1:06:28"}
|
||||
{"current_steps": 3220, "total_steps": 4214, "loss": 0.2412, "lr": 6.4191188682232266e-06, "epoch": 5.348837209302325, "percentage": 76.41, "elapsed_time": "3:34:31", "remaining_time": "1:06:13"}
|
||||
{"current_steps": 3225, "total_steps": 4214, "loss": 0.2355, "lr": 6.358417118670062e-06, "epoch": 5.357142857142857, "percentage": 76.53, "elapsed_time": "3:35:10", "remaining_time": "1:05:59"}
|
||||
{"current_steps": 3230, "total_steps": 4214, "loss": 0.2358, "lr": 6.297949450697711e-06, "epoch": 5.365448504983389, "percentage": 76.65, "elapsed_time": "3:35:49", "remaining_time": "1:05:44"}
|
||||
{"current_steps": 3235, "total_steps": 4214, "loss": 0.2435, "lr": 6.2377169018959735e-06, "epoch": 5.3737541528239205, "percentage": 76.77, "elapsed_time": "3:36:24", "remaining_time": "1:05:29"}
|
||||
{"current_steps": 3240, "total_steps": 4214, "loss": 0.244, "lr": 6.177720505820142e-06, "epoch": 5.382059800664452, "percentage": 76.89, "elapsed_time": "3:37:03", "remaining_time": "1:05:14"}
|
||||
{"current_steps": 3245, "total_steps": 4214, "loss": 0.2352, "lr": 6.117961291973267e-06, "epoch": 5.3903654485049834, "percentage": 77.01, "elapsed_time": "3:37:40", "remaining_time": "1:05:00"}
|
||||
{"current_steps": 3250, "total_steps": 4214, "loss": 0.2445, "lr": 6.058440285788507e-06, "epoch": 5.398671096345515, "percentage": 77.12, "elapsed_time": "3:38:14", "remaining_time": "1:04:43"}
|
||||
{"current_steps": 3255, "total_steps": 4214, "loss": 0.221, "lr": 5.999158508611496e-06, "epoch": 5.406976744186046, "percentage": 77.24, "elapsed_time": "3:38:48", "remaining_time": "1:04:27"}
|
||||
{"current_steps": 3260, "total_steps": 4214, "loss": 0.2281, "lr": 5.940116977682843e-06, "epoch": 5.415282392026578, "percentage": 77.36, "elapsed_time": "3:39:25", "remaining_time": "1:04:12"}
|
||||
{"current_steps": 3265, "total_steps": 4214, "loss": 0.2644, "lr": 5.881316706120674e-06, "epoch": 5.423588039867109, "percentage": 77.48, "elapsed_time": "3:40:06", "remaining_time": "1:03:58"}
|
||||
{"current_steps": 3270, "total_steps": 4214, "loss": 0.2214, "lr": 5.8227587029032555e-06, "epoch": 5.431893687707642, "percentage": 77.6, "elapsed_time": "3:40:46", "remaining_time": "1:03:44"}
|
||||
{"current_steps": 3275, "total_steps": 4214, "loss": 0.2443, "lr": 5.7644439728516544e-06, "epoch": 5.440199335548173, "percentage": 77.72, "elapsed_time": "3:41:21", "remaining_time": "1:03:27"}
|
||||
{"current_steps": 3280, "total_steps": 4214, "loss": 0.2318, "lr": 5.7063735166125134e-06, "epoch": 5.4485049833887045, "percentage": 77.84, "elapsed_time": "3:41:58", "remaining_time": "1:03:12"}
|
||||
{"current_steps": 3285, "total_steps": 4214, "loss": 0.2251, "lr": 5.6485483306409015e-06, "epoch": 5.456810631229236, "percentage": 77.95, "elapsed_time": "3:42:36", "remaining_time": "1:02:57"}
|
||||
{"current_steps": 3290, "total_steps": 4214, "loss": 0.229, "lr": 5.590969407183169e-06, "epoch": 5.465116279069767, "percentage": 78.07, "elapsed_time": "3:43:14", "remaining_time": "1:02:41"}
|
||||
{"current_steps": 3295, "total_steps": 4214, "loss": 0.2459, "lr": 5.533637734259952e-06, "epoch": 5.473421926910299, "percentage": 78.19, "elapsed_time": "3:43:46", "remaining_time": "1:02:24"}
|
||||
{"current_steps": 3300, "total_steps": 4214, "loss": 0.2334, "lr": 5.47655429564921e-06, "epoch": 5.48172757475083, "percentage": 78.31, "elapsed_time": "3:44:21", "remaining_time": "1:02:08"}
|
||||
{"current_steps": 3305, "total_steps": 4214, "loss": 0.2696, "lr": 5.419720070869365e-06, "epoch": 5.490033222591362, "percentage": 78.43, "elapsed_time": "3:44:59", "remaining_time": "1:01:52"}
|
||||
{"current_steps": 3310, "total_steps": 4214, "loss": 0.2369, "lr": 5.363136035162453e-06, "epoch": 5.498338870431894, "percentage": 78.55, "elapsed_time": "3:45:34", "remaining_time": "1:01:36"}
|
||||
{"current_steps": 3315, "total_steps": 4214, "loss": 0.2312, "lr": 5.306803159477421e-06, "epoch": 5.5066445182724255, "percentage": 78.67, "elapsed_time": "3:46:05", "remaining_time": "1:01:18"}
|
||||
{"current_steps": 3320, "total_steps": 4214, "loss": 0.2436, "lr": 5.250722410453451e-06, "epoch": 5.514950166112957, "percentage": 78.79, "elapsed_time": "3:46:42", "remaining_time": "1:01:02"}
|
||||
{"current_steps": 3325, "total_steps": 4214, "loss": 0.2324, "lr": 5.194894750403397e-06, "epoch": 5.523255813953488, "percentage": 78.9, "elapsed_time": "3:47:14", "remaining_time": "1:00:45"}
|
||||
{"current_steps": 3330, "total_steps": 4214, "loss": 0.2378, "lr": 5.139321137297233e-06, "epoch": 5.53156146179402, "percentage": 79.02, "elapsed_time": "3:47:51", "remaining_time": "1:00:29"}
|
||||
{"current_steps": 3335, "total_steps": 4214, "loss": 0.2374, "lr": 5.084002524745642e-06, "epoch": 5.539867109634551, "percentage": 79.14, "elapsed_time": "3:48:32", "remaining_time": "1:00:14"}
|
||||
{"current_steps": 3340, "total_steps": 4214, "loss": 0.2414, "lr": 5.028939861983659e-06, "epoch": 5.548172757475083, "percentage": 79.26, "elapsed_time": "3:49:04", "remaining_time": "0:59:56"}
|
||||
{"current_steps": 3345, "total_steps": 4214, "loss": 0.2267, "lr": 4.974134093854357e-06, "epoch": 5.556478405315614, "percentage": 79.38, "elapsed_time": "3:49:42", "remaining_time": "0:59:40"}
|
||||
{"current_steps": 3350, "total_steps": 4214, "loss": 0.2348, "lr": 4.919586160792644e-06, "epoch": 5.5647840531561465, "percentage": 79.5, "elapsed_time": "3:50:16", "remaining_time": "0:59:23"}
|
||||
{"current_steps": 3355, "total_steps": 4214, "loss": 0.2422, "lr": 4.86529699880915e-06, "epoch": 5.573089700996678, "percentage": 79.62, "elapsed_time": "3:50:54", "remaining_time": "0:59:07"}
|
||||
{"current_steps": 3360, "total_steps": 4214, "loss": 0.2384, "lr": 4.811267539474118e-06, "epoch": 5.5813953488372094, "percentage": 79.73, "elapsed_time": "3:51:31", "remaining_time": "0:58:50"}
|
||||
{"current_steps": 3365, "total_steps": 4214, "loss": 0.2273, "lr": 4.757498709901469e-06, "epoch": 5.589700996677741, "percentage": 79.85, "elapsed_time": "3:52:09", "remaining_time": "0:58:34"}
|
||||
{"current_steps": 3370, "total_steps": 4214, "loss": 0.2313, "lr": 4.7039914327328525e-06, "epoch": 5.598006644518272, "percentage": 79.97, "elapsed_time": "3:52:46", "remaining_time": "0:58:17"}
|
||||
{"current_steps": 3375, "total_steps": 4214, "loss": 0.2265, "lr": 4.650746626121838e-06, "epoch": 5.606312292358804, "percentage": 80.09, "elapsed_time": "3:53:18", "remaining_time": "0:57:59"}
|
||||
{"current_steps": 3380, "total_steps": 4214, "loss": 0.2137, "lr": 4.597765203718163e-06, "epoch": 5.614617940199335, "percentage": 80.21, "elapsed_time": "3:53:58", "remaining_time": "0:57:43"}
|
||||
{"current_steps": 3385, "total_steps": 4214, "loss": 0.2478, "lr": 4.54504807465203e-06, "epoch": 5.622923588039868, "percentage": 80.33, "elapsed_time": "3:54:33", "remaining_time": "0:57:26"}
|
||||
{"current_steps": 3390, "total_steps": 4214, "loss": 0.2485, "lr": 4.4925961435185325e-06, "epoch": 5.631229235880399, "percentage": 80.45, "elapsed_time": "3:55:10", "remaining_time": "0:57:09"}
|
||||
{"current_steps": 3395, "total_steps": 4214, "loss": 0.2185, "lr": 4.4404103103621136e-06, "epoch": 5.6395348837209305, "percentage": 80.56, "elapsed_time": "3:55:44", "remaining_time": "0:56:52"}
|
||||
{"current_steps": 3400, "total_steps": 4214, "loss": 0.2117, "lr": 4.388491470661149e-06, "epoch": 5.647840531561462, "percentage": 80.68, "elapsed_time": "3:56:19", "remaining_time": "0:56:34"}
|
||||
{"current_steps": 3405, "total_steps": 4214, "loss": 0.2331, "lr": 4.3368405153125435e-06, "epoch": 5.656146179401993, "percentage": 80.8, "elapsed_time": "3:57:01", "remaining_time": "0:56:18"}
|
||||
{"current_steps": 3410, "total_steps": 4214, "loss": 0.2541, "lr": 4.285458330616467e-06, "epoch": 5.664451827242525, "percentage": 80.92, "elapsed_time": "3:57:38", "remaining_time": "0:56:01"}
|
||||
{"current_steps": 3415, "total_steps": 4214, "loss": 0.2574, "lr": 4.2343457982611595e-06, "epoch": 5.672757475083056, "percentage": 81.04, "elapsed_time": "3:58:19", "remaining_time": "0:55:45"}
|
||||
{"current_steps": 3420, "total_steps": 4214, "loss": 0.2544, "lr": 4.183503795307762e-06, "epoch": 5.681063122923588, "percentage": 81.16, "elapsed_time": "3:58:58", "remaining_time": "0:55:28"}
|
||||
{"current_steps": 3425, "total_steps": 4214, "loss": 0.2533, "lr": 4.132933194175299e-06, "epoch": 5.689368770764119, "percentage": 81.28, "elapsed_time": "3:59:40", "remaining_time": "0:55:12"}
|
||||
{"current_steps": 3430, "total_steps": 4214, "loss": 0.2432, "lr": 4.082634862625697e-06, "epoch": 5.6976744186046515, "percentage": 81.4, "elapsed_time": "4:00:17", "remaining_time": "0:54:55"}
|
||||
{"current_steps": 3435, "total_steps": 4214, "loss": 0.2222, "lr": 4.032609663748898e-06, "epoch": 5.705980066445183, "percentage": 81.51, "elapsed_time": "4:00:48", "remaining_time": "0:54:36"}
|
||||
{"current_steps": 3440, "total_steps": 4214, "loss": 0.2483, "lr": 3.982858455948051e-06, "epoch": 5.714285714285714, "percentage": 81.63, "elapsed_time": "4:01:23", "remaining_time": "0:54:18"}
|
||||
{"current_steps": 3445, "total_steps": 4214, "loss": 0.2282, "lr": 3.933382092924769e-06, "epoch": 5.722591362126246, "percentage": 81.75, "elapsed_time": "4:02:00", "remaining_time": "0:54:01"}
|
||||
{"current_steps": 3450, "total_steps": 4214, "loss": 0.2506, "lr": 3.8841814236644856e-06, "epoch": 5.730897009966777, "percentage": 81.87, "elapsed_time": "4:02:38", "remaining_time": "0:53:43"}
|
||||
{"current_steps": 3455, "total_steps": 4214, "loss": 0.2487, "lr": 3.835257292421915e-06, "epoch": 5.739202657807309, "percentage": 81.99, "elapsed_time": "4:03:16", "remaining_time": "0:53:26"}
|
||||
{"current_steps": 3460, "total_steps": 4214, "loss": 0.2492, "lr": 3.786610538706514e-06, "epoch": 5.74750830564784, "percentage": 82.11, "elapsed_time": "4:03:58", "remaining_time": "0:53:09"}
|
||||
{"current_steps": 3465, "total_steps": 4214, "loss": 0.2334, "lr": 3.7382419972681196e-06, "epoch": 5.7558139534883725, "percentage": 82.23, "elapsed_time": "4:04:34", "remaining_time": "0:52:52"}
|
||||
{"current_steps": 3470, "total_steps": 4214, "loss": 0.2365, "lr": 3.690152498082593e-06, "epoch": 5.764119601328904, "percentage": 82.34, "elapsed_time": "4:05:16", "remaining_time": "0:52:35"}
|
||||
{"current_steps": 3475, "total_steps": 4214, "loss": 0.2466, "lr": 3.642342866337618e-06, "epoch": 5.7724252491694354, "percentage": 82.46, "elapsed_time": "4:05:50", "remaining_time": "0:52:16"}
|
||||
{"current_steps": 3480, "total_steps": 4214, "loss": 0.2426, "lr": 3.5948139224184963e-06, "epoch": 5.780730897009967, "percentage": 82.58, "elapsed_time": "4:06:24", "remaining_time": "0:51:58"}
|
||||
{"current_steps": 3485, "total_steps": 4214, "loss": 0.217, "lr": 3.5475664818940915e-06, "epoch": 5.789036544850498, "percentage": 82.7, "elapsed_time": "4:06:58", "remaining_time": "0:51:39"}
|
||||
{"current_steps": 3490, "total_steps": 4214, "loss": 0.2341, "lr": 3.5006013555028508e-06, "epoch": 5.79734219269103, "percentage": 82.82, "elapsed_time": "4:07:35", "remaining_time": "0:51:21"}
|
||||
{"current_steps": 3495, "total_steps": 4214, "loss": 0.2362, "lr": 3.453919349138859e-06, "epoch": 5.805647840531561, "percentage": 82.94, "elapsed_time": "4:08:11", "remaining_time": "0:51:03"}
|
||||
{"current_steps": 3500, "total_steps": 4214, "loss": 0.2427, "lr": 3.4075212638380274e-06, "epoch": 5.813953488372093, "percentage": 83.06, "elapsed_time": "4:08:49", "remaining_time": "0:50:45"}
|
||||
{"current_steps": 3505, "total_steps": 4214, "loss": 0.2332, "lr": 3.361407895764364e-06, "epoch": 5.822259136212624, "percentage": 83.18, "elapsed_time": "4:09:26", "remaining_time": "0:50:27"}
|
||||
{"current_steps": 3510, "total_steps": 4214, "loss": 0.2459, "lr": 3.3155800361962733e-06, "epoch": 5.8305647840531565, "percentage": 83.29, "elapsed_time": "4:10:08", "remaining_time": "0:50:10"}
|
||||
{"current_steps": 3515, "total_steps": 4214, "loss": 0.2357, "lr": 3.270038471513022e-06, "epoch": 5.838870431893688, "percentage": 83.41, "elapsed_time": "4:10:45", "remaining_time": "0:49:52"}
|
||||
{"current_steps": 3520, "total_steps": 4214, "loss": 0.2432, "lr": 3.224783983181212e-06, "epoch": 5.847176079734219, "percentage": 83.53, "elapsed_time": "4:11:21", "remaining_time": "0:49:33"}
|
||||
{"current_steps": 3525, "total_steps": 4214, "loss": 0.2349, "lr": 3.179817347741381e-06, "epoch": 5.855481727574751, "percentage": 83.65, "elapsed_time": "4:11:57", "remaining_time": "0:49:14"}
|
||||
{"current_steps": 3530, "total_steps": 4214, "loss": 0.2469, "lr": 3.1351393367946904e-06, "epoch": 5.863787375415282, "percentage": 83.77, "elapsed_time": "4:12:31", "remaining_time": "0:48:55"}
|
||||
{"current_steps": 3535, "total_steps": 4214, "loss": 0.2169, "lr": 3.0907507169896657e-06, "epoch": 5.872093023255814, "percentage": 83.89, "elapsed_time": "4:13:06", "remaining_time": "0:48:36"}
|
||||
{"current_steps": 3540, "total_steps": 4214, "loss": 0.2486, "lr": 3.0466522500090435e-06, "epoch": 5.880398671096345, "percentage": 84.01, "elapsed_time": "4:13:41", "remaining_time": "0:48:18"}
|
||||
{"current_steps": 3545, "total_steps": 4214, "loss": 0.2395, "lr": 3.00284469255673e-06, "epoch": 5.8887043189368775, "percentage": 84.12, "elapsed_time": "4:14:18", "remaining_time": "0:47:59"}
|
||||
{"current_steps": 3550, "total_steps": 4214, "loss": 0.2366, "lr": 2.959328796344774e-06, "epoch": 5.897009966777409, "percentage": 84.24, "elapsed_time": "4:14:54", "remaining_time": "0:47:40"}
|
||||
{"current_steps": 3555, "total_steps": 4214, "loss": 0.236, "lr": 2.9161053080804924e-06, "epoch": 5.90531561461794, "percentage": 84.36, "elapsed_time": "4:15:31", "remaining_time": "0:47:22"}
|
||||
{"current_steps": 3560, "total_steps": 4214, "loss": 0.2531, "lr": 2.8731749694536514e-06, "epoch": 5.913621262458472, "percentage": 84.48, "elapsed_time": "4:16:09", "remaining_time": "0:47:03"}
|
||||
{"current_steps": 3565, "total_steps": 4214, "loss": 0.2355, "lr": 2.8305385171237533e-06, "epoch": 5.921926910299003, "percentage": 84.6, "elapsed_time": "4:16:42", "remaining_time": "0:46:43"}
|
||||
{"current_steps": 3570, "total_steps": 4214, "loss": 0.2588, "lr": 2.7881966827073694e-06, "epoch": 5.930232558139535, "percentage": 84.72, "elapsed_time": "4:17:20", "remaining_time": "0:46:25"}
|
||||
{"current_steps": 3575, "total_steps": 4214, "loss": 0.259, "lr": 2.7461501927656066e-06, "epoch": 5.938538205980066, "percentage": 84.84, "elapsed_time": "4:18:02", "remaining_time": "0:46:07"}
|
||||
{"current_steps": 3580, "total_steps": 4214, "loss": 0.2349, "lr": 2.7043997687916233e-06, "epoch": 5.946843853820598, "percentage": 84.95, "elapsed_time": "4:18:37", "remaining_time": "0:45:48"}
|
||||
{"current_steps": 3585, "total_steps": 4214, "loss": 0.2236, "lr": 2.6629461271982782e-06, "epoch": 5.955149501661129, "percentage": 85.07, "elapsed_time": "4:19:14", "remaining_time": "0:45:29"}
|
||||
{"current_steps": 3590, "total_steps": 4214, "loss": 0.2376, "lr": 2.6217899793058045e-06, "epoch": 5.9634551495016614, "percentage": 85.19, "elapsed_time": "4:19:53", "remaining_time": "0:45:10"}
|
||||
{"current_steps": 3595, "total_steps": 4214, "loss": 0.2228, "lr": 2.580932031329615e-06, "epoch": 5.971760797342193, "percentage": 85.31, "elapsed_time": "4:20:29", "remaining_time": "0:44:51"}
|
||||
{"current_steps": 3600, "total_steps": 4214, "loss": 0.2368, "lr": 2.5403729843681977e-06, "epoch": 5.980066445182724, "percentage": 85.43, "elapsed_time": "4:21:04", "remaining_time": "0:44:31"}
|
||||
{"current_steps": 3605, "total_steps": 4214, "loss": 0.2437, "lr": 2.500113534391069e-06, "epoch": 5.988372093023256, "percentage": 85.55, "elapsed_time": "4:21:47", "remaining_time": "0:44:13"}
|
||||
{"current_steps": 3610, "total_steps": 4214, "loss": 0.209, "lr": 2.4601543722268306e-06, "epoch": 5.996677740863787, "percentage": 85.67, "elapsed_time": "4:22:22", "remaining_time": "0:43:53"}
|
||||
{"current_steps": 3615, "total_steps": 4214, "loss": 0.238, "lr": 2.4204961835513263e-06, "epoch": 6.004983388704319, "percentage": 85.79, "elapsed_time": "4:22:57", "remaining_time": "0:43:34"}
|
||||
{"current_steps": 3620, "total_steps": 4214, "loss": 0.2388, "lr": 2.381139648875874e-06, "epoch": 6.01328903654485, "percentage": 85.9, "elapsed_time": "4:23:35", "remaining_time": "0:43:15"}
|
||||
{"current_steps": 3625, "total_steps": 4214, "loss": 0.2345, "lr": 2.342085443535582e-06, "epoch": 6.0215946843853825, "percentage": 86.02, "elapsed_time": "4:24:08", "remaining_time": "0:42:55"}
|
||||
{"current_steps": 3630, "total_steps": 4214, "loss": 0.2064, "lr": 2.303334237677761e-06, "epoch": 6.029900332225914, "percentage": 86.14, "elapsed_time": "4:24:41", "remaining_time": "0:42:35"}
|
||||
{"current_steps": 3635, "total_steps": 4214, "loss": 0.2392, "lr": 2.264886696250428e-06, "epoch": 6.038205980066445, "percentage": 86.26, "elapsed_time": "4:25:19", "remaining_time": "0:42:15"}
|
||||
{"current_steps": 3640, "total_steps": 4214, "loss": 0.2494, "lr": 2.226743478990907e-06, "epoch": 6.046511627906977, "percentage": 86.38, "elapsed_time": "4:25:56", "remaining_time": "0:41:56"}
|
||||
{"current_steps": 3645, "total_steps": 4214, "loss": 0.2359, "lr": 2.188905240414485e-06, "epoch": 6.054817275747508, "percentage": 86.5, "elapsed_time": "4:26:33", "remaining_time": "0:41:36"}
|
||||
{"current_steps": 3650, "total_steps": 4214, "loss": 0.2362, "lr": 2.1513726298031943e-06, "epoch": 6.06312292358804, "percentage": 86.62, "elapsed_time": "4:27:09", "remaining_time": "0:41:16"}
|
||||
{"current_steps": 3655, "total_steps": 4214, "loss": 0.2238, "lr": 2.114146291194683e-06, "epoch": 6.071428571428571, "percentage": 86.73, "elapsed_time": "4:27:45", "remaining_time": "0:40:57"}
|
||||
{"current_steps": 3660, "total_steps": 4214, "loss": 0.2064, "lr": 2.0772268633711333e-06, "epoch": 6.079734219269103, "percentage": 86.85, "elapsed_time": "4:28:18", "remaining_time": "0:40:36"}
|
||||
{"current_steps": 3665, "total_steps": 4214, "loss": 0.2227, "lr": 2.040614979848323e-06, "epoch": 6.088039867109635, "percentage": 86.97, "elapsed_time": "4:28:58", "remaining_time": "0:40:17"}
|
||||
{"current_steps": 3670, "total_steps": 4214, "loss": 0.216, "lr": 2.0043112688647624e-06, "epoch": 6.096345514950166, "percentage": 87.09, "elapsed_time": "4:29:32", "remaining_time": "0:39:57"}
|
||||
{"current_steps": 3675, "total_steps": 4214, "loss": 0.2271, "lr": 1.9683163533708804e-06, "epoch": 6.104651162790698, "percentage": 87.21, "elapsed_time": "4:30:06", "remaining_time": "0:39:36"}
|
||||
{"current_steps": 3680, "total_steps": 4214, "loss": 0.2335, "lr": 1.9326308510183778e-06, "epoch": 6.112956810631229, "percentage": 87.33, "elapsed_time": "4:30:44", "remaining_time": "0:39:17"}
|
||||
{"current_steps": 3685, "total_steps": 4214, "loss": 0.2339, "lr": 1.8972553741495891e-06, "epoch": 6.121262458471761, "percentage": 87.45, "elapsed_time": "4:31:22", "remaining_time": "0:38:57"}
|
||||
{"current_steps": 3690, "total_steps": 4214, "loss": 0.2366, "lr": 1.8621905297870001e-06, "epoch": 6.129568106312292, "percentage": 87.57, "elapsed_time": "4:32:02", "remaining_time": "0:38:37"}
|
||||
{"current_steps": 3695, "total_steps": 4214, "loss": 0.2207, "lr": 1.827436919622827e-06, "epoch": 6.137873754152824, "percentage": 87.68, "elapsed_time": "4:32:41", "remaining_time": "0:38:18"}
|
||||
{"current_steps": 3700, "total_steps": 4214, "loss": 0.2389, "lr": 1.7929951400086865e-06, "epoch": 6.146179401993355, "percentage": 87.8, "elapsed_time": "4:33:18", "remaining_time": "0:37:58"}
|
||||
{"current_steps": 3705, "total_steps": 4214, "loss": 0.2399, "lr": 1.7588657819453647e-06, "epoch": 6.1544850498338874, "percentage": 87.92, "elapsed_time": "4:33:56", "remaining_time": "0:37:38"}
|
||||
{"current_steps": 3710, "total_steps": 4214, "loss": 0.2245, "lr": 1.7250494310726717e-06, "epoch": 6.162790697674419, "percentage": 88.04, "elapsed_time": "4:34:32", "remaining_time": "0:37:17"}
|
||||
{"current_steps": 3715, "total_steps": 4214, "loss": 0.2487, "lr": 1.6915466676594139e-06, "epoch": 6.17109634551495, "percentage": 88.16, "elapsed_time": "4:35:10", "remaining_time": "0:36:57"}
|
||||
{"current_steps": 3720, "total_steps": 4214, "loss": 0.2144, "lr": 1.6583580665934019e-06, "epoch": 6.179401993355482, "percentage": 88.28, "elapsed_time": "4:35:44", "remaining_time": "0:36:37"}
|
||||
{"current_steps": 3725, "total_steps": 4214, "loss": 0.2385, "lr": 1.625484197371614e-06, "epoch": 6.187707641196013, "percentage": 88.4, "elapsed_time": "4:36:26", "remaining_time": "0:36:17"}
|
||||
{"current_steps": 3730, "total_steps": 4214, "loss": 0.2147, "lr": 1.5929256240904134e-06, "epoch": 6.196013289036545, "percentage": 88.51, "elapsed_time": "4:37:02", "remaining_time": "0:35:56"}
|
||||
{"current_steps": 3735, "total_steps": 4214, "loss": 0.2111, "lr": 1.5606829054358686e-06, "epoch": 6.204318936877076, "percentage": 88.63, "elapsed_time": "4:37:36", "remaining_time": "0:35:36"}
|
||||
{"current_steps": 3740, "total_steps": 4214, "loss": 0.2454, "lr": 1.5287565946741634e-06, "epoch": 6.212624584717608, "percentage": 88.75, "elapsed_time": "4:38:18", "remaining_time": "0:35:16"}
|
||||
{"current_steps": 3745, "total_steps": 4214, "loss": 0.218, "lr": 1.4971472396421117e-06, "epoch": 6.22093023255814, "percentage": 88.87, "elapsed_time": "4:38:57", "remaining_time": "0:34:56"}
|
||||
{"current_steps": 3750, "total_steps": 4214, "loss": 0.2058, "lr": 1.4658553827377576e-06, "epoch": 6.229235880398671, "percentage": 88.99, "elapsed_time": "4:39:35", "remaining_time": "0:34:35"}
|
||||
{"current_steps": 3755, "total_steps": 4214, "loss": 0.2409, "lr": 1.4348815609110522e-06, "epoch": 6.237541528239203, "percentage": 89.11, "elapsed_time": "4:40:11", "remaining_time": "0:34:15"}
|
||||
{"current_steps": 3760, "total_steps": 4214, "loss": 0.2151, "lr": 1.4042263056546568e-06, "epoch": 6.245847176079734, "percentage": 89.23, "elapsed_time": "4:40:52", "remaining_time": "0:33:54"}
|
||||
{"current_steps": 3765, "total_steps": 4214, "loss": 0.2377, "lr": 1.3738901429948115e-06, "epoch": 6.254152823920266, "percentage": 89.35, "elapsed_time": "4:41:28", "remaining_time": "0:33:34"}
|
||||
{"current_steps": 3770, "total_steps": 4214, "loss": 0.2178, "lr": 1.3438735934823277e-06, "epoch": 6.262458471760797, "percentage": 89.46, "elapsed_time": "4:42:01", "remaining_time": "0:33:12"}
|
||||
{"current_steps": 3775, "total_steps": 4214, "loss": 0.2221, "lr": 1.314177172183626e-06, "epoch": 6.270764119601329, "percentage": 89.58, "elapsed_time": "4:42:36", "remaining_time": "0:32:51"}
|
||||
{"current_steps": 3780, "total_steps": 4214, "loss": 0.2405, "lr": 1.2848013886719213e-06, "epoch": 6.27906976744186, "percentage": 89.7, "elapsed_time": "4:43:12", "remaining_time": "0:32:31"}
|
||||
{"current_steps": 3785, "total_steps": 4214, "loss": 0.2233, "lr": 1.2557467470184759e-06, "epoch": 6.287375415282392, "percentage": 89.82, "elapsed_time": "4:43:48", "remaining_time": "0:32:10"}
|
||||
{"current_steps": 3790, "total_steps": 4214, "loss": 0.2196, "lr": 1.2270137457839382e-06, "epoch": 6.295681063122924, "percentage": 89.94, "elapsed_time": "4:44:24", "remaining_time": "0:31:49"}
|
||||
{"current_steps": 3795, "total_steps": 4214, "loss": 0.2178, "lr": 1.198602878009798e-06, "epoch": 6.303986710963455, "percentage": 90.06, "elapsed_time": "4:44:58", "remaining_time": "0:31:27"}
|
||||
{"current_steps": 3800, "total_steps": 4214, "loss": 0.2232, "lr": 1.1705146312099203e-06, "epoch": 6.312292358803987, "percentage": 90.18, "elapsed_time": "4:45:37", "remaining_time": "0:31:07"}
|
||||
{"current_steps": 3805, "total_steps": 4214, "loss": 0.253, "lr": 1.1427494873621935e-06, "epoch": 6.320598006644518, "percentage": 90.29, "elapsed_time": "4:46:17", "remaining_time": "0:30:46"}
|
||||
{"current_steps": 3810, "total_steps": 4214, "loss": 0.2487, "lr": 1.1153079229002394e-06, "epoch": 6.32890365448505, "percentage": 90.41, "elapsed_time": "4:46:58", "remaining_time": "0:30:25"}
|
||||
{"current_steps": 3815, "total_steps": 4214, "loss": 0.2378, "lr": 1.088190408705243e-06, "epoch": 6.337209302325581, "percentage": 90.53, "elapsed_time": "4:47:34", "remaining_time": "0:30:04"}
|
||||
{"current_steps": 3820, "total_steps": 4214, "loss": 0.2331, "lr": 1.0613974100978885e-06, "epoch": 6.3455149501661126, "percentage": 90.65, "elapsed_time": "4:48:15", "remaining_time": "0:29:43"}
|
||||
{"current_steps": 3825, "total_steps": 4214, "loss": 0.2418, "lr": 1.0349293868303501e-06, "epoch": 6.353820598006645, "percentage": 90.77, "elapsed_time": "4:48:54", "remaining_time": "0:29:22"}
|
||||
{"current_steps": 3830, "total_steps": 4214, "loss": 0.2268, "lr": 1.0087867930784268e-06, "epoch": 6.362126245847176, "percentage": 90.89, "elapsed_time": "4:49:28", "remaining_time": "0:29:01"}
|
||||
{"current_steps": 3835, "total_steps": 4214, "loss": 0.231, "lr": 9.829700774337314e-07, "epoch": 6.370431893687708, "percentage": 91.01, "elapsed_time": "4:50:05", "remaining_time": "0:28:40"}
|
||||
{"current_steps": 3840, "total_steps": 4214, "loss": 0.2441, "lr": 9.57479682895992e-07, "epoch": 6.378737541528239, "percentage": 91.12, "elapsed_time": "4:50:44", "remaining_time": "0:28:19"}
|
||||
{"current_steps": 3845, "total_steps": 4214, "loss": 0.2286, "lr": 9.323160468654757e-07, "epoch": 6.387043189368771, "percentage": 91.24, "elapsed_time": "4:51:24", "remaining_time": "0:27:57"}
|
||||
{"current_steps": 3850, "total_steps": 4214, "loss": 0.2341, "lr": 9.074796011354481e-07, "epoch": 6.395348837209302, "percentage": 91.36, "elapsed_time": "4:51:59", "remaining_time": "0:27:36"}
|
||||
{"current_steps": 3855, "total_steps": 4214, "loss": 0.2265, "lr": 8.829707718847835e-07, "epoch": 6.403654485049834, "percentage": 91.48, "elapsed_time": "4:52:33", "remaining_time": "0:27:14"}
|
||||
{"current_steps": 3860, "total_steps": 4214, "loss": 0.2314, "lr": 8.587899796706578e-07, "epoch": 6.411960132890365, "percentage": 91.6, "elapsed_time": "4:53:08", "remaining_time": "0:26:52"}
|
||||
{"current_steps": 3865, "total_steps": 4214, "loss": 0.2227, "lr": 8.34937639421316e-07, "epoch": 6.420265780730897, "percentage": 91.72, "elapsed_time": "4:53:45", "remaining_time": "0:26:31"}
|
||||
{"current_steps": 3870, "total_steps": 4214, "loss": 0.2367, "lr": 8.114141604289627e-07, "epoch": 6.428571428571429, "percentage": 91.84, "elapsed_time": "4:54:23", "remaining_time": "0:26:10"}
|
||||
{"current_steps": 3875, "total_steps": 4214, "loss": 0.2326, "lr": 7.882199463427276e-07, "epoch": 6.43687707641196, "percentage": 91.96, "elapsed_time": "4:55:03", "remaining_time": "0:25:48"}
|
||||
{"current_steps": 3880, "total_steps": 4214, "loss": 0.2381, "lr": 7.653553951617642e-07, "epoch": 6.445182724252492, "percentage": 92.07, "elapsed_time": "4:55:43", "remaining_time": "0:25:27"}
|
||||
{"current_steps": 3885, "total_steps": 4214, "loss": 0.2385, "lr": 7.428208992283848e-07, "epoch": 6.453488372093023, "percentage": 92.19, "elapsed_time": "4:56:14", "remaining_time": "0:25:05"}
|
||||
{"current_steps": 3890, "total_steps": 4214, "loss": 0.2408, "lr": 7.206168452213602e-07, "epoch": 6.461794019933555, "percentage": 92.31, "elapsed_time": "4:56:51", "remaining_time": "0:24:43"}
|
||||
{"current_steps": 3895, "total_steps": 4214, "loss": 0.2122, "lr": 6.987436141492598e-07, "epoch": 6.470099667774086, "percentage": 92.43, "elapsed_time": "4:57:27", "remaining_time": "0:24:21"}
|
||||
{"current_steps": 3900, "total_steps": 4214, "loss": 0.2318, "lr": 6.772015813439381e-07, "epoch": 6.4784053156146175, "percentage": 92.55, "elapsed_time": "4:58:07", "remaining_time": "0:24:00"}
|
||||
{"current_steps": 3905, "total_steps": 4214, "loss": 0.2468, "lr": 6.559911164540711e-07, "epoch": 6.48671096345515, "percentage": 92.67, "elapsed_time": "4:58:44", "remaining_time": "0:23:38"}
|
||||
{"current_steps": 3910, "total_steps": 4214, "loss": 0.2183, "lr": 6.351125834388239e-07, "epoch": 6.495016611295681, "percentage": 92.79, "elapsed_time": "4:59:19", "remaining_time": "0:23:16"}
|
||||
{"current_steps": 3915, "total_steps": 4214, "loss": 0.2495, "lr": 6.145663405616131e-07, "epoch": 6.503322259136213, "percentage": 92.9, "elapsed_time": "4:59:55", "remaining_time": "0:22:54"}
|
||||
{"current_steps": 3920, "total_steps": 4214, "loss": 0.2195, "lr": 5.943527403839433e-07, "epoch": 6.511627906976744, "percentage": 93.02, "elapsed_time": "5:00:27", "remaining_time": "0:22:32"}
|
||||
{"current_steps": 3925, "total_steps": 4214, "loss": 0.2321, "lr": 5.744721297593647e-07, "epoch": 6.519933554817276, "percentage": 93.14, "elapsed_time": "5:01:02", "remaining_time": "0:22:09"}
|
||||
{"current_steps": 3930, "total_steps": 4214, "loss": 0.2327, "lr": 5.549248498275228e-07, "epoch": 6.528239202657807, "percentage": 93.26, "elapsed_time": "5:01:42", "remaining_time": "0:21:48"}
|
||||
{"current_steps": 3935, "total_steps": 4214, "loss": 0.24, "lr": 5.357112360083094e-07, "epoch": 6.5365448504983386, "percentage": 93.38, "elapsed_time": "5:02:23", "remaining_time": "0:21:26"}
|
||||
{"current_steps": 3940, "total_steps": 4214, "loss": 0.2304, "lr": 5.168316179960941e-07, "epoch": 6.544850498338871, "percentage": 93.5, "elapsed_time": "5:02:54", "remaining_time": "0:21:03"}
|
||||
{"current_steps": 3945, "total_steps": 4214, "loss": 0.2184, "lr": 4.982863197540733e-07, "epoch": 6.553156146179402, "percentage": 93.62, "elapsed_time": "5:03:29", "remaining_time": "0:20:41"}
|
||||
{"current_steps": 3950, "total_steps": 4214, "loss": 0.2266, "lr": 4.800756595087164e-07, "epoch": 6.561461794019934, "percentage": 93.74, "elapsed_time": "5:04:06", "remaining_time": "0:20:19"}
|
||||
{"current_steps": 3955, "total_steps": 4214, "loss": 0.2375, "lr": 4.6219994974429973e-07, "epoch": 6.569767441860465, "percentage": 93.85, "elapsed_time": "5:04:39", "remaining_time": "0:19:57"}
|
||||
{"current_steps": 3960, "total_steps": 4214, "loss": 0.2637, "lr": 4.446594971975415e-07, "epoch": 6.578073089700997, "percentage": 93.97, "elapsed_time": "5:05:18", "remaining_time": "0:19:34"}
|
||||
{"current_steps": 3965, "total_steps": 4214, "loss": 0.2055, "lr": 4.274546028523441e-07, "epoch": 6.586378737541528, "percentage": 94.09, "elapsed_time": "5:05:57", "remaining_time": "0:19:12"}
|
||||
{"current_steps": 3970, "total_steps": 4214, "loss": 0.2587, "lr": 4.1058556193463327e-07, "epoch": 6.59468438538206, "percentage": 94.21, "elapsed_time": "5:06:40", "remaining_time": "0:18:50"}
|
||||
{"current_steps": 3975, "total_steps": 4214, "loss": 0.231, "lr": 3.9405266390727836e-07, "epoch": 6.602990033222591, "percentage": 94.33, "elapsed_time": "5:07:22", "remaining_time": "0:18:28"}
|
||||
{"current_steps": 3980, "total_steps": 4214, "loss": 0.2412, "lr": 3.778561924651336e-07, "epoch": 6.6112956810631225, "percentage": 94.45, "elapsed_time": "5:08:04", "remaining_time": "0:18:06"}
|
||||
{"current_steps": 3985, "total_steps": 4214, "loss": 0.2559, "lr": 3.6199642553017776e-07, "epoch": 6.619601328903655, "percentage": 94.57, "elapsed_time": "5:08:39", "remaining_time": "0:17:44"}
|
||||
{"current_steps": 3990, "total_steps": 4214, "loss": 0.2445, "lr": 3.4647363524672906e-07, "epoch": 6.627906976744186, "percentage": 94.68, "elapsed_time": "5:09:16", "remaining_time": "0:17:21"}
|
||||
{"current_steps": 3995, "total_steps": 4214, "loss": 0.2357, "lr": 3.312880879767888e-07, "epoch": 6.636212624584718, "percentage": 94.8, "elapsed_time": "5:09:50", "remaining_time": "0:16:59"}
|
||||
{"current_steps": 4000, "total_steps": 4214, "loss": 0.2443, "lr": 3.164400442954607e-07, "epoch": 6.644518272425249, "percentage": 94.92, "elapsed_time": "5:10:28", "remaining_time": "0:16:36"}
|
||||
{"current_steps": 4005, "total_steps": 4214, "loss": 0.2334, "lr": 3.0192975898649e-07, "epoch": 6.652823920265781, "percentage": 95.04, "elapsed_time": "5:11:07", "remaining_time": "0:16:14"}
|
||||
{"current_steps": 4010, "total_steps": 4214, "loss": 0.2489, "lr": 2.8775748103788026e-07, "epoch": 6.661129568106312, "percentage": 95.16, "elapsed_time": "5:11:44", "remaining_time": "0:15:51"}
|
||||
{"current_steps": 4015, "total_steps": 4214, "loss": 0.2195, "lr": 2.739234536376301e-07, "epoch": 6.6694352159468435, "percentage": 95.28, "elapsed_time": "5:12:17", "remaining_time": "0:15:28"}
|
||||
{"current_steps": 4020, "total_steps": 4214, "loss": 0.2241, "lr": 2.604279141695565e-07, "epoch": 6.677740863787376, "percentage": 95.4, "elapsed_time": "5:12:58", "remaining_time": "0:15:06"}
|
||||
{"current_steps": 4025, "total_steps": 4214, "loss": 0.235, "lr": 2.4727109420921826e-07, "epoch": 6.686046511627907, "percentage": 95.51, "elapsed_time": "5:13:33", "remaining_time": "0:14:43"}
|
||||
{"current_steps": 4030, "total_steps": 4214, "loss": 0.2299, "lr": 2.3445321951995003e-07, "epoch": 6.694352159468439, "percentage": 95.63, "elapsed_time": "5:14:05", "remaining_time": "0:14:20"}
|
||||
{"current_steps": 4035, "total_steps": 4214, "loss": 0.2289, "lr": 2.219745100489834e-07, "epoch": 6.70265780730897, "percentage": 95.75, "elapsed_time": "5:14:40", "remaining_time": "0:13:57"}
|
||||
{"current_steps": 4040, "total_steps": 4214, "loss": 0.2263, "lr": 2.0983517992366975e-07, "epoch": 6.710963455149502, "percentage": 95.87, "elapsed_time": "5:15:16", "remaining_time": "0:13:34"}
|
||||
{"current_steps": 4045, "total_steps": 4214, "loss": 0.2342, "lr": 1.9803543744780994e-07, "epoch": 6.719269102990033, "percentage": 95.99, "elapsed_time": "5:15:56", "remaining_time": "0:13:11"}
|
||||
{"current_steps": 4050, "total_steps": 4214, "loss": 0.2196, "lr": 1.865754850980861e-07, "epoch": 6.7275747508305646, "percentage": 96.11, "elapsed_time": "5:16:32", "remaining_time": "0:12:49"}
|
||||
{"current_steps": 4055, "total_steps": 4214, "loss": 0.2232, "lr": 1.7545551952057095e-07, "epoch": 6.735880398671096, "percentage": 96.23, "elapsed_time": "5:17:10", "remaining_time": "0:12:26"}
|
||||
{"current_steps": 4060, "total_steps": 4214, "loss": 0.2393, "lr": 1.6467573152736837e-07, "epoch": 6.7441860465116275, "percentage": 96.35, "elapsed_time": "5:17:50", "remaining_time": "0:12:03"}
|
||||
{"current_steps": 4065, "total_steps": 4214, "loss": 0.2124, "lr": 1.5423630609333607e-07, "epoch": 6.75249169435216, "percentage": 96.46, "elapsed_time": "5:18:24", "remaining_time": "0:11:40"}
|
||||
{"current_steps": 4070, "total_steps": 4214, "loss": 0.2255, "lr": 1.4413742235290573e-07, "epoch": 6.760797342192691, "percentage": 96.58, "elapsed_time": "5:19:00", "remaining_time": "0:11:17"}
|
||||
{"current_steps": 4075, "total_steps": 4214, "loss": 0.2251, "lr": 1.3437925359701008e-07, "epoch": 6.769102990033223, "percentage": 96.7, "elapsed_time": "5:19:36", "remaining_time": "0:10:54"}
|
||||
{"current_steps": 4080, "total_steps": 4214, "loss": 0.2207, "lr": 1.2496196727011856e-07, "epoch": 6.777408637873754, "percentage": 96.82, "elapsed_time": "5:20:10", "remaining_time": "0:10:30"}
|
||||
{"current_steps": 4085, "total_steps": 4214, "loss": 0.239, "lr": 1.1588572496735506e-07, "epoch": 6.785714285714286, "percentage": 96.94, "elapsed_time": "5:20:47", "remaining_time": "0:10:07"}
|
||||
{"current_steps": 4090, "total_steps": 4214, "loss": 0.2302, "lr": 1.0715068243172699e-07, "epoch": 6.794019933554817, "percentage": 97.06, "elapsed_time": "5:21:21", "remaining_time": "0:09:44"}
|
||||
{"current_steps": 4095, "total_steps": 4214, "loss": 0.2306, "lr": 9.875698955145174e-08, "epoch": 6.8023255813953485, "percentage": 97.18, "elapsed_time": "5:21:58", "remaining_time": "0:09:21"}
|
||||
{"current_steps": 4100, "total_steps": 4214, "loss": 0.2297, "lr": 9.070479035738988e-08, "epoch": 6.810631229235881, "percentage": 97.29, "elapsed_time": "5:22:38", "remaining_time": "0:08:58"}
|
||||
{"current_steps": 4105, "total_steps": 4214, "loss": 0.2194, "lr": 8.299422302056715e-08, "epoch": 6.818936877076412, "percentage": 97.41, "elapsed_time": "5:23:17", "remaining_time": "0:08:35"}
|
||||
{"current_steps": 4110, "total_steps": 4214, "loss": 0.2324, "lr": 7.562541984980964e-08, "epoch": 6.827242524916944, "percentage": 97.53, "elapsed_time": "5:23:54", "remaining_time": "0:08:11"}
|
||||
{"current_steps": 4115, "total_steps": 4214, "loss": 0.2316, "lr": 6.85985072894657e-08, "epoch": 6.835548172757475, "percentage": 97.65, "elapsed_time": "5:24:29", "remaining_time": "0:07:48"}
|
||||
{"current_steps": 4120, "total_steps": 4214, "loss": 0.2426, "lr": 6.19136059172476e-08, "epoch": 6.843853820598007, "percentage": 97.77, "elapsed_time": "5:25:04", "remaining_time": "0:07:25"}
|
||||
{"current_steps": 4125, "total_steps": 4214, "loss": 0.2344, "lr": 5.557083044214651e-08, "epoch": 6.852159468438538, "percentage": 97.89, "elapsed_time": "5:25:43", "remaining_time": "0:07:01"}
|
||||
{"current_steps": 4130, "total_steps": 4214, "loss": 0.2351, "lr": 4.957028970248301e-08, "epoch": 6.8604651162790695, "percentage": 98.01, "elapsed_time": "5:26:17", "remaining_time": "0:06:38"}
|
||||
{"current_steps": 4135, "total_steps": 4214, "loss": 0.2305, "lr": 4.3912086664021914e-08, "epoch": 6.868770764119601, "percentage": 98.13, "elapsed_time": "5:26:51", "remaining_time": "0:06:14"}
|
||||
{"current_steps": 4140, "total_steps": 4214, "loss": 0.2482, "lr": 3.859631841822031e-08, "epoch": 6.877076411960132, "percentage": 98.24, "elapsed_time": "5:27:29", "remaining_time": "0:05:51"}
|
||||
{"current_steps": 4145, "total_steps": 4214, "loss": 0.2482, "lr": 3.3623076180548944e-08, "epoch": 6.885382059800665, "percentage": 98.36, "elapsed_time": "5:28:04", "remaining_time": "0:05:27"}
|
||||
{"current_steps": 4150, "total_steps": 4214, "loss": 0.2476, "lr": 2.8992445288935633e-08, "epoch": 6.893687707641196, "percentage": 98.48, "elapsed_time": "5:28:44", "remaining_time": "0:05:04"}
|
||||
{"current_steps": 4155, "total_steps": 4214, "loss": 0.2241, "lr": 2.4704505202295393e-08, "epoch": 6.901993355481728, "percentage": 98.6, "elapsed_time": "5:29:22", "remaining_time": "0:04:40"}
|
||||
{"current_steps": 4160, "total_steps": 4214, "loss": 0.2359, "lr": 2.0759329499173698e-08, "epoch": 6.910299003322259, "percentage": 98.72, "elapsed_time": "5:29:55", "remaining_time": "0:04:16"}
|
||||
{"current_steps": 4165, "total_steps": 4214, "loss": 0.2328, "lr": 1.7156985876476406e-08, "epoch": 6.9186046511627906, "percentage": 98.84, "elapsed_time": "5:30:33", "remaining_time": "0:03:53"}
|
||||
{"current_steps": 4170, "total_steps": 4214, "loss": 0.225, "lr": 1.3897536148310687e-08, "epoch": 6.926910299003322, "percentage": 98.96, "elapsed_time": "5:31:10", "remaining_time": "0:03:29"}
|
||||
{"current_steps": 4175, "total_steps": 4214, "loss": 0.24, "lr": 1.09810362449303e-08, "epoch": 6.9352159468438535, "percentage": 99.07, "elapsed_time": "5:31:47", "remaining_time": "0:03:05"}
|
||||
{"current_steps": 4180, "total_steps": 4214, "loss": 0.226, "lr": 8.407536211765265e-09, "epoch": 6.943521594684386, "percentage": 99.19, "elapsed_time": "5:32:25", "remaining_time": "0:02:42"}
|
||||
{"current_steps": 4185, "total_steps": 4214, "loss": 0.2363, "lr": 6.1770802085714395e-09, "epoch": 6.951827242524917, "percentage": 99.31, "elapsed_time": "5:33:00", "remaining_time": "0:02:18"}
|
||||
{"current_steps": 4190, "total_steps": 4214, "loss": 0.2283, "lr": 4.289706508666669e-09, "epoch": 6.960132890365449, "percentage": 99.43, "elapsed_time": "5:33:39", "remaining_time": "0:01:54"}
|
||||
{"current_steps": 4195, "total_steps": 4214, "loss": 0.2446, "lr": 2.7454474982824276e-09, "epoch": 6.96843853820598, "percentage": 99.55, "elapsed_time": "5:34:18", "remaining_time": "0:01:30"}
|
||||
{"current_steps": 4200, "total_steps": 4214, "loss": 0.2271, "lr": 1.5443296759976022e-09, "epoch": 6.976744186046512, "percentage": 99.67, "elapsed_time": "5:34:50", "remaining_time": "0:01:06"}
|
||||
{"current_steps": 4205, "total_steps": 4214, "loss": 0.2326, "lr": 6.863736522899623e-10, "epoch": 6.985049833887043, "percentage": 99.79, "elapsed_time": "5:35:31", "remaining_time": "0:00:43"}
|
||||
{"current_steps": 4210, "total_steps": 4214, "loss": 0.2403, "lr": 1.715941491853279e-10, "epoch": 6.9933554817275745, "percentage": 99.91, "elapsed_time": "5:36:10", "remaining_time": "0:00:19"}
|
||||
{"current_steps": 4214, "total_steps": 4214, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "5:36:54", "remaining_time": "0:00:00"}
|
||||
9309
trainer_state.json
Normal file
9309
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 sha256:8e2026e74605de47abea2db3907e94fc36602676fb6d6f7ad4244438841e78d0
|
||||
size 8657
|
||||
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 44 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