初始化项目,由ModelHub XC社区提供模型

Model: laion/exp-uns-tezos-10x_glm_4_7_traces_jupiter_cleaned
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-09 20:24:53 +08:00
commit 5ad328da1b
23 changed files with 163199 additions and 0 deletions

36
.gitattributes vendored Normal file
View File

@@ -0,0 +1,36 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

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: exp-uns-tezos-10x_glm_4_7_traces_jupiter_cleaned
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. -->
# exp-uns-tezos-10x_glm_4_7_traces_jupiter_cleaned
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--DCAgent--exp-uns-tezos-10x_glm_4.7_traces_jupiter_cleaned/snapshots/2864d3bb974be2af999add0fb2c482c3605afc27_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": 3.5085839993463646,
"achieved_tflops_per_gpu_theoretical": 379.4453110361948,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.11891636997461319,
"mfu_percent": 0.35476076838689224,
"mfu_percent_theoretical": 38.36656329991859,
"total_flos": 1.1243312580845896e+18,
"train_loss": 0.34437558135542856,
"train_runtime": 40056.4465,
"train_samples_per_second": 1.785,
"train_steps_per_second": 0.112,
"valid_targets_mean": 3517.0,
"valid_targets_min": 1483
}

89
chat_template.jinja Normal file
View File

@@ -0,0 +1,89 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if message.content is string %}
{%- set content = message.content %}
{%- else %}
{%- set content = '' %}
{%- endif %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in content %}
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and reasoning_content) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}

68
config.json Normal file
View File

@@ -0,0 +1,68 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "4.57.6",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

12
generation_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "4.57.6"
}

151388
merges.txt Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2ff7469e72be91085308c6847852d22000eb13a92711d3871d0779fcdfd3f334
size 4902257696

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aa44bc2f08e92f0cc70f6f09e24b88ccb69821932e20bfd42095224d5ecbafe2
size 4915960368

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:18f7a0ca2a7664c721903cbd1942daf449bf975753465c19342c14912c0f8d86
size 4983068496

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b5db9ce35b614614c3de749ed8e97fed2a0100bc7ef85330f248577ceb94c7d0
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": "2864d3bb974be2af999add0fb2c482c3605afc27_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--DCAgent--exp-uns-tezos-10x_glm_4.7_traces_jupiter_cleaned/snapshots/2864d3bb974be2af999add0fb2c482c3605afc27_thinking_preprocessed",
"training_type": "SFT",
"training_parameters": "https://huggingface.co/laion/exp-uns-tezos-10x_glm_4_7_traces_jupiter_cleaned/blob/main/config.json",
"wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/sft_exp-uns-tezos-10x_glm_4-7_traces_jupiter_cleaned_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": 3.5085839993463646,
"achieved_tflops_per_gpu_theoretical": 379.4453110361948,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.11891636997461319,
"mfu_percent": 0.35476076838689224,
"mfu_percent_theoretical": 38.36656329991859,
"total_flos": 1.1243312580845896e+18,
"train_loss": 0.34437558135542856,
"train_runtime": 40056.4465,
"train_samples_per_second": 1.785,
"train_steps_per_second": 0.112,
"valid_targets_mean": 3517.0,
"valid_targets_min": 1483
}

895
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,895 @@
{"current_steps": 5, "total_steps": 4473, "loss": 0.8512, "lr": 3.5714285714285716e-07, "epoch": 0.00782472613458529, "percentage": 0.11, "elapsed_time": "0:01:09", "remaining_time": "17:19:07"}
{"current_steps": 10, "total_steps": 4473, "loss": 0.9841, "lr": 8.035714285714287e-07, "epoch": 0.01564945226917058, "percentage": 0.22, "elapsed_time": "0:01:54", "remaining_time": "14:14:17"}
{"current_steps": 15, "total_steps": 4473, "loss": 0.9025, "lr": 1.25e-06, "epoch": 0.023474178403755867, "percentage": 0.34, "elapsed_time": "0:02:42", "remaining_time": "13:24:31"}
{"current_steps": 20, "total_steps": 4473, "loss": 0.8985, "lr": 1.6964285714285717e-06, "epoch": 0.03129890453834116, "percentage": 0.45, "elapsed_time": "0:03:19", "remaining_time": "12:20:59"}
{"current_steps": 25, "total_steps": 4473, "loss": 0.8522, "lr": 2.1428571428571427e-06, "epoch": 0.03912363067292645, "percentage": 0.56, "elapsed_time": "0:04:13", "remaining_time": "12:32:11"}
{"current_steps": 30, "total_steps": 4473, "loss": 0.7623, "lr": 2.5892857142857148e-06, "epoch": 0.046948356807511735, "percentage": 0.67, "elapsed_time": "0:05:01", "remaining_time": "12:23:54"}
{"current_steps": 35, "total_steps": 4473, "loss": 0.7298, "lr": 3.0357142857142856e-06, "epoch": 0.054773082942097026, "percentage": 0.78, "elapsed_time": "0:05:39", "remaining_time": "11:57:12"}
{"current_steps": 40, "total_steps": 4473, "loss": 0.637, "lr": 3.482142857142857e-06, "epoch": 0.06259780907668232, "percentage": 0.89, "elapsed_time": "0:06:29", "remaining_time": "11:59:37"}
{"current_steps": 45, "total_steps": 4473, "loss": 0.6746, "lr": 3.928571428571429e-06, "epoch": 0.07042253521126761, "percentage": 1.01, "elapsed_time": "0:07:24", "remaining_time": "12:09:22"}
{"current_steps": 50, "total_steps": 4473, "loss": 0.6594, "lr": 4.3750000000000005e-06, "epoch": 0.0782472613458529, "percentage": 1.12, "elapsed_time": "0:08:04", "remaining_time": "11:54:03"}
{"current_steps": 55, "total_steps": 4473, "loss": 0.6574, "lr": 4.821428571428572e-06, "epoch": 0.08607198748043818, "percentage": 1.23, "elapsed_time": "0:09:02", "remaining_time": "12:06:53"}
{"current_steps": 60, "total_steps": 4473, "loss": 0.6602, "lr": 5.267857142857144e-06, "epoch": 0.09389671361502347, "percentage": 1.34, "elapsed_time": "0:09:38", "remaining_time": "11:49:21"}
{"current_steps": 65, "total_steps": 4473, "loss": 0.6166, "lr": 5.7142857142857145e-06, "epoch": 0.10172143974960876, "percentage": 1.45, "elapsed_time": "0:10:17", "remaining_time": "11:37:22"}
{"current_steps": 70, "total_steps": 4473, "loss": 0.63, "lr": 6.160714285714286e-06, "epoch": 0.10954616588419405, "percentage": 1.56, "elapsed_time": "0:11:04", "remaining_time": "11:37:00"}
{"current_steps": 75, "total_steps": 4473, "loss": 0.5609, "lr": 6.607142857142858e-06, "epoch": 0.11737089201877934, "percentage": 1.68, "elapsed_time": "0:11:57", "remaining_time": "11:41:20"}
{"current_steps": 80, "total_steps": 4473, "loss": 0.6192, "lr": 7.053571428571429e-06, "epoch": 0.12519561815336464, "percentage": 1.79, "elapsed_time": "0:12:39", "remaining_time": "11:34:55"}
{"current_steps": 85, "total_steps": 4473, "loss": 0.602, "lr": 7.500000000000001e-06, "epoch": 0.13302034428794993, "percentage": 1.9, "elapsed_time": "0:13:12", "remaining_time": "11:22:16"}
{"current_steps": 90, "total_steps": 4473, "loss": 0.5817, "lr": 7.946428571428571e-06, "epoch": 0.14084507042253522, "percentage": 2.01, "elapsed_time": "0:13:52", "remaining_time": "11:15:26"}
{"current_steps": 95, "total_steps": 4473, "loss": 0.5545, "lr": 8.392857142857144e-06, "epoch": 0.1486697965571205, "percentage": 2.12, "elapsed_time": "0:14:36", "remaining_time": "11:13:13"}
{"current_steps": 100, "total_steps": 4473, "loss": 0.5399, "lr": 8.839285714285714e-06, "epoch": 0.1564945226917058, "percentage": 2.24, "elapsed_time": "0:15:28", "remaining_time": "11:16:49"}
{"current_steps": 105, "total_steps": 4473, "loss": 0.5684, "lr": 9.285714285714288e-06, "epoch": 0.1643192488262911, "percentage": 2.35, "elapsed_time": "0:16:18", "remaining_time": "11:18:29"}
{"current_steps": 110, "total_steps": 4473, "loss": 0.5736, "lr": 9.732142857142858e-06, "epoch": 0.17214397496087636, "percentage": 2.46, "elapsed_time": "0:17:00", "remaining_time": "11:14:56"}
{"current_steps": 115, "total_steps": 4473, "loss": 0.5631, "lr": 1.0178571428571429e-05, "epoch": 0.17996870109546165, "percentage": 2.57, "elapsed_time": "0:17:38", "remaining_time": "11:08:42"}
{"current_steps": 120, "total_steps": 4473, "loss": 0.5707, "lr": 1.0625e-05, "epoch": 0.18779342723004694, "percentage": 2.68, "elapsed_time": "0:18:28", "remaining_time": "11:09:53"}
{"current_steps": 125, "total_steps": 4473, "loss": 0.5311, "lr": 1.1071428571428572e-05, "epoch": 0.19561815336463223, "percentage": 2.79, "elapsed_time": "0:19:18", "remaining_time": "11:11:23"}
{"current_steps": 130, "total_steps": 4473, "loss": 0.5303, "lr": 1.1517857142857142e-05, "epoch": 0.20344287949921752, "percentage": 2.91, "elapsed_time": "0:19:53", "remaining_time": "11:04:39"}
{"current_steps": 135, "total_steps": 4473, "loss": 0.5115, "lr": 1.1964285714285716e-05, "epoch": 0.2112676056338028, "percentage": 3.02, "elapsed_time": "0:20:33", "remaining_time": "11:00:31"}
{"current_steps": 140, "total_steps": 4473, "loss": 0.5176, "lr": 1.2410714285714287e-05, "epoch": 0.2190923317683881, "percentage": 3.13, "elapsed_time": "0:21:27", "remaining_time": "11:03:59"}
{"current_steps": 145, "total_steps": 4473, "loss": 0.5588, "lr": 1.2857142857142859e-05, "epoch": 0.2269170579029734, "percentage": 3.24, "elapsed_time": "0:22:10", "remaining_time": "11:02:06"}
{"current_steps": 150, "total_steps": 4473, "loss": 0.5132, "lr": 1.3303571428571429e-05, "epoch": 0.2347417840375587, "percentage": 3.35, "elapsed_time": "0:22:51", "remaining_time": "10:58:33"}
{"current_steps": 155, "total_steps": 4473, "loss": 0.5135, "lr": 1.375e-05, "epoch": 0.24256651017214398, "percentage": 3.47, "elapsed_time": "0:23:36", "remaining_time": "10:57:49"}
{"current_steps": 160, "total_steps": 4473, "loss": 0.5287, "lr": 1.4196428571428574e-05, "epoch": 0.25039123630672927, "percentage": 3.58, "elapsed_time": "0:24:20", "remaining_time": "10:56:04"}
{"current_steps": 165, "total_steps": 4473, "loss": 0.5242, "lr": 1.4642857142857144e-05, "epoch": 0.25821596244131456, "percentage": 3.69, "elapsed_time": "0:25:09", "remaining_time": "10:56:58"}
{"current_steps": 170, "total_steps": 4473, "loss": 0.5075, "lr": 1.5089285714285715e-05, "epoch": 0.26604068857589985, "percentage": 3.8, "elapsed_time": "0:25:58", "remaining_time": "10:57:18"}
{"current_steps": 175, "total_steps": 4473, "loss": 0.5169, "lr": 1.553571428571429e-05, "epoch": 0.27386541471048514, "percentage": 3.91, "elapsed_time": "0:26:47", "remaining_time": "10:58:00"}
{"current_steps": 180, "total_steps": 4473, "loss": 0.5168, "lr": 1.598214285714286e-05, "epoch": 0.28169014084507044, "percentage": 4.02, "elapsed_time": "0:27:34", "remaining_time": "10:57:34"}
{"current_steps": 185, "total_steps": 4473, "loss": 0.5073, "lr": 1.642857142857143e-05, "epoch": 0.2895148669796557, "percentage": 4.14, "elapsed_time": "0:28:26", "remaining_time": "10:59:25"}
{"current_steps": 190, "total_steps": 4473, "loss": 0.4956, "lr": 1.6875e-05, "epoch": 0.297339593114241, "percentage": 4.25, "elapsed_time": "0:29:09", "remaining_time": "10:57:20"}
{"current_steps": 195, "total_steps": 4473, "loss": 0.5384, "lr": 1.7321428571428572e-05, "epoch": 0.3051643192488263, "percentage": 4.36, "elapsed_time": "0:29:54", "remaining_time": "10:56:19"}
{"current_steps": 200, "total_steps": 4473, "loss": 0.4963, "lr": 1.7767857142857143e-05, "epoch": 0.3129890453834116, "percentage": 4.47, "elapsed_time": "0:30:34", "remaining_time": "10:53:21"}
{"current_steps": 205, "total_steps": 4473, "loss": 0.4953, "lr": 1.8214285714285715e-05, "epoch": 0.3208137715179969, "percentage": 4.58, "elapsed_time": "0:31:15", "remaining_time": "10:50:54"}
{"current_steps": 210, "total_steps": 4473, "loss": 0.4876, "lr": 1.8660714285714287e-05, "epoch": 0.3286384976525822, "percentage": 4.69, "elapsed_time": "0:32:10", "remaining_time": "10:53:06"}
{"current_steps": 215, "total_steps": 4473, "loss": 0.4813, "lr": 1.910714285714286e-05, "epoch": 0.3364632237871675, "percentage": 4.81, "elapsed_time": "0:32:59", "remaining_time": "10:53:31"}
{"current_steps": 220, "total_steps": 4473, "loss": 0.524, "lr": 1.955357142857143e-05, "epoch": 0.3442879499217527, "percentage": 4.92, "elapsed_time": "0:33:38", "remaining_time": "10:50:18"}
{"current_steps": 225, "total_steps": 4473, "loss": 0.4969, "lr": 2e-05, "epoch": 0.352112676056338, "percentage": 5.03, "elapsed_time": "0:34:16", "remaining_time": "10:47:04"}
{"current_steps": 230, "total_steps": 4473, "loss": 0.4961, "lr": 2.0446428571428573e-05, "epoch": 0.3599374021909233, "percentage": 5.14, "elapsed_time": "0:34:44", "remaining_time": "10:40:52"}
{"current_steps": 235, "total_steps": 4473, "loss": 0.4393, "lr": 2.0892857142857145e-05, "epoch": 0.3677621283255086, "percentage": 5.25, "elapsed_time": "0:35:33", "remaining_time": "10:41:06"}
{"current_steps": 240, "total_steps": 4473, "loss": 0.4743, "lr": 2.1339285714285717e-05, "epoch": 0.3755868544600939, "percentage": 5.37, "elapsed_time": "0:36:16", "remaining_time": "10:39:46"}
{"current_steps": 245, "total_steps": 4473, "loss": 0.4916, "lr": 2.1785714285714285e-05, "epoch": 0.38341158059467917, "percentage": 5.48, "elapsed_time": "0:36:55", "remaining_time": "10:37:09"}
{"current_steps": 250, "total_steps": 4473, "loss": 0.4749, "lr": 2.2232142857142856e-05, "epoch": 0.39123630672926446, "percentage": 5.59, "elapsed_time": "0:37:30", "remaining_time": "10:33:42"}
{"current_steps": 255, "total_steps": 4473, "loss": 0.4899, "lr": 2.267857142857143e-05, "epoch": 0.39906103286384975, "percentage": 5.7, "elapsed_time": "0:38:15", "remaining_time": "10:32:52"}
{"current_steps": 260, "total_steps": 4473, "loss": 0.4361, "lr": 2.3125000000000003e-05, "epoch": 0.40688575899843504, "percentage": 5.81, "elapsed_time": "0:39:07", "remaining_time": "10:33:50"}
{"current_steps": 265, "total_steps": 4473, "loss": 0.4696, "lr": 2.3571428571428575e-05, "epoch": 0.41471048513302033, "percentage": 5.92, "elapsed_time": "0:39:49", "remaining_time": "10:32:21"}
{"current_steps": 270, "total_steps": 4473, "loss": 0.4849, "lr": 2.4017857142857146e-05, "epoch": 0.4225352112676056, "percentage": 6.04, "elapsed_time": "0:40:43", "remaining_time": "10:34:02"}
{"current_steps": 275, "total_steps": 4473, "loss": 0.4564, "lr": 2.4464285714285718e-05, "epoch": 0.4303599374021909, "percentage": 6.15, "elapsed_time": "0:41:18", "remaining_time": "10:30:30"}
{"current_steps": 280, "total_steps": 4473, "loss": 0.4962, "lr": 2.4910714285714286e-05, "epoch": 0.4381846635367762, "percentage": 6.26, "elapsed_time": "0:42:02", "remaining_time": "10:29:33"}
{"current_steps": 285, "total_steps": 4473, "loss": 0.4452, "lr": 2.5357142857142858e-05, "epoch": 0.4460093896713615, "percentage": 6.37, "elapsed_time": "0:42:56", "remaining_time": "10:30:54"}
{"current_steps": 290, "total_steps": 4473, "loss": 0.4585, "lr": 2.580357142857143e-05, "epoch": 0.4538341158059468, "percentage": 6.48, "elapsed_time": "0:43:46", "remaining_time": "10:31:19"}
{"current_steps": 295, "total_steps": 4473, "loss": 0.4699, "lr": 2.625e-05, "epoch": 0.4616588419405321, "percentage": 6.6, "elapsed_time": "0:44:33", "remaining_time": "10:31:07"}
{"current_steps": 300, "total_steps": 4473, "loss": 0.4382, "lr": 2.6696428571428573e-05, "epoch": 0.4694835680751174, "percentage": 6.71, "elapsed_time": "0:45:22", "remaining_time": "10:31:14"}
{"current_steps": 305, "total_steps": 4473, "loss": 0.4611, "lr": 2.7142857142857148e-05, "epoch": 0.47730829420970267, "percentage": 6.82, "elapsed_time": "0:46:08", "remaining_time": "10:30:39"}
{"current_steps": 310, "total_steps": 4473, "loss": 0.4596, "lr": 2.758928571428572e-05, "epoch": 0.48513302034428796, "percentage": 6.93, "elapsed_time": "0:46:44", "remaining_time": "10:27:42"}
{"current_steps": 315, "total_steps": 4473, "loss": 0.4674, "lr": 2.8035714285714288e-05, "epoch": 0.49295774647887325, "percentage": 7.04, "elapsed_time": "0:47:38", "remaining_time": "10:28:47"}
{"current_steps": 320, "total_steps": 4473, "loss": 0.4814, "lr": 2.848214285714286e-05, "epoch": 0.5007824726134585, "percentage": 7.15, "elapsed_time": "0:48:29", "remaining_time": "10:29:19"}
{"current_steps": 325, "total_steps": 4473, "loss": 0.4767, "lr": 2.892857142857143e-05, "epoch": 0.5086071987480438, "percentage": 7.27, "elapsed_time": "0:49:21", "remaining_time": "10:29:52"}
{"current_steps": 330, "total_steps": 4473, "loss": 0.438, "lr": 2.9375000000000003e-05, "epoch": 0.5164319248826291, "percentage": 7.38, "elapsed_time": "0:50:04", "remaining_time": "10:28:37"}
{"current_steps": 335, "total_steps": 4473, "loss": 0.4645, "lr": 2.9821428571428574e-05, "epoch": 0.5242566510172144, "percentage": 7.49, "elapsed_time": "0:51:06", "remaining_time": "10:31:21"}
{"current_steps": 340, "total_steps": 4473, "loss": 0.439, "lr": 3.0267857142857146e-05, "epoch": 0.5320813771517997, "percentage": 7.6, "elapsed_time": "0:52:00", "remaining_time": "10:32:07"}
{"current_steps": 345, "total_steps": 4473, "loss": 0.4199, "lr": 3.071428571428572e-05, "epoch": 0.539906103286385, "percentage": 7.71, "elapsed_time": "0:52:31", "remaining_time": "10:28:29"}
{"current_steps": 350, "total_steps": 4473, "loss": 0.4767, "lr": 3.116071428571429e-05, "epoch": 0.5477308294209703, "percentage": 7.82, "elapsed_time": "0:53:32", "remaining_time": "10:30:43"}
{"current_steps": 355, "total_steps": 4473, "loss": 0.4761, "lr": 3.160714285714286e-05, "epoch": 0.5555555555555556, "percentage": 7.94, "elapsed_time": "0:54:08", "remaining_time": "10:28:02"}
{"current_steps": 360, "total_steps": 4473, "loss": 0.447, "lr": 3.205357142857143e-05, "epoch": 0.5633802816901409, "percentage": 8.05, "elapsed_time": "0:54:41", "remaining_time": "10:24:55"}
{"current_steps": 365, "total_steps": 4473, "loss": 0.4613, "lr": 3.2500000000000004e-05, "epoch": 0.5712050078247262, "percentage": 8.16, "elapsed_time": "0:55:24", "remaining_time": "10:23:40"}
{"current_steps": 370, "total_steps": 4473, "loss": 0.4559, "lr": 3.2946428571428576e-05, "epoch": 0.5790297339593115, "percentage": 8.27, "elapsed_time": "0:56:09", "remaining_time": "10:22:40"}
{"current_steps": 375, "total_steps": 4473, "loss": 0.4673, "lr": 3.339285714285715e-05, "epoch": 0.5868544600938967, "percentage": 8.38, "elapsed_time": "0:56:50", "remaining_time": "10:21:06"}
{"current_steps": 380, "total_steps": 4473, "loss": 0.4623, "lr": 3.383928571428572e-05, "epoch": 0.594679186228482, "percentage": 8.5, "elapsed_time": "0:57:36", "remaining_time": "10:20:31"}
{"current_steps": 385, "total_steps": 4473, "loss": 0.4603, "lr": 3.4285714285714284e-05, "epoch": 0.6025039123630673, "percentage": 8.61, "elapsed_time": "0:58:26", "remaining_time": "10:20:33"}
{"current_steps": 390, "total_steps": 4473, "loss": 0.4712, "lr": 3.473214285714286e-05, "epoch": 0.6103286384976526, "percentage": 8.72, "elapsed_time": "0:59:07", "remaining_time": "10:19:03"}
{"current_steps": 395, "total_steps": 4473, "loss": 0.4343, "lr": 3.5178571428571434e-05, "epoch": 0.6181533646322379, "percentage": 8.83, "elapsed_time": "0:59:57", "remaining_time": "10:19:01"}
{"current_steps": 400, "total_steps": 4473, "loss": 0.4625, "lr": 3.5625000000000005e-05, "epoch": 0.6259780907668232, "percentage": 8.94, "elapsed_time": "1:00:44", "remaining_time": "10:18:25"}
{"current_steps": 405, "total_steps": 4473, "loss": 0.4418, "lr": 3.607142857142858e-05, "epoch": 0.6338028169014085, "percentage": 9.05, "elapsed_time": "1:01:33", "remaining_time": "10:18:18"}
{"current_steps": 410, "total_steps": 4473, "loss": 0.4401, "lr": 3.651785714285715e-05, "epoch": 0.6416275430359938, "percentage": 9.17, "elapsed_time": "1:02:13", "remaining_time": "10:16:35"}
{"current_steps": 415, "total_steps": 4473, "loss": 0.4448, "lr": 3.696428571428572e-05, "epoch": 0.6494522691705791, "percentage": 9.28, "elapsed_time": "1:03:05", "remaining_time": "10:16:51"}
{"current_steps": 420, "total_steps": 4473, "loss": 0.462, "lr": 3.7410714285714285e-05, "epoch": 0.6572769953051644, "percentage": 9.39, "elapsed_time": "1:03:46", "remaining_time": "10:15:29"}
{"current_steps": 425, "total_steps": 4473, "loss": 0.4455, "lr": 3.785714285714286e-05, "epoch": 0.6651017214397497, "percentage": 9.5, "elapsed_time": "1:04:34", "remaining_time": "10:15:01"}
{"current_steps": 430, "total_steps": 4473, "loss": 0.4107, "lr": 3.830357142857143e-05, "epoch": 0.672926447574335, "percentage": 9.61, "elapsed_time": "1:05:14", "remaining_time": "10:13:24"}
{"current_steps": 435, "total_steps": 4473, "loss": 0.4363, "lr": 3.875e-05, "epoch": 0.6807511737089202, "percentage": 9.73, "elapsed_time": "1:06:03", "remaining_time": "10:13:15"}
{"current_steps": 440, "total_steps": 4473, "loss": 0.461, "lr": 3.919642857142858e-05, "epoch": 0.6885758998435054, "percentage": 9.84, "elapsed_time": "1:06:40", "remaining_time": "10:11:11"}
{"current_steps": 445, "total_steps": 4473, "loss": 0.4281, "lr": 3.964285714285715e-05, "epoch": 0.6964006259780907, "percentage": 9.95, "elapsed_time": "1:07:29", "remaining_time": "10:10:52"}
{"current_steps": 450, "total_steps": 4473, "loss": 0.4131, "lr": 3.999999390788695e-05, "epoch": 0.704225352112676, "percentage": 10.06, "elapsed_time": "1:08:25", "remaining_time": "10:11:39"}
{"current_steps": 455, "total_steps": 4473, "loss": 0.4542, "lr": 3.999978068431985e-05, "epoch": 0.7120500782472613, "percentage": 10.17, "elapsed_time": "1:09:18", "remaining_time": "10:12:00"}
{"current_steps": 460, "total_steps": 4473, "loss": 0.4405, "lr": 3.999926285881157e-05, "epoch": 0.7198748043818466, "percentage": 10.28, "elapsed_time": "1:10:16", "remaining_time": "10:13:03"}
{"current_steps": 465, "total_steps": 4473, "loss": 0.4538, "lr": 3.999844043924872e-05, "epoch": 0.7276995305164319, "percentage": 10.4, "elapsed_time": "1:11:02", "remaining_time": "10:12:19"}
{"current_steps": 470, "total_steps": 4473, "loss": 0.4448, "lr": 3.999731343815697e-05, "epoch": 0.7355242566510172, "percentage": 10.51, "elapsed_time": "1:11:57", "remaining_time": "10:12:51"}
{"current_steps": 475, "total_steps": 4473, "loss": 0.4446, "lr": 3.999588187270084e-05, "epoch": 0.7433489827856025, "percentage": 10.62, "elapsed_time": "1:12:38", "remaining_time": "10:11:25"}
{"current_steps": 480, "total_steps": 4473, "loss": 0.4673, "lr": 3.999414576468345e-05, "epoch": 0.7511737089201878, "percentage": 10.73, "elapsed_time": "1:13:27", "remaining_time": "10:11:06"}
{"current_steps": 485, "total_steps": 4473, "loss": 0.4303, "lr": 3.99921051405462e-05, "epoch": 0.758998435054773, "percentage": 10.84, "elapsed_time": "1:14:26", "remaining_time": "10:12:06"}
{"current_steps": 490, "total_steps": 4473, "loss": 0.4486, "lr": 3.998976003136831e-05, "epoch": 0.7668231611893583, "percentage": 10.95, "elapsed_time": "1:15:05", "remaining_time": "10:10:20"}
{"current_steps": 495, "total_steps": 4473, "loss": 0.4536, "lr": 3.998711047286643e-05, "epoch": 0.7746478873239436, "percentage": 11.07, "elapsed_time": "1:15:53", "remaining_time": "10:09:52"}
{"current_steps": 500, "total_steps": 4473, "loss": 0.4196, "lr": 3.998415650539403e-05, "epoch": 0.7824726134585289, "percentage": 11.18, "elapsed_time": "1:16:33", "remaining_time": "10:08:19"}
{"current_steps": 505, "total_steps": 4473, "loss": 0.4585, "lr": 3.998089817394081e-05, "epoch": 0.7902973395931142, "percentage": 11.29, "elapsed_time": "1:17:14", "remaining_time": "10:06:54"}
{"current_steps": 510, "total_steps": 4473, "loss": 0.452, "lr": 3.9977335528132026e-05, "epoch": 0.7981220657276995, "percentage": 11.4, "elapsed_time": "1:18:13", "remaining_time": "10:07:50"}
{"current_steps": 515, "total_steps": 4473, "loss": 0.4211, "lr": 3.997346862222771e-05, "epoch": 0.8059467918622848, "percentage": 11.51, "elapsed_time": "1:18:58", "remaining_time": "10:06:55"}
{"current_steps": 520, "total_steps": 4473, "loss": 0.4498, "lr": 3.9969297515121856e-05, "epoch": 0.8137715179968701, "percentage": 11.63, "elapsed_time": "1:19:47", "remaining_time": "10:06:37"}
{"current_steps": 525, "total_steps": 4473, "loss": 0.4172, "lr": 3.996482227034154e-05, "epoch": 0.8215962441314554, "percentage": 11.74, "elapsed_time": "1:20:31", "remaining_time": "10:05:31"}
{"current_steps": 530, "total_steps": 4473, "loss": 0.4517, "lr": 3.996004295604591e-05, "epoch": 0.8294209702660407, "percentage": 11.85, "elapsed_time": "1:21:25", "remaining_time": "10:05:45"}
{"current_steps": 535, "total_steps": 4473, "loss": 0.4294, "lr": 3.995495964502519e-05, "epoch": 0.837245696400626, "percentage": 11.96, "elapsed_time": "1:22:12", "remaining_time": "10:05:09"}
{"current_steps": 540, "total_steps": 4473, "loss": 0.4511, "lr": 3.994957241469955e-05, "epoch": 0.8450704225352113, "percentage": 12.07, "elapsed_time": "1:23:11", "remaining_time": "10:05:52"}
{"current_steps": 545, "total_steps": 4473, "loss": 0.4149, "lr": 3.994388134711792e-05, "epoch": 0.8528951486697965, "percentage": 12.18, "elapsed_time": "1:23:48", "remaining_time": "10:04:01"}
{"current_steps": 550, "total_steps": 4473, "loss": 0.4372, "lr": 3.993788652895678e-05, "epoch": 0.8607198748043818, "percentage": 12.3, "elapsed_time": "1:24:13", "remaining_time": "10:00:44"}
{"current_steps": 555, "total_steps": 4473, "loss": 0.4437, "lr": 3.993158805151878e-05, "epoch": 0.8685446009389671, "percentage": 12.41, "elapsed_time": "1:24:57", "remaining_time": "9:59:43"}
{"current_steps": 560, "total_steps": 4473, "loss": 0.4122, "lr": 3.9924986010731396e-05, "epoch": 0.8763693270735524, "percentage": 12.52, "elapsed_time": "1:25:40", "remaining_time": "9:58:41"}
{"current_steps": 565, "total_steps": 4473, "loss": 0.4131, "lr": 3.991808050714546e-05, "epoch": 0.8841940532081377, "percentage": 12.63, "elapsed_time": "1:26:35", "remaining_time": "9:58:59"}
{"current_steps": 570, "total_steps": 4473, "loss": 0.4194, "lr": 3.99108716459336e-05, "epoch": 0.892018779342723, "percentage": 12.74, "elapsed_time": "1:27:20", "remaining_time": "9:58:04"}
{"current_steps": 575, "total_steps": 4473, "loss": 0.4497, "lr": 3.990335953688869e-05, "epoch": 0.8998435054773083, "percentage": 12.85, "elapsed_time": "1:28:05", "remaining_time": "9:57:11"}
{"current_steps": 580, "total_steps": 4473, "loss": 0.4095, "lr": 3.989554429442214e-05, "epoch": 0.9076682316118936, "percentage": 12.97, "elapsed_time": "1:28:55", "remaining_time": "9:56:53"}
{"current_steps": 585, "total_steps": 4473, "loss": 0.4239, "lr": 3.988742603756214e-05, "epoch": 0.9154929577464789, "percentage": 13.08, "elapsed_time": "1:29:32", "remaining_time": "9:55:08"}
{"current_steps": 590, "total_steps": 4473, "loss": 0.4374, "lr": 3.9879004889951896e-05, "epoch": 0.9233176838810642, "percentage": 13.19, "elapsed_time": "1:30:18", "remaining_time": "9:54:18"}
{"current_steps": 595, "total_steps": 4473, "loss": 0.4392, "lr": 3.98702809798477e-05, "epoch": 0.9311424100156495, "percentage": 13.3, "elapsed_time": "1:31:02", "remaining_time": "9:53:22"}
{"current_steps": 600, "total_steps": 4473, "loss": 0.4327, "lr": 3.986125444011702e-05, "epoch": 0.9389671361502347, "percentage": 13.41, "elapsed_time": "1:31:46", "remaining_time": "9:52:26"}
{"current_steps": 605, "total_steps": 4473, "loss": 0.4408, "lr": 3.985192540823644e-05, "epoch": 0.94679186228482, "percentage": 13.53, "elapsed_time": "1:32:17", "remaining_time": "9:50:02"}
{"current_steps": 610, "total_steps": 4473, "loss": 0.3992, "lr": 3.9842294026289565e-05, "epoch": 0.9546165884194053, "percentage": 13.64, "elapsed_time": "1:33:07", "remaining_time": "9:49:45"}
{"current_steps": 615, "total_steps": 4473, "loss": 0.4276, "lr": 3.9832360440964884e-05, "epoch": 0.9624413145539906, "percentage": 13.75, "elapsed_time": "1:33:41", "remaining_time": "9:47:41"}
{"current_steps": 620, "total_steps": 4473, "loss": 0.4023, "lr": 3.9822124803553545e-05, "epoch": 0.9702660406885759, "percentage": 13.86, "elapsed_time": "1:34:34", "remaining_time": "9:47:44"}
{"current_steps": 625, "total_steps": 4473, "loss": 0.4398, "lr": 3.981158726994699e-05, "epoch": 0.9780907668231612, "percentage": 13.97, "elapsed_time": "1:35:13", "remaining_time": "9:46:16"}
{"current_steps": 630, "total_steps": 4473, "loss": 0.3989, "lr": 3.980074800063465e-05, "epoch": 0.9859154929577465, "percentage": 14.08, "elapsed_time": "1:35:59", "remaining_time": "9:45:32"}
{"current_steps": 635, "total_steps": 4473, "loss": 0.416, "lr": 3.978960716070146e-05, "epoch": 0.9937402190923318, "percentage": 14.2, "elapsed_time": "1:36:50", "remaining_time": "9:45:19"}
{"current_steps": 640, "total_steps": 4473, "loss": 0.4047, "lr": 3.977816491982534e-05, "epoch": 1.001564945226917, "percentage": 14.31, "elapsed_time": "1:37:44", "remaining_time": "9:45:24"}
{"current_steps": 645, "total_steps": 4473, "loss": 0.4021, "lr": 3.976642145227465e-05, "epoch": 1.0093896713615023, "percentage": 14.42, "elapsed_time": "1:38:37", "remaining_time": "9:45:21"}
{"current_steps": 650, "total_steps": 4473, "loss": 0.4052, "lr": 3.97543769369055e-05, "epoch": 1.0172143974960877, "percentage": 14.53, "elapsed_time": "1:39:22", "remaining_time": "9:44:27"}
{"current_steps": 655, "total_steps": 4473, "loss": 0.4033, "lr": 3.974203155715904e-05, "epoch": 1.0250391236306728, "percentage": 14.64, "elapsed_time": "1:40:03", "remaining_time": "9:43:13"}
{"current_steps": 660, "total_steps": 4473, "loss": 0.3879, "lr": 3.972938550105867e-05, "epoch": 1.0328638497652582, "percentage": 14.76, "elapsed_time": "1:40:45", "remaining_time": "9:42:03"}
{"current_steps": 665, "total_steps": 4473, "loss": 0.4432, "lr": 3.971643896120715e-05, "epoch": 1.0406885758998434, "percentage": 14.87, "elapsed_time": "1:41:21", "remaining_time": "9:40:25"}
{"current_steps": 670, "total_steps": 4473, "loss": 0.4216, "lr": 3.970319213478371e-05, "epoch": 1.0485133020344288, "percentage": 14.98, "elapsed_time": "1:42:08", "remaining_time": "9:39:43"}
{"current_steps": 675, "total_steps": 4473, "loss": 0.3942, "lr": 3.9689645223541024e-05, "epoch": 1.056338028169014, "percentage": 15.09, "elapsed_time": "1:42:45", "remaining_time": "9:38:13"}
{"current_steps": 680, "total_steps": 4473, "loss": 0.4233, "lr": 3.967579843380211e-05, "epoch": 1.0641627543035994, "percentage": 15.2, "elapsed_time": "1:43:43", "remaining_time": "9:38:35"}
{"current_steps": 685, "total_steps": 4473, "loss": 0.4003, "lr": 3.9661651976457236e-05, "epoch": 1.0719874804381846, "percentage": 15.31, "elapsed_time": "1:44:39", "remaining_time": "9:38:46"}
{"current_steps": 690, "total_steps": 4473, "loss": 0.41, "lr": 3.9647206066960684e-05, "epoch": 1.07981220657277, "percentage": 15.43, "elapsed_time": "1:45:25", "remaining_time": "9:38:00"}
{"current_steps": 695, "total_steps": 4473, "loss": 0.3824, "lr": 3.9632460925327477e-05, "epoch": 1.0876369327073552, "percentage": 15.54, "elapsed_time": "1:46:22", "remaining_time": "9:38:13"}
{"current_steps": 700, "total_steps": 4473, "loss": 0.4112, "lr": 3.961741677613001e-05, "epoch": 1.0954616588419406, "percentage": 15.65, "elapsed_time": "1:47:03", "remaining_time": "9:37:03"}
{"current_steps": 705, "total_steps": 4473, "loss": 0.4016, "lr": 3.960207384849465e-05, "epoch": 1.1032863849765258, "percentage": 15.76, "elapsed_time": "1:47:56", "remaining_time": "9:36:55"}
{"current_steps": 710, "total_steps": 4473, "loss": 0.4151, "lr": 3.958643237609823e-05, "epoch": 1.1111111111111112, "percentage": 15.87, "elapsed_time": "1:48:41", "remaining_time": "9:36:05"}
{"current_steps": 715, "total_steps": 4473, "loss": 0.3979, "lr": 3.9570492597164524e-05, "epoch": 1.1189358372456963, "percentage": 15.98, "elapsed_time": "1:49:15", "remaining_time": "9:34:16"}
{"current_steps": 720, "total_steps": 4473, "loss": 0.3807, "lr": 3.955425475446055e-05, "epoch": 1.1267605633802817, "percentage": 16.1, "elapsed_time": "1:49:53", "remaining_time": "9:32:47"}
{"current_steps": 725, "total_steps": 4473, "loss": 0.4218, "lr": 3.953771909529295e-05, "epoch": 1.134585289514867, "percentage": 16.21, "elapsed_time": "1:50:31", "remaining_time": "9:31:23"}
{"current_steps": 730, "total_steps": 4473, "loss": 0.4086, "lr": 3.952088587150419e-05, "epoch": 1.1424100156494523, "percentage": 16.32, "elapsed_time": "1:51:22", "remaining_time": "9:31:03"}
{"current_steps": 735, "total_steps": 4473, "loss": 0.3738, "lr": 3.9503755339468704e-05, "epoch": 1.1502347417840375, "percentage": 16.43, "elapsed_time": "1:52:06", "remaining_time": "9:30:10"}
{"current_steps": 740, "total_steps": 4473, "loss": 0.4107, "lr": 3.9486327760089015e-05, "epoch": 1.158059467918623, "percentage": 16.54, "elapsed_time": "1:52:51", "remaining_time": "9:29:19"}
{"current_steps": 745, "total_steps": 4473, "loss": 0.3886, "lr": 3.946860339879177e-05, "epoch": 1.165884194053208, "percentage": 16.66, "elapsed_time": "1:53:38", "remaining_time": "9:28:37"}
{"current_steps": 750, "total_steps": 4473, "loss": 0.4111, "lr": 3.945058252552366e-05, "epoch": 1.1737089201877935, "percentage": 16.77, "elapsed_time": "1:54:28", "remaining_time": "9:28:17"}
{"current_steps": 755, "total_steps": 4473, "loss": 0.3957, "lr": 3.943226541474734e-05, "epoch": 1.1815336463223787, "percentage": 16.88, "elapsed_time": "1:55:31", "remaining_time": "9:28:54"}
{"current_steps": 760, "total_steps": 4473, "loss": 0.4427, "lr": 3.941365234543727e-05, "epoch": 1.189358372456964, "percentage": 16.99, "elapsed_time": "1:56:07", "remaining_time": "9:27:17"}
{"current_steps": 765, "total_steps": 4473, "loss": 0.398, "lr": 3.9394743601075384e-05, "epoch": 1.1971830985915493, "percentage": 17.1, "elapsed_time": "1:56:52", "remaining_time": "9:26:29"}
{"current_steps": 770, "total_steps": 4473, "loss": 0.3694, "lr": 3.9375539469646866e-05, "epoch": 1.2050078247261347, "percentage": 17.21, "elapsed_time": "1:57:37", "remaining_time": "9:25:40"}
{"current_steps": 775, "total_steps": 4473, "loss": 0.3966, "lr": 3.9356040243635695e-05, "epoch": 1.2128325508607198, "percentage": 17.33, "elapsed_time": "1:58:25", "remaining_time": "9:25:06"}
{"current_steps": 780, "total_steps": 4473, "loss": 0.4127, "lr": 3.9336246220020254e-05, "epoch": 1.2206572769953052, "percentage": 17.44, "elapsed_time": "1:59:00", "remaining_time": "9:23:28"}
{"current_steps": 785, "total_steps": 4473, "loss": 0.4161, "lr": 3.931615770026874e-05, "epoch": 1.2284820031298904, "percentage": 17.55, "elapsed_time": "1:59:45", "remaining_time": "9:22:36"}
{"current_steps": 790, "total_steps": 4473, "loss": 0.4172, "lr": 3.9295774990334604e-05, "epoch": 1.2363067292644758, "percentage": 17.66, "elapsed_time": "2:00:27", "remaining_time": "9:21:33"}
{"current_steps": 795, "total_steps": 4473, "loss": 0.4207, "lr": 3.927509840065191e-05, "epoch": 1.244131455399061, "percentage": 17.77, "elapsed_time": "2:01:15", "remaining_time": "9:20:59"}
{"current_steps": 800, "total_steps": 4473, "loss": 0.4088, "lr": 3.9254128246130574e-05, "epoch": 1.2519561815336462, "percentage": 17.89, "elapsed_time": "2:01:59", "remaining_time": "9:20:04"}
{"current_steps": 805, "total_steps": 4473, "loss": 0.4127, "lr": 3.9232864846151596e-05, "epoch": 1.2597809076682316, "percentage": 18.0, "elapsed_time": "2:02:50", "remaining_time": "9:19:42"}
{"current_steps": 810, "total_steps": 4473, "loss": 0.4004, "lr": 3.921130852456216e-05, "epoch": 1.267605633802817, "percentage": 18.11, "elapsed_time": "2:03:22", "remaining_time": "9:17:53"}
{"current_steps": 815, "total_steps": 4473, "loss": 0.4168, "lr": 3.918945960967075e-05, "epoch": 1.2754303599374022, "percentage": 18.22, "elapsed_time": "2:03:59", "remaining_time": "9:16:29"}
{"current_steps": 820, "total_steps": 4473, "loss": 0.3972, "lr": 3.9167318434242096e-05, "epoch": 1.2832550860719873, "percentage": 18.33, "elapsed_time": "2:04:47", "remaining_time": "9:15:54"}
{"current_steps": 825, "total_steps": 4473, "loss": 0.3953, "lr": 3.9144885335492163e-05, "epoch": 1.2910798122065728, "percentage": 18.44, "elapsed_time": "2:05:25", "remaining_time": "9:14:38"}
{"current_steps": 830, "total_steps": 4473, "loss": 0.4032, "lr": 3.912216065508295e-05, "epoch": 1.2989045383411582, "percentage": 18.56, "elapsed_time": "2:06:08", "remaining_time": "9:13:37"}
{"current_steps": 835, "total_steps": 4473, "loss": 0.4138, "lr": 3.909914473911735e-05, "epoch": 1.3067292644757433, "percentage": 18.67, "elapsed_time": "2:06:48", "remaining_time": "9:12:28"}
{"current_steps": 840, "total_steps": 4473, "loss": 0.3755, "lr": 3.9075837938133845e-05, "epoch": 1.3145539906103285, "percentage": 18.78, "elapsed_time": "2:07:28", "remaining_time": "9:11:19"}
{"current_steps": 845, "total_steps": 4473, "loss": 0.3852, "lr": 3.905224060710116e-05, "epoch": 1.322378716744914, "percentage": 18.89, "elapsed_time": "2:08:23", "remaining_time": "9:11:13"}
{"current_steps": 850, "total_steps": 4473, "loss": 0.377, "lr": 3.902835310541288e-05, "epoch": 1.3302034428794993, "percentage": 19.0, "elapsed_time": "2:09:12", "remaining_time": "9:10:43"}
{"current_steps": 855, "total_steps": 4473, "loss": 0.3827, "lr": 3.9004175796881976e-05, "epoch": 1.3380281690140845, "percentage": 19.11, "elapsed_time": "2:09:57", "remaining_time": "9:09:55"}
{"current_steps": 860, "total_steps": 4473, "loss": 0.4039, "lr": 3.8979709049735234e-05, "epoch": 1.3458528951486697, "percentage": 19.23, "elapsed_time": "2:10:33", "remaining_time": "9:08:29"}
{"current_steps": 865, "total_steps": 4473, "loss": 0.3813, "lr": 3.8954953236607656e-05, "epoch": 1.353677621283255, "percentage": 19.34, "elapsed_time": "2:11:14", "remaining_time": "9:07:24"}
{"current_steps": 870, "total_steps": 4473, "loss": 0.3779, "lr": 3.892990873453684e-05, "epoch": 1.3615023474178405, "percentage": 19.45, "elapsed_time": "2:11:57", "remaining_time": "9:06:28"}
{"current_steps": 875, "total_steps": 4473, "loss": 0.396, "lr": 3.8904575924957144e-05, "epoch": 1.3693270735524257, "percentage": 19.56, "elapsed_time": "2:12:41", "remaining_time": "9:05:37"}
{"current_steps": 880, "total_steps": 4473, "loss": 0.389, "lr": 3.887895519369397e-05, "epoch": 1.3771517996870108, "percentage": 19.67, "elapsed_time": "2:13:24", "remaining_time": "9:04:42"}
{"current_steps": 885, "total_steps": 4473, "loss": 0.3963, "lr": 3.8853046930957807e-05, "epoch": 1.3849765258215962, "percentage": 19.79, "elapsed_time": "2:14:05", "remaining_time": "9:03:40"}
{"current_steps": 890, "total_steps": 4473, "loss": 0.3895, "lr": 3.882685153133833e-05, "epoch": 1.3928012519561817, "percentage": 19.9, "elapsed_time": "2:14:50", "remaining_time": "9:02:50"}
{"current_steps": 895, "total_steps": 4473, "loss": 0.4025, "lr": 3.8800369393798415e-05, "epoch": 1.4006259780907668, "percentage": 20.01, "elapsed_time": "2:15:41", "remaining_time": "9:02:28"}
{"current_steps": 900, "total_steps": 4473, "loss": 0.3877, "lr": 3.877360092166799e-05, "epoch": 1.408450704225352, "percentage": 20.12, "elapsed_time": "2:16:16", "remaining_time": "9:00:59"}
{"current_steps": 905, "total_steps": 4473, "loss": 0.3798, "lr": 3.874654652263797e-05, "epoch": 1.4162754303599374, "percentage": 20.23, "elapsed_time": "2:16:54", "remaining_time": "8:59:47"}
{"current_steps": 910, "total_steps": 4473, "loss": 0.4, "lr": 3.8719206608753983e-05, "epoch": 1.4241001564945228, "percentage": 20.34, "elapsed_time": "2:17:38", "remaining_time": "8:58:53"}
{"current_steps": 915, "total_steps": 4473, "loss": 0.3832, "lr": 3.8691581596410144e-05, "epoch": 1.431924882629108, "percentage": 20.46, "elapsed_time": "2:18:16", "remaining_time": "8:57:42"}
{"current_steps": 920, "total_steps": 4473, "loss": 0.3856, "lr": 3.866367190634268e-05, "epoch": 1.4397496087636932, "percentage": 20.57, "elapsed_time": "2:19:12", "remaining_time": "8:57:36"}
{"current_steps": 925, "total_steps": 4473, "loss": 0.419, "lr": 3.863547796362355e-05, "epoch": 1.4475743348982786, "percentage": 20.68, "elapsed_time": "2:20:02", "remaining_time": "8:57:09"}
{"current_steps": 930, "total_steps": 4473, "loss": 0.389, "lr": 3.8607000197653944e-05, "epoch": 1.455399061032864, "percentage": 20.79, "elapsed_time": "2:20:41", "remaining_time": "8:55:57"}
{"current_steps": 935, "total_steps": 4473, "loss": 0.3841, "lr": 3.857823904215776e-05, "epoch": 1.4632237871674492, "percentage": 20.9, "elapsed_time": "2:21:30", "remaining_time": "8:55:26"}
{"current_steps": 940, "total_steps": 4473, "loss": 0.3568, "lr": 3.854919493517498e-05, "epoch": 1.4710485133020343, "percentage": 21.01, "elapsed_time": "2:22:14", "remaining_time": "8:54:38"}
{"current_steps": 945, "total_steps": 4473, "loss": 0.3777, "lr": 3.8519868319055034e-05, "epoch": 1.4788732394366197, "percentage": 21.13, "elapsed_time": "2:22:53", "remaining_time": "8:53:27"}
{"current_steps": 950, "total_steps": 4473, "loss": 0.4025, "lr": 3.849025964045002e-05, "epoch": 1.486697965571205, "percentage": 21.24, "elapsed_time": "2:23:32", "remaining_time": "8:52:19"}
{"current_steps": 955, "total_steps": 4473, "loss": 0.3784, "lr": 3.846036935030795e-05, "epoch": 1.4945226917057903, "percentage": 21.35, "elapsed_time": "2:24:16", "remaining_time": "8:51:28"}
{"current_steps": 960, "total_steps": 4473, "loss": 0.3751, "lr": 3.843019790386581e-05, "epoch": 1.5023474178403755, "percentage": 21.46, "elapsed_time": "2:25:13", "remaining_time": "8:51:25"}
{"current_steps": 965, "total_steps": 4473, "loss": 0.4206, "lr": 3.839974576064273e-05, "epoch": 1.510172143974961, "percentage": 21.57, "elapsed_time": "2:25:50", "remaining_time": "8:50:08"}
{"current_steps": 970, "total_steps": 4473, "loss": 0.3865, "lr": 3.8369013384432856e-05, "epoch": 1.5179968701095463, "percentage": 21.69, "elapsed_time": "2:26:33", "remaining_time": "8:49:17"}
{"current_steps": 975, "total_steps": 4473, "loss": 0.3975, "lr": 3.833800124329842e-05, "epoch": 1.5258215962441315, "percentage": 21.8, "elapsed_time": "2:27:10", "remaining_time": "8:48:01"}
{"current_steps": 980, "total_steps": 4473, "loss": 0.4034, "lr": 3.8306709809562515e-05, "epoch": 1.5336463223787167, "percentage": 21.91, "elapsed_time": "2:27:54", "remaining_time": "8:47:12"}
{"current_steps": 985, "total_steps": 4473, "loss": 0.3816, "lr": 3.827513955980193e-05, "epoch": 1.541471048513302, "percentage": 22.02, "elapsed_time": "2:28:36", "remaining_time": "8:46:14"}
{"current_steps": 990, "total_steps": 4473, "loss": 0.3872, "lr": 3.824329097483991e-05, "epoch": 1.5492957746478875, "percentage": 22.13, "elapsed_time": "2:29:26", "remaining_time": "8:45:44"}
{"current_steps": 995, "total_steps": 4473, "loss": 0.3732, "lr": 3.8211164539738826e-05, "epoch": 1.5571205007824727, "percentage": 22.24, "elapsed_time": "2:30:09", "remaining_time": "8:44:53"}
{"current_steps": 1000, "total_steps": 4473, "loss": 0.3896, "lr": 3.817876074379275e-05, "epoch": 1.5649452269170578, "percentage": 22.36, "elapsed_time": "2:31:04", "remaining_time": "8:44:41"}
{"current_steps": 1005, "total_steps": 4473, "loss": 0.3702, "lr": 3.8146080080520066e-05, "epoch": 1.5727699530516432, "percentage": 22.47, "elapsed_time": "2:31:47", "remaining_time": "8:43:46"}
{"current_steps": 1010, "total_steps": 4473, "loss": 0.3961, "lr": 3.81131230476559e-05, "epoch": 1.5805946791862286, "percentage": 22.58, "elapsed_time": "2:32:26", "remaining_time": "8:42:42"}
{"current_steps": 1015, "total_steps": 4473, "loss": 0.4048, "lr": 3.8079890147144565e-05, "epoch": 1.5884194053208138, "percentage": 22.69, "elapsed_time": "2:33:13", "remaining_time": "8:42:00"}
{"current_steps": 1020, "total_steps": 4473, "loss": 0.3877, "lr": 3.804638188513191e-05, "epoch": 1.596244131455399, "percentage": 22.8, "elapsed_time": "2:34:03", "remaining_time": "8:41:33"}
{"current_steps": 1025, "total_steps": 4473, "loss": 0.378, "lr": 3.8012598771957616e-05, "epoch": 1.6040688575899842, "percentage": 22.92, "elapsed_time": "2:34:55", "remaining_time": "8:41:08"}
{"current_steps": 1030, "total_steps": 4473, "loss": 0.3991, "lr": 3.797854132214742e-05, "epoch": 1.6118935837245696, "percentage": 23.03, "elapsed_time": "2:35:56", "remaining_time": "8:41:15"}
{"current_steps": 1035, "total_steps": 4473, "loss": 0.3896, "lr": 3.7944210054405274e-05, "epoch": 1.619718309859155, "percentage": 23.14, "elapsed_time": "2:36:28", "remaining_time": "8:39:46"}
{"current_steps": 1040, "total_steps": 4473, "loss": 0.369, "lr": 3.790960549160545e-05, "epoch": 1.6275430359937402, "percentage": 23.25, "elapsed_time": "2:37:23", "remaining_time": "8:39:33"}
{"current_steps": 1045, "total_steps": 4473, "loss": 0.3751, "lr": 3.7874728160784575e-05, "epoch": 1.6353677621283254, "percentage": 23.36, "elapsed_time": "2:38:10", "remaining_time": "8:38:52"}
{"current_steps": 1050, "total_steps": 4473, "loss": 0.3689, "lr": 3.7839578593133624e-05, "epoch": 1.6431924882629108, "percentage": 23.47, "elapsed_time": "2:38:48", "remaining_time": "8:37:42"}
{"current_steps": 1055, "total_steps": 4473, "loss": 0.3839, "lr": 3.780415732398977e-05, "epoch": 1.6510172143974962, "percentage": 23.59, "elapsed_time": "2:39:44", "remaining_time": "8:37:31"}
{"current_steps": 1060, "total_steps": 4473, "loss": 0.3877, "lr": 3.7768464892828316e-05, "epoch": 1.6588419405320813, "percentage": 23.7, "elapsed_time": "2:40:25", "remaining_time": "8:36:33"}
{"current_steps": 1065, "total_steps": 4473, "loss": 0.3593, "lr": 3.77325018432544e-05, "epoch": 1.6666666666666665, "percentage": 23.81, "elapsed_time": "2:41:19", "remaining_time": "8:36:12"}
{"current_steps": 1070, "total_steps": 4473, "loss": 0.3914, "lr": 3.769626872299477e-05, "epoch": 1.674491392801252, "percentage": 23.92, "elapsed_time": "2:42:03", "remaining_time": "8:35:24"}
{"current_steps": 1075, "total_steps": 4473, "loss": 0.3738, "lr": 3.765976608388942e-05, "epoch": 1.6823161189358373, "percentage": 24.03, "elapsed_time": "2:42:39", "remaining_time": "8:34:08"}
{"current_steps": 1080, "total_steps": 4473, "loss": 0.3588, "lr": 3.7622994481883175e-05, "epoch": 1.6901408450704225, "percentage": 24.14, "elapsed_time": "2:43:34", "remaining_time": "8:33:53"}
{"current_steps": 1085, "total_steps": 4473, "loss": 0.3866, "lr": 3.7585954477017246e-05, "epoch": 1.6979655712050077, "percentage": 24.26, "elapsed_time": "2:44:15", "remaining_time": "8:32:56"}
{"current_steps": 1090, "total_steps": 4473, "loss": 0.391, "lr": 3.754864663342069e-05, "epoch": 1.705790297339593, "percentage": 24.37, "elapsed_time": "2:45:02", "remaining_time": "8:32:14"}
{"current_steps": 1095, "total_steps": 4473, "loss": 0.3847, "lr": 3.751107151930182e-05, "epoch": 1.7136150234741785, "percentage": 24.48, "elapsed_time": "2:45:42", "remaining_time": "8:31:11"}
{"current_steps": 1100, "total_steps": 4473, "loss": 0.3674, "lr": 3.747322970693954e-05, "epoch": 1.7214397496087637, "percentage": 24.59, "elapsed_time": "2:46:15", "remaining_time": "8:29:47"}
{"current_steps": 1105, "total_steps": 4473, "loss": 0.3891, "lr": 3.743512177267464e-05, "epoch": 1.7292644757433489, "percentage": 24.7, "elapsed_time": "2:47:05", "remaining_time": "8:29:17"}
{"current_steps": 1110, "total_steps": 4473, "loss": 0.4134, "lr": 3.7396748296901045e-05, "epoch": 1.7370892018779343, "percentage": 24.82, "elapsed_time": "2:47:54", "remaining_time": "8:28:42"}
{"current_steps": 1115, "total_steps": 4473, "loss": 0.374, "lr": 3.7358109864056895e-05, "epoch": 1.7449139280125197, "percentage": 24.93, "elapsed_time": "2:48:39", "remaining_time": "8:27:55"}
{"current_steps": 1120, "total_steps": 4473, "loss": 0.3581, "lr": 3.731920706261575e-05, "epoch": 1.7527386541471048, "percentage": 25.04, "elapsed_time": "2:49:32", "remaining_time": "8:27:32"}
{"current_steps": 1125, "total_steps": 4473, "loss": 0.3801, "lr": 3.728004048507753e-05, "epoch": 1.76056338028169, "percentage": 25.15, "elapsed_time": "2:50:36", "remaining_time": "8:27:43"}
{"current_steps": 1130, "total_steps": 4473, "loss": 0.3886, "lr": 3.724061072795957e-05, "epoch": 1.7683881064162754, "percentage": 25.26, "elapsed_time": "2:51:15", "remaining_time": "8:26:40"}
{"current_steps": 1135, "total_steps": 4473, "loss": 0.337, "lr": 3.7200918391787474e-05, "epoch": 1.7762128325508608, "percentage": 25.37, "elapsed_time": "2:51:56", "remaining_time": "8:25:40"}
{"current_steps": 1140, "total_steps": 4473, "loss": 0.4111, "lr": 3.716096408108601e-05, "epoch": 1.784037558685446, "percentage": 25.49, "elapsed_time": "2:52:49", "remaining_time": "8:25:17"}
{"current_steps": 1145, "total_steps": 4473, "loss": 0.375, "lr": 3.7120748404369866e-05, "epoch": 1.7918622848200312, "percentage": 25.6, "elapsed_time": "2:53:27", "remaining_time": "8:24:11"}
{"current_steps": 1150, "total_steps": 4473, "loss": 0.3812, "lr": 3.7080271974134434e-05, "epoch": 1.7996870109546166, "percentage": 25.71, "elapsed_time": "2:54:02", "remaining_time": "8:22:53"}
{"current_steps": 1155, "total_steps": 4473, "loss": 0.3641, "lr": 3.703953540684643e-05, "epoch": 1.807511737089202, "percentage": 25.82, "elapsed_time": "2:54:34", "remaining_time": "8:21:29"}
{"current_steps": 1160, "total_steps": 4473, "loss": 0.372, "lr": 3.6998539322934525e-05, "epoch": 1.8153364632237872, "percentage": 25.93, "elapsed_time": "2:55:21", "remaining_time": "8:20:49"}
{"current_steps": 1165, "total_steps": 4473, "loss": 0.3959, "lr": 3.695728434677992e-05, "epoch": 1.8231611893583723, "percentage": 26.05, "elapsed_time": "2:56:17", "remaining_time": "8:20:33"}
{"current_steps": 1170, "total_steps": 4473, "loss": 0.3747, "lr": 3.691577110670677e-05, "epoch": 1.8309859154929577, "percentage": 26.16, "elapsed_time": "2:56:56", "remaining_time": "8:19:30"}
{"current_steps": 1175, "total_steps": 4473, "loss": 0.3977, "lr": 3.6874000234972706e-05, "epoch": 1.8388106416275432, "percentage": 26.27, "elapsed_time": "2:57:43", "remaining_time": "8:18:50"}
{"current_steps": 1180, "total_steps": 4473, "loss": 0.4035, "lr": 3.6831972367759126e-05, "epoch": 1.8466353677621283, "percentage": 26.38, "elapsed_time": "2:58:18", "remaining_time": "8:17:34"}
{"current_steps": 1185, "total_steps": 4473, "loss": 0.4049, "lr": 3.6789688145161544e-05, "epoch": 1.8544600938967135, "percentage": 26.49, "elapsed_time": "2:58:59", "remaining_time": "8:16:37"}
{"current_steps": 1190, "total_steps": 4473, "loss": 0.3775, "lr": 3.6747148211179846e-05, "epoch": 1.862284820031299, "percentage": 26.6, "elapsed_time": "2:59:47", "remaining_time": "8:16:01"}
{"current_steps": 1195, "total_steps": 4473, "loss": 0.3826, "lr": 3.670435321370845e-05, "epoch": 1.8701095461658843, "percentage": 26.72, "elapsed_time": "3:00:25", "remaining_time": "8:14:54"}
{"current_steps": 1200, "total_steps": 4473, "loss": 0.3739, "lr": 3.666130380452647e-05, "epoch": 1.8779342723004695, "percentage": 26.83, "elapsed_time": "3:01:03", "remaining_time": "8:13:49"}
{"current_steps": 1205, "total_steps": 4473, "loss": 0.3731, "lr": 3.6618000639287784e-05, "epoch": 1.8857589984350547, "percentage": 26.94, "elapsed_time": "3:01:38", "remaining_time": "8:12:36"}
{"current_steps": 1210, "total_steps": 4473, "loss": 0.401, "lr": 3.6574444377511025e-05, "epoch": 1.89358372456964, "percentage": 27.05, "elapsed_time": "3:02:21", "remaining_time": "8:11:45"}
{"current_steps": 1215, "total_steps": 4473, "loss": 0.3939, "lr": 3.653063568256956e-05, "epoch": 1.9014084507042255, "percentage": 27.16, "elapsed_time": "3:03:04", "remaining_time": "8:10:55"}
{"current_steps": 1220, "total_steps": 4473, "loss": 0.3662, "lr": 3.6486575221681386e-05, "epoch": 1.9092331768388107, "percentage": 27.27, "elapsed_time": "3:03:38", "remaining_time": "8:09:39"}
{"current_steps": 1225, "total_steps": 4473, "loss": 0.3809, "lr": 3.6442263665898964e-05, "epoch": 1.9170579029733958, "percentage": 27.39, "elapsed_time": "3:04:17", "remaining_time": "8:08:38"}
{"current_steps": 1230, "total_steps": 4473, "loss": 0.3634, "lr": 3.6397701690098974e-05, "epoch": 1.9248826291079812, "percentage": 27.5, "elapsed_time": "3:05:05", "remaining_time": "8:08:00"}
{"current_steps": 1235, "total_steps": 4473, "loss": 0.3753, "lr": 3.6352889972972095e-05, "epoch": 1.9327073552425666, "percentage": 27.61, "elapsed_time": "3:05:54", "remaining_time": "8:07:24"}
{"current_steps": 1240, "total_steps": 4473, "loss": 0.3819, "lr": 3.63078291970126e-05, "epoch": 1.9405320813771518, "percentage": 27.72, "elapsed_time": "3:06:30", "remaining_time": "8:06:16"}
{"current_steps": 1245, "total_steps": 4473, "loss": 0.3723, "lr": 3.626252004850799e-05, "epoch": 1.948356807511737, "percentage": 27.83, "elapsed_time": "3:07:19", "remaining_time": "8:05:40"}
{"current_steps": 1250, "total_steps": 4473, "loss": 0.4093, "lr": 3.62169632175286e-05, "epoch": 1.9561815336463224, "percentage": 27.95, "elapsed_time": "3:07:39", "remaining_time": "8:03:52"}
{"current_steps": 1255, "total_steps": 4473, "loss": 0.3522, "lr": 3.617115939791697e-05, "epoch": 1.9640062597809078, "percentage": 28.06, "elapsed_time": "3:08:16", "remaining_time": "8:02:46"}
{"current_steps": 1260, "total_steps": 4473, "loss": 0.3456, "lr": 3.612510928727737e-05, "epoch": 1.971830985915493, "percentage": 28.17, "elapsed_time": "3:09:00", "remaining_time": "8:01:57"}
{"current_steps": 1265, "total_steps": 4473, "loss": 0.4104, "lr": 3.6078813586965155e-05, "epoch": 1.9796557120500782, "percentage": 28.28, "elapsed_time": "3:09:43", "remaining_time": "8:01:08"}
{"current_steps": 1270, "total_steps": 4473, "loss": 0.3948, "lr": 3.6032273002076054e-05, "epoch": 1.9874804381846636, "percentage": 28.39, "elapsed_time": "3:10:39", "remaining_time": "8:00:50"}
{"current_steps": 1275, "total_steps": 4473, "loss": 0.3798, "lr": 3.598548824143547e-05, "epoch": 1.995305164319249, "percentage": 28.5, "elapsed_time": "3:11:23", "remaining_time": "8:00:04"}
{"current_steps": 1280, "total_steps": 4473, "loss": 0.365, "lr": 3.593846001758767e-05, "epoch": 2.003129890453834, "percentage": 28.62, "elapsed_time": "3:12:10", "remaining_time": "7:59:23"}
{"current_steps": 1285, "total_steps": 4473, "loss": 0.3728, "lr": 3.589118904678491e-05, "epoch": 2.0109546165884193, "percentage": 28.73, "elapsed_time": "3:12:44", "remaining_time": "7:58:10"}
{"current_steps": 1290, "total_steps": 4473, "loss": 0.3614, "lr": 3.584367604897657e-05, "epoch": 2.0187793427230045, "percentage": 28.84, "elapsed_time": "3:13:30", "remaining_time": "7:57:28"}
{"current_steps": 1295, "total_steps": 4473, "loss": 0.362, "lr": 3.5795921747798136e-05, "epoch": 2.02660406885759, "percentage": 28.95, "elapsed_time": "3:14:20", "remaining_time": "7:56:55"}
{"current_steps": 1300, "total_steps": 4473, "loss": 0.3629, "lr": 3.5747926870560244e-05, "epoch": 2.0344287949921753, "percentage": 29.06, "elapsed_time": "3:15:00", "remaining_time": "7:55:59"}
{"current_steps": 1305, "total_steps": 4473, "loss": 0.3361, "lr": 3.569969214823753e-05, "epoch": 2.0422535211267605, "percentage": 29.18, "elapsed_time": "3:15:37", "remaining_time": "7:54:53"}
{"current_steps": 1310, "total_steps": 4473, "loss": 0.3505, "lr": 3.565121831545757e-05, "epoch": 2.0500782472613457, "percentage": 29.29, "elapsed_time": "3:16:29", "remaining_time": "7:54:25"}
{"current_steps": 1315, "total_steps": 4473, "loss": 0.3582, "lr": 3.5602506110489634e-05, "epoch": 2.0579029733959313, "percentage": 29.4, "elapsed_time": "3:17:14", "remaining_time": "7:53:41"}
{"current_steps": 1320, "total_steps": 4473, "loss": 0.3664, "lr": 3.555355627523347e-05, "epoch": 2.0657276995305165, "percentage": 29.51, "elapsed_time": "3:18:15", "remaining_time": "7:53:33"}
{"current_steps": 1325, "total_steps": 4473, "loss": 0.3542, "lr": 3.550436955520798e-05, "epoch": 2.0735524256651017, "percentage": 29.62, "elapsed_time": "3:19:03", "remaining_time": "7:52:55"}
{"current_steps": 1330, "total_steps": 4473, "loss": 0.3378, "lr": 3.545494669953991e-05, "epoch": 2.081377151799687, "percentage": 29.73, "elapsed_time": "3:19:42", "remaining_time": "7:51:56"}
{"current_steps": 1335, "total_steps": 4473, "loss": 0.3481, "lr": 3.5405288460952394e-05, "epoch": 2.0892018779342725, "percentage": 29.85, "elapsed_time": "3:20:27", "remaining_time": "7:51:12"}
{"current_steps": 1340, "total_steps": 4473, "loss": 0.3758, "lr": 3.535539559575353e-05, "epoch": 2.0970266040688577, "percentage": 29.96, "elapsed_time": "3:21:25", "remaining_time": "7:50:56"}
{"current_steps": 1345, "total_steps": 4473, "loss": 0.372, "lr": 3.5305268863824835e-05, "epoch": 2.104851330203443, "percentage": 30.07, "elapsed_time": "3:22:04", "remaining_time": "7:49:56"}
{"current_steps": 1350, "total_steps": 4473, "loss": 0.3487, "lr": 3.5254909028609654e-05, "epoch": 2.112676056338028, "percentage": 30.18, "elapsed_time": "3:22:49", "remaining_time": "7:49:12"}
{"current_steps": 1355, "total_steps": 4473, "loss": 0.3532, "lr": 3.520431685710159e-05, "epoch": 2.1205007824726136, "percentage": 30.29, "elapsed_time": "3:23:25", "remaining_time": "7:48:05"}
{"current_steps": 1360, "total_steps": 4473, "loss": 0.364, "lr": 3.5153493119832776e-05, "epoch": 2.128325508607199, "percentage": 30.4, "elapsed_time": "3:24:09", "remaining_time": "7:47:17"}
{"current_steps": 1365, "total_steps": 4473, "loss": 0.357, "lr": 3.510243859086214e-05, "epoch": 2.136150234741784, "percentage": 30.52, "elapsed_time": "3:24:45", "remaining_time": "7:46:13"}
{"current_steps": 1370, "total_steps": 4473, "loss": 0.3545, "lr": 3.505115404776365e-05, "epoch": 2.143974960876369, "percentage": 30.63, "elapsed_time": "3:25:25", "remaining_time": "7:45:17"}
{"current_steps": 1375, "total_steps": 4473, "loss": 0.3573, "lr": 3.4999640271614436e-05, "epoch": 2.151799687010955, "percentage": 30.74, "elapsed_time": "3:26:05", "remaining_time": "7:44:20"}
{"current_steps": 1380, "total_steps": 4473, "loss": 0.3318, "lr": 3.494789804698291e-05, "epoch": 2.15962441314554, "percentage": 30.85, "elapsed_time": "3:26:38", "remaining_time": "7:43:07"}
{"current_steps": 1385, "total_steps": 4473, "loss": 0.3473, "lr": 3.489592816191683e-05, "epoch": 2.167449139280125, "percentage": 30.96, "elapsed_time": "3:27:32", "remaining_time": "7:42:45"}
{"current_steps": 1390, "total_steps": 4473, "loss": 0.3434, "lr": 3.484373140793125e-05, "epoch": 2.1752738654147104, "percentage": 31.08, "elapsed_time": "3:28:17", "remaining_time": "7:41:59"}
{"current_steps": 1395, "total_steps": 4473, "loss": 0.3732, "lr": 3.479130857999653e-05, "epoch": 2.183098591549296, "percentage": 31.19, "elapsed_time": "3:29:02", "remaining_time": "7:41:13"}
{"current_steps": 1400, "total_steps": 4473, "loss": 0.3316, "lr": 3.4738660476526185e-05, "epoch": 2.190923317683881, "percentage": 31.3, "elapsed_time": "3:29:45", "remaining_time": "7:40:25"}
{"current_steps": 1405, "total_steps": 4473, "loss": 0.3752, "lr": 3.468578789936472e-05, "epoch": 2.1987480438184663, "percentage": 31.41, "elapsed_time": "3:30:30", "remaining_time": "7:39:39"}
{"current_steps": 1410, "total_steps": 4473, "loss": 0.3131, "lr": 3.4632691653775455e-05, "epoch": 2.2065727699530515, "percentage": 31.52, "elapsed_time": "3:31:12", "remaining_time": "7:38:49"}
{"current_steps": 1415, "total_steps": 4473, "loss": 0.3551, "lr": 3.457937254842823e-05, "epoch": 2.214397496087637, "percentage": 31.63, "elapsed_time": "3:32:00", "remaining_time": "7:38:11"}
{"current_steps": 1420, "total_steps": 4473, "loss": 0.328, "lr": 3.452583139538711e-05, "epoch": 2.2222222222222223, "percentage": 31.75, "elapsed_time": "3:32:48", "remaining_time": "7:37:31"}
{"current_steps": 1425, "total_steps": 4473, "loss": 0.356, "lr": 3.447206901009798e-05, "epoch": 2.2300469483568075, "percentage": 31.86, "elapsed_time": "3:33:35", "remaining_time": "7:36:52"}
{"current_steps": 1430, "total_steps": 4473, "loss": 0.3315, "lr": 3.4418086211376174e-05, "epoch": 2.2378716744913927, "percentage": 31.97, "elapsed_time": "3:34:23", "remaining_time": "7:36:13"}
{"current_steps": 1435, "total_steps": 4473, "loss": 0.3638, "lr": 3.436388382139396e-05, "epoch": 2.2456964006259783, "percentage": 32.08, "elapsed_time": "3:35:04", "remaining_time": "7:35:19"}
{"current_steps": 1440, "total_steps": 4473, "loss": 0.3282, "lr": 3.4309462665668065e-05, "epoch": 2.2535211267605635, "percentage": 32.19, "elapsed_time": "3:35:57", "remaining_time": "7:34:50"}
{"current_steps": 1445, "total_steps": 4473, "loss": 0.3589, "lr": 3.425482357304706e-05, "epoch": 2.2613458528951487, "percentage": 32.3, "elapsed_time": "3:36:47", "remaining_time": "7:34:17"}
{"current_steps": 1450, "total_steps": 4473, "loss": 0.3323, "lr": 3.419996737569875e-05, "epoch": 2.269170579029734, "percentage": 32.42, "elapsed_time": "3:37:43", "remaining_time": "7:33:55"}
{"current_steps": 1455, "total_steps": 4473, "loss": 0.3619, "lr": 3.41448949090975e-05, "epoch": 2.276995305164319, "percentage": 32.53, "elapsed_time": "3:38:27", "remaining_time": "7:33:08"}
{"current_steps": 1460, "total_steps": 4473, "loss": 0.3554, "lr": 3.408960701201153e-05, "epoch": 2.2848200312989047, "percentage": 32.64, "elapsed_time": "3:39:13", "remaining_time": "7:32:24"}
{"current_steps": 1465, "total_steps": 4473, "loss": 0.3186, "lr": 3.403410452649011e-05, "epoch": 2.29264475743349, "percentage": 32.75, "elapsed_time": "3:39:44", "remaining_time": "7:31:10"}
{"current_steps": 1470, "total_steps": 4473, "loss": 0.355, "lr": 3.397838829785075e-05, "epoch": 2.300469483568075, "percentage": 32.86, "elapsed_time": "3:40:34", "remaining_time": "7:30:37"}
{"current_steps": 1475, "total_steps": 4473, "loss": 0.3757, "lr": 3.392245917466632e-05, "epoch": 2.3082942097026606, "percentage": 32.98, "elapsed_time": "3:41:20", "remaining_time": "7:29:53"}
{"current_steps": 1480, "total_steps": 4473, "loss": 0.3584, "lr": 3.386631800875214e-05, "epoch": 2.316118935837246, "percentage": 33.09, "elapsed_time": "3:42:14", "remaining_time": "7:29:25"}
{"current_steps": 1485, "total_steps": 4473, "loss": 0.336, "lr": 3.3809965655152996e-05, "epoch": 2.323943661971831, "percentage": 33.2, "elapsed_time": "3:43:05", "remaining_time": "7:28:53"}
{"current_steps": 1490, "total_steps": 4473, "loss": 0.3614, "lr": 3.375340297213011e-05, "epoch": 2.331768388106416, "percentage": 33.31, "elapsed_time": "3:43:54", "remaining_time": "7:28:15"}
{"current_steps": 1495, "total_steps": 4473, "loss": 0.3468, "lr": 3.369663082114809e-05, "epoch": 2.3395931142410014, "percentage": 33.42, "elapsed_time": "3:44:42", "remaining_time": "7:27:36"}
{"current_steps": 1500, "total_steps": 4473, "loss": 0.3218, "lr": 3.3639650066861764e-05, "epoch": 2.347417840375587, "percentage": 33.53, "elapsed_time": "3:45:24", "remaining_time": "7:26:44"}
{"current_steps": 1505, "total_steps": 4473, "loss": 0.3779, "lr": 3.3582461577103096e-05, "epoch": 2.355242566510172, "percentage": 33.65, "elapsed_time": "3:46:47", "remaining_time": "7:27:14"}
{"current_steps": 1510, "total_steps": 4473, "loss": 0.3222, "lr": 3.352506622286786e-05, "epoch": 2.3630672926447573, "percentage": 33.76, "elapsed_time": "3:47:41", "remaining_time": "7:26:47"}
{"current_steps": 1515, "total_steps": 4473, "loss": 0.3434, "lr": 3.346746487830248e-05, "epoch": 2.370892018779343, "percentage": 33.87, "elapsed_time": "3:48:24", "remaining_time": "7:25:58"}
{"current_steps": 1520, "total_steps": 4473, "loss": 0.3394, "lr": 3.3409658420690634e-05, "epoch": 2.378716744913928, "percentage": 33.98, "elapsed_time": "3:49:12", "remaining_time": "7:25:17"}
{"current_steps": 1525, "total_steps": 4473, "loss": 0.3293, "lr": 3.3351647730439936e-05, "epoch": 2.3865414710485133, "percentage": 34.09, "elapsed_time": "3:49:59", "remaining_time": "7:24:36"}
{"current_steps": 1530, "total_steps": 4473, "loss": 0.35, "lr": 3.329343369106852e-05, "epoch": 2.3943661971830985, "percentage": 34.21, "elapsed_time": "3:50:44", "remaining_time": "7:23:50"}
{"current_steps": 1535, "total_steps": 4473, "loss": 0.3901, "lr": 3.323501718919157e-05, "epoch": 2.4021909233176837, "percentage": 34.32, "elapsed_time": "3:51:20", "remaining_time": "7:22:46"}
{"current_steps": 1540, "total_steps": 4473, "loss": 0.3515, "lr": 3.317639911450785e-05, "epoch": 2.4100156494522693, "percentage": 34.43, "elapsed_time": "3:52:11", "remaining_time": "7:22:12"}
{"current_steps": 1545, "total_steps": 4473, "loss": 0.3625, "lr": 3.311758035978611e-05, "epoch": 2.4178403755868545, "percentage": 34.54, "elapsed_time": "3:53:01", "remaining_time": "7:21:36"}
{"current_steps": 1550, "total_steps": 4473, "loss": 0.3305, "lr": 3.3058561820851513e-05, "epoch": 2.4256651017214397, "percentage": 34.65, "elapsed_time": "3:53:53", "remaining_time": "7:21:04"}
{"current_steps": 1555, "total_steps": 4473, "loss": 0.3415, "lr": 3.299934439657199e-05, "epoch": 2.433489827856025, "percentage": 34.76, "elapsed_time": "3:54:41", "remaining_time": "7:20:24"}
{"current_steps": 1560, "total_steps": 4473, "loss": 0.3688, "lr": 3.293992898884456e-05, "epoch": 2.4413145539906105, "percentage": 34.88, "elapsed_time": "3:55:17", "remaining_time": "7:19:21"}
{"current_steps": 1565, "total_steps": 4473, "loss": 0.3557, "lr": 3.288031650258157e-05, "epoch": 2.4491392801251957, "percentage": 34.99, "elapsed_time": "3:55:54", "remaining_time": "7:18:21"}
{"current_steps": 1570, "total_steps": 4473, "loss": 0.3652, "lr": 3.282050784569693e-05, "epoch": 2.456964006259781, "percentage": 35.1, "elapsed_time": "3:56:41", "remaining_time": "7:17:38"}
{"current_steps": 1575, "total_steps": 4473, "loss": 0.3599, "lr": 3.276050392909227e-05, "epoch": 2.464788732394366, "percentage": 35.21, "elapsed_time": "3:57:16", "remaining_time": "7:16:34"}
{"current_steps": 1580, "total_steps": 4473, "loss": 0.3343, "lr": 3.270030566664309e-05, "epoch": 2.4726134585289516, "percentage": 35.32, "elapsed_time": "3:57:59", "remaining_time": "7:15:46"}
{"current_steps": 1585, "total_steps": 4473, "loss": 0.3575, "lr": 3.2639913975184825e-05, "epoch": 2.480438184663537, "percentage": 35.43, "elapsed_time": "3:58:44", "remaining_time": "7:14:59"}
{"current_steps": 1590, "total_steps": 4473, "loss": 0.3395, "lr": 3.257932977449888e-05, "epoch": 2.488262910798122, "percentage": 35.55, "elapsed_time": "3:59:30", "remaining_time": "7:14:15"}
{"current_steps": 1595, "total_steps": 4473, "loss": 0.3705, "lr": 3.2518553987298624e-05, "epoch": 2.496087636932707, "percentage": 35.66, "elapsed_time": "4:00:15", "remaining_time": "7:13:30"}
{"current_steps": 1600, "total_steps": 4473, "loss": 0.3464, "lr": 3.2457587539215364e-05, "epoch": 2.5039123630672924, "percentage": 35.77, "elapsed_time": "4:01:11", "remaining_time": "7:13:05"}
{"current_steps": 1605, "total_steps": 4473, "loss": 0.3352, "lr": 3.239643135878419e-05, "epoch": 2.511737089201878, "percentage": 35.88, "elapsed_time": "4:01:53", "remaining_time": "7:12:14"}
{"current_steps": 1610, "total_steps": 4473, "loss": 0.3456, "lr": 3.233508637742988e-05, "epoch": 2.519561815336463, "percentage": 35.99, "elapsed_time": "4:02:36", "remaining_time": "7:11:25"}
{"current_steps": 1615, "total_steps": 4473, "loss": 0.379, "lr": 3.2273553529452696e-05, "epoch": 2.5273865414710484, "percentage": 36.11, "elapsed_time": "4:03:15", "remaining_time": "7:10:29"}
{"current_steps": 1620, "total_steps": 4473, "loss": 0.3367, "lr": 3.221183375201418e-05, "epoch": 2.535211267605634, "percentage": 36.22, "elapsed_time": "4:04:05", "remaining_time": "7:09:52"}
{"current_steps": 1625, "total_steps": 4473, "loss": 0.3327, "lr": 3.214992798512282e-05, "epoch": 2.543035993740219, "percentage": 36.33, "elapsed_time": "4:04:45", "remaining_time": "7:08:58"}
{"current_steps": 1630, "total_steps": 4473, "loss": 0.3363, "lr": 3.20878371716198e-05, "epoch": 2.5508607198748043, "percentage": 36.44, "elapsed_time": "4:05:29", "remaining_time": "7:08:10"}
{"current_steps": 1635, "total_steps": 4473, "loss": 0.3638, "lr": 3.2025562257164613e-05, "epoch": 2.5586854460093895, "percentage": 36.55, "elapsed_time": "4:06:14", "remaining_time": "7:07:24"}
{"current_steps": 1640, "total_steps": 4473, "loss": 0.3494, "lr": 3.1963104190220645e-05, "epoch": 2.5665101721439747, "percentage": 36.66, "elapsed_time": "4:07:06", "remaining_time": "7:06:52"}
{"current_steps": 1645, "total_steps": 4473, "loss": 0.3274, "lr": 3.1900463922040746e-05, "epoch": 2.5743348982785603, "percentage": 36.78, "elapsed_time": "4:07:50", "remaining_time": "7:06:04"}
{"current_steps": 1650, "total_steps": 4473, "loss": 0.346, "lr": 3.183764240665275e-05, "epoch": 2.5821596244131455, "percentage": 36.89, "elapsed_time": "4:08:24", "remaining_time": "7:04:59"}
{"current_steps": 1655, "total_steps": 4473, "loss": 0.3337, "lr": 3.177464060084492e-05, "epoch": 2.5899843505477307, "percentage": 37.0, "elapsed_time": "4:09:07", "remaining_time": "7:04:11"}
{"current_steps": 1660, "total_steps": 4473, "loss": 0.3217, "lr": 3.171145946415139e-05, "epoch": 2.5978090766823163, "percentage": 37.11, "elapsed_time": "4:09:51", "remaining_time": "7:03:24"}
{"current_steps": 1665, "total_steps": 4473, "loss": 0.3439, "lr": 3.164809995883757e-05, "epoch": 2.6056338028169015, "percentage": 37.22, "elapsed_time": "4:10:23", "remaining_time": "7:02:16"}
{"current_steps": 1670, "total_steps": 4473, "loss": 0.3409, "lr": 3.1584563049885444e-05, "epoch": 2.6134585289514867, "percentage": 37.34, "elapsed_time": "4:11:04", "remaining_time": "7:01:24"}
{"current_steps": 1675, "total_steps": 4473, "loss": 0.3523, "lr": 3.152084970497893e-05, "epoch": 2.621283255086072, "percentage": 37.45, "elapsed_time": "4:11:54", "remaining_time": "7:00:48"}
{"current_steps": 1680, "total_steps": 4473, "loss": 0.3756, "lr": 3.145696089448907e-05, "epoch": 2.629107981220657, "percentage": 37.56, "elapsed_time": "4:12:51", "remaining_time": "7:00:22"}
{"current_steps": 1685, "total_steps": 4473, "loss": 0.3534, "lr": 3.1392897591459343e-05, "epoch": 2.6369327073552427, "percentage": 37.67, "elapsed_time": "4:13:37", "remaining_time": "6:59:39"}
{"current_steps": 1690, "total_steps": 4473, "loss": 0.3306, "lr": 3.1328660771590766e-05, "epoch": 2.644757433489828, "percentage": 37.78, "elapsed_time": "4:14:36", "remaining_time": "6:59:16"}
{"current_steps": 1695, "total_steps": 4473, "loss": 0.3435, "lr": 3.126425141322707e-05, "epoch": 2.652582159624413, "percentage": 37.89, "elapsed_time": "4:15:18", "remaining_time": "6:58:26"}
{"current_steps": 1700, "total_steps": 4473, "loss": 0.3588, "lr": 3.119967049733977e-05, "epoch": 2.6604068857589986, "percentage": 38.01, "elapsed_time": "4:16:08", "remaining_time": "6:57:48"}
{"current_steps": 1705, "total_steps": 4473, "loss": 0.3613, "lr": 3.1134919007513295e-05, "epoch": 2.668231611893584, "percentage": 38.12, "elapsed_time": "4:16:47", "remaining_time": "6:56:54"}
{"current_steps": 1710, "total_steps": 4473, "loss": 0.3791, "lr": 3.106999792992993e-05, "epoch": 2.676056338028169, "percentage": 38.23, "elapsed_time": "4:17:25", "remaining_time": "6:55:56"}
{"current_steps": 1715, "total_steps": 4473, "loss": 0.3407, "lr": 3.100490825335482e-05, "epoch": 2.683881064162754, "percentage": 38.34, "elapsed_time": "4:18:02", "remaining_time": "6:54:58"}
{"current_steps": 1720, "total_steps": 4473, "loss": 0.3439, "lr": 3.093965096912094e-05, "epoch": 2.6917057902973394, "percentage": 38.45, "elapsed_time": "4:18:41", "remaining_time": "6:54:03"}
{"current_steps": 1725, "total_steps": 4473, "loss": 0.3302, "lr": 3.0874227071113936e-05, "epoch": 2.699530516431925, "percentage": 38.56, "elapsed_time": "4:19:18", "remaining_time": "6:53:06"}
{"current_steps": 1730, "total_steps": 4473, "loss": 0.3384, "lr": 3.080863755575709e-05, "epoch": 2.70735524256651, "percentage": 38.68, "elapsed_time": "4:19:58", "remaining_time": "6:52:11"}
{"current_steps": 1735, "total_steps": 4473, "loss": 0.3418, "lr": 3.074288342199601e-05, "epoch": 2.7151799687010953, "percentage": 38.79, "elapsed_time": "4:20:45", "remaining_time": "6:51:29"}
{"current_steps": 1740, "total_steps": 4473, "loss": 0.3184, "lr": 3.067696567128353e-05, "epoch": 2.723004694835681, "percentage": 38.9, "elapsed_time": "4:21:27", "remaining_time": "6:50:40"}
{"current_steps": 1745, "total_steps": 4473, "loss": 0.345, "lr": 3.06108853075644e-05, "epoch": 2.730829420970266, "percentage": 39.01, "elapsed_time": "4:22:09", "remaining_time": "6:49:49"}
{"current_steps": 1750, "total_steps": 4473, "loss": 0.3491, "lr": 3.054464333726e-05, "epoch": 2.7386541471048513, "percentage": 39.12, "elapsed_time": "4:22:54", "remaining_time": "6:49:05"}
{"current_steps": 1755, "total_steps": 4473, "loss": 0.3343, "lr": 3.0478240769253048e-05, "epoch": 2.7464788732394365, "percentage": 39.24, "elapsed_time": "4:23:34", "remaining_time": "6:48:12"}
{"current_steps": 1760, "total_steps": 4473, "loss": 0.3522, "lr": 3.0411678614872176e-05, "epoch": 2.7543035993740217, "percentage": 39.35, "elapsed_time": "4:24:13", "remaining_time": "6:47:17"}
{"current_steps": 1765, "total_steps": 4473, "loss": 0.3828, "lr": 3.0344957887876575e-05, "epoch": 2.7621283255086073, "percentage": 39.46, "elapsed_time": "4:24:54", "remaining_time": "6:46:25"}
{"current_steps": 1770, "total_steps": 4473, "loss": 0.3199, "lr": 3.0278079604440536e-05, "epoch": 2.7699530516431925, "percentage": 39.57, "elapsed_time": "4:25:43", "remaining_time": "6:45:47"}
{"current_steps": 1775, "total_steps": 4473, "loss": 0.3305, "lr": 3.0211044783137975e-05, "epoch": 2.7777777777777777, "percentage": 39.68, "elapsed_time": "4:26:40", "remaining_time": "6:45:20"}
{"current_steps": 1780, "total_steps": 4473, "loss": 0.3486, "lr": 3.014385444492693e-05, "epoch": 2.7856025039123633, "percentage": 39.79, "elapsed_time": "4:27:23", "remaining_time": "6:44:32"}
{"current_steps": 1785, "total_steps": 4473, "loss": 0.3686, "lr": 3.0076509613133988e-05, "epoch": 2.7934272300469485, "percentage": 39.91, "elapsed_time": "4:28:15", "remaining_time": "6:43:58"}
{"current_steps": 1790, "total_steps": 4473, "loss": 0.3502, "lr": 3.000901131343872e-05, "epoch": 2.8012519561815337, "percentage": 40.02, "elapsed_time": "4:29:01", "remaining_time": "6:43:13"}
{"current_steps": 1795, "total_steps": 4473, "loss": 0.3619, "lr": 2.9941360573858057e-05, "epoch": 2.809076682316119, "percentage": 40.13, "elapsed_time": "4:29:54", "remaining_time": "6:42:40"}
{"current_steps": 1800, "total_steps": 4473, "loss": 0.3558, "lr": 2.9873558424730634e-05, "epoch": 2.816901408450704, "percentage": 40.24, "elapsed_time": "4:30:35", "remaining_time": "6:41:49"}
{"current_steps": 1805, "total_steps": 4473, "loss": 0.3666, "lr": 2.9805605898701078e-05, "epoch": 2.8247261345852896, "percentage": 40.35, "elapsed_time": "4:31:24", "remaining_time": "6:41:09"}
{"current_steps": 1810, "total_steps": 4473, "loss": 0.3426, "lr": 2.9737504030704306e-05, "epoch": 2.832550860719875, "percentage": 40.47, "elapsed_time": "4:31:57", "remaining_time": "6:40:07"}
{"current_steps": 1815, "total_steps": 4473, "loss": 0.3488, "lr": 2.9669253857949757e-05, "epoch": 2.84037558685446, "percentage": 40.58, "elapsed_time": "4:32:38", "remaining_time": "6:39:16"}
{"current_steps": 1820, "total_steps": 4473, "loss": 0.3727, "lr": 2.960085641990557e-05, "epoch": 2.8482003129890456, "percentage": 40.69, "elapsed_time": "4:33:24", "remaining_time": "6:38:32"}
{"current_steps": 1825, "total_steps": 4473, "loss": 0.3534, "lr": 2.953231275828281e-05, "epoch": 2.856025039123631, "percentage": 40.8, "elapsed_time": "4:34:16", "remaining_time": "6:37:57"}
{"current_steps": 1830, "total_steps": 4473, "loss": 0.3554, "lr": 2.946362391701953e-05, "epoch": 2.863849765258216, "percentage": 40.91, "elapsed_time": "4:35:06", "remaining_time": "6:37:19"}
{"current_steps": 1835, "total_steps": 4473, "loss": 0.3544, "lr": 2.939479094226492e-05, "epoch": 2.871674491392801, "percentage": 41.02, "elapsed_time": "4:35:56", "remaining_time": "6:36:41"}
{"current_steps": 1840, "total_steps": 4473, "loss": 0.3474, "lr": 2.9325814882363367e-05, "epoch": 2.8794992175273864, "percentage": 41.14, "elapsed_time": "4:36:43", "remaining_time": "6:35:59"}
{"current_steps": 1845, "total_steps": 4473, "loss": 0.3525, "lr": 2.925669678783848e-05, "epoch": 2.887323943661972, "percentage": 41.25, "elapsed_time": "4:37:30", "remaining_time": "6:35:17"}
{"current_steps": 1850, "total_steps": 4473, "loss": 0.3352, "lr": 2.9187437711377086e-05, "epoch": 2.895148669796557, "percentage": 41.36, "elapsed_time": "4:38:11", "remaining_time": "6:34:25"}
{"current_steps": 1855, "total_steps": 4473, "loss": 0.3434, "lr": 2.9118038707813218e-05, "epoch": 2.9029733959311423, "percentage": 41.47, "elapsed_time": "4:38:46", "remaining_time": "6:33:25"}
{"current_steps": 1860, "total_steps": 4473, "loss": 0.3664, "lr": 2.904850083411201e-05, "epoch": 2.910798122065728, "percentage": 41.58, "elapsed_time": "4:39:28", "remaining_time": "6:32:36"}
{"current_steps": 1865, "total_steps": 4473, "loss": 0.3417, "lr": 2.8978825149353656e-05, "epoch": 2.918622848200313, "percentage": 41.69, "elapsed_time": "4:40:08", "remaining_time": "6:31:44"}
{"current_steps": 1870, "total_steps": 4473, "loss": 0.3377, "lr": 2.8909012714717222e-05, "epoch": 2.9264475743348983, "percentage": 41.81, "elapsed_time": "4:40:57", "remaining_time": "6:31:04"}
{"current_steps": 1875, "total_steps": 4473, "loss": 0.3332, "lr": 2.8839064593464542e-05, "epoch": 2.9342723004694835, "percentage": 41.92, "elapsed_time": "4:41:47", "remaining_time": "6:30:26"}
{"current_steps": 1880, "total_steps": 4473, "loss": 0.3533, "lr": 2.876898185092395e-05, "epoch": 2.9420970266040687, "percentage": 42.03, "elapsed_time": "4:42:25", "remaining_time": "6:29:31"}
{"current_steps": 1885, "total_steps": 4473, "loss": 0.3661, "lr": 2.869876555447414e-05, "epoch": 2.9499217527386543, "percentage": 42.14, "elapsed_time": "4:43:05", "remaining_time": "6:28:39"}
{"current_steps": 1890, "total_steps": 4473, "loss": 0.3234, "lr": 2.8628416773527837e-05, "epoch": 2.9577464788732395, "percentage": 42.25, "elapsed_time": "4:43:48", "remaining_time": "6:27:51"}
{"current_steps": 1895, "total_steps": 4473, "loss": 0.3519, "lr": 2.855793657951556e-05, "epoch": 2.9655712050078247, "percentage": 42.37, "elapsed_time": "4:44:35", "remaining_time": "6:27:09"}
{"current_steps": 1900, "total_steps": 4473, "loss": 0.3483, "lr": 2.8487326045869276e-05, "epoch": 2.97339593114241, "percentage": 42.48, "elapsed_time": "4:45:10", "remaining_time": "6:26:11"}
{"current_steps": 1905, "total_steps": 4473, "loss": 0.3572, "lr": 2.8416586248006056e-05, "epoch": 2.981220657276995, "percentage": 42.59, "elapsed_time": "4:45:55", "remaining_time": "6:25:25"}
{"current_steps": 1910, "total_steps": 4473, "loss": 0.3609, "lr": 2.83457182633117e-05, "epoch": 2.9890453834115807, "percentage": 42.7, "elapsed_time": "4:46:47", "remaining_time": "6:24:50"}
{"current_steps": 1915, "total_steps": 4473, "loss": 0.3409, "lr": 2.8274723171124327e-05, "epoch": 2.996870109546166, "percentage": 42.81, "elapsed_time": "4:47:27", "remaining_time": "6:23:58"}
{"current_steps": 1920, "total_steps": 4473, "loss": 0.3238, "lr": 2.8203602052717946e-05, "epoch": 3.004694835680751, "percentage": 42.92, "elapsed_time": "4:48:15", "remaining_time": "6:23:17"}
{"current_steps": 1925, "total_steps": 4473, "loss": 0.3188, "lr": 2.813235599128597e-05, "epoch": 3.0125195618153366, "percentage": 43.04, "elapsed_time": "4:49:01", "remaining_time": "6:22:33"}
{"current_steps": 1930, "total_steps": 4473, "loss": 0.3151, "lr": 2.806098607192472e-05, "epoch": 3.020344287949922, "percentage": 43.15, "elapsed_time": "4:49:45", "remaining_time": "6:21:47"}
{"current_steps": 1935, "total_steps": 4473, "loss": 0.2806, "lr": 2.7989493381616926e-05, "epoch": 3.028169014084507, "percentage": 43.26, "elapsed_time": "4:50:28", "remaining_time": "6:20:59"}
{"current_steps": 1940, "total_steps": 4473, "loss": 0.3016, "lr": 2.791787900921513e-05, "epoch": 3.035993740219092, "percentage": 43.37, "elapsed_time": "4:51:12", "remaining_time": "6:20:12"}
{"current_steps": 1945, "total_steps": 4473, "loss": 0.3457, "lr": 2.784614404542515e-05, "epoch": 3.043818466353678, "percentage": 43.48, "elapsed_time": "4:52:01", "remaining_time": "6:19:32"}
{"current_steps": 1950, "total_steps": 4473, "loss": 0.3154, "lr": 2.7774289582789407e-05, "epoch": 3.051643192488263, "percentage": 43.59, "elapsed_time": "4:52:59", "remaining_time": "6:19:04"}
{"current_steps": 1955, "total_steps": 4473, "loss": 0.2983, "lr": 2.7702316715670363e-05, "epoch": 3.059467918622848, "percentage": 43.71, "elapsed_time": "4:53:51", "remaining_time": "6:18:28"}
{"current_steps": 1960, "total_steps": 4473, "loss": 0.3025, "lr": 2.7630226540233775e-05, "epoch": 3.0672926447574334, "percentage": 43.82, "elapsed_time": "4:54:41", "remaining_time": "6:17:50"}
{"current_steps": 1965, "total_steps": 4473, "loss": 0.3328, "lr": 2.7558020154432054e-05, "epoch": 3.075117370892019, "percentage": 43.93, "elapsed_time": "4:55:24", "remaining_time": "6:17:02"}
{"current_steps": 1970, "total_steps": 4473, "loss": 0.321, "lr": 2.7485698657987528e-05, "epoch": 3.082942097026604, "percentage": 44.04, "elapsed_time": "4:56:13", "remaining_time": "6:16:22"}
{"current_steps": 1975, "total_steps": 4473, "loss": 0.3234, "lr": 2.7413263152375684e-05, "epoch": 3.0907668231611893, "percentage": 44.15, "elapsed_time": "4:56:49", "remaining_time": "6:15:25"}
{"current_steps": 1980, "total_steps": 4473, "loss": 0.307, "lr": 2.7340714740808404e-05, "epoch": 3.0985915492957745, "percentage": 44.27, "elapsed_time": "4:57:36", "remaining_time": "6:14:42"}
{"current_steps": 1985, "total_steps": 4473, "loss": 0.2995, "lr": 2.7268054528217144e-05, "epoch": 3.10641627543036, "percentage": 44.38, "elapsed_time": "4:58:17", "remaining_time": "6:13:52"}
{"current_steps": 1990, "total_steps": 4473, "loss": 0.3105, "lr": 2.7195283621236143e-05, "epoch": 3.1142410015649453, "percentage": 44.49, "elapsed_time": "4:58:57", "remaining_time": "6:13:00"}
{"current_steps": 1995, "total_steps": 4473, "loss": 0.3146, "lr": 2.7122403128185516e-05, "epoch": 3.1220657276995305, "percentage": 44.6, "elapsed_time": "4:59:34", "remaining_time": "6:12:06"}
{"current_steps": 2000, "total_steps": 4473, "loss": 0.319, "lr": 2.7049414159054435e-05, "epoch": 3.1298904538341157, "percentage": 44.71, "elapsed_time": "5:00:19", "remaining_time": "6:11:21"}
{"current_steps": 2005, "total_steps": 4473, "loss": 0.2991, "lr": 2.697631782548416e-05, "epoch": 3.1377151799687013, "percentage": 44.82, "elapsed_time": "5:01:02", "remaining_time": "6:10:33"}
{"current_steps": 2010, "total_steps": 4473, "loss": 0.3226, "lr": 2.6903115240751156e-05, "epoch": 3.1455399061032865, "percentage": 44.94, "elapsed_time": "5:01:47", "remaining_time": "6:09:48"}
{"current_steps": 2015, "total_steps": 4473, "loss": 0.3274, "lr": 2.6829807519750127e-05, "epoch": 3.1533646322378717, "percentage": 45.05, "elapsed_time": "5:02:43", "remaining_time": "6:09:16"}
{"current_steps": 2020, "total_steps": 4473, "loss": 0.3219, "lr": 2.6756395778977014e-05, "epoch": 3.161189358372457, "percentage": 45.16, "elapsed_time": "5:03:18", "remaining_time": "6:08:20"}
{"current_steps": 2025, "total_steps": 4473, "loss": 0.3071, "lr": 2.668288113651202e-05, "epoch": 3.169014084507042, "percentage": 45.27, "elapsed_time": "5:04:04", "remaining_time": "6:07:35"}
{"current_steps": 2030, "total_steps": 4473, "loss": 0.3106, "lr": 2.6609264712002557e-05, "epoch": 3.1768388106416277, "percentage": 45.38, "elapsed_time": "5:04:54", "remaining_time": "6:06:56"}
{"current_steps": 2035, "total_steps": 4473, "loss": 0.3358, "lr": 2.6535547626646222e-05, "epoch": 3.184663536776213, "percentage": 45.5, "elapsed_time": "5:05:47", "remaining_time": "6:06:20"}
{"current_steps": 2040, "total_steps": 4473, "loss": 0.3212, "lr": 2.646173100317368e-05, "epoch": 3.192488262910798, "percentage": 45.61, "elapsed_time": "5:06:39", "remaining_time": "6:05:43"}
{"current_steps": 2045, "total_steps": 4473, "loss": 0.3261, "lr": 2.63878159658316e-05, "epoch": 3.2003129890453836, "percentage": 45.72, "elapsed_time": "5:07:16", "remaining_time": "6:04:49"}
{"current_steps": 2050, "total_steps": 4473, "loss": 0.3164, "lr": 2.631380364036553e-05, "epoch": 3.208137715179969, "percentage": 45.83, "elapsed_time": "5:08:08", "remaining_time": "6:04:12"}
{"current_steps": 2055, "total_steps": 4473, "loss": 0.3095, "lr": 2.6239695154002718e-05, "epoch": 3.215962441314554, "percentage": 45.94, "elapsed_time": "5:08:51", "remaining_time": "6:03:25"}
{"current_steps": 2060, "total_steps": 4473, "loss": 0.3341, "lr": 2.616549163543499e-05, "epoch": 3.223787167449139, "percentage": 46.05, "elapsed_time": "5:09:45", "remaining_time": "6:02:50"}
{"current_steps": 2065, "total_steps": 4473, "loss": 0.3492, "lr": 2.6091194214801527e-05, "epoch": 3.2316118935837244, "percentage": 46.17, "elapsed_time": "5:10:29", "remaining_time": "6:02:04"}
{"current_steps": 2070, "total_steps": 4473, "loss": 0.3161, "lr": 2.601680402367166e-05, "epoch": 3.23943661971831, "percentage": 46.28, "elapsed_time": "5:11:12", "remaining_time": "6:01:16"}
{"current_steps": 2075, "total_steps": 4473, "loss": 0.298, "lr": 2.594232219502765e-05, "epoch": 3.247261345852895, "percentage": 46.39, "elapsed_time": "5:11:58", "remaining_time": "6:00:32"}
{"current_steps": 2080, "total_steps": 4473, "loss": 0.3264, "lr": 2.5867749863247415e-05, "epoch": 3.2550860719874803, "percentage": 46.5, "elapsed_time": "5:12:43", "remaining_time": "5:59:47"}
{"current_steps": 2085, "total_steps": 4473, "loss": 0.3352, "lr": 2.579308816408726e-05, "epoch": 3.262910798122066, "percentage": 46.61, "elapsed_time": "5:13:30", "remaining_time": "5:59:04"}
{"current_steps": 2090, "total_steps": 4473, "loss": 0.3345, "lr": 2.5718338234664577e-05, "epoch": 3.270735524256651, "percentage": 46.72, "elapsed_time": "5:14:17", "remaining_time": "5:58:21"}
{"current_steps": 2095, "total_steps": 4473, "loss": 0.3634, "lr": 2.5643501213440528e-05, "epoch": 3.2785602503912363, "percentage": 46.84, "elapsed_time": "5:14:58", "remaining_time": "5:57:31"}
{"current_steps": 2100, "total_steps": 4473, "loss": 0.3081, "lr": 2.556857824020272e-05, "epoch": 3.2863849765258215, "percentage": 46.95, "elapsed_time": "5:15:38", "remaining_time": "5:56:40"}
{"current_steps": 2105, "total_steps": 4473, "loss": 0.3006, "lr": 2.5493570456047808e-05, "epoch": 3.2942097026604067, "percentage": 47.06, "elapsed_time": "5:16:23", "remaining_time": "5:55:55"}
{"current_steps": 2110, "total_steps": 4473, "loss": 0.3298, "lr": 2.5418479003364157e-05, "epoch": 3.3020344287949923, "percentage": 47.17, "elapsed_time": "5:17:01", "remaining_time": "5:55:02"}
{"current_steps": 2115, "total_steps": 4473, "loss": 0.3158, "lr": 2.5343305025814426e-05, "epoch": 3.3098591549295775, "percentage": 47.28, "elapsed_time": "5:17:46", "remaining_time": "5:54:17"}
{"current_steps": 2120, "total_steps": 4473, "loss": 0.3319, "lr": 2.5268049668318133e-05, "epoch": 3.3176838810641627, "percentage": 47.4, "elapsed_time": "5:18:23", "remaining_time": "5:53:23"}
{"current_steps": 2125, "total_steps": 4473, "loss": 0.3132, "lr": 2.5192714077034257e-05, "epoch": 3.325508607198748, "percentage": 47.51, "elapsed_time": "5:19:03", "remaining_time": "5:52:31"}
{"current_steps": 2130, "total_steps": 4473, "loss": 0.3122, "lr": 2.511729939934374e-05, "epoch": 3.3333333333333335, "percentage": 47.62, "elapsed_time": "5:19:47", "remaining_time": "5:51:46"}
{"current_steps": 2135, "total_steps": 4473, "loss": 0.3017, "lr": 2.504180678383204e-05, "epoch": 3.3411580594679187, "percentage": 47.73, "elapsed_time": "5:20:34", "remaining_time": "5:51:03"}
{"current_steps": 2140, "total_steps": 4473, "loss": 0.3007, "lr": 2.4966237380271623e-05, "epoch": 3.348982785602504, "percentage": 47.84, "elapsed_time": "5:21:15", "remaining_time": "5:50:14"}
{"current_steps": 2145, "total_steps": 4473, "loss": 0.2967, "lr": 2.489059233960447e-05, "epoch": 3.356807511737089, "percentage": 47.95, "elapsed_time": "5:22:06", "remaining_time": "5:49:35"}
{"current_steps": 2150, "total_steps": 4473, "loss": 0.3179, "lr": 2.481487281392452e-05, "epoch": 3.3646322378716746, "percentage": 48.07, "elapsed_time": "5:23:00", "remaining_time": "5:48:59"}
{"current_steps": 2155, "total_steps": 4473, "loss": 0.3092, "lr": 2.473907995646014e-05, "epoch": 3.37245696400626, "percentage": 48.18, "elapsed_time": "5:23:49", "remaining_time": "5:48:19"}
{"current_steps": 2160, "total_steps": 4473, "loss": 0.3331, "lr": 2.4663214921556576e-05, "epoch": 3.380281690140845, "percentage": 48.29, "elapsed_time": "5:24:39", "remaining_time": "5:47:39"}
{"current_steps": 2165, "total_steps": 4473, "loss": 0.3242, "lr": 2.458727886465833e-05, "epoch": 3.38810641627543, "percentage": 48.4, "elapsed_time": "5:25:30", "remaining_time": "5:47:00"}
{"current_steps": 2170, "total_steps": 4473, "loss": 0.3101, "lr": 2.4511272942291615e-05, "epoch": 3.395931142410016, "percentage": 48.51, "elapsed_time": "5:26:08", "remaining_time": "5:46:07"}
{"current_steps": 2175, "total_steps": 4473, "loss": 0.3213, "lr": 2.443519831204668e-05, "epoch": 3.403755868544601, "percentage": 48.63, "elapsed_time": "5:26:57", "remaining_time": "5:45:27"}
{"current_steps": 2180, "total_steps": 4473, "loss": 0.3256, "lr": 2.4359056132560258e-05, "epoch": 3.411580594679186, "percentage": 48.74, "elapsed_time": "5:27:35", "remaining_time": "5:44:34"}
{"current_steps": 2185, "total_steps": 4473, "loss": 0.3436, "lr": 2.4282847563497826e-05, "epoch": 3.4194053208137714, "percentage": 48.85, "elapsed_time": "5:28:13", "remaining_time": "5:43:42"}
{"current_steps": 2190, "total_steps": 4473, "loss": 0.3376, "lr": 2.4206573765536034e-05, "epoch": 3.427230046948357, "percentage": 48.96, "elapsed_time": "5:29:00", "remaining_time": "5:42:59"}
{"current_steps": 2195, "total_steps": 4473, "loss": 0.3398, "lr": 2.4130235900344958e-05, "epoch": 3.435054773082942, "percentage": 49.07, "elapsed_time": "5:29:51", "remaining_time": "5:42:20"}
{"current_steps": 2200, "total_steps": 4473, "loss": 0.3151, "lr": 2.4053835130570433e-05, "epoch": 3.4428794992175273, "percentage": 49.18, "elapsed_time": "5:30:28", "remaining_time": "5:41:26"}
{"current_steps": 2205, "total_steps": 4473, "loss": 0.3449, "lr": 2.3977372619816378e-05, "epoch": 3.4507042253521125, "percentage": 49.3, "elapsed_time": "5:31:15", "remaining_time": "5:40:43"}
{"current_steps": 2210, "total_steps": 4473, "loss": 0.3504, "lr": 2.390084953262701e-05, "epoch": 3.458528951486698, "percentage": 49.41, "elapsed_time": "5:32:01", "remaining_time": "5:39:59"}
{"current_steps": 2215, "total_steps": 4473, "loss": 0.3257, "lr": 2.3824267034469163e-05, "epoch": 3.4663536776212833, "percentage": 49.52, "elapsed_time": "5:32:45", "remaining_time": "5:39:13"}
{"current_steps": 2220, "total_steps": 4473, "loss": 0.3347, "lr": 2.37476262917145e-05, "epoch": 3.4741784037558685, "percentage": 49.63, "elapsed_time": "5:33:16", "remaining_time": "5:38:14"}
{"current_steps": 2225, "total_steps": 4473, "loss": 0.3316, "lr": 2.3670928471621766e-05, "epoch": 3.4820031298904537, "percentage": 49.74, "elapsed_time": "5:34:12", "remaining_time": "5:37:40"}
{"current_steps": 2230, "total_steps": 4473, "loss": 0.2904, "lr": 2.3594174742319035e-05, "epoch": 3.4898278560250393, "percentage": 49.85, "elapsed_time": "5:34:56", "remaining_time": "5:36:53"}
{"current_steps": 2235, "total_steps": 4473, "loss": 0.3234, "lr": 2.3517366272785856e-05, "epoch": 3.4976525821596245, "percentage": 49.97, "elapsed_time": "5:35:36", "remaining_time": "5:36:03"}
{"current_steps": 2240, "total_steps": 4473, "loss": 0.329, "lr": 2.3440504232835508e-05, "epoch": 3.5054773082942097, "percentage": 50.08, "elapsed_time": "5:36:35", "remaining_time": "5:35:32"}
{"current_steps": 2245, "total_steps": 4473, "loss": 0.3479, "lr": 2.3363589793097153e-05, "epoch": 3.513302034428795, "percentage": 50.19, "elapsed_time": "5:37:29", "remaining_time": "5:34:56"}
{"current_steps": 2250, "total_steps": 4473, "loss": 0.3338, "lr": 2.3286624124998028e-05, "epoch": 3.52112676056338, "percentage": 50.3, "elapsed_time": "5:38:06", "remaining_time": "5:34:02"}
{"current_steps": 2255, "total_steps": 4473, "loss": 0.3365, "lr": 2.3209608400745572e-05, "epoch": 3.5289514866979657, "percentage": 50.41, "elapsed_time": "5:38:56", "remaining_time": "5:33:22"}
{"current_steps": 2260, "total_steps": 4473, "loss": 0.3163, "lr": 2.313254379330961e-05, "epoch": 3.536776212832551, "percentage": 50.53, "elapsed_time": "5:39:35", "remaining_time": "5:32:31"}
{"current_steps": 2265, "total_steps": 4473, "loss": 0.3412, "lr": 2.305543147640446e-05, "epoch": 3.544600938967136, "percentage": 50.64, "elapsed_time": "5:40:37", "remaining_time": "5:32:03"}
{"current_steps": 2270, "total_steps": 4473, "loss": 0.328, "lr": 2.2978272624471073e-05, "epoch": 3.5524256651017216, "percentage": 50.75, "elapsed_time": "5:41:39", "remaining_time": "5:31:34"}
{"current_steps": 2275, "total_steps": 4473, "loss": 0.3065, "lr": 2.2901068412659143e-05, "epoch": 3.560250391236307, "percentage": 50.86, "elapsed_time": "5:42:28", "remaining_time": "5:30:52"}
{"current_steps": 2280, "total_steps": 4473, "loss": 0.3251, "lr": 2.2823820016809197e-05, "epoch": 3.568075117370892, "percentage": 50.97, "elapsed_time": "5:43:14", "remaining_time": "5:30:08"}
{"current_steps": 2285, "total_steps": 4473, "loss": 0.3207, "lr": 2.2746528613434708e-05, "epoch": 3.575899843505477, "percentage": 51.08, "elapsed_time": "5:43:58", "remaining_time": "5:29:21"}
{"current_steps": 2290, "total_steps": 4473, "loss": 0.334, "lr": 2.266919537970415e-05, "epoch": 3.5837245696400624, "percentage": 51.2, "elapsed_time": "5:44:30", "remaining_time": "5:28:24"}
{"current_steps": 2295, "total_steps": 4473, "loss": 0.343, "lr": 2.2591821493423113e-05, "epoch": 3.591549295774648, "percentage": 51.31, "elapsed_time": "5:45:04", "remaining_time": "5:27:28"}
{"current_steps": 2300, "total_steps": 4473, "loss": 0.324, "lr": 2.25144081330163e-05, "epoch": 3.599374021909233, "percentage": 51.42, "elapsed_time": "5:45:45", "remaining_time": "5:26:40"}
{"current_steps": 2305, "total_steps": 4473, "loss": 0.3198, "lr": 2.243695647750964e-05, "epoch": 3.6071987480438183, "percentage": 51.53, "elapsed_time": "5:46:26", "remaining_time": "5:25:50"}
{"current_steps": 2310, "total_steps": 4473, "loss": 0.3177, "lr": 2.2359467706512293e-05, "epoch": 3.615023474178404, "percentage": 51.64, "elapsed_time": "5:47:06", "remaining_time": "5:25:01"}
{"current_steps": 2315, "total_steps": 4473, "loss": 0.3258, "lr": 2.2281943000198716e-05, "epoch": 3.622848200312989, "percentage": 51.75, "elapsed_time": "5:47:47", "remaining_time": "5:24:12"}
{"current_steps": 2320, "total_steps": 4473, "loss": 0.3403, "lr": 2.2204383539290645e-05, "epoch": 3.6306729264475743, "percentage": 51.87, "elapsed_time": "5:48:31", "remaining_time": "5:23:26"}
{"current_steps": 2325, "total_steps": 4473, "loss": 0.3311, "lr": 2.212679050503916e-05, "epoch": 3.6384976525821595, "percentage": 51.98, "elapsed_time": "5:49:13", "remaining_time": "5:22:37"}
{"current_steps": 2330, "total_steps": 4473, "loss": 0.3023, "lr": 2.204916507920666e-05, "epoch": 3.6463223787167447, "percentage": 52.09, "elapsed_time": "5:49:56", "remaining_time": "5:21:50"}
{"current_steps": 2335, "total_steps": 4473, "loss": 0.321, "lr": 2.1971508444048874e-05, "epoch": 3.6541471048513303, "percentage": 52.2, "elapsed_time": "5:50:58", "remaining_time": "5:21:22"}
{"current_steps": 2340, "total_steps": 4473, "loss": 0.333, "lr": 2.1893821782296873e-05, "epoch": 3.6619718309859155, "percentage": 52.31, "elapsed_time": "5:51:36", "remaining_time": "5:20:30"}
{"current_steps": 2345, "total_steps": 4473, "loss": 0.3237, "lr": 2.1816106277139015e-05, "epoch": 3.6697965571205007, "percentage": 52.43, "elapsed_time": "5:52:24", "remaining_time": "5:19:48"}
{"current_steps": 2350, "total_steps": 4473, "loss": 0.3224, "lr": 2.1738363112202982e-05, "epoch": 3.6776212832550863, "percentage": 52.54, "elapsed_time": "5:53:08", "remaining_time": "5:19:01"}
{"current_steps": 2355, "total_steps": 4473, "loss": 0.3313, "lr": 2.1660593471537697e-05, "epoch": 3.6854460093896715, "percentage": 52.65, "elapsed_time": "5:53:50", "remaining_time": "5:18:13"}
{"current_steps": 2360, "total_steps": 4473, "loss": 0.3511, "lr": 2.158279853959532e-05, "epoch": 3.6932707355242567, "percentage": 52.76, "elapsed_time": "5:54:18", "remaining_time": "5:17:13"}
{"current_steps": 2365, "total_steps": 4473, "loss": 0.3158, "lr": 2.1504979501213224e-05, "epoch": 3.701095461658842, "percentage": 52.87, "elapsed_time": "5:55:14", "remaining_time": "5:16:38"}
{"current_steps": 2370, "total_steps": 4473, "loss": 0.3178, "lr": 2.1427137541595894e-05, "epoch": 3.708920187793427, "percentage": 52.98, "elapsed_time": "5:55:58", "remaining_time": "5:15:51"}
{"current_steps": 2375, "total_steps": 4473, "loss": 0.3207, "lr": 2.134927384629695e-05, "epoch": 3.7167449139280127, "percentage": 53.1, "elapsed_time": "5:56:37", "remaining_time": "5:15:02"}
{"current_steps": 2380, "total_steps": 4473, "loss": 0.3226, "lr": 2.127138960120101e-05, "epoch": 3.724569640062598, "percentage": 53.21, "elapsed_time": "5:57:24", "remaining_time": "5:14:18"}
{"current_steps": 2385, "total_steps": 4473, "loss": 0.3275, "lr": 2.1193485992505715e-05, "epoch": 3.732394366197183, "percentage": 53.32, "elapsed_time": "5:58:09", "remaining_time": "5:13:33"}
{"current_steps": 2390, "total_steps": 4473, "loss": 0.3105, "lr": 2.1115564206703584e-05, "epoch": 3.7402190923317686, "percentage": 53.43, "elapsed_time": "5:58:55", "remaining_time": "5:12:49"}
{"current_steps": 2395, "total_steps": 4473, "loss": 0.3004, "lr": 2.1037625430564003e-05, "epoch": 3.748043818466354, "percentage": 53.54, "elapsed_time": "5:59:44", "remaining_time": "5:12:07"}
{"current_steps": 2400, "total_steps": 4473, "loss": 0.3231, "lr": 2.09596708511151e-05, "epoch": 3.755868544600939, "percentage": 53.66, "elapsed_time": "6:00:25", "remaining_time": "5:11:18"}
{"current_steps": 2405, "total_steps": 4473, "loss": 0.3441, "lr": 2.0881701655625713e-05, "epoch": 3.763693270735524, "percentage": 53.77, "elapsed_time": "6:01:01", "remaining_time": "5:10:26"}
{"current_steps": 2410, "total_steps": 4473, "loss": 0.3228, "lr": 2.0803719031587282e-05, "epoch": 3.7715179968701094, "percentage": 53.88, "elapsed_time": "6:01:52", "remaining_time": "5:09:45"}
{"current_steps": 2415, "total_steps": 4473, "loss": 0.3327, "lr": 2.0725724166695765e-05, "epoch": 3.779342723004695, "percentage": 53.99, "elapsed_time": "6:02:33", "remaining_time": "5:08:57"}
{"current_steps": 2420, "total_steps": 4473, "loss": 0.3033, "lr": 2.064771824883354e-05, "epoch": 3.78716744913928, "percentage": 54.1, "elapsed_time": "6:03:17", "remaining_time": "5:08:12"}
{"current_steps": 2425, "total_steps": 4473, "loss": 0.3038, "lr": 2.0569702466051344e-05, "epoch": 3.7949921752738653, "percentage": 54.21, "elapsed_time": "6:03:59", "remaining_time": "5:07:24"}
{"current_steps": 2430, "total_steps": 4473, "loss": 0.3094, "lr": 2.0491678006550152e-05, "epoch": 3.802816901408451, "percentage": 54.33, "elapsed_time": "6:04:41", "remaining_time": "5:06:36"}
{"current_steps": 2435, "total_steps": 4473, "loss": 0.3331, "lr": 2.0413646058663076e-05, "epoch": 3.810641627543036, "percentage": 54.44, "elapsed_time": "6:05:32", "remaining_time": "5:05:56"}
{"current_steps": 2440, "total_steps": 4473, "loss": 0.3037, "lr": 2.0335607810837293e-05, "epoch": 3.8184663536776213, "percentage": 54.55, "elapsed_time": "6:06:14", "remaining_time": "5:05:09"}
{"current_steps": 2445, "total_steps": 4473, "loss": 0.3145, "lr": 2.0257564451615933e-05, "epoch": 3.8262910798122065, "percentage": 54.66, "elapsed_time": "6:06:59", "remaining_time": "5:04:24"}
{"current_steps": 2450, "total_steps": 4473, "loss": 0.3139, "lr": 2.017951716961996e-05, "epoch": 3.8341158059467917, "percentage": 54.77, "elapsed_time": "6:07:35", "remaining_time": "5:03:31"}
{"current_steps": 2455, "total_steps": 4473, "loss": 0.3312, "lr": 2.010146715353009e-05, "epoch": 3.8419405320813773, "percentage": 54.88, "elapsed_time": "6:08:13", "remaining_time": "5:02:41"}
{"current_steps": 2460, "total_steps": 4473, "loss": 0.3123, "lr": 2.002341559206867e-05, "epoch": 3.8497652582159625, "percentage": 55.0, "elapsed_time": "6:08:55", "remaining_time": "5:01:53"}
{"current_steps": 2465, "total_steps": 4473, "loss": 0.321, "lr": 1.99453636739816e-05, "epoch": 3.8575899843505477, "percentage": 55.11, "elapsed_time": "6:09:42", "remaining_time": "5:01:10"}
{"current_steps": 2470, "total_steps": 4473, "loss": 0.3216, "lr": 1.986731258802021e-05, "epoch": 3.865414710485133, "percentage": 55.22, "elapsed_time": "6:10:25", "remaining_time": "5:00:23"}
{"current_steps": 2475, "total_steps": 4473, "loss": 0.3292, "lr": 1.978926352292314e-05, "epoch": 3.873239436619718, "percentage": 55.33, "elapsed_time": "6:11:24", "remaining_time": "4:59:49"}
{"current_steps": 2480, "total_steps": 4473, "loss": 0.3119, "lr": 1.9711217667398264e-05, "epoch": 3.8810641627543037, "percentage": 55.44, "elapsed_time": "6:12:05", "remaining_time": "4:59:01"}
{"current_steps": 2485, "total_steps": 4473, "loss": 0.3272, "lr": 1.9633176210104572e-05, "epoch": 3.888888888888889, "percentage": 55.56, "elapsed_time": "6:12:39", "remaining_time": "4:58:07"}
{"current_steps": 2490, "total_steps": 4473, "loss": 0.2976, "lr": 1.9555140339634064e-05, "epoch": 3.896713615023474, "percentage": 55.67, "elapsed_time": "6:13:22", "remaining_time": "4:57:21"}
{"current_steps": 2495, "total_steps": 4473, "loss": 0.329, "lr": 1.9477111244493672e-05, "epoch": 3.9045383411580596, "percentage": 55.78, "elapsed_time": "6:13:51", "remaining_time": "4:56:23"}
{"current_steps": 2500, "total_steps": 4473, "loss": 0.303, "lr": 1.9399090113087092e-05, "epoch": 3.912363067292645, "percentage": 55.89, "elapsed_time": "6:14:39", "remaining_time": "4:55:40"}
{"current_steps": 2505, "total_steps": 4473, "loss": 0.3329, "lr": 1.932107813369678e-05, "epoch": 3.92018779342723, "percentage": 56.0, "elapsed_time": "6:15:08", "remaining_time": "4:54:43"}
{"current_steps": 2510, "total_steps": 4473, "loss": 0.319, "lr": 1.9243076494465766e-05, "epoch": 3.928012519561815, "percentage": 56.11, "elapsed_time": "6:15:54", "remaining_time": "4:53:59"}
{"current_steps": 2515, "total_steps": 4473, "loss": 0.3017, "lr": 1.916508638337964e-05, "epoch": 3.9358372456964004, "percentage": 56.23, "elapsed_time": "6:16:37", "remaining_time": "4:53:12"}
{"current_steps": 2520, "total_steps": 4473, "loss": 0.2981, "lr": 1.9087108988248357e-05, "epoch": 3.943661971830986, "percentage": 56.34, "elapsed_time": "6:17:27", "remaining_time": "4:52:31"}
{"current_steps": 2525, "total_steps": 4473, "loss": 0.321, "lr": 1.9009145496688255e-05, "epoch": 3.951486697965571, "percentage": 56.45, "elapsed_time": "6:18:06", "remaining_time": "4:51:41"}
{"current_steps": 2530, "total_steps": 4473, "loss": 0.3331, "lr": 1.8931197096103892e-05, "epoch": 3.9593114241001564, "percentage": 56.56, "elapsed_time": "6:18:54", "remaining_time": "4:51:00"}
{"current_steps": 2535, "total_steps": 4473, "loss": 0.3129, "lr": 1.8853264973669997e-05, "epoch": 3.967136150234742, "percentage": 56.67, "elapsed_time": "6:19:51", "remaining_time": "4:50:23"}
{"current_steps": 2540, "total_steps": 4473, "loss": 0.3359, "lr": 1.877535031631338e-05, "epoch": 3.974960876369327, "percentage": 56.79, "elapsed_time": "6:20:41", "remaining_time": "4:49:42"}
{"current_steps": 2545, "total_steps": 4473, "loss": 0.2874, "lr": 1.8697454310694832e-05, "epoch": 3.9827856025039123, "percentage": 56.9, "elapsed_time": "6:21:26", "remaining_time": "4:48:57"}
{"current_steps": 2550, "total_steps": 4473, "loss": 0.298, "lr": 1.8619578143191096e-05, "epoch": 3.9906103286384975, "percentage": 57.01, "elapsed_time": "6:22:00", "remaining_time": "4:48:04"}
{"current_steps": 2555, "total_steps": 4473, "loss": 0.2927, "lr": 1.854172299987677e-05, "epoch": 3.9984350547730827, "percentage": 57.12, "elapsed_time": "6:22:57", "remaining_time": "4:47:28"}
{"current_steps": 2560, "total_steps": 4473, "loss": 0.2858, "lr": 1.8463890066506253e-05, "epoch": 4.006259780907668, "percentage": 57.23, "elapsed_time": "6:23:26", "remaining_time": "4:46:31"}
{"current_steps": 2565, "total_steps": 4473, "loss": 0.2918, "lr": 1.838608052849566e-05, "epoch": 4.014084507042254, "percentage": 57.34, "elapsed_time": "6:24:19", "remaining_time": "4:45:52"}
{"current_steps": 2570, "total_steps": 4473, "loss": 0.305, "lr": 1.8308295570904803e-05, "epoch": 4.021909233176839, "percentage": 57.46, "elapsed_time": "6:25:09", "remaining_time": "4:45:11"}
{"current_steps": 2575, "total_steps": 4473, "loss": 0.2864, "lr": 1.823053637841913e-05, "epoch": 4.029733959311424, "percentage": 57.57, "elapsed_time": "6:25:48", "remaining_time": "4:44:22"}
{"current_steps": 2580, "total_steps": 4473, "loss": 0.3067, "lr": 1.8152804135331688e-05, "epoch": 4.037558685446009, "percentage": 57.68, "elapsed_time": "6:26:28", "remaining_time": "4:43:33"}
{"current_steps": 2585, "total_steps": 4473, "loss": 0.279, "lr": 1.8075100025525052e-05, "epoch": 4.045383411580595, "percentage": 57.79, "elapsed_time": "6:27:20", "remaining_time": "4:42:54"}
{"current_steps": 2590, "total_steps": 4473, "loss": 0.2684, "lr": 1.7997425232453335e-05, "epoch": 4.05320813771518, "percentage": 57.9, "elapsed_time": "6:28:02", "remaining_time": "4:42:07"}
{"current_steps": 2595, "total_steps": 4473, "loss": 0.2879, "lr": 1.7919780939124154e-05, "epoch": 4.061032863849765, "percentage": 58.01, "elapsed_time": "6:28:57", "remaining_time": "4:41:29"}
{"current_steps": 2600, "total_steps": 4473, "loss": 0.2998, "lr": 1.7842168328080593e-05, "epoch": 4.068857589984351, "percentage": 58.13, "elapsed_time": "6:29:31", "remaining_time": "4:40:36"}
{"current_steps": 2605, "total_steps": 4473, "loss": 0.2959, "lr": 1.7764588581383218e-05, "epoch": 4.076682316118935, "percentage": 58.24, "elapsed_time": "6:30:21", "remaining_time": "4:39:55"}
{"current_steps": 2610, "total_steps": 4473, "loss": 0.3103, "lr": 1.768704288059205e-05, "epoch": 4.084507042253521, "percentage": 58.35, "elapsed_time": "6:30:58", "remaining_time": "4:39:04"}
{"current_steps": 2615, "total_steps": 4473, "loss": 0.3013, "lr": 1.7609532406748605e-05, "epoch": 4.092331768388107, "percentage": 58.46, "elapsed_time": "6:31:48", "remaining_time": "4:38:23"}
{"current_steps": 2620, "total_steps": 4473, "loss": 0.2924, "lr": 1.753205834035785e-05, "epoch": 4.100156494522691, "percentage": 58.57, "elapsed_time": "6:32:32", "remaining_time": "4:37:37"}
{"current_steps": 2625, "total_steps": 4473, "loss": 0.2909, "lr": 1.7454621861370286e-05, "epoch": 4.107981220657277, "percentage": 58.69, "elapsed_time": "6:33:10", "remaining_time": "4:36:47"}
{"current_steps": 2630, "total_steps": 4473, "loss": 0.2999, "lr": 1.7377224149163945e-05, "epoch": 4.115805946791863, "percentage": 58.8, "elapsed_time": "6:33:46", "remaining_time": "4:35:56"}
{"current_steps": 2635, "total_steps": 4473, "loss": 0.2924, "lr": 1.7299866382526402e-05, "epoch": 4.123630672926447, "percentage": 58.91, "elapsed_time": "6:34:34", "remaining_time": "4:35:13"}
{"current_steps": 2640, "total_steps": 4473, "loss": 0.2839, "lr": 1.7222549739636875e-05, "epoch": 4.131455399061033, "percentage": 59.02, "elapsed_time": "6:35:15", "remaining_time": "4:34:26"}
{"current_steps": 2645, "total_steps": 4473, "loss": 0.2995, "lr": 1.714527539804826e-05, "epoch": 4.139280125195619, "percentage": 59.13, "elapsed_time": "6:36:06", "remaining_time": "4:33:45"}
{"current_steps": 2650, "total_steps": 4473, "loss": 0.3086, "lr": 1.7068044534669196e-05, "epoch": 4.147104851330203, "percentage": 59.24, "elapsed_time": "6:36:58", "remaining_time": "4:33:05"}
{"current_steps": 2655, "total_steps": 4473, "loss": 0.2938, "lr": 1.6990858325746102e-05, "epoch": 4.154929577464789, "percentage": 59.36, "elapsed_time": "6:37:34", "remaining_time": "4:32:14"}
{"current_steps": 2660, "total_steps": 4473, "loss": 0.3091, "lr": 1.6913717946845335e-05, "epoch": 4.162754303599374, "percentage": 59.47, "elapsed_time": "6:38:23", "remaining_time": "4:31:32"}
{"current_steps": 2665, "total_steps": 4473, "loss": 0.3078, "lr": 1.6836624572835236e-05, "epoch": 4.170579029733959, "percentage": 59.58, "elapsed_time": "6:38:55", "remaining_time": "4:30:38"}
{"current_steps": 2670, "total_steps": 4473, "loss": 0.3254, "lr": 1.6759579377868246e-05, "epoch": 4.178403755868545, "percentage": 59.69, "elapsed_time": "6:39:45", "remaining_time": "4:29:56"}
{"current_steps": 2675, "total_steps": 4473, "loss": 0.3057, "lr": 1.6682583535363046e-05, "epoch": 4.18622848200313, "percentage": 59.8, "elapsed_time": "6:40:25", "remaining_time": "4:29:08"}
{"current_steps": 2680, "total_steps": 4473, "loss": 0.2729, "lr": 1.6605638217986622e-05, "epoch": 4.194053208137715, "percentage": 59.92, "elapsed_time": "6:41:06", "remaining_time": "4:28:21"}
{"current_steps": 2685, "total_steps": 4473, "loss": 0.2888, "lr": 1.6528744597636497e-05, "epoch": 4.2018779342723, "percentage": 60.03, "elapsed_time": "6:41:55", "remaining_time": "4:27:39"}
{"current_steps": 2690, "total_steps": 4473, "loss": 0.2908, "lr": 1.6451903845422804e-05, "epoch": 4.209702660406886, "percentage": 60.14, "elapsed_time": "6:42:32", "remaining_time": "4:26:48"}
{"current_steps": 2695, "total_steps": 4473, "loss": 0.2875, "lr": 1.6375117131650507e-05, "epoch": 4.217527386541471, "percentage": 60.25, "elapsed_time": "6:43:10", "remaining_time": "4:25:59"}
{"current_steps": 2700, "total_steps": 4473, "loss": 0.2984, "lr": 1.629838562580151e-05, "epoch": 4.225352112676056, "percentage": 60.36, "elapsed_time": "6:44:12", "remaining_time": "4:25:25"}
{"current_steps": 2705, "total_steps": 4473, "loss": 0.2892, "lr": 1.6221710496516922e-05, "epoch": 4.233176838810642, "percentage": 60.47, "elapsed_time": "6:44:45", "remaining_time": "4:24:33"}
{"current_steps": 2710, "total_steps": 4473, "loss": 0.3012, "lr": 1.614509291157921e-05, "epoch": 4.241001564945227, "percentage": 60.59, "elapsed_time": "6:45:29", "remaining_time": "4:23:47"}
{"current_steps": 2715, "total_steps": 4473, "loss": 0.3083, "lr": 1.606853403789443e-05, "epoch": 4.248826291079812, "percentage": 60.7, "elapsed_time": "6:46:23", "remaining_time": "4:23:08"}
{"current_steps": 2720, "total_steps": 4473, "loss": 0.273, "lr": 1.5992035041474437e-05, "epoch": 4.256651017214398, "percentage": 60.81, "elapsed_time": "6:47:15", "remaining_time": "4:22:28"}
{"current_steps": 2725, "total_steps": 4473, "loss": 0.2918, "lr": 1.591559708741915e-05, "epoch": 4.264475743348982, "percentage": 60.92, "elapsed_time": "6:48:03", "remaining_time": "4:21:45"}
{"current_steps": 2730, "total_steps": 4473, "loss": 0.2985, "lr": 1.5839221339898787e-05, "epoch": 4.272300469483568, "percentage": 61.03, "elapsed_time": "6:48:57", "remaining_time": "4:21:06"}
{"current_steps": 2735, "total_steps": 4473, "loss": 0.2856, "lr": 1.576290896213617e-05, "epoch": 4.280125195618154, "percentage": 61.14, "elapsed_time": "6:49:40", "remaining_time": "4:20:20"}
{"current_steps": 2740, "total_steps": 4473, "loss": 0.3129, "lr": 1.5686661116388947e-05, "epoch": 4.287949921752738, "percentage": 61.26, "elapsed_time": "6:50:25", "remaining_time": "4:19:35"}
{"current_steps": 2745, "total_steps": 4473, "loss": 0.2935, "lr": 1.5610478963931953e-05, "epoch": 4.295774647887324, "percentage": 61.37, "elapsed_time": "6:51:13", "remaining_time": "4:18:52"}
{"current_steps": 2750, "total_steps": 4473, "loss": 0.3149, "lr": 1.5534363665039482e-05, "epoch": 4.30359937402191, "percentage": 61.48, "elapsed_time": "6:51:41", "remaining_time": "4:17:56"}
{"current_steps": 2755, "total_steps": 4473, "loss": 0.3114, "lr": 1.5458316378967638e-05, "epoch": 4.311424100156494, "percentage": 61.59, "elapsed_time": "6:52:27", "remaining_time": "4:17:12"}
{"current_steps": 2760, "total_steps": 4473, "loss": 0.2715, "lr": 1.5382338263936663e-05, "epoch": 4.31924882629108, "percentage": 61.7, "elapsed_time": "6:53:08", "remaining_time": "4:16:24"}
{"current_steps": 2765, "total_steps": 4473, "loss": 0.291, "lr": 1.5306430477113336e-05, "epoch": 4.327073552425665, "percentage": 61.82, "elapsed_time": "6:53:50", "remaining_time": "4:15:38"}
{"current_steps": 2770, "total_steps": 4473, "loss": 0.3056, "lr": 1.5230594174593267e-05, "epoch": 4.33489827856025, "percentage": 61.93, "elapsed_time": "6:54:35", "remaining_time": "4:14:53"}
{"current_steps": 2775, "total_steps": 4473, "loss": 0.3125, "lr": 1.515483051138338e-05, "epoch": 4.342723004694836, "percentage": 62.04, "elapsed_time": "6:55:16", "remaining_time": "4:14:06"}
{"current_steps": 2780, "total_steps": 4473, "loss": 0.3121, "lr": 1.5079140641384275e-05, "epoch": 4.350547730829421, "percentage": 62.15, "elapsed_time": "6:56:04", "remaining_time": "4:13:23"}
{"current_steps": 2785, "total_steps": 4473, "loss": 0.2961, "lr": 1.5003525717372669e-05, "epoch": 4.358372456964006, "percentage": 62.26, "elapsed_time": "6:56:44", "remaining_time": "4:12:35"}
{"current_steps": 2790, "total_steps": 4473, "loss": 0.3117, "lr": 1.4927986890983801e-05, "epoch": 4.366197183098592, "percentage": 62.37, "elapsed_time": "6:57:14", "remaining_time": "4:11:41"}
{"current_steps": 2795, "total_steps": 4473, "loss": 0.2823, "lr": 1.4852525312693958e-05, "epoch": 4.374021909233177, "percentage": 62.49, "elapsed_time": "6:57:54", "remaining_time": "4:10:53"}
{"current_steps": 2800, "total_steps": 4473, "loss": 0.2648, "lr": 1.4777142131802897e-05, "epoch": 4.381846635367762, "percentage": 62.6, "elapsed_time": "6:58:33", "remaining_time": "4:10:05"}
{"current_steps": 2805, "total_steps": 4473, "loss": 0.3008, "lr": 1.4701838496416379e-05, "epoch": 4.389671361502347, "percentage": 62.71, "elapsed_time": "6:59:08", "remaining_time": "4:09:14"}
{"current_steps": 2810, "total_steps": 4473, "loss": 0.2929, "lr": 1.4626615553428659e-05, "epoch": 4.397496087636933, "percentage": 62.82, "elapsed_time": "6:59:46", "remaining_time": "4:08:25"}
{"current_steps": 2815, "total_steps": 4473, "loss": 0.2952, "lr": 1.4551474448505008e-05, "epoch": 4.405320813771518, "percentage": 62.93, "elapsed_time": "7:00:26", "remaining_time": "4:07:37"}
{"current_steps": 2820, "total_steps": 4473, "loss": 0.2675, "lr": 1.4476416326064304e-05, "epoch": 4.413145539906103, "percentage": 63.04, "elapsed_time": "7:01:17", "remaining_time": "4:06:57"}
{"current_steps": 2825, "total_steps": 4473, "loss": 0.3046, "lr": 1.4401442329261575e-05, "epoch": 4.420970266040689, "percentage": 63.16, "elapsed_time": "7:02:02", "remaining_time": "4:06:12"}
{"current_steps": 2830, "total_steps": 4473, "loss": 0.2978, "lr": 1.4326553599970585e-05, "epoch": 4.428794992175274, "percentage": 63.27, "elapsed_time": "7:02:42", "remaining_time": "4:05:24"}
{"current_steps": 2835, "total_steps": 4473, "loss": 0.2911, "lr": 1.4251751278766472e-05, "epoch": 4.436619718309859, "percentage": 63.38, "elapsed_time": "7:03:29", "remaining_time": "4:04:41"}
{"current_steps": 2840, "total_steps": 4473, "loss": 0.2969, "lr": 1.4177036504908322e-05, "epoch": 4.444444444444445, "percentage": 63.49, "elapsed_time": "7:04:11", "remaining_time": "4:03:54"}
{"current_steps": 2845, "total_steps": 4473, "loss": 0.3257, "lr": 1.4102410416321877e-05, "epoch": 4.452269170579029, "percentage": 63.6, "elapsed_time": "7:05:02", "remaining_time": "4:03:13"}
{"current_steps": 2850, "total_steps": 4473, "loss": 0.3195, "lr": 1.4027874149582177e-05, "epoch": 4.460093896713615, "percentage": 63.72, "elapsed_time": "7:05:48", "remaining_time": "4:02:29"}
{"current_steps": 2855, "total_steps": 4473, "loss": 0.2957, "lr": 1.395342883989625e-05, "epoch": 4.467918622848201, "percentage": 63.83, "elapsed_time": "7:06:37", "remaining_time": "4:01:46"}
{"current_steps": 2860, "total_steps": 4473, "loss": 0.3111, "lr": 1.387907562108581e-05, "epoch": 4.475743348982785, "percentage": 63.94, "elapsed_time": "7:07:18", "remaining_time": "4:00:59"}
{"current_steps": 2865, "total_steps": 4473, "loss": 0.2763, "lr": 1.380481562557002e-05, "epoch": 4.483568075117371, "percentage": 64.05, "elapsed_time": "7:08:11", "remaining_time": "4:00:19"}
{"current_steps": 2870, "total_steps": 4473, "loss": 0.293, "lr": 1.3730649984348224e-05, "epoch": 4.491392801251957, "percentage": 64.16, "elapsed_time": "7:09:04", "remaining_time": "3:59:39"}
{"current_steps": 2875, "total_steps": 4473, "loss": 0.3145, "lr": 1.3656579826982718e-05, "epoch": 4.499217527386541, "percentage": 64.27, "elapsed_time": "7:09:46", "remaining_time": "3:58:52"}
{"current_steps": 2880, "total_steps": 4473, "loss": 0.3083, "lr": 1.3582606281581567e-05, "epoch": 4.507042253521127, "percentage": 64.39, "elapsed_time": "7:10:26", "remaining_time": "3:58:05"}
{"current_steps": 2885, "total_steps": 4473, "loss": 0.2946, "lr": 1.3508730474781393e-05, "epoch": 4.514866979655712, "percentage": 64.5, "elapsed_time": "7:11:14", "remaining_time": "3:57:21"}
{"current_steps": 2890, "total_steps": 4473, "loss": 0.312, "lr": 1.3434953531730241e-05, "epoch": 4.522691705790297, "percentage": 64.61, "elapsed_time": "7:11:55", "remaining_time": "3:56:35"}
{"current_steps": 2895, "total_steps": 4473, "loss": 0.2816, "lr": 1.3361276576070443e-05, "epoch": 4.530516431924883, "percentage": 64.72, "elapsed_time": "7:12:57", "remaining_time": "3:55:59"}
{"current_steps": 2900, "total_steps": 4473, "loss": 0.3159, "lr": 1.3287700729921489e-05, "epoch": 4.538341158059468, "percentage": 64.83, "elapsed_time": "7:13:40", "remaining_time": "3:55:13"}
{"current_steps": 2905, "total_steps": 4473, "loss": 0.3092, "lr": 1.3214227113862941e-05, "epoch": 4.546165884194053, "percentage": 64.95, "elapsed_time": "7:14:27", "remaining_time": "3:54:30"}
{"current_steps": 2910, "total_steps": 4473, "loss": 0.3089, "lr": 1.3140856846917374e-05, "epoch": 4.553990610328638, "percentage": 65.06, "elapsed_time": "7:15:08", "remaining_time": "3:53:43"}
{"current_steps": 2915, "total_steps": 4473, "loss": 0.3064, "lr": 1.3067591046533327e-05, "epoch": 4.561815336463224, "percentage": 65.17, "elapsed_time": "7:16:03", "remaining_time": "3:53:03"}
{"current_steps": 2920, "total_steps": 4473, "loss": 0.2957, "lr": 1.2994430828568292e-05, "epoch": 4.569640062597809, "percentage": 65.28, "elapsed_time": "7:16:57", "remaining_time": "3:52:23"}
{"current_steps": 2925, "total_steps": 4473, "loss": 0.2803, "lr": 1.2921377307271717e-05, "epoch": 4.577464788732394, "percentage": 65.39, "elapsed_time": "7:17:52", "remaining_time": "3:51:44"}
{"current_steps": 2930, "total_steps": 4473, "loss": 0.305, "lr": 1.2848431595268001e-05, "epoch": 4.58528951486698, "percentage": 65.5, "elapsed_time": "7:18:39", "remaining_time": "3:51:00"}
{"current_steps": 2935, "total_steps": 4473, "loss": 0.2831, "lr": 1.2775594803539613e-05, "epoch": 4.593114241001565, "percentage": 65.62, "elapsed_time": "7:19:28", "remaining_time": "3:50:17"}
{"current_steps": 2940, "total_steps": 4473, "loss": 0.2804, "lr": 1.2702868041410122e-05, "epoch": 4.60093896713615, "percentage": 65.73, "elapsed_time": "7:20:11", "remaining_time": "3:49:31"}
{"current_steps": 2945, "total_steps": 4473, "loss": 0.3139, "lr": 1.2630252416527332e-05, "epoch": 4.608763693270736, "percentage": 65.84, "elapsed_time": "7:20:57", "remaining_time": "3:48:47"}
{"current_steps": 2950, "total_steps": 4473, "loss": 0.3028, "lr": 1.2557749034846367e-05, "epoch": 4.616588419405321, "percentage": 65.95, "elapsed_time": "7:21:39", "remaining_time": "3:48:00"}
{"current_steps": 2955, "total_steps": 4473, "loss": 0.3236, "lr": 1.2485359000612886e-05, "epoch": 4.624413145539906, "percentage": 66.06, "elapsed_time": "7:22:19", "remaining_time": "3:47:13"}
{"current_steps": 2960, "total_steps": 4473, "loss": 0.2991, "lr": 1.2413083416346226e-05, "epoch": 4.632237871674492, "percentage": 66.17, "elapsed_time": "7:23:14", "remaining_time": "3:46:33"}
{"current_steps": 2965, "total_steps": 4473, "loss": 0.3095, "lr": 1.2340923382822617e-05, "epoch": 4.640062597809076, "percentage": 66.29, "elapsed_time": "7:23:52", "remaining_time": "3:45:45"}
{"current_steps": 2970, "total_steps": 4473, "loss": 0.3014, "lr": 1.226887999905844e-05, "epoch": 4.647887323943662, "percentage": 66.4, "elapsed_time": "7:24:31", "remaining_time": "3:44:57"}
{"current_steps": 2975, "total_steps": 4473, "loss": 0.2917, "lr": 1.2196954362293433e-05, "epoch": 4.655712050078248, "percentage": 66.51, "elapsed_time": "7:25:26", "remaining_time": "3:44:17"}
{"current_steps": 2980, "total_steps": 4473, "loss": 0.2855, "lr": 1.2125147567974049e-05, "epoch": 4.663536776212832, "percentage": 66.62, "elapsed_time": "7:26:14", "remaining_time": "3:43:34"}
{"current_steps": 2985, "total_steps": 4473, "loss": 0.3022, "lr": 1.2053460709736724e-05, "epoch": 4.671361502347418, "percentage": 66.73, "elapsed_time": "7:27:12", "remaining_time": "3:42:55"}
{"current_steps": 2990, "total_steps": 4473, "loss": 0.3093, "lr": 1.1981894879391249e-05, "epoch": 4.679186228482003, "percentage": 66.85, "elapsed_time": "7:27:52", "remaining_time": "3:42:08"}
{"current_steps": 2995, "total_steps": 4473, "loss": 0.2818, "lr": 1.1910451166904107e-05, "epoch": 4.687010954616588, "percentage": 66.96, "elapsed_time": "7:28:35", "remaining_time": "3:41:22"}
{"current_steps": 3000, "total_steps": 4473, "loss": 0.2869, "lr": 1.1839130660381906e-05, "epoch": 4.694835680751174, "percentage": 67.07, "elapsed_time": "7:29:18", "remaining_time": "3:40:36"}
{"current_steps": 3005, "total_steps": 4473, "loss": 0.2752, "lr": 1.17679344460548e-05, "epoch": 4.702660406885759, "percentage": 67.18, "elapsed_time": "7:30:51", "remaining_time": "3:40:15"}
{"current_steps": 3010, "total_steps": 4473, "loss": 0.3091, "lr": 1.169686360825993e-05, "epoch": 4.710485133020344, "percentage": 67.29, "elapsed_time": "7:31:25", "remaining_time": "3:39:24"}
{"current_steps": 3015, "total_steps": 4473, "loss": 0.2854, "lr": 1.1625919229424927e-05, "epoch": 4.71830985915493, "percentage": 67.4, "elapsed_time": "7:32:09", "remaining_time": "3:38:39"}
{"current_steps": 3020, "total_steps": 4473, "loss": 0.2989, "lr": 1.1555102390051416e-05, "epoch": 4.726134585289515, "percentage": 67.52, "elapsed_time": "7:32:58", "remaining_time": "3:37:56"}
{"current_steps": 3025, "total_steps": 4473, "loss": 0.2868, "lr": 1.1484414168698547e-05, "epoch": 4.7339593114241, "percentage": 67.63, "elapsed_time": "7:33:43", "remaining_time": "3:37:11"}
{"current_steps": 3030, "total_steps": 4473, "loss": 0.294, "lr": 1.1413855641966616e-05, "epoch": 4.741784037558686, "percentage": 67.74, "elapsed_time": "7:34:33", "remaining_time": "3:36:28"}
{"current_steps": 3035, "total_steps": 4473, "loss": 0.2893, "lr": 1.1343427884480614e-05, "epoch": 4.749608763693271, "percentage": 67.85, "elapsed_time": "7:35:30", "remaining_time": "3:35:49"}
{"current_steps": 3040, "total_steps": 4473, "loss": 0.3014, "lr": 1.1273131968873878e-05, "epoch": 4.757433489827856, "percentage": 67.96, "elapsed_time": "7:36:19", "remaining_time": "3:35:06"}
{"current_steps": 3045, "total_steps": 4473, "loss": 0.2872, "lr": 1.1202968965771767e-05, "epoch": 4.765258215962441, "percentage": 68.08, "elapsed_time": "7:36:48", "remaining_time": "3:34:13"}
{"current_steps": 3050, "total_steps": 4473, "loss": 0.3067, "lr": 1.1132939943775353e-05, "epoch": 4.773082942097027, "percentage": 68.19, "elapsed_time": "7:37:37", "remaining_time": "3:33:30"}
{"current_steps": 3055, "total_steps": 4473, "loss": 0.3114, "lr": 1.1063045969445123e-05, "epoch": 4.780907668231611, "percentage": 68.3, "elapsed_time": "7:38:33", "remaining_time": "3:32:50"}
{"current_steps": 3060, "total_steps": 4473, "loss": 0.2971, "lr": 1.0993288107284787e-05, "epoch": 4.788732394366197, "percentage": 68.41, "elapsed_time": "7:39:10", "remaining_time": "3:32:02"}
{"current_steps": 3065, "total_steps": 4473, "loss": 0.2618, "lr": 1.0923667419724973e-05, "epoch": 4.796557120500783, "percentage": 68.52, "elapsed_time": "7:40:00", "remaining_time": "3:31:19"}
{"current_steps": 3070, "total_steps": 4473, "loss": 0.2908, "lr": 1.0854184967107162e-05, "epoch": 4.804381846635367, "percentage": 68.63, "elapsed_time": "7:40:48", "remaining_time": "3:30:35"}
{"current_steps": 3075, "total_steps": 4473, "loss": 0.2787, "lr": 1.0784841807667448e-05, "epoch": 4.812206572769953, "percentage": 68.75, "elapsed_time": "7:41:41", "remaining_time": "3:29:53"}
{"current_steps": 3080, "total_steps": 4473, "loss": 0.337, "lr": 1.071563899752046e-05, "epoch": 4.820031298904539, "percentage": 68.86, "elapsed_time": "7:42:28", "remaining_time": "3:29:09"}
{"current_steps": 3085, "total_steps": 4473, "loss": 0.3212, "lr": 1.0646577590643261e-05, "epoch": 4.827856025039123, "percentage": 68.97, "elapsed_time": "7:43:10", "remaining_time": "3:28:23"}
{"current_steps": 3090, "total_steps": 4473, "loss": 0.3044, "lr": 1.0577658638859336e-05, "epoch": 4.835680751173709, "percentage": 69.08, "elapsed_time": "7:43:34", "remaining_time": "3:27:29"}
{"current_steps": 3095, "total_steps": 4473, "loss": 0.2854, "lr": 1.050888319182251e-05, "epoch": 4.843505477308295, "percentage": 69.19, "elapsed_time": "7:44:14", "remaining_time": "3:26:41"}
{"current_steps": 3100, "total_steps": 4473, "loss": 0.305, "lr": 1.0440252297000993e-05, "epoch": 4.851330203442879, "percentage": 69.3, "elapsed_time": "7:45:03", "remaining_time": "3:25:58"}
{"current_steps": 3105, "total_steps": 4473, "loss": 0.2939, "lr": 1.0371766999661452e-05, "epoch": 4.859154929577465, "percentage": 69.42, "elapsed_time": "7:45:51", "remaining_time": "3:25:14"}
{"current_steps": 3110, "total_steps": 4473, "loss": 0.2827, "lr": 1.0303428342853049e-05, "epoch": 4.86697965571205, "percentage": 69.53, "elapsed_time": "7:46:30", "remaining_time": "3:24:27"}
{"current_steps": 3115, "total_steps": 4473, "loss": 0.3156, "lr": 1.0235237367391567e-05, "epoch": 4.874804381846635, "percentage": 69.64, "elapsed_time": "7:47:05", "remaining_time": "3:23:37"}
{"current_steps": 3120, "total_steps": 4473, "loss": 0.2856, "lr": 1.0167195111843561e-05, "epoch": 4.882629107981221, "percentage": 69.75, "elapsed_time": "7:47:57", "remaining_time": "3:22:56"}
{"current_steps": 3125, "total_steps": 4473, "loss": 0.2958, "lr": 1.009930261251058e-05, "epoch": 4.890453834115806, "percentage": 69.86, "elapsed_time": "7:48:40", "remaining_time": "3:22:10"}
{"current_steps": 3130, "total_steps": 4473, "loss": 0.2927, "lr": 1.0031560903413283e-05, "epoch": 4.898278560250391, "percentage": 69.98, "elapsed_time": "7:49:24", "remaining_time": "3:21:24"}
{"current_steps": 3135, "total_steps": 4473, "loss": 0.2931, "lr": 9.963971016275811e-06, "epoch": 4.906103286384976, "percentage": 70.09, "elapsed_time": "7:50:12", "remaining_time": "3:20:41"}
{"current_steps": 3140, "total_steps": 4473, "loss": 0.3006, "lr": 9.896533980509979e-06, "epoch": 4.913928012519562, "percentage": 70.2, "elapsed_time": "7:50:56", "remaining_time": "3:19:55"}
{"current_steps": 3145, "total_steps": 4473, "loss": 0.2992, "lr": 9.829250823199665e-06, "epoch": 4.921752738654147, "percentage": 70.31, "elapsed_time": "7:51:42", "remaining_time": "3:19:11"}
{"current_steps": 3150, "total_steps": 4473, "loss": 0.2812, "lr": 9.762122569085116e-06, "epoch": 4.929577464788732, "percentage": 70.42, "elapsed_time": "7:52:34", "remaining_time": "3:18:28"}
{"current_steps": 3155, "total_steps": 4473, "loss": 0.2986, "lr": 9.695150240547367e-06, "epoch": 4.937402190923318, "percentage": 70.53, "elapsed_time": "7:53:12", "remaining_time": "3:17:41"}
{"current_steps": 3160, "total_steps": 4473, "loss": 0.323, "lr": 9.628334857592658e-06, "epoch": 4.945226917057903, "percentage": 70.65, "elapsed_time": "7:54:02", "remaining_time": "3:16:57"}
{"current_steps": 3165, "total_steps": 4473, "loss": 0.295, "lr": 9.561677437836933e-06, "epoch": 4.953051643192488, "percentage": 70.76, "elapsed_time": "7:54:41", "remaining_time": "3:16:10"}
{"current_steps": 3170, "total_steps": 4473, "loss": 0.3241, "lr": 9.495178996490293e-06, "epoch": 4.960876369327074, "percentage": 70.87, "elapsed_time": "7:55:11", "remaining_time": "3:15:19"}
{"current_steps": 3175, "total_steps": 4473, "loss": 0.2776, "lr": 9.428840546341553e-06, "epoch": 4.968701095461659, "percentage": 70.98, "elapsed_time": "7:55:58", "remaining_time": "3:14:35"}
{"current_steps": 3180, "total_steps": 4473, "loss": 0.2961, "lr": 9.362663097742823e-06, "epoch": 4.976525821596244, "percentage": 71.09, "elapsed_time": "7:56:30", "remaining_time": "3:13:45"}
{"current_steps": 3185, "total_steps": 4473, "loss": 0.2758, "lr": 9.296647658594138e-06, "epoch": 4.98435054773083, "percentage": 71.21, "elapsed_time": "7:57:15", "remaining_time": "3:13:00"}
{"current_steps": 3190, "total_steps": 4473, "loss": 0.2705, "lr": 9.230795234328049e-06, "epoch": 4.992175273865414, "percentage": 71.32, "elapsed_time": "7:57:57", "remaining_time": "3:12:13"}
{"current_steps": 3195, "total_steps": 4473, "loss": 0.2896, "lr": 9.165106827894391e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "7:58:36", "remaining_time": "3:11:26"}
{"current_steps": 3200, "total_steps": 4473, "loss": 0.2931, "lr": 9.099583439744915e-06, "epoch": 5.007824726134586, "percentage": 71.54, "elapsed_time": "7:59:14", "remaining_time": "3:10:38"}
{"current_steps": 3205, "total_steps": 4473, "loss": 0.2688, "lr": 9.034226067818142e-06, "epoch": 5.01564945226917, "percentage": 71.65, "elapsed_time": "7:59:59", "remaining_time": "3:09:54"}
{"current_steps": 3210, "total_steps": 4473, "loss": 0.2717, "lr": 8.9690357075241e-06, "epoch": 5.023474178403756, "percentage": 71.76, "elapsed_time": "8:00:33", "remaining_time": "3:09:04"}
{"current_steps": 3215, "total_steps": 4473, "loss": 0.2746, "lr": 8.904013351729193e-06, "epoch": 5.031298904538341, "percentage": 71.88, "elapsed_time": "8:01:22", "remaining_time": "3:08:21"}
{"current_steps": 3220, "total_steps": 4473, "loss": 0.2629, "lr": 8.839159990741061e-06, "epoch": 5.039123630672926, "percentage": 71.99, "elapsed_time": "8:02:09", "remaining_time": "3:07:37"}
{"current_steps": 3225, "total_steps": 4473, "loss": 0.2886, "lr": 8.774476612293534e-06, "epoch": 5.046948356807512, "percentage": 72.1, "elapsed_time": "8:03:00", "remaining_time": "3:06:54"}
{"current_steps": 3230, "total_steps": 4473, "loss": 0.287, "lr": 8.709964201531538e-06, "epoch": 5.054773082942097, "percentage": 72.21, "elapsed_time": "8:03:48", "remaining_time": "3:06:11"}
{"current_steps": 3235, "total_steps": 4473, "loss": 0.2697, "lr": 8.645623740996117e-06, "epoch": 5.062597809076682, "percentage": 72.32, "elapsed_time": "8:04:26", "remaining_time": "3:05:23"}
{"current_steps": 3240, "total_steps": 4473, "loss": 0.2579, "lr": 8.58145621060949e-06, "epoch": 5.070422535211268, "percentage": 72.43, "elapsed_time": "8:05:08", "remaining_time": "3:04:37"}
{"current_steps": 3245, "total_steps": 4473, "loss": 0.274, "lr": 8.517462587660084e-06, "epoch": 5.078247261345853, "percentage": 72.55, "elapsed_time": "8:05:49", "remaining_time": "3:03:51"}
{"current_steps": 3250, "total_steps": 4473, "loss": 0.3013, "lr": 8.453643846787673e-06, "epoch": 5.086071987480438, "percentage": 72.66, "elapsed_time": "8:06:32", "remaining_time": "3:03:05"}
{"current_steps": 3255, "total_steps": 4473, "loss": 0.256, "lr": 8.390000959968529e-06, "epoch": 5.093896713615023, "percentage": 72.77, "elapsed_time": "8:07:18", "remaining_time": "3:02:20"}
{"current_steps": 3260, "total_steps": 4473, "loss": 0.3207, "lr": 8.326534896500646e-06, "epoch": 5.101721439749609, "percentage": 72.88, "elapsed_time": "8:08:04", "remaining_time": "3:01:36"}
{"current_steps": 3265, "total_steps": 4473, "loss": 0.2864, "lr": 8.263246622988899e-06, "epoch": 5.109546165884194, "percentage": 72.99, "elapsed_time": "8:08:46", "remaining_time": "3:00:50"}
{"current_steps": 3270, "total_steps": 4473, "loss": 0.2755, "lr": 8.200137103330428e-06, "epoch": 5.117370892018779, "percentage": 73.11, "elapsed_time": "8:09:21", "remaining_time": "3:00:01"}
{"current_steps": 3275, "total_steps": 4473, "loss": 0.2639, "lr": 8.13720729869987e-06, "epoch": 5.125195618153365, "percentage": 73.22, "elapsed_time": "8:10:13", "remaining_time": "2:59:19"}
{"current_steps": 3280, "total_steps": 4473, "loss": 0.2933, "lr": 8.07445816753478e-06, "epoch": 5.13302034428795, "percentage": 73.33, "elapsed_time": "8:10:54", "remaining_time": "2:58:33"}
{"current_steps": 3285, "total_steps": 4473, "loss": 0.3029, "lr": 8.01189066552099e-06, "epoch": 5.140845070422535, "percentage": 73.44, "elapsed_time": "8:11:40", "remaining_time": "2:57:48"}
{"current_steps": 3290, "total_steps": 4473, "loss": 0.2834, "lr": 7.949505745578076e-06, "epoch": 5.148669796557121, "percentage": 73.55, "elapsed_time": "8:12:22", "remaining_time": "2:57:02"}
{"current_steps": 3295, "total_steps": 4473, "loss": 0.2581, "lr": 7.887304357844838e-06, "epoch": 5.156494522691705, "percentage": 73.66, "elapsed_time": "8:13:13", "remaining_time": "2:56:19"}
{"current_steps": 3300, "total_steps": 4473, "loss": 0.2686, "lr": 7.825287449664854e-06, "epoch": 5.164319248826291, "percentage": 73.78, "elapsed_time": "8:13:51", "remaining_time": "2:55:32"}
{"current_steps": 3305, "total_steps": 4473, "loss": 0.2808, "lr": 7.763455965571998e-06, "epoch": 5.172143974960877, "percentage": 73.89, "elapsed_time": "8:14:39", "remaining_time": "2:54:48"}
{"current_steps": 3310, "total_steps": 4473, "loss": 0.2818, "lr": 7.701810847276104e-06, "epoch": 5.179968701095461, "percentage": 74.0, "elapsed_time": "8:15:15", "remaining_time": "2:54:00"}
{"current_steps": 3315, "total_steps": 4473, "loss": 0.2649, "lr": 7.640353033648598e-06, "epoch": 5.187793427230047, "percentage": 74.11, "elapsed_time": "8:16:02", "remaining_time": "2:53:16"}
{"current_steps": 3320, "total_steps": 4473, "loss": 0.2895, "lr": 7.579083460708218e-06, "epoch": 5.195618153364633, "percentage": 74.22, "elapsed_time": "8:16:31", "remaining_time": "2:52:26"}
{"current_steps": 3325, "total_steps": 4473, "loss": 0.2817, "lr": 7.518003061606734e-06, "epoch": 5.203442879499217, "percentage": 74.33, "elapsed_time": "8:17:16", "remaining_time": "2:51:41"}
{"current_steps": 3330, "total_steps": 4473, "loss": 0.2926, "lr": 7.457112766614769e-06, "epoch": 5.211267605633803, "percentage": 74.45, "elapsed_time": "8:18:05", "remaining_time": "2:50:58"}
{"current_steps": 3335, "total_steps": 4473, "loss": 0.2618, "lr": 7.396413503107571e-06, "epoch": 5.219092331768388, "percentage": 74.56, "elapsed_time": "8:18:45", "remaining_time": "2:50:11"}
{"current_steps": 3340, "total_steps": 4473, "loss": 0.2643, "lr": 7.335906195550968e-06, "epoch": 5.226917057902973, "percentage": 74.67, "elapsed_time": "8:19:19", "remaining_time": "2:49:22"}
{"current_steps": 3345, "total_steps": 4473, "loss": 0.2677, "lr": 7.275591765487222e-06, "epoch": 5.234741784037559, "percentage": 74.78, "elapsed_time": "8:19:57", "remaining_time": "2:48:35"}
{"current_steps": 3350, "total_steps": 4473, "loss": 0.2714, "lr": 7.215471131521043e-06, "epoch": 5.242566510172144, "percentage": 74.89, "elapsed_time": "8:20:34", "remaining_time": "2:47:48"}
{"current_steps": 3355, "total_steps": 4473, "loss": 0.2907, "lr": 7.155545209305559e-06, "epoch": 5.250391236306729, "percentage": 75.01, "elapsed_time": "8:21:11", "remaining_time": "2:47:00"}
{"current_steps": 3360, "total_steps": 4473, "loss": 0.2773, "lr": 7.095814911528383e-06, "epoch": 5.258215962441315, "percentage": 75.12, "elapsed_time": "8:21:50", "remaining_time": "2:46:14"}
{"current_steps": 3365, "total_steps": 4473, "loss": 0.2939, "lr": 7.03628114789773e-06, "epoch": 5.2660406885759, "percentage": 75.23, "elapsed_time": "8:22:28", "remaining_time": "2:45:27"}
{"current_steps": 3370, "total_steps": 4473, "loss": 0.2927, "lr": 6.976944825128529e-06, "epoch": 5.273865414710485, "percentage": 75.34, "elapsed_time": "8:23:13", "remaining_time": "2:44:42"}
{"current_steps": 3375, "total_steps": 4473, "loss": 0.272, "lr": 6.917806846928663e-06, "epoch": 5.28169014084507, "percentage": 75.45, "elapsed_time": "8:24:09", "remaining_time": "2:44:01"}
{"current_steps": 3380, "total_steps": 4473, "loss": 0.2958, "lr": 6.858868113985146e-06, "epoch": 5.289514866979656, "percentage": 75.56, "elapsed_time": "8:24:52", "remaining_time": "2:43:15"}
{"current_steps": 3385, "total_steps": 4473, "loss": 0.2768, "lr": 6.800129523950447e-06, "epoch": 5.297339593114241, "percentage": 75.68, "elapsed_time": "8:25:30", "remaining_time": "2:42:28"}
{"current_steps": 3390, "total_steps": 4473, "loss": 0.2911, "lr": 6.741591971428796e-06, "epoch": 5.305164319248826, "percentage": 75.79, "elapsed_time": "8:26:28", "remaining_time": "2:41:48"}
{"current_steps": 3395, "total_steps": 4473, "loss": 0.2747, "lr": 6.6832563479625904e-06, "epoch": 5.312989045383412, "percentage": 75.9, "elapsed_time": "8:27:19", "remaining_time": "2:41:05"}
{"current_steps": 3400, "total_steps": 4473, "loss": 0.2846, "lr": 6.625123542018772e-06, "epoch": 5.320813771517997, "percentage": 76.01, "elapsed_time": "8:27:53", "remaining_time": "2:40:17"}
{"current_steps": 3405, "total_steps": 4473, "loss": 0.2809, "lr": 6.567194438975329e-06, "epoch": 5.328638497652582, "percentage": 76.12, "elapsed_time": "8:28:32", "remaining_time": "2:39:30"}
{"current_steps": 3410, "total_steps": 4473, "loss": 0.2765, "lr": 6.509469921107787e-06, "epoch": 5.336463223787168, "percentage": 76.24, "elapsed_time": "8:29:24", "remaining_time": "2:38:47"}
{"current_steps": 3415, "total_steps": 4473, "loss": 0.2695, "lr": 6.451950867575814e-06, "epoch": 5.344287949921752, "percentage": 76.35, "elapsed_time": "8:30:09", "remaining_time": "2:38:03"}
{"current_steps": 3420, "total_steps": 4473, "loss": 0.2707, "lr": 6.394638154409776e-06, "epoch": 5.352112676056338, "percentage": 76.46, "elapsed_time": "8:30:51", "remaining_time": "2:37:17"}
{"current_steps": 3425, "total_steps": 4473, "loss": 0.2691, "lr": 6.337532654497429e-06, "epoch": 5.359937402190924, "percentage": 76.57, "elapsed_time": "8:31:44", "remaining_time": "2:36:35"}
{"current_steps": 3430, "total_steps": 4473, "loss": 0.285, "lr": 6.280635237570612e-06, "epoch": 5.367762128325508, "percentage": 76.68, "elapsed_time": "8:32:31", "remaining_time": "2:35:51"}
{"current_steps": 3435, "total_steps": 4473, "loss": 0.2744, "lr": 6.22394677019202e-06, "epoch": 5.375586854460094, "percentage": 76.79, "elapsed_time": "8:33:14", "remaining_time": "2:35:05"}
{"current_steps": 3440, "total_steps": 4473, "loss": 0.2954, "lr": 6.16746811574197e-06, "epoch": 5.383411580594679, "percentage": 76.91, "elapsed_time": "8:34:08", "remaining_time": "2:34:23"}
{"current_steps": 3445, "total_steps": 4473, "loss": 0.281, "lr": 6.111200134405304e-06, "epoch": 5.391236306729264, "percentage": 77.02, "elapsed_time": "8:34:54", "remaining_time": "2:33:38"}
{"current_steps": 3450, "total_steps": 4473, "loss": 0.2911, "lr": 6.055143683158206e-06, "epoch": 5.39906103286385, "percentage": 77.13, "elapsed_time": "8:35:27", "remaining_time": "2:32:50"}
{"current_steps": 3455, "total_steps": 4473, "loss": 0.271, "lr": 5.999299615755256e-06, "epoch": 5.406885758998435, "percentage": 77.24, "elapsed_time": "8:36:12", "remaining_time": "2:32:06"}
{"current_steps": 3460, "total_steps": 4473, "loss": 0.3064, "lr": 5.943668782716332e-06, "epoch": 5.41471048513302, "percentage": 77.35, "elapsed_time": "8:36:57", "remaining_time": "2:31:21"}
{"current_steps": 3465, "total_steps": 4473, "loss": 0.258, "lr": 5.88825203131373e-06, "epoch": 5.422535211267606, "percentage": 77.46, "elapsed_time": "8:37:31", "remaining_time": "2:30:33"}
{"current_steps": 3470, "total_steps": 4473, "loss": 0.2968, "lr": 5.8330502055591855e-06, "epoch": 5.430359937402191, "percentage": 77.58, "elapsed_time": "8:38:26", "remaining_time": "2:29:51"}
{"current_steps": 3475, "total_steps": 4473, "loss": 0.2654, "lr": 5.778064146191098e-06, "epoch": 5.438184663536776, "percentage": 77.69, "elapsed_time": "8:39:21", "remaining_time": "2:29:09"}
{"current_steps": 3480, "total_steps": 4473, "loss": 0.2802, "lr": 5.7232946906616605e-06, "epoch": 5.446009389671362, "percentage": 77.8, "elapsed_time": "8:40:01", "remaining_time": "2:28:23"}
{"current_steps": 3485, "total_steps": 4473, "loss": 0.2701, "lr": 5.668742673124154e-06, "epoch": 5.453834115805947, "percentage": 77.91, "elapsed_time": "8:41:01", "remaining_time": "2:27:42"}
{"current_steps": 3490, "total_steps": 4473, "loss": 0.2862, "lr": 5.614408924420209e-06, "epoch": 5.461658841940532, "percentage": 78.02, "elapsed_time": "8:41:40", "remaining_time": "2:26:56"}
{"current_steps": 3495, "total_steps": 4473, "loss": 0.2748, "lr": 5.560294272067166e-06, "epoch": 5.469483568075117, "percentage": 78.14, "elapsed_time": "8:42:22", "remaining_time": "2:26:10"}
{"current_steps": 3500, "total_steps": 4473, "loss": 0.2751, "lr": 5.506399540245466e-06, "epoch": 5.477308294209703, "percentage": 78.25, "elapsed_time": "8:43:06", "remaining_time": "2:25:25"}
{"current_steps": 3505, "total_steps": 4473, "loss": 0.2737, "lr": 5.452725549786104e-06, "epoch": 5.485133020344288, "percentage": 78.36, "elapsed_time": "8:43:52", "remaining_time": "2:24:40"}
{"current_steps": 3510, "total_steps": 4473, "loss": 0.2772, "lr": 5.39927311815814e-06, "epoch": 5.492957746478873, "percentage": 78.47, "elapsed_time": "8:44:33", "remaining_time": "2:23:54"}
{"current_steps": 3515, "total_steps": 4473, "loss": 0.2876, "lr": 5.346043059456216e-06, "epoch": 5.500782472613459, "percentage": 78.58, "elapsed_time": "8:45:20", "remaining_time": "2:23:10"}
{"current_steps": 3520, "total_steps": 4473, "loss": 0.2516, "lr": 5.293036184388185e-06, "epoch": 5.508607198748043, "percentage": 78.69, "elapsed_time": "8:46:15", "remaining_time": "2:22:28"}
{"current_steps": 3525, "total_steps": 4473, "loss": 0.2737, "lr": 5.240253300262743e-06, "epoch": 5.516431924882629, "percentage": 78.81, "elapsed_time": "8:46:56", "remaining_time": "2:21:42"}
{"current_steps": 3530, "total_steps": 4473, "loss": 0.2971, "lr": 5.187695210977168e-06, "epoch": 5.524256651017215, "percentage": 78.92, "elapsed_time": "8:47:47", "remaining_time": "2:20:59"}
{"current_steps": 3535, "total_steps": 4473, "loss": 0.2659, "lr": 5.13536271700503e-06, "epoch": 5.532081377151799, "percentage": 79.03, "elapsed_time": "8:48:32", "remaining_time": "2:20:14"}
{"current_steps": 3540, "total_steps": 4473, "loss": 0.2619, "lr": 5.083256615384035e-06, "epoch": 5.539906103286385, "percentage": 79.14, "elapsed_time": "8:49:18", "remaining_time": "2:19:30"}
{"current_steps": 3545, "total_steps": 4473, "loss": 0.2843, "lr": 5.0313776997038635e-06, "epoch": 5.547730829420971, "percentage": 79.25, "elapsed_time": "8:49:55", "remaining_time": "2:18:43"}
{"current_steps": 3550, "total_steps": 4473, "loss": 0.2761, "lr": 4.97972676009411e-06, "epoch": 5.555555555555555, "percentage": 79.37, "elapsed_time": "8:50:30", "remaining_time": "2:17:56"}
{"current_steps": 3555, "total_steps": 4473, "loss": 0.2713, "lr": 4.9283045832122225e-06, "epoch": 5.563380281690141, "percentage": 79.48, "elapsed_time": "8:51:12", "remaining_time": "2:17:10"}
{"current_steps": 3560, "total_steps": 4473, "loss": 0.2904, "lr": 4.877111952231533e-06, "epoch": 5.571205007824727, "percentage": 79.59, "elapsed_time": "8:51:55", "remaining_time": "2:16:25"}
{"current_steps": 3565, "total_steps": 4473, "loss": 0.2727, "lr": 4.826149646829321e-06, "epoch": 5.579029733959311, "percentage": 79.7, "elapsed_time": "8:52:32", "remaining_time": "2:15:38"}
{"current_steps": 3570, "total_steps": 4473, "loss": 0.2816, "lr": 4.775418443174971e-06, "epoch": 5.586854460093897, "percentage": 79.81, "elapsed_time": "8:53:06", "remaining_time": "2:14:50"}
{"current_steps": 3575, "total_steps": 4473, "loss": 0.2871, "lr": 4.724919113918099e-06, "epoch": 5.594679186228482, "percentage": 79.92, "elapsed_time": "8:53:55", "remaining_time": "2:14:07"}
{"current_steps": 3580, "total_steps": 4473, "loss": 0.276, "lr": 4.674652428176838e-06, "epoch": 5.602503912363067, "percentage": 80.04, "elapsed_time": "8:54:44", "remaining_time": "2:13:23"}
{"current_steps": 3585, "total_steps": 4473, "loss": 0.2875, "lr": 4.624619151526069e-06, "epoch": 5.610328638497653, "percentage": 80.15, "elapsed_time": "8:55:20", "remaining_time": "2:12:36"}
{"current_steps": 3590, "total_steps": 4473, "loss": 0.2834, "lr": 4.57482004598582e-06, "epoch": 5.618153364632238, "percentage": 80.26, "elapsed_time": "8:56:01", "remaining_time": "2:11:50"}
{"current_steps": 3595, "total_steps": 4473, "loss": 0.2575, "lr": 4.52525587000961e-06, "epoch": 5.625978090766823, "percentage": 80.37, "elapsed_time": "8:56:53", "remaining_time": "2:11:07"}
{"current_steps": 3600, "total_steps": 4473, "loss": 0.2815, "lr": 4.475927378472944e-06, "epoch": 5.633802816901408, "percentage": 80.48, "elapsed_time": "8:57:35", "remaining_time": "2:10:21"}
{"current_steps": 3605, "total_steps": 4473, "loss": 0.2649, "lr": 4.4268353226617535e-06, "epoch": 5.641627543035994, "percentage": 80.59, "elapsed_time": "8:58:34", "remaining_time": "2:09:40"}
{"current_steps": 3610, "total_steps": 4473, "loss": 0.277, "lr": 4.377980450261025e-06, "epoch": 5.649452269170579, "percentage": 80.71, "elapsed_time": "8:59:23", "remaining_time": "2:08:56"}
{"current_steps": 3615, "total_steps": 4473, "loss": 0.2907, "lr": 4.3293635053433605e-06, "epoch": 5.657276995305164, "percentage": 80.82, "elapsed_time": "9:00:10", "remaining_time": "2:08:12"}
{"current_steps": 3620, "total_steps": 4473, "loss": 0.2906, "lr": 4.280985228357677e-06, "epoch": 5.66510172143975, "percentage": 80.93, "elapsed_time": "9:00:43", "remaining_time": "2:07:24"}
{"current_steps": 3625, "total_steps": 4473, "loss": 0.2723, "lr": 4.2328463561179014e-06, "epoch": 5.672926447574335, "percentage": 81.04, "elapsed_time": "9:01:21", "remaining_time": "2:06:38"}
{"current_steps": 3630, "total_steps": 4473, "loss": 0.2886, "lr": 4.184947621791775e-06, "epoch": 5.68075117370892, "percentage": 81.15, "elapsed_time": "9:02:17", "remaining_time": "2:05:56"}
{"current_steps": 3635, "total_steps": 4473, "loss": 0.2869, "lr": 4.13728975488966e-06, "epoch": 5.688575899843506, "percentage": 81.27, "elapsed_time": "9:03:11", "remaining_time": "2:05:13"}
{"current_steps": 3640, "total_steps": 4473, "loss": 0.2838, "lr": 4.089873481253468e-06, "epoch": 5.69640062597809, "percentage": 81.38, "elapsed_time": "9:03:48", "remaining_time": "2:04:27"}
{"current_steps": 3645, "total_steps": 4473, "loss": 0.2798, "lr": 4.042699523045561e-06, "epoch": 5.704225352112676, "percentage": 81.49, "elapsed_time": "9:04:43", "remaining_time": "2:03:44"}
{"current_steps": 3650, "total_steps": 4473, "loss": 0.2865, "lr": 3.995768598737779e-06, "epoch": 5.712050078247262, "percentage": 81.6, "elapsed_time": "9:05:26", "remaining_time": "2:02:59"}
{"current_steps": 3655, "total_steps": 4473, "loss": 0.3153, "lr": 3.949081423100496e-06, "epoch": 5.719874804381846, "percentage": 81.71, "elapsed_time": "9:06:14", "remaining_time": "2:02:14"}
{"current_steps": 3660, "total_steps": 4473, "loss": 0.2666, "lr": 3.902638707191717e-06, "epoch": 5.727699530516432, "percentage": 81.82, "elapsed_time": "9:07:03", "remaining_time": "2:01:31"}
{"current_steps": 3665, "total_steps": 4473, "loss": 0.2959, "lr": 3.85644115834628e-06, "epoch": 5.735524256651017, "percentage": 81.94, "elapsed_time": "9:07:52", "remaining_time": "2:00:47"}
{"current_steps": 3670, "total_steps": 4473, "loss": 0.295, "lr": 3.8104894801650517e-06, "epoch": 5.743348982785602, "percentage": 82.05, "elapsed_time": "9:08:35", "remaining_time": "2:00:01"}
{"current_steps": 3675, "total_steps": 4473, "loss": 0.2782, "lr": 3.76478437250422e-06, "epoch": 5.751173708920188, "percentage": 82.16, "elapsed_time": "9:09:21", "remaining_time": "1:59:17"}
{"current_steps": 3680, "total_steps": 4473, "loss": 0.3102, "lr": 3.7193265314646445e-06, "epoch": 5.758998435054773, "percentage": 82.27, "elapsed_time": "9:10:05", "remaining_time": "1:58:32"}
{"current_steps": 3685, "total_steps": 4473, "loss": 0.2701, "lr": 3.674116649381252e-06, "epoch": 5.766823161189358, "percentage": 82.38, "elapsed_time": "9:10:44", "remaining_time": "1:57:46"}
{"current_steps": 3690, "total_steps": 4473, "loss": 0.2857, "lr": 3.6291554148124865e-06, "epoch": 5.774647887323944, "percentage": 82.49, "elapsed_time": "9:11:23", "remaining_time": "1:57:00"}
{"current_steps": 3695, "total_steps": 4473, "loss": 0.2765, "lr": 3.5844435125298206e-06, "epoch": 5.782472613458529, "percentage": 82.61, "elapsed_time": "9:12:04", "remaining_time": "1:56:14"}
{"current_steps": 3700, "total_steps": 4473, "loss": 0.2707, "lr": 3.539981623507327e-06, "epoch": 5.790297339593114, "percentage": 82.72, "elapsed_time": "9:12:43", "remaining_time": "1:55:28"}
{"current_steps": 3705, "total_steps": 4473, "loss": 0.2949, "lr": 3.495770424911329e-06, "epoch": 5.7981220657277, "percentage": 82.83, "elapsed_time": "9:13:28", "remaining_time": "1:54:43"}
{"current_steps": 3710, "total_steps": 4473, "loss": 0.3074, "lr": 3.4518105900900432e-06, "epoch": 5.805946791862285, "percentage": 82.94, "elapsed_time": "9:14:05", "remaining_time": "1:53:57"}
{"current_steps": 3715, "total_steps": 4473, "loss": 0.2861, "lr": 3.408102788563381e-06, "epoch": 5.81377151799687, "percentage": 83.05, "elapsed_time": "9:14:46", "remaining_time": "1:53:11"}
{"current_steps": 3720, "total_steps": 4473, "loss": 0.2515, "lr": 3.3646476860126787e-06, "epoch": 5.821596244131455, "percentage": 83.17, "elapsed_time": "9:15:30", "remaining_time": "1:52:26"}
{"current_steps": 3725, "total_steps": 4473, "loss": 0.2984, "lr": 3.3214459442706405e-06, "epoch": 5.829420970266041, "percentage": 83.28, "elapsed_time": "9:16:10", "remaining_time": "1:51:40"}
{"current_steps": 3730, "total_steps": 4473, "loss": 0.2831, "lr": 3.2784982213111904e-06, "epoch": 5.837245696400626, "percentage": 83.39, "elapsed_time": "9:16:52", "remaining_time": "1:50:55"}
{"current_steps": 3735, "total_steps": 4473, "loss": 0.2698, "lr": 3.2358051712395056e-06, "epoch": 5.845070422535211, "percentage": 83.5, "elapsed_time": "9:17:34", "remaining_time": "1:50:10"}
{"current_steps": 3740, "total_steps": 4473, "loss": 0.2641, "lr": 3.193367444281994e-06, "epoch": 5.852895148669797, "percentage": 83.61, "elapsed_time": "9:18:22", "remaining_time": "1:49:26"}
{"current_steps": 3745, "total_steps": 4473, "loss": 0.3083, "lr": 3.1511856867764547e-06, "epoch": 5.860719874804381, "percentage": 83.72, "elapsed_time": "9:19:02", "remaining_time": "1:48:40"}
{"current_steps": 3750, "total_steps": 4473, "loss": 0.2771, "lr": 3.109260541162189e-06, "epoch": 5.868544600938967, "percentage": 83.84, "elapsed_time": "9:19:49", "remaining_time": "1:47:56"}
{"current_steps": 3755, "total_steps": 4473, "loss": 0.2808, "lr": 3.067592645970241e-06, "epoch": 5.876369327073553, "percentage": 83.95, "elapsed_time": "9:20:26", "remaining_time": "1:47:09"}
{"current_steps": 3760, "total_steps": 4473, "loss": 0.2635, "lr": 3.026182635813655e-06, "epoch": 5.884194053208137, "percentage": 84.06, "elapsed_time": "9:21:21", "remaining_time": "1:46:26"}
{"current_steps": 3765, "total_steps": 4473, "loss": 0.2672, "lr": 2.9850311413778186e-06, "epoch": 5.892018779342723, "percentage": 84.17, "elapsed_time": "9:22:07", "remaining_time": "1:45:42"}
{"current_steps": 3770, "total_steps": 4473, "loss": 0.2701, "lr": 2.9441387894108596e-06, "epoch": 5.899843505477309, "percentage": 84.28, "elapsed_time": "9:22:48", "remaining_time": "1:44:56"}
{"current_steps": 3775, "total_steps": 4473, "loss": 0.3028, "lr": 2.9035062027141014e-06, "epoch": 5.907668231611893, "percentage": 84.4, "elapsed_time": "9:23:28", "remaining_time": "1:44:11"}
{"current_steps": 3780, "total_steps": 4473, "loss": 0.2845, "lr": 2.863134000132566e-06, "epoch": 5.915492957746479, "percentage": 84.51, "elapsed_time": "9:24:16", "remaining_time": "1:43:27"}
{"current_steps": 3785, "total_steps": 4473, "loss": 0.2668, "lr": 2.8230227965455604e-06, "epoch": 5.923317683881065, "percentage": 84.62, "elapsed_time": "9:25:05", "remaining_time": "1:42:42"}
{"current_steps": 3790, "total_steps": 4473, "loss": 0.3162, "lr": 2.7831732028573077e-06, "epoch": 5.931142410015649, "percentage": 84.73, "elapsed_time": "9:25:56", "remaining_time": "1:41:59"}
{"current_steps": 3795, "total_steps": 4473, "loss": 0.2908, "lr": 2.7435858259876358e-06, "epoch": 5.938967136150235, "percentage": 84.84, "elapsed_time": "9:26:38", "remaining_time": "1:41:13"}
{"current_steps": 3800, "total_steps": 4473, "loss": 0.2948, "lr": 2.70426126886276e-06, "epoch": 5.94679186228482, "percentage": 84.95, "elapsed_time": "9:27:17", "remaining_time": "1:40:28"}
{"current_steps": 3805, "total_steps": 4473, "loss": 0.2879, "lr": 2.665200130406065e-06, "epoch": 5.954616588419405, "percentage": 85.07, "elapsed_time": "9:28:05", "remaining_time": "1:39:43"}
{"current_steps": 3810, "total_steps": 4473, "loss": 0.2698, "lr": 2.6264030055290057e-06, "epoch": 5.962441314553991, "percentage": 85.18, "elapsed_time": "9:28:55", "remaining_time": "1:39:00"}
{"current_steps": 3815, "total_steps": 4473, "loss": 0.2944, "lr": 2.5878704851220306e-06, "epoch": 5.970266040688576, "percentage": 85.29, "elapsed_time": "9:29:39", "remaining_time": "1:38:15"}
{"current_steps": 3820, "total_steps": 4473, "loss": 0.2948, "lr": 2.5496031560456124e-06, "epoch": 5.978090766823161, "percentage": 85.4, "elapsed_time": "9:30:19", "remaining_time": "1:37:29"}
{"current_steps": 3825, "total_steps": 4473, "loss": 0.2687, "lr": 2.5116016011212697e-06, "epoch": 5.985915492957746, "percentage": 85.51, "elapsed_time": "9:31:12", "remaining_time": "1:36:46"}
{"current_steps": 3830, "total_steps": 4473, "loss": 0.2959, "lr": 2.473866399122733e-06, "epoch": 5.993740219092332, "percentage": 85.62, "elapsed_time": "9:31:51", "remaining_time": "1:36:00"}
{"current_steps": 3835, "total_steps": 4473, "loss": 0.2818, "lr": 2.4363981247670722e-06, "epoch": 6.001564945226917, "percentage": 85.74, "elapsed_time": "9:32:27", "remaining_time": "1:35:14"}
{"current_steps": 3840, "total_steps": 4473, "loss": 0.2476, "lr": 2.399197348706017e-06, "epoch": 6.009389671361502, "percentage": 85.85, "elapsed_time": "9:33:08", "remaining_time": "1:34:28"}
{"current_steps": 3845, "total_steps": 4473, "loss": 0.2638, "lr": 2.3622646375171998e-06, "epoch": 6.017214397496088, "percentage": 85.96, "elapsed_time": "9:33:54", "remaining_time": "1:33:44"}
{"current_steps": 3850, "total_steps": 4473, "loss": 0.274, "lr": 2.3256005536955797e-06, "epoch": 6.025039123630673, "percentage": 86.07, "elapsed_time": "9:34:24", "remaining_time": "1:32:57"}
{"current_steps": 3855, "total_steps": 4473, "loss": 0.2804, "lr": 2.289205655644815e-06, "epoch": 6.032863849765258, "percentage": 86.18, "elapsed_time": "9:34:58", "remaining_time": "1:32:10"}
{"current_steps": 3860, "total_steps": 4473, "loss": 0.2512, "lr": 2.253080497668829e-06, "epoch": 6.040688575899844, "percentage": 86.3, "elapsed_time": "9:35:51", "remaining_time": "1:31:27"}
{"current_steps": 3865, "total_steps": 4473, "loss": 0.2898, "lr": 2.217225629963309e-06, "epoch": 6.048513302034428, "percentage": 86.41, "elapsed_time": "9:36:29", "remaining_time": "1:30:41"}
{"current_steps": 3870, "total_steps": 4473, "loss": 0.2671, "lr": 2.181641598607367e-06, "epoch": 6.056338028169014, "percentage": 86.52, "elapsed_time": "9:37:13", "remaining_time": "1:29:56"}
{"current_steps": 3875, "total_steps": 4473, "loss": 0.2667, "lr": 2.1463289455551894e-06, "epoch": 6.0641627543036, "percentage": 86.63, "elapsed_time": "9:37:54", "remaining_time": "1:29:11"}
{"current_steps": 3880, "total_steps": 4473, "loss": 0.2412, "lr": 2.1112882086278107e-06, "epoch": 6.071987480438184, "percentage": 86.74, "elapsed_time": "9:38:51", "remaining_time": "1:28:28"}
{"current_steps": 3885, "total_steps": 4473, "loss": 0.2672, "lr": 2.0765199215049046e-06, "epoch": 6.07981220657277, "percentage": 86.85, "elapsed_time": "9:39:44", "remaining_time": "1:27:44"}
{"current_steps": 3890, "total_steps": 4473, "loss": 0.2931, "lr": 2.042024613716671e-06, "epoch": 6.087636932707356, "percentage": 86.97, "elapsed_time": "9:40:37", "remaining_time": "1:27:01"}
{"current_steps": 3895, "total_steps": 4473, "loss": 0.2881, "lr": 2.0078028106357506e-06, "epoch": 6.09546165884194, "percentage": 87.08, "elapsed_time": "9:41:16", "remaining_time": "1:26:15"}
{"current_steps": 3900, "total_steps": 4473, "loss": 0.2894, "lr": 1.9738550334692475e-06, "epoch": 6.103286384976526, "percentage": 87.19, "elapsed_time": "9:42:02", "remaining_time": "1:25:30"}
{"current_steps": 3905, "total_steps": 4473, "loss": 0.2845, "lr": 1.9401817992507622e-06, "epoch": 6.111111111111111, "percentage": 87.3, "elapsed_time": "9:42:48", "remaining_time": "1:24:46"}
{"current_steps": 3910, "total_steps": 4473, "loss": 0.2782, "lr": 1.9067836208325573e-06, "epoch": 6.118935837245696, "percentage": 87.41, "elapsed_time": "9:43:39", "remaining_time": "1:24:02"}
{"current_steps": 3915, "total_steps": 4473, "loss": 0.2885, "lr": 1.8736610068777006e-06, "epoch": 6.126760563380282, "percentage": 87.53, "elapsed_time": "9:44:18", "remaining_time": "1:23:16"}
{"current_steps": 3920, "total_steps": 4473, "loss": 0.2744, "lr": 1.8408144618523539e-06, "epoch": 6.134585289514867, "percentage": 87.64, "elapsed_time": "9:44:54", "remaining_time": "1:22:30"}
{"current_steps": 3925, "total_steps": 4473, "loss": 0.2876, "lr": 1.808244486018067e-06, "epoch": 6.142410015649452, "percentage": 87.75, "elapsed_time": "9:45:23", "remaining_time": "1:21:43"}
{"current_steps": 3930, "total_steps": 4473, "loss": 0.2425, "lr": 1.7759515754241753e-06, "epoch": 6.150234741784038, "percentage": 87.86, "elapsed_time": "9:46:13", "remaining_time": "1:20:59"}
{"current_steps": 3935, "total_steps": 4473, "loss": 0.2769, "lr": 1.7439362219002354e-06, "epoch": 6.158059467918623, "percentage": 87.97, "elapsed_time": "9:47:06", "remaining_time": "1:20:16"}
{"current_steps": 3940, "total_steps": 4473, "loss": 0.2933, "lr": 1.7121989130485372e-06, "epoch": 6.165884194053208, "percentage": 88.08, "elapsed_time": "9:47:57", "remaining_time": "1:19:32"}
{"current_steps": 3945, "total_steps": 4473, "loss": 0.2662, "lr": 1.6807401322366711e-06, "epoch": 6.173708920187793, "percentage": 88.2, "elapsed_time": "9:48:39", "remaining_time": "1:18:47"}
{"current_steps": 3950, "total_steps": 4473, "loss": 0.2594, "lr": 1.6495603585901787e-06, "epoch": 6.181533646322379, "percentage": 88.31, "elapsed_time": "9:49:25", "remaining_time": "1:18:02"}
{"current_steps": 3955, "total_steps": 4473, "loss": 0.2628, "lr": 1.618660066985247e-06, "epoch": 6.189358372456964, "percentage": 88.42, "elapsed_time": "9:50:22", "remaining_time": "1:17:19"}
{"current_steps": 3960, "total_steps": 4473, "loss": 0.2808, "lr": 1.5880397280414728e-06, "epoch": 6.197183098591549, "percentage": 88.53, "elapsed_time": "9:51:08", "remaining_time": "1:16:34"}
{"current_steps": 3965, "total_steps": 4473, "loss": 0.2659, "lr": 1.5576998081147144e-06, "epoch": 6.205007824726135, "percentage": 88.64, "elapsed_time": "9:51:58", "remaining_time": "1:15:50"}
{"current_steps": 3970, "total_steps": 4473, "loss": 0.2723, "lr": 1.5276407692899508e-06, "epoch": 6.21283255086072, "percentage": 88.75, "elapsed_time": "9:52:47", "remaining_time": "1:15:06"}
{"current_steps": 3975, "total_steps": 4473, "loss": 0.2622, "lr": 1.4978630693742923e-06, "epoch": 6.220657276995305, "percentage": 88.87, "elapsed_time": "9:53:28", "remaining_time": "1:14:21"}
{"current_steps": 3980, "total_steps": 4473, "loss": 0.2639, "lr": 1.468367161889963e-06, "epoch": 6.228482003129891, "percentage": 88.98, "elapsed_time": "9:54:12", "remaining_time": "1:13:36"}
{"current_steps": 3985, "total_steps": 4473, "loss": 0.2588, "lr": 1.4391534960674336e-06, "epoch": 6.236306729264475, "percentage": 89.09, "elapsed_time": "9:54:58", "remaining_time": "1:12:51"}
{"current_steps": 3990, "total_steps": 4473, "loss": 0.2787, "lr": 1.4102225168385374e-06, "epoch": 6.244131455399061, "percentage": 89.2, "elapsed_time": "9:55:31", "remaining_time": "1:12:05"}
{"current_steps": 3995, "total_steps": 4473, "loss": 0.2705, "lr": 1.3815746648297347e-06, "epoch": 6.251956181533647, "percentage": 89.31, "elapsed_time": "9:56:20", "remaining_time": "1:11:21"}
{"current_steps": 4000, "total_steps": 4473, "loss": 0.2924, "lr": 1.3532103763553716e-06, "epoch": 6.259780907668231, "percentage": 89.43, "elapsed_time": "9:56:59", "remaining_time": "1:10:35"}
{"current_steps": 4005, "total_steps": 4473, "loss": 0.2947, "lr": 1.3251300834110592e-06, "epoch": 6.267605633802817, "percentage": 89.54, "elapsed_time": "9:57:45", "remaining_time": "1:09:51"}
{"current_steps": 4010, "total_steps": 4473, "loss": 0.2814, "lr": 1.2973342136670719e-06, "epoch": 6.275430359937403, "percentage": 89.65, "elapsed_time": "9:58:33", "remaining_time": "1:09:06"}
{"current_steps": 4015, "total_steps": 4473, "loss": 0.2686, "lr": 1.269823190461843e-06, "epoch": 6.283255086071987, "percentage": 89.76, "elapsed_time": "9:59:11", "remaining_time": "1:08:21"}
{"current_steps": 4020, "total_steps": 4473, "loss": 0.2788, "lr": 1.242597432795518e-06, "epoch": 6.291079812206573, "percentage": 89.87, "elapsed_time": "9:59:55", "remaining_time": "1:07:36"}
{"current_steps": 4025, "total_steps": 4473, "loss": 0.2616, "lr": 1.215657355323585e-06, "epoch": 6.298904538341158, "percentage": 89.98, "elapsed_time": "10:00:38", "remaining_time": "1:06:51"}
{"current_steps": 4030, "total_steps": 4473, "loss": 0.2781, "lr": 1.189003368350532e-06, "epoch": 6.306729264475743, "percentage": 90.1, "elapsed_time": "10:01:08", "remaining_time": "1:06:04"}
{"current_steps": 4035, "total_steps": 4473, "loss": 0.2527, "lr": 1.1626358778236192e-06, "epoch": 6.314553990610329, "percentage": 90.21, "elapsed_time": "10:01:49", "remaining_time": "1:05:19"}
{"current_steps": 4040, "total_steps": 4473, "loss": 0.2587, "lr": 1.1365552853266904e-06, "epoch": 6.322378716744914, "percentage": 90.32, "elapsed_time": "10:02:36", "remaining_time": "1:04:35"}
{"current_steps": 4045, "total_steps": 4473, "loss": 0.2892, "lr": 1.1107619880740584e-06, "epoch": 6.330203442879499, "percentage": 90.43, "elapsed_time": "10:03:22", "remaining_time": "1:03:50"}
{"current_steps": 4050, "total_steps": 4473, "loss": 0.2852, "lr": 1.085256378904449e-06, "epoch": 6.338028169014084, "percentage": 90.54, "elapsed_time": "10:03:58", "remaining_time": "1:03:04"}
{"current_steps": 4055, "total_steps": 4473, "loss": 0.2567, "lr": 1.0600388462750287e-06, "epoch": 6.34585289514867, "percentage": 90.66, "elapsed_time": "10:04:44", "remaining_time": "1:02:20"}
{"current_steps": 4060, "total_steps": 4473, "loss": 0.2744, "lr": 1.0351097742554716e-06, "epoch": 6.353677621283255, "percentage": 90.77, "elapsed_time": "10:05:37", "remaining_time": "1:01:36"}
{"current_steps": 4065, "total_steps": 4473, "loss": 0.2669, "lr": 1.0104695425221367e-06, "epoch": 6.36150234741784, "percentage": 90.88, "elapsed_time": "10:06:24", "remaining_time": "1:00:51"}
{"current_steps": 4070, "total_steps": 4473, "loss": 0.2888, "lr": 9.861185263522578e-07, "epoch": 6.369327073552426, "percentage": 90.99, "elapsed_time": "10:06:59", "remaining_time": "1:00:06"}
{"current_steps": 4075, "total_steps": 4473, "loss": 0.268, "lr": 9.620570966182363e-07, "epoch": 6.377151799687011, "percentage": 91.1, "elapsed_time": "10:07:49", "remaining_time": "0:59:21"}
{"current_steps": 4080, "total_steps": 4473, "loss": 0.2931, "lr": 9.382856197820045e-07, "epoch": 6.384976525821596, "percentage": 91.21, "elapsed_time": "10:08:32", "remaining_time": "0:58:37"}
{"current_steps": 4085, "total_steps": 4473, "loss": 0.2626, "lr": 9.148044578894311e-07, "epoch": 6.392801251956182, "percentage": 91.33, "elapsed_time": "10:09:25", "remaining_time": "0:57:53"}
{"current_steps": 4090, "total_steps": 4473, "loss": 0.2542, "lr": 8.91613968564815e-07, "epoch": 6.400625978090767, "percentage": 91.44, "elapsed_time": "10:10:12", "remaining_time": "0:57:08"}
{"current_steps": 4095, "total_steps": 4473, "loss": 0.2883, "lr": 8.687145050054279e-07, "epoch": 6.408450704225352, "percentage": 91.55, "elapsed_time": "10:11:04", "remaining_time": "0:56:24"}
{"current_steps": 4100, "total_steps": 4473, "loss": 0.2594, "lr": 8.461064159761534e-07, "epoch": 6.416275430359938, "percentage": 91.66, "elapsed_time": "10:11:47", "remaining_time": "0:55:39"}
{"current_steps": 4105, "total_steps": 4473, "loss": 0.2769, "lr": 8.237900458041492e-07, "epoch": 6.424100156494522, "percentage": 91.77, "elapsed_time": "10:12:40", "remaining_time": "0:54:55"}
{"current_steps": 4110, "total_steps": 4473, "loss": 0.2746, "lr": 8.017657343736341e-07, "epoch": 6.431924882629108, "percentage": 91.88, "elapsed_time": "10:13:20", "remaining_time": "0:54:10"}
{"current_steps": 4115, "total_steps": 4473, "loss": 0.2666, "lr": 7.800338171206823e-07, "epoch": 6.439749608763694, "percentage": 92.0, "elapsed_time": "10:14:07", "remaining_time": "0:53:25"}
{"current_steps": 4120, "total_steps": 4473, "loss": 0.2763, "lr": 7.585946250281373e-07, "epoch": 6.447574334898278, "percentage": 92.11, "elapsed_time": "10:14:42", "remaining_time": "0:52:40"}
{"current_steps": 4125, "total_steps": 4473, "loss": 0.2574, "lr": 7.374484846205465e-07, "epoch": 6.455399061032864, "percentage": 92.22, "elapsed_time": "10:15:30", "remaining_time": "0:51:55"}
{"current_steps": 4130, "total_steps": 4473, "loss": 0.2705, "lr": 7.165957179592231e-07, "epoch": 6.463223787167449, "percentage": 92.33, "elapsed_time": "10:16:08", "remaining_time": "0:51:10"}
{"current_steps": 4135, "total_steps": 4473, "loss": 0.29, "lr": 6.960366426373033e-07, "epoch": 6.471048513302034, "percentage": 92.44, "elapsed_time": "10:16:51", "remaining_time": "0:50:25"}
{"current_steps": 4140, "total_steps": 4473, "loss": 0.2836, "lr": 6.757715717749347e-07, "epoch": 6.47887323943662, "percentage": 92.56, "elapsed_time": "10:17:41", "remaining_time": "0:49:41"}
{"current_steps": 4145, "total_steps": 4473, "loss": 0.2834, "lr": 6.558008140145023e-07, "epoch": 6.486697965571205, "percentage": 92.67, "elapsed_time": "10:18:11", "remaining_time": "0:48:55"}
{"current_steps": 4150, "total_steps": 4473, "loss": 0.2764, "lr": 6.361246735159143e-07, "epoch": 6.49452269170579, "percentage": 92.78, "elapsed_time": "10:18:51", "remaining_time": "0:48:09"}
{"current_steps": 4155, "total_steps": 4473, "loss": 0.2571, "lr": 6.167434499519886e-07, "epoch": 6.502347417840376, "percentage": 92.89, "elapsed_time": "10:19:23", "remaining_time": "0:47:24"}
{"current_steps": 4160, "total_steps": 4473, "loss": 0.2923, "lr": 5.976574385038802e-07, "epoch": 6.510172143974961, "percentage": 93.0, "elapsed_time": "10:20:12", "remaining_time": "0:46:39"}
{"current_steps": 4165, "total_steps": 4473, "loss": 0.2698, "lr": 5.788669298565808e-07, "epoch": 6.517996870109546, "percentage": 93.11, "elapsed_time": "10:20:53", "remaining_time": "0:45:54"}
{"current_steps": 4170, "total_steps": 4473, "loss": 0.2479, "lr": 5.603722101944997e-07, "epoch": 6.525821596244132, "percentage": 93.23, "elapsed_time": "10:21:41", "remaining_time": "0:45:10"}
{"current_steps": 4175, "total_steps": 4473, "loss": 0.2715, "lr": 5.421735611971013e-07, "epoch": 6.533646322378717, "percentage": 93.34, "elapsed_time": "10:22:22", "remaining_time": "0:44:25"}
{"current_steps": 4180, "total_steps": 4473, "loss": 0.2643, "lr": 5.242712600346167e-07, "epoch": 6.541471048513302, "percentage": 93.45, "elapsed_time": "10:23:08", "remaining_time": "0:43:40"}
{"current_steps": 4185, "total_steps": 4473, "loss": 0.2704, "lr": 5.066655793638209e-07, "epoch": 6.549295774647887, "percentage": 93.56, "elapsed_time": "10:23:51", "remaining_time": "0:42:55"}
{"current_steps": 4190, "total_steps": 4473, "loss": 0.2842, "lr": 4.893567873238781e-07, "epoch": 6.557120500782473, "percentage": 93.67, "elapsed_time": "10:24:45", "remaining_time": "0:42:11"}
{"current_steps": 4195, "total_steps": 4473, "loss": 0.2756, "lr": 4.7234514753225824e-07, "epoch": 6.564945226917058, "percentage": 93.78, "elapsed_time": "10:25:22", "remaining_time": "0:41:26"}
{"current_steps": 4200, "total_steps": 4473, "loss": 0.262, "lr": 4.55630919080734e-07, "epoch": 6.572769953051643, "percentage": 93.9, "elapsed_time": "10:26:09", "remaining_time": "0:40:42"}
{"current_steps": 4205, "total_steps": 4473, "loss": 0.2913, "lr": 4.3921435653141444e-07, "epoch": 6.580594679186229, "percentage": 94.01, "elapsed_time": "10:26:52", "remaining_time": "0:39:57"}
{"current_steps": 4210, "total_steps": 4473, "loss": 0.2711, "lr": 4.2309570991288406e-07, "epoch": 6.588419405320813, "percentage": 94.12, "elapsed_time": "10:27:38", "remaining_time": "0:39:12"}
{"current_steps": 4215, "total_steps": 4473, "loss": 0.2416, "lr": 4.0727522471638803e-07, "epoch": 6.596244131455399, "percentage": 94.23, "elapsed_time": "10:28:22", "remaining_time": "0:38:27"}
{"current_steps": 4220, "total_steps": 4473, "loss": 0.2629, "lr": 3.9175314189209056e-07, "epoch": 6.604068857589985, "percentage": 94.34, "elapsed_time": "10:29:10", "remaining_time": "0:37:43"}
{"current_steps": 4225, "total_steps": 4473, "loss": 0.2833, "lr": 3.765296978454136e-07, "epoch": 6.611893583724569, "percentage": 94.46, "elapsed_time": "10:29:45", "remaining_time": "0:36:57"}
{"current_steps": 4230, "total_steps": 4473, "loss": 0.2706, "lr": 3.6160512443343064e-07, "epoch": 6.619718309859155, "percentage": 94.57, "elapsed_time": "10:30:31", "remaining_time": "0:36:13"}
{"current_steps": 4235, "total_steps": 4473, "loss": 0.2852, "lr": 3.469796489613386e-07, "epoch": 6.627543035993741, "percentage": 94.68, "elapsed_time": "10:31:17", "remaining_time": "0:35:28"}
{"current_steps": 4240, "total_steps": 4473, "loss": 0.2929, "lr": 3.3265349417898497e-07, "epoch": 6.635367762128325, "percentage": 94.79, "elapsed_time": "10:32:14", "remaining_time": "0:34:44"}
{"current_steps": 4245, "total_steps": 4473, "loss": 0.2582, "lr": 3.186268782774926e-07, "epoch": 6.643192488262911, "percentage": 94.9, "elapsed_time": "10:32:54", "remaining_time": "0:33:59"}
{"current_steps": 4250, "total_steps": 4473, "loss": 0.2642, "lr": 3.0490001488592715e-07, "epoch": 6.651017214397496, "percentage": 95.01, "elapsed_time": "10:33:34", "remaining_time": "0:33:14"}
{"current_steps": 4255, "total_steps": 4473, "loss": 0.2943, "lr": 2.9147311306804593e-07, "epoch": 6.658841940532081, "percentage": 95.13, "elapsed_time": "10:34:21", "remaining_time": "0:32:30"}
{"current_steps": 4260, "total_steps": 4473, "loss": 0.2716, "lr": 2.7834637731910086e-07, "epoch": 6.666666666666667, "percentage": 95.24, "elapsed_time": "10:35:02", "remaining_time": "0:31:45"}
{"current_steps": 4265, "total_steps": 4473, "loss": 0.2735, "lr": 2.6552000756274956e-07, "epoch": 6.674491392801252, "percentage": 95.35, "elapsed_time": "10:35:49", "remaining_time": "0:31:00"}
{"current_steps": 4270, "total_steps": 4473, "loss": 0.2652, "lr": 2.5299419914798897e-07, "epoch": 6.682316118935837, "percentage": 95.46, "elapsed_time": "10:36:35", "remaining_time": "0:30:15"}
{"current_steps": 4275, "total_steps": 4473, "loss": 0.2568, "lr": 2.407691428461911e-07, "epoch": 6.690140845070422, "percentage": 95.57, "elapsed_time": "10:37:19", "remaining_time": "0:29:31"}
{"current_steps": 4280, "total_steps": 4473, "loss": 0.2843, "lr": 2.288450248481877e-07, "epoch": 6.697965571205008, "percentage": 95.69, "elapsed_time": "10:38:15", "remaining_time": "0:28:46"}
{"current_steps": 4285, "total_steps": 4473, "loss": 0.2909, "lr": 2.1722202676144998e-07, "epoch": 6.705790297339593, "percentage": 95.8, "elapsed_time": "10:39:07", "remaining_time": "0:28:02"}
{"current_steps": 4290, "total_steps": 4473, "loss": 0.2843, "lr": 2.0590032560730221e-07, "epoch": 6.713615023474178, "percentage": 95.91, "elapsed_time": "10:40:04", "remaining_time": "0:27:18"}
{"current_steps": 4295, "total_steps": 4473, "loss": 0.2615, "lr": 1.9488009381824603e-07, "epoch": 6.721439749608764, "percentage": 96.02, "elapsed_time": "10:40:47", "remaining_time": "0:26:33"}
{"current_steps": 4300, "total_steps": 4473, "loss": 0.2842, "lr": 1.8416149923532244e-07, "epoch": 6.729264475743349, "percentage": 96.13, "elapsed_time": "10:41:32", "remaining_time": "0:25:48"}
{"current_steps": 4305, "total_steps": 4473, "loss": 0.2413, "lr": 1.737447051055563e-07, "epoch": 6.737089201877934, "percentage": 96.24, "elapsed_time": "10:42:19", "remaining_time": "0:25:03"}
{"current_steps": 4310, "total_steps": 4473, "loss": 0.273, "lr": 1.636298700794714e-07, "epoch": 6.74491392801252, "percentage": 96.36, "elapsed_time": "10:43:11", "remaining_time": "0:24:19"}
{"current_steps": 4315, "total_steps": 4473, "loss": 0.2688, "lr": 1.538171482086792e-07, "epoch": 6.752738654147105, "percentage": 96.47, "elapsed_time": "10:43:51", "remaining_time": "0:23:34"}
{"current_steps": 4320, "total_steps": 4473, "loss": 0.2421, "lr": 1.4430668894352295e-07, "epoch": 6.76056338028169, "percentage": 96.58, "elapsed_time": "10:44:34", "remaining_time": "0:22:49"}
{"current_steps": 4325, "total_steps": 4473, "loss": 0.274, "lr": 1.3509863713081052e-07, "epoch": 6.768388106416276, "percentage": 96.69, "elapsed_time": "10:45:16", "remaining_time": "0:22:04"}
{"current_steps": 4330, "total_steps": 4473, "loss": 0.2692, "lr": 1.2619313301159843e-07, "epoch": 6.77621283255086, "percentage": 96.8, "elapsed_time": "10:45:58", "remaining_time": "0:21:20"}
{"current_steps": 4335, "total_steps": 4473, "loss": 0.3018, "lr": 1.1759031221907135e-07, "epoch": 6.784037558685446, "percentage": 96.91, "elapsed_time": "10:46:51", "remaining_time": "0:20:35"}
{"current_steps": 4340, "total_steps": 4473, "loss": 0.2931, "lr": 1.0929030577645938e-07, "epoch": 6.791862284820032, "percentage": 97.03, "elapsed_time": "10:47:32", "remaining_time": "0:19:50"}
{"current_steps": 4345, "total_steps": 4473, "loss": 0.2646, "lr": 1.012932400950506e-07, "epoch": 6.799687010954616, "percentage": 97.14, "elapsed_time": "10:48:19", "remaining_time": "0:19:05"}
{"current_steps": 4350, "total_steps": 4473, "loss": 0.2934, "lr": 9.359923697227047e-08, "epoch": 6.807511737089202, "percentage": 97.25, "elapsed_time": "10:48:58", "remaining_time": "0:18:21"}
{"current_steps": 4355, "total_steps": 4473, "loss": 0.2498, "lr": 8.62084135898189e-08, "epoch": 6.815336463223787, "percentage": 97.36, "elapsed_time": "10:49:44", "remaining_time": "0:17:36"}
{"current_steps": 4360, "total_steps": 4473, "loss": 0.2648, "lr": 7.912088251188277e-08, "epoch": 6.823161189358372, "percentage": 97.47, "elapsed_time": "10:50:36", "remaining_time": "0:16:51"}
{"current_steps": 4365, "total_steps": 4473, "loss": 0.2676, "lr": 7.233675168343501e-08, "epoch": 6.830985915492958, "percentage": 97.59, "elapsed_time": "10:51:24", "remaining_time": "0:16:07"}
{"current_steps": 4370, "total_steps": 4473, "loss": 0.2449, "lr": 6.585612442858269e-08, "epoch": 6.838810641627543, "percentage": 97.7, "elapsed_time": "10:52:10", "remaining_time": "0:15:22"}
{"current_steps": 4375, "total_steps": 4473, "loss": 0.2893, "lr": 5.967909944898375e-08, "epoch": 6.846635367762128, "percentage": 97.81, "elapsed_time": "10:52:52", "remaining_time": "0:14:37"}
{"current_steps": 4380, "total_steps": 4473, "loss": 0.2635, "lr": 5.3805770822363826e-08, "epoch": 6.854460093896714, "percentage": 97.92, "elapsed_time": "10:53:37", "remaining_time": "0:13:52"}
{"current_steps": 4385, "total_steps": 4473, "loss": 0.2601, "lr": 4.823622800106842e-08, "epoch": 6.862284820031299, "percentage": 98.03, "elapsed_time": "10:54:22", "remaining_time": "0:13:07"}
{"current_steps": 4390, "total_steps": 4473, "loss": 0.2749, "lr": 4.2970555810706307e-08, "epoch": 6.870109546165884, "percentage": 98.14, "elapsed_time": "10:55:09", "remaining_time": "0:12:23"}
{"current_steps": 4395, "total_steps": 4473, "loss": 0.2688, "lr": 3.8008834448852724e-08, "epoch": 6.87793427230047, "percentage": 98.26, "elapsed_time": "10:55:45", "remaining_time": "0:11:38"}
{"current_steps": 4400, "total_steps": 4473, "loss": 0.2476, "lr": 3.335113948383706e-08, "epoch": 6.885758998435055, "percentage": 98.37, "elapsed_time": "10:56:21", "remaining_time": "0:10:53"}
{"current_steps": 4405, "total_steps": 4473, "loss": 0.2864, "lr": 2.89975418535815e-08, "epoch": 6.89358372456964, "percentage": 98.48, "elapsed_time": "10:56:55", "remaining_time": "0:10:08"}
{"current_steps": 4410, "total_steps": 4473, "loss": 0.2713, "lr": 2.4948107864528615e-08, "epoch": 6.901408450704225, "percentage": 98.59, "elapsed_time": "10:57:36", "remaining_time": "0:09:23"}
{"current_steps": 4415, "total_steps": 4473, "loss": 0.2959, "lr": 2.120289919062879e-08, "epoch": 6.909233176838811, "percentage": 98.7, "elapsed_time": "10:58:23", "remaining_time": "0:08:38"}
{"current_steps": 4420, "total_steps": 4473, "loss": 0.2755, "lr": 1.776197287239656e-08, "epoch": 6.917057902973396, "percentage": 98.82, "elapsed_time": "10:59:01", "remaining_time": "0:07:54"}
{"current_steps": 4425, "total_steps": 4473, "loss": 0.2769, "lr": 1.462538131604907e-08, "epoch": 6.924882629107981, "percentage": 98.93, "elapsed_time": "10:59:32", "remaining_time": "0:07:09"}
{"current_steps": 4430, "total_steps": 4473, "loss": 0.2498, "lr": 1.179317229270449e-08, "epoch": 6.932707355242567, "percentage": 99.04, "elapsed_time": "11:00:19", "remaining_time": "0:06:24"}
{"current_steps": 4435, "total_steps": 4473, "loss": 0.2857, "lr": 9.265388937655939e-09, "epoch": 6.940532081377151, "percentage": 99.15, "elapsed_time": "11:00:54", "remaining_time": "0:05:39"}
{"current_steps": 4440, "total_steps": 4473, "loss": 0.284, "lr": 7.042069749707559e-09, "epoch": 6.948356807511737, "percentage": 99.26, "elapsed_time": "11:01:46", "remaining_time": "0:04:55"}
{"current_steps": 4445, "total_steps": 4473, "loss": 0.2588, "lr": 5.123248590599428e-09, "epoch": 6.956181533646323, "percentage": 99.37, "elapsed_time": "11:02:28", "remaining_time": "0:04:10"}
{"current_steps": 4450, "total_steps": 4473, "loss": 0.2642, "lr": 3.5089546844879753e-09, "epoch": 6.964006259780907, "percentage": 99.49, "elapsed_time": "11:03:15", "remaining_time": "0:03:25"}
{"current_steps": 4455, "total_steps": 4473, "loss": 0.2804, "lr": 2.1992126174885663e-09, "epoch": 6.971830985915493, "percentage": 99.6, "elapsed_time": "11:04:06", "remaining_time": "0:02:40"}
{"current_steps": 4460, "total_steps": 4473, "loss": 0.2613, "lr": 1.1940423373246746e-09, "epoch": 6.979655712050079, "percentage": 99.71, "elapsed_time": "11:04:59", "remaining_time": "0:01:56"}
{"current_steps": 4465, "total_steps": 4473, "loss": 0.264, "lr": 4.934591530036947e-10, "epoch": 6.987480438184663, "percentage": 99.82, "elapsed_time": "11:05:49", "remaining_time": "0:01:11"}
{"current_steps": 4470, "total_steps": 4473, "loss": 0.2821, "lr": 9.747373459267906e-11, "epoch": 6.995305164319249, "percentage": 99.93, "elapsed_time": "11:06:30", "remaining_time": "0:00:26"}
{"current_steps": 4473, "total_steps": 4473, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "11:07:33", "remaining_time": "0:00:00"}

9881
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:d4347c85a7e7d17e728143ccda2f8f0a4cd8fc84a2c6edb28dd68d8042b89314
size 8657

BIN
training_loss.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 43 KiB

1
vocab.json Normal file

File diff suppressed because one or more lines are too long