初始化项目,由ModelHub XC社区提供模型

Model: laion/glm46-swesmith-maxeps-131k-fixthink
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-07 09:24:12 +08:00
commit 179635f48e
24 changed files with 9113 additions and 0 deletions

56
.gitattributes vendored Normal file
View File

@@ -0,0 +1,56 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bz2 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
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack 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
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* 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
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
training_args.bin filter=lfs diff=lfs merge=lfs -text
model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
vocab.json filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text
model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
merges.txt filter=lfs diff=lfs merge=lfs -text
model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text

61
README.md Normal file
View File

@@ -0,0 +1,61 @@
---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3-8B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: glm46-swesmith-maxeps-131k-fixthink
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. -->
# glm46-swesmith-maxeps-131k-fixthink
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--glm46-swesmith-maxeps-131k/snapshots/4d4c2d4a9d21f73870ed31c7bc6028035b3b6ca7_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: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 64
- 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 2.9.0+cu128
- Datasets 4.4.1
- 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": 6.044664775062429,
"achieved_tflops_per_gpu_theoretical": 203.27427376939005,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.1423269808292389,
"mfu_percent": 0.6111895626958977,
"mfu_percent_theoretical": 20.55351605352781,
"total_flos": 2.6890471642266337e+18,
"train_loss": 0.1819671289975788,
"train_runtime": 55607.8638,
"train_samples_per_second": 0.959,
"train_steps_per_second": 0.06,
"valid_targets_mean": 5815.2,
"valid_targets_min": 1781
}

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
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "others", "allow_remote": true}

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"
}

BIN
merges.txt (Stored with Git LFS) Normal file

Binary file not shown.

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d78554cd6a8387184f7acd4648eeefc7ef13576f39c50ca9b11d1b0c097333b1
size 4902257696

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6d99bb411de10393a99af38d0e7027f0836fe42ff2b1e04f341b908378573874
size 4915960368

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d5561d90f3dce480734f13b6ea18c0b75b21a1c945ce511e47cafa1b4353fea2
size 4983068496

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2b65fa64ecee457f78b29d0b1766fa9af6afb6b56b7aa2f46faffd357c812278
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": "4d4c2d4a9d21f73870ed31c7bc6028035b3b6ca7_thinking_preprocessed",
"training_start": null,
"training_end": null,
"created_by": "DCAgent",
"base_model_name": "Qwen/Qwen3-8B",
"dataset_name": "/data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--glm46-swesmith-maxeps-131k/snapshots/4d4c2d4a9d21f73870ed31c7bc6028035b3b6ca7_thinking_preprocessed",
"training_type": "SFT",
"training_parameters": "https://huggingface.co/laion/glm46-swesmith-maxeps-131k-fixthink/blob/main/config.json",
"wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/sft_glm46-swesmith-maxeps-131k_Qwen3-8B",
"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
}
}

BIN
tokenizer.json (Stored with Git LFS) Normal file

Binary file not shown.

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": 6.044664775062429,
"achieved_tflops_per_gpu_theoretical": 203.27427376939005,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.1423269808292389,
"mfu_percent": 0.6111895626958977,
"mfu_percent_theoretical": 20.55351605352781,
"total_flos": 2.6890471642266337e+18,
"train_loss": 0.1819671289975788,
"train_runtime": 55607.8638,
"train_samples_per_second": 0.959,
"train_steps_per_second": 0.06,
"valid_targets_mean": 5815.2,
"valid_targets_min": 1781
}

668
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,668 @@
{"current_steps": 5, "total_steps": 3339, "loss": 0.5478, "lr": 4.790419161676648e-07, "epoch": 0.01049317943336831, "percentage": 0.15, "elapsed_time": "0:01:32", "remaining_time": "17:07:48"}
{"current_steps": 10, "total_steps": 3339, "loss": 0.5587, "lr": 1.0778443113772456e-06, "epoch": 0.02098635886673662, "percentage": 0.3, "elapsed_time": "0:02:57", "remaining_time": "16:24:48"}
{"current_steps": 15, "total_steps": 3339, "loss": 0.5301, "lr": 1.6766467065868263e-06, "epoch": 0.03147953830010493, "percentage": 0.45, "elapsed_time": "0:04:22", "remaining_time": "16:11:09"}
{"current_steps": 20, "total_steps": 3339, "loss": 0.5158, "lr": 2.2754491017964075e-06, "epoch": 0.04197271773347324, "percentage": 0.6, "elapsed_time": "0:05:48", "remaining_time": "16:05:16"}
{"current_steps": 25, "total_steps": 3339, "loss": 0.4672, "lr": 2.874251497005988e-06, "epoch": 0.05246589716684155, "percentage": 0.75, "elapsed_time": "0:07:16", "remaining_time": "16:04:32"}
{"current_steps": 30, "total_steps": 3339, "loss": 0.4327, "lr": 3.4730538922155693e-06, "epoch": 0.06295907660020986, "percentage": 0.9, "elapsed_time": "0:08:43", "remaining_time": "16:02:14"}
{"current_steps": 35, "total_steps": 3339, "loss": 0.4349, "lr": 4.07185628742515e-06, "epoch": 0.07345225603357818, "percentage": 1.05, "elapsed_time": "0:10:09", "remaining_time": "15:59:43"}
{"current_steps": 40, "total_steps": 3339, "loss": 0.385, "lr": 4.670658682634731e-06, "epoch": 0.08394543546694648, "percentage": 1.2, "elapsed_time": "0:11:36", "remaining_time": "15:57:36"}
{"current_steps": 45, "total_steps": 3339, "loss": 0.3846, "lr": 5.2694610778443125e-06, "epoch": 0.0944386149003148, "percentage": 1.35, "elapsed_time": "0:13:03", "remaining_time": "15:56:22"}
{"current_steps": 50, "total_steps": 3339, "loss": 0.3689, "lr": 5.868263473053893e-06, "epoch": 0.1049317943336831, "percentage": 1.5, "elapsed_time": "0:14:31", "remaining_time": "15:55:33"}
{"current_steps": 55, "total_steps": 3339, "loss": 0.364, "lr": 6.4670658682634736e-06, "epoch": 0.11542497376705142, "percentage": 1.65, "elapsed_time": "0:15:57", "remaining_time": "15:53:17"}
{"current_steps": 60, "total_steps": 3339, "loss": 0.3559, "lr": 7.0658682634730545e-06, "epoch": 0.1259181532004197, "percentage": 1.8, "elapsed_time": "0:17:23", "remaining_time": "15:50:42"}
{"current_steps": 65, "total_steps": 3339, "loss": 0.3527, "lr": 7.664670658682636e-06, "epoch": 0.13641133263378805, "percentage": 1.95, "elapsed_time": "0:18:50", "remaining_time": "15:48:42"}
{"current_steps": 70, "total_steps": 3339, "loss": 0.3472, "lr": 8.263473053892216e-06, "epoch": 0.14690451206715635, "percentage": 2.1, "elapsed_time": "0:20:15", "remaining_time": "15:45:46"}
{"current_steps": 75, "total_steps": 3339, "loss": 0.3256, "lr": 8.862275449101796e-06, "epoch": 0.15739769150052466, "percentage": 2.25, "elapsed_time": "0:21:39", "remaining_time": "15:42:29"}
{"current_steps": 80, "total_steps": 3339, "loss": 0.3088, "lr": 9.461077844311378e-06, "epoch": 0.16789087093389296, "percentage": 2.4, "elapsed_time": "0:23:05", "remaining_time": "15:40:55"}
{"current_steps": 85, "total_steps": 3339, "loss": 0.3132, "lr": 1.0059880239520958e-05, "epoch": 0.1783840503672613, "percentage": 2.55, "elapsed_time": "0:24:33", "remaining_time": "15:40:01"}
{"current_steps": 90, "total_steps": 3339, "loss": 0.3157, "lr": 1.065868263473054e-05, "epoch": 0.1888772298006296, "percentage": 2.7, "elapsed_time": "0:25:58", "remaining_time": "15:37:57"}
{"current_steps": 95, "total_steps": 3339, "loss": 0.3021, "lr": 1.125748502994012e-05, "epoch": 0.1993704092339979, "percentage": 2.85, "elapsed_time": "0:27:24", "remaining_time": "15:36:03"}
{"current_steps": 100, "total_steps": 3339, "loss": 0.2913, "lr": 1.1856287425149702e-05, "epoch": 0.2098635886673662, "percentage": 2.99, "elapsed_time": "0:28:50", "remaining_time": "15:34:03"}
{"current_steps": 105, "total_steps": 3339, "loss": 0.299, "lr": 1.2455089820359284e-05, "epoch": 0.2203567681007345, "percentage": 3.14, "elapsed_time": "0:30:15", "remaining_time": "15:31:48"}
{"current_steps": 110, "total_steps": 3339, "loss": 0.2922, "lr": 1.3053892215568864e-05, "epoch": 0.23084994753410285, "percentage": 3.29, "elapsed_time": "0:31:39", "remaining_time": "15:29:24"}
{"current_steps": 115, "total_steps": 3339, "loss": 0.2916, "lr": 1.3652694610778446e-05, "epoch": 0.24134312696747115, "percentage": 3.44, "elapsed_time": "0:33:05", "remaining_time": "15:27:38"}
{"current_steps": 120, "total_steps": 3339, "loss": 0.2873, "lr": 1.4251497005988024e-05, "epoch": 0.2518363064008394, "percentage": 3.59, "elapsed_time": "0:34:30", "remaining_time": "15:25:44"}
{"current_steps": 125, "total_steps": 3339, "loss": 0.2819, "lr": 1.4850299401197606e-05, "epoch": 0.2623294858342078, "percentage": 3.74, "elapsed_time": "0:35:56", "remaining_time": "15:24:16"}
{"current_steps": 130, "total_steps": 3339, "loss": 0.2735, "lr": 1.5449101796407188e-05, "epoch": 0.2728226652675761, "percentage": 3.89, "elapsed_time": "0:37:21", "remaining_time": "15:22:21"}
{"current_steps": 135, "total_steps": 3339, "loss": 0.2725, "lr": 1.604790419161677e-05, "epoch": 0.2833158447009444, "percentage": 4.04, "elapsed_time": "0:38:48", "remaining_time": "15:20:52"}
{"current_steps": 140, "total_steps": 3339, "loss": 0.2745, "lr": 1.6646706586826348e-05, "epoch": 0.2938090241343127, "percentage": 4.19, "elapsed_time": "0:40:14", "remaining_time": "15:19:32"}
{"current_steps": 145, "total_steps": 3339, "loss": 0.2756, "lr": 1.724550898203593e-05, "epoch": 0.304302203567681, "percentage": 4.34, "elapsed_time": "0:41:38", "remaining_time": "15:17:25"}
{"current_steps": 150, "total_steps": 3339, "loss": 0.262, "lr": 1.784431137724551e-05, "epoch": 0.3147953830010493, "percentage": 4.49, "elapsed_time": "0:43:05", "remaining_time": "15:15:57"}
{"current_steps": 155, "total_steps": 3339, "loss": 0.2752, "lr": 1.8443113772455093e-05, "epoch": 0.3252885624344176, "percentage": 4.64, "elapsed_time": "0:44:31", "remaining_time": "15:14:36"}
{"current_steps": 160, "total_steps": 3339, "loss": 0.2699, "lr": 1.904191616766467e-05, "epoch": 0.3357817418677859, "percentage": 4.79, "elapsed_time": "0:45:55", "remaining_time": "15:12:35"}
{"current_steps": 165, "total_steps": 3339, "loss": 0.2647, "lr": 1.9640718562874253e-05, "epoch": 0.3462749213011542, "percentage": 4.94, "elapsed_time": "0:47:19", "remaining_time": "15:10:20"}
{"current_steps": 170, "total_steps": 3339, "loss": 0.269, "lr": 2.0239520958083835e-05, "epoch": 0.3567681007345226, "percentage": 5.09, "elapsed_time": "0:48:46", "remaining_time": "15:09:05"}
{"current_steps": 175, "total_steps": 3339, "loss": 0.2593, "lr": 2.0838323353293413e-05, "epoch": 0.3672612801678909, "percentage": 5.24, "elapsed_time": "0:50:12", "remaining_time": "15:07:50"}
{"current_steps": 180, "total_steps": 3339, "loss": 0.2679, "lr": 2.1437125748502995e-05, "epoch": 0.3777544596012592, "percentage": 5.39, "elapsed_time": "0:51:37", "remaining_time": "15:06:02"}
{"current_steps": 185, "total_steps": 3339, "loss": 0.2668, "lr": 2.2035928143712577e-05, "epoch": 0.3882476390346275, "percentage": 5.54, "elapsed_time": "0:53:01", "remaining_time": "15:04:02"}
{"current_steps": 190, "total_steps": 3339, "loss": 0.2611, "lr": 2.2634730538922155e-05, "epoch": 0.3987408184679958, "percentage": 5.69, "elapsed_time": "0:54:26", "remaining_time": "15:02:24"}
{"current_steps": 195, "total_steps": 3339, "loss": 0.2534, "lr": 2.323353293413174e-05, "epoch": 0.4092339979013641, "percentage": 5.84, "elapsed_time": "0:55:49", "remaining_time": "15:00:02"}
{"current_steps": 200, "total_steps": 3339, "loss": 0.257, "lr": 2.383233532934132e-05, "epoch": 0.4197271773347324, "percentage": 5.99, "elapsed_time": "0:57:14", "remaining_time": "14:58:29"}
{"current_steps": 205, "total_steps": 3339, "loss": 0.2471, "lr": 2.44311377245509e-05, "epoch": 0.4302203567681007, "percentage": 6.14, "elapsed_time": "0:58:38", "remaining_time": "14:56:32"}
{"current_steps": 210, "total_steps": 3339, "loss": 0.2462, "lr": 2.502994011976048e-05, "epoch": 0.440713536201469, "percentage": 6.29, "elapsed_time": "1:00:02", "remaining_time": "14:54:34"}
{"current_steps": 215, "total_steps": 3339, "loss": 0.2499, "lr": 2.5628742514970064e-05, "epoch": 0.45120671563483733, "percentage": 6.44, "elapsed_time": "1:01:27", "remaining_time": "14:53:05"}
{"current_steps": 220, "total_steps": 3339, "loss": 0.2541, "lr": 2.6227544910179643e-05, "epoch": 0.4616998950682057, "percentage": 6.59, "elapsed_time": "1:02:53", "remaining_time": "14:51:31"}
{"current_steps": 225, "total_steps": 3339, "loss": 0.2519, "lr": 2.682634730538922e-05, "epoch": 0.472193074501574, "percentage": 6.74, "elapsed_time": "1:04:17", "remaining_time": "14:49:46"}
{"current_steps": 230, "total_steps": 3339, "loss": 0.2439, "lr": 2.7425149700598806e-05, "epoch": 0.4826862539349423, "percentage": 6.89, "elapsed_time": "1:05:42", "remaining_time": "14:48:08"}
{"current_steps": 235, "total_steps": 3339, "loss": 0.2436, "lr": 2.8023952095808385e-05, "epoch": 0.4931794333683106, "percentage": 7.04, "elapsed_time": "1:07:06", "remaining_time": "14:46:25"}
{"current_steps": 240, "total_steps": 3339, "loss": 0.2359, "lr": 2.8622754491017966e-05, "epoch": 0.5036726128016789, "percentage": 7.19, "elapsed_time": "1:08:31", "remaining_time": "14:44:47"}
{"current_steps": 245, "total_steps": 3339, "loss": 0.2377, "lr": 2.9221556886227548e-05, "epoch": 0.5141657922350472, "percentage": 7.34, "elapsed_time": "1:09:57", "remaining_time": "14:43:32"}
{"current_steps": 250, "total_steps": 3339, "loss": 0.2408, "lr": 2.982035928143713e-05, "epoch": 0.5246589716684156, "percentage": 7.49, "elapsed_time": "1:11:23", "remaining_time": "14:42:07"}
{"current_steps": 255, "total_steps": 3339, "loss": 0.24, "lr": 3.041916167664671e-05, "epoch": 0.5351521511017838, "percentage": 7.64, "elapsed_time": "1:12:49", "remaining_time": "14:40:40"}
{"current_steps": 260, "total_steps": 3339, "loss": 0.2371, "lr": 3.101796407185629e-05, "epoch": 0.5456453305351522, "percentage": 7.79, "elapsed_time": "1:14:13", "remaining_time": "14:38:55"}
{"current_steps": 265, "total_steps": 3339, "loss": 0.2438, "lr": 3.161676646706587e-05, "epoch": 0.5561385099685204, "percentage": 7.94, "elapsed_time": "1:15:36", "remaining_time": "14:37:07"}
{"current_steps": 270, "total_steps": 3339, "loss": 0.2372, "lr": 3.221556886227545e-05, "epoch": 0.5666316894018888, "percentage": 8.09, "elapsed_time": "1:17:01", "remaining_time": "14:35:28"}
{"current_steps": 275, "total_steps": 3339, "loss": 0.2386, "lr": 3.2814371257485035e-05, "epoch": 0.577124868835257, "percentage": 8.24, "elapsed_time": "1:18:27", "remaining_time": "14:34:08"}
{"current_steps": 280, "total_steps": 3339, "loss": 0.2417, "lr": 3.3413173652694614e-05, "epoch": 0.5876180482686254, "percentage": 8.39, "elapsed_time": "1:19:52", "remaining_time": "14:32:42"}
{"current_steps": 285, "total_steps": 3339, "loss": 0.2361, "lr": 3.40119760479042e-05, "epoch": 0.5981112277019937, "percentage": 8.54, "elapsed_time": "1:21:16", "remaining_time": "14:31:00"}
{"current_steps": 290, "total_steps": 3339, "loss": 0.2317, "lr": 3.461077844311378e-05, "epoch": 0.608604407135362, "percentage": 8.69, "elapsed_time": "1:22:42", "remaining_time": "14:29:30"}
{"current_steps": 295, "total_steps": 3339, "loss": 0.2427, "lr": 3.5209580838323356e-05, "epoch": 0.6190975865687304, "percentage": 8.83, "elapsed_time": "1:24:07", "remaining_time": "14:28:02"}
{"current_steps": 300, "total_steps": 3339, "loss": 0.2351, "lr": 3.5808383233532934e-05, "epoch": 0.6295907660020986, "percentage": 8.98, "elapsed_time": "1:25:32", "remaining_time": "14:26:28"}
{"current_steps": 305, "total_steps": 3339, "loss": 0.2384, "lr": 3.640718562874252e-05, "epoch": 0.640083945435467, "percentage": 9.13, "elapsed_time": "1:26:57", "remaining_time": "14:25:03"}
{"current_steps": 310, "total_steps": 3339, "loss": 0.2351, "lr": 3.70059880239521e-05, "epoch": 0.6505771248688352, "percentage": 9.28, "elapsed_time": "1:28:23", "remaining_time": "14:23:36"}
{"current_steps": 315, "total_steps": 3339, "loss": 0.2393, "lr": 3.7604790419161676e-05, "epoch": 0.6610703043022036, "percentage": 9.43, "elapsed_time": "1:29:47", "remaining_time": "14:22:00"}
{"current_steps": 320, "total_steps": 3339, "loss": 0.2268, "lr": 3.820359281437126e-05, "epoch": 0.6715634837355718, "percentage": 9.58, "elapsed_time": "1:31:10", "remaining_time": "14:20:08"}
{"current_steps": 325, "total_steps": 3339, "loss": 0.2302, "lr": 3.880239520958084e-05, "epoch": 0.6820566631689402, "percentage": 9.73, "elapsed_time": "1:32:34", "remaining_time": "14:18:32"}
{"current_steps": 330, "total_steps": 3339, "loss": 0.2331, "lr": 3.9401197604790425e-05, "epoch": 0.6925498426023085, "percentage": 9.88, "elapsed_time": "1:33:57", "remaining_time": "14:16:45"}
{"current_steps": 335, "total_steps": 3339, "loss": 0.2285, "lr": 4e-05, "epoch": 0.7030430220356768, "percentage": 10.03, "elapsed_time": "1:35:23", "remaining_time": "14:15:20"}
{"current_steps": 340, "total_steps": 3339, "loss": 0.2214, "lr": 3.9999726756517076e-05, "epoch": 0.7135362014690452, "percentage": 10.18, "elapsed_time": "1:36:47", "remaining_time": "14:13:49"}
{"current_steps": 345, "total_steps": 3339, "loss": 0.2242, "lr": 3.9998907033534495e-05, "epoch": 0.7240293809024134, "percentage": 10.33, "elapsed_time": "1:38:11", "remaining_time": "14:12:12"}
{"current_steps": 350, "total_steps": 3339, "loss": 0.2279, "lr": 3.999754085345065e-05, "epoch": 0.7345225603357818, "percentage": 10.48, "elapsed_time": "1:39:35", "remaining_time": "14:10:28"}
{"current_steps": 355, "total_steps": 3339, "loss": 0.2298, "lr": 3.9995628253595536e-05, "epoch": 0.74501573976915, "percentage": 10.63, "elapsed_time": "1:40:58", "remaining_time": "14:08:45"}
{"current_steps": 360, "total_steps": 3339, "loss": 0.2265, "lr": 3.999316928622968e-05, "epoch": 0.7555089192025184, "percentage": 10.78, "elapsed_time": "1:42:22", "remaining_time": "14:07:07"}
{"current_steps": 365, "total_steps": 3339, "loss": 0.2319, "lr": 3.999016401854278e-05, "epoch": 0.7660020986358866, "percentage": 10.93, "elapsed_time": "1:43:45", "remaining_time": "14:05:28"}
{"current_steps": 370, "total_steps": 3339, "loss": 0.2244, "lr": 3.9986612532651804e-05, "epoch": 0.776495278069255, "percentage": 11.08, "elapsed_time": "1:45:09", "remaining_time": "14:03:49"}
{"current_steps": 375, "total_steps": 3339, "loss": 0.2335, "lr": 3.9982514925598794e-05, "epoch": 0.7869884575026233, "percentage": 11.23, "elapsed_time": "1:46:34", "remaining_time": "14:02:22"}
{"current_steps": 380, "total_steps": 3339, "loss": 0.227, "lr": 3.997787130934819e-05, "epoch": 0.7974816369359916, "percentage": 11.38, "elapsed_time": "1:47:59", "remaining_time": "14:00:53"}
{"current_steps": 385, "total_steps": 3339, "loss": 0.2321, "lr": 3.997268181078379e-05, "epoch": 0.8079748163693599, "percentage": 11.53, "elapsed_time": "1:49:23", "remaining_time": "13:59:17"}
{"current_steps": 390, "total_steps": 3339, "loss": 0.2248, "lr": 3.9966946571705244e-05, "epoch": 0.8184679958027282, "percentage": 11.68, "elapsed_time": "1:50:47", "remaining_time": "13:57:48"}
{"current_steps": 395, "total_steps": 3339, "loss": 0.2195, "lr": 3.996066574882424e-05, "epoch": 0.8289611752360966, "percentage": 11.83, "elapsed_time": "1:52:11", "remaining_time": "13:56:07"}
{"current_steps": 400, "total_steps": 3339, "loss": 0.2246, "lr": 3.9953839513760154e-05, "epoch": 0.8394543546694648, "percentage": 11.98, "elapsed_time": "1:53:35", "remaining_time": "13:54:39"}
{"current_steps": 405, "total_steps": 3339, "loss": 0.2237, "lr": 3.9946468053035417e-05, "epoch": 0.8499475341028332, "percentage": 12.13, "elapsed_time": "1:55:00", "remaining_time": "13:53:10"}
{"current_steps": 410, "total_steps": 3339, "loss": 0.2254, "lr": 3.993855156807039e-05, "epoch": 0.8604407135362014, "percentage": 12.28, "elapsed_time": "1:56:23", "remaining_time": "13:51:30"}
{"current_steps": 415, "total_steps": 3339, "loss": 0.2205, "lr": 3.993009027517786e-05, "epoch": 0.8709338929695698, "percentage": 12.43, "elapsed_time": "1:57:47", "remaining_time": "13:49:58"}
{"current_steps": 420, "total_steps": 3339, "loss": 0.2191, "lr": 3.992108440555715e-05, "epoch": 0.881427072402938, "percentage": 12.58, "elapsed_time": "1:59:11", "remaining_time": "13:48:25"}
{"current_steps": 425, "total_steps": 3339, "loss": 0.2177, "lr": 3.991153420528777e-05, "epoch": 0.8919202518363064, "percentage": 12.73, "elapsed_time": "2:00:36", "remaining_time": "13:46:54"}
{"current_steps": 430, "total_steps": 3339, "loss": 0.225, "lr": 3.9901439935322726e-05, "epoch": 0.9024134312696747, "percentage": 12.88, "elapsed_time": "2:02:00", "remaining_time": "13:45:26"}
{"current_steps": 435, "total_steps": 3339, "loss": 0.2247, "lr": 3.989080187148136e-05, "epoch": 0.912906610703043, "percentage": 13.03, "elapsed_time": "2:03:25", "remaining_time": "13:43:55"}
{"current_steps": 440, "total_steps": 3339, "loss": 0.2196, "lr": 3.9879620304441834e-05, "epoch": 0.9233997901364114, "percentage": 13.18, "elapsed_time": "2:04:50", "remaining_time": "13:42:29"}
{"current_steps": 445, "total_steps": 3339, "loss": 0.2314, "lr": 3.986789553973319e-05, "epoch": 0.9338929695697796, "percentage": 13.33, "elapsed_time": "2:06:13", "remaining_time": "13:40:54"}
{"current_steps": 450, "total_steps": 3339, "loss": 0.2164, "lr": 3.985562789772697e-05, "epoch": 0.944386149003148, "percentage": 13.48, "elapsed_time": "2:07:37", "remaining_time": "13:39:20"}
{"current_steps": 455, "total_steps": 3339, "loss": 0.2144, "lr": 3.9842817713628494e-05, "epoch": 0.9548793284365162, "percentage": 13.63, "elapsed_time": "2:09:00", "remaining_time": "13:37:45"}
{"current_steps": 460, "total_steps": 3339, "loss": 0.2282, "lr": 3.982946533746771e-05, "epoch": 0.9653725078698846, "percentage": 13.78, "elapsed_time": "2:10:24", "remaining_time": "13:36:09"}
{"current_steps": 465, "total_steps": 3339, "loss": 0.2142, "lr": 3.9815571134089584e-05, "epoch": 0.9758656873032528, "percentage": 13.93, "elapsed_time": "2:11:47", "remaining_time": "13:34:33"}
{"current_steps": 470, "total_steps": 3339, "loss": 0.2206, "lr": 3.9801135483144174e-05, "epoch": 0.9863588667366212, "percentage": 14.08, "elapsed_time": "2:13:12", "remaining_time": "13:33:05"}
{"current_steps": 475, "total_steps": 3339, "loss": 0.2224, "lr": 3.9786158779076226e-05, "epoch": 0.9968520461699895, "percentage": 14.23, "elapsed_time": "2:14:36", "remaining_time": "13:31:39"}
{"current_steps": 480, "total_steps": 3339, "loss": 0.208, "lr": 3.977064143111443e-05, "epoch": 1.006295907660021, "percentage": 14.38, "elapsed_time": "2:15:51", "remaining_time": "13:29:09"}
{"current_steps": 485, "total_steps": 3339, "loss": 0.202, "lr": 3.9754583863260195e-05, "epoch": 1.0167890870933893, "percentage": 14.53, "elapsed_time": "2:17:15", "remaining_time": "13:27:41"}
{"current_steps": 490, "total_steps": 3339, "loss": 0.2074, "lr": 3.97379865142761e-05, "epoch": 1.0272822665267576, "percentage": 14.68, "elapsed_time": "2:18:40", "remaining_time": "13:26:14"}
{"current_steps": 495, "total_steps": 3339, "loss": 0.212, "lr": 3.97208498376739e-05, "epoch": 1.0377754459601258, "percentage": 14.82, "elapsed_time": "2:20:04", "remaining_time": "13:24:47"}
{"current_steps": 500, "total_steps": 3339, "loss": 0.2093, "lr": 3.97031743017021e-05, "epoch": 1.0482686253934943, "percentage": 14.97, "elapsed_time": "2:21:28", "remaining_time": "13:23:18"}
{"current_steps": 505, "total_steps": 3339, "loss": 0.2052, "lr": 3.9684960389333206e-05, "epoch": 1.0587618048268626, "percentage": 15.12, "elapsed_time": "2:22:52", "remaining_time": "13:21:45"}
{"current_steps": 510, "total_steps": 3339, "loss": 0.2151, "lr": 3.966620859825051e-05, "epoch": 1.0692549842602308, "percentage": 15.27, "elapsed_time": "2:24:14", "remaining_time": "13:20:09"}
{"current_steps": 515, "total_steps": 3339, "loss": 0.21, "lr": 3.964691944083448e-05, "epoch": 1.079748163693599, "percentage": 15.42, "elapsed_time": "2:25:38", "remaining_time": "13:18:39"}
{"current_steps": 520, "total_steps": 3339, "loss": 0.2127, "lr": 3.9627093444148766e-05, "epoch": 1.0902413431269675, "percentage": 15.57, "elapsed_time": "2:27:01", "remaining_time": "13:17:02"}
{"current_steps": 525, "total_steps": 3339, "loss": 0.2079, "lr": 3.960673114992581e-05, "epoch": 1.1007345225603358, "percentage": 15.72, "elapsed_time": "2:28:25", "remaining_time": "13:15:31"}
{"current_steps": 530, "total_steps": 3339, "loss": 0.2083, "lr": 3.958583311455203e-05, "epoch": 1.111227701993704, "percentage": 15.87, "elapsed_time": "2:29:49", "remaining_time": "13:14:02"}
{"current_steps": 535, "total_steps": 3339, "loss": 0.2104, "lr": 3.9564399909052626e-05, "epoch": 1.1217208814270725, "percentage": 16.02, "elapsed_time": "2:31:12", "remaining_time": "13:12:31"}
{"current_steps": 540, "total_steps": 3339, "loss": 0.2077, "lr": 3.954243211907596e-05, "epoch": 1.1322140608604407, "percentage": 16.17, "elapsed_time": "2:32:37", "remaining_time": "13:11:04"}
{"current_steps": 545, "total_steps": 3339, "loss": 0.2124, "lr": 3.9519930344877606e-05, "epoch": 1.142707240293809, "percentage": 16.32, "elapsed_time": "2:34:00", "remaining_time": "13:09:33"}
{"current_steps": 550, "total_steps": 3339, "loss": 0.2154, "lr": 3.949689520130384e-05, "epoch": 1.1532004197271772, "percentage": 16.47, "elapsed_time": "2:35:24", "remaining_time": "13:08:05"}
{"current_steps": 555, "total_steps": 3339, "loss": 0.2073, "lr": 3.947332731777498e-05, "epoch": 1.1636935991605457, "percentage": 16.62, "elapsed_time": "2:36:48", "remaining_time": "13:06:33"}
{"current_steps": 560, "total_steps": 3339, "loss": 0.2032, "lr": 3.944922733826806e-05, "epoch": 1.174186778593914, "percentage": 16.77, "elapsed_time": "2:38:11", "remaining_time": "13:05:02"}
{"current_steps": 565, "total_steps": 3339, "loss": 0.2117, "lr": 3.942459592129933e-05, "epoch": 1.1846799580272822, "percentage": 16.92, "elapsed_time": "2:39:34", "remaining_time": "13:03:29"}
{"current_steps": 570, "total_steps": 3339, "loss": 0.2063, "lr": 3.9399433739906195e-05, "epoch": 1.1951731374606505, "percentage": 17.07, "elapsed_time": "2:40:58", "remaining_time": "13:02:01"}
{"current_steps": 575, "total_steps": 3339, "loss": 0.1963, "lr": 3.937374148162888e-05, "epoch": 1.205666316894019, "percentage": 17.22, "elapsed_time": "2:42:21", "remaining_time": "13:00:27"}
{"current_steps": 580, "total_steps": 3339, "loss": 0.2086, "lr": 3.934751984849158e-05, "epoch": 1.2161594963273872, "percentage": 17.37, "elapsed_time": "2:43:44", "remaining_time": "12:58:53"}
{"current_steps": 585, "total_steps": 3339, "loss": 0.2049, "lr": 3.932076955698334e-05, "epoch": 1.2266526757607554, "percentage": 17.52, "elapsed_time": "2:45:07", "remaining_time": "12:57:21"}
{"current_steps": 590, "total_steps": 3339, "loss": 0.2054, "lr": 3.929349133803844e-05, "epoch": 1.237145855194124, "percentage": 17.67, "elapsed_time": "2:46:30", "remaining_time": "12:55:50"}
{"current_steps": 595, "total_steps": 3339, "loss": 0.1986, "lr": 3.926568593701644e-05, "epoch": 1.2476390346274921, "percentage": 17.82, "elapsed_time": "2:47:54", "remaining_time": "12:54:20"}
{"current_steps": 600, "total_steps": 3339, "loss": 0.2041, "lr": 3.9237354113681795e-05, "epoch": 1.2581322140608604, "percentage": 17.97, "elapsed_time": "2:49:17", "remaining_time": "12:52:49"}
{"current_steps": 605, "total_steps": 3339, "loss": 0.2043, "lr": 3.920849664218312e-05, "epoch": 1.2686253934942289, "percentage": 18.12, "elapsed_time": "2:50:41", "remaining_time": "12:51:22"}
{"current_steps": 610, "total_steps": 3339, "loss": 0.2038, "lr": 3.917911431103201e-05, "epoch": 1.2791185729275971, "percentage": 18.27, "elapsed_time": "2:52:05", "remaining_time": "12:49:52"}
{"current_steps": 615, "total_steps": 3339, "loss": 0.2087, "lr": 3.914920792308153e-05, "epoch": 1.2896117523609654, "percentage": 18.42, "elapsed_time": "2:53:29", "remaining_time": "12:48:27"}
{"current_steps": 620, "total_steps": 3339, "loss": 0.2088, "lr": 3.9118778295504224e-05, "epoch": 1.3001049317943336, "percentage": 18.57, "elapsed_time": "2:54:52", "remaining_time": "12:46:55"}
{"current_steps": 625, "total_steps": 3339, "loss": 0.2122, "lr": 3.908782625976984e-05, "epoch": 1.3105981112277019, "percentage": 18.72, "elapsed_time": "2:56:16", "remaining_time": "12:45:27"}
{"current_steps": 630, "total_steps": 3339, "loss": 0.2086, "lr": 3.905635266162258e-05, "epoch": 1.3210912906610703, "percentage": 18.87, "elapsed_time": "2:57:39", "remaining_time": "12:43:57"}
{"current_steps": 635, "total_steps": 3339, "loss": 0.206, "lr": 3.9024358361058e-05, "epoch": 1.3315844700944386, "percentage": 19.02, "elapsed_time": "2:59:03", "remaining_time": "12:42:26"}
{"current_steps": 640, "total_steps": 3339, "loss": 0.2027, "lr": 3.8991844232299526e-05, "epoch": 1.3420776495278068, "percentage": 19.17, "elapsed_time": "3:00:27", "remaining_time": "12:41:00"}
{"current_steps": 645, "total_steps": 3339, "loss": 0.2089, "lr": 3.8958811163774526e-05, "epoch": 1.3525708289611753, "percentage": 19.32, "elapsed_time": "3:01:51", "remaining_time": "12:39:34"}
{"current_steps": 650, "total_steps": 3339, "loss": 0.2011, "lr": 3.892526005809007e-05, "epoch": 1.3630640083945436, "percentage": 19.47, "elapsed_time": "3:03:14", "remaining_time": "12:38:03"}
{"current_steps": 655, "total_steps": 3339, "loss": 0.2038, "lr": 3.8891191832008256e-05, "epoch": 1.3735571878279118, "percentage": 19.62, "elapsed_time": "3:04:38", "remaining_time": "12:36:37"}
{"current_steps": 660, "total_steps": 3339, "loss": 0.209, "lr": 3.885660741642116e-05, "epoch": 1.3840503672612803, "percentage": 19.77, "elapsed_time": "3:06:01", "remaining_time": "12:35:06"}
{"current_steps": 665, "total_steps": 3339, "loss": 0.2093, "lr": 3.882150775632539e-05, "epoch": 1.3945435466946485, "percentage": 19.92, "elapsed_time": "3:07:24", "remaining_time": "12:33:35"}
{"current_steps": 670, "total_steps": 3339, "loss": 0.2036, "lr": 3.87858938107963e-05, "epoch": 1.4050367261280168, "percentage": 20.07, "elapsed_time": "3:08:48", "remaining_time": "12:32:06"}
{"current_steps": 675, "total_steps": 3339, "loss": 0.1979, "lr": 3.8749766552961736e-05, "epoch": 1.415529905561385, "percentage": 20.22, "elapsed_time": "3:10:11", "remaining_time": "12:30:35"}
{"current_steps": 680, "total_steps": 3339, "loss": 0.2041, "lr": 3.871312696997547e-05, "epoch": 1.4260230849947533, "percentage": 20.37, "elapsed_time": "3:11:34", "remaining_time": "12:29:05"}
{"current_steps": 685, "total_steps": 3339, "loss": 0.2037, "lr": 3.867597606299023e-05, "epoch": 1.4365162644281217, "percentage": 20.52, "elapsed_time": "3:12:55", "remaining_time": "12:27:30"}
{"current_steps": 690, "total_steps": 3339, "loss": 0.1972, "lr": 3.863831484713033e-05, "epoch": 1.44700944386149, "percentage": 20.66, "elapsed_time": "3:14:18", "remaining_time": "12:25:59"}
{"current_steps": 695, "total_steps": 3339, "loss": 0.2015, "lr": 3.860014435146397e-05, "epoch": 1.4575026232948582, "percentage": 20.81, "elapsed_time": "3:15:42", "remaining_time": "12:24:32"}
{"current_steps": 700, "total_steps": 3339, "loss": 0.1951, "lr": 3.856146561897505e-05, "epoch": 1.4679958027282267, "percentage": 20.96, "elapsed_time": "3:17:06", "remaining_time": "12:23:07"}
{"current_steps": 705, "total_steps": 3339, "loss": 0.2097, "lr": 3.852227970653473e-05, "epoch": 1.478488982161595, "percentage": 21.11, "elapsed_time": "3:18:29", "remaining_time": "12:21:37"}
{"current_steps": 710, "total_steps": 3339, "loss": 0.1968, "lr": 3.8482587684872536e-05, "epoch": 1.4889821615949632, "percentage": 21.26, "elapsed_time": "3:19:53", "remaining_time": "12:20:09"}
{"current_steps": 715, "total_steps": 3339, "loss": 0.2097, "lr": 3.844239063854709e-05, "epoch": 1.4994753410283317, "percentage": 21.41, "elapsed_time": "3:21:16", "remaining_time": "12:18:39"}
{"current_steps": 720, "total_steps": 3339, "loss": 0.1965, "lr": 3.8401689665916485e-05, "epoch": 1.5099685204617, "percentage": 21.56, "elapsed_time": "3:22:40", "remaining_time": "12:17:13"}
{"current_steps": 725, "total_steps": 3339, "loss": 0.2111, "lr": 3.836048587910828e-05, "epoch": 1.5204616998950682, "percentage": 21.71, "elapsed_time": "3:24:04", "remaining_time": "12:15:47"}
{"current_steps": 730, "total_steps": 3339, "loss": 0.201, "lr": 3.831878040398908e-05, "epoch": 1.5309548793284367, "percentage": 21.86, "elapsed_time": "3:25:29", "remaining_time": "12:14:24"}
{"current_steps": 735, "total_steps": 3339, "loss": 0.2025, "lr": 3.8276574380133826e-05, "epoch": 1.5414480587618047, "percentage": 22.01, "elapsed_time": "3:26:52", "remaining_time": "12:12:56"}
{"current_steps": 740, "total_steps": 3339, "loss": 0.2008, "lr": 3.823386896079462e-05, "epoch": 1.5519412381951732, "percentage": 22.16, "elapsed_time": "3:28:15", "remaining_time": "12:11:27"}
{"current_steps": 745, "total_steps": 3339, "loss": 0.2024, "lr": 3.8190665312869194e-05, "epoch": 1.5624344176285414, "percentage": 22.31, "elapsed_time": "3:29:39", "remaining_time": "12:10:00"}
{"current_steps": 750, "total_steps": 3339, "loss": 0.2052, "lr": 3.814696461686909e-05, "epoch": 1.5729275970619097, "percentage": 22.46, "elapsed_time": "3:31:04", "remaining_time": "12:08:39"}
{"current_steps": 755, "total_steps": 3339, "loss": 0.2014, "lr": 3.8102768066887335e-05, "epoch": 1.5834207764952781, "percentage": 22.61, "elapsed_time": "3:32:29", "remaining_time": "12:07:16"}
{"current_steps": 760, "total_steps": 3339, "loss": 0.1936, "lr": 3.805807687056586e-05, "epoch": 1.5939139559286464, "percentage": 22.76, "elapsed_time": "3:33:52", "remaining_time": "12:05:46"}
{"current_steps": 765, "total_steps": 3339, "loss": 0.2022, "lr": 3.801289224906248e-05, "epoch": 1.6044071353620146, "percentage": 22.91, "elapsed_time": "3:35:16", "remaining_time": "12:04:19"}
{"current_steps": 770, "total_steps": 3339, "loss": 0.1975, "lr": 3.7967215437017514e-05, "epoch": 1.614900314795383, "percentage": 23.06, "elapsed_time": "3:36:41", "remaining_time": "12:02:57"}
{"current_steps": 775, "total_steps": 3339, "loss": 0.2026, "lr": 3.792104768252011e-05, "epoch": 1.6253934942287513, "percentage": 23.21, "elapsed_time": "3:38:05", "remaining_time": "12:01:31"}
{"current_steps": 780, "total_steps": 3339, "loss": 0.1994, "lr": 3.787439024707405e-05, "epoch": 1.6358866736621196, "percentage": 23.36, "elapsed_time": "3:39:29", "remaining_time": "12:00:07"}
{"current_steps": 785, "total_steps": 3339, "loss": 0.2034, "lr": 3.782724440556336e-05, "epoch": 1.646379853095488, "percentage": 23.51, "elapsed_time": "3:40:54", "remaining_time": "11:58:42"}
{"current_steps": 790, "total_steps": 3339, "loss": 0.1927, "lr": 3.7779611446217434e-05, "epoch": 1.656873032528856, "percentage": 23.66, "elapsed_time": "3:42:17", "remaining_time": "11:57:12"}
{"current_steps": 795, "total_steps": 3339, "loss": 0.2028, "lr": 3.7731492670575846e-05, "epoch": 1.6673662119622246, "percentage": 23.81, "elapsed_time": "3:43:40", "remaining_time": "11:55:46"}
{"current_steps": 800, "total_steps": 3339, "loss": 0.2084, "lr": 3.7682889393452775e-05, "epoch": 1.6778593913955928, "percentage": 23.96, "elapsed_time": "3:45:05", "remaining_time": "11:54:22"}
{"current_steps": 805, "total_steps": 3339, "loss": 0.2002, "lr": 3.763380294290109e-05, "epoch": 1.688352570828961, "percentage": 24.11, "elapsed_time": "3:46:29", "remaining_time": "11:52:57"}
{"current_steps": 810, "total_steps": 3339, "loss": 0.1965, "lr": 3.7584234660176074e-05, "epoch": 1.6988457502623295, "percentage": 24.26, "elapsed_time": "3:47:53", "remaining_time": "11:51:31"}
{"current_steps": 815, "total_steps": 3339, "loss": 0.2015, "lr": 3.753418589969874e-05, "epoch": 1.7093389296956978, "percentage": 24.41, "elapsed_time": "3:49:17", "remaining_time": "11:50:06"}
{"current_steps": 820, "total_steps": 3339, "loss": 0.1976, "lr": 3.7483658029018854e-05, "epoch": 1.719832109129066, "percentage": 24.56, "elapsed_time": "3:50:40", "remaining_time": "11:48:38"}
{"current_steps": 825, "total_steps": 3339, "loss": 0.1963, "lr": 3.743265242877756e-05, "epoch": 1.7303252885624345, "percentage": 24.71, "elapsed_time": "3:52:03", "remaining_time": "11:47:08"}
{"current_steps": 830, "total_steps": 3339, "loss": 0.2063, "lr": 3.7381170492669624e-05, "epoch": 1.7408184679958028, "percentage": 24.86, "elapsed_time": "3:53:25", "remaining_time": "11:45:38"}
{"current_steps": 835, "total_steps": 3339, "loss": 0.2027, "lr": 3.732921362740541e-05, "epoch": 1.751311647429171, "percentage": 25.01, "elapsed_time": "3:54:48", "remaining_time": "11:44:09"}
{"current_steps": 840, "total_steps": 3339, "loss": 0.2016, "lr": 3.727678325267241e-05, "epoch": 1.7618048268625395, "percentage": 25.16, "elapsed_time": "3:56:10", "remaining_time": "11:42:37"}
{"current_steps": 845, "total_steps": 3339, "loss": 0.2047, "lr": 3.722388080109643e-05, "epoch": 1.7722980062959075, "percentage": 25.31, "elapsed_time": "3:57:32", "remaining_time": "11:41:06"}
{"current_steps": 850, "total_steps": 3339, "loss": 0.194, "lr": 3.7170507718202494e-05, "epoch": 1.782791185729276, "percentage": 25.46, "elapsed_time": "3:58:55", "remaining_time": "11:39:38"}
{"current_steps": 855, "total_steps": 3339, "loss": 0.2033, "lr": 3.71166654623753e-05, "epoch": 1.7932843651626444, "percentage": 25.61, "elapsed_time": "4:00:19", "remaining_time": "11:38:12"}
{"current_steps": 860, "total_steps": 3339, "loss": 0.197, "lr": 3.70623555048194e-05, "epoch": 1.8037775445960125, "percentage": 25.76, "elapsed_time": "4:01:42", "remaining_time": "11:36:43"}
{"current_steps": 865, "total_steps": 3339, "loss": 0.1897, "lr": 3.700757932951899e-05, "epoch": 1.814270724029381, "percentage": 25.91, "elapsed_time": "4:03:05", "remaining_time": "11:35:15"}
{"current_steps": 870, "total_steps": 3339, "loss": 0.1914, "lr": 3.695233843319737e-05, "epoch": 1.8247639034627492, "percentage": 26.06, "elapsed_time": "4:04:27", "remaining_time": "11:33:44"}
{"current_steps": 875, "total_steps": 3339, "loss": 0.204, "lr": 3.689663432527602e-05, "epoch": 1.8352570828961174, "percentage": 26.21, "elapsed_time": "4:05:51", "remaining_time": "11:32:19"}
{"current_steps": 880, "total_steps": 3339, "loss": 0.1942, "lr": 3.684046852783339e-05, "epoch": 1.845750262329486, "percentage": 26.36, "elapsed_time": "4:07:14", "remaining_time": "11:30:52"}
{"current_steps": 885, "total_steps": 3339, "loss": 0.1938, "lr": 3.67838425755633e-05, "epoch": 1.8562434417628542, "percentage": 26.5, "elapsed_time": "4:08:39", "remaining_time": "11:29:29"}
{"current_steps": 890, "total_steps": 3339, "loss": 0.191, "lr": 3.672675801573298e-05, "epoch": 1.8667366211962224, "percentage": 26.65, "elapsed_time": "4:10:02", "remaining_time": "11:28:03"}
{"current_steps": 895, "total_steps": 3339, "loss": 0.1867, "lr": 3.6669216408140835e-05, "epoch": 1.8772298006295909, "percentage": 26.8, "elapsed_time": "4:11:26", "remaining_time": "11:26:37"}
{"current_steps": 900, "total_steps": 3339, "loss": 0.2065, "lr": 3.661121932507378e-05, "epoch": 1.887722980062959, "percentage": 26.95, "elapsed_time": "4:12:50", "remaining_time": "11:25:11"}
{"current_steps": 905, "total_steps": 3339, "loss": 0.197, "lr": 3.655276835126432e-05, "epoch": 1.8982161594963274, "percentage": 27.1, "elapsed_time": "4:14:14", "remaining_time": "11:23:47"}
{"current_steps": 910, "total_steps": 3339, "loss": 0.1985, "lr": 3.6493865083847226e-05, "epoch": 1.9087093389296959, "percentage": 27.25, "elapsed_time": "4:15:33", "remaining_time": "11:22:09"}
{"current_steps": 915, "total_steps": 3339, "loss": 0.1969, "lr": 3.6434511132315886e-05, "epoch": 1.9192025183630639, "percentage": 27.4, "elapsed_time": "4:16:57", "remaining_time": "11:20:43"}
{"current_steps": 920, "total_steps": 3339, "loss": 0.1957, "lr": 3.637470811847834e-05, "epoch": 1.9296956977964324, "percentage": 27.55, "elapsed_time": "4:18:21", "remaining_time": "11:19:17"}
{"current_steps": 925, "total_steps": 3339, "loss": 0.1945, "lr": 3.631445767641298e-05, "epoch": 1.9401888772298006, "percentage": 27.7, "elapsed_time": "4:19:43", "remaining_time": "11:17:49"}
{"current_steps": 930, "total_steps": 3339, "loss": 0.1995, "lr": 3.625376145242386e-05, "epoch": 1.9506820566631689, "percentage": 27.85, "elapsed_time": "4:21:08", "remaining_time": "11:16:27"}
{"current_steps": 935, "total_steps": 3339, "loss": 0.2035, "lr": 3.619262110499575e-05, "epoch": 1.9611752360965373, "percentage": 28.0, "elapsed_time": "4:22:31", "remaining_time": "11:14:58"}
{"current_steps": 940, "total_steps": 3339, "loss": 0.1964, "lr": 3.6131038304748794e-05, "epoch": 1.9716684155299056, "percentage": 28.15, "elapsed_time": "4:23:54", "remaining_time": "11:13:30"}
{"current_steps": 945, "total_steps": 3339, "loss": 0.205, "lr": 3.6069014734392874e-05, "epoch": 1.9821615949632738, "percentage": 28.3, "elapsed_time": "4:25:17", "remaining_time": "11:12:04"}
{"current_steps": 950, "total_steps": 3339, "loss": 0.1964, "lr": 3.600655208868163e-05, "epoch": 1.9926547743966423, "percentage": 28.45, "elapsed_time": "4:26:38", "remaining_time": "11:10:33"}
{"current_steps": 955, "total_steps": 3339, "loss": 0.1905, "lr": 3.594365207436615e-05, "epoch": 2.0020986358866737, "percentage": 28.6, "elapsed_time": "4:27:54", "remaining_time": "11:08:47"}
{"current_steps": 960, "total_steps": 3339, "loss": 0.1841, "lr": 3.588031641014833e-05, "epoch": 2.012591815320042, "percentage": 28.75, "elapsed_time": "4:29:17", "remaining_time": "11:07:21"}
{"current_steps": 965, "total_steps": 3339, "loss": 0.1863, "lr": 3.5816546826633925e-05, "epoch": 2.02308499475341, "percentage": 28.9, "elapsed_time": "4:30:41", "remaining_time": "11:05:56"}
{"current_steps": 970, "total_steps": 3339, "loss": 0.1797, "lr": 3.575234506628524e-05, "epoch": 2.0335781741867787, "percentage": 29.05, "elapsed_time": "4:32:06", "remaining_time": "11:04:32"}
{"current_steps": 975, "total_steps": 3339, "loss": 0.1827, "lr": 3.568771288337353e-05, "epoch": 2.0440713536201467, "percentage": 29.2, "elapsed_time": "4:33:29", "remaining_time": "11:03:06"}
{"current_steps": 980, "total_steps": 3339, "loss": 0.1853, "lr": 3.562265204393108e-05, "epoch": 2.054564533053515, "percentage": 29.35, "elapsed_time": "4:34:54", "remaining_time": "11:01:45"}
{"current_steps": 985, "total_steps": 3339, "loss": 0.1818, "lr": 3.555716432570293e-05, "epoch": 2.0650577124868836, "percentage": 29.5, "elapsed_time": "4:36:18", "remaining_time": "11:00:19"}
{"current_steps": 990, "total_steps": 3339, "loss": 0.1886, "lr": 3.5491251518098296e-05, "epoch": 2.0755508919202517, "percentage": 29.65, "elapsed_time": "4:37:41", "remaining_time": "10:58:53"}
{"current_steps": 995, "total_steps": 3339, "loss": 0.1843, "lr": 3.542491542214169e-05, "epoch": 2.08604407135362, "percentage": 29.8, "elapsed_time": "4:39:04", "remaining_time": "10:57:25"}
{"current_steps": 1000, "total_steps": 3339, "loss": 0.1822, "lr": 3.535815785042371e-05, "epoch": 2.0965372507869886, "percentage": 29.95, "elapsed_time": "4:40:28", "remaining_time": "10:56:00"}
{"current_steps": 1005, "total_steps": 3339, "loss": 0.1872, "lr": 3.529098062705148e-05, "epoch": 2.1070304302203566, "percentage": 30.1, "elapsed_time": "4:41:50", "remaining_time": "10:54:33"}
{"current_steps": 1010, "total_steps": 3339, "loss": 0.1852, "lr": 3.522338558759886e-05, "epoch": 2.117523609653725, "percentage": 30.25, "elapsed_time": "4:43:15", "remaining_time": "10:53:10"}
{"current_steps": 1015, "total_steps": 3339, "loss": 0.1792, "lr": 3.5155374579056254e-05, "epoch": 2.1280167890870936, "percentage": 30.4, "elapsed_time": "4:44:38", "remaining_time": "10:51:42"}
{"current_steps": 1020, "total_steps": 3339, "loss": 0.181, "lr": 3.508694945978015e-05, "epoch": 2.1385099685204616, "percentage": 30.55, "elapsed_time": "4:46:01", "remaining_time": "10:50:16"}
{"current_steps": 1025, "total_steps": 3339, "loss": 0.179, "lr": 3.501811209944232e-05, "epoch": 2.14900314795383, "percentage": 30.7, "elapsed_time": "4:47:25", "remaining_time": "10:48:51"}
{"current_steps": 1030, "total_steps": 3339, "loss": 0.1888, "lr": 3.494886437897879e-05, "epoch": 2.159496327387198, "percentage": 30.85, "elapsed_time": "4:48:48", "remaining_time": "10:47:26"}
{"current_steps": 1035, "total_steps": 3339, "loss": 0.1923, "lr": 3.4879208190538386e-05, "epoch": 2.1699895068205666, "percentage": 31.0, "elapsed_time": "4:50:12", "remaining_time": "10:46:02"}
{"current_steps": 1040, "total_steps": 3339, "loss": 0.186, "lr": 3.4809145437431065e-05, "epoch": 2.180482686253935, "percentage": 31.15, "elapsed_time": "4:51:36", "remaining_time": "10:44:36"}
{"current_steps": 1045, "total_steps": 3339, "loss": 0.1873, "lr": 3.473867803407589e-05, "epoch": 2.190975865687303, "percentage": 31.3, "elapsed_time": "4:53:05", "remaining_time": "10:43:24"}
{"current_steps": 1050, "total_steps": 3339, "loss": 0.1824, "lr": 3.466780790594875e-05, "epoch": 2.2014690451206715, "percentage": 31.45, "elapsed_time": "4:54:30", "remaining_time": "10:42:00"}
{"current_steps": 1055, "total_steps": 3339, "loss": 0.181, "lr": 3.4596536989529685e-05, "epoch": 2.21196222455404, "percentage": 31.6, "elapsed_time": "4:55:53", "remaining_time": "10:40:34"}
{"current_steps": 1060, "total_steps": 3339, "loss": 0.1819, "lr": 3.452486723225005e-05, "epoch": 2.222455403987408, "percentage": 31.75, "elapsed_time": "4:57:16", "remaining_time": "10:39:09"}
{"current_steps": 1065, "total_steps": 3339, "loss": 0.1906, "lr": 3.445280059243926e-05, "epoch": 2.2329485834207765, "percentage": 31.9, "elapsed_time": "4:58:39", "remaining_time": "10:37:42"}
{"current_steps": 1070, "total_steps": 3339, "loss": 0.1887, "lr": 3.438033903927128e-05, "epoch": 2.243441762854145, "percentage": 32.05, "elapsed_time": "5:00:03", "remaining_time": "10:36:17"}
{"current_steps": 1075, "total_steps": 3339, "loss": 0.1863, "lr": 3.430748455271082e-05, "epoch": 2.253934942287513, "percentage": 32.2, "elapsed_time": "5:01:26", "remaining_time": "10:34:50"}
{"current_steps": 1080, "total_steps": 3339, "loss": 0.1873, "lr": 3.423423912345925e-05, "epoch": 2.2644281217208815, "percentage": 32.35, "elapsed_time": "5:02:50", "remaining_time": "10:33:26"}
{"current_steps": 1085, "total_steps": 3339, "loss": 0.186, "lr": 3.416060475290019e-05, "epoch": 2.27492130115425, "percentage": 32.49, "elapsed_time": "5:04:15", "remaining_time": "10:32:03"}
{"current_steps": 1090, "total_steps": 3339, "loss": 0.1848, "lr": 3.408658345304482e-05, "epoch": 2.285414480587618, "percentage": 32.64, "elapsed_time": "5:05:38", "remaining_time": "10:30:37"}
{"current_steps": 1095, "total_steps": 3339, "loss": 0.1785, "lr": 3.401217724647693e-05, "epoch": 2.2959076600209865, "percentage": 32.79, "elapsed_time": "5:07:01", "remaining_time": "10:29:10"}
{"current_steps": 1100, "total_steps": 3339, "loss": 0.1868, "lr": 3.393738816629761e-05, "epoch": 2.3064008394543545, "percentage": 32.94, "elapsed_time": "5:08:24", "remaining_time": "10:27:45"}
{"current_steps": 1105, "total_steps": 3339, "loss": 0.1809, "lr": 3.386221825606975e-05, "epoch": 2.316894018887723, "percentage": 33.09, "elapsed_time": "5:09:47", "remaining_time": "10:26:18"}
{"current_steps": 1110, "total_steps": 3339, "loss": 0.1852, "lr": 3.378666956976215e-05, "epoch": 2.3273871983210914, "percentage": 33.24, "elapsed_time": "5:11:10", "remaining_time": "10:24:52"}
{"current_steps": 1115, "total_steps": 3339, "loss": 0.1842, "lr": 3.371074417169343e-05, "epoch": 2.3378803777544594, "percentage": 33.39, "elapsed_time": "5:12:34", "remaining_time": "10:23:28"}
{"current_steps": 1120, "total_steps": 3339, "loss": 0.1769, "lr": 3.363444413647561e-05, "epoch": 2.348373557187828, "percentage": 33.54, "elapsed_time": "5:13:58", "remaining_time": "10:22:02"}
{"current_steps": 1125, "total_steps": 3339, "loss": 0.1861, "lr": 3.3557771548957425e-05, "epoch": 2.3588667366211964, "percentage": 33.69, "elapsed_time": "5:15:21", "remaining_time": "10:20:38"}
{"current_steps": 1130, "total_steps": 3339, "loss": 0.182, "lr": 3.348072850416737e-05, "epoch": 2.3693599160545644, "percentage": 33.84, "elapsed_time": "5:16:46", "remaining_time": "10:19:14"}
{"current_steps": 1135, "total_steps": 3339, "loss": 0.1909, "lr": 3.340331710725641e-05, "epoch": 2.379853095487933, "percentage": 33.99, "elapsed_time": "5:18:10", "remaining_time": "10:17:50"}
{"current_steps": 1140, "total_steps": 3339, "loss": 0.1765, "lr": 3.3325539473440546e-05, "epoch": 2.390346274921301, "percentage": 34.14, "elapsed_time": "5:19:32", "remaining_time": "10:16:22"}
{"current_steps": 1145, "total_steps": 3339, "loss": 0.1886, "lr": 3.324739772794292e-05, "epoch": 2.4008394543546694, "percentage": 34.29, "elapsed_time": "5:20:57", "remaining_time": "10:14:59"}
{"current_steps": 1150, "total_steps": 3339, "loss": 0.1783, "lr": 3.316889400593581e-05, "epoch": 2.411332633788038, "percentage": 34.44, "elapsed_time": "5:22:20", "remaining_time": "10:13:34"}
{"current_steps": 1155, "total_steps": 3339, "loss": 0.1764, "lr": 3.309003045248224e-05, "epoch": 2.421825813221406, "percentage": 34.59, "elapsed_time": "5:23:44", "remaining_time": "10:12:09"}
{"current_steps": 1160, "total_steps": 3339, "loss": 0.1782, "lr": 3.301080922247743e-05, "epoch": 2.4323189926547744, "percentage": 34.74, "elapsed_time": "5:25:06", "remaining_time": "10:10:42"}
{"current_steps": 1165, "total_steps": 3339, "loss": 0.1666, "lr": 3.2931232480589853e-05, "epoch": 2.442812172088143, "percentage": 34.89, "elapsed_time": "5:26:30", "remaining_time": "10:09:18"}
{"current_steps": 1170, "total_steps": 3339, "loss": 0.1764, "lr": 3.285130240120212e-05, "epoch": 2.453305351521511, "percentage": 35.04, "elapsed_time": "5:27:55", "remaining_time": "10:07:55"}
{"current_steps": 1175, "total_steps": 3339, "loss": 0.1775, "lr": 3.277102116835157e-05, "epoch": 2.4637985309548793, "percentage": 35.19, "elapsed_time": "5:29:18", "remaining_time": "10:06:30"}
{"current_steps": 1180, "total_steps": 3339, "loss": 0.1837, "lr": 3.2690390975670554e-05, "epoch": 2.474291710388248, "percentage": 35.34, "elapsed_time": "5:30:42", "remaining_time": "10:05:04"}
{"current_steps": 1185, "total_steps": 3339, "loss": 0.1806, "lr": 3.260941402632655e-05, "epoch": 2.484784889821616, "percentage": 35.49, "elapsed_time": "5:32:05", "remaining_time": "10:03:39"}
{"current_steps": 1190, "total_steps": 3339, "loss": 0.1811, "lr": 3.252809253296192e-05, "epoch": 2.4952780692549843, "percentage": 35.64, "elapsed_time": "5:33:30", "remaining_time": "10:02:16"}
{"current_steps": 1195, "total_steps": 3339, "loss": 0.18, "lr": 3.244642871763348e-05, "epoch": 2.5057712486883528, "percentage": 35.79, "elapsed_time": "5:34:54", "remaining_time": "10:00:52"}
{"current_steps": 1200, "total_steps": 3339, "loss": 0.1862, "lr": 3.236442481175176e-05, "epoch": 2.516264428121721, "percentage": 35.94, "elapsed_time": "5:36:18", "remaining_time": "9:59:28"}
{"current_steps": 1205, "total_steps": 3339, "loss": 0.1762, "lr": 3.228208305602004e-05, "epoch": 2.5267576075550893, "percentage": 36.09, "elapsed_time": "5:37:41", "remaining_time": "9:58:02"}
{"current_steps": 1210, "total_steps": 3339, "loss": 0.1819, "lr": 3.219940570037314e-05, "epoch": 2.5372507869884577, "percentage": 36.24, "elapsed_time": "5:39:04", "remaining_time": "9:56:36"}
{"current_steps": 1215, "total_steps": 3339, "loss": 0.1841, "lr": 3.211639500391592e-05, "epoch": 2.5477439664218258, "percentage": 36.39, "elapsed_time": "5:40:27", "remaining_time": "9:55:10"}
{"current_steps": 1220, "total_steps": 3339, "loss": 0.1805, "lr": 3.2033053234861557e-05, "epoch": 2.5582371458551942, "percentage": 36.54, "elapsed_time": "5:41:50", "remaining_time": "9:53:43"}
{"current_steps": 1225, "total_steps": 3339, "loss": 0.1832, "lr": 3.194938267046958e-05, "epoch": 2.5687303252885627, "percentage": 36.69, "elapsed_time": "5:43:14", "remaining_time": "9:52:20"}
{"current_steps": 1230, "total_steps": 3339, "loss": 0.1894, "lr": 3.186538559698364e-05, "epoch": 2.5792235047219307, "percentage": 36.84, "elapsed_time": "5:44:37", "remaining_time": "9:50:53"}
{"current_steps": 1235, "total_steps": 3339, "loss": 0.177, "lr": 3.1781064309569015e-05, "epoch": 2.589716684155299, "percentage": 36.99, "elapsed_time": "5:46:00", "remaining_time": "9:49:29"}
{"current_steps": 1240, "total_steps": 3339, "loss": 0.1898, "lr": 3.1696421112249925e-05, "epoch": 2.6002098635886672, "percentage": 37.14, "elapsed_time": "5:47:24", "remaining_time": "9:48:04"}
{"current_steps": 1245, "total_steps": 3339, "loss": 0.1839, "lr": 3.16114583178466e-05, "epoch": 2.6107030430220357, "percentage": 37.29, "elapsed_time": "5:48:48", "remaining_time": "9:46:39"}
{"current_steps": 1250, "total_steps": 3339, "loss": 0.1818, "lr": 3.1526178247912005e-05, "epoch": 2.6211962224554037, "percentage": 37.44, "elapsed_time": "5:50:12", "remaining_time": "9:45:16"}
{"current_steps": 1255, "total_steps": 3339, "loss": 0.1913, "lr": 3.1440583232668484e-05, "epoch": 2.631689401888772, "percentage": 37.59, "elapsed_time": "5:51:35", "remaining_time": "9:43:51"}
{"current_steps": 1260, "total_steps": 3339, "loss": 0.1876, "lr": 3.1354675610944046e-05, "epoch": 2.6421825813221407, "percentage": 37.74, "elapsed_time": "5:52:57", "remaining_time": "9:42:23"}
{"current_steps": 1265, "total_steps": 3339, "loss": 0.1853, "lr": 3.1268457730108454e-05, "epoch": 2.6526757607555087, "percentage": 37.89, "elapsed_time": "5:54:21", "remaining_time": "9:40:58"}
{"current_steps": 1270, "total_steps": 3339, "loss": 0.1818, "lr": 3.1181931946009125e-05, "epoch": 2.663168940188877, "percentage": 38.04, "elapsed_time": "5:55:44", "remaining_time": "9:39:33"}
{"current_steps": 1275, "total_steps": 3339, "loss": 0.1756, "lr": 3.1095100622906715e-05, "epoch": 2.6736621196222456, "percentage": 38.19, "elapsed_time": "5:57:08", "remaining_time": "9:38:08"}
{"current_steps": 1280, "total_steps": 3339, "loss": 0.1793, "lr": 3.100796613341055e-05, "epoch": 2.6841552990556137, "percentage": 38.33, "elapsed_time": "5:58:32", "remaining_time": "9:36:44"}
{"current_steps": 1285, "total_steps": 3339, "loss": 0.183, "lr": 3.092053085841375e-05, "epoch": 2.694648478488982, "percentage": 38.48, "elapsed_time": "5:59:57", "remaining_time": "9:35:21"}
{"current_steps": 1290, "total_steps": 3339, "loss": 0.1815, "lr": 3.083279718702824e-05, "epoch": 2.7051416579223506, "percentage": 38.63, "elapsed_time": "6:01:19", "remaining_time": "9:33:55"}
{"current_steps": 1295, "total_steps": 3339, "loss": 0.1758, "lr": 3.074476751651941e-05, "epoch": 2.7156348373557186, "percentage": 38.78, "elapsed_time": "6:02:44", "remaining_time": "9:32:32"}
{"current_steps": 1300, "total_steps": 3339, "loss": 0.1792, "lr": 3.065644425224063e-05, "epoch": 2.726128016789087, "percentage": 38.93, "elapsed_time": "6:04:07", "remaining_time": "9:31:07"}
{"current_steps": 1305, "total_steps": 3339, "loss": 0.1811, "lr": 3.056782980756754e-05, "epoch": 2.7366211962224556, "percentage": 39.08, "elapsed_time": "6:05:31", "remaining_time": "9:29:43"}
{"current_steps": 1310, "total_steps": 3339, "loss": 0.1766, "lr": 3.047892660383209e-05, "epoch": 2.7471143756558236, "percentage": 39.23, "elapsed_time": "6:06:56", "remaining_time": "9:28:19"}
{"current_steps": 1315, "total_steps": 3339, "loss": 0.1818, "lr": 3.0389737070256388e-05, "epoch": 2.757607555089192, "percentage": 39.38, "elapsed_time": "6:08:18", "remaining_time": "9:26:53"}
{"current_steps": 1320, "total_steps": 3339, "loss": 0.1792, "lr": 3.0300263643886302e-05, "epoch": 2.7681007345225606, "percentage": 39.53, "elapsed_time": "6:09:43", "remaining_time": "9:25:30"}
{"current_steps": 1325, "total_steps": 3339, "loss": 0.1786, "lr": 3.0210508769524906e-05, "epoch": 2.7785939139559286, "percentage": 39.68, "elapsed_time": "6:11:06", "remaining_time": "9:24:05"}
{"current_steps": 1330, "total_steps": 3339, "loss": 0.1837, "lr": 3.0120474899665643e-05, "epoch": 2.789087093389297, "percentage": 39.83, "elapsed_time": "6:12:30", "remaining_time": "9:22:40"}
{"current_steps": 1335, "total_steps": 3339, "loss": 0.1775, "lr": 3.0030164494425333e-05, "epoch": 2.7995802728226655, "percentage": 39.98, "elapsed_time": "6:13:54", "remaining_time": "9:21:16"}
{"current_steps": 1340, "total_steps": 3339, "loss": 0.1767, "lr": 2.993958002147695e-05, "epoch": 2.8100734522560336, "percentage": 40.13, "elapsed_time": "6:15:18", "remaining_time": "9:19:52"}
{"current_steps": 1345, "total_steps": 3339, "loss": 0.1848, "lr": 2.9848723955982168e-05, "epoch": 2.820566631689402, "percentage": 40.28, "elapsed_time": "6:16:42", "remaining_time": "9:18:29"}
{"current_steps": 1350, "total_steps": 3339, "loss": 0.1834, "lr": 2.9757598780523784e-05, "epoch": 2.83105981112277, "percentage": 40.43, "elapsed_time": "6:18:05", "remaining_time": "9:17:03"}
{"current_steps": 1355, "total_steps": 3339, "loss": 0.1778, "lr": 2.966620698503781e-05, "epoch": 2.8415529905561385, "percentage": 40.58, "elapsed_time": "6:19:26", "remaining_time": "9:15:35"}
{"current_steps": 1360, "total_steps": 3339, "loss": 0.1703, "lr": 2.9574551066745518e-05, "epoch": 2.8520461699895066, "percentage": 40.73, "elapsed_time": "6:20:48", "remaining_time": "9:14:08"}
{"current_steps": 1365, "total_steps": 3339, "loss": 0.1778, "lr": 2.9482633530085122e-05, "epoch": 2.862539349422875, "percentage": 40.88, "elapsed_time": "6:22:13", "remaining_time": "9:12:44"}
{"current_steps": 1370, "total_steps": 3339, "loss": 0.1872, "lr": 2.939045688664342e-05, "epoch": 2.8730325288562435, "percentage": 41.03, "elapsed_time": "6:23:36", "remaining_time": "9:11:20"}
{"current_steps": 1375, "total_steps": 3339, "loss": 0.1806, "lr": 2.929802365508712e-05, "epoch": 2.8835257082896115, "percentage": 41.18, "elapsed_time": "6:25:02", "remaining_time": "9:09:58"}
{"current_steps": 1380, "total_steps": 3339, "loss": 0.1799, "lr": 2.920533636109404e-05, "epoch": 2.89401888772298, "percentage": 41.33, "elapsed_time": "6:26:28", "remaining_time": "9:08:36"}
{"current_steps": 1385, "total_steps": 3339, "loss": 0.179, "lr": 2.911239753728407e-05, "epoch": 2.9045120671563485, "percentage": 41.48, "elapsed_time": "6:27:51", "remaining_time": "9:07:12"}
{"current_steps": 1390, "total_steps": 3339, "loss": 0.1816, "lr": 2.9019209723150008e-05, "epoch": 2.9150052465897165, "percentage": 41.63, "elapsed_time": "6:29:16", "remaining_time": "9:05:49"}
{"current_steps": 1395, "total_steps": 3339, "loss": 0.1846, "lr": 2.8925775464988154e-05, "epoch": 2.925498426023085, "percentage": 41.78, "elapsed_time": "6:30:40", "remaining_time": "9:04:26"}
{"current_steps": 1400, "total_steps": 3339, "loss": 0.1715, "lr": 2.8832097315828706e-05, "epoch": 2.9359916054564534, "percentage": 41.93, "elapsed_time": "6:32:05", "remaining_time": "9:03:03"}
{"current_steps": 1405, "total_steps": 3339, "loss": 0.1801, "lr": 2.873817783536605e-05, "epoch": 2.9464847848898215, "percentage": 42.08, "elapsed_time": "6:33:29", "remaining_time": "9:01:39"}
{"current_steps": 1410, "total_steps": 3339, "loss": 0.183, "lr": 2.8644019589888768e-05, "epoch": 2.95697796432319, "percentage": 42.23, "elapsed_time": "6:34:53", "remaining_time": "9:00:14"}
{"current_steps": 1415, "total_steps": 3339, "loss": 0.18, "lr": 2.854962515220957e-05, "epoch": 2.9674711437565584, "percentage": 42.38, "elapsed_time": "6:36:17", "remaining_time": "8:58:50"}
{"current_steps": 1420, "total_steps": 3339, "loss": 0.1795, "lr": 2.845499710159494e-05, "epoch": 2.9779643231899264, "percentage": 42.53, "elapsed_time": "6:37:38", "remaining_time": "8:57:22"}
{"current_steps": 1425, "total_steps": 3339, "loss": 0.1848, "lr": 2.8360138023694693e-05, "epoch": 2.988457502623295, "percentage": 42.68, "elapsed_time": "6:39:03", "remaining_time": "8:55:59"}
{"current_steps": 1430, "total_steps": 3339, "loss": 0.1833, "lr": 2.826505051047131e-05, "epoch": 2.9989506820566634, "percentage": 42.83, "elapsed_time": "6:40:27", "remaining_time": "8:54:35"}
{"current_steps": 1435, "total_steps": 3339, "loss": 0.1621, "lr": 2.816973716012912e-05, "epoch": 3.0083945435466948, "percentage": 42.98, "elapsed_time": "6:41:43", "remaining_time": "8:53:00"}
{"current_steps": 1440, "total_steps": 3339, "loss": 0.1656, "lr": 2.807420057704331e-05, "epoch": 3.018887722980063, "percentage": 43.13, "elapsed_time": "6:43:06", "remaining_time": "8:51:36"}
{"current_steps": 1445, "total_steps": 3339, "loss": 0.1681, "lr": 2.797844337168874e-05, "epoch": 3.0293809024134313, "percentage": 43.28, "elapsed_time": "6:44:30", "remaining_time": "8:50:11"}
{"current_steps": 1450, "total_steps": 3339, "loss": 0.1675, "lr": 2.7882468160568653e-05, "epoch": 3.0398740818467997, "percentage": 43.43, "elapsed_time": "6:45:54", "remaining_time": "8:48:47"}
{"current_steps": 1455, "total_steps": 3339, "loss": 0.1639, "lr": 2.778627756614314e-05, "epoch": 3.0503672612801678, "percentage": 43.58, "elapsed_time": "6:47:17", "remaining_time": "8:47:23"}
{"current_steps": 1460, "total_steps": 3339, "loss": 0.1672, "lr": 2.768987421675751e-05, "epoch": 3.0608604407135362, "percentage": 43.73, "elapsed_time": "6:48:40", "remaining_time": "8:45:57"}
{"current_steps": 1465, "total_steps": 3339, "loss": 0.1732, "lr": 2.7593260746570448e-05, "epoch": 3.0713536201469047, "percentage": 43.88, "elapsed_time": "6:50:04", "remaining_time": "8:44:33"}
{"current_steps": 1470, "total_steps": 3339, "loss": 0.165, "lr": 2.749643979548207e-05, "epoch": 3.0818467995802727, "percentage": 44.03, "elapsed_time": "6:51:27", "remaining_time": "8:43:07"}
{"current_steps": 1475, "total_steps": 3339, "loss": 0.1706, "lr": 2.7399414009061767e-05, "epoch": 3.092339979013641, "percentage": 44.17, "elapsed_time": "6:52:49", "remaining_time": "8:41:42"}
{"current_steps": 1480, "total_steps": 3339, "loss": 0.1648, "lr": 2.7302186038475915e-05, "epoch": 3.1028331584470092, "percentage": 44.32, "elapsed_time": "6:54:13", "remaining_time": "8:40:18"}
{"current_steps": 1485, "total_steps": 3339, "loss": 0.167, "lr": 2.7204758540415456e-05, "epoch": 3.1133263378803777, "percentage": 44.47, "elapsed_time": "6:55:37", "remaining_time": "8:38:54"}
{"current_steps": 1490, "total_steps": 3339, "loss": 0.1748, "lr": 2.710713417702327e-05, "epoch": 3.123819517313746, "percentage": 44.62, "elapsed_time": "6:57:01", "remaining_time": "8:37:29"}
{"current_steps": 1495, "total_steps": 3339, "loss": 0.1648, "lr": 2.700931561582147e-05, "epoch": 3.134312696747114, "percentage": 44.77, "elapsed_time": "6:58:24", "remaining_time": "8:36:04"}
{"current_steps": 1500, "total_steps": 3339, "loss": 0.1662, "lr": 2.6911305529638482e-05, "epoch": 3.1448058761804827, "percentage": 44.92, "elapsed_time": "6:59:48", "remaining_time": "8:34:40"}
{"current_steps": 1505, "total_steps": 3339, "loss": 0.1712, "lr": 2.681310659653605e-05, "epoch": 3.155299055613851, "percentage": 45.07, "elapsed_time": "7:01:48", "remaining_time": "8:34:01"}
{"current_steps": 1510, "total_steps": 3339, "loss": 0.169, "lr": 2.671472149973602e-05, "epoch": 3.165792235047219, "percentage": 45.22, "elapsed_time": "7:03:11", "remaining_time": "8:32:35"}
{"current_steps": 1515, "total_steps": 3339, "loss": 0.1672, "lr": 2.6616152927547037e-05, "epoch": 3.1762854144805877, "percentage": 45.37, "elapsed_time": "7:04:34", "remaining_time": "8:31:10"}
{"current_steps": 1520, "total_steps": 3339, "loss": 0.1681, "lr": 2.6517403573291112e-05, "epoch": 3.186778593913956, "percentage": 45.52, "elapsed_time": "7:05:57", "remaining_time": "8:29:44"}
{"current_steps": 1525, "total_steps": 3339, "loss": 0.1698, "lr": 2.6418476135229978e-05, "epoch": 3.197271773347324, "percentage": 45.67, "elapsed_time": "7:07:20", "remaining_time": "8:28:20"}
{"current_steps": 1530, "total_steps": 3339, "loss": 0.1689, "lr": 2.6319373316491425e-05, "epoch": 3.2077649527806926, "percentage": 45.82, "elapsed_time": "7:08:43", "remaining_time": "8:26:54"}
{"current_steps": 1535, "total_steps": 3339, "loss": 0.1656, "lr": 2.622009782499537e-05, "epoch": 3.2182581322140607, "percentage": 45.97, "elapsed_time": "7:10:07", "remaining_time": "8:25:30"}
{"current_steps": 1540, "total_steps": 3339, "loss": 0.1798, "lr": 2.6120652373379944e-05, "epoch": 3.228751311647429, "percentage": 46.12, "elapsed_time": "7:11:31", "remaining_time": "8:24:05"}
{"current_steps": 1545, "total_steps": 3339, "loss": 0.1756, "lr": 2.6021039678927275e-05, "epoch": 3.2392444910807976, "percentage": 46.27, "elapsed_time": "7:12:54", "remaining_time": "8:22:40"}
{"current_steps": 1550, "total_steps": 3339, "loss": 0.1644, "lr": 2.592126246348934e-05, "epoch": 3.2497376705141656, "percentage": 46.42, "elapsed_time": "7:14:18", "remaining_time": "8:21:16"}
{"current_steps": 1555, "total_steps": 3339, "loss": 0.1717, "lr": 2.5821323453413517e-05, "epoch": 3.260230849947534, "percentage": 46.57, "elapsed_time": "7:15:43", "remaining_time": "8:19:53"}
{"current_steps": 1560, "total_steps": 3339, "loss": 0.1675, "lr": 2.5721225379468133e-05, "epoch": 3.2707240293809026, "percentage": 46.72, "elapsed_time": "7:17:06", "remaining_time": "8:18:28"}
{"current_steps": 1565, "total_steps": 3339, "loss": 0.1681, "lr": 2.5620970976767816e-05, "epoch": 3.2812172088142706, "percentage": 46.87, "elapsed_time": "7:18:28", "remaining_time": "8:17:02"}
{"current_steps": 1570, "total_steps": 3339, "loss": 0.1721, "lr": 2.5520562984698787e-05, "epoch": 3.291710388247639, "percentage": 47.02, "elapsed_time": "7:19:52", "remaining_time": "8:15:38"}
{"current_steps": 1575, "total_steps": 3339, "loss": 0.1673, "lr": 2.542000414684399e-05, "epoch": 3.3022035676810075, "percentage": 47.17, "elapsed_time": "7:21:17", "remaining_time": "8:14:14"}
{"current_steps": 1580, "total_steps": 3339, "loss": 0.1672, "lr": 2.5319297210908143e-05, "epoch": 3.3126967471143756, "percentage": 47.32, "elapsed_time": "7:22:40", "remaining_time": "8:12:49"}
{"current_steps": 1585, "total_steps": 3339, "loss": 0.1705, "lr": 2.5218444928642633e-05, "epoch": 3.323189926547744, "percentage": 47.47, "elapsed_time": "7:24:03", "remaining_time": "8:11:24"}
{"current_steps": 1590, "total_steps": 3339, "loss": 0.1724, "lr": 2.5117450055770334e-05, "epoch": 3.3336831059811125, "percentage": 47.62, "elapsed_time": "7:25:27", "remaining_time": "8:10:00"}
{"current_steps": 1595, "total_steps": 3339, "loss": 0.1671, "lr": 2.5016315351910355e-05, "epoch": 3.3441762854144805, "percentage": 47.77, "elapsed_time": "7:26:50", "remaining_time": "8:08:34"}
{"current_steps": 1600, "total_steps": 3339, "loss": 0.1695, "lr": 2.4915043580502543e-05, "epoch": 3.354669464847849, "percentage": 47.92, "elapsed_time": "7:28:13", "remaining_time": "8:07:09"}
{"current_steps": 1605, "total_steps": 3339, "loss": 0.1695, "lr": 2.4813637508732068e-05, "epoch": 3.365162644281217, "percentage": 48.07, "elapsed_time": "7:29:36", "remaining_time": "8:05:44"}
{"current_steps": 1610, "total_steps": 3339, "loss": 0.165, "lr": 2.4712099907453756e-05, "epoch": 3.3756558237145855, "percentage": 48.22, "elapsed_time": "7:30:59", "remaining_time": "8:04:19"}
{"current_steps": 1615, "total_steps": 3339, "loss": 0.1601, "lr": 2.4610433551116374e-05, "epoch": 3.386149003147954, "percentage": 48.37, "elapsed_time": "7:32:23", "remaining_time": "8:02:55"}
{"current_steps": 1620, "total_steps": 3339, "loss": 0.1728, "lr": 2.4508641217686868e-05, "epoch": 3.396642182581322, "percentage": 48.52, "elapsed_time": "7:33:47", "remaining_time": "8:01:30"}
{"current_steps": 1625, "total_steps": 3339, "loss": 0.1663, "lr": 2.4406725688574394e-05, "epoch": 3.4071353620146905, "percentage": 48.67, "elapsed_time": "7:35:09", "remaining_time": "8:00:05"}
{"current_steps": 1630, "total_steps": 3339, "loss": 0.1669, "lr": 2.430468974855438e-05, "epoch": 3.417628541448059, "percentage": 48.82, "elapsed_time": "7:36:31", "remaining_time": "7:58:39"}
{"current_steps": 1635, "total_steps": 3339, "loss": 0.1676, "lr": 2.4202536185692386e-05, "epoch": 3.428121720881427, "percentage": 48.97, "elapsed_time": "7:37:55", "remaining_time": "7:57:14"}
{"current_steps": 1640, "total_steps": 3339, "loss": 0.167, "lr": 2.410026779126794e-05, "epoch": 3.4386149003147954, "percentage": 49.12, "elapsed_time": "7:39:18", "remaining_time": "7:55:49"}
{"current_steps": 1645, "total_steps": 3339, "loss": 0.1714, "lr": 2.399788735969827e-05, "epoch": 3.4491080797481635, "percentage": 49.27, "elapsed_time": "7:40:41", "remaining_time": "7:54:25"}
{"current_steps": 1650, "total_steps": 3339, "loss": 0.1674, "lr": 2.3895397688461946e-05, "epoch": 3.459601259181532, "percentage": 49.42, "elapsed_time": "7:42:04", "remaining_time": "7:52:59"}
{"current_steps": 1655, "total_steps": 3339, "loss": 0.165, "lr": 2.379280157802245e-05, "epoch": 3.4700944386149004, "percentage": 49.57, "elapsed_time": "7:43:26", "remaining_time": "7:51:33"}
{"current_steps": 1660, "total_steps": 3339, "loss": 0.1673, "lr": 2.3690101831751627e-05, "epoch": 3.4805876180482684, "percentage": 49.72, "elapsed_time": "7:44:49", "remaining_time": "7:50:09"}
{"current_steps": 1665, "total_steps": 3339, "loss": 0.1671, "lr": 2.3587301255853122e-05, "epoch": 3.491080797481637, "percentage": 49.87, "elapsed_time": "7:46:12", "remaining_time": "7:48:44"}
{"current_steps": 1670, "total_steps": 3339, "loss": 0.1715, "lr": 2.3484402659285666e-05, "epoch": 3.5015739769150054, "percentage": 50.01, "elapsed_time": "7:47:35", "remaining_time": "7:47:18"}
{"current_steps": 1675, "total_steps": 3339, "loss": 0.1677, "lr": 2.3381408853686362e-05, "epoch": 3.5120671563483734, "percentage": 50.16, "elapsed_time": "7:48:58", "remaining_time": "7:45:53"}
{"current_steps": 1680, "total_steps": 3339, "loss": 0.1674, "lr": 2.327832265329381e-05, "epoch": 3.522560335781742, "percentage": 50.31, "elapsed_time": "7:50:21", "remaining_time": "7:44:28"}
{"current_steps": 1685, "total_steps": 3339, "loss": 0.1672, "lr": 2.3175146874871265e-05, "epoch": 3.5330535152151104, "percentage": 50.46, "elapsed_time": "7:51:43", "remaining_time": "7:43:03"}
{"current_steps": 1690, "total_steps": 3339, "loss": 0.1718, "lr": 2.3071884337629638e-05, "epoch": 3.5435466946484784, "percentage": 50.61, "elapsed_time": "7:53:07", "remaining_time": "7:41:38"}
{"current_steps": 1695, "total_steps": 3339, "loss": 0.1635, "lr": 2.296853786315045e-05, "epoch": 3.554039874081847, "percentage": 50.76, "elapsed_time": "7:54:29", "remaining_time": "7:40:12"}
{"current_steps": 1700, "total_steps": 3339, "loss": 0.1701, "lr": 2.2865110275308774e-05, "epoch": 3.5645330535152153, "percentage": 50.91, "elapsed_time": "7:55:52", "remaining_time": "7:38:48"}
{"current_steps": 1705, "total_steps": 3339, "loss": 0.1738, "lr": 2.276160440019603e-05, "epoch": 3.5750262329485833, "percentage": 51.06, "elapsed_time": "7:57:15", "remaining_time": "7:37:23"}
{"current_steps": 1710, "total_steps": 3339, "loss": 0.1658, "lr": 2.2658023066042815e-05, "epoch": 3.585519412381952, "percentage": 51.21, "elapsed_time": "7:58:39", "remaining_time": "7:35:59"}
{"current_steps": 1715, "total_steps": 3339, "loss": 0.1722, "lr": 2.2554369103141566e-05, "epoch": 3.5960125918153203, "percentage": 51.36, "elapsed_time": "8:00:03", "remaining_time": "7:34:34"}
{"current_steps": 1720, "total_steps": 3339, "loss": 0.1661, "lr": 2.2450645343769285e-05, "epoch": 3.6065057712486883, "percentage": 51.51, "elapsed_time": "8:01:27", "remaining_time": "7:33:10"}
{"current_steps": 1725, "total_steps": 3339, "loss": 0.1638, "lr": 2.2346854622110082e-05, "epoch": 3.616998950682057, "percentage": 51.66, "elapsed_time": "8:02:49", "remaining_time": "7:31:45"}
{"current_steps": 1730, "total_steps": 3339, "loss": 0.168, "lr": 2.224299977417779e-05, "epoch": 3.627492130115425, "percentage": 51.81, "elapsed_time": "8:04:11", "remaining_time": "7:30:19"}
{"current_steps": 1735, "total_steps": 3339, "loss": 0.1633, "lr": 2.2139083637738455e-05, "epoch": 3.6379853095487933, "percentage": 51.96, "elapsed_time": "8:05:34", "remaining_time": "7:28:54"}
{"current_steps": 1740, "total_steps": 3339, "loss": 0.1647, "lr": 2.2035109052232768e-05, "epoch": 3.6484784889821618, "percentage": 52.11, "elapsed_time": "8:06:56", "remaining_time": "7:27:29"}
{"current_steps": 1745, "total_steps": 3339, "loss": 0.1679, "lr": 2.1931078858698526e-05, "epoch": 3.65897166841553, "percentage": 52.26, "elapsed_time": "8:08:19", "remaining_time": "7:26:03"}
{"current_steps": 1750, "total_steps": 3339, "loss": 0.1571, "lr": 2.1826995899692968e-05, "epoch": 3.6694648478488983, "percentage": 52.41, "elapsed_time": "8:09:43", "remaining_time": "7:24:40"}
{"current_steps": 1755, "total_steps": 3339, "loss": 0.1715, "lr": 2.1722863019215122e-05, "epoch": 3.6799580272822663, "percentage": 52.56, "elapsed_time": "8:11:07", "remaining_time": "7:23:16"}
{"current_steps": 1760, "total_steps": 3339, "loss": 0.1704, "lr": 2.1618683062628068e-05, "epoch": 3.6904512067156348, "percentage": 52.71, "elapsed_time": "8:12:32", "remaining_time": "7:21:53"}
{"current_steps": 1765, "total_steps": 3339, "loss": 0.1643, "lr": 2.151445887658125e-05, "epoch": 3.7009443861490032, "percentage": 52.86, "elapsed_time": "8:13:55", "remaining_time": "7:20:28"}
{"current_steps": 1770, "total_steps": 3339, "loss": 0.169, "lr": 2.1410193308932602e-05, "epoch": 3.7114375655823713, "percentage": 53.01, "elapsed_time": "8:15:19", "remaining_time": "7:19:04"}
{"current_steps": 1775, "total_steps": 3339, "loss": 0.1715, "lr": 2.1305889208670827e-05, "epoch": 3.7219307450157397, "percentage": 53.16, "elapsed_time": "8:16:41", "remaining_time": "7:17:38"}
{"current_steps": 1780, "total_steps": 3339, "loss": 0.1595, "lr": 2.120154942583748e-05, "epoch": 3.732423924449108, "percentage": 53.31, "elapsed_time": "8:18:04", "remaining_time": "7:16:13"}
{"current_steps": 1785, "total_steps": 3339, "loss": 0.1606, "lr": 2.1097176811449127e-05, "epoch": 3.7429171038824762, "percentage": 53.46, "elapsed_time": "8:19:27", "remaining_time": "7:14:49"}
{"current_steps": 1790, "total_steps": 3339, "loss": 0.1681, "lr": 2.0992774217419445e-05, "epoch": 3.7534102833158447, "percentage": 53.61, "elapsed_time": "8:20:50", "remaining_time": "7:13:24"}
{"current_steps": 1795, "total_steps": 3339, "loss": 0.1633, "lr": 2.088834449648127e-05, "epoch": 3.763903462749213, "percentage": 53.76, "elapsed_time": "8:22:13", "remaining_time": "7:11:59"}
{"current_steps": 1800, "total_steps": 3339, "loss": 0.1695, "lr": 2.0783890502108665e-05, "epoch": 3.774396642182581, "percentage": 53.91, "elapsed_time": "8:23:37", "remaining_time": "7:10:35"}
{"current_steps": 1805, "total_steps": 3339, "loss": 0.1656, "lr": 2.067941508843896e-05, "epoch": 3.7848898216159497, "percentage": 54.06, "elapsed_time": "8:25:01", "remaining_time": "7:09:11"}
{"current_steps": 1810, "total_steps": 3339, "loss": 0.1656, "lr": 2.057492111019474e-05, "epoch": 3.795383001049318, "percentage": 54.21, "elapsed_time": "8:26:24", "remaining_time": "7:07:47"}
{"current_steps": 1815, "total_steps": 3339, "loss": 0.1543, "lr": 2.0470411422605866e-05, "epoch": 3.805876180482686, "percentage": 54.36, "elapsed_time": "8:27:48", "remaining_time": "7:06:23"}
{"current_steps": 1820, "total_steps": 3339, "loss": 0.1643, "lr": 2.0365888881331437e-05, "epoch": 3.8163693599160546, "percentage": 54.51, "elapsed_time": "8:29:11", "remaining_time": "7:04:58"}
{"current_steps": 1825, "total_steps": 3339, "loss": 0.1624, "lr": 2.0261356342381785e-05, "epoch": 3.826862539349423, "percentage": 54.66, "elapsed_time": "8:30:34", "remaining_time": "7:03:34"}
{"current_steps": 1830, "total_steps": 3339, "loss": 0.1631, "lr": 2.01568166620404e-05, "epoch": 3.837355718782791, "percentage": 54.81, "elapsed_time": "8:31:57", "remaining_time": "7:02:09"}
{"current_steps": 1835, "total_steps": 3339, "loss": 0.1643, "lr": 2.0052272696785926e-05, "epoch": 3.8478488982161596, "percentage": 54.96, "elapsed_time": "8:33:21", "remaining_time": "7:00:45"}
{"current_steps": 1840, "total_steps": 3339, "loss": 0.1636, "lr": 1.9947727303214077e-05, "epoch": 3.858342077649528, "percentage": 55.11, "elapsed_time": "8:34:45", "remaining_time": "6:59:21"}
{"current_steps": 1845, "total_steps": 3339, "loss": 0.1662, "lr": 1.9843183337959607e-05, "epoch": 3.868835257082896, "percentage": 55.26, "elapsed_time": "8:36:08", "remaining_time": "6:57:57"}
{"current_steps": 1850, "total_steps": 3339, "loss": 0.1631, "lr": 1.973864365761822e-05, "epoch": 3.8793284365162646, "percentage": 55.41, "elapsed_time": "8:37:32", "remaining_time": "6:56:33"}
{"current_steps": 1855, "total_steps": 3339, "loss": 0.1714, "lr": 1.9634111118668566e-05, "epoch": 3.8898216159496326, "percentage": 55.56, "elapsed_time": "8:38:56", "remaining_time": "6:55:09"}
{"current_steps": 1860, "total_steps": 3339, "loss": 0.1618, "lr": 1.9529588577394138e-05, "epoch": 3.900314795383001, "percentage": 55.71, "elapsed_time": "8:40:20", "remaining_time": "6:53:45"}
{"current_steps": 1865, "total_steps": 3339, "loss": 0.1661, "lr": 1.9425078889805263e-05, "epoch": 3.910807974816369, "percentage": 55.86, "elapsed_time": "8:41:42", "remaining_time": "6:52:19"}
{"current_steps": 1870, "total_steps": 3339, "loss": 0.171, "lr": 1.9320584911561048e-05, "epoch": 3.9213011542497376, "percentage": 56.0, "elapsed_time": "8:43:04", "remaining_time": "6:50:54"}
{"current_steps": 1875, "total_steps": 3339, "loss": 0.1607, "lr": 1.921610949789134e-05, "epoch": 3.931794333683106, "percentage": 56.15, "elapsed_time": "8:44:27", "remaining_time": "6:49:29"}
{"current_steps": 1880, "total_steps": 3339, "loss": 0.1686, "lr": 1.911165550351874e-05, "epoch": 3.942287513116474, "percentage": 56.3, "elapsed_time": "8:45:49", "remaining_time": "6:48:04"}
{"current_steps": 1885, "total_steps": 3339, "loss": 0.1666, "lr": 1.9007225782580562e-05, "epoch": 3.9527806925498425, "percentage": 56.45, "elapsed_time": "8:47:10", "remaining_time": "6:46:38"}
{"current_steps": 1890, "total_steps": 3339, "loss": 0.1613, "lr": 1.8902823188550877e-05, "epoch": 3.963273871983211, "percentage": 56.6, "elapsed_time": "8:48:32", "remaining_time": "6:45:13"}
{"current_steps": 1895, "total_steps": 3339, "loss": 0.1686, "lr": 1.8798450574162526e-05, "epoch": 3.973767051416579, "percentage": 56.75, "elapsed_time": "8:49:54", "remaining_time": "6:43:47"}
{"current_steps": 1900, "total_steps": 3339, "loss": 0.1664, "lr": 1.869411079132918e-05, "epoch": 3.9842602308499475, "percentage": 56.9, "elapsed_time": "8:51:17", "remaining_time": "6:42:23"}
{"current_steps": 1905, "total_steps": 3339, "loss": 0.1651, "lr": 1.85898066910674e-05, "epoch": 3.994753410283316, "percentage": 57.05, "elapsed_time": "8:52:40", "remaining_time": "6:40:58"}
{"current_steps": 1910, "total_steps": 3339, "loss": 0.1653, "lr": 1.848554112341876e-05, "epoch": 4.004197271773347, "percentage": 57.2, "elapsed_time": "8:53:55", "remaining_time": "6:39:27"}
{"current_steps": 1915, "total_steps": 3339, "loss": 0.1595, "lr": 1.8381316937371935e-05, "epoch": 4.014690451206715, "percentage": 57.35, "elapsed_time": "8:55:18", "remaining_time": "6:38:03"}
{"current_steps": 1920, "total_steps": 3339, "loss": 0.1521, "lr": 1.8277136980784888e-05, "epoch": 4.025183630640084, "percentage": 57.5, "elapsed_time": "8:56:41", "remaining_time": "6:36:38"}
{"current_steps": 1925, "total_steps": 3339, "loss": 0.1588, "lr": 1.817300410030704e-05, "epoch": 4.035676810073452, "percentage": 57.65, "elapsed_time": "8:58:04", "remaining_time": "6:35:14"}
{"current_steps": 1930, "total_steps": 3339, "loss": 0.156, "lr": 1.806892114130148e-05, "epoch": 4.04616998950682, "percentage": 57.8, "elapsed_time": "8:59:27", "remaining_time": "6:33:49"}
{"current_steps": 1935, "total_steps": 3339, "loss": 0.1587, "lr": 1.7964890947767242e-05, "epoch": 4.056663168940189, "percentage": 57.95, "elapsed_time": "9:00:51", "remaining_time": "6:32:25"}
{"current_steps": 1940, "total_steps": 3339, "loss": 0.1563, "lr": 1.786091636226156e-05, "epoch": 4.067156348373557, "percentage": 58.1, "elapsed_time": "9:02:13", "remaining_time": "6:31:00"}
{"current_steps": 1945, "total_steps": 3339, "loss": 0.156, "lr": 1.7757000225822216e-05, "epoch": 4.077649527806925, "percentage": 58.25, "elapsed_time": "9:03:36", "remaining_time": "6:29:36"}
{"current_steps": 1950, "total_steps": 3339, "loss": 0.1571, "lr": 1.765314537788993e-05, "epoch": 4.088142707240293, "percentage": 58.4, "elapsed_time": "9:05:00", "remaining_time": "6:28:13"}
{"current_steps": 1955, "total_steps": 3339, "loss": 0.1565, "lr": 1.7549354656230725e-05, "epoch": 4.098635886673662, "percentage": 58.55, "elapsed_time": "9:06:24", "remaining_time": "6:26:48"}
{"current_steps": 1960, "total_steps": 3339, "loss": 0.1597, "lr": 1.744563089685844e-05, "epoch": 4.10912906610703, "percentage": 58.7, "elapsed_time": "9:07:47", "remaining_time": "6:25:24"}
{"current_steps": 1965, "total_steps": 3339, "loss": 0.148, "lr": 1.7341976933957195e-05, "epoch": 4.119622245540398, "percentage": 58.85, "elapsed_time": "9:09:10", "remaining_time": "6:24:00"}
{"current_steps": 1970, "total_steps": 3339, "loss": 0.1556, "lr": 1.723839559980398e-05, "epoch": 4.130115424973767, "percentage": 59.0, "elapsed_time": "9:10:32", "remaining_time": "6:22:35"}
{"current_steps": 1975, "total_steps": 3339, "loss": 0.1526, "lr": 1.713488972469124e-05, "epoch": 4.140608604407135, "percentage": 59.15, "elapsed_time": "9:11:55", "remaining_time": "6:21:10"}
{"current_steps": 1980, "total_steps": 3339, "loss": 0.1557, "lr": 1.7031462136849557e-05, "epoch": 4.151101783840503, "percentage": 59.3, "elapsed_time": "9:13:18", "remaining_time": "6:19:46"}
{"current_steps": 1985, "total_steps": 3339, "loss": 0.1522, "lr": 1.6928115662370372e-05, "epoch": 4.161594963273872, "percentage": 59.45, "elapsed_time": "9:14:41", "remaining_time": "6:18:21"}
{"current_steps": 1990, "total_steps": 3339, "loss": 0.1568, "lr": 1.682485312512874e-05, "epoch": 4.17208814270724, "percentage": 59.6, "elapsed_time": "9:16:04", "remaining_time": "6:16:57"}
{"current_steps": 1995, "total_steps": 3339, "loss": 0.1564, "lr": 1.67216773467062e-05, "epoch": 4.182581322140608, "percentage": 59.75, "elapsed_time": "9:17:26", "remaining_time": "6:15:32"}
{"current_steps": 2000, "total_steps": 3339, "loss": 0.1611, "lr": 1.661859114631365e-05, "epoch": 4.193074501573977, "percentage": 59.9, "elapsed_time": "9:18:50", "remaining_time": "6:14:08"}
{"current_steps": 2005, "total_steps": 3339, "loss": 0.1534, "lr": 1.6515597340714348e-05, "epoch": 4.203567681007345, "percentage": 60.05, "elapsed_time": "9:20:12", "remaining_time": "6:12:43"}
{"current_steps": 2010, "total_steps": 3339, "loss": 0.1534, "lr": 1.641269874414689e-05, "epoch": 4.214060860440713, "percentage": 60.2, "elapsed_time": "9:21:34", "remaining_time": "6:11:18"}
{"current_steps": 2015, "total_steps": 3339, "loss": 0.1623, "lr": 1.6309898168248383e-05, "epoch": 4.224554039874082, "percentage": 60.35, "elapsed_time": "9:22:57", "remaining_time": "6:09:54"}
{"current_steps": 2020, "total_steps": 3339, "loss": 0.1579, "lr": 1.6207198421977558e-05, "epoch": 4.23504721930745, "percentage": 60.5, "elapsed_time": "9:24:21", "remaining_time": "6:08:30"}
{"current_steps": 2025, "total_steps": 3339, "loss": 0.1501, "lr": 1.6104602311538058e-05, "epoch": 4.245540398740818, "percentage": 60.65, "elapsed_time": "9:25:45", "remaining_time": "6:07:06"}
{"current_steps": 2030, "total_steps": 3339, "loss": 0.1597, "lr": 1.6002112640301732e-05, "epoch": 4.256033578174187, "percentage": 60.8, "elapsed_time": "9:27:09", "remaining_time": "6:05:42"}
{"current_steps": 2035, "total_steps": 3339, "loss": 0.1527, "lr": 1.5899732208732066e-05, "epoch": 4.266526757607555, "percentage": 60.95, "elapsed_time": "9:28:32", "remaining_time": "6:04:18"}
{"current_steps": 2040, "total_steps": 3339, "loss": 0.1599, "lr": 1.5797463814307617e-05, "epoch": 4.277019937040923, "percentage": 61.1, "elapsed_time": "9:29:55", "remaining_time": "6:02:54"}
{"current_steps": 2045, "total_steps": 3339, "loss": 0.1584, "lr": 1.5695310251445623e-05, "epoch": 4.287513116474292, "percentage": 61.25, "elapsed_time": "9:31:17", "remaining_time": "6:01:29"}
{"current_steps": 2050, "total_steps": 3339, "loss": 0.1544, "lr": 1.5593274311425606e-05, "epoch": 4.29800629590766, "percentage": 61.4, "elapsed_time": "9:32:40", "remaining_time": "6:00:05"}
{"current_steps": 2055, "total_steps": 3339, "loss": 0.1538, "lr": 1.5491358782313136e-05, "epoch": 4.308499475341028, "percentage": 61.55, "elapsed_time": "9:34:04", "remaining_time": "5:58:41"}
{"current_steps": 2060, "total_steps": 3339, "loss": 0.1548, "lr": 1.5389566448883626e-05, "epoch": 4.318992654774396, "percentage": 61.7, "elapsed_time": "9:35:27", "remaining_time": "5:57:17"}
{"current_steps": 2065, "total_steps": 3339, "loss": 0.1567, "lr": 1.5287900092546247e-05, "epoch": 4.329485834207765, "percentage": 61.84, "elapsed_time": "9:36:48", "remaining_time": "5:55:51"}
{"current_steps": 2070, "total_steps": 3339, "loss": 0.1577, "lr": 1.518636249126793e-05, "epoch": 4.339979013641133, "percentage": 61.99, "elapsed_time": "9:38:12", "remaining_time": "5:54:28"}
{"current_steps": 2075, "total_steps": 3339, "loss": 0.1581, "lr": 1.5084956419497455e-05, "epoch": 4.350472193074501, "percentage": 62.14, "elapsed_time": "9:39:33", "remaining_time": "5:53:02"}
{"current_steps": 2080, "total_steps": 3339, "loss": 0.1524, "lr": 1.498368464808965e-05, "epoch": 4.36096537250787, "percentage": 62.29, "elapsed_time": "9:40:56", "remaining_time": "5:51:38"}
{"current_steps": 2085, "total_steps": 3339, "loss": 0.154, "lr": 1.4882549944229662e-05, "epoch": 4.371458551941238, "percentage": 62.44, "elapsed_time": "9:42:17", "remaining_time": "5:50:13"}
{"current_steps": 2090, "total_steps": 3339, "loss": 0.1577, "lr": 1.4781555071357372e-05, "epoch": 4.381951731374606, "percentage": 62.59, "elapsed_time": "9:43:40", "remaining_time": "5:48:48"}
{"current_steps": 2095, "total_steps": 3339, "loss": 0.1525, "lr": 1.468070278909186e-05, "epoch": 4.392444910807975, "percentage": 62.74, "elapsed_time": "9:45:03", "remaining_time": "5:47:24"}
{"current_steps": 2100, "total_steps": 3339, "loss": 0.1569, "lr": 1.4579995853156008e-05, "epoch": 4.402938090241343, "percentage": 62.89, "elapsed_time": "9:46:26", "remaining_time": "5:46:00"}
{"current_steps": 2105, "total_steps": 3339, "loss": 0.1562, "lr": 1.4479437015301217e-05, "epoch": 4.413431269674711, "percentage": 63.04, "elapsed_time": "9:47:50", "remaining_time": "5:44:36"}
{"current_steps": 2110, "total_steps": 3339, "loss": 0.1569, "lr": 1.4379029023232188e-05, "epoch": 4.42392444910808, "percentage": 63.19, "elapsed_time": "9:49:13", "remaining_time": "5:43:12"}
{"current_steps": 2115, "total_steps": 3339, "loss": 0.1661, "lr": 1.4278774620531875e-05, "epoch": 4.434417628541448, "percentage": 63.34, "elapsed_time": "9:50:35", "remaining_time": "5:41:47"}
{"current_steps": 2120, "total_steps": 3339, "loss": 0.1595, "lr": 1.4178676546586484e-05, "epoch": 4.444910807974816, "percentage": 63.49, "elapsed_time": "9:51:58", "remaining_time": "5:40:23"}
{"current_steps": 2125, "total_steps": 3339, "loss": 0.1564, "lr": 1.407873753651067e-05, "epoch": 4.455403987408185, "percentage": 63.64, "elapsed_time": "9:53:21", "remaining_time": "5:38:59"}
{"current_steps": 2130, "total_steps": 3339, "loss": 0.1533, "lr": 1.3978960321072733e-05, "epoch": 4.465897166841553, "percentage": 63.79, "elapsed_time": "9:54:44", "remaining_time": "5:37:34"}
{"current_steps": 2135, "total_steps": 3339, "loss": 0.1551, "lr": 1.3879347626620066e-05, "epoch": 4.476390346274921, "percentage": 63.94, "elapsed_time": "9:56:07", "remaining_time": "5:36:10"}
{"current_steps": 2140, "total_steps": 3339, "loss": 0.151, "lr": 1.3779902175004634e-05, "epoch": 4.48688352570829, "percentage": 64.09, "elapsed_time": "9:57:30", "remaining_time": "5:34:46"}
{"current_steps": 2145, "total_steps": 3339, "loss": 0.1556, "lr": 1.3680626683508582e-05, "epoch": 4.497376705141658, "percentage": 64.24, "elapsed_time": "9:58:53", "remaining_time": "5:33:22"}
{"current_steps": 2150, "total_steps": 3339, "loss": 0.1518, "lr": 1.3581523864770027e-05, "epoch": 4.507869884575026, "percentage": 64.39, "elapsed_time": "10:00:17", "remaining_time": "5:31:58"}
{"current_steps": 2155, "total_steps": 3339, "loss": 0.1589, "lr": 1.3482596426708896e-05, "epoch": 4.518363064008394, "percentage": 64.54, "elapsed_time": "10:01:38", "remaining_time": "5:30:33"}
{"current_steps": 2160, "total_steps": 3339, "loss": 0.1539, "lr": 1.3383847072452966e-05, "epoch": 4.528856243441763, "percentage": 64.69, "elapsed_time": "10:03:02", "remaining_time": "5:29:09"}
{"current_steps": 2165, "total_steps": 3339, "loss": 0.1518, "lr": 1.3285278500263987e-05, "epoch": 4.539349422875131, "percentage": 64.84, "elapsed_time": "10:04:24", "remaining_time": "5:27:45"}
{"current_steps": 2170, "total_steps": 3339, "loss": 0.1563, "lr": 1.3186893403463954e-05, "epoch": 4.5498426023085, "percentage": 64.99, "elapsed_time": "10:05:47", "remaining_time": "5:26:20"}
{"current_steps": 2175, "total_steps": 3339, "loss": 0.1572, "lr": 1.3088694470361523e-05, "epoch": 4.560335781741868, "percentage": 65.14, "elapsed_time": "10:07:09", "remaining_time": "5:24:56"}
{"current_steps": 2180, "total_steps": 3339, "loss": 0.1595, "lr": 1.2990684384178538e-05, "epoch": 4.570828961175236, "percentage": 65.29, "elapsed_time": "10:08:32", "remaining_time": "5:23:32"}
{"current_steps": 2185, "total_steps": 3339, "loss": 0.16, "lr": 1.289286582297674e-05, "epoch": 4.581322140608604, "percentage": 65.44, "elapsed_time": "10:09:56", "remaining_time": "5:22:08"}
{"current_steps": 2190, "total_steps": 3339, "loss": 0.1583, "lr": 1.279524145958455e-05, "epoch": 4.591815320041973, "percentage": 65.59, "elapsed_time": "10:11:20", "remaining_time": "5:20:44"}
{"current_steps": 2195, "total_steps": 3339, "loss": 0.1604, "lr": 1.2697813961524088e-05, "epoch": 4.602308499475341, "percentage": 65.74, "elapsed_time": "10:12:43", "remaining_time": "5:19:20"}
{"current_steps": 2200, "total_steps": 3339, "loss": 0.1551, "lr": 1.260058599093824e-05, "epoch": 4.612801678908709, "percentage": 65.89, "elapsed_time": "10:14:05", "remaining_time": "5:17:56"}
{"current_steps": 2205, "total_steps": 3339, "loss": 0.1563, "lr": 1.2503560204517937e-05, "epoch": 4.623294858342078, "percentage": 66.04, "elapsed_time": "10:15:28", "remaining_time": "5:16:31"}
{"current_steps": 2210, "total_steps": 3339, "loss": 0.1557, "lr": 1.2406739253429558e-05, "epoch": 4.633788037775446, "percentage": 66.19, "elapsed_time": "10:16:50", "remaining_time": "5:15:07"}
{"current_steps": 2215, "total_steps": 3339, "loss": 0.1485, "lr": 1.2310125783242497e-05, "epoch": 4.644281217208814, "percentage": 66.34, "elapsed_time": "10:18:12", "remaining_time": "5:13:42"}
{"current_steps": 2220, "total_steps": 3339, "loss": 0.156, "lr": 1.2213722433856865e-05, "epoch": 4.654774396642183, "percentage": 66.49, "elapsed_time": "10:19:34", "remaining_time": "5:12:17"}
{"current_steps": 2225, "total_steps": 3339, "loss": 0.1608, "lr": 1.2117531839431349e-05, "epoch": 4.665267576075551, "percentage": 66.64, "elapsed_time": "10:20:57", "remaining_time": "5:10:53"}
{"current_steps": 2230, "total_steps": 3339, "loss": 0.1591, "lr": 1.2021556628311266e-05, "epoch": 4.675760755508919, "percentage": 66.79, "elapsed_time": "10:22:20", "remaining_time": "5:09:30"}
{"current_steps": 2235, "total_steps": 3339, "loss": 0.1543, "lr": 1.19257994229567e-05, "epoch": 4.686253934942288, "percentage": 66.94, "elapsed_time": "10:23:43", "remaining_time": "5:08:05"}
{"current_steps": 2240, "total_steps": 3339, "loss": 0.1554, "lr": 1.183026283987089e-05, "epoch": 4.696747114375656, "percentage": 67.09, "elapsed_time": "10:25:05", "remaining_time": "5:06:41"}
{"current_steps": 2245, "total_steps": 3339, "loss": 0.1562, "lr": 1.17349494895287e-05, "epoch": 4.707240293809024, "percentage": 67.24, "elapsed_time": "10:26:28", "remaining_time": "5:05:17"}
{"current_steps": 2250, "total_steps": 3339, "loss": 0.1585, "lr": 1.1639861976305315e-05, "epoch": 4.717733473242393, "percentage": 67.39, "elapsed_time": "10:27:50", "remaining_time": "5:03:52"}
{"current_steps": 2255, "total_steps": 3339, "loss": 0.1546, "lr": 1.1545002898405064e-05, "epoch": 4.728226652675761, "percentage": 67.54, "elapsed_time": "10:29:13", "remaining_time": "5:02:28"}
{"current_steps": 2260, "total_steps": 3339, "loss": 0.1549, "lr": 1.1450374847790434e-05, "epoch": 4.738719832109129, "percentage": 67.68, "elapsed_time": "10:30:37", "remaining_time": "5:01:04"}
{"current_steps": 2265, "total_steps": 3339, "loss": 0.1557, "lr": 1.1355980410111232e-05, "epoch": 4.749213011542498, "percentage": 67.83, "elapsed_time": "10:32:00", "remaining_time": "4:59:40"}
{"current_steps": 2270, "total_steps": 3339, "loss": 0.1567, "lr": 1.1261822164633962e-05, "epoch": 4.759706190975866, "percentage": 67.98, "elapsed_time": "10:33:22", "remaining_time": "4:58:16"}
{"current_steps": 2275, "total_steps": 3339, "loss": 0.1546, "lr": 1.1167902684171299e-05, "epoch": 4.770199370409234, "percentage": 68.13, "elapsed_time": "10:34:45", "remaining_time": "4:56:52"}
{"current_steps": 2280, "total_steps": 3339, "loss": 0.1538, "lr": 1.1074224535011853e-05, "epoch": 4.780692549842602, "percentage": 68.28, "elapsed_time": "10:36:07", "remaining_time": "4:55:28"}
{"current_steps": 2285, "total_steps": 3339, "loss": 0.1527, "lr": 1.098079027684999e-05, "epoch": 4.791185729275971, "percentage": 68.43, "elapsed_time": "10:37:30", "remaining_time": "4:54:03"}
{"current_steps": 2290, "total_steps": 3339, "loss": 0.1563, "lr": 1.0887602462715931e-05, "epoch": 4.801678908709339, "percentage": 68.58, "elapsed_time": "10:38:53", "remaining_time": "4:52:39"}
{"current_steps": 2295, "total_steps": 3339, "loss": 0.1517, "lr": 1.0794663638905974e-05, "epoch": 4.812172088142708, "percentage": 68.73, "elapsed_time": "10:40:15", "remaining_time": "4:51:15"}
{"current_steps": 2300, "total_steps": 3339, "loss": 0.1528, "lr": 1.0701976344912886e-05, "epoch": 4.822665267576076, "percentage": 68.88, "elapsed_time": "10:41:36", "remaining_time": "4:49:50"}
{"current_steps": 2305, "total_steps": 3339, "loss": 0.1568, "lr": 1.0609543113356585e-05, "epoch": 4.833158447009444, "percentage": 69.03, "elapsed_time": "10:42:59", "remaining_time": "4:48:26"}
{"current_steps": 2310, "total_steps": 3339, "loss": 0.1538, "lr": 1.0517366469914883e-05, "epoch": 4.843651626442812, "percentage": 69.18, "elapsed_time": "10:44:20", "remaining_time": "4:47:01"}
{"current_steps": 2315, "total_steps": 3339, "loss": 0.154, "lr": 1.0425448933254496e-05, "epoch": 4.854144805876181, "percentage": 69.33, "elapsed_time": "10:45:40", "remaining_time": "4:45:36"}
{"current_steps": 2320, "total_steps": 3339, "loss": 0.1488, "lr": 1.0333793014962197e-05, "epoch": 4.864637985309549, "percentage": 69.48, "elapsed_time": "10:47:02", "remaining_time": "4:44:11"}
{"current_steps": 2325, "total_steps": 3339, "loss": 0.1537, "lr": 1.0242401219476226e-05, "epoch": 4.875131164742917, "percentage": 69.63, "elapsed_time": "10:48:24", "remaining_time": "4:42:47"}
{"current_steps": 2330, "total_steps": 3339, "loss": 0.1656, "lr": 1.0151276044017836e-05, "epoch": 4.885624344176286, "percentage": 69.78, "elapsed_time": "10:49:46", "remaining_time": "4:41:23"}
{"current_steps": 2335, "total_steps": 3339, "loss": 0.156, "lr": 1.0060419978523055e-05, "epoch": 4.896117523609654, "percentage": 69.93, "elapsed_time": "10:51:09", "remaining_time": "4:39:58"}
{"current_steps": 2340, "total_steps": 3339, "loss": 0.1558, "lr": 9.969835505574677e-06, "epoch": 4.906610703043022, "percentage": 70.08, "elapsed_time": "10:52:31", "remaining_time": "4:38:34"}
{"current_steps": 2345, "total_steps": 3339, "loss": 0.1487, "lr": 9.879525100334365e-06, "epoch": 4.917103882476391, "percentage": 70.23, "elapsed_time": "10:53:53", "remaining_time": "4:37:10"}
{"current_steps": 2350, "total_steps": 3339, "loss": 0.1568, "lr": 9.789491230475104e-06, "epoch": 4.927597061909759, "percentage": 70.38, "elapsed_time": "10:55:15", "remaining_time": "4:35:46"}
{"current_steps": 2355, "total_steps": 3339, "loss": 0.1622, "lr": 9.699736356113705e-06, "epoch": 4.938090241343127, "percentage": 70.53, "elapsed_time": "10:56:35", "remaining_time": "4:34:20"}
{"current_steps": 2360, "total_steps": 3339, "loss": 0.1539, "lr": 9.610262929743625e-06, "epoch": 4.948583420776496, "percentage": 70.68, "elapsed_time": "10:57:57", "remaining_time": "4:32:56"}
{"current_steps": 2365, "total_steps": 3339, "loss": 0.1489, "lr": 9.521073396167916e-06, "epoch": 4.959076600209864, "percentage": 70.83, "elapsed_time": "10:59:20", "remaining_time": "4:31:32"}
{"current_steps": 2370, "total_steps": 3339, "loss": 0.1617, "lr": 9.432170192432466e-06, "epoch": 4.969569779643232, "percentage": 70.98, "elapsed_time": "11:00:43", "remaining_time": "4:30:08"}
{"current_steps": 2375, "total_steps": 3339, "loss": 0.1512, "lr": 9.343555747759376e-06, "epoch": 4.980062959076601, "percentage": 71.13, "elapsed_time": "11:02:04", "remaining_time": "4:28:43"}
{"current_steps": 2380, "total_steps": 3339, "loss": 0.1511, "lr": 9.255232483480594e-06, "epoch": 4.990556138509969, "percentage": 71.28, "elapsed_time": "11:03:26", "remaining_time": "4:27:19"}
{"current_steps": 2385, "total_steps": 3339, "loss": 0.1436, "lr": 9.167202812971767e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "11:04:41", "remaining_time": "4:25:52"}
{"current_steps": 2390, "total_steps": 3339, "loss": 0.1508, "lr": 9.079469141586255e-06, "epoch": 5.010493179433368, "percentage": 71.58, "elapsed_time": "11:06:04", "remaining_time": "4:24:28"}
{"current_steps": 2395, "total_steps": 3339, "loss": 0.1448, "lr": 8.99203386658946e-06, "epoch": 5.020986358866737, "percentage": 71.73, "elapsed_time": "11:07:26", "remaining_time": "4:23:04"}
{"current_steps": 2400, "total_steps": 3339, "loss": 0.1531, "lr": 8.904899377093289e-06, "epoch": 5.031479538300105, "percentage": 71.88, "elapsed_time": "11:08:47", "remaining_time": "4:21:39"}
{"current_steps": 2405, "total_steps": 3339, "loss": 0.1478, "lr": 8.81806805399088e-06, "epoch": 5.041972717733473, "percentage": 72.03, "elapsed_time": "11:10:08", "remaining_time": "4:20:15"}
{"current_steps": 2410, "total_steps": 3339, "loss": 0.1474, "lr": 8.73154226989155e-06, "epoch": 5.052465897166842, "percentage": 72.18, "elapsed_time": "11:11:28", "remaining_time": "4:18:50"}
{"current_steps": 2415, "total_steps": 3339, "loss": 0.1449, "lr": 8.64532438905596e-06, "epoch": 5.06295907660021, "percentage": 72.33, "elapsed_time": "11:12:50", "remaining_time": "4:17:26"}
{"current_steps": 2420, "total_steps": 3339, "loss": 0.1482, "lr": 8.559416767331514e-06, "epoch": 5.073452256033578, "percentage": 72.48, "elapsed_time": "11:14:13", "remaining_time": "4:16:02"}
{"current_steps": 2425, "total_steps": 3339, "loss": 0.1495, "lr": 8.473821752087998e-06, "epoch": 5.083945435466947, "percentage": 72.63, "elapsed_time": "11:15:35", "remaining_time": "4:14:37"}
{"current_steps": 2430, "total_steps": 3339, "loss": 0.1521, "lr": 8.388541682153403e-06, "epoch": 5.094438614900315, "percentage": 72.78, "elapsed_time": "11:16:56", "remaining_time": "4:13:13"}
{"current_steps": 2435, "total_steps": 3339, "loss": 0.1459, "lr": 8.303578887750073e-06, "epoch": 5.104931794333683, "percentage": 72.93, "elapsed_time": "11:18:18", "remaining_time": "4:11:49"}
{"current_steps": 2440, "total_steps": 3339, "loss": 0.1489, "lr": 8.218935690430991e-06, "epoch": 5.115424973767052, "percentage": 73.08, "elapsed_time": "11:19:39", "remaining_time": "4:10:25"}
{"current_steps": 2445, "total_steps": 3339, "loss": 0.1467, "lr": 8.134614403016364e-06, "epoch": 5.12591815320042, "percentage": 73.23, "elapsed_time": "11:21:01", "remaining_time": "4:09:00"}
{"current_steps": 2450, "total_steps": 3339, "loss": 0.156, "lr": 8.050617329530421e-06, "epoch": 5.136411332633788, "percentage": 73.38, "elapsed_time": "11:22:23", "remaining_time": "4:07:36"}
{"current_steps": 2455, "total_steps": 3339, "loss": 0.1454, "lr": 7.966946765138445e-06, "epoch": 5.146904512067156, "percentage": 73.53, "elapsed_time": "11:23:44", "remaining_time": "4:06:12"}
{"current_steps": 2460, "total_steps": 3339, "loss": 0.1484, "lr": 7.883604996084083e-06, "epoch": 5.157397691500525, "percentage": 73.67, "elapsed_time": "11:25:05", "remaining_time": "4:04:47"}
{"current_steps": 2465, "total_steps": 3339, "loss": 0.1508, "lr": 7.800594299626858e-06, "epoch": 5.167890870933893, "percentage": 73.82, "elapsed_time": "11:26:27", "remaining_time": "4:03:23"}
{"current_steps": 2470, "total_steps": 3339, "loss": 0.1496, "lr": 7.717916943979964e-06, "epoch": 5.178384050367261, "percentage": 73.97, "elapsed_time": "11:27:49", "remaining_time": "4:01:59"}
{"current_steps": 2475, "total_steps": 3339, "loss": 0.1498, "lr": 7.635575188248245e-06, "epoch": 5.18887722980063, "percentage": 74.12, "elapsed_time": "11:29:09", "remaining_time": "4:00:34"}
{"current_steps": 2480, "total_steps": 3339, "loss": 0.1522, "lr": 7.553571282366521e-06, "epoch": 5.199370409233998, "percentage": 74.27, "elapsed_time": "11:30:30", "remaining_time": "3:59:10"}
{"current_steps": 2485, "total_steps": 3339, "loss": 0.146, "lr": 7.47190746703808e-06, "epoch": 5.209863588667366, "percentage": 74.42, "elapsed_time": "11:31:50", "remaining_time": "3:57:45"}
{"current_steps": 2490, "total_steps": 3339, "loss": 0.1433, "lr": 7.390585973673452e-06, "epoch": 5.220356768100735, "percentage": 74.57, "elapsed_time": "11:33:12", "remaining_time": "3:56:21"}
{"current_steps": 2495, "total_steps": 3339, "loss": 0.1477, "lr": 7.309609024329452e-06, "epoch": 5.230849947534103, "percentage": 74.72, "elapsed_time": "11:34:33", "remaining_time": "3:54:57"}
{"current_steps": 2500, "total_steps": 3339, "loss": 0.1523, "lr": 7.2289788316484365e-06, "epoch": 5.241343126967471, "percentage": 74.87, "elapsed_time": "11:35:55", "remaining_time": "3:53:33"}
{"current_steps": 2505, "total_steps": 3339, "loss": 0.1504, "lr": 7.14869759879788e-06, "epoch": 5.25183630640084, "percentage": 75.02, "elapsed_time": "11:37:17", "remaining_time": "3:52:09"}
{"current_steps": 2510, "total_steps": 3339, "loss": 0.1495, "lr": 7.068767519410149e-06, "epoch": 5.262329485834208, "percentage": 75.17, "elapsed_time": "11:38:39", "remaining_time": "3:50:45"}
{"current_steps": 2515, "total_steps": 3339, "loss": 0.1525, "lr": 6.989190777522577e-06, "epoch": 5.272822665267576, "percentage": 75.32, "elapsed_time": "11:40:00", "remaining_time": "3:49:20"}
{"current_steps": 2520, "total_steps": 3339, "loss": 0.1442, "lr": 6.9099695475177655e-06, "epoch": 5.283315844700945, "percentage": 75.47, "elapsed_time": "11:41:21", "remaining_time": "3:47:56"}
{"current_steps": 2525, "total_steps": 3339, "loss": 0.1463, "lr": 6.8311059940641975e-06, "epoch": 5.293809024134313, "percentage": 75.62, "elapsed_time": "11:42:42", "remaining_time": "3:46:32"}
{"current_steps": 2530, "total_steps": 3339, "loss": 0.1554, "lr": 6.752602272057081e-06, "epoch": 5.304302203567681, "percentage": 75.77, "elapsed_time": "11:44:03", "remaining_time": "3:45:08"}
{"current_steps": 2535, "total_steps": 3339, "loss": 0.1458, "lr": 6.674460526559452e-06, "epoch": 5.31479538300105, "percentage": 75.92, "elapsed_time": "11:45:25", "remaining_time": "3:43:44"}
{"current_steps": 2540, "total_steps": 3339, "loss": 0.1401, "lr": 6.596682892743593e-06, "epoch": 5.325288562434418, "percentage": 76.07, "elapsed_time": "11:46:47", "remaining_time": "3:42:20"}
{"current_steps": 2545, "total_steps": 3339, "loss": 0.148, "lr": 6.519271495832642e-06, "epoch": 5.335781741867786, "percentage": 76.22, "elapsed_time": "11:48:09", "remaining_time": "3:40:55"}
{"current_steps": 2550, "total_steps": 3339, "loss": 0.1515, "lr": 6.44222845104258e-06, "epoch": 5.346274921301154, "percentage": 76.37, "elapsed_time": "11:49:31", "remaining_time": "3:39:32"}
{"current_steps": 2555, "total_steps": 3339, "loss": 0.1439, "lr": 6.365555863524395e-06, "epoch": 5.356768100734523, "percentage": 76.52, "elapsed_time": "11:50:52", "remaining_time": "3:38:07"}
{"current_steps": 2560, "total_steps": 3339, "loss": 0.1443, "lr": 6.289255828306573e-06, "epoch": 5.367261280167891, "percentage": 76.67, "elapsed_time": "11:52:13", "remaining_time": "3:36:43"}
{"current_steps": 2565, "total_steps": 3339, "loss": 0.1471, "lr": 6.213330430237856e-06, "epoch": 5.37775445960126, "percentage": 76.82, "elapsed_time": "11:53:35", "remaining_time": "3:35:19"}
{"current_steps": 2570, "total_steps": 3339, "loss": 0.1501, "lr": 6.137781743930256e-06, "epoch": 5.388247639034628, "percentage": 76.97, "elapsed_time": "11:54:56", "remaining_time": "3:33:55"}
{"current_steps": 2575, "total_steps": 3339, "loss": 0.1506, "lr": 6.062611833702392e-06, "epoch": 5.398740818467996, "percentage": 77.12, "elapsed_time": "11:56:18", "remaining_time": "3:32:31"}
{"current_steps": 2580, "total_steps": 3339, "loss": 0.1509, "lr": 5.987822753523076e-06, "epoch": 5.409233997901364, "percentage": 77.27, "elapsed_time": "11:57:40", "remaining_time": "3:31:07"}
{"current_steps": 2585, "total_steps": 3339, "loss": 0.1484, "lr": 5.9134165469551886e-06, "epoch": 5.419727177334733, "percentage": 77.42, "elapsed_time": "11:59:02", "remaining_time": "3:29:43"}
{"current_steps": 2590, "total_steps": 3339, "loss": 0.148, "lr": 5.839395247099819e-06, "epoch": 5.430220356768101, "percentage": 77.57, "elapsed_time": "12:00:24", "remaining_time": "3:28:20"}
{"current_steps": 2595, "total_steps": 3339, "loss": 0.1537, "lr": 5.765760876540756e-06, "epoch": 5.440713536201469, "percentage": 77.72, "elapsed_time": "12:01:46", "remaining_time": "3:26:56"}
{"current_steps": 2600, "total_steps": 3339, "loss": 0.1458, "lr": 5.692515447289184e-06, "epoch": 5.451206715634838, "percentage": 77.87, "elapsed_time": "12:03:09", "remaining_time": "3:25:32"}
{"current_steps": 2605, "total_steps": 3339, "loss": 0.1437, "lr": 5.6196609607287215e-06, "epoch": 5.461699895068206, "percentage": 78.02, "elapsed_time": "12:04:30", "remaining_time": "3:24:08"}
{"current_steps": 2610, "total_steps": 3339, "loss": 0.1493, "lr": 5.5471994075607435e-06, "epoch": 5.472193074501574, "percentage": 78.17, "elapsed_time": "12:05:51", "remaining_time": "3:22:44"}
{"current_steps": 2615, "total_steps": 3339, "loss": 0.1488, "lr": 5.475132767749951e-06, "epoch": 5.482686253934943, "percentage": 78.32, "elapsed_time": "12:07:13", "remaining_time": "3:21:20"}
{"current_steps": 2620, "total_steps": 3339, "loss": 0.1462, "lr": 5.4034630104703204e-06, "epoch": 5.493179433368311, "percentage": 78.47, "elapsed_time": "12:08:35", "remaining_time": "3:19:56"}
{"current_steps": 2625, "total_steps": 3339, "loss": 0.1466, "lr": 5.332192094051256e-06, "epoch": 5.503672612801679, "percentage": 78.62, "elapsed_time": "12:09:56", "remaining_time": "3:18:32"}
{"current_steps": 2630, "total_steps": 3339, "loss": 0.1527, "lr": 5.261321965924114e-06, "epoch": 5.5141657922350475, "percentage": 78.77, "elapsed_time": "12:11:18", "remaining_time": "3:17:08"}
{"current_steps": 2635, "total_steps": 3339, "loss": 0.1432, "lr": 5.190854562568941e-06, "epoch": 5.524658971668416, "percentage": 78.92, "elapsed_time": "12:12:39", "remaining_time": "3:15:44"}
{"current_steps": 2640, "total_steps": 3339, "loss": 0.1457, "lr": 5.120791809461621e-06, "epoch": 5.535152151101784, "percentage": 79.07, "elapsed_time": "12:14:01", "remaining_time": "3:14:20"}
{"current_steps": 2645, "total_steps": 3339, "loss": 0.148, "lr": 5.051135621021217e-06, "epoch": 5.5456453305351525, "percentage": 79.22, "elapsed_time": "12:15:23", "remaining_time": "3:12:57"}
{"current_steps": 2650, "total_steps": 3339, "loss": 0.141, "lr": 4.981887900557685e-06, "epoch": 5.5561385099685205, "percentage": 79.37, "elapsed_time": "12:16:45", "remaining_time": "3:11:33"}
{"current_steps": 2655, "total_steps": 3339, "loss": 0.1449, "lr": 4.913050540219864e-06, "epoch": 5.566631689401889, "percentage": 79.51, "elapsed_time": "12:18:07", "remaining_time": "3:10:09"}
{"current_steps": 2660, "total_steps": 3339, "loss": 0.1397, "lr": 4.844625420943752e-06, "epoch": 5.5771248688352575, "percentage": 79.66, "elapsed_time": "12:19:26", "remaining_time": "3:08:45"}
{"current_steps": 2665, "total_steps": 3339, "loss": 0.1466, "lr": 4.776614412401144e-06, "epoch": 5.5876180482686255, "percentage": 79.81, "elapsed_time": "12:20:46", "remaining_time": "3:07:20"}
{"current_steps": 2670, "total_steps": 3339, "loss": 0.1482, "lr": 4.709019372948524e-06, "epoch": 5.5981112277019935, "percentage": 79.96, "elapsed_time": "12:22:07", "remaining_time": "3:05:56"}
{"current_steps": 2675, "total_steps": 3339, "loss": 0.148, "lr": 4.641842149576303e-06, "epoch": 5.608604407135362, "percentage": 80.11, "elapsed_time": "12:23:29", "remaining_time": "3:04:33"}
{"current_steps": 2680, "total_steps": 3339, "loss": 0.1487, "lr": 4.575084577858318e-06, "epoch": 5.6190975865687305, "percentage": 80.26, "elapsed_time": "12:24:50", "remaining_time": "3:03:09"}
{"current_steps": 2685, "total_steps": 3339, "loss": 0.1455, "lr": 4.50874848190171e-06, "epoch": 5.6295907660020985, "percentage": 80.41, "elapsed_time": "12:26:12", "remaining_time": "3:01:45"}
{"current_steps": 2690, "total_steps": 3339, "loss": 0.1544, "lr": 4.4428356742970744e-06, "epoch": 5.640083945435467, "percentage": 80.56, "elapsed_time": "12:27:34", "remaining_time": "3:00:21"}
{"current_steps": 2695, "total_steps": 3339, "loss": 0.1515, "lr": 4.37734795606892e-06, "epoch": 5.6505771248688355, "percentage": 80.71, "elapsed_time": "12:28:56", "remaining_time": "2:58:58"}
{"current_steps": 2700, "total_steps": 3339, "loss": 0.1445, "lr": 4.312287116626479e-06, "epoch": 5.6610703043022035, "percentage": 80.86, "elapsed_time": "12:30:18", "remaining_time": "2:57:34"}
{"current_steps": 2705, "total_steps": 3339, "loss": 0.1446, "lr": 4.247654933714771e-06, "epoch": 5.6715634837355715, "percentage": 81.01, "elapsed_time": "12:31:40", "remaining_time": "2:56:10"}
{"current_steps": 2710, "total_steps": 3339, "loss": 0.1557, "lr": 4.1834531733660835e-06, "epoch": 5.68205666316894, "percentage": 81.16, "elapsed_time": "12:33:02", "remaining_time": "2:54:47"}
{"current_steps": 2715, "total_steps": 3339, "loss": 0.1509, "lr": 4.119683589851673e-06, "epoch": 5.6925498426023085, "percentage": 81.31, "elapsed_time": "12:34:23", "remaining_time": "2:53:23"}
{"current_steps": 2720, "total_steps": 3339, "loss": 0.1521, "lr": 4.056347925633855e-06, "epoch": 5.7030430220356765, "percentage": 81.46, "elapsed_time": "12:35:45", "remaining_time": "2:51:59"}
{"current_steps": 2725, "total_steps": 3339, "loss": 0.1484, "lr": 3.993447911318378e-06, "epoch": 5.713536201469045, "percentage": 81.61, "elapsed_time": "12:37:07", "remaining_time": "2:50:35"}
{"current_steps": 2730, "total_steps": 3339, "loss": 0.1517, "lr": 3.930985265607135e-06, "epoch": 5.724029380902413, "percentage": 81.76, "elapsed_time": "12:38:29", "remaining_time": "2:49:12"}
{"current_steps": 2735, "total_steps": 3339, "loss": 0.1478, "lr": 3.868961695251212e-06, "epoch": 5.7345225603357814, "percentage": 81.91, "elapsed_time": "12:39:51", "remaining_time": "2:47:48"}
{"current_steps": 2740, "total_steps": 3339, "loss": 0.1493, "lr": 3.8073788950042546e-06, "epoch": 5.74501573976915, "percentage": 82.06, "elapsed_time": "12:41:12", "remaining_time": "2:46:24"}
{"current_steps": 2745, "total_steps": 3339, "loss": 0.1475, "lr": 3.7462385475761463e-06, "epoch": 5.755508919202518, "percentage": 82.21, "elapsed_time": "12:42:34", "remaining_time": "2:45:00"}
{"current_steps": 2750, "total_steps": 3339, "loss": 0.1489, "lr": 3.6855423235870256e-06, "epoch": 5.766002098635886, "percentage": 82.36, "elapsed_time": "12:43:56", "remaining_time": "2:43:37"}
{"current_steps": 2755, "total_steps": 3339, "loss": 0.1511, "lr": 3.625291881521662e-06, "epoch": 5.776495278069255, "percentage": 82.51, "elapsed_time": "12:45:17", "remaining_time": "2:42:13"}
{"current_steps": 2760, "total_steps": 3339, "loss": 0.1464, "lr": 3.5654888676841214e-06, "epoch": 5.786988457502623, "percentage": 82.66, "elapsed_time": "12:46:38", "remaining_time": "2:40:49"}
{"current_steps": 2765, "total_steps": 3339, "loss": 0.1431, "lr": 3.506134916152779e-06, "epoch": 5.797481636935991, "percentage": 82.81, "elapsed_time": "12:48:00", "remaining_time": "2:39:26"}
{"current_steps": 2770, "total_steps": 3339, "loss": 0.152, "lr": 3.4472316487356873e-06, "epoch": 5.807974816369359, "percentage": 82.96, "elapsed_time": "12:49:22", "remaining_time": "2:38:02"}
{"current_steps": 2775, "total_steps": 3339, "loss": 0.1462, "lr": 3.3887806749262285e-06, "epoch": 5.818467995802728, "percentage": 83.11, "elapsed_time": "12:50:44", "remaining_time": "2:36:38"}
{"current_steps": 2780, "total_steps": 3339, "loss": 0.1505, "lr": 3.3307835918591703e-06, "epoch": 5.828961175236096, "percentage": 83.26, "elapsed_time": "12:52:05", "remaining_time": "2:35:15"}
{"current_steps": 2785, "total_steps": 3339, "loss": 0.1518, "lr": 3.273241984267026e-06, "epoch": 5.839454354669465, "percentage": 83.41, "elapsed_time": "12:53:25", "remaining_time": "2:33:51"}
{"current_steps": 2790, "total_steps": 3339, "loss": 0.1432, "lr": 3.2161574244367056e-06, "epoch": 5.849947534102833, "percentage": 83.56, "elapsed_time": "12:54:47", "remaining_time": "2:32:27"}
{"current_steps": 2795, "total_steps": 3339, "loss": 0.1523, "lr": 3.1595314721666103e-06, "epoch": 5.860440713536201, "percentage": 83.71, "elapsed_time": "12:56:08", "remaining_time": "2:31:03"}
{"current_steps": 2800, "total_steps": 3339, "loss": 0.1457, "lr": 3.1033656747239836e-06, "epoch": 5.870933892969569, "percentage": 83.86, "elapsed_time": "12:57:30", "remaining_time": "2:29:40"}
{"current_steps": 2805, "total_steps": 3339, "loss": 0.1434, "lr": 3.0476615668026334e-06, "epoch": 5.881427072402938, "percentage": 84.01, "elapsed_time": "12:58:51", "remaining_time": "2:28:16"}
{"current_steps": 2810, "total_steps": 3339, "loss": 0.1455, "lr": 2.9924206704810153e-06, "epoch": 5.891920251836306, "percentage": 84.16, "elapsed_time": "13:00:12", "remaining_time": "2:26:52"}
{"current_steps": 2815, "total_steps": 3339, "loss": 0.1369, "lr": 2.937644495180607e-06, "epoch": 5.902413431269674, "percentage": 84.31, "elapsed_time": "13:01:34", "remaining_time": "2:25:29"}
{"current_steps": 2820, "total_steps": 3339, "loss": 0.1484, "lr": 2.883334537624707e-06, "epoch": 5.912906610703043, "percentage": 84.46, "elapsed_time": "13:02:54", "remaining_time": "2:24:05"}
{"current_steps": 2825, "total_steps": 3339, "loss": 0.1507, "lr": 2.8294922817975125e-06, "epoch": 5.923399790136411, "percentage": 84.61, "elapsed_time": "13:04:16", "remaining_time": "2:22:41"}
{"current_steps": 2830, "total_steps": 3339, "loss": 0.1451, "lr": 2.7761191989035753e-06, "epoch": 5.933892969569779, "percentage": 84.76, "elapsed_time": "13:05:38", "remaining_time": "2:21:18"}
{"current_steps": 2835, "total_steps": 3339, "loss": 0.1496, "lr": 2.723216747327597e-06, "epoch": 5.944386149003148, "percentage": 84.91, "elapsed_time": "13:07:00", "remaining_time": "2:19:54"}
{"current_steps": 2840, "total_steps": 3339, "loss": 0.1487, "lr": 2.6707863725945913e-06, "epoch": 5.954879328436516, "percentage": 85.06, "elapsed_time": "13:08:23", "remaining_time": "2:18:31"}
{"current_steps": 2845, "total_steps": 3339, "loss": 0.1413, "lr": 2.6188295073303825e-06, "epoch": 5.965372507869884, "percentage": 85.21, "elapsed_time": "13:09:43", "remaining_time": "2:17:07"}
{"current_steps": 2850, "total_steps": 3339, "loss": 0.1487, "lr": 2.5673475712224493e-06, "epoch": 5.975865687303253, "percentage": 85.35, "elapsed_time": "13:11:05", "remaining_time": "2:15:44"}
{"current_steps": 2855, "total_steps": 3339, "loss": 0.1456, "lr": 2.5163419709811487e-06, "epoch": 5.986358866736621, "percentage": 85.5, "elapsed_time": "13:12:27", "remaining_time": "2:14:20"}
{"current_steps": 2860, "total_steps": 3339, "loss": 0.1424, "lr": 2.4658141003012626e-06, "epoch": 5.996852046169989, "percentage": 85.65, "elapsed_time": "13:13:49", "remaining_time": "2:12:57"}
{"current_steps": 2865, "total_steps": 3339, "loss": 0.1425, "lr": 2.415765339823928e-06, "epoch": 6.006295907660021, "percentage": 85.8, "elapsed_time": "13:15:02", "remaining_time": "2:11:32"}
{"current_steps": 2870, "total_steps": 3339, "loss": 0.1441, "lr": 2.366197057098909e-06, "epoch": 6.0167890870933896, "percentage": 85.95, "elapsed_time": "13:16:24", "remaining_time": "2:10:08"}
{"current_steps": 2875, "total_steps": 3339, "loss": 0.1452, "lr": 2.317110606547228e-06, "epoch": 6.027282266526758, "percentage": 86.1, "elapsed_time": "13:17:46", "remaining_time": "2:08:45"}
{"current_steps": 2880, "total_steps": 3339, "loss": 0.1433, "lr": 2.2685073294241587e-06, "epoch": 6.037775445960126, "percentage": 86.25, "elapsed_time": "13:19:08", "remaining_time": "2:07:21"}
{"current_steps": 2885, "total_steps": 3339, "loss": 0.1432, "lr": 2.2203885537825664e-06, "epoch": 6.0482686253934945, "percentage": 86.4, "elapsed_time": "13:20:31", "remaining_time": "2:05:58"}
{"current_steps": 2890, "total_steps": 3339, "loss": 0.1487, "lr": 2.172755594436642e-06, "epoch": 6.0587618048268626, "percentage": 86.55, "elapsed_time": "13:21:52", "remaining_time": "2:04:34"}
{"current_steps": 2895, "total_steps": 3339, "loss": 0.1378, "lr": 2.125609752925952e-06, "epoch": 6.069254984260231, "percentage": 86.7, "elapsed_time": "13:23:13", "remaining_time": "2:03:11"}
{"current_steps": 2900, "total_steps": 3339, "loss": 0.1416, "lr": 2.078952317479899e-06, "epoch": 6.0797481636935995, "percentage": 86.85, "elapsed_time": "13:24:36", "remaining_time": "2:01:48"}
{"current_steps": 2905, "total_steps": 3339, "loss": 0.146, "lr": 2.0327845629824883e-06, "epoch": 6.0902413431269675, "percentage": 87.0, "elapsed_time": "13:25:57", "remaining_time": "2:00:24"}
{"current_steps": 2910, "total_steps": 3339, "loss": 0.1414, "lr": 1.9871077509375316e-06, "epoch": 6.1007345225603355, "percentage": 87.15, "elapsed_time": "13:27:19", "remaining_time": "1:59:01"}
{"current_steps": 2915, "total_steps": 3339, "loss": 0.1424, "lr": 1.9419231294341467e-06, "epoch": 6.1112277019937045, "percentage": 87.3, "elapsed_time": "13:28:40", "remaining_time": "1:57:37"}
{"current_steps": 2920, "total_steps": 3339, "loss": 0.1453, "lr": 1.8972319331126686e-06, "epoch": 6.1217208814270725, "percentage": 87.45, "elapsed_time": "13:30:02", "remaining_time": "1:56:14"}
{"current_steps": 2925, "total_steps": 3339, "loss": 0.1489, "lr": 1.853035383130919e-06, "epoch": 6.1322140608604405, "percentage": 87.6, "elapsed_time": "13:31:25", "remaining_time": "1:54:50"}
{"current_steps": 2930, "total_steps": 3339, "loss": 0.1488, "lr": 1.8093346871308104e-06, "epoch": 6.142707240293809, "percentage": 87.75, "elapsed_time": "13:32:47", "remaining_time": "1:53:27"}
{"current_steps": 2935, "total_steps": 3339, "loss": 0.1451, "lr": 1.7661310392053877e-06, "epoch": 6.1532004197271775, "percentage": 87.9, "elapsed_time": "13:34:09", "remaining_time": "1:52:04"}
{"current_steps": 2940, "total_steps": 3339, "loss": 0.1442, "lr": 1.7234256198661748e-06, "epoch": 6.1636935991605455, "percentage": 88.05, "elapsed_time": "13:35:31", "remaining_time": "1:50:40"}
{"current_steps": 2945, "total_steps": 3339, "loss": 0.1537, "lr": 1.6812195960109257e-06, "epoch": 6.1741867785939135, "percentage": 88.2, "elapsed_time": "13:36:52", "remaining_time": "1:49:17"}
{"current_steps": 2950, "total_steps": 3339, "loss": 0.1447, "lr": 1.6395141208917297e-06, "epoch": 6.184679958027282, "percentage": 88.35, "elapsed_time": "13:38:13", "remaining_time": "1:47:53"}
{"current_steps": 2955, "total_steps": 3339, "loss": 0.141, "lr": 1.5983103340835194e-06, "epoch": 6.1951731374606505, "percentage": 88.5, "elapsed_time": "13:39:37", "remaining_time": "1:46:30"}
{"current_steps": 2960, "total_steps": 3339, "loss": 0.1487, "lr": 1.5576093614529141e-06, "epoch": 6.2056663168940185, "percentage": 88.65, "elapsed_time": "13:41:03", "remaining_time": "1:45:07"}
{"current_steps": 2965, "total_steps": 3339, "loss": 0.1424, "lr": 1.5174123151274668e-06, "epoch": 6.216159496327387, "percentage": 88.8, "elapsed_time": "13:42:33", "remaining_time": "1:43:45"}
{"current_steps": 2970, "total_steps": 3339, "loss": 0.1447, "lr": 1.4777202934652746e-06, "epoch": 6.226652675760755, "percentage": 88.95, "elapsed_time": "13:43:59", "remaining_time": "1:42:22"}
{"current_steps": 2975, "total_steps": 3339, "loss": 0.1432, "lr": 1.4385343810249586e-06, "epoch": 6.2371458551941235, "percentage": 89.1, "elapsed_time": "13:45:26", "remaining_time": "1:40:59"}
{"current_steps": 2980, "total_steps": 3339, "loss": 0.1476, "lr": 1.3998556485360372e-06, "epoch": 6.247639034627492, "percentage": 89.25, "elapsed_time": "13:46:50", "remaining_time": "1:39:36"}
{"current_steps": 2985, "total_steps": 3339, "loss": 0.1428, "lr": 1.3616851528696694e-06, "epoch": 6.25813221406086, "percentage": 89.4, "elapsed_time": "13:48:13", "remaining_time": "1:38:13"}
{"current_steps": 2990, "total_steps": 3339, "loss": 0.1434, "lr": 1.3240239370097752e-06, "epoch": 6.268625393494228, "percentage": 89.55, "elapsed_time": "13:49:35", "remaining_time": "1:36:49"}
{"current_steps": 2995, "total_steps": 3339, "loss": 0.143, "lr": 1.2868730300245357e-06, "epoch": 6.279118572927597, "percentage": 89.7, "elapsed_time": "13:50:59", "remaining_time": "1:35:26"}
{"current_steps": 3000, "total_steps": 3339, "loss": 0.1394, "lr": 1.250233447038267e-06, "epoch": 6.289611752360965, "percentage": 89.85, "elapsed_time": "13:52:26", "remaining_time": "1:34:03"}
{"current_steps": 3005, "total_steps": 3339, "loss": 0.1482, "lr": 1.2141061892037009e-06, "epoch": 6.300104931794333, "percentage": 90.0, "elapsed_time": "13:54:30", "remaining_time": "1:32:45"}
{"current_steps": 3010, "total_steps": 3339, "loss": 0.1499, "lr": 1.1784922436746094e-06, "epoch": 6.310598111227702, "percentage": 90.15, "elapsed_time": "13:55:54", "remaining_time": "1:31:21"}
{"current_steps": 3015, "total_steps": 3339, "loss": 0.1425, "lr": 1.1433925835788484e-06, "epoch": 6.32109129066107, "percentage": 90.3, "elapsed_time": "13:57:18", "remaining_time": "1:29:58"}
{"current_steps": 3020, "total_steps": 3339, "loss": 0.1456, "lr": 1.1088081679917506e-06, "epoch": 6.331584470094438, "percentage": 90.45, "elapsed_time": "13:58:42", "remaining_time": "1:28:35"}
{"current_steps": 3025, "total_steps": 3339, "loss": 0.1448, "lr": 1.0747399419099347e-06, "epoch": 6.342077649527807, "percentage": 90.6, "elapsed_time": "14:00:06", "remaining_time": "1:27:12"}
{"current_steps": 3030, "total_steps": 3339, "loss": 0.144, "lr": 1.0411888362254775e-06, "epoch": 6.352570828961175, "percentage": 90.75, "elapsed_time": "14:01:30", "remaining_time": "1:25:48"}
{"current_steps": 3035, "total_steps": 3339, "loss": 0.1455, "lr": 1.008155767700476e-06, "epoch": 6.363064008394543, "percentage": 90.9, "elapsed_time": "14:02:54", "remaining_time": "1:24:25"}
{"current_steps": 3040, "total_steps": 3339, "loss": 0.1452, "lr": 9.75641638942002e-07, "epoch": 6.373557187827912, "percentage": 91.05, "elapsed_time": "14:04:35", "remaining_time": "1:23:04"}
{"current_steps": 3045, "total_steps": 3339, "loss": 0.1437, "lr": 9.436473383774269e-07, "epoch": 6.38405036726128, "percentage": 91.19, "elapsed_time": "14:06:19", "remaining_time": "1:21:42"}
{"current_steps": 3050, "total_steps": 3339, "loss": 0.1426, "lr": 9.121737402301689e-07, "epoch": 6.394543546694648, "percentage": 91.34, "elapsed_time": "14:07:44", "remaining_time": "1:20:19"}
{"current_steps": 3055, "total_steps": 3339, "loss": 0.1423, "lr": 8.812217044957827e-07, "epoch": 6.405036726128017, "percentage": 91.49, "elapsed_time": "14:09:08", "remaining_time": "1:18:56"}
{"current_steps": 3060, "total_steps": 3339, "loss": 0.1472, "lr": 8.507920769184763e-07, "epoch": 6.415529905561385, "percentage": 91.64, "elapsed_time": "14:10:30", "remaining_time": "1:17:32"}
{"current_steps": 3065, "total_steps": 3339, "loss": 0.1468, "lr": 8.208856889679895e-07, "epoch": 6.426023084994753, "percentage": 91.79, "elapsed_time": "14:11:51", "remaining_time": "1:16:09"}
{"current_steps": 3070, "total_steps": 3339, "loss": 0.1447, "lr": 7.915033578168829e-07, "epoch": 6.436516264428121, "percentage": 91.94, "elapsed_time": "14:13:14", "remaining_time": "1:14:45"}
{"current_steps": 3075, "total_steps": 3339, "loss": 0.1414, "lr": 7.626458863182051e-07, "epoch": 6.44700944386149, "percentage": 92.09, "elapsed_time": "14:14:35", "remaining_time": "1:13:22"}
{"current_steps": 3080, "total_steps": 3339, "loss": 0.1444, "lr": 7.343140629835632e-07, "epoch": 6.457502623294858, "percentage": 92.24, "elapsed_time": "14:15:56", "remaining_time": "1:11:58"}
{"current_steps": 3085, "total_steps": 3339, "loss": 0.1504, "lr": 7.065086619615624e-07, "epoch": 6.467995802728226, "percentage": 92.39, "elapsed_time": "14:17:18", "remaining_time": "1:10:35"}
{"current_steps": 3090, "total_steps": 3339, "loss": 0.1505, "lr": 6.792304430166652e-07, "epoch": 6.478488982161595, "percentage": 92.54, "elapsed_time": "14:18:39", "remaining_time": "1:09:11"}
{"current_steps": 3095, "total_steps": 3339, "loss": 0.1414, "lr": 6.524801515084256e-07, "epoch": 6.488982161594963, "percentage": 92.69, "elapsed_time": "14:20:00", "remaining_time": "1:07:48"}
{"current_steps": 3100, "total_steps": 3339, "loss": 0.145, "lr": 6.262585183711256e-07, "epoch": 6.499475341028331, "percentage": 92.84, "elapsed_time": "14:21:21", "remaining_time": "1:06:24"}
{"current_steps": 3105, "total_steps": 3339, "loss": 0.1449, "lr": 6.005662600938067e-07, "epoch": 6.5099685204617, "percentage": 92.99, "elapsed_time": "14:22:42", "remaining_time": "1:05:00"}
{"current_steps": 3110, "total_steps": 3339, "loss": 0.1393, "lr": 5.754040787006765e-07, "epoch": 6.520461699895068, "percentage": 93.14, "elapsed_time": "14:24:05", "remaining_time": "1:03:37"}
{"current_steps": 3115, "total_steps": 3339, "loss": 0.1337, "lr": 5.507726617319442e-07, "epoch": 6.530954879328436, "percentage": 93.29, "elapsed_time": "14:25:26", "remaining_time": "1:02:14"}
{"current_steps": 3120, "total_steps": 3339, "loss": 0.1405, "lr": 5.266726822250268e-07, "epoch": 6.541448058761805, "percentage": 93.44, "elapsed_time": "14:26:48", "remaining_time": "1:00:50"}
{"current_steps": 3125, "total_steps": 3339, "loss": 0.1424, "lr": 5.031047986961613e-07, "epoch": 6.551941238195173, "percentage": 93.59, "elapsed_time": "14:28:08", "remaining_time": "0:59:27"}
{"current_steps": 3130, "total_steps": 3339, "loss": 0.1376, "lr": 4.800696551224038e-07, "epoch": 6.562434417628541, "percentage": 93.74, "elapsed_time": "14:29:29", "remaining_time": "0:58:03"}
{"current_steps": 3135, "total_steps": 3339, "loss": 0.1396, "lr": 4.575678809240369e-07, "epoch": 6.57292759706191, "percentage": 93.89, "elapsed_time": "14:30:49", "remaining_time": "0:56:39"}
{"current_steps": 3140, "total_steps": 3339, "loss": 0.1465, "lr": 4.35600090947379e-07, "epoch": 6.583420776495278, "percentage": 94.04, "elapsed_time": "14:32:11", "remaining_time": "0:55:16"}
{"current_steps": 3145, "total_steps": 3339, "loss": 0.1404, "lr": 4.141668854479752e-07, "epoch": 6.593913955928646, "percentage": 94.19, "elapsed_time": "14:33:32", "remaining_time": "0:53:53"}
{"current_steps": 3150, "total_steps": 3339, "loss": 0.1419, "lr": 3.9326885007419546e-07, "epoch": 6.604407135362015, "percentage": 94.34, "elapsed_time": "14:34:53", "remaining_time": "0:52:29"}
{"current_steps": 3155, "total_steps": 3339, "loss": 0.1501, "lr": 3.729065558512401e-07, "epoch": 6.614900314795383, "percentage": 94.49, "elapsed_time": "14:36:14", "remaining_time": "0:51:06"}
{"current_steps": 3160, "total_steps": 3339, "loss": 0.1446, "lr": 3.5308055916552395e-07, "epoch": 6.625393494228751, "percentage": 94.64, "elapsed_time": "14:37:36", "remaining_time": "0:49:42"}
{"current_steps": 3165, "total_steps": 3339, "loss": 0.1444, "lr": 3.337914017494903e-07, "epoch": 6.635886673662119, "percentage": 94.79, "elapsed_time": "14:38:57", "remaining_time": "0:48:19"}
{"current_steps": 3170, "total_steps": 3339, "loss": 0.1471, "lr": 3.1503961066679414e-07, "epoch": 6.646379853095488, "percentage": 94.94, "elapsed_time": "14:40:19", "remaining_time": "0:46:55"}
{"current_steps": 3175, "total_steps": 3339, "loss": 0.1415, "lr": 2.968256982979023e-07, "epoch": 6.656873032528856, "percentage": 95.09, "elapsed_time": "14:41:40", "remaining_time": "0:45:32"}
{"current_steps": 3180, "total_steps": 3339, "loss": 0.1426, "lr": 2.7915016232610505e-07, "epoch": 6.667366211962225, "percentage": 95.24, "elapsed_time": "14:43:01", "remaining_time": "0:44:09"}
{"current_steps": 3185, "total_steps": 3339, "loss": 0.1487, "lr": 2.6201348572389764e-07, "epoch": 6.677859391395593, "percentage": 95.39, "elapsed_time": "14:44:23", "remaining_time": "0:42:45"}
{"current_steps": 3190, "total_steps": 3339, "loss": 0.1433, "lr": 2.4541613673980667e-07, "epoch": 6.688352570828961, "percentage": 95.54, "elapsed_time": "14:45:45", "remaining_time": "0:41:22"}
{"current_steps": 3195, "total_steps": 3339, "loss": 0.1424, "lr": 2.2935856888557372e-07, "epoch": 6.698845750262329, "percentage": 95.69, "elapsed_time": "14:47:07", "remaining_time": "0:39:58"}
{"current_steps": 3200, "total_steps": 3339, "loss": 0.1435, "lr": 2.1384122092377391e-07, "epoch": 6.709338929695698, "percentage": 95.84, "elapsed_time": "14:48:29", "remaining_time": "0:38:35"}
{"current_steps": 3205, "total_steps": 3339, "loss": 0.1387, "lr": 1.9886451685582787e-07, "epoch": 6.719832109129066, "percentage": 95.99, "elapsed_time": "14:49:51", "remaining_time": "0:37:12"}
{"current_steps": 3210, "total_steps": 3339, "loss": 0.1449, "lr": 1.8442886591041542e-07, "epoch": 6.730325288562434, "percentage": 96.14, "elapsed_time": "14:51:12", "remaining_time": "0:35:48"}
{"current_steps": 3215, "total_steps": 3339, "loss": 0.1476, "lr": 1.7053466253229123e-07, "epoch": 6.740818467995803, "percentage": 96.29, "elapsed_time": "14:52:34", "remaining_time": "0:34:25"}
{"current_steps": 3220, "total_steps": 3339, "loss": 0.1441, "lr": 1.5718228637150668e-07, "epoch": 6.751311647429171, "percentage": 96.44, "elapsed_time": "14:53:56", "remaining_time": "0:33:02"}
{"current_steps": 3225, "total_steps": 3339, "loss": 0.1389, "lr": 1.44372102273036e-07, "epoch": 6.761804826862539, "percentage": 96.59, "elapsed_time": "14:55:18", "remaining_time": "0:31:38"}
{"current_steps": 3230, "total_steps": 3339, "loss": 0.1505, "lr": 1.3210446026681533e-07, "epoch": 6.772298006295908, "percentage": 96.74, "elapsed_time": "14:56:40", "remaining_time": "0:30:15"}
{"current_steps": 3235, "total_steps": 3339, "loss": 0.1394, "lr": 1.2037969555816597e-07, "epoch": 6.782791185729276, "percentage": 96.89, "elapsed_time": "14:58:01", "remaining_time": "0:28:52"}
{"current_steps": 3240, "total_steps": 3339, "loss": 0.1439, "lr": 1.0919812851864387e-07, "epoch": 6.793284365162644, "percentage": 97.04, "elapsed_time": "14:59:22", "remaining_time": "0:27:28"}
{"current_steps": 3245, "total_steps": 3339, "loss": 0.139, "lr": 9.856006467727775e-08, "epoch": 6.803777544596013, "percentage": 97.18, "elapsed_time": "15:00:44", "remaining_time": "0:26:05"}
{"current_steps": 3250, "total_steps": 3339, "loss": 0.1375, "lr": 8.84657947122336e-08, "epoch": 6.814270724029381, "percentage": 97.33, "elapsed_time": "15:02:06", "remaining_time": "0:24:42"}
{"current_steps": 3255, "total_steps": 3339, "loss": 0.143, "lr": 7.891559444285435e-08, "epoch": 6.824763903462749, "percentage": 97.48, "elapsed_time": "15:03:27", "remaining_time": "0:23:18"}
{"current_steps": 3260, "total_steps": 3339, "loss": 0.1425, "lr": 6.990972482214364e-08, "epoch": 6.835257082896118, "percentage": 97.63, "elapsed_time": "15:04:49", "remaining_time": "0:21:55"}
{"current_steps": 3265, "total_steps": 3339, "loss": 0.1433, "lr": 6.144843192961825e-08, "epoch": 6.845750262329486, "percentage": 97.78, "elapsed_time": "15:06:09", "remaining_time": "0:20:32"}
{"current_steps": 3270, "total_steps": 3339, "loss": 0.1492, "lr": 5.3531946964588966e-08, "epoch": 6.856243441762854, "percentage": 97.93, "elapsed_time": "15:07:31", "remaining_time": "0:19:08"}
{"current_steps": 3275, "total_steps": 3339, "loss": 0.1413, "lr": 4.616048623985236e-08, "epoch": 6.866736621196223, "percentage": 98.08, "elapsed_time": "15:08:50", "remaining_time": "0:17:45"}
{"current_steps": 3280, "total_steps": 3339, "loss": 0.1411, "lr": 3.9334251175764396e-08, "epoch": 6.877229800629591, "percentage": 98.23, "elapsed_time": "15:10:11", "remaining_time": "0:16:22"}
{"current_steps": 3285, "total_steps": 3339, "loss": 0.141, "lr": 3.305342829475589e-08, "epoch": 6.887722980062959, "percentage": 98.38, "elapsed_time": "15:11:32", "remaining_time": "0:14:59"}
{"current_steps": 3290, "total_steps": 3339, "loss": 0.1428, "lr": 2.7318189216212208e-08, "epoch": 6.898216159496327, "percentage": 98.53, "elapsed_time": "15:12:53", "remaining_time": "0:13:35"}
{"current_steps": 3295, "total_steps": 3339, "loss": 0.1419, "lr": 2.2128690651808115e-08, "epoch": 6.908709338929696, "percentage": 98.68, "elapsed_time": "15:14:16", "remaining_time": "0:12:12"}
{"current_steps": 3300, "total_steps": 3339, "loss": 0.1415, "lr": 1.7485074401206725e-08, "epoch": 6.919202518363064, "percentage": 98.83, "elapsed_time": "15:15:37", "remaining_time": "0:10:49"}
{"current_steps": 3305, "total_steps": 3339, "loss": 0.1427, "lr": 1.3387467348195959e-08, "epoch": 6.929695697796433, "percentage": 98.98, "elapsed_time": "15:16:59", "remaining_time": "0:09:26"}
{"current_steps": 3310, "total_steps": 3339, "loss": 0.1452, "lr": 9.835981457222421e-09, "epoch": 6.940188877229801, "percentage": 99.13, "elapsed_time": "15:18:21", "remaining_time": "0:08:02"}
{"current_steps": 3315, "total_steps": 3339, "loss": 0.1412, "lr": 6.830713770318298e-09, "epoch": 6.950682056663169, "percentage": 99.28, "elapsed_time": "15:19:43", "remaining_time": "0:06:39"}
{"current_steps": 3320, "total_steps": 3339, "loss": 0.1427, "lr": 4.371746404467914e-09, "epoch": 6.961175236096537, "percentage": 99.43, "elapsed_time": "15:21:04", "remaining_time": "0:05:16"}
{"current_steps": 3325, "total_steps": 3339, "loss": 0.1407, "lr": 2.4591465493495336e-09, "epoch": 6.971668415529906, "percentage": 99.58, "elapsed_time": "15:22:25", "remaining_time": "0:03:53"}
{"current_steps": 3330, "total_steps": 3339, "loss": 0.1453, "lr": 1.092966465510159e-09, "epoch": 6.982161594963274, "percentage": 99.73, "elapsed_time": "15:23:46", "remaining_time": "0:02:29"}
{"current_steps": 3335, "total_steps": 3339, "loss": 0.1466, "lr": 2.732434829266772e-10, "epoch": 6.992654774396642, "percentage": 99.88, "elapsed_time": "15:25:07", "remaining_time": "0:01:06"}
{"current_steps": 3339, "total_steps": 3339, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "15:26:44", "remaining_time": "0:00:00"}

7384
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:bb612f056b634ae0e64fff52f03872fbf16575f18da6d9ffc056ab97ac256cd0
size 8593

BIN
training_loss.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 38 KiB

BIN
vocab.json (Stored with Git LFS) Normal file

Binary file not shown.