初始化项目,由ModelHub XC社区提供模型

Model: DCAgent/a1-ghactions
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-05 02:19:57 +08:00
commit 2f50a30ef4
23 changed files with 162310 additions and 0 deletions

36
.gitattributes vendored Normal file
View 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
View 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_ghactions__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_ghactions__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_ghactions_glm_4.7_traces_jupiter/snapshots/640f8ad849fb18ab4a07eb41d7a469a33c7811bf_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
View 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
View File

@@ -0,0 +1,16 @@
{
"achieved_tflops_per_gpu": 0.0030214454931977936,
"achieved_tflops_per_gpu_theoretical": 498.0219707350057,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.11442745476961136,
"mfu_percent": 0.00021352971683376632,
"mfu_percent_theoretical": 35.1958989918732,
"total_flos": 1222766426718208.0,
"train_loss": 0.19705863873869428,
"train_runtime": 25293.4901,
"train_samples_per_second": 2.35,
"train_steps_per_second": 0.147,
"valid_targets_mean": 7264.7,
"valid_targets_min": 669
}

89
chat_template.jinja Normal file
View 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
View 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
View 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

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:64a39227ce3824aef7f0cf2f998ec475cd6fe5fd89bbb8fb3df42b90a6618ab5
size 4902257696

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ede3492c4aeb247815b02d6c6b32b6542923df4f54c80029068b28f4b4fbcd6f
size 4915960368

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c88e845f28196a632caab86dfacc1ea52337cbffa6d5bf9516fa5c83bac0382a
size 4983068496

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1810bc2830d5ee2d11140dacce15a826791bcbb594017e9c21e72c2de0e89426
size 1580230264

View 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
View File

@@ -0,0 +1,12 @@
{
"agent_name": "640f8ad849fb18ab4a07eb41d7a469a33c7811bf_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_ghactions_glm_4.7_traces_jupiter/snapshots/640f8ad849fb18ab4a07eb41d7a469a33c7811bf_thinking_preprocessed",
"training_type": "SFT",
"training_parameters": "https://huggingface.co/DCAgent/a1-ghactions/blob/main/config.json",
"wandb_link": null,
"traces_location_s3": null
}

31
special_tokens_map.json Normal file
View 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
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
size 11422654

240
tokenizer_config.json Normal file
View 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
View File

@@ -0,0 +1,16 @@
{
"achieved_tflops_per_gpu": 0.0030214454931977936,
"achieved_tflops_per_gpu_theoretical": 498.0219707350057,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.11442745476961136,
"mfu_percent": 0.00021352971683376632,
"mfu_percent_theoretical": 35.1958989918732,
"total_flos": 1222766426718208.0,
"train_loss": 0.19705863873869428,
"train_runtime": 25293.4901,
"train_samples_per_second": 2.35,
"train_steps_per_second": 0.147,
"valid_targets_mean": 7264.7,
"valid_targets_min": 669
}

744
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,744 @@
{"current_steps": 5, "total_steps": 3717, "loss": 0.5903, "lr": 4.301075268817205e-07, "epoch": 0.009416195856873822, "percentage": 0.13, "elapsed_time": "0:00:40", "remaining_time": "8:17:02"}
{"current_steps": 10, "total_steps": 3717, "loss": 0.5832, "lr": 9.67741935483871e-07, "epoch": 0.018832391713747645, "percentage": 0.27, "elapsed_time": "0:01:16", "remaining_time": "7:53:05"}
{"current_steps": 15, "total_steps": 3717, "loss": 0.5947, "lr": 1.5053763440860217e-06, "epoch": 0.02824858757062147, "percentage": 0.4, "elapsed_time": "0:01:49", "remaining_time": "7:32:00"}
{"current_steps": 20, "total_steps": 3717, "loss": 0.5399, "lr": 2.043010752688172e-06, "epoch": 0.03766478342749529, "percentage": 0.54, "elapsed_time": "0:02:26", "remaining_time": "7:30:21"}
{"current_steps": 25, "total_steps": 3717, "loss": 0.5036, "lr": 2.580645161290323e-06, "epoch": 0.047080979284369114, "percentage": 0.67, "elapsed_time": "0:02:58", "remaining_time": "7:18:07"}
{"current_steps": 30, "total_steps": 3717, "loss": 0.4993, "lr": 3.1182795698924735e-06, "epoch": 0.05649717514124294, "percentage": 0.81, "elapsed_time": "0:03:35", "remaining_time": "7:20:48"}
{"current_steps": 35, "total_steps": 3717, "loss": 0.4378, "lr": 3.655913978494624e-06, "epoch": 0.06591337099811675, "percentage": 0.94, "elapsed_time": "0:04:11", "remaining_time": "7:21:00"}
{"current_steps": 40, "total_steps": 3717, "loss": 0.4221, "lr": 4.193548387096774e-06, "epoch": 0.07532956685499058, "percentage": 1.08, "elapsed_time": "0:04:44", "remaining_time": "7:15:34"}
{"current_steps": 45, "total_steps": 3717, "loss": 0.3869, "lr": 4.731182795698925e-06, "epoch": 0.0847457627118644, "percentage": 1.21, "elapsed_time": "0:05:17", "remaining_time": "7:12:05"}
{"current_steps": 50, "total_steps": 3717, "loss": 0.3879, "lr": 5.268817204301076e-06, "epoch": 0.09416195856873823, "percentage": 1.35, "elapsed_time": "0:05:53", "remaining_time": "7:12:10"}
{"current_steps": 55, "total_steps": 3717, "loss": 0.3746, "lr": 5.806451612903226e-06, "epoch": 0.10357815442561205, "percentage": 1.48, "elapsed_time": "0:06:28", "remaining_time": "7:11:09"}
{"current_steps": 60, "total_steps": 3717, "loss": 0.3967, "lr": 6.344086021505377e-06, "epoch": 0.11299435028248588, "percentage": 1.61, "elapsed_time": "0:07:03", "remaining_time": "7:09:43"}
{"current_steps": 65, "total_steps": 3717, "loss": 0.4042, "lr": 6.881720430107528e-06, "epoch": 0.1224105461393597, "percentage": 1.75, "elapsed_time": "0:07:39", "remaining_time": "7:09:59"}
{"current_steps": 70, "total_steps": 3717, "loss": 0.3701, "lr": 7.4193548387096784e-06, "epoch": 0.1318267419962335, "percentage": 1.88, "elapsed_time": "0:08:10", "remaining_time": "7:06:14"}
{"current_steps": 75, "total_steps": 3717, "loss": 0.343, "lr": 7.956989247311828e-06, "epoch": 0.14124293785310735, "percentage": 2.02, "elapsed_time": "0:08:40", "remaining_time": "7:01:36"}
{"current_steps": 80, "total_steps": 3717, "loss": 0.3335, "lr": 8.494623655913979e-06, "epoch": 0.15065913370998116, "percentage": 2.15, "elapsed_time": "0:09:15", "remaining_time": "7:00:45"}
{"current_steps": 85, "total_steps": 3717, "loss": 0.3341, "lr": 9.03225806451613e-06, "epoch": 0.160075329566855, "percentage": 2.29, "elapsed_time": "0:09:50", "remaining_time": "7:00:21"}
{"current_steps": 90, "total_steps": 3717, "loss": 0.3371, "lr": 9.56989247311828e-06, "epoch": 0.1694915254237288, "percentage": 2.42, "elapsed_time": "0:10:22", "remaining_time": "6:57:58"}
{"current_steps": 95, "total_steps": 3717, "loss": 0.3718, "lr": 1.0107526881720431e-05, "epoch": 0.17890772128060264, "percentage": 2.56, "elapsed_time": "0:10:54", "remaining_time": "6:56:04"}
{"current_steps": 100, "total_steps": 3717, "loss": 0.3074, "lr": 1.0645161290322582e-05, "epoch": 0.18832391713747645, "percentage": 2.69, "elapsed_time": "0:11:31", "remaining_time": "6:56:34"}
{"current_steps": 105, "total_steps": 3717, "loss": 0.3401, "lr": 1.118279569892473e-05, "epoch": 0.1977401129943503, "percentage": 2.82, "elapsed_time": "0:12:09", "remaining_time": "6:58:15"}
{"current_steps": 110, "total_steps": 3717, "loss": 0.3255, "lr": 1.1720430107526883e-05, "epoch": 0.2071563088512241, "percentage": 2.96, "elapsed_time": "0:12:43", "remaining_time": "6:57:15"}
{"current_steps": 115, "total_steps": 3717, "loss": 0.3208, "lr": 1.2258064516129034e-05, "epoch": 0.21657250470809794, "percentage": 3.09, "elapsed_time": "0:13:15", "remaining_time": "6:55:26"}
{"current_steps": 120, "total_steps": 3717, "loss": 0.3199, "lr": 1.2795698924731184e-05, "epoch": 0.22598870056497175, "percentage": 3.23, "elapsed_time": "0:13:49", "remaining_time": "6:54:38"}
{"current_steps": 125, "total_steps": 3717, "loss": 0.3182, "lr": 1.3333333333333333e-05, "epoch": 0.23540489642184556, "percentage": 3.36, "elapsed_time": "0:14:25", "remaining_time": "6:54:44"}
{"current_steps": 130, "total_steps": 3717, "loss": 0.3055, "lr": 1.3870967741935486e-05, "epoch": 0.2448210922787194, "percentage": 3.5, "elapsed_time": "0:15:01", "remaining_time": "6:54:24"}
{"current_steps": 135, "total_steps": 3717, "loss": 0.3429, "lr": 1.4408602150537636e-05, "epoch": 0.2542372881355932, "percentage": 3.63, "elapsed_time": "0:15:38", "remaining_time": "6:54:53"}
{"current_steps": 140, "total_steps": 3717, "loss": 0.3451, "lr": 1.4946236559139787e-05, "epoch": 0.263653483992467, "percentage": 3.77, "elapsed_time": "0:16:12", "remaining_time": "6:54:07"}
{"current_steps": 145, "total_steps": 3717, "loss": 0.3035, "lr": 1.5483870967741936e-05, "epoch": 0.2730696798493409, "percentage": 3.9, "elapsed_time": "0:16:49", "remaining_time": "6:54:36"}
{"current_steps": 150, "total_steps": 3717, "loss": 0.298, "lr": 1.6021505376344087e-05, "epoch": 0.2824858757062147, "percentage": 4.04, "elapsed_time": "0:17:25", "remaining_time": "6:54:14"}
{"current_steps": 155, "total_steps": 3717, "loss": 0.3036, "lr": 1.6559139784946237e-05, "epoch": 0.2919020715630885, "percentage": 4.17, "elapsed_time": "0:18:02", "remaining_time": "6:54:47"}
{"current_steps": 160, "total_steps": 3717, "loss": 0.31, "lr": 1.7096774193548388e-05, "epoch": 0.3013182674199623, "percentage": 4.3, "elapsed_time": "0:18:40", "remaining_time": "6:55:17"}
{"current_steps": 165, "total_steps": 3717, "loss": 0.3133, "lr": 1.763440860215054e-05, "epoch": 0.3107344632768362, "percentage": 4.44, "elapsed_time": "0:19:15", "remaining_time": "6:54:44"}
{"current_steps": 170, "total_steps": 3717, "loss": 0.3373, "lr": 1.817204301075269e-05, "epoch": 0.32015065913371, "percentage": 4.57, "elapsed_time": "0:19:45", "remaining_time": "6:52:17"}
{"current_steps": 175, "total_steps": 3717, "loss": 0.3008, "lr": 1.870967741935484e-05, "epoch": 0.3295668549905838, "percentage": 4.71, "elapsed_time": "0:20:20", "remaining_time": "6:51:50"}
{"current_steps": 180, "total_steps": 3717, "loss": 0.3162, "lr": 1.924731182795699e-05, "epoch": 0.3389830508474576, "percentage": 4.84, "elapsed_time": "0:20:55", "remaining_time": "6:51:09"}
{"current_steps": 185, "total_steps": 3717, "loss": 0.3288, "lr": 1.978494623655914e-05, "epoch": 0.3483992467043315, "percentage": 4.98, "elapsed_time": "0:21:30", "remaining_time": "6:50:34"}
{"current_steps": 190, "total_steps": 3717, "loss": 0.2908, "lr": 2.0322580645161292e-05, "epoch": 0.3578154425612053, "percentage": 5.11, "elapsed_time": "0:22:05", "remaining_time": "6:50:00"}
{"current_steps": 195, "total_steps": 3717, "loss": 0.2954, "lr": 2.0860215053763443e-05, "epoch": 0.3672316384180791, "percentage": 5.25, "elapsed_time": "0:22:37", "remaining_time": "6:48:38"}
{"current_steps": 200, "total_steps": 3717, "loss": 0.2873, "lr": 2.1397849462365593e-05, "epoch": 0.3766478342749529, "percentage": 5.38, "elapsed_time": "0:23:14", "remaining_time": "6:48:40"}
{"current_steps": 205, "total_steps": 3717, "loss": 0.2727, "lr": 2.193548387096774e-05, "epoch": 0.3860640301318267, "percentage": 5.52, "elapsed_time": "0:23:48", "remaining_time": "6:47:50"}
{"current_steps": 210, "total_steps": 3717, "loss": 0.3009, "lr": 2.247311827956989e-05, "epoch": 0.3954802259887006, "percentage": 5.65, "elapsed_time": "0:24:23", "remaining_time": "6:47:21"}
{"current_steps": 215, "total_steps": 3717, "loss": 0.2883, "lr": 2.3010752688172045e-05, "epoch": 0.4048964218455744, "percentage": 5.78, "elapsed_time": "0:24:59", "remaining_time": "6:47:02"}
{"current_steps": 220, "total_steps": 3717, "loss": 0.2806, "lr": 2.3548387096774196e-05, "epoch": 0.4143126177024482, "percentage": 5.92, "elapsed_time": "0:25:35", "remaining_time": "6:46:44"}
{"current_steps": 225, "total_steps": 3717, "loss": 0.3102, "lr": 2.4086021505376347e-05, "epoch": 0.423728813559322, "percentage": 6.05, "elapsed_time": "0:26:07", "remaining_time": "6:45:30"}
{"current_steps": 230, "total_steps": 3717, "loss": 0.289, "lr": 2.4623655913978497e-05, "epoch": 0.4331450094161959, "percentage": 6.19, "elapsed_time": "0:26:40", "remaining_time": "6:44:22"}
{"current_steps": 235, "total_steps": 3717, "loss": 0.2773, "lr": 2.5161290322580648e-05, "epoch": 0.4425612052730697, "percentage": 6.32, "elapsed_time": "0:27:15", "remaining_time": "6:43:57"}
{"current_steps": 240, "total_steps": 3717, "loss": 0.2888, "lr": 2.56989247311828e-05, "epoch": 0.4519774011299435, "percentage": 6.46, "elapsed_time": "0:27:46", "remaining_time": "6:42:24"}
{"current_steps": 245, "total_steps": 3717, "loss": 0.2738, "lr": 2.6236559139784946e-05, "epoch": 0.4613935969868173, "percentage": 6.59, "elapsed_time": "0:28:20", "remaining_time": "6:41:37"}
{"current_steps": 250, "total_steps": 3717, "loss": 0.2788, "lr": 2.6774193548387097e-05, "epoch": 0.4708097928436911, "percentage": 6.73, "elapsed_time": "0:28:54", "remaining_time": "6:40:51"}
{"current_steps": 255, "total_steps": 3717, "loss": 0.3048, "lr": 2.7311827956989247e-05, "epoch": 0.480225988700565, "percentage": 6.86, "elapsed_time": "0:29:23", "remaining_time": "6:39:02"}
{"current_steps": 260, "total_steps": 3717, "loss": 0.2634, "lr": 2.78494623655914e-05, "epoch": 0.4896421845574388, "percentage": 6.99, "elapsed_time": "0:29:59", "remaining_time": "6:38:44"}
{"current_steps": 265, "total_steps": 3717, "loss": 0.2693, "lr": 2.8387096774193552e-05, "epoch": 0.4990583804143126, "percentage": 7.13, "elapsed_time": "0:30:33", "remaining_time": "6:38:02"}
{"current_steps": 270, "total_steps": 3717, "loss": 0.2695, "lr": 2.8924731182795703e-05, "epoch": 0.5084745762711864, "percentage": 7.26, "elapsed_time": "0:31:08", "remaining_time": "6:37:38"}
{"current_steps": 275, "total_steps": 3717, "loss": 0.2663, "lr": 2.9462365591397853e-05, "epoch": 0.5178907721280602, "percentage": 7.4, "elapsed_time": "0:31:43", "remaining_time": "6:37:01"}
{"current_steps": 280, "total_steps": 3717, "loss": 0.2805, "lr": 3.0000000000000004e-05, "epoch": 0.527306967984934, "percentage": 7.53, "elapsed_time": "0:32:15", "remaining_time": "6:36:01"}
{"current_steps": 285, "total_steps": 3717, "loss": 0.2505, "lr": 3.053763440860215e-05, "epoch": 0.536723163841808, "percentage": 7.67, "elapsed_time": "0:32:52", "remaining_time": "6:35:52"}
{"current_steps": 290, "total_steps": 3717, "loss": 0.2644, "lr": 3.1075268817204305e-05, "epoch": 0.5461393596986818, "percentage": 7.8, "elapsed_time": "0:33:28", "remaining_time": "6:35:39"}
{"current_steps": 295, "total_steps": 3717, "loss": 0.2715, "lr": 3.161290322580645e-05, "epoch": 0.5555555555555556, "percentage": 7.94, "elapsed_time": "0:34:03", "remaining_time": "6:34:59"}
{"current_steps": 300, "total_steps": 3717, "loss": 0.29, "lr": 3.21505376344086e-05, "epoch": 0.5649717514124294, "percentage": 8.07, "elapsed_time": "0:34:37", "remaining_time": "6:34:26"}
{"current_steps": 305, "total_steps": 3717, "loss": 0.2849, "lr": 3.2688172043010754e-05, "epoch": 0.5743879472693032, "percentage": 8.21, "elapsed_time": "0:35:11", "remaining_time": "6:33:44"}
{"current_steps": 310, "total_steps": 3717, "loss": 0.2774, "lr": 3.322580645161291e-05, "epoch": 0.583804143126177, "percentage": 8.34, "elapsed_time": "0:35:44", "remaining_time": "6:32:50"}
{"current_steps": 315, "total_steps": 3717, "loss": 0.2587, "lr": 3.3763440860215055e-05, "epoch": 0.5932203389830508, "percentage": 8.47, "elapsed_time": "0:36:17", "remaining_time": "6:32:00"}
{"current_steps": 320, "total_steps": 3717, "loss": 0.2849, "lr": 3.430107526881721e-05, "epoch": 0.6026365348399246, "percentage": 8.61, "elapsed_time": "0:36:50", "remaining_time": "6:31:06"}
{"current_steps": 325, "total_steps": 3717, "loss": 0.2854, "lr": 3.483870967741936e-05, "epoch": 0.6120527306967984, "percentage": 8.74, "elapsed_time": "0:37:23", "remaining_time": "6:30:15"}
{"current_steps": 330, "total_steps": 3717, "loss": 0.2851, "lr": 3.537634408602151e-05, "epoch": 0.6214689265536724, "percentage": 8.88, "elapsed_time": "0:37:57", "remaining_time": "6:29:31"}
{"current_steps": 335, "total_steps": 3717, "loss": 0.2674, "lr": 3.591397849462366e-05, "epoch": 0.6308851224105462, "percentage": 9.01, "elapsed_time": "0:38:31", "remaining_time": "6:28:56"}
{"current_steps": 340, "total_steps": 3717, "loss": 0.2455, "lr": 3.6451612903225805e-05, "epoch": 0.64030131826742, "percentage": 9.15, "elapsed_time": "0:39:07", "remaining_time": "6:28:32"}
{"current_steps": 345, "total_steps": 3717, "loss": 0.2706, "lr": 3.698924731182796e-05, "epoch": 0.6497175141242938, "percentage": 9.28, "elapsed_time": "0:39:41", "remaining_time": "6:27:55"}
{"current_steps": 350, "total_steps": 3717, "loss": 0.2497, "lr": 3.7526881720430114e-05, "epoch": 0.6591337099811676, "percentage": 9.42, "elapsed_time": "0:40:16", "remaining_time": "6:27:24"}
{"current_steps": 355, "total_steps": 3717, "loss": 0.2805, "lr": 3.806451612903226e-05, "epoch": 0.6685499058380414, "percentage": 9.55, "elapsed_time": "0:40:52", "remaining_time": "6:27:03"}
{"current_steps": 360, "total_steps": 3717, "loss": 0.2569, "lr": 3.8602150537634415e-05, "epoch": 0.6779661016949152, "percentage": 9.69, "elapsed_time": "0:41:24", "remaining_time": "6:26:08"}
{"current_steps": 365, "total_steps": 3717, "loss": 0.2513, "lr": 3.913978494623656e-05, "epoch": 0.687382297551789, "percentage": 9.82, "elapsed_time": "0:41:59", "remaining_time": "6:25:33"}
{"current_steps": 370, "total_steps": 3717, "loss": 0.2698, "lr": 3.9677419354838716e-05, "epoch": 0.696798493408663, "percentage": 9.95, "elapsed_time": "0:42:33", "remaining_time": "6:24:56"}
{"current_steps": 375, "total_steps": 3717, "loss": 0.2732, "lr": 3.999996471684888e-05, "epoch": 0.7062146892655368, "percentage": 10.09, "elapsed_time": "0:43:05", "remaining_time": "6:24:02"}
{"current_steps": 380, "total_steps": 3717, "loss": 0.2638, "lr": 3.9999567782828465e-05, "epoch": 0.7156308851224106, "percentage": 10.22, "elapsed_time": "0:43:40", "remaining_time": "6:23:28"}
{"current_steps": 385, "total_steps": 3717, "loss": 0.2676, "lr": 3.999872981963107e-05, "epoch": 0.7250470809792844, "percentage": 10.36, "elapsed_time": "0:44:13", "remaining_time": "6:22:45"}
{"current_steps": 390, "total_steps": 3717, "loss": 0.2745, "lr": 3.9997450845735416e-05, "epoch": 0.7344632768361582, "percentage": 10.49, "elapsed_time": "0:44:48", "remaining_time": "6:22:13"}
{"current_steps": 395, "total_steps": 3717, "loss": 0.2665, "lr": 3.9995730889345336e-05, "epoch": 0.743879472693032, "percentage": 10.63, "elapsed_time": "0:45:22", "remaining_time": "6:21:40"}
{"current_steps": 400, "total_steps": 3717, "loss": 0.2657, "lr": 3.999356998838921e-05, "epoch": 0.7532956685499058, "percentage": 10.76, "elapsed_time": "0:45:57", "remaining_time": "6:21:03"}
{"current_steps": 405, "total_steps": 3717, "loss": 0.255, "lr": 3.999096819051908e-05, "epoch": 0.7627118644067796, "percentage": 10.9, "elapsed_time": "0:46:32", "remaining_time": "6:20:38"}
{"current_steps": 410, "total_steps": 3717, "loss": 0.257, "lr": 3.998792555310963e-05, "epoch": 0.7721280602636534, "percentage": 11.03, "elapsed_time": "0:47:09", "remaining_time": "6:20:25"}
{"current_steps": 415, "total_steps": 3717, "loss": 0.2507, "lr": 3.99844421432569e-05, "epoch": 0.7815442561205274, "percentage": 11.16, "elapsed_time": "0:47:44", "remaining_time": "6:19:51"}
{"current_steps": 420, "total_steps": 3717, "loss": 0.266, "lr": 3.9980518037776826e-05, "epoch": 0.7909604519774012, "percentage": 11.3, "elapsed_time": "0:48:14", "remaining_time": "6:18:38"}
{"current_steps": 425, "total_steps": 3717, "loss": 0.2454, "lr": 3.997615332320351e-05, "epoch": 0.800376647834275, "percentage": 11.43, "elapsed_time": "0:48:49", "remaining_time": "6:18:13"}
{"current_steps": 430, "total_steps": 3717, "loss": 0.2436, "lr": 3.997134809578738e-05, "epoch": 0.8097928436911488, "percentage": 11.57, "elapsed_time": "0:49:21", "remaining_time": "6:17:20"}
{"current_steps": 435, "total_steps": 3717, "loss": 0.2585, "lr": 3.996610246149298e-05, "epoch": 0.8192090395480226, "percentage": 11.7, "elapsed_time": "0:49:53", "remaining_time": "6:16:25"}
{"current_steps": 440, "total_steps": 3717, "loss": 0.2469, "lr": 3.996041653599672e-05, "epoch": 0.8286252354048964, "percentage": 11.84, "elapsed_time": "0:50:25", "remaining_time": "6:15:34"}
{"current_steps": 445, "total_steps": 3717, "loss": 0.2562, "lr": 3.995429044468424e-05, "epoch": 0.8380414312617702, "percentage": 11.97, "elapsed_time": "0:50:59", "remaining_time": "6:14:58"}
{"current_steps": 450, "total_steps": 3717, "loss": 0.2643, "lr": 3.9947724322647714e-05, "epoch": 0.847457627118644, "percentage": 12.11, "elapsed_time": "0:51:37", "remaining_time": "6:14:45"}
{"current_steps": 455, "total_steps": 3717, "loss": 0.2392, "lr": 3.9940718314682855e-05, "epoch": 0.8568738229755178, "percentage": 12.24, "elapsed_time": "0:52:10", "remaining_time": "6:14:03"}
{"current_steps": 460, "total_steps": 3717, "loss": 0.2522, "lr": 3.993327257528569e-05, "epoch": 0.8662900188323918, "percentage": 12.38, "elapsed_time": "0:52:45", "remaining_time": "6:13:33"}
{"current_steps": 465, "total_steps": 3717, "loss": 0.2626, "lr": 3.9925387268649184e-05, "epoch": 0.8757062146892656, "percentage": 12.51, "elapsed_time": "0:53:15", "remaining_time": "6:12:25"}
{"current_steps": 470, "total_steps": 3717, "loss": 0.2334, "lr": 3.991706256865961e-05, "epoch": 0.8851224105461394, "percentage": 12.64, "elapsed_time": "0:53:50", "remaining_time": "6:11:55"}
{"current_steps": 475, "total_steps": 3717, "loss": 0.2534, "lr": 3.9908298658892706e-05, "epoch": 0.8945386064030132, "percentage": 12.78, "elapsed_time": "0:54:23", "remaining_time": "6:11:14"}
{"current_steps": 480, "total_steps": 3717, "loss": 0.2562, "lr": 3.989909573260965e-05, "epoch": 0.903954802259887, "percentage": 12.91, "elapsed_time": "0:54:59", "remaining_time": "6:10:54"}
{"current_steps": 485, "total_steps": 3717, "loss": 0.2378, "lr": 3.9889453992752785e-05, "epoch": 0.9133709981167608, "percentage": 13.05, "elapsed_time": "0:55:31", "remaining_time": "6:10:03"}
{"current_steps": 490, "total_steps": 3717, "loss": 0.265, "lr": 3.987937365194113e-05, "epoch": 0.9227871939736346, "percentage": 13.18, "elapsed_time": "0:56:05", "remaining_time": "6:09:22"}
{"current_steps": 495, "total_steps": 3717, "loss": 0.2552, "lr": 3.98688549324657e-05, "epoch": 0.9322033898305084, "percentage": 13.32, "elapsed_time": "0:56:35", "remaining_time": "6:08:22"}
{"current_steps": 500, "total_steps": 3717, "loss": 0.2347, "lr": 3.9857898066284636e-05, "epoch": 0.9416195856873822, "percentage": 13.45, "elapsed_time": "0:57:08", "remaining_time": "6:07:40"}
{"current_steps": 505, "total_steps": 3717, "loss": 0.2345, "lr": 3.984650329501803e-05, "epoch": 0.9510357815442562, "percentage": 13.59, "elapsed_time": "0:57:42", "remaining_time": "6:07:05"}
{"current_steps": 510, "total_steps": 3717, "loss": 0.2446, "lr": 3.983467086994265e-05, "epoch": 0.96045197740113, "percentage": 13.72, "elapsed_time": "0:58:18", "remaining_time": "6:06:41"}
{"current_steps": 515, "total_steps": 3717, "loss": 0.2454, "lr": 3.9822401051986365e-05, "epoch": 0.9698681732580038, "percentage": 13.86, "elapsed_time": "0:58:54", "remaining_time": "6:06:12"}
{"current_steps": 520, "total_steps": 3717, "loss": 0.2992, "lr": 3.980969411172241e-05, "epoch": 0.9792843691148776, "percentage": 13.99, "elapsed_time": "0:59:25", "remaining_time": "6:05:22"}
{"current_steps": 525, "total_steps": 3717, "loss": 0.2441, "lr": 3.97965503293634e-05, "epoch": 0.9887005649717514, "percentage": 14.12, "elapsed_time": "1:00:01", "remaining_time": "6:04:57"}
{"current_steps": 530, "total_steps": 3717, "loss": 0.2374, "lr": 3.978296999475519e-05, "epoch": 0.9981167608286252, "percentage": 14.26, "elapsed_time": "1:00:37", "remaining_time": "6:04:32"}
{"current_steps": 535, "total_steps": 3717, "loss": 0.2327, "lr": 3.9768953407370436e-05, "epoch": 1.0075329566854991, "percentage": 14.39, "elapsed_time": "1:01:13", "remaining_time": "6:04:07"}
{"current_steps": 540, "total_steps": 3717, "loss": 0.2307, "lr": 3.9754500876302015e-05, "epoch": 1.0169491525423728, "percentage": 14.53, "elapsed_time": "1:01:46", "remaining_time": "6:03:29"}
{"current_steps": 545, "total_steps": 3717, "loss": 0.2364, "lr": 3.973961272025621e-05, "epoch": 1.0263653483992468, "percentage": 14.66, "elapsed_time": "1:02:20", "remaining_time": "6:02:51"}
{"current_steps": 550, "total_steps": 3717, "loss": 0.2413, "lr": 3.972428926754568e-05, "epoch": 1.0357815442561205, "percentage": 14.8, "elapsed_time": "1:02:55", "remaining_time": "6:02:17"}
{"current_steps": 555, "total_steps": 3717, "loss": 0.2426, "lr": 3.9708530856082224e-05, "epoch": 1.0451977401129944, "percentage": 14.93, "elapsed_time": "1:03:28", "remaining_time": "6:01:39"}
{"current_steps": 560, "total_steps": 3717, "loss": 0.2506, "lr": 3.969233783336928e-05, "epoch": 1.054613935969868, "percentage": 15.07, "elapsed_time": "1:04:00", "remaining_time": "6:00:51"}
{"current_steps": 565, "total_steps": 3717, "loss": 0.2522, "lr": 3.9675710556494376e-05, "epoch": 1.064030131826742, "percentage": 15.2, "elapsed_time": "1:04:36", "remaining_time": "6:00:26"}
{"current_steps": 570, "total_steps": 3717, "loss": 0.2489, "lr": 3.9658649392121124e-05, "epoch": 1.073446327683616, "percentage": 15.33, "elapsed_time": "1:05:09", "remaining_time": "5:59:46"}
{"current_steps": 575, "total_steps": 3717, "loss": 0.2305, "lr": 3.964115471648123e-05, "epoch": 1.0828625235404896, "percentage": 15.47, "elapsed_time": "1:05:45", "remaining_time": "5:59:17"}
{"current_steps": 580, "total_steps": 3717, "loss": 0.231, "lr": 3.962322691536615e-05, "epoch": 1.0922787193973635, "percentage": 15.6, "elapsed_time": "1:06:20", "remaining_time": "5:58:50"}
{"current_steps": 585, "total_steps": 3717, "loss": 0.2506, "lr": 3.96048663841186e-05, "epoch": 1.1016949152542372, "percentage": 15.74, "elapsed_time": "1:06:53", "remaining_time": "5:58:07"}
{"current_steps": 590, "total_steps": 3717, "loss": 0.2393, "lr": 3.958607352762381e-05, "epoch": 1.1111111111111112, "percentage": 15.87, "elapsed_time": "1:07:28", "remaining_time": "5:57:38"}
{"current_steps": 595, "total_steps": 3717, "loss": 0.2312, "lr": 3.956684876030067e-05, "epoch": 1.1205273069679849, "percentage": 16.01, "elapsed_time": "1:08:05", "remaining_time": "5:57:18"}
{"current_steps": 600, "total_steps": 3717, "loss": 0.2254, "lr": 3.9547192506092473e-05, "epoch": 1.1299435028248588, "percentage": 16.14, "elapsed_time": "1:08:38", "remaining_time": "5:56:35"}
{"current_steps": 605, "total_steps": 3717, "loss": 0.2247, "lr": 3.952710519845768e-05, "epoch": 1.1393596986817327, "percentage": 16.28, "elapsed_time": "1:09:11", "remaining_time": "5:55:53"}
{"current_steps": 610, "total_steps": 3717, "loss": 0.2227, "lr": 3.950658728036031e-05, "epoch": 1.1487758945386064, "percentage": 16.41, "elapsed_time": "1:09:46", "remaining_time": "5:55:22"}
{"current_steps": 615, "total_steps": 3717, "loss": 0.2372, "lr": 3.948563920426017e-05, "epoch": 1.1581920903954803, "percentage": 16.55, "elapsed_time": "1:10:20", "remaining_time": "5:54:48"}
{"current_steps": 620, "total_steps": 3717, "loss": 0.2532, "lr": 3.946426143210287e-05, "epoch": 1.167608286252354, "percentage": 16.68, "elapsed_time": "1:10:55", "remaining_time": "5:54:16"}
{"current_steps": 625, "total_steps": 3717, "loss": 0.2162, "lr": 3.9442454435309654e-05, "epoch": 1.177024482109228, "percentage": 16.81, "elapsed_time": "1:11:28", "remaining_time": "5:53:36"}
{"current_steps": 630, "total_steps": 3717, "loss": 0.2363, "lr": 3.942021869476703e-05, "epoch": 1.1864406779661016, "percentage": 16.95, "elapsed_time": "1:12:03", "remaining_time": "5:53:06"}
{"current_steps": 635, "total_steps": 3717, "loss": 0.2322, "lr": 3.939755470081609e-05, "epoch": 1.1958568738229756, "percentage": 17.08, "elapsed_time": "1:12:46", "remaining_time": "5:53:13"}
{"current_steps": 640, "total_steps": 3717, "loss": 0.2314, "lr": 3.937446295324178e-05, "epoch": 1.2052730696798493, "percentage": 17.22, "elapsed_time": "1:13:19", "remaining_time": "5:52:33"}
{"current_steps": 645, "total_steps": 3717, "loss": 0.2212, "lr": 3.935094396126181e-05, "epoch": 1.2146892655367232, "percentage": 17.35, "elapsed_time": "1:13:57", "remaining_time": "5:52:12"}
{"current_steps": 650, "total_steps": 3717, "loss": 0.2332, "lr": 3.9326998243515493e-05, "epoch": 1.2241054613935969, "percentage": 17.49, "elapsed_time": "1:14:36", "remaining_time": "5:52:01"}
{"current_steps": 655, "total_steps": 3717, "loss": 0.2306, "lr": 3.930262632805224e-05, "epoch": 1.2335216572504708, "percentage": 17.62, "elapsed_time": "1:15:18", "remaining_time": "5:52:02"}
{"current_steps": 660, "total_steps": 3717, "loss": 0.2213, "lr": 3.927782875231994e-05, "epoch": 1.2429378531073447, "percentage": 17.76, "elapsed_time": "1:16:04", "remaining_time": "5:52:19"}
{"current_steps": 665, "total_steps": 3717, "loss": 0.2401, "lr": 3.925260606315316e-05, "epoch": 1.2523540489642184, "percentage": 17.89, "elapsed_time": "1:16:36", "remaining_time": "5:51:37"}
{"current_steps": 670, "total_steps": 3717, "loss": 0.2237, "lr": 3.9226958816760993e-05, "epoch": 1.2617702448210923, "percentage": 18.03, "elapsed_time": "1:17:19", "remaining_time": "5:51:39"}
{"current_steps": 675, "total_steps": 3717, "loss": 0.2226, "lr": 3.920088757871487e-05, "epoch": 1.271186440677966, "percentage": 18.16, "elapsed_time": "1:18:02", "remaining_time": "5:51:41"}
{"current_steps": 680, "total_steps": 3717, "loss": 0.2335, "lr": 3.9174392923936045e-05, "epoch": 1.28060263653484, "percentage": 18.29, "elapsed_time": "1:18:45", "remaining_time": "5:51:46"}
{"current_steps": 685, "total_steps": 3717, "loss": 0.2643, "lr": 3.914747543668293e-05, "epoch": 1.2900188323917137, "percentage": 18.43, "elapsed_time": "1:19:31", "remaining_time": "5:51:59"}
{"current_steps": 690, "total_steps": 3717, "loss": 0.2439, "lr": 3.9120135710538224e-05, "epoch": 1.2994350282485876, "percentage": 18.56, "elapsed_time": "1:20:09", "remaining_time": "5:51:37"}
{"current_steps": 695, "total_steps": 3717, "loss": 0.2531, "lr": 3.909237434839579e-05, "epoch": 1.3088512241054615, "percentage": 18.7, "elapsed_time": "1:20:50", "remaining_time": "5:51:31"}
{"current_steps": 700, "total_steps": 3717, "loss": 0.2164, "lr": 3.906419196244741e-05, "epoch": 1.3182674199623352, "percentage": 18.83, "elapsed_time": "1:21:31", "remaining_time": "5:51:21"}
{"current_steps": 705, "total_steps": 3717, "loss": 0.2312, "lr": 3.903558917416922e-05, "epoch": 1.327683615819209, "percentage": 18.97, "elapsed_time": "1:22:08", "remaining_time": "5:50:56"}
{"current_steps": 710, "total_steps": 3717, "loss": 0.2429, "lr": 3.9006566614308064e-05, "epoch": 1.3370998116760828, "percentage": 19.1, "elapsed_time": "1:22:48", "remaining_time": "5:50:44"}
{"current_steps": 715, "total_steps": 3717, "loss": 0.2381, "lr": 3.8977124922867565e-05, "epoch": 1.3465160075329567, "percentage": 19.24, "elapsed_time": "1:23:34", "remaining_time": "5:50:51"}
{"current_steps": 720, "total_steps": 3717, "loss": 0.2226, "lr": 3.8947264749094004e-05, "epoch": 1.3559322033898304, "percentage": 19.37, "elapsed_time": "1:24:16", "remaining_time": "5:50:49"}
{"current_steps": 725, "total_steps": 3717, "loss": 0.224, "lr": 3.891698675146199e-05, "epoch": 1.3653483992467044, "percentage": 19.5, "elapsed_time": "1:25:05", "remaining_time": "5:51:08"}
{"current_steps": 730, "total_steps": 3717, "loss": 0.2192, "lr": 3.8886291597659986e-05, "epoch": 1.3747645951035783, "percentage": 19.64, "elapsed_time": "1:25:57", "remaining_time": "5:51:44"}
{"current_steps": 735, "total_steps": 3717, "loss": 0.2366, "lr": 3.885517996457553e-05, "epoch": 1.384180790960452, "percentage": 19.77, "elapsed_time": "1:26:39", "remaining_time": "5:51:33"}
{"current_steps": 740, "total_steps": 3717, "loss": 0.2473, "lr": 3.882365253828035e-05, "epoch": 1.3935969868173257, "percentage": 19.91, "elapsed_time": "1:27:11", "remaining_time": "5:50:47"}
{"current_steps": 745, "total_steps": 3717, "loss": 0.2307, "lr": 3.8791710014015214e-05, "epoch": 1.4030131826741996, "percentage": 20.04, "elapsed_time": "1:27:57", "remaining_time": "5:50:52"}
{"current_steps": 750, "total_steps": 3717, "loss": 0.2053, "lr": 3.87593530961746e-05, "epoch": 1.4124293785310735, "percentage": 20.18, "elapsed_time": "1:28:29", "remaining_time": "5:50:05"}
{"current_steps": 755, "total_steps": 3717, "loss": 0.2198, "lr": 3.872658249829118e-05, "epoch": 1.4218455743879472, "percentage": 20.31, "elapsed_time": "1:29:09", "remaining_time": "5:49:46"}
{"current_steps": 760, "total_steps": 3717, "loss": 0.2338, "lr": 3.8693398943020055e-05, "epoch": 1.4312617702448212, "percentage": 20.45, "elapsed_time": "1:29:48", "remaining_time": "5:49:25"}
{"current_steps": 765, "total_steps": 3717, "loss": 0.2233, "lr": 3.865980316212284e-05, "epoch": 1.4406779661016949, "percentage": 20.58, "elapsed_time": "1:30:27", "remaining_time": "5:49:03"}
{"current_steps": 770, "total_steps": 3717, "loss": 0.2299, "lr": 3.862579589645153e-05, "epoch": 1.4500941619585688, "percentage": 20.72, "elapsed_time": "1:31:01", "remaining_time": "5:48:23"}
{"current_steps": 775, "total_steps": 3717, "loss": 0.2206, "lr": 3.859137789593215e-05, "epoch": 1.4595103578154425, "percentage": 20.85, "elapsed_time": "1:31:35", "remaining_time": "5:47:42"}
{"current_steps": 780, "total_steps": 3717, "loss": 0.2129, "lr": 3.855654991954822e-05, "epoch": 1.4689265536723164, "percentage": 20.98, "elapsed_time": "1:32:07", "remaining_time": "5:46:54"}
{"current_steps": 785, "total_steps": 3717, "loss": 0.2218, "lr": 3.852131273532404e-05, "epoch": 1.4783427495291903, "percentage": 21.12, "elapsed_time": "1:32:43", "remaining_time": "5:46:21"}
{"current_steps": 790, "total_steps": 3717, "loss": 0.2172, "lr": 3.84856671203077e-05, "epoch": 1.487758945386064, "percentage": 21.25, "elapsed_time": "1:33:18", "remaining_time": "5:45:42"}
{"current_steps": 795, "total_steps": 3717, "loss": 0.2156, "lr": 3.844961386055402e-05, "epoch": 1.497175141242938, "percentage": 21.39, "elapsed_time": "1:33:50", "remaining_time": "5:44:55"}
{"current_steps": 800, "total_steps": 3717, "loss": 0.2343, "lr": 3.8413153751107135e-05, "epoch": 1.5065913370998116, "percentage": 21.52, "elapsed_time": "1:34:25", "remaining_time": "5:44:17"}
{"current_steps": 805, "total_steps": 3717, "loss": 0.2146, "lr": 3.837628759598304e-05, "epoch": 1.5160075329566856, "percentage": 21.66, "elapsed_time": "1:35:00", "remaining_time": "5:43:39"}
{"current_steps": 810, "total_steps": 3717, "loss": 0.2234, "lr": 3.83390162081518e-05, "epoch": 1.5254237288135593, "percentage": 21.79, "elapsed_time": "1:35:31", "remaining_time": "5:42:50"}
{"current_steps": 815, "total_steps": 3717, "loss": 0.2287, "lr": 3.8301340409519655e-05, "epoch": 1.5348399246704332, "percentage": 21.93, "elapsed_time": "1:36:06", "remaining_time": "5:42:12"}
{"current_steps": 820, "total_steps": 3717, "loss": 0.2297, "lr": 3.826326103091088e-05, "epoch": 1.544256120527307, "percentage": 22.06, "elapsed_time": "1:36:37", "remaining_time": "5:41:23"}
{"current_steps": 825, "total_steps": 3717, "loss": 0.2208, "lr": 3.8224778912049475e-05, "epoch": 1.5536723163841808, "percentage": 22.2, "elapsed_time": "1:37:11", "remaining_time": "5:40:41"}
{"current_steps": 830, "total_steps": 3717, "loss": 0.2361, "lr": 3.8185894901540636e-05, "epoch": 1.5630885122410545, "percentage": 22.33, "elapsed_time": "1:37:43", "remaining_time": "5:39:56"}
{"current_steps": 835, "total_steps": 3717, "loss": 0.227, "lr": 3.8146609856852054e-05, "epoch": 1.5725047080979284, "percentage": 22.46, "elapsed_time": "1:38:20", "remaining_time": "5:39:23"}
{"current_steps": 840, "total_steps": 3717, "loss": 0.2306, "lr": 3.810692464429499e-05, "epoch": 1.5819209039548023, "percentage": 22.6, "elapsed_time": "1:38:53", "remaining_time": "5:38:43"}
{"current_steps": 845, "total_steps": 3717, "loss": 0.224, "lr": 3.806684013900521e-05, "epoch": 1.591337099811676, "percentage": 22.73, "elapsed_time": "1:39:26", "remaining_time": "5:37:57"}
{"current_steps": 850, "total_steps": 3717, "loss": 0.2285, "lr": 3.802635722492361e-05, "epoch": 1.60075329566855, "percentage": 22.87, "elapsed_time": "1:39:57", "remaining_time": "5:37:10"}
{"current_steps": 855, "total_steps": 3717, "loss": 0.2515, "lr": 3.7985476794776807e-05, "epoch": 1.6101694915254239, "percentage": 23.0, "elapsed_time": "1:40:33", "remaining_time": "5:36:35"}
{"current_steps": 860, "total_steps": 3717, "loss": 0.227, "lr": 3.7944199750057404e-05, "epoch": 1.6195856873822976, "percentage": 23.14, "elapsed_time": "1:41:06", "remaining_time": "5:35:54"}
{"current_steps": 865, "total_steps": 3717, "loss": 0.2089, "lr": 3.790252700100413e-05, "epoch": 1.6290018832391713, "percentage": 23.27, "elapsed_time": "1:41:42", "remaining_time": "5:35:21"}
{"current_steps": 870, "total_steps": 3717, "loss": 0.2425, "lr": 3.786045946658175e-05, "epoch": 1.6384180790960452, "percentage": 23.41, "elapsed_time": "1:42:16", "remaining_time": "5:34:42"}
{"current_steps": 875, "total_steps": 3717, "loss": 0.2155, "lr": 3.781799807446082e-05, "epoch": 1.6478342749529191, "percentage": 23.54, "elapsed_time": "1:42:50", "remaining_time": "5:34:01"}
{"current_steps": 880, "total_steps": 3717, "loss": 0.2243, "lr": 3.777514376099722e-05, "epoch": 1.6572504708097928, "percentage": 23.68, "elapsed_time": "1:43:21", "remaining_time": "5:33:14"}
{"current_steps": 885, "total_steps": 3717, "loss": 0.239, "lr": 3.7731897471211485e-05, "epoch": 1.6666666666666665, "percentage": 23.81, "elapsed_time": "1:43:57", "remaining_time": "5:32:41"}
{"current_steps": 890, "total_steps": 3717, "loss": 0.2103, "lr": 3.7688260158768025e-05, "epoch": 1.6760828625235404, "percentage": 23.94, "elapsed_time": "1:44:33", "remaining_time": "5:32:08"}
{"current_steps": 895, "total_steps": 3717, "loss": 0.2253, "lr": 3.764423278595403e-05, "epoch": 1.6854990583804144, "percentage": 24.08, "elapsed_time": "1:45:07", "remaining_time": "5:31:28"}
{"current_steps": 900, "total_steps": 3717, "loss": 0.2222, "lr": 3.7599816323658264e-05, "epoch": 1.694915254237288, "percentage": 24.21, "elapsed_time": "1:45:43", "remaining_time": "5:30:54"}
{"current_steps": 905, "total_steps": 3717, "loss": 0.2355, "lr": 3.755501175134971e-05, "epoch": 1.704331450094162, "percentage": 24.35, "elapsed_time": "1:46:16", "remaining_time": "5:30:13"}
{"current_steps": 910, "total_steps": 3717, "loss": 0.2172, "lr": 3.750982005705589e-05, "epoch": 1.713747645951036, "percentage": 24.48, "elapsed_time": "1:46:51", "remaining_time": "5:29:37"}
{"current_steps": 915, "total_steps": 3717, "loss": 0.2257, "lr": 3.746424223734113e-05, "epoch": 1.7231638418079096, "percentage": 24.62, "elapsed_time": "1:47:25", "remaining_time": "5:28:58"}
{"current_steps": 920, "total_steps": 3717, "loss": 0.2173, "lr": 3.7418279297284566e-05, "epoch": 1.7325800376647833, "percentage": 24.75, "elapsed_time": "1:47:56", "remaining_time": "5:28:10"}
{"current_steps": 925, "total_steps": 3717, "loss": 0.2114, "lr": 3.737193225045798e-05, "epoch": 1.7419962335216572, "percentage": 24.89, "elapsed_time": "1:48:31", "remaining_time": "5:27:33"}
{"current_steps": 930, "total_steps": 3717, "loss": 0.2296, "lr": 3.732520211890347e-05, "epoch": 1.7514124293785311, "percentage": 25.02, "elapsed_time": "1:49:05", "remaining_time": "5:26:56"}
{"current_steps": 935, "total_steps": 3717, "loss": 0.2211, "lr": 3.727808993311085e-05, "epoch": 1.7608286252354048, "percentage": 25.15, "elapsed_time": "1:49:39", "remaining_time": "5:26:17"}
{"current_steps": 940, "total_steps": 3717, "loss": 0.2379, "lr": 3.723059673199502e-05, "epoch": 1.7702448210922788, "percentage": 25.29, "elapsed_time": "1:50:14", "remaining_time": "5:25:39"}
{"current_steps": 945, "total_steps": 3717, "loss": 0.2544, "lr": 3.7182723562872986e-05, "epoch": 1.7796610169491527, "percentage": 25.42, "elapsed_time": "1:50:46", "remaining_time": "5:24:55"}
{"current_steps": 950, "total_steps": 3717, "loss": 0.233, "lr": 3.713447148144077e-05, "epoch": 1.7890772128060264, "percentage": 25.56, "elapsed_time": "1:51:20", "remaining_time": "5:24:18"}
{"current_steps": 955, "total_steps": 3717, "loss": 0.2338, "lr": 3.7085841551750156e-05, "epoch": 1.7984934086629, "percentage": 25.69, "elapsed_time": "1:51:53", "remaining_time": "5:23:36"}
{"current_steps": 960, "total_steps": 3717, "loss": 0.2263, "lr": 3.703683484618522e-05, "epoch": 1.807909604519774, "percentage": 25.83, "elapsed_time": "1:52:27", "remaining_time": "5:22:58"}
{"current_steps": 965, "total_steps": 3717, "loss": 0.2228, "lr": 3.698745244543866e-05, "epoch": 1.817325800376648, "percentage": 25.96, "elapsed_time": "1:53:01", "remaining_time": "5:22:20"}
{"current_steps": 970, "total_steps": 3717, "loss": 0.2325, "lr": 3.693769543848799e-05, "epoch": 1.8267419962335216, "percentage": 26.1, "elapsed_time": "1:53:36", "remaining_time": "5:21:44"}
{"current_steps": 975, "total_steps": 3717, "loss": 0.2245, "lr": 3.688756492257152e-05, "epoch": 1.8361581920903953, "percentage": 26.23, "elapsed_time": "1:54:07", "remaining_time": "5:20:55"}
{"current_steps": 980, "total_steps": 3717, "loss": 0.2303, "lr": 3.683706200316414e-05, "epoch": 1.8455743879472695, "percentage": 26.37, "elapsed_time": "1:54:42", "remaining_time": "5:20:20"}
{"current_steps": 985, "total_steps": 3717, "loss": 0.2161, "lr": 3.678618779395297e-05, "epoch": 1.8549905838041432, "percentage": 26.5, "elapsed_time": "1:55:14", "remaining_time": "5:19:38"}
{"current_steps": 990, "total_steps": 3717, "loss": 0.226, "lr": 3.673494341681279e-05, "epoch": 1.8644067796610169, "percentage": 26.63, "elapsed_time": "1:55:47", "remaining_time": "5:18:56"}
{"current_steps": 995, "total_steps": 3717, "loss": 0.2311, "lr": 3.668333000178129e-05, "epoch": 1.8738229755178908, "percentage": 26.77, "elapsed_time": "1:56:17", "remaining_time": "5:18:08"}
{"current_steps": 1000, "total_steps": 3717, "loss": 0.2118, "lr": 3.663134868703416e-05, "epoch": 1.8832391713747647, "percentage": 26.9, "elapsed_time": "1:56:50", "remaining_time": "5:17:28"}
{"current_steps": 1005, "total_steps": 3717, "loss": 0.2221, "lr": 3.657900061886e-05, "epoch": 1.8926553672316384, "percentage": 27.04, "elapsed_time": "1:57:24", "remaining_time": "5:16:48"}
{"current_steps": 1010, "total_steps": 3717, "loss": 0.2231, "lr": 3.652628695163503e-05, "epoch": 1.902071563088512, "percentage": 27.17, "elapsed_time": "1:58:00", "remaining_time": "5:16:18"}
{"current_steps": 1015, "total_steps": 3717, "loss": 0.2266, "lr": 3.647320884779764e-05, "epoch": 1.911487758945386, "percentage": 27.31, "elapsed_time": "1:58:34", "remaining_time": "5:15:38"}
{"current_steps": 1020, "total_steps": 3717, "loss": 0.2204, "lr": 3.641976747782274e-05, "epoch": 1.92090395480226, "percentage": 27.44, "elapsed_time": "1:59:06", "remaining_time": "5:14:57"}
{"current_steps": 1025, "total_steps": 3717, "loss": 0.2236, "lr": 3.636596402019597e-05, "epoch": 1.9303201506591336, "percentage": 27.58, "elapsed_time": "1:59:38", "remaining_time": "5:14:13"}
{"current_steps": 1030, "total_steps": 3717, "loss": 0.2301, "lr": 3.63117996613877e-05, "epoch": 1.9397363465160076, "percentage": 27.71, "elapsed_time": "2:00:13", "remaining_time": "5:13:37"}
{"current_steps": 1035, "total_steps": 3717, "loss": 0.2271, "lr": 3.625727559582687e-05, "epoch": 1.9491525423728815, "percentage": 27.85, "elapsed_time": "2:00:45", "remaining_time": "5:12:55"}
{"current_steps": 1040, "total_steps": 3717, "loss": 0.2377, "lr": 3.620239302587466e-05, "epoch": 1.9585687382297552, "percentage": 27.98, "elapsed_time": "2:01:19", "remaining_time": "5:12:17"}
{"current_steps": 1045, "total_steps": 3717, "loss": 0.228, "lr": 3.614715316179796e-05, "epoch": 1.967984934086629, "percentage": 28.11, "elapsed_time": "2:01:55", "remaining_time": "5:11:44"}
{"current_steps": 1050, "total_steps": 3717, "loss": 0.2409, "lr": 3.6091557221742676e-05, "epoch": 1.9774011299435028, "percentage": 28.25, "elapsed_time": "2:02:26", "remaining_time": "5:11:00"}
{"current_steps": 1055, "total_steps": 3717, "loss": 0.2117, "lr": 3.603560643170688e-05, "epoch": 1.9868173258003767, "percentage": 28.38, "elapsed_time": "2:02:58", "remaining_time": "5:10:17"}
{"current_steps": 1060, "total_steps": 3717, "loss": 0.2156, "lr": 3.5979302025513806e-05, "epoch": 1.9962335216572504, "percentage": 28.52, "elapsed_time": "2:03:28", "remaining_time": "5:09:29"}
{"current_steps": 1065, "total_steps": 3717, "loss": 0.2011, "lr": 3.5922645244784563e-05, "epoch": 2.005649717514124, "percentage": 28.65, "elapsed_time": "2:04:02", "remaining_time": "5:08:52"}
{"current_steps": 1070, "total_steps": 3717, "loss": 0.2286, "lr": 3.5865637338910824e-05, "epoch": 2.0150659133709983, "percentage": 28.79, "elapsed_time": "2:04:33", "remaining_time": "5:08:09"}
{"current_steps": 1075, "total_steps": 3717, "loss": 0.1928, "lr": 3.5808279565027236e-05, "epoch": 2.024482109227872, "percentage": 28.92, "elapsed_time": "2:05:08", "remaining_time": "5:07:33"}
{"current_steps": 1080, "total_steps": 3717, "loss": 0.2087, "lr": 3.5750573187983746e-05, "epoch": 2.0338983050847457, "percentage": 29.06, "elapsed_time": "2:05:42", "remaining_time": "5:06:57"}
{"current_steps": 1085, "total_steps": 3717, "loss": 0.1925, "lr": 3.569251948031764e-05, "epoch": 2.0433145009416194, "percentage": 29.19, "elapsed_time": "2:06:17", "remaining_time": "5:06:22"}
{"current_steps": 1090, "total_steps": 3717, "loss": 0.2109, "lr": 3.563411972222554e-05, "epoch": 2.0527306967984935, "percentage": 29.32, "elapsed_time": "2:06:51", "remaining_time": "5:05:45"}
{"current_steps": 1095, "total_steps": 3717, "loss": 0.1985, "lr": 3.557537520153513e-05, "epoch": 2.062146892655367, "percentage": 29.46, "elapsed_time": "2:07:27", "remaining_time": "5:05:11"}
{"current_steps": 1100, "total_steps": 3717, "loss": 0.1993, "lr": 3.551628721367677e-05, "epoch": 2.071563088512241, "percentage": 29.59, "elapsed_time": "2:08:02", "remaining_time": "5:04:37"}
{"current_steps": 1105, "total_steps": 3717, "loss": 0.2102, "lr": 3.5456857061654984e-05, "epoch": 2.080979284369115, "percentage": 29.73, "elapsed_time": "2:08:40", "remaining_time": "5:04:09"}
{"current_steps": 1110, "total_steps": 3717, "loss": 0.19, "lr": 3.539708605601963e-05, "epoch": 2.0903954802259888, "percentage": 29.86, "elapsed_time": "2:09:12", "remaining_time": "5:03:27"}
{"current_steps": 1115, "total_steps": 3717, "loss": 0.2126, "lr": 3.533697551483706e-05, "epoch": 2.0998116760828625, "percentage": 30.0, "elapsed_time": "2:09:48", "remaining_time": "5:02:54"}
{"current_steps": 1120, "total_steps": 3717, "loss": 0.1963, "lr": 3.527652676366106e-05, "epoch": 2.109227871939736, "percentage": 30.13, "elapsed_time": "2:10:27", "remaining_time": "5:02:30"}
{"current_steps": 1125, "total_steps": 3717, "loss": 0.2191, "lr": 3.521574113550357e-05, "epoch": 2.1186440677966103, "percentage": 30.27, "elapsed_time": "2:11:01", "remaining_time": "5:01:52"}
{"current_steps": 1130, "total_steps": 3717, "loss": 0.1971, "lr": 3.515461997080535e-05, "epoch": 2.128060263653484, "percentage": 30.4, "elapsed_time": "2:11:35", "remaining_time": "5:01:16"}
{"current_steps": 1135, "total_steps": 3717, "loss": 0.1864, "lr": 3.509316461740636e-05, "epoch": 2.1374764595103577, "percentage": 30.54, "elapsed_time": "2:12:07", "remaining_time": "5:00:33"}
{"current_steps": 1140, "total_steps": 3717, "loss": 0.2058, "lr": 3.5031376430516095e-05, "epoch": 2.146892655367232, "percentage": 30.67, "elapsed_time": "2:12:38", "remaining_time": "4:59:50"}
{"current_steps": 1145, "total_steps": 3717, "loss": 0.2164, "lr": 3.4969256772683665e-05, "epoch": 2.1563088512241055, "percentage": 30.8, "elapsed_time": "2:13:12", "remaining_time": "4:59:14"}
{"current_steps": 1150, "total_steps": 3717, "loss": 0.2128, "lr": 3.490680701376774e-05, "epoch": 2.1657250470809792, "percentage": 30.94, "elapsed_time": "2:13:45", "remaining_time": "4:58:34"}
{"current_steps": 1155, "total_steps": 3717, "loss": 0.2257, "lr": 3.484402853090638e-05, "epoch": 2.175141242937853, "percentage": 31.07, "elapsed_time": "2:14:17", "remaining_time": "4:57:53"}
{"current_steps": 1160, "total_steps": 3717, "loss": 0.2065, "lr": 3.478092270848663e-05, "epoch": 2.184557438794727, "percentage": 31.21, "elapsed_time": "2:14:51", "remaining_time": "4:57:16"}
{"current_steps": 1165, "total_steps": 3717, "loss": 0.2073, "lr": 3.471749093811401e-05, "epoch": 2.193973634651601, "percentage": 31.34, "elapsed_time": "2:15:24", "remaining_time": "4:56:36"}
{"current_steps": 1170, "total_steps": 3717, "loss": 0.1971, "lr": 3.465373461858183e-05, "epoch": 2.2033898305084745, "percentage": 31.48, "elapsed_time": "2:15:59", "remaining_time": "4:56:01"}
{"current_steps": 1175, "total_steps": 3717, "loss": 0.1942, "lr": 3.4589655155840315e-05, "epoch": 2.2128060263653486, "percentage": 31.61, "elapsed_time": "2:16:33", "remaining_time": "4:55:24"}
{"current_steps": 1180, "total_steps": 3717, "loss": 0.1993, "lr": 3.452525396296565e-05, "epoch": 2.2222222222222223, "percentage": 31.75, "elapsed_time": "2:17:07", "remaining_time": "4:54:48"}
{"current_steps": 1185, "total_steps": 3717, "loss": 0.1932, "lr": 3.446053246012878e-05, "epoch": 2.231638418079096, "percentage": 31.88, "elapsed_time": "2:17:41", "remaining_time": "4:54:11"}
{"current_steps": 1190, "total_steps": 3717, "loss": 0.1806, "lr": 3.4395492074564105e-05, "epoch": 2.2410546139359697, "percentage": 32.02, "elapsed_time": "2:18:14", "remaining_time": "4:53:33"}
{"current_steps": 1195, "total_steps": 3717, "loss": 0.1882, "lr": 3.4330134240538e-05, "epoch": 2.250470809792844, "percentage": 32.15, "elapsed_time": "2:18:50", "remaining_time": "4:53:01"}
{"current_steps": 1200, "total_steps": 3717, "loss": 0.2184, "lr": 3.426446039931721e-05, "epoch": 2.2598870056497176, "percentage": 32.28, "elapsed_time": "2:19:22", "remaining_time": "4:52:19"}
{"current_steps": 1205, "total_steps": 3717, "loss": 0.2096, "lr": 3.4198471999137034e-05, "epoch": 2.2693032015065913, "percentage": 32.42, "elapsed_time": "2:19:54", "remaining_time": "4:51:40"}
{"current_steps": 1210, "total_steps": 3717, "loss": 0.2132, "lr": 3.413217049516941e-05, "epoch": 2.2787193973634654, "percentage": 32.55, "elapsed_time": "2:20:29", "remaining_time": "4:51:04"}
{"current_steps": 1215, "total_steps": 3717, "loss": 0.2128, "lr": 3.4065557349490826e-05, "epoch": 2.288135593220339, "percentage": 32.69, "elapsed_time": "2:21:00", "remaining_time": "4:50:22"}
{"current_steps": 1220, "total_steps": 3717, "loss": 0.2062, "lr": 3.3998634031050056e-05, "epoch": 2.297551789077213, "percentage": 32.82, "elapsed_time": "2:21:32", "remaining_time": "4:49:41"}
{"current_steps": 1225, "total_steps": 3717, "loss": 0.2021, "lr": 3.393140201563581e-05, "epoch": 2.3069679849340865, "percentage": 32.96, "elapsed_time": "2:22:05", "remaining_time": "4:49:03"}
{"current_steps": 1230, "total_steps": 3717, "loss": 0.205, "lr": 3.3863862785844136e-05, "epoch": 2.3163841807909606, "percentage": 33.09, "elapsed_time": "2:22:39", "remaining_time": "4:48:26"}
{"current_steps": 1235, "total_steps": 3717, "loss": 0.2059, "lr": 3.379601783104578e-05, "epoch": 2.3258003766478343, "percentage": 33.23, "elapsed_time": "2:23:13", "remaining_time": "4:47:49"}
{"current_steps": 1240, "total_steps": 3717, "loss": 0.2101, "lr": 3.37278686473533e-05, "epoch": 2.335216572504708, "percentage": 33.36, "elapsed_time": "2:23:49", "remaining_time": "4:47:18"}
{"current_steps": 1245, "total_steps": 3717, "loss": 0.207, "lr": 3.3659416737588087e-05, "epoch": 2.3446327683615817, "percentage": 33.49, "elapsed_time": "2:24:23", "remaining_time": "4:46:40"}
{"current_steps": 1250, "total_steps": 3717, "loss": 0.2034, "lr": 3.3590663611247234e-05, "epoch": 2.354048964218456, "percentage": 33.63, "elapsed_time": "2:25:00", "remaining_time": "4:46:11"}
{"current_steps": 1255, "total_steps": 3717, "loss": 0.1936, "lr": 3.352161078447025e-05, "epoch": 2.3634651600753296, "percentage": 33.76, "elapsed_time": "2:25:32", "remaining_time": "4:45:31"}
{"current_steps": 1260, "total_steps": 3717, "loss": 0.2006, "lr": 3.34522597800056e-05, "epoch": 2.3728813559322033, "percentage": 33.9, "elapsed_time": "2:26:05", "remaining_time": "4:44:53"}
{"current_steps": 1265, "total_steps": 3717, "loss": 0.2016, "lr": 3.3382612127177166e-05, "epoch": 2.382297551789077, "percentage": 34.03, "elapsed_time": "2:26:40", "remaining_time": "4:44:18"}
{"current_steps": 1270, "total_steps": 3717, "loss": 0.2114, "lr": 3.331266936185048e-05, "epoch": 2.391713747645951, "percentage": 34.17, "elapsed_time": "2:27:14", "remaining_time": "4:43:41"}
{"current_steps": 1275, "total_steps": 3717, "loss": 0.2042, "lr": 3.32424330263989e-05, "epoch": 2.401129943502825, "percentage": 34.3, "elapsed_time": "2:27:48", "remaining_time": "4:43:06"}
{"current_steps": 1280, "total_steps": 3717, "loss": 0.1915, "lr": 3.3171904669669545e-05, "epoch": 2.4105461393596985, "percentage": 34.44, "elapsed_time": "2:28:21", "remaining_time": "4:42:27"}
{"current_steps": 1285, "total_steps": 3717, "loss": 0.228, "lr": 3.310108584694919e-05, "epoch": 2.4199623352165727, "percentage": 34.57, "elapsed_time": "2:28:51", "remaining_time": "4:41:44"}
{"current_steps": 1290, "total_steps": 3717, "loss": 0.1957, "lr": 3.3029978119929925e-05, "epoch": 2.4293785310734464, "percentage": 34.71, "elapsed_time": "2:29:28", "remaining_time": "4:41:12"}
{"current_steps": 1295, "total_steps": 3717, "loss": 0.225, "lr": 3.295858305667477e-05, "epoch": 2.43879472693032, "percentage": 34.84, "elapsed_time": "2:30:04", "remaining_time": "4:40:41"}
{"current_steps": 1300, "total_steps": 3717, "loss": 0.2168, "lr": 3.288690223158305e-05, "epoch": 2.4482109227871938, "percentage": 34.97, "elapsed_time": "2:30:38", "remaining_time": "4:40:05"}
{"current_steps": 1305, "total_steps": 3717, "loss": 0.1931, "lr": 3.2814937225355675e-05, "epoch": 2.457627118644068, "percentage": 35.11, "elapsed_time": "2:31:19", "remaining_time": "4:39:40"}
{"current_steps": 1310, "total_steps": 3717, "loss": 0.1974, "lr": 3.2742689624960327e-05, "epoch": 2.4670433145009416, "percentage": 35.24, "elapsed_time": "2:31:59", "remaining_time": "4:39:16"}
{"current_steps": 1315, "total_steps": 3717, "loss": 0.1951, "lr": 3.267016102359641e-05, "epoch": 2.4764595103578153, "percentage": 35.38, "elapsed_time": "2:32:38", "remaining_time": "4:38:49"}
{"current_steps": 1320, "total_steps": 3717, "loss": 0.1893, "lr": 3.259735302065997e-05, "epoch": 2.4858757062146895, "percentage": 35.51, "elapsed_time": "2:33:17", "remaining_time": "4:38:22"}
{"current_steps": 1325, "total_steps": 3717, "loss": 0.2147, "lr": 3.252426722170838e-05, "epoch": 2.495291902071563, "percentage": 35.65, "elapsed_time": "2:33:53", "remaining_time": "4:37:49"}
{"current_steps": 1330, "total_steps": 3717, "loss": 0.2109, "lr": 3.245090523842496e-05, "epoch": 2.504708097928437, "percentage": 35.78, "elapsed_time": "2:34:31", "remaining_time": "4:37:19"}
{"current_steps": 1335, "total_steps": 3717, "loss": 0.1991, "lr": 3.2377268688583425e-05, "epoch": 2.5141242937853105, "percentage": 35.92, "elapsed_time": "2:35:03", "remaining_time": "4:36:40"}
{"current_steps": 1340, "total_steps": 3717, "loss": 0.19, "lr": 3.2303359196012214e-05, "epoch": 2.5235404896421847, "percentage": 36.05, "elapsed_time": "2:35:44", "remaining_time": "4:36:16"}
{"current_steps": 1345, "total_steps": 3717, "loss": 0.1883, "lr": 3.2229178390558685e-05, "epoch": 2.5329566854990584, "percentage": 36.19, "elapsed_time": "2:36:19", "remaining_time": "4:35:41"}
{"current_steps": 1350, "total_steps": 3717, "loss": 0.1958, "lr": 3.2154727908053166e-05, "epoch": 2.542372881355932, "percentage": 36.32, "elapsed_time": "2:36:53", "remaining_time": "4:35:05"}
{"current_steps": 1355, "total_steps": 3717, "loss": 0.1891, "lr": 3.20800093902729e-05, "epoch": 2.5517890772128062, "percentage": 36.45, "elapsed_time": "2:37:28", "remaining_time": "4:34:30"}
{"current_steps": 1360, "total_steps": 3717, "loss": 0.1883, "lr": 3.20050244849058e-05, "epoch": 2.56120527306968, "percentage": 36.59, "elapsed_time": "2:38:11", "remaining_time": "4:34:09"}
{"current_steps": 1365, "total_steps": 3717, "loss": 0.2117, "lr": 3.192977484551416e-05, "epoch": 2.5706214689265536, "percentage": 36.72, "elapsed_time": "2:38:56", "remaining_time": "4:33:51"}
{"current_steps": 1370, "total_steps": 3717, "loss": 0.1875, "lr": 3.185426213149818e-05, "epoch": 2.5800376647834273, "percentage": 36.86, "elapsed_time": "2:39:33", "remaining_time": "4:33:20"}
{"current_steps": 1375, "total_steps": 3717, "loss": 0.1983, "lr": 3.177848800805933e-05, "epoch": 2.5894538606403015, "percentage": 36.99, "elapsed_time": "2:40:07", "remaining_time": "4:32:44"}
{"current_steps": 1380, "total_steps": 3717, "loss": 0.2199, "lr": 3.1702454146163705e-05, "epoch": 2.598870056497175, "percentage": 37.13, "elapsed_time": "2:40:36", "remaining_time": "4:31:59"}
{"current_steps": 1385, "total_steps": 3717, "loss": 0.2073, "lr": 3.162616222250511e-05, "epoch": 2.608286252354049, "percentage": 37.26, "elapsed_time": "2:41:06", "remaining_time": "4:31:16"}
{"current_steps": 1390, "total_steps": 3717, "loss": 0.2128, "lr": 3.1549613919468104e-05, "epoch": 2.617702448210923, "percentage": 37.4, "elapsed_time": "2:41:41", "remaining_time": "4:30:41"}
{"current_steps": 1395, "total_steps": 3717, "loss": 0.2106, "lr": 3.1472810925090945e-05, "epoch": 2.6271186440677967, "percentage": 37.53, "elapsed_time": "2:42:15", "remaining_time": "4:30:04"}
{"current_steps": 1400, "total_steps": 3717, "loss": 0.1945, "lr": 3.1395754933028295e-05, "epoch": 2.6365348399246704, "percentage": 37.66, "elapsed_time": "2:42:46", "remaining_time": "4:29:23"}
{"current_steps": 1405, "total_steps": 3717, "loss": 0.2117, "lr": 3.1318447642513905e-05, "epoch": 2.645951035781544, "percentage": 37.8, "elapsed_time": "2:43:20", "remaining_time": "4:28:47"}
{"current_steps": 1410, "total_steps": 3717, "loss": 0.205, "lr": 3.124089075832317e-05, "epoch": 2.655367231638418, "percentage": 37.93, "elapsed_time": "2:43:54", "remaining_time": "4:28:10"}
{"current_steps": 1415, "total_steps": 3717, "loss": 0.1912, "lr": 3.1163085990735474e-05, "epoch": 2.664783427495292, "percentage": 38.07, "elapsed_time": "2:44:27", "remaining_time": "4:27:33"}
{"current_steps": 1420, "total_steps": 3717, "loss": 0.1773, "lr": 3.1085035055496535e-05, "epoch": 2.6741996233521657, "percentage": 38.2, "elapsed_time": "2:45:02", "remaining_time": "4:26:58"}
{"current_steps": 1425, "total_steps": 3717, "loss": 0.1976, "lr": 3.100673967378053e-05, "epoch": 2.68361581920904, "percentage": 38.34, "elapsed_time": "2:45:38", "remaining_time": "4:26:24"}
{"current_steps": 1430, "total_steps": 3717, "loss": 0.1838, "lr": 3.0928201572152164e-05, "epoch": 2.6930320150659135, "percentage": 38.47, "elapsed_time": "2:46:14", "remaining_time": "4:25:52"}
{"current_steps": 1435, "total_steps": 3717, "loss": 0.1844, "lr": 3.0849422482528585e-05, "epoch": 2.702448210922787, "percentage": 38.61, "elapsed_time": "2:46:52", "remaining_time": "4:25:22"}
{"current_steps": 1440, "total_steps": 3717, "loss": 0.227, "lr": 3.077040414214118e-05, "epoch": 2.711864406779661, "percentage": 38.74, "elapsed_time": "2:47:26", "remaining_time": "4:24:45"}
{"current_steps": 1445, "total_steps": 3717, "loss": 0.195, "lr": 3.0691148293497295e-05, "epoch": 2.7212806026365346, "percentage": 38.88, "elapsed_time": "2:48:02", "remaining_time": "4:24:13"}
{"current_steps": 1450, "total_steps": 3717, "loss": 0.1971, "lr": 3.061165668434178e-05, "epoch": 2.7306967984934087, "percentage": 39.01, "elapsed_time": "2:48:38", "remaining_time": "4:23:40"}
{"current_steps": 1455, "total_steps": 3717, "loss": 0.1965, "lr": 3.053193106761847e-05, "epoch": 2.7401129943502824, "percentage": 39.14, "elapsed_time": "2:49:12", "remaining_time": "4:23:04"}
{"current_steps": 1460, "total_steps": 3717, "loss": 0.2158, "lr": 3.0451973201431504e-05, "epoch": 2.7495291902071566, "percentage": 39.28, "elapsed_time": "2:49:48", "remaining_time": "4:22:29"}
{"current_steps": 1465, "total_steps": 3717, "loss": 0.2059, "lr": 3.0371784849006604e-05, "epoch": 2.7589453860640303, "percentage": 39.41, "elapsed_time": "2:50:24", "remaining_time": "4:21:57"}
{"current_steps": 1470, "total_steps": 3717, "loss": 0.1916, "lr": 3.029136777865212e-05, "epoch": 2.768361581920904, "percentage": 39.55, "elapsed_time": "2:50:57", "remaining_time": "4:21:20"}
{"current_steps": 1475, "total_steps": 3717, "loss": 0.1906, "lr": 3.0210723763720106e-05, "epoch": 2.7777777777777777, "percentage": 39.68, "elapsed_time": "2:51:34", "remaining_time": "4:20:48"}
{"current_steps": 1480, "total_steps": 3717, "loss": 0.2243, "lr": 3.0129854582567155e-05, "epoch": 2.7871939736346514, "percentage": 39.82, "elapsed_time": "2:52:05", "remaining_time": "4:20:06"}
{"current_steps": 1485, "total_steps": 3717, "loss": 0.2041, "lr": 3.0048762018515238e-05, "epoch": 2.7966101694915255, "percentage": 39.95, "elapsed_time": "2:52:36", "remaining_time": "4:19:25"}
{"current_steps": 1490, "total_steps": 3717, "loss": 0.1853, "lr": 2.996744785981234e-05, "epoch": 2.806026365348399, "percentage": 40.09, "elapsed_time": "2:53:09", "remaining_time": "4:18:48"}
{"current_steps": 1495, "total_steps": 3717, "loss": 0.1779, "lr": 2.988591389959303e-05, "epoch": 2.815442561205273, "percentage": 40.22, "elapsed_time": "2:53:45", "remaining_time": "4:18:14"}
{"current_steps": 1500, "total_steps": 3717, "loss": 0.2039, "lr": 2.980416193583894e-05, "epoch": 2.824858757062147, "percentage": 40.36, "elapsed_time": "2:54:15", "remaining_time": "4:17:33"}
{"current_steps": 1505, "total_steps": 3717, "loss": 0.2157, "lr": 2.972219377133909e-05, "epoch": 2.8342749529190208, "percentage": 40.49, "elapsed_time": "2:55:08", "remaining_time": "4:17:25"}
{"current_steps": 1510, "total_steps": 3717, "loss": 0.1884, "lr": 2.9640011213650147e-05, "epoch": 2.8436911487758945, "percentage": 40.62, "elapsed_time": "2:55:43", "remaining_time": "4:16:50"}
{"current_steps": 1515, "total_steps": 3717, "loss": 0.2168, "lr": 2.9557616075056576e-05, "epoch": 2.853107344632768, "percentage": 40.76, "elapsed_time": "2:56:18", "remaining_time": "4:16:16"}
{"current_steps": 1520, "total_steps": 3717, "loss": 0.2097, "lr": 2.9475010172530636e-05, "epoch": 2.8625235404896423, "percentage": 40.89, "elapsed_time": "2:56:54", "remaining_time": "4:15:41"}
{"current_steps": 1525, "total_steps": 3717, "loss": 0.1961, "lr": 2.9392195327692364e-05, "epoch": 2.871939736346516, "percentage": 41.03, "elapsed_time": "2:57:29", "remaining_time": "4:15:07"}
{"current_steps": 1530, "total_steps": 3717, "loss": 0.2141, "lr": 2.930917336676937e-05, "epoch": 2.8813559322033897, "percentage": 41.16, "elapsed_time": "2:58:03", "remaining_time": "4:14:31"}
{"current_steps": 1535, "total_steps": 3717, "loss": 0.2122, "lr": 2.922594612055656e-05, "epoch": 2.890772128060264, "percentage": 41.3, "elapsed_time": "2:58:35", "remaining_time": "4:13:51"}
{"current_steps": 1540, "total_steps": 3717, "loss": 0.1962, "lr": 2.9142515424375814e-05, "epoch": 2.9001883239171375, "percentage": 41.43, "elapsed_time": "2:59:09", "remaining_time": "4:13:16"}
{"current_steps": 1545, "total_steps": 3717, "loss": 0.1984, "lr": 2.9058883118035438e-05, "epoch": 2.9096045197740112, "percentage": 41.57, "elapsed_time": "2:59:45", "remaining_time": "4:12:42"}
{"current_steps": 1550, "total_steps": 3717, "loss": 0.198, "lr": 2.897505104578965e-05, "epoch": 2.919020715630885, "percentage": 41.7, "elapsed_time": "3:00:15", "remaining_time": "4:12:01"}
{"current_steps": 1555, "total_steps": 3717, "loss": 0.205, "lr": 2.889102105629791e-05, "epoch": 2.928436911487759, "percentage": 41.83, "elapsed_time": "3:00:49", "remaining_time": "4:11:24"}
{"current_steps": 1560, "total_steps": 3717, "loss": 0.2075, "lr": 2.8806795002584097e-05, "epoch": 2.937853107344633, "percentage": 41.97, "elapsed_time": "3:01:22", "remaining_time": "4:10:47"}
{"current_steps": 1565, "total_steps": 3717, "loss": 0.2107, "lr": 2.8722374741995726e-05, "epoch": 2.9472693032015065, "percentage": 42.1, "elapsed_time": "3:01:58", "remaining_time": "4:10:13"}
{"current_steps": 1570, "total_steps": 3717, "loss": 0.1956, "lr": 2.8637762136162913e-05, "epoch": 2.9566854990583806, "percentage": 42.24, "elapsed_time": "3:02:30", "remaining_time": "4:09:34"}
{"current_steps": 1575, "total_steps": 3717, "loss": 0.1928, "lr": 2.8552959050957384e-05, "epoch": 2.9661016949152543, "percentage": 42.37, "elapsed_time": "3:03:03", "remaining_time": "4:08:56"}
{"current_steps": 1580, "total_steps": 3717, "loss": 0.1973, "lr": 2.846796735645131e-05, "epoch": 2.975517890772128, "percentage": 42.51, "elapsed_time": "3:03:35", "remaining_time": "4:08:19"}
{"current_steps": 1585, "total_steps": 3717, "loss": 0.2046, "lr": 2.8382788926876027e-05, "epoch": 2.9849340866290017, "percentage": 42.64, "elapsed_time": "3:04:07", "remaining_time": "4:07:40"}
{"current_steps": 1590, "total_steps": 3717, "loss": 0.1946, "lr": 2.829742564058078e-05, "epoch": 2.994350282485876, "percentage": 42.78, "elapsed_time": "3:04:39", "remaining_time": "4:07:02"}
{"current_steps": 1595, "total_steps": 3717, "loss": 0.2013, "lr": 2.821187937999123e-05, "epoch": 3.0037664783427496, "percentage": 42.91, "elapsed_time": "3:05:16", "remaining_time": "4:06:29"}
{"current_steps": 1600, "total_steps": 3717, "loss": 0.1854, "lr": 2.8126152031567994e-05, "epoch": 3.0131826741996233, "percentage": 43.05, "elapsed_time": "3:05:52", "remaining_time": "4:05:56"}
{"current_steps": 1605, "total_steps": 3717, "loss": 0.1711, "lr": 2.8040245485765036e-05, "epoch": 3.022598870056497, "percentage": 43.18, "elapsed_time": "3:06:24", "remaining_time": "4:05:17"}
{"current_steps": 1610, "total_steps": 3717, "loss": 0.1908, "lr": 2.7954161636987937e-05, "epoch": 3.032015065913371, "percentage": 43.31, "elapsed_time": "3:06:53", "remaining_time": "4:04:35"}
{"current_steps": 1615, "total_steps": 3717, "loss": 0.1761, "lr": 2.786790238355218e-05, "epoch": 3.041431261770245, "percentage": 43.45, "elapsed_time": "3:07:28", "remaining_time": "4:04:00"}
{"current_steps": 1620, "total_steps": 3717, "loss": 0.1848, "lr": 2.7781469627641246e-05, "epoch": 3.0508474576271185, "percentage": 43.58, "elapsed_time": "3:08:01", "remaining_time": "4:03:23"}
{"current_steps": 1625, "total_steps": 3717, "loss": 0.1847, "lr": 2.769486527526469e-05, "epoch": 3.0602636534839927, "percentage": 43.72, "elapsed_time": "3:08:35", "remaining_time": "4:02:47"}
{"current_steps": 1630, "total_steps": 3717, "loss": 0.1833, "lr": 2.7608091236216092e-05, "epoch": 3.0696798493408664, "percentage": 43.85, "elapsed_time": "3:09:09", "remaining_time": "4:02:11"}
{"current_steps": 1635, "total_steps": 3717, "loss": 0.1625, "lr": 2.752114942403096e-05, "epoch": 3.07909604519774, "percentage": 43.99, "elapsed_time": "3:09:44", "remaining_time": "4:01:37"}
{"current_steps": 1640, "total_steps": 3717, "loss": 0.1789, "lr": 2.743404175594452e-05, "epoch": 3.0885122410546137, "percentage": 44.12, "elapsed_time": "3:10:18", "remaining_time": "4:01:00"}
{"current_steps": 1645, "total_steps": 3717, "loss": 0.1689, "lr": 2.734677015284944e-05, "epoch": 3.097928436911488, "percentage": 44.26, "elapsed_time": "3:10:50", "remaining_time": "4:00:23"}
{"current_steps": 1650, "total_steps": 3717, "loss": 0.1909, "lr": 2.7259336539253484e-05, "epoch": 3.1073446327683616, "percentage": 44.39, "elapsed_time": "3:11:23", "remaining_time": "3:59:46"}
{"current_steps": 1655, "total_steps": 3717, "loss": 0.181, "lr": 2.717174284323703e-05, "epoch": 3.1167608286252353, "percentage": 44.53, "elapsed_time": "3:11:58", "remaining_time": "3:59:11"}
{"current_steps": 1660, "total_steps": 3717, "loss": 0.1724, "lr": 2.708399099641063e-05, "epoch": 3.1261770244821094, "percentage": 44.66, "elapsed_time": "3:12:32", "remaining_time": "3:58:35"}
{"current_steps": 1665, "total_steps": 3717, "loss": 0.1895, "lr": 2.699608293387233e-05, "epoch": 3.135593220338983, "percentage": 44.79, "elapsed_time": "3:13:06", "remaining_time": "3:57:59"}
{"current_steps": 1670, "total_steps": 3717, "loss": 0.1735, "lr": 2.6908020594165046e-05, "epoch": 3.145009416195857, "percentage": 44.93, "elapsed_time": "3:13:41", "remaining_time": "3:57:24"}
{"current_steps": 1675, "total_steps": 3717, "loss": 0.1784, "lr": 2.681980591923381e-05, "epoch": 3.1544256120527305, "percentage": 45.06, "elapsed_time": "3:14:13", "remaining_time": "3:56:47"}
{"current_steps": 1680, "total_steps": 3717, "loss": 0.178, "lr": 2.673144085438293e-05, "epoch": 3.1638418079096047, "percentage": 45.2, "elapsed_time": "3:14:46", "remaining_time": "3:56:09"}
{"current_steps": 1685, "total_steps": 3717, "loss": 0.1726, "lr": 2.6642927348233113e-05, "epoch": 3.1732580037664784, "percentage": 45.33, "elapsed_time": "3:15:23", "remaining_time": "3:55:37"}
{"current_steps": 1690, "total_steps": 3717, "loss": 0.1653, "lr": 2.6554267352678485e-05, "epoch": 3.182674199623352, "percentage": 45.47, "elapsed_time": "3:15:56", "remaining_time": "3:55:01"}
{"current_steps": 1695, "total_steps": 3717, "loss": 0.1739, "lr": 2.646546282284353e-05, "epoch": 3.1920903954802258, "percentage": 45.6, "elapsed_time": "3:16:30", "remaining_time": "3:54:24"}
{"current_steps": 1700, "total_steps": 3717, "loss": 0.1805, "lr": 2.6376515717040012e-05, "epoch": 3.2015065913371, "percentage": 45.74, "elapsed_time": "3:17:04", "remaining_time": "3:53:49"}
{"current_steps": 1705, "total_steps": 3717, "loss": 0.1787, "lr": 2.6287427996723756e-05, "epoch": 3.2109227871939736, "percentage": 45.87, "elapsed_time": "3:17:37", "remaining_time": "3:53:12"}
{"current_steps": 1710, "total_steps": 3717, "loss": 0.1714, "lr": 2.6198201626451428e-05, "epoch": 3.2203389830508473, "percentage": 46.0, "elapsed_time": "3:18:08", "remaining_time": "3:52:33"}
{"current_steps": 1715, "total_steps": 3717, "loss": 0.1777, "lr": 2.6108838573837165e-05, "epoch": 3.2297551789077215, "percentage": 46.14, "elapsed_time": "3:18:39", "remaining_time": "3:51:53"}
{"current_steps": 1720, "total_steps": 3717, "loss": 0.1825, "lr": 2.6019340809509248e-05, "epoch": 3.239171374764595, "percentage": 46.27, "elapsed_time": "3:19:13", "remaining_time": "3:51:18"}
{"current_steps": 1725, "total_steps": 3717, "loss": 0.1717, "lr": 2.5929710307066588e-05, "epoch": 3.248587570621469, "percentage": 46.41, "elapsed_time": "3:19:47", "remaining_time": "3:50:43"}
{"current_steps": 1730, "total_steps": 3717, "loss": 0.1881, "lr": 2.583994904303523e-05, "epoch": 3.2580037664783426, "percentage": 46.54, "elapsed_time": "3:20:23", "remaining_time": "3:50:09"}
{"current_steps": 1735, "total_steps": 3717, "loss": 0.1791, "lr": 2.575005899682479e-05, "epoch": 3.2674199623352167, "percentage": 46.68, "elapsed_time": "3:20:57", "remaining_time": "3:49:34"}
{"current_steps": 1740, "total_steps": 3717, "loss": 0.1909, "lr": 2.5660042150684735e-05, "epoch": 3.2768361581920904, "percentage": 46.81, "elapsed_time": "3:21:33", "remaining_time": "3:49:00"}
{"current_steps": 1745, "total_steps": 3717, "loss": 0.1695, "lr": 2.556990048966076e-05, "epoch": 3.286252354048964, "percentage": 46.95, "elapsed_time": "3:22:05", "remaining_time": "3:48:22"}
{"current_steps": 1750, "total_steps": 3717, "loss": 0.1759, "lr": 2.547963600155094e-05, "epoch": 3.2956685499058382, "percentage": 47.08, "elapsed_time": "3:22:40", "remaining_time": "3:47:48"}
{"current_steps": 1755, "total_steps": 3717, "loss": 0.1712, "lr": 2.5389250676861945e-05, "epoch": 3.305084745762712, "percentage": 47.22, "elapsed_time": "3:23:14", "remaining_time": "3:47:12"}
{"current_steps": 1760, "total_steps": 3717, "loss": 0.191, "lr": 2.529874650876512e-05, "epoch": 3.3145009416195856, "percentage": 47.35, "elapsed_time": "3:23:47", "remaining_time": "3:46:35"}
{"current_steps": 1765, "total_steps": 3717, "loss": 0.1838, "lr": 2.5208125493052527e-05, "epoch": 3.3239171374764593, "percentage": 47.48, "elapsed_time": "3:24:23", "remaining_time": "3:46:02"}
{"current_steps": 1770, "total_steps": 3717, "loss": 0.1901, "lr": 2.511738962809295e-05, "epoch": 3.3333333333333335, "percentage": 47.62, "elapsed_time": "3:24:53", "remaining_time": "3:45:22"}
{"current_steps": 1775, "total_steps": 3717, "loss": 0.1788, "lr": 2.5026540914787835e-05, "epoch": 3.342749529190207, "percentage": 47.75, "elapsed_time": "3:25:26", "remaining_time": "3:44:46"}
{"current_steps": 1780, "total_steps": 3717, "loss": 0.1869, "lr": 2.493558135652712e-05, "epoch": 3.352165725047081, "percentage": 47.89, "elapsed_time": "3:25:59", "remaining_time": "3:44:10"}
{"current_steps": 1785, "total_steps": 3717, "loss": 0.1693, "lr": 2.4844512959145126e-05, "epoch": 3.361581920903955, "percentage": 48.02, "elapsed_time": "3:26:33", "remaining_time": "3:43:33"}
{"current_steps": 1790, "total_steps": 3717, "loss": 0.2063, "lr": 2.4753337730876267e-05, "epoch": 3.3709981167608287, "percentage": 48.16, "elapsed_time": "3:27:04", "remaining_time": "3:42:55"}
{"current_steps": 1795, "total_steps": 3717, "loss": 0.174, "lr": 2.466205768231078e-05, "epoch": 3.3804143126177024, "percentage": 48.29, "elapsed_time": "3:27:40", "remaining_time": "3:42:21"}
{"current_steps": 1800, "total_steps": 3717, "loss": 0.1748, "lr": 2.4570674826350406e-05, "epoch": 3.389830508474576, "percentage": 48.43, "elapsed_time": "3:28:15", "remaining_time": "3:41:47"}
{"current_steps": 1805, "total_steps": 3717, "loss": 0.1848, "lr": 2.4479191178163975e-05, "epoch": 3.3992467043314503, "percentage": 48.56, "elapsed_time": "3:28:49", "remaining_time": "3:41:12"}
{"current_steps": 1810, "total_steps": 3717, "loss": 0.1936, "lr": 2.4387608755142997e-05, "epoch": 3.408662900188324, "percentage": 48.7, "elapsed_time": "3:29:24", "remaining_time": "3:40:38"}
{"current_steps": 1815, "total_steps": 3717, "loss": 0.1744, "lr": 2.429592957685715e-05, "epoch": 3.4180790960451977, "percentage": 48.83, "elapsed_time": "3:29:59", "remaining_time": "3:40:03"}
{"current_steps": 1820, "total_steps": 3717, "loss": 0.1725, "lr": 2.4204155665009746e-05, "epoch": 3.427495291902072, "percentage": 48.96, "elapsed_time": "3:30:34", "remaining_time": "3:39:28"}
{"current_steps": 1825, "total_steps": 3717, "loss": 0.2083, "lr": 2.411228904339316e-05, "epoch": 3.4369114877589455, "percentage": 49.1, "elapsed_time": "3:31:00", "remaining_time": "3:38:45"}
{"current_steps": 1830, "total_steps": 3717, "loss": 0.1815, "lr": 2.40203317378442e-05, "epoch": 3.446327683615819, "percentage": 49.23, "elapsed_time": "3:31:33", "remaining_time": "3:38:08"}
{"current_steps": 1835, "total_steps": 3717, "loss": 0.1761, "lr": 2.3928285776199432e-05, "epoch": 3.455743879472693, "percentage": 49.37, "elapsed_time": "3:32:06", "remaining_time": "3:37:32"}
{"current_steps": 1840, "total_steps": 3717, "loss": 0.1801, "lr": 2.3836153188250456e-05, "epoch": 3.465160075329567, "percentage": 49.5, "elapsed_time": "3:32:42", "remaining_time": "3:36:59"}
{"current_steps": 1845, "total_steps": 3717, "loss": 0.1715, "lr": 2.3743936005699153e-05, "epoch": 3.4745762711864407, "percentage": 49.64, "elapsed_time": "3:33:17", "remaining_time": "3:36:24"}
{"current_steps": 1850, "total_steps": 3717, "loss": 0.1737, "lr": 2.365163626211287e-05, "epoch": 3.4839924670433144, "percentage": 49.77, "elapsed_time": "3:33:51", "remaining_time": "3:35:49"}
{"current_steps": 1855, "total_steps": 3717, "loss": 0.1953, "lr": 2.3559255992879586e-05, "epoch": 3.493408662900188, "percentage": 49.91, "elapsed_time": "3:34:26", "remaining_time": "3:35:15"}
{"current_steps": 1860, "total_steps": 3717, "loss": 0.1903, "lr": 2.3466797235163047e-05, "epoch": 3.5028248587570623, "percentage": 50.04, "elapsed_time": "3:34:59", "remaining_time": "3:34:38"}
{"current_steps": 1865, "total_steps": 3717, "loss": 0.182, "lr": 2.3374262027857796e-05, "epoch": 3.512241054613936, "percentage": 50.17, "elapsed_time": "3:35:26", "remaining_time": "3:33:55"}
{"current_steps": 1870, "total_steps": 3717, "loss": 0.1764, "lr": 2.3281652411544252e-05, "epoch": 3.5216572504708097, "percentage": 50.31, "elapsed_time": "3:35:59", "remaining_time": "3:33:20"}
{"current_steps": 1875, "total_steps": 3717, "loss": 0.1895, "lr": 2.318897042844369e-05, "epoch": 3.5310734463276834, "percentage": 50.44, "elapsed_time": "3:36:35", "remaining_time": "3:32:46"}
{"current_steps": 1880, "total_steps": 3717, "loss": 0.1852, "lr": 2.309621812237321e-05, "epoch": 3.5404896421845575, "percentage": 50.58, "elapsed_time": "3:37:06", "remaining_time": "3:32:08"}
{"current_steps": 1885, "total_steps": 3717, "loss": 0.2007, "lr": 2.300339753870069e-05, "epoch": 3.5499058380414312, "percentage": 50.71, "elapsed_time": "3:37:39", "remaining_time": "3:31:31"}
{"current_steps": 1890, "total_steps": 3717, "loss": 0.1672, "lr": 2.291051072429963e-05, "epoch": 3.559322033898305, "percentage": 50.85, "elapsed_time": "3:38:11", "remaining_time": "3:30:55"}
{"current_steps": 1895, "total_steps": 3717, "loss": 0.1824, "lr": 2.2817559727504067e-05, "epoch": 3.568738229755179, "percentage": 50.98, "elapsed_time": "3:38:45", "remaining_time": "3:30:20"}
{"current_steps": 1900, "total_steps": 3717, "loss": 0.1872, "lr": 2.2724546598063376e-05, "epoch": 3.5781544256120528, "percentage": 51.12, "elapsed_time": "3:39:18", "remaining_time": "3:29:43"}
{"current_steps": 1905, "total_steps": 3717, "loss": 0.1959, "lr": 2.263147338709709e-05, "epoch": 3.5875706214689265, "percentage": 51.25, "elapsed_time": "3:39:51", "remaining_time": "3:29:07"}
{"current_steps": 1910, "total_steps": 3717, "loss": 0.1708, "lr": 2.253834214704963e-05, "epoch": 3.5969868173258, "percentage": 51.39, "elapsed_time": "3:40:21", "remaining_time": "3:28:28"}
{"current_steps": 1915, "total_steps": 3717, "loss": 0.1894, "lr": 2.2445154931645102e-05, "epoch": 3.6064030131826743, "percentage": 51.52, "elapsed_time": "3:40:51", "remaining_time": "3:27:49"}
{"current_steps": 1920, "total_steps": 3717, "loss": 0.1906, "lr": 2.235191379584195e-05, "epoch": 3.615819209039548, "percentage": 51.65, "elapsed_time": "3:41:25", "remaining_time": "3:27:14"}
{"current_steps": 1925, "total_steps": 3717, "loss": 0.192, "lr": 2.225862079578768e-05, "epoch": 3.6252354048964217, "percentage": 51.79, "elapsed_time": "3:41:58", "remaining_time": "3:26:37"}
{"current_steps": 1930, "total_steps": 3717, "loss": 0.1838, "lr": 2.2165277988773513e-05, "epoch": 3.634651600753296, "percentage": 51.92, "elapsed_time": "3:42:29", "remaining_time": "3:26:00"}
{"current_steps": 1935, "total_steps": 3717, "loss": 0.186, "lr": 2.2071887433188982e-05, "epoch": 3.6440677966101696, "percentage": 52.06, "elapsed_time": "3:43:00", "remaining_time": "3:25:22"}
{"current_steps": 1940, "total_steps": 3717, "loss": 0.1696, "lr": 2.1978451188476604e-05, "epoch": 3.6534839924670433, "percentage": 52.19, "elapsed_time": "3:43:33", "remaining_time": "3:24:46"}
{"current_steps": 1945, "total_steps": 3717, "loss": 0.18, "lr": 2.1884971315086406e-05, "epoch": 3.662900188323917, "percentage": 52.33, "elapsed_time": "3:44:09", "remaining_time": "3:24:12"}
{"current_steps": 1950, "total_steps": 3717, "loss": 0.1715, "lr": 2.179144987443051e-05, "epoch": 3.672316384180791, "percentage": 52.46, "elapsed_time": "3:44:43", "remaining_time": "3:23:37"}
{"current_steps": 1955, "total_steps": 3717, "loss": 0.1631, "lr": 2.1697888928837707e-05, "epoch": 3.681732580037665, "percentage": 52.6, "elapsed_time": "3:45:16", "remaining_time": "3:23:01"}
{"current_steps": 1960, "total_steps": 3717, "loss": 0.1769, "lr": 2.16042905415079e-05, "epoch": 3.6911487758945385, "percentage": 52.73, "elapsed_time": "3:45:50", "remaining_time": "3:22:27"}
{"current_steps": 1965, "total_steps": 3717, "loss": 0.1771, "lr": 2.151065677646669e-05, "epoch": 3.7005649717514126, "percentage": 52.87, "elapsed_time": "3:46:23", "remaining_time": "3:21:50"}
{"current_steps": 1970, "total_steps": 3717, "loss": 0.1591, "lr": 2.1416989698519833e-05, "epoch": 3.7099811676082863, "percentage": 53.0, "elapsed_time": "3:46:57", "remaining_time": "3:21:16"}
{"current_steps": 1975, "total_steps": 3717, "loss": 0.1736, "lr": 2.1323291373207655e-05, "epoch": 3.71939736346516, "percentage": 53.13, "elapsed_time": "3:47:31", "remaining_time": "3:20:40"}
{"current_steps": 1980, "total_steps": 3717, "loss": 0.1751, "lr": 2.1229563866759592e-05, "epoch": 3.7288135593220337, "percentage": 53.27, "elapsed_time": "3:48:03", "remaining_time": "3:20:04"}
{"current_steps": 1985, "total_steps": 3717, "loss": 0.1842, "lr": 2.1135809246048553e-05, "epoch": 3.738229755178908, "percentage": 53.4, "elapsed_time": "3:48:33", "remaining_time": "3:19:25"}
{"current_steps": 1990, "total_steps": 3717, "loss": 0.1728, "lr": 2.104202957854539e-05, "epoch": 3.7476459510357816, "percentage": 53.54, "elapsed_time": "3:49:08", "remaining_time": "3:18:51"}
{"current_steps": 1995, "total_steps": 3717, "loss": 0.1972, "lr": 2.0948226932273256e-05, "epoch": 3.7570621468926553, "percentage": 53.67, "elapsed_time": "3:49:37", "remaining_time": "3:18:12"}
{"current_steps": 2000, "total_steps": 3717, "loss": 0.1903, "lr": 2.085440337576206e-05, "epoch": 3.7664783427495294, "percentage": 53.81, "elapsed_time": "3:50:13", "remaining_time": "3:17:38"}
{"current_steps": 2005, "total_steps": 3717, "loss": 0.1903, "lr": 2.0760560978002808e-05, "epoch": 3.775894538606403, "percentage": 53.94, "elapsed_time": "3:50:45", "remaining_time": "3:17:02"}
{"current_steps": 2010, "total_steps": 3717, "loss": 0.2062, "lr": 2.0666701808401996e-05, "epoch": 3.785310734463277, "percentage": 54.08, "elapsed_time": "3:51:18", "remaining_time": "3:16:26"}
{"current_steps": 2015, "total_steps": 3717, "loss": 0.1941, "lr": 2.0572827936735967e-05, "epoch": 3.7947269303201505, "percentage": 54.21, "elapsed_time": "3:51:51", "remaining_time": "3:15:50"}
{"current_steps": 2020, "total_steps": 3717, "loss": 0.1782, "lr": 2.0478941433105276e-05, "epoch": 3.804143126177024, "percentage": 54.34, "elapsed_time": "3:52:25", "remaining_time": "3:15:15"}
{"current_steps": 2025, "total_steps": 3717, "loss": 0.1829, "lr": 2.038504436788903e-05, "epoch": 3.8135593220338984, "percentage": 54.48, "elapsed_time": "3:52:58", "remaining_time": "3:14:40"}
{"current_steps": 2030, "total_steps": 3717, "loss": 0.1929, "lr": 2.029113881169926e-05, "epoch": 3.822975517890772, "percentage": 54.61, "elapsed_time": "3:53:31", "remaining_time": "3:14:03"}
{"current_steps": 2035, "total_steps": 3717, "loss": 0.1665, "lr": 2.0197226835335217e-05, "epoch": 3.832391713747646, "percentage": 54.75, "elapsed_time": "3:54:06", "remaining_time": "3:13:29"}
{"current_steps": 2040, "total_steps": 3717, "loss": 0.1777, "lr": 2.010331050973774e-05, "epoch": 3.84180790960452, "percentage": 54.88, "elapsed_time": "3:54:40", "remaining_time": "3:12:54"}
{"current_steps": 2045, "total_steps": 3717, "loss": 0.1758, "lr": 2.000939190594358e-05, "epoch": 3.8512241054613936, "percentage": 55.02, "elapsed_time": "3:55:13", "remaining_time": "3:12:19"}
{"current_steps": 2050, "total_steps": 3717, "loss": 0.1885, "lr": 1.9915473095039708e-05, "epoch": 3.8606403013182673, "percentage": 55.15, "elapsed_time": "3:55:46", "remaining_time": "3:11:43"}
{"current_steps": 2055, "total_steps": 3717, "loss": 0.1668, "lr": 1.982155614811769e-05, "epoch": 3.870056497175141, "percentage": 55.29, "elapsed_time": "3:56:20", "remaining_time": "3:11:08"}
{"current_steps": 2060, "total_steps": 3717, "loss": 0.1866, "lr": 1.9727643136227975e-05, "epoch": 3.879472693032015, "percentage": 55.42, "elapsed_time": "3:56:50", "remaining_time": "3:10:30"}
{"current_steps": 2065, "total_steps": 3717, "loss": 0.1818, "lr": 1.963373613033421e-05, "epoch": 3.888888888888889, "percentage": 55.56, "elapsed_time": "3:57:23", "remaining_time": "3:09:54"}
{"current_steps": 2070, "total_steps": 3717, "loss": 0.1868, "lr": 1.953983720126766e-05, "epoch": 3.898305084745763, "percentage": 55.69, "elapsed_time": "3:57:57", "remaining_time": "3:09:20"}
{"current_steps": 2075, "total_steps": 3717, "loss": 0.1722, "lr": 1.9445948419681418e-05, "epoch": 3.9077212806026367, "percentage": 55.82, "elapsed_time": "3:58:32", "remaining_time": "3:08:45"}
{"current_steps": 2080, "total_steps": 3717, "loss": 0.1848, "lr": 1.9352071856004833e-05, "epoch": 3.9171374764595104, "percentage": 55.96, "elapsed_time": "3:59:09", "remaining_time": "3:08:13"}
{"current_steps": 2085, "total_steps": 3717, "loss": 0.1758, "lr": 1.925820958039784e-05, "epoch": 3.926553672316384, "percentage": 56.09, "elapsed_time": "3:59:42", "remaining_time": "3:07:37"}
{"current_steps": 2090, "total_steps": 3717, "loss": 0.1952, "lr": 1.9164363662705264e-05, "epoch": 3.935969868173258, "percentage": 56.23, "elapsed_time": "4:00:08", "remaining_time": "3:06:56"}
{"current_steps": 2095, "total_steps": 3717, "loss": 0.1718, "lr": 1.9070536172411227e-05, "epoch": 3.945386064030132, "percentage": 56.36, "elapsed_time": "4:00:41", "remaining_time": "3:06:21"}
{"current_steps": 2100, "total_steps": 3717, "loss": 0.1734, "lr": 1.8976729178593475e-05, "epoch": 3.9548022598870056, "percentage": 56.5, "elapsed_time": "4:01:15", "remaining_time": "3:05:45"}
{"current_steps": 2105, "total_steps": 3717, "loss": 0.1802, "lr": 1.888294474987779e-05, "epoch": 3.9642184557438793, "percentage": 56.63, "elapsed_time": "4:01:48", "remaining_time": "3:05:10"}
{"current_steps": 2110, "total_steps": 3717, "loss": 0.1769, "lr": 1.878918495439233e-05, "epoch": 3.9736346516007535, "percentage": 56.77, "elapsed_time": "4:02:24", "remaining_time": "3:04:37"}
{"current_steps": 2115, "total_steps": 3717, "loss": 0.1876, "lr": 1.8695451859722043e-05, "epoch": 3.983050847457627, "percentage": 56.9, "elapsed_time": "4:02:57", "remaining_time": "3:04:01"}
{"current_steps": 2120, "total_steps": 3717, "loss": 0.1737, "lr": 1.860174753286309e-05, "epoch": 3.992467043314501, "percentage": 57.04, "elapsed_time": "4:03:31", "remaining_time": "3:03:27"}
{"current_steps": 2125, "total_steps": 3717, "loss": 0.1779, "lr": 1.8508074040177235e-05, "epoch": 4.001883239171375, "percentage": 57.17, "elapsed_time": "4:04:03", "remaining_time": "3:02:50"}
{"current_steps": 2130, "total_steps": 3717, "loss": 0.1545, "lr": 1.8414433447346277e-05, "epoch": 4.011299435028248, "percentage": 57.3, "elapsed_time": "4:04:38", "remaining_time": "3:02:16"}
{"current_steps": 2135, "total_steps": 3717, "loss": 0.16, "lr": 1.8320827819326523e-05, "epoch": 4.020715630885123, "percentage": 57.44, "elapsed_time": "4:05:09", "remaining_time": "3:01:39"}
{"current_steps": 2140, "total_steps": 3717, "loss": 0.1586, "lr": 1.8227259220303243e-05, "epoch": 4.0301318267419965, "percentage": 57.57, "elapsed_time": "4:05:43", "remaining_time": "3:01:04"}
{"current_steps": 2145, "total_steps": 3717, "loss": 0.1634, "lr": 1.8133729713645138e-05, "epoch": 4.03954802259887, "percentage": 57.71, "elapsed_time": "4:06:18", "remaining_time": "3:00:30"}
{"current_steps": 2150, "total_steps": 3717, "loss": 0.1567, "lr": 1.8040241361858837e-05, "epoch": 4.048964218455744, "percentage": 57.84, "elapsed_time": "4:06:51", "remaining_time": "2:59:55"}
{"current_steps": 2155, "total_steps": 3717, "loss": 0.1739, "lr": 1.794679622654345e-05, "epoch": 4.058380414312618, "percentage": 57.98, "elapsed_time": "4:07:25", "remaining_time": "2:59:20"}
{"current_steps": 2160, "total_steps": 3717, "loss": 0.1605, "lr": 1.785339636834506e-05, "epoch": 4.067796610169491, "percentage": 58.11, "elapsed_time": "4:08:00", "remaining_time": "2:58:46"}
{"current_steps": 2165, "total_steps": 3717, "loss": 0.1658, "lr": 1.77600438469113e-05, "epoch": 4.077212806026365, "percentage": 58.25, "elapsed_time": "4:08:33", "remaining_time": "2:58:10"}
{"current_steps": 2170, "total_steps": 3717, "loss": 0.1565, "lr": 1.7666740720845957e-05, "epoch": 4.086629001883239, "percentage": 58.38, "elapsed_time": "4:09:07", "remaining_time": "2:57:35"}
{"current_steps": 2175, "total_steps": 3717, "loss": 0.1788, "lr": 1.7573489047663534e-05, "epoch": 4.096045197740113, "percentage": 58.51, "elapsed_time": "4:09:42", "remaining_time": "2:57:01"}
{"current_steps": 2180, "total_steps": 3717, "loss": 0.1682, "lr": 1.7480290883743903e-05, "epoch": 4.105461393596987, "percentage": 58.65, "elapsed_time": "4:10:15", "remaining_time": "2:56:26"}
{"current_steps": 2185, "total_steps": 3717, "loss": 0.1536, "lr": 1.7387148284286944e-05, "epoch": 4.114877589453861, "percentage": 58.78, "elapsed_time": "4:10:48", "remaining_time": "2:55:51"}
{"current_steps": 2190, "total_steps": 3717, "loss": 0.1795, "lr": 1.729406330326727e-05, "epoch": 4.124293785310734, "percentage": 58.92, "elapsed_time": "4:11:21", "remaining_time": "2:55:15"}
{"current_steps": 2195, "total_steps": 3717, "loss": 0.1532, "lr": 1.720103799338885e-05, "epoch": 4.133709981167608, "percentage": 59.05, "elapsed_time": "4:11:53", "remaining_time": "2:54:39"}
{"current_steps": 2200, "total_steps": 3717, "loss": 0.164, "lr": 1.7108074406039814e-05, "epoch": 4.143126177024482, "percentage": 59.19, "elapsed_time": "4:12:26", "remaining_time": "2:54:04"}
{"current_steps": 2205, "total_steps": 3717, "loss": 0.1582, "lr": 1.701517459124719e-05, "epoch": 4.1525423728813555, "percentage": 59.32, "elapsed_time": "4:12:59", "remaining_time": "2:53:28"}
{"current_steps": 2210, "total_steps": 3717, "loss": 0.1584, "lr": 1.692234059763169e-05, "epoch": 4.16195856873823, "percentage": 59.46, "elapsed_time": "4:13:34", "remaining_time": "2:52:54"}
{"current_steps": 2215, "total_steps": 3717, "loss": 0.1626, "lr": 1.6829574472362547e-05, "epoch": 4.171374764595104, "percentage": 59.59, "elapsed_time": "4:14:06", "remaining_time": "2:52:19"}
{"current_steps": 2220, "total_steps": 3717, "loss": 0.1735, "lr": 1.6736878261112355e-05, "epoch": 4.1807909604519775, "percentage": 59.73, "elapsed_time": "4:14:39", "remaining_time": "2:51:43"}
{"current_steps": 2225, "total_steps": 3717, "loss": 0.1665, "lr": 1.664425400801199e-05, "epoch": 4.190207156308851, "percentage": 59.86, "elapsed_time": "4:15:12", "remaining_time": "2:51:08"}
{"current_steps": 2230, "total_steps": 3717, "loss": 0.1723, "lr": 1.6551703755605496e-05, "epoch": 4.199623352165725, "percentage": 59.99, "elapsed_time": "4:15:48", "remaining_time": "2:50:34"}
{"current_steps": 2235, "total_steps": 3717, "loss": 0.1548, "lr": 1.6459229544805045e-05, "epoch": 4.209039548022599, "percentage": 60.13, "elapsed_time": "4:16:21", "remaining_time": "2:49:59"}
{"current_steps": 2240, "total_steps": 3717, "loss": 0.1667, "lr": 1.636683341484599e-05, "epoch": 4.218455743879472, "percentage": 60.26, "elapsed_time": "4:16:56", "remaining_time": "2:49:25"}
{"current_steps": 2245, "total_steps": 3717, "loss": 0.178, "lr": 1.62745174032418e-05, "epoch": 4.227871939736347, "percentage": 60.4, "elapsed_time": "4:17:27", "remaining_time": "2:48:48"}
{"current_steps": 2250, "total_steps": 3717, "loss": 0.1652, "lr": 1.61822835457392e-05, "epoch": 4.237288135593221, "percentage": 60.53, "elapsed_time": "4:18:01", "remaining_time": "2:48:14"}
{"current_steps": 2255, "total_steps": 3717, "loss": 0.1492, "lr": 1.6090133876273267e-05, "epoch": 4.246704331450094, "percentage": 60.67, "elapsed_time": "4:18:37", "remaining_time": "2:47:40"}
{"current_steps": 2260, "total_steps": 3717, "loss": 0.1635, "lr": 1.5998070426922556e-05, "epoch": 4.256120527306968, "percentage": 60.8, "elapsed_time": "4:19:08", "remaining_time": "2:47:04"}
{"current_steps": 2265, "total_steps": 3717, "loss": 0.1552, "lr": 1.5906095227864307e-05, "epoch": 4.265536723163842, "percentage": 60.94, "elapsed_time": "4:19:43", "remaining_time": "2:46:30"}
{"current_steps": 2270, "total_steps": 3717, "loss": 0.1628, "lr": 1.5814210307329665e-05, "epoch": 4.274952919020715, "percentage": 61.07, "elapsed_time": "4:20:17", "remaining_time": "2:45:55"}
{"current_steps": 2275, "total_steps": 3717, "loss": 0.1691, "lr": 1.572241769155897e-05, "epoch": 4.284369114877589, "percentage": 61.21, "elapsed_time": "4:20:49", "remaining_time": "2:45:19"}
{"current_steps": 2280, "total_steps": 3717, "loss": 0.1524, "lr": 1.5630719404757057e-05, "epoch": 4.293785310734464, "percentage": 61.34, "elapsed_time": "4:21:24", "remaining_time": "2:44:45"}
{"current_steps": 2285, "total_steps": 3717, "loss": 0.156, "lr": 1.5539117469048602e-05, "epoch": 4.303201506591337, "percentage": 61.47, "elapsed_time": "4:21:58", "remaining_time": "2:44:10"}
{"current_steps": 2290, "total_steps": 3717, "loss": 0.1681, "lr": 1.544761390443361e-05, "epoch": 4.312617702448211, "percentage": 61.61, "elapsed_time": "4:22:33", "remaining_time": "2:43:36"}
{"current_steps": 2295, "total_steps": 3717, "loss": 0.1666, "lr": 1.535621072874275e-05, "epoch": 4.322033898305085, "percentage": 61.74, "elapsed_time": "4:23:07", "remaining_time": "2:43:02"}
{"current_steps": 2300, "total_steps": 3717, "loss": 0.1524, "lr": 1.526490995759296e-05, "epoch": 4.3314500941619585, "percentage": 61.88, "elapsed_time": "4:23:41", "remaining_time": "2:42:27"}
{"current_steps": 2305, "total_steps": 3717, "loss": 0.1629, "lr": 1.5173713604342943e-05, "epoch": 4.340866290018832, "percentage": 62.01, "elapsed_time": "4:24:16", "remaining_time": "2:41:53"}
{"current_steps": 2310, "total_steps": 3717, "loss": 0.1699, "lr": 1.5082623680048797e-05, "epoch": 4.350282485875706, "percentage": 62.15, "elapsed_time": "4:24:47", "remaining_time": "2:41:17"}
{"current_steps": 2315, "total_steps": 3717, "loss": 0.1487, "lr": 1.4991642193419647e-05, "epoch": 4.35969868173258, "percentage": 62.28, "elapsed_time": "4:25:23", "remaining_time": "2:40:43"}
{"current_steps": 2320, "total_steps": 3717, "loss": 0.1658, "lr": 1.4900771150773352e-05, "epoch": 4.369114877589454, "percentage": 62.42, "elapsed_time": "4:25:56", "remaining_time": "2:40:08"}
{"current_steps": 2325, "total_steps": 3717, "loss": 0.1647, "lr": 1.4810012555992288e-05, "epoch": 4.378531073446328, "percentage": 62.55, "elapsed_time": "4:26:32", "remaining_time": "2:39:35"}
{"current_steps": 2330, "total_steps": 3717, "loss": 0.1831, "lr": 1.4719368410479118e-05, "epoch": 4.387947269303202, "percentage": 62.68, "elapsed_time": "4:27:05", "remaining_time": "2:38:59"}
{"current_steps": 2335, "total_steps": 3717, "loss": 0.1563, "lr": 1.462884071311268e-05, "epoch": 4.397363465160075, "percentage": 62.82, "elapsed_time": "4:27:39", "remaining_time": "2:38:24"}
{"current_steps": 2340, "total_steps": 3717, "loss": 0.153, "lr": 1.4538431460203914e-05, "epoch": 4.406779661016949, "percentage": 62.95, "elapsed_time": "4:28:14", "remaining_time": "2:37:51"}
{"current_steps": 2345, "total_steps": 3717, "loss": 0.1556, "lr": 1.4448142645451836e-05, "epoch": 4.416195856873823, "percentage": 63.09, "elapsed_time": "4:28:45", "remaining_time": "2:37:14"}
{"current_steps": 2350, "total_steps": 3717, "loss": 0.1592, "lr": 1.4357976259899537e-05, "epoch": 4.425612052730697, "percentage": 63.22, "elapsed_time": "4:29:18", "remaining_time": "2:36:39"}
{"current_steps": 2355, "total_steps": 3717, "loss": 0.1762, "lr": 1.4267934291890338e-05, "epoch": 4.435028248587571, "percentage": 63.36, "elapsed_time": "4:29:51", "remaining_time": "2:36:04"}
{"current_steps": 2360, "total_steps": 3717, "loss": 0.1549, "lr": 1.4178018727023901e-05, "epoch": 4.444444444444445, "percentage": 63.49, "elapsed_time": "4:30:25", "remaining_time": "2:35:29"}
{"current_steps": 2365, "total_steps": 3717, "loss": 0.1619, "lr": 1.4088231548112457e-05, "epoch": 4.453860640301318, "percentage": 63.63, "elapsed_time": "4:30:58", "remaining_time": "2:34:54"}
{"current_steps": 2370, "total_steps": 3717, "loss": 0.1773, "lr": 1.3998574735137066e-05, "epoch": 4.463276836158192, "percentage": 63.76, "elapsed_time": "4:31:33", "remaining_time": "2:34:20"}
{"current_steps": 2375, "total_steps": 3717, "loss": 0.1622, "lr": 1.3909050265203992e-05, "epoch": 4.472693032015066, "percentage": 63.9, "elapsed_time": "4:32:08", "remaining_time": "2:33:46"}
{"current_steps": 2380, "total_steps": 3717, "loss": 0.1525, "lr": 1.3819660112501054e-05, "epoch": 4.482109227871939, "percentage": 64.03, "elapsed_time": "4:32:42", "remaining_time": "2:33:11"}
{"current_steps": 2385, "total_steps": 3717, "loss": 0.1884, "lr": 1.3730406248254133e-05, "epoch": 4.491525423728813, "percentage": 64.16, "elapsed_time": "4:33:15", "remaining_time": "2:32:36"}
{"current_steps": 2390, "total_steps": 3717, "loss": 0.1624, "lr": 1.364129064068366e-05, "epoch": 4.500941619585688, "percentage": 64.3, "elapsed_time": "4:33:52", "remaining_time": "2:32:03"}
{"current_steps": 2395, "total_steps": 3717, "loss": 0.1598, "lr": 1.3552315254961281e-05, "epoch": 4.510357815442561, "percentage": 64.43, "elapsed_time": "4:34:26", "remaining_time": "2:31:29"}
{"current_steps": 2400, "total_steps": 3717, "loss": 0.1703, "lr": 1.3463482053166442e-05, "epoch": 4.519774011299435, "percentage": 64.57, "elapsed_time": "4:35:01", "remaining_time": "2:30:55"}
{"current_steps": 2405, "total_steps": 3717, "loss": 0.1485, "lr": 1.3374792994243165e-05, "epoch": 4.529190207156309, "percentage": 64.7, "elapsed_time": "4:35:36", "remaining_time": "2:30:20"}
{"current_steps": 2410, "total_steps": 3717, "loss": 0.1518, "lr": 1.3286250033956868e-05, "epoch": 4.5386064030131825, "percentage": 64.84, "elapsed_time": "4:36:10", "remaining_time": "2:29:46"}
{"current_steps": 2415, "total_steps": 3717, "loss": 0.1622, "lr": 1.319785512485118e-05, "epoch": 4.548022598870056, "percentage": 64.97, "elapsed_time": "4:36:41", "remaining_time": "2:29:10"}
{"current_steps": 2420, "total_steps": 3717, "loss": 0.1586, "lr": 1.3109610216204924e-05, "epoch": 4.557438794726931, "percentage": 65.11, "elapsed_time": "4:37:17", "remaining_time": "2:28:36"}
{"current_steps": 2425, "total_steps": 3717, "loss": 0.1554, "lr": 1.3021517253989135e-05, "epoch": 4.5668549905838045, "percentage": 65.24, "elapsed_time": "4:37:53", "remaining_time": "2:28:03"}
{"current_steps": 2430, "total_steps": 3717, "loss": 0.1702, "lr": 1.293357818082412e-05, "epoch": 4.576271186440678, "percentage": 65.38, "elapsed_time": "4:38:24", "remaining_time": "2:27:27"}
{"current_steps": 2435, "total_steps": 3717, "loss": 0.1637, "lr": 1.2845794935936646e-05, "epoch": 4.585687382297552, "percentage": 65.51, "elapsed_time": "4:38:58", "remaining_time": "2:26:52"}
{"current_steps": 2440, "total_steps": 3717, "loss": 0.1626, "lr": 1.2758169455117146e-05, "epoch": 4.595103578154426, "percentage": 65.64, "elapsed_time": "4:39:33", "remaining_time": "2:26:18"}
{"current_steps": 2445, "total_steps": 3717, "loss": 0.1728, "lr": 1.2670703670677083e-05, "epoch": 4.604519774011299, "percentage": 65.78, "elapsed_time": "4:40:06", "remaining_time": "2:25:43"}
{"current_steps": 2450, "total_steps": 3717, "loss": 0.1643, "lr": 1.2583399511406275e-05, "epoch": 4.613935969868173, "percentage": 65.91, "elapsed_time": "4:40:38", "remaining_time": "2:25:07"}
{"current_steps": 2455, "total_steps": 3717, "loss": 0.1659, "lr": 1.2496258902530391e-05, "epoch": 4.623352165725047, "percentage": 66.05, "elapsed_time": "4:41:10", "remaining_time": "2:24:32"}
{"current_steps": 2460, "total_steps": 3717, "loss": 0.1735, "lr": 1.2409283765668536e-05, "epoch": 4.632768361581921, "percentage": 66.18, "elapsed_time": "4:41:46", "remaining_time": "2:23:59"}
{"current_steps": 2465, "total_steps": 3717, "loss": 0.1699, "lr": 1.2322476018790794e-05, "epoch": 4.642184557438795, "percentage": 66.32, "elapsed_time": "4:42:20", "remaining_time": "2:23:24"}
{"current_steps": 2470, "total_steps": 3717, "loss": 0.1609, "lr": 1.223583757617599e-05, "epoch": 4.651600753295669, "percentage": 66.45, "elapsed_time": "4:42:58", "remaining_time": "2:22:51"}
{"current_steps": 2475, "total_steps": 3717, "loss": 0.1546, "lr": 1.2149370348369476e-05, "epoch": 4.661016949152542, "percentage": 66.59, "elapsed_time": "4:43:30", "remaining_time": "2:22:15"}
{"current_steps": 2480, "total_steps": 3717, "loss": 0.169, "lr": 1.2063076242140967e-05, "epoch": 4.670433145009416, "percentage": 66.72, "elapsed_time": "4:44:04", "remaining_time": "2:21:41"}
{"current_steps": 2485, "total_steps": 3717, "loss": 0.1574, "lr": 1.1976957160442519e-05, "epoch": 4.67984934086629, "percentage": 66.85, "elapsed_time": "4:44:38", "remaining_time": "2:21:06"}
{"current_steps": 2490, "total_steps": 3717, "loss": 0.1702, "lr": 1.1891015002366559e-05, "epoch": 4.6892655367231635, "percentage": 66.99, "elapsed_time": "4:45:13", "remaining_time": "2:20:32"}
{"current_steps": 2495, "total_steps": 3717, "loss": 0.1668, "lr": 1.1805251663104013e-05, "epoch": 4.698681732580038, "percentage": 67.12, "elapsed_time": "4:45:46", "remaining_time": "2:19:58"}
{"current_steps": 2500, "total_steps": 3717, "loss": 0.186, "lr": 1.1719669033902496e-05, "epoch": 4.708097928436912, "percentage": 67.26, "elapsed_time": "4:46:19", "remaining_time": "2:19:22"}
{"current_steps": 2505, "total_steps": 3717, "loss": 0.1811, "lr": 1.163426900202461e-05, "epoch": 4.7175141242937855, "percentage": 67.39, "elapsed_time": "4:46:52", "remaining_time": "2:18:48"}
{"current_steps": 2510, "total_steps": 3717, "loss": 0.165, "lr": 1.1549053450706356e-05, "epoch": 4.726930320150659, "percentage": 67.53, "elapsed_time": "4:47:24", "remaining_time": "2:18:12"}
{"current_steps": 2515, "total_steps": 3717, "loss": 0.1701, "lr": 1.1464024259115559e-05, "epoch": 4.736346516007533, "percentage": 67.66, "elapsed_time": "4:47:57", "remaining_time": "2:17:37"}
{"current_steps": 2520, "total_steps": 3717, "loss": 0.1672, "lr": 1.137918330231047e-05, "epoch": 4.745762711864407, "percentage": 67.8, "elapsed_time": "4:48:29", "remaining_time": "2:17:02"}
{"current_steps": 2525, "total_steps": 3717, "loss": 0.1728, "lr": 1.1294532451198368e-05, "epoch": 4.75517890772128, "percentage": 67.93, "elapsed_time": "4:49:02", "remaining_time": "2:16:26"}
{"current_steps": 2530, "total_steps": 3717, "loss": 0.1732, "lr": 1.121007357249437e-05, "epoch": 4.764595103578154, "percentage": 68.07, "elapsed_time": "4:49:36", "remaining_time": "2:15:52"}
{"current_steps": 2535, "total_steps": 3717, "loss": 0.162, "lr": 1.1125808528680215e-05, "epoch": 4.7740112994350286, "percentage": 68.2, "elapsed_time": "4:50:11", "remaining_time": "2:15:18"}
{"current_steps": 2540, "total_steps": 3717, "loss": 0.1587, "lr": 1.1041739177963194e-05, "epoch": 4.783427495291902, "percentage": 68.33, "elapsed_time": "4:50:46", "remaining_time": "2:14:44"}
{"current_steps": 2545, "total_steps": 3717, "loss": 0.1573, "lr": 1.0957867374235223e-05, "epoch": 4.792843691148776, "percentage": 68.47, "elapsed_time": "4:51:21", "remaining_time": "2:14:10"}
{"current_steps": 2550, "total_steps": 3717, "loss": 0.1672, "lr": 1.0874194967031875e-05, "epoch": 4.80225988700565, "percentage": 68.6, "elapsed_time": "4:51:54", "remaining_time": "2:13:35"}
{"current_steps": 2555, "total_steps": 3717, "loss": 0.1773, "lr": 1.0790723801491673e-05, "epoch": 4.811676082862523, "percentage": 68.74, "elapsed_time": "4:52:26", "remaining_time": "2:13:00"}
{"current_steps": 2560, "total_steps": 3717, "loss": 0.1694, "lr": 1.0707455718315383e-05, "epoch": 4.821092278719397, "percentage": 68.87, "elapsed_time": "4:53:02", "remaining_time": "2:12:26"}
{"current_steps": 2565, "total_steps": 3717, "loss": 0.1651, "lr": 1.0624392553725386e-05, "epoch": 4.830508474576272, "percentage": 69.01, "elapsed_time": "4:53:32", "remaining_time": "2:11:50"}
{"current_steps": 2570, "total_steps": 3717, "loss": 0.1593, "lr": 1.0541536139425225e-05, "epoch": 4.839924670433145, "percentage": 69.14, "elapsed_time": "4:54:06", "remaining_time": "2:11:15"}
{"current_steps": 2575, "total_steps": 3717, "loss": 0.1592, "lr": 1.0458888302559198e-05, "epoch": 4.849340866290019, "percentage": 69.28, "elapsed_time": "4:54:42", "remaining_time": "2:10:42"}
{"current_steps": 2580, "total_steps": 3717, "loss": 0.1578, "lr": 1.0376450865672063e-05, "epoch": 4.858757062146893, "percentage": 69.41, "elapsed_time": "4:55:15", "remaining_time": "2:10:07"}
{"current_steps": 2585, "total_steps": 3717, "loss": 0.1708, "lr": 1.0294225646668852e-05, "epoch": 4.868173258003766, "percentage": 69.55, "elapsed_time": "4:55:49", "remaining_time": "2:09:32"}
{"current_steps": 2590, "total_steps": 3717, "loss": 0.1529, "lr": 1.0212214458774781e-05, "epoch": 4.87758945386064, "percentage": 69.68, "elapsed_time": "4:56:20", "remaining_time": "2:08:56"}
{"current_steps": 2595, "total_steps": 3717, "loss": 0.1593, "lr": 1.0130419110495286e-05, "epoch": 4.887005649717514, "percentage": 69.81, "elapsed_time": "4:56:53", "remaining_time": "2:08:21"}
{"current_steps": 2600, "total_steps": 3717, "loss": 0.1532, "lr": 1.0048841405576084e-05, "epoch": 4.8964218455743875, "percentage": 69.95, "elapsed_time": "4:57:28", "remaining_time": "2:07:47"}
{"current_steps": 2605, "total_steps": 3717, "loss": 0.1702, "lr": 9.967483142963463e-06, "epoch": 4.905838041431262, "percentage": 70.08, "elapsed_time": "4:58:03", "remaining_time": "2:07:14"}
{"current_steps": 2610, "total_steps": 3717, "loss": 0.1627, "lr": 9.886346116764566e-06, "epoch": 4.915254237288136, "percentage": 70.22, "elapsed_time": "4:58:39", "remaining_time": "2:06:40"}
{"current_steps": 2615, "total_steps": 3717, "loss": 0.1701, "lr": 9.805432116207869e-06, "epoch": 4.9246704331450095, "percentage": 70.35, "elapsed_time": "4:59:12", "remaining_time": "2:06:05"}
{"current_steps": 2620, "total_steps": 3717, "loss": 0.1563, "lr": 9.724742925603681e-06, "epoch": 4.934086629001883, "percentage": 70.49, "elapsed_time": "4:59:48", "remaining_time": "2:05:31"}
{"current_steps": 2625, "total_steps": 3717, "loss": 0.164, "lr": 9.644280324304818e-06, "epoch": 4.943502824858757, "percentage": 70.62, "elapsed_time": "5:00:21", "remaining_time": "2:04:57"}
{"current_steps": 2630, "total_steps": 3717, "loss": 0.1882, "lr": 9.564046086667369e-06, "epoch": 4.952919020715631, "percentage": 70.76, "elapsed_time": "5:00:53", "remaining_time": "2:04:21"}
{"current_steps": 2635, "total_steps": 3717, "loss": 0.1498, "lr": 9.484041982011559e-06, "epoch": 4.962335216572505, "percentage": 70.89, "elapsed_time": "5:01:25", "remaining_time": "2:03:46"}
{"current_steps": 2640, "total_steps": 3717, "loss": 0.1688, "lr": 9.40426977458273e-06, "epoch": 4.971751412429379, "percentage": 71.03, "elapsed_time": "5:01:59", "remaining_time": "2:03:12"}
{"current_steps": 2645, "total_steps": 3717, "loss": 0.1471, "lr": 9.324731223512463e-06, "epoch": 4.981167608286253, "percentage": 71.16, "elapsed_time": "5:02:35", "remaining_time": "2:02:38"}
{"current_steps": 2650, "total_steps": 3717, "loss": 0.1693, "lr": 9.245428082779747e-06, "epoch": 4.990583804143126, "percentage": 71.29, "elapsed_time": "5:03:07", "remaining_time": "2:02:03"}
{"current_steps": 2655, "total_steps": 3717, "loss": 0.1527, "lr": 9.166362101172306e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "5:03:41", "remaining_time": "2:01:28"}
{"current_steps": 2660, "total_steps": 3717, "loss": 0.1672, "lr": 9.087535022248057e-06, "epoch": 5.009416195856874, "percentage": 71.56, "elapsed_time": "5:04:16", "remaining_time": "2:00:54"}
{"current_steps": 2665, "total_steps": 3717, "loss": 0.1487, "lr": 9.008948584296674e-06, "epoch": 5.018832391713747, "percentage": 71.7, "elapsed_time": "5:04:49", "remaining_time": "2:00:19"}
{"current_steps": 2670, "total_steps": 3717, "loss": 0.1558, "lr": 8.930604520301196e-06, "epoch": 5.028248587570621, "percentage": 71.83, "elapsed_time": "5:05:23", "remaining_time": "1:59:45"}
{"current_steps": 2675, "total_steps": 3717, "loss": 0.16, "lr": 8.852504557899866e-06, "epoch": 5.037664783427496, "percentage": 71.97, "elapsed_time": "5:06:00", "remaining_time": "1:59:11"}
{"current_steps": 2680, "total_steps": 3717, "loss": 0.1418, "lr": 8.774650419348007e-06, "epoch": 5.047080979284369, "percentage": 72.1, "elapsed_time": "5:06:33", "remaining_time": "1:58:37"}
{"current_steps": 2685, "total_steps": 3717, "loss": 0.1581, "lr": 8.69704382148006e-06, "epoch": 5.056497175141243, "percentage": 72.24, "elapsed_time": "5:07:05", "remaining_time": "1:58:01"}
{"current_steps": 2690, "total_steps": 3717, "loss": 0.1426, "lr": 8.619686475671702e-06, "epoch": 5.065913370998117, "percentage": 72.37, "elapsed_time": "5:07:38", "remaining_time": "1:57:27"}
{"current_steps": 2695, "total_steps": 3717, "loss": 0.1573, "lr": 8.542580087802126e-06, "epoch": 5.0753295668549905, "percentage": 72.5, "elapsed_time": "5:08:11", "remaining_time": "1:56:52"}
{"current_steps": 2700, "total_steps": 3717, "loss": 0.1464, "lr": 8.46572635821643e-06, "epoch": 5.084745762711864, "percentage": 72.64, "elapsed_time": "5:08:45", "remaining_time": "1:56:17"}
{"current_steps": 2705, "total_steps": 3717, "loss": 0.1424, "lr": 8.38912698168808e-06, "epoch": 5.094161958568738, "percentage": 72.77, "elapsed_time": "5:09:19", "remaining_time": "1:55:43"}
{"current_steps": 2710, "total_steps": 3717, "loss": 0.1476, "lr": 8.312783647381579e-06, "epoch": 5.1035781544256125, "percentage": 72.91, "elapsed_time": "5:09:50", "remaining_time": "1:55:07"}
{"current_steps": 2715, "total_steps": 3717, "loss": 0.1584, "lr": 8.236698038815213e-06, "epoch": 5.112994350282486, "percentage": 73.04, "elapsed_time": "5:10:25", "remaining_time": "1:54:33"}
{"current_steps": 2720, "total_steps": 3717, "loss": 0.1568, "lr": 8.16087183382391e-06, "epoch": 5.12241054613936, "percentage": 73.18, "elapsed_time": "5:10:59", "remaining_time": "1:53:59"}
{"current_steps": 2725, "total_steps": 3717, "loss": 0.1519, "lr": 8.085306704522236e-06, "epoch": 5.131826741996234, "percentage": 73.31, "elapsed_time": "5:11:32", "remaining_time": "1:53:24"}
{"current_steps": 2730, "total_steps": 3717, "loss": 0.1391, "lr": 8.010004317267543e-06, "epoch": 5.141242937853107, "percentage": 73.45, "elapsed_time": "5:12:04", "remaining_time": "1:52:49"}
{"current_steps": 2735, "total_steps": 3717, "loss": 0.1485, "lr": 7.934966332623218e-06, "epoch": 5.150659133709981, "percentage": 73.58, "elapsed_time": "5:12:40", "remaining_time": "1:52:15"}
{"current_steps": 2740, "total_steps": 3717, "loss": 0.1409, "lr": 7.860194405322043e-06, "epoch": 5.160075329566855, "percentage": 73.72, "elapsed_time": "5:13:12", "remaining_time": "1:51:40"}
{"current_steps": 2745, "total_steps": 3717, "loss": 0.1583, "lr": 7.785690184229725e-06, "epoch": 5.169491525423728, "percentage": 73.85, "elapsed_time": "5:13:45", "remaining_time": "1:51:05"}
{"current_steps": 2750, "total_steps": 3717, "loss": 0.1646, "lr": 7.711455312308553e-06, "epoch": 5.178907721280603, "percentage": 73.98, "elapsed_time": "5:14:15", "remaining_time": "1:50:30"}
{"current_steps": 2755, "total_steps": 3717, "loss": 0.1641, "lr": 7.637491426581125e-06, "epoch": 5.188323917137477, "percentage": 74.12, "elapsed_time": "5:14:49", "remaining_time": "1:49:55"}
{"current_steps": 2760, "total_steps": 3717, "loss": 0.1633, "lr": 7.56380015809425e-06, "epoch": 5.19774011299435, "percentage": 74.25, "elapsed_time": "5:15:17", "remaining_time": "1:49:19"}
{"current_steps": 2765, "total_steps": 3717, "loss": 0.1343, "lr": 7.490383131883043e-06, "epoch": 5.207156308851224, "percentage": 74.39, "elapsed_time": "5:15:53", "remaining_time": "1:48:45"}
{"current_steps": 2770, "total_steps": 3717, "loss": 0.1439, "lr": 7.417241966935018e-06, "epoch": 5.216572504708098, "percentage": 74.52, "elapsed_time": "5:16:27", "remaining_time": "1:48:11"}
{"current_steps": 2775, "total_steps": 3717, "loss": 0.1445, "lr": 7.344378276154418e-06, "epoch": 5.2259887005649714, "percentage": 74.66, "elapsed_time": "5:16:59", "remaining_time": "1:47:36"}
{"current_steps": 2780, "total_steps": 3717, "loss": 0.1648, "lr": 7.271793666326646e-06, "epoch": 5.235404896421845, "percentage": 74.79, "elapsed_time": "5:17:35", "remaining_time": "1:47:02"}
{"current_steps": 2785, "total_steps": 3717, "loss": 0.1414, "lr": 7.19948973808283e-06, "epoch": 5.24482109227872, "percentage": 74.93, "elapsed_time": "5:18:10", "remaining_time": "1:46:28"}
{"current_steps": 2790, "total_steps": 3717, "loss": 0.1649, "lr": 7.1274680858645285e-06, "epoch": 5.254237288135593, "percentage": 75.06, "elapsed_time": "5:18:42", "remaining_time": "1:45:53"}
{"current_steps": 2795, "total_steps": 3717, "loss": 0.1667, "lr": 7.055730297888555e-06, "epoch": 5.263653483992467, "percentage": 75.2, "elapsed_time": "5:19:17", "remaining_time": "1:45:19"}
{"current_steps": 2800, "total_steps": 3717, "loss": 0.1352, "lr": 6.984277956111989e-06, "epoch": 5.273069679849341, "percentage": 75.33, "elapsed_time": "5:19:53", "remaining_time": "1:44:45"}
{"current_steps": 2805, "total_steps": 3717, "loss": 0.141, "lr": 6.913112636197257e-06, "epoch": 5.2824858757062145, "percentage": 75.46, "elapsed_time": "5:20:28", "remaining_time": "1:44:11"}
{"current_steps": 2810, "total_steps": 3717, "loss": 0.1501, "lr": 6.842235907477377e-06, "epoch": 5.291902071563088, "percentage": 75.6, "elapsed_time": "5:21:03", "remaining_time": "1:43:37"}
{"current_steps": 2815, "total_steps": 3717, "loss": 0.142, "lr": 6.771649332921415e-06, "epoch": 5.301318267419962, "percentage": 75.73, "elapsed_time": "5:21:36", "remaining_time": "1:43:03"}
{"current_steps": 2820, "total_steps": 3717, "loss": 0.1425, "lr": 6.7013544690999455e-06, "epoch": 5.3107344632768365, "percentage": 75.87, "elapsed_time": "5:22:07", "remaining_time": "1:42:27"}
{"current_steps": 2825, "total_steps": 3717, "loss": 0.1493, "lr": 6.631352866150764e-06, "epoch": 5.32015065913371, "percentage": 76.0, "elapsed_time": "5:22:41", "remaining_time": "1:41:53"}
{"current_steps": 2830, "total_steps": 3717, "loss": 0.163, "lr": 6.5616460677447e-06, "epoch": 5.329566854990584, "percentage": 76.14, "elapsed_time": "5:23:15", "remaining_time": "1:41:19"}
{"current_steps": 2835, "total_steps": 3717, "loss": 0.1515, "lr": 6.492235611051567e-06, "epoch": 5.338983050847458, "percentage": 76.27, "elapsed_time": "5:23:52", "remaining_time": "1:40:45"}
{"current_steps": 2840, "total_steps": 3717, "loss": 0.1499, "lr": 6.423123026706273e-06, "epoch": 5.348399246704331, "percentage": 76.41, "elapsed_time": "5:24:24", "remaining_time": "1:40:10"}
{"current_steps": 2845, "total_steps": 3717, "loss": 0.1685, "lr": 6.354309838775061e-06, "epoch": 5.357815442561205, "percentage": 76.54, "elapsed_time": "5:24:57", "remaining_time": "1:39:36"}
{"current_steps": 2850, "total_steps": 3717, "loss": 0.1501, "lr": 6.285797564721916e-06, "epoch": 5.367231638418079, "percentage": 76.67, "elapsed_time": "5:25:27", "remaining_time": "1:39:00"}
{"current_steps": 2855, "total_steps": 3717, "loss": 0.1503, "lr": 6.217587715375073e-06, "epoch": 5.376647834274953, "percentage": 76.81, "elapsed_time": "5:26:00", "remaining_time": "1:38:25"}
{"current_steps": 2860, "total_steps": 3717, "loss": 0.1471, "lr": 6.149681794893734e-06, "epoch": 5.386064030131827, "percentage": 76.94, "elapsed_time": "5:26:33", "remaining_time": "1:37:51"}
{"current_steps": 2865, "total_steps": 3717, "loss": 0.1739, "lr": 6.08208130073485e-06, "epoch": 5.395480225988701, "percentage": 77.08, "elapsed_time": "5:27:01", "remaining_time": "1:37:15"}
{"current_steps": 2870, "total_steps": 3717, "loss": 0.1629, "lr": 6.014787723620172e-06, "epoch": 5.404896421845574, "percentage": 77.21, "elapsed_time": "5:27:34", "remaining_time": "1:36:40"}
{"current_steps": 2875, "total_steps": 3717, "loss": 0.1374, "lr": 5.94780254750331e-06, "epoch": 5.414312617702448, "percentage": 77.35, "elapsed_time": "5:28:09", "remaining_time": "1:36:06"}
{"current_steps": 2880, "total_steps": 3717, "loss": 0.1618, "lr": 5.88112724953704e-06, "epoch": 5.423728813559322, "percentage": 77.48, "elapsed_time": "5:28:40", "remaining_time": "1:35:31"}
{"current_steps": 2885, "total_steps": 3717, "loss": 0.1515, "lr": 5.814763300040726e-06, "epoch": 5.4331450094161955, "percentage": 77.62, "elapsed_time": "5:29:14", "remaining_time": "1:34:57"}
{"current_steps": 2890, "total_steps": 3717, "loss": 0.1469, "lr": 5.7487121624678955e-06, "epoch": 5.44256120527307, "percentage": 77.75, "elapsed_time": "5:29:47", "remaining_time": "1:34:22"}
{"current_steps": 2895, "total_steps": 3717, "loss": 0.1418, "lr": 5.682975293373965e-06, "epoch": 5.451977401129944, "percentage": 77.89, "elapsed_time": "5:30:21", "remaining_time": "1:33:48"}
{"current_steps": 2900, "total_steps": 3717, "loss": 0.1513, "lr": 5.617554142384134e-06, "epoch": 5.4613935969868175, "percentage": 78.02, "elapsed_time": "5:30:56", "remaining_time": "1:33:13"}
{"current_steps": 2905, "total_steps": 3717, "loss": 0.1558, "lr": 5.552450152161397e-06, "epoch": 5.470809792843691, "percentage": 78.15, "elapsed_time": "5:31:30", "remaining_time": "1:32:39"}
{"current_steps": 2910, "total_steps": 3717, "loss": 0.1418, "lr": 5.487664758374742e-06, "epoch": 5.480225988700565, "percentage": 78.29, "elapsed_time": "5:32:03", "remaining_time": "1:32:05"}
{"current_steps": 2915, "total_steps": 3717, "loss": 0.1421, "lr": 5.423199389667475e-06, "epoch": 5.489642184557439, "percentage": 78.42, "elapsed_time": "5:32:37", "remaining_time": "1:31:30"}
{"current_steps": 2920, "total_steps": 3717, "loss": 0.1399, "lr": 5.359055467625758e-06, "epoch": 5.499058380414312, "percentage": 78.56, "elapsed_time": "5:33:10", "remaining_time": "1:30:56"}
{"current_steps": 2925, "total_steps": 3717, "loss": 0.1459, "lr": 5.295234406747212e-06, "epoch": 5.508474576271187, "percentage": 78.69, "elapsed_time": "5:33:46", "remaining_time": "1:30:22"}
{"current_steps": 2930, "total_steps": 3717, "loss": 0.1566, "lr": 5.231737614409742e-06, "epoch": 5.517890772128061, "percentage": 78.83, "elapsed_time": "5:34:17", "remaining_time": "1:29:47"}
{"current_steps": 2935, "total_steps": 3717, "loss": 0.1546, "lr": 5.168566490840532e-06, "epoch": 5.527306967984934, "percentage": 78.96, "elapsed_time": "5:34:48", "remaining_time": "1:29:12"}
{"current_steps": 2940, "total_steps": 3717, "loss": 0.145, "lr": 5.105722429085098e-06, "epoch": 5.536723163841808, "percentage": 79.1, "elapsed_time": "5:35:22", "remaining_time": "1:28:37"}
{"current_steps": 2945, "total_steps": 3717, "loss": 0.1485, "lr": 5.043206814976638e-06, "epoch": 5.546139359698682, "percentage": 79.23, "elapsed_time": "5:35:53", "remaining_time": "1:28:02"}
{"current_steps": 2950, "total_steps": 3717, "loss": 0.1549, "lr": 4.981021027105431e-06, "epoch": 5.555555555555555, "percentage": 79.37, "elapsed_time": "5:36:28", "remaining_time": "1:27:28"}
{"current_steps": 2955, "total_steps": 3717, "loss": 0.1549, "lr": 4.919166436788465e-06, "epoch": 5.564971751412429, "percentage": 79.5, "elapsed_time": "5:37:00", "remaining_time": "1:26:54"}
{"current_steps": 2960, "total_steps": 3717, "loss": 0.1559, "lr": 4.857644408039166e-06, "epoch": 5.574387947269303, "percentage": 79.63, "elapsed_time": "5:37:32", "remaining_time": "1:26:19"}
{"current_steps": 2965, "total_steps": 3717, "loss": 0.1438, "lr": 4.796456297537337e-06, "epoch": 5.583804143126177, "percentage": 79.77, "elapsed_time": "5:38:02", "remaining_time": "1:25:44"}
{"current_steps": 2970, "total_steps": 3717, "loss": 0.1562, "lr": 4.735603454599243e-06, "epoch": 5.593220338983051, "percentage": 79.9, "elapsed_time": "5:38:34", "remaining_time": "1:25:09"}
{"current_steps": 2975, "total_steps": 3717, "loss": 0.1388, "lr": 4.675087221147838e-06, "epoch": 5.602636534839925, "percentage": 80.04, "elapsed_time": "5:39:09", "remaining_time": "1:24:35"}
{"current_steps": 2980, "total_steps": 3717, "loss": 0.1553, "lr": 4.614908931683193e-06, "epoch": 5.612052730696798, "percentage": 80.17, "elapsed_time": "5:39:41", "remaining_time": "1:24:00"}
{"current_steps": 2985, "total_steps": 3717, "loss": 0.1604, "lr": 4.555069913253076e-06, "epoch": 5.621468926553672, "percentage": 80.31, "elapsed_time": "5:40:12", "remaining_time": "1:23:25"}
{"current_steps": 2990, "total_steps": 3717, "loss": 0.1518, "lr": 4.495571485423642e-06, "epoch": 5.630885122410546, "percentage": 80.44, "elapsed_time": "5:40:46", "remaining_time": "1:22:51"}
{"current_steps": 2995, "total_steps": 3717, "loss": 0.1494, "lr": 4.436414960250379e-06, "epoch": 5.64030131826742, "percentage": 80.58, "elapsed_time": "5:41:22", "remaining_time": "1:22:17"}
{"current_steps": 3000, "total_steps": 3717, "loss": 0.1506, "lr": 4.377601642249158e-06, "epoch": 5.649717514124294, "percentage": 80.71, "elapsed_time": "5:41:57", "remaining_time": "1:21:43"}
{"current_steps": 3005, "total_steps": 3717, "loss": 0.1425, "lr": 4.319132828367478e-06, "epoch": 5.659133709981168, "percentage": 80.84, "elapsed_time": "5:42:43", "remaining_time": "1:21:12"}
{"current_steps": 3010, "total_steps": 3717, "loss": 0.1493, "lr": 4.261009807955843e-06, "epoch": 5.6685499058380415, "percentage": 80.98, "elapsed_time": "5:43:18", "remaining_time": "1:20:38"}
{"current_steps": 3015, "total_steps": 3717, "loss": 0.138, "lr": 4.203233862739342e-06, "epoch": 5.677966101694915, "percentage": 81.11, "elapsed_time": "5:43:51", "remaining_time": "1:20:03"}
{"current_steps": 3020, "total_steps": 3717, "loss": 0.1586, "lr": 4.145806266789387e-06, "epoch": 5.687382297551789, "percentage": 81.25, "elapsed_time": "5:44:26", "remaining_time": "1:19:29"}
{"current_steps": 3025, "total_steps": 3717, "loss": 0.1466, "lr": 4.088728286495618e-06, "epoch": 5.696798493408663, "percentage": 81.38, "elapsed_time": "5:45:00", "remaining_time": "1:18:55"}
{"current_steps": 3030, "total_steps": 3717, "loss": 0.1497, "lr": 4.032001180537965e-06, "epoch": 5.706214689265536, "percentage": 81.52, "elapsed_time": "5:45:28", "remaining_time": "1:18:19"}
{"current_steps": 3035, "total_steps": 3717, "loss": 0.1462, "lr": 3.97562619985891e-06, "epoch": 5.715630885122411, "percentage": 81.65, "elapsed_time": "5:46:04", "remaining_time": "1:17:45"}
{"current_steps": 3040, "total_steps": 3717, "loss": 0.1487, "lr": 3.919604587635883e-06, "epoch": 5.725047080979285, "percentage": 81.79, "elapsed_time": "5:46:37", "remaining_time": "1:17:11"}
{"current_steps": 3045, "total_steps": 3717, "loss": 0.1383, "lr": 3.863937579253858e-06, "epoch": 5.734463276836158, "percentage": 81.92, "elapsed_time": "5:47:12", "remaining_time": "1:16:37"}
{"current_steps": 3050, "total_steps": 3717, "loss": 0.151, "lr": 3.8086264022781018e-06, "epoch": 5.743879472693032, "percentage": 82.06, "elapsed_time": "5:47:45", "remaining_time": "1:16:03"}
{"current_steps": 3055, "total_steps": 3717, "loss": 0.1396, "lr": 3.7536722764271295e-06, "epoch": 5.753295668549906, "percentage": 82.19, "elapsed_time": "5:48:20", "remaining_time": "1:15:29"}
{"current_steps": 3060, "total_steps": 3717, "loss": 0.1445, "lr": 3.69907641354577e-06, "epoch": 5.762711864406779, "percentage": 82.32, "elapsed_time": "5:48:54", "remaining_time": "1:14:54"}
{"current_steps": 3065, "total_steps": 3717, "loss": 0.1514, "lr": 3.6448400175784617e-06, "epoch": 5.772128060263653, "percentage": 82.46, "elapsed_time": "5:49:28", "remaining_time": "1:14:20"}
{"current_steps": 3070, "total_steps": 3717, "loss": 0.1602, "lr": 3.5909642845427085e-06, "epoch": 5.781544256120528, "percentage": 82.59, "elapsed_time": "5:49:59", "remaining_time": "1:13:45"}
{"current_steps": 3075, "total_steps": 3717, "loss": 0.1527, "lr": 3.5374504025026957e-06, "epoch": 5.790960451977401, "percentage": 82.73, "elapsed_time": "5:50:31", "remaining_time": "1:13:10"}
{"current_steps": 3080, "total_steps": 3717, "loss": 0.1581, "lr": 3.4842995515430913e-06, "epoch": 5.800376647834275, "percentage": 82.86, "elapsed_time": "5:51:04", "remaining_time": "1:12:36"}
{"current_steps": 3085, "total_steps": 3717, "loss": 0.1772, "lr": 3.431512903743024e-06, "epoch": 5.809792843691149, "percentage": 83.0, "elapsed_time": "5:51:37", "remaining_time": "1:12:01"}
{"current_steps": 3090, "total_steps": 3717, "loss": 0.1693, "lr": 3.379091623150257e-06, "epoch": 5.8192090395480225, "percentage": 83.13, "elapsed_time": "5:52:11", "remaining_time": "1:11:27"}
{"current_steps": 3095, "total_steps": 3717, "loss": 0.1612, "lr": 3.3270368657554664e-06, "epoch": 5.828625235404896, "percentage": 83.27, "elapsed_time": "5:52:44", "remaining_time": "1:10:53"}
{"current_steps": 3100, "total_steps": 3717, "loss": 0.157, "lr": 3.2753497794668054e-06, "epoch": 5.83804143126177, "percentage": 83.4, "elapsed_time": "5:53:16", "remaining_time": "1:10:18"}
{"current_steps": 3105, "total_steps": 3717, "loss": 0.1503, "lr": 3.224031504084566e-06, "epoch": 5.847457627118644, "percentage": 83.54, "elapsed_time": "5:53:49", "remaining_time": "1:09:44"}
{"current_steps": 3110, "total_steps": 3717, "loss": 0.16, "lr": 3.1730831712760415e-06, "epoch": 5.856873822975518, "percentage": 83.67, "elapsed_time": "5:54:20", "remaining_time": "1:09:09"}
{"current_steps": 3115, "total_steps": 3717, "loss": 0.1418, "lr": 3.122505904550577e-06, "epoch": 5.866290018832392, "percentage": 83.8, "elapsed_time": "5:54:52", "remaining_time": "1:08:34"}
{"current_steps": 3120, "total_steps": 3717, "loss": 0.1513, "lr": 3.072300819234788e-06, "epoch": 5.875706214689266, "percentage": 83.94, "elapsed_time": "5:55:26", "remaining_time": "1:08:00"}
{"current_steps": 3125, "total_steps": 3717, "loss": 0.164, "lr": 3.0224690224479736e-06, "epoch": 5.885122410546139, "percentage": 84.07, "elapsed_time": "5:55:56", "remaining_time": "1:07:25"}
{"current_steps": 3130, "total_steps": 3717, "loss": 0.1581, "lr": 2.973011613077701e-06, "epoch": 5.894538606403013, "percentage": 84.21, "elapsed_time": "5:56:30", "remaining_time": "1:06:51"}
{"current_steps": 3135, "total_steps": 3717, "loss": 0.1458, "lr": 2.9239296817555594e-06, "epoch": 5.903954802259887, "percentage": 84.34, "elapsed_time": "5:57:05", "remaining_time": "1:06:17"}
{"current_steps": 3140, "total_steps": 3717, "loss": 0.1479, "lr": 2.8752243108331445e-06, "epoch": 5.913370998116761, "percentage": 84.48, "elapsed_time": "5:57:41", "remaining_time": "1:05:43"}
{"current_steps": 3145, "total_steps": 3717, "loss": 0.1652, "lr": 2.826896574358133e-06, "epoch": 5.922787193973635, "percentage": 84.61, "elapsed_time": "5:58:15", "remaining_time": "1:05:09"}
{"current_steps": 3150, "total_steps": 3717, "loss": 0.1552, "lr": 2.7789475380506535e-06, "epoch": 5.932203389830509, "percentage": 84.75, "elapsed_time": "5:58:46", "remaining_time": "1:04:34"}
{"current_steps": 3155, "total_steps": 3717, "loss": 0.1492, "lr": 2.73137825927976e-06, "epoch": 5.941619585687382, "percentage": 84.88, "elapsed_time": "5:59:19", "remaining_time": "1:04:00"}
{"current_steps": 3160, "total_steps": 3717, "loss": 0.1659, "lr": 2.6841897870401167e-06, "epoch": 5.951035781544256, "percentage": 85.01, "elapsed_time": "5:59:53", "remaining_time": "1:03:26"}
{"current_steps": 3165, "total_steps": 3717, "loss": 0.1592, "lr": 2.6373831619288616e-06, "epoch": 5.96045197740113, "percentage": 85.15, "elapsed_time": "6:00:27", "remaining_time": "1:02:51"}
{"current_steps": 3170, "total_steps": 3717, "loss": 0.1587, "lr": 2.5909594161226716e-06, "epoch": 5.9698681732580035, "percentage": 85.28, "elapsed_time": "6:01:02", "remaining_time": "1:02:18"}
{"current_steps": 3175, "total_steps": 3717, "loss": 0.1544, "lr": 2.544919573354987e-06, "epoch": 5.979284369114877, "percentage": 85.42, "elapsed_time": "6:01:38", "remaining_time": "1:01:44"}
{"current_steps": 3180, "total_steps": 3717, "loss": 0.1534, "lr": 2.499264648893449e-06, "epoch": 5.988700564971752, "percentage": 85.55, "elapsed_time": "6:02:09", "remaining_time": "1:01:09"}
{"current_steps": 3185, "total_steps": 3717, "loss": 0.1567, "lr": 2.4539956495174998e-06, "epoch": 5.998116760828625, "percentage": 85.69, "elapsed_time": "6:02:38", "remaining_time": "1:00:34"}
{"current_steps": 3190, "total_steps": 3717, "loss": 0.1458, "lr": 2.4091135734961978e-06, "epoch": 6.007532956685499, "percentage": 85.82, "elapsed_time": "6:03:13", "remaining_time": "1:00:00"}
{"current_steps": 3195, "total_steps": 3717, "loss": 0.1438, "lr": 2.3646194105661823e-06, "epoch": 6.016949152542373, "percentage": 85.96, "elapsed_time": "6:03:47", "remaining_time": "0:59:26"}
{"current_steps": 3200, "total_steps": 3717, "loss": 0.1406, "lr": 2.320514141909853e-06, "epoch": 6.0263653483992465, "percentage": 86.09, "elapsed_time": "6:04:22", "remaining_time": "0:58:52"}
{"current_steps": 3205, "total_steps": 3717, "loss": 0.1362, "lr": 2.2767987401337453e-06, "epoch": 6.03578154425612, "percentage": 86.23, "elapsed_time": "6:04:57", "remaining_time": "0:58:18"}
{"current_steps": 3210, "total_steps": 3717, "loss": 0.1516, "lr": 2.2334741692470872e-06, "epoch": 6.045197740112994, "percentage": 86.36, "elapsed_time": "6:05:31", "remaining_time": "0:57:43"}
{"current_steps": 3215, "total_steps": 3717, "loss": 0.166, "lr": 2.1905413846405075e-06, "epoch": 6.0546139359698685, "percentage": 86.49, "elapsed_time": "6:06:05", "remaining_time": "0:57:09"}
{"current_steps": 3220, "total_steps": 3717, "loss": 0.1482, "lr": 2.148001333065006e-06, "epoch": 6.064030131826742, "percentage": 86.63, "elapsed_time": "6:06:40", "remaining_time": "0:56:35"}
{"current_steps": 3225, "total_steps": 3717, "loss": 0.1647, "lr": 2.1058549526110463e-06, "epoch": 6.073446327683616, "percentage": 86.76, "elapsed_time": "6:07:13", "remaining_time": "0:56:01"}
{"current_steps": 3230, "total_steps": 3717, "loss": 0.1314, "lr": 2.0641031726878923e-06, "epoch": 6.08286252354049, "percentage": 86.9, "elapsed_time": "6:07:47", "remaining_time": "0:55:27"}
{"current_steps": 3235, "total_steps": 3717, "loss": 0.1324, "lr": 2.0227469140030907e-06, "epoch": 6.092278719397363, "percentage": 87.03, "elapsed_time": "6:08:21", "remaining_time": "0:54:53"}
{"current_steps": 3240, "total_steps": 3717, "loss": 0.1367, "lr": 1.9817870885421976e-06, "epoch": 6.101694915254237, "percentage": 87.17, "elapsed_time": "6:08:54", "remaining_time": "0:54:18"}
{"current_steps": 3245, "total_steps": 3717, "loss": 0.1485, "lr": 1.941224599548637e-06, "epoch": 6.111111111111111, "percentage": 87.3, "elapsed_time": "6:09:27", "remaining_time": "0:53:44"}
{"current_steps": 3250, "total_steps": 3717, "loss": 0.1434, "lr": 1.9010603415037886e-06, "epoch": 6.120527306967985, "percentage": 87.44, "elapsed_time": "6:09:59", "remaining_time": "0:53:09"}
{"current_steps": 3255, "total_steps": 3717, "loss": 0.1584, "lr": 1.861295200107276e-06, "epoch": 6.129943502824859, "percentage": 87.57, "elapsed_time": "6:10:31", "remaining_time": "0:52:35"}
{"current_steps": 3260, "total_steps": 3717, "loss": 0.1428, "lr": 1.821930052257439e-06, "epoch": 6.139359698681733, "percentage": 87.71, "elapsed_time": "6:11:02", "remaining_time": "0:52:00"}
{"current_steps": 3265, "total_steps": 3717, "loss": 0.1505, "lr": 1.78296576603197e-06, "epoch": 6.148775894538606, "percentage": 87.84, "elapsed_time": "6:11:35", "remaining_time": "0:51:26"}
{"current_steps": 3270, "total_steps": 3717, "loss": 0.1564, "lr": 1.7444032006687894e-06, "epoch": 6.15819209039548, "percentage": 87.97, "elapsed_time": "6:12:06", "remaining_time": "0:50:51"}
{"current_steps": 3275, "total_steps": 3717, "loss": 0.1505, "lr": 1.7062432065471025e-06, "epoch": 6.167608286252354, "percentage": 88.11, "elapsed_time": "6:12:38", "remaining_time": "0:50:17"}
{"current_steps": 3280, "total_steps": 3717, "loss": 0.1637, "lr": 1.6684866251686327e-06, "epoch": 6.1770244821092275, "percentage": 88.24, "elapsed_time": "6:13:11", "remaining_time": "0:49:43"}
{"current_steps": 3285, "total_steps": 3717, "loss": 0.1446, "lr": 1.6311342891390736e-06, "epoch": 6.186440677966102, "percentage": 88.38, "elapsed_time": "6:13:42", "remaining_time": "0:49:08"}
{"current_steps": 3290, "total_steps": 3717, "loss": 0.1483, "lr": 1.5941870221497246e-06, "epoch": 6.195856873822976, "percentage": 88.51, "elapsed_time": "6:14:15", "remaining_time": "0:48:34"}
{"current_steps": 3295, "total_steps": 3717, "loss": 0.1373, "lr": 1.5576456389593352e-06, "epoch": 6.2052730696798495, "percentage": 88.65, "elapsed_time": "6:14:50", "remaining_time": "0:48:00"}
{"current_steps": 3300, "total_steps": 3717, "loss": 0.1486, "lr": 1.5215109453761323e-06, "epoch": 6.214689265536723, "percentage": 88.78, "elapsed_time": "6:15:22", "remaining_time": "0:47:25"}
{"current_steps": 3305, "total_steps": 3717, "loss": 0.1574, "lr": 1.4857837382400274e-06, "epoch": 6.224105461393597, "percentage": 88.92, "elapsed_time": "6:15:55", "remaining_time": "0:46:51"}
{"current_steps": 3310, "total_steps": 3717, "loss": 0.1306, "lr": 1.4504648054051008e-06, "epoch": 6.233521657250471, "percentage": 89.05, "elapsed_time": "6:16:28", "remaining_time": "0:46:17"}
{"current_steps": 3315, "total_steps": 3717, "loss": 0.1669, "lr": 1.4155549257221734e-06, "epoch": 6.242937853107344, "percentage": 89.18, "elapsed_time": "6:17:02", "remaining_time": "0:45:43"}
{"current_steps": 3320, "total_steps": 3717, "loss": 0.1437, "lr": 1.3810548690216564e-06, "epoch": 6.252354048964219, "percentage": 89.32, "elapsed_time": "6:17:36", "remaining_time": "0:45:09"}
{"current_steps": 3325, "total_steps": 3717, "loss": 0.1545, "lr": 1.346965396096571e-06, "epoch": 6.261770244821093, "percentage": 89.45, "elapsed_time": "6:18:07", "remaining_time": "0:44:34"}
{"current_steps": 3330, "total_steps": 3717, "loss": 0.1631, "lr": 1.3132872586857737e-06, "epoch": 6.271186440677966, "percentage": 89.59, "elapsed_time": "6:18:35", "remaining_time": "0:43:59"}
{"current_steps": 3335, "total_steps": 3717, "loss": 0.1433, "lr": 1.2800211994573753e-06, "epoch": 6.28060263653484, "percentage": 89.72, "elapsed_time": "6:19:08", "remaining_time": "0:43:25"}
{"current_steps": 3340, "total_steps": 3717, "loss": 0.1498, "lr": 1.2471679519923607e-06, "epoch": 6.290018832391714, "percentage": 89.86, "elapsed_time": "6:19:41", "remaining_time": "0:42:51"}
{"current_steps": 3345, "total_steps": 3717, "loss": 0.1526, "lr": 1.214728240768428e-06, "epoch": 6.299435028248587, "percentage": 89.99, "elapsed_time": "6:20:11", "remaining_time": "0:42:16"}
{"current_steps": 3350, "total_steps": 3717, "loss": 0.1522, "lr": 1.1827027811439962e-06, "epoch": 6.308851224105461, "percentage": 90.13, "elapsed_time": "6:20:42", "remaining_time": "0:41:42"}
{"current_steps": 3355, "total_steps": 3717, "loss": 0.1429, "lr": 1.1510922793424206e-06, "epoch": 6.318267419962336, "percentage": 90.26, "elapsed_time": "6:21:14", "remaining_time": "0:41:08"}
{"current_steps": 3360, "total_steps": 3717, "loss": 0.1417, "lr": 1.1198974324364541e-06, "epoch": 6.327683615819209, "percentage": 90.4, "elapsed_time": "6:21:47", "remaining_time": "0:40:33"}
{"current_steps": 3365, "total_steps": 3717, "loss": 0.138, "lr": 1.089118928332844e-06, "epoch": 6.337099811676083, "percentage": 90.53, "elapsed_time": "6:22:18", "remaining_time": "0:39:59"}
{"current_steps": 3370, "total_steps": 3717, "loss": 0.1508, "lr": 1.0587574457571704e-06, "epoch": 6.346516007532957, "percentage": 90.66, "elapsed_time": "6:22:52", "remaining_time": "0:39:25"}
{"current_steps": 3375, "total_steps": 3717, "loss": 0.1485, "lr": 1.028813654238896e-06, "epoch": 6.3559322033898304, "percentage": 90.8, "elapsed_time": "6:23:26", "remaining_time": "0:38:51"}
{"current_steps": 3380, "total_steps": 3717, "loss": 0.1487, "lr": 9.9928821409657e-07, "epoch": 6.365348399246704, "percentage": 90.93, "elapsed_time": "6:24:00", "remaining_time": "0:38:17"}
{"current_steps": 3385, "total_steps": 3717, "loss": 0.1355, "lr": 9.701817764232912e-07, "epoch": 6.374764595103578, "percentage": 91.07, "elapsed_time": "6:24:34", "remaining_time": "0:37:43"}
{"current_steps": 3390, "total_steps": 3717, "loss": 0.1493, "lr": 9.414949830723419e-07, "epoch": 6.3841807909604515, "percentage": 91.2, "elapsed_time": "6:25:08", "remaining_time": "0:37:09"}
{"current_steps": 3395, "total_steps": 3717, "loss": 0.157, "lr": 9.132284666430413e-07, "epoch": 6.393596986817326, "percentage": 91.34, "elapsed_time": "6:25:42", "remaining_time": "0:36:35"}
{"current_steps": 3400, "total_steps": 3717, "loss": 0.1411, "lr": 8.853828504667828e-07, "epoch": 6.4030131826742, "percentage": 91.47, "elapsed_time": "6:26:16", "remaining_time": "0:36:00"}
{"current_steps": 3405, "total_steps": 3717, "loss": 0.1439, "lr": 8.57958748593295e-07, "epoch": 6.4124293785310735, "percentage": 91.61, "elapsed_time": "6:26:48", "remaining_time": "0:35:26"}
{"current_steps": 3410, "total_steps": 3717, "loss": 0.1609, "lr": 8.309567657771e-07, "epoch": 6.421845574387947, "percentage": 91.74, "elapsed_time": "6:27:21", "remaining_time": "0:34:52"}
{"current_steps": 3415, "total_steps": 3717, "loss": 0.1511, "lr": 8.043774974641793e-07, "epoch": 6.431261770244821, "percentage": 91.88, "elapsed_time": "6:27:54", "remaining_time": "0:34:18"}
{"current_steps": 3420, "total_steps": 3717, "loss": 0.1538, "lr": 7.782215297788398e-07, "epoch": 6.440677966101695, "percentage": 92.01, "elapsed_time": "6:28:29", "remaining_time": "0:33:44"}
{"current_steps": 3425, "total_steps": 3717, "loss": 0.1414, "lr": 7.524894395107951e-07, "epoch": 6.450094161958568, "percentage": 92.14, "elapsed_time": "6:29:02", "remaining_time": "0:33:10"}
{"current_steps": 3430, "total_steps": 3717, "loss": 0.1543, "lr": 7.271817941024339e-07, "epoch": 6.459510357815443, "percentage": 92.28, "elapsed_time": "6:29:36", "remaining_time": "0:32:35"}
{"current_steps": 3435, "total_steps": 3717, "loss": 0.1483, "lr": 7.022991516363209e-07, "epoch": 6.468926553672317, "percentage": 92.41, "elapsed_time": "6:30:07", "remaining_time": "0:32:01"}
{"current_steps": 3440, "total_steps": 3717, "loss": 0.1542, "lr": 6.778420608228775e-07, "epoch": 6.47834274952919, "percentage": 92.55, "elapsed_time": "6:30:38", "remaining_time": "0:31:27"}
{"current_steps": 3445, "total_steps": 3717, "loss": 0.1485, "lr": 6.538110609882942e-07, "epoch": 6.487758945386064, "percentage": 92.68, "elapsed_time": "6:31:13", "remaining_time": "0:30:53"}
{"current_steps": 3450, "total_steps": 3717, "loss": 0.157, "lr": 6.30206682062624e-07, "epoch": 6.497175141242938, "percentage": 92.82, "elapsed_time": "6:31:43", "remaining_time": "0:30:18"}
{"current_steps": 3455, "total_steps": 3717, "loss": 0.1443, "lr": 6.070294445681102e-07, "epoch": 6.506591337099811, "percentage": 92.95, "elapsed_time": "6:32:17", "remaining_time": "0:29:44"}
{"current_steps": 3460, "total_steps": 3717, "loss": 0.1405, "lr": 5.842798596076948e-07, "epoch": 6.516007532956685, "percentage": 93.09, "elapsed_time": "6:32:48", "remaining_time": "0:29:10"}
{"current_steps": 3465, "total_steps": 3717, "loss": 0.1498, "lr": 5.61958428853755e-07, "epoch": 6.52542372881356, "percentage": 93.22, "elapsed_time": "6:33:20", "remaining_time": "0:28:36"}
{"current_steps": 3470, "total_steps": 3717, "loss": 0.1484, "lr": 5.4006564453704e-07, "epoch": 6.534839924670433, "percentage": 93.35, "elapsed_time": "6:33:51", "remaining_time": "0:28:02"}
{"current_steps": 3475, "total_steps": 3717, "loss": 0.1532, "lr": 5.186019894358163e-07, "epoch": 6.544256120527307, "percentage": 93.49, "elapsed_time": "6:34:25", "remaining_time": "0:27:28"}
{"current_steps": 3480, "total_steps": 3717, "loss": 0.1432, "lr": 4.97567936865222e-07, "epoch": 6.553672316384181, "percentage": 93.62, "elapsed_time": "6:35:00", "remaining_time": "0:26:54"}
{"current_steps": 3485, "total_steps": 3717, "loss": 0.1444, "lr": 4.769639506668222e-07, "epoch": 6.5630885122410545, "percentage": 93.76, "elapsed_time": "6:35:32", "remaining_time": "0:26:19"}
{"current_steps": 3490, "total_steps": 3717, "loss": 0.1434, "lr": 4.5679048519839064e-07, "epoch": 6.572504708097928, "percentage": 93.89, "elapsed_time": "6:36:05", "remaining_time": "0:25:45"}
{"current_steps": 3495, "total_steps": 3717, "loss": 0.1377, "lr": 4.3704798532388624e-07, "epoch": 6.581920903954802, "percentage": 94.03, "elapsed_time": "6:36:39", "remaining_time": "0:25:11"}
{"current_steps": 3500, "total_steps": 3717, "loss": 0.1536, "lr": 4.177368864036413e-07, "epoch": 6.5913370998116765, "percentage": 94.16, "elapsed_time": "6:37:12", "remaining_time": "0:24:37"}
{"current_steps": 3505, "total_steps": 3717, "loss": 0.1598, "lr": 3.988576142847622e-07, "epoch": 6.60075329566855, "percentage": 94.3, "elapsed_time": "6:37:47", "remaining_time": "0:24:03"}
{"current_steps": 3510, "total_steps": 3717, "loss": 0.1467, "lr": 3.8041058529173504e-07, "epoch": 6.610169491525424, "percentage": 94.43, "elapsed_time": "6:38:20", "remaining_time": "0:23:29"}
{"current_steps": 3515, "total_steps": 3717, "loss": 0.1339, "lr": 3.623962062172526e-07, "epoch": 6.619585687382298, "percentage": 94.57, "elapsed_time": "6:38:53", "remaining_time": "0:22:55"}
{"current_steps": 3520, "total_steps": 3717, "loss": 0.1454, "lr": 3.448148743132418e-07, "epoch": 6.629001883239171, "percentage": 94.7, "elapsed_time": "6:39:26", "remaining_time": "0:22:21"}
{"current_steps": 3525, "total_steps": 3717, "loss": 0.1588, "lr": 3.2766697728209507e-07, "epoch": 6.638418079096045, "percentage": 94.83, "elapsed_time": "6:40:00", "remaining_time": "0:21:47"}
{"current_steps": 3530, "total_steps": 3717, "loss": 0.1551, "lr": 3.109528932681327e-07, "epoch": 6.647834274952919, "percentage": 94.97, "elapsed_time": "6:40:35", "remaining_time": "0:21:13"}
{"current_steps": 3535, "total_steps": 3717, "loss": 0.1444, "lr": 2.9467299084925405e-07, "epoch": 6.657250470809792, "percentage": 95.1, "elapsed_time": "6:41:09", "remaining_time": "0:20:39"}
{"current_steps": 3540, "total_steps": 3717, "loss": 0.1445, "lr": 2.7882762902881277e-07, "epoch": 6.666666666666667, "percentage": 95.24, "elapsed_time": "6:41:44", "remaining_time": "0:20:05"}
{"current_steps": 3545, "total_steps": 3717, "loss": 0.1541, "lr": 2.6341715722771223e-07, "epoch": 6.676082862523541, "percentage": 95.37, "elapsed_time": "6:42:19", "remaining_time": "0:19:31"}
{"current_steps": 3550, "total_steps": 3717, "loss": 0.1433, "lr": 2.484419152766737e-07, "epoch": 6.685499058380414, "percentage": 95.51, "elapsed_time": "6:42:51", "remaining_time": "0:18:57"}
{"current_steps": 3555, "total_steps": 3717, "loss": 0.1579, "lr": 2.3390223340876928e-07, "epoch": 6.694915254237288, "percentage": 95.64, "elapsed_time": "6:43:23", "remaining_time": "0:18:22"}
{"current_steps": 3560, "total_steps": 3717, "loss": 0.1337, "lr": 2.1979843225212293e-07, "epoch": 6.704331450094162, "percentage": 95.78, "elapsed_time": "6:43:59", "remaining_time": "0:17:49"}
{"current_steps": 3565, "total_steps": 3717, "loss": 0.1454, "lr": 2.0613082282284978e-07, "epoch": 6.7137476459510355, "percentage": 95.91, "elapsed_time": "6:44:35", "remaining_time": "0:17:15"}
{"current_steps": 3570, "total_steps": 3717, "loss": 0.1297, "lr": 1.928997065181859e-07, "epoch": 6.72316384180791, "percentage": 96.05, "elapsed_time": "6:45:07", "remaining_time": "0:16:40"}
{"current_steps": 3575, "total_steps": 3717, "loss": 0.1583, "lr": 1.801053751098536e-07, "epoch": 6.732580037664784, "percentage": 96.18, "elapsed_time": "6:45:40", "remaining_time": "0:16:06"}
{"current_steps": 3580, "total_steps": 3717, "loss": 0.144, "lr": 1.6774811073762665e-07, "epoch": 6.7419962335216574, "percentage": 96.31, "elapsed_time": "6:46:15", "remaining_time": "0:15:32"}
{"current_steps": 3585, "total_steps": 3717, "loss": 0.1619, "lr": 1.5582818590309744e-07, "epoch": 6.751412429378531, "percentage": 96.45, "elapsed_time": "6:46:45", "remaining_time": "0:14:58"}
{"current_steps": 3590, "total_steps": 3717, "loss": 0.1348, "lr": 1.4434586346367962e-07, "epoch": 6.760828625235405, "percentage": 96.58, "elapsed_time": "6:47:19", "remaining_time": "0:14:24"}
{"current_steps": 3595, "total_steps": 3717, "loss": 0.1412, "lr": 1.3330139662680596e-07, "epoch": 6.7702448210922785, "percentage": 96.72, "elapsed_time": "6:47:50", "remaining_time": "0:13:50"}
{"current_steps": 3600, "total_steps": 3717, "loss": 0.1439, "lr": 1.2269502894434626e-07, "epoch": 6.779661016949152, "percentage": 96.85, "elapsed_time": "6:48:22", "remaining_time": "0:13:16"}
{"current_steps": 3605, "total_steps": 3717, "loss": 0.1277, "lr": 1.125269943072338e-07, "epoch": 6.789077212806026, "percentage": 96.99, "elapsed_time": "6:48:58", "remaining_time": "0:12:42"}
{"current_steps": 3610, "total_steps": 3717, "loss": 0.1441, "lr": 1.0279751694031393e-07, "epoch": 6.7984934086629005, "percentage": 97.12, "elapsed_time": "6:49:32", "remaining_time": "0:12:08"}
{"current_steps": 3615, "total_steps": 3717, "loss": 0.1616, "lr": 9.350681139739249e-08, "epoch": 6.807909604519774, "percentage": 97.26, "elapsed_time": "6:50:04", "remaining_time": "0:11:34"}
{"current_steps": 3620, "total_steps": 3717, "loss": 0.1325, "lr": 8.465508255650845e-08, "epoch": 6.817325800376648, "percentage": 97.39, "elapsed_time": "6:50:38", "remaining_time": "0:11:00"}
{"current_steps": 3625, "total_steps": 3717, "loss": 0.1347, "lr": 7.62425256154109e-08, "epoch": 6.826741996233522, "percentage": 97.52, "elapsed_time": "6:51:12", "remaining_time": "0:10:26"}
{"current_steps": 3630, "total_steps": 3717, "loss": 0.1432, "lr": 6.826932608726689e-08, "epoch": 6.836158192090395, "percentage": 97.66, "elapsed_time": "6:51:46", "remaining_time": "0:09:52"}
{"current_steps": 3635, "total_steps": 3717, "loss": 0.1421, "lr": 6.073565979655804e-08, "epoch": 6.845574387947269, "percentage": 97.79, "elapsed_time": "6:52:19", "remaining_time": "0:09:18"}
{"current_steps": 3640, "total_steps": 3717, "loss": 0.1364, "lr": 5.364169287520149e-08, "epoch": 6.854990583804144, "percentage": 97.93, "elapsed_time": "6:52:55", "remaining_time": "0:08:44"}
{"current_steps": 3645, "total_steps": 3717, "loss": 0.1438, "lr": 4.698758175889939e-08, "epoch": 6.864406779661017, "percentage": 98.06, "elapsed_time": "6:53:27", "remaining_time": "0:08:10"}
{"current_steps": 3650, "total_steps": 3717, "loss": 0.1478, "lr": 4.077347318368175e-08, "epoch": 6.873822975517891, "percentage": 98.2, "elapsed_time": "6:53:59", "remaining_time": "0:07:35"}
{"current_steps": 3655, "total_steps": 3717, "loss": 0.1241, "lr": 3.499950418266895e-08, "epoch": 6.883239171374765, "percentage": 98.33, "elapsed_time": "6:54:32", "remaining_time": "0:07:01"}
{"current_steps": 3660, "total_steps": 3717, "loss": 0.1355, "lr": 2.9665802083054253e-08, "epoch": 6.892655367231638, "percentage": 98.47, "elapsed_time": "6:55:06", "remaining_time": "0:06:27"}
{"current_steps": 3665, "total_steps": 3717, "loss": 0.1329, "lr": 2.4772484503288174e-08, "epoch": 6.902071563088512, "percentage": 98.6, "elapsed_time": "6:55:39", "remaining_time": "0:05:53"}
{"current_steps": 3670, "total_steps": 3717, "loss": 0.1529, "lr": 2.03196593504984e-08, "epoch": 6.911487758945386, "percentage": 98.74, "elapsed_time": "6:56:10", "remaining_time": "0:05:19"}
{"current_steps": 3675, "total_steps": 3717, "loss": 0.1607, "lr": 1.6307424818091666e-08, "epoch": 6.9209039548022595, "percentage": 98.87, "elapsed_time": "6:56:42", "remaining_time": "0:04:45"}
{"current_steps": 3680, "total_steps": 3717, "loss": 0.1387, "lr": 1.2735869383611043e-08, "epoch": 6.930320150659134, "percentage": 99.0, "elapsed_time": "6:57:17", "remaining_time": "0:04:11"}
{"current_steps": 3685, "total_steps": 3717, "loss": 0.1463, "lr": 9.605071806761957e-09, "epoch": 6.939736346516008, "percentage": 99.14, "elapsed_time": "6:57:50", "remaining_time": "0:03:37"}
{"current_steps": 3690, "total_steps": 3717, "loss": 0.131, "lr": 6.915101127691337e-09, "epoch": 6.9491525423728815, "percentage": 99.27, "elapsed_time": "6:58:24", "remaining_time": "0:03:03"}
{"current_steps": 3695, "total_steps": 3717, "loss": 0.1454, "lr": 4.666016665459961e-09, "epoch": 6.958568738229755, "percentage": 99.41, "elapsed_time": "6:58:55", "remaining_time": "0:02:29"}
{"current_steps": 3700, "total_steps": 3717, "loss": 0.1393, "lr": 2.857868016732379e-09, "epoch": 6.967984934086629, "percentage": 99.54, "elapsed_time": "6:59:28", "remaining_time": "0:01:55"}
{"current_steps": 3705, "total_steps": 3717, "loss": 0.1386, "lr": 1.4906950546866861e-09, "epoch": 6.977401129943503, "percentage": 99.68, "elapsed_time": "7:00:03", "remaining_time": "0:01:21"}
{"current_steps": 3710, "total_steps": 3717, "loss": 0.1342, "lr": 5.645279281307758e-10, "epoch": 6.986817325800376, "percentage": 99.81, "elapsed_time": "7:00:37", "remaining_time": "0:00:47"}
{"current_steps": 3715, "total_steps": 3717, "loss": 0.1388, "lr": 7.938706084287262e-11, "epoch": 6.996233521657251, "percentage": 99.95, "elapsed_time": "7:01:09", "remaining_time": "0:00:13"}
{"current_steps": 3717, "total_steps": 3717, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "7:01:31", "remaining_time": "0:00:00"}

9144
trainer_state.json Normal file

File diff suppressed because it is too large Load Diff

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ea1675c024fb333d7a939c609c7edb8f7053604177e8e7e0d8387e2dbdad0344
size 8529

BIN
training_loss.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 44 KiB

1
vocab.json Normal file

File diff suppressed because one or more lines are too long