初始化项目,由ModelHub XC社区提供模型

Model: laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-11 23:03:12 +08:00
commit ca4d22c132
24 changed files with 11021 additions and 0 deletions

56
.gitattributes vendored Normal file
View File

@@ -0,0 +1,56 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
training_args.bin filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text
vocab.json filter=lfs diff=lfs merge=lfs -text
model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
merges.txt filter=lfs diff=lfs merge=lfs -text
model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text

61
README.md Normal file
View File

@@ -0,0 +1,61 @@
---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3-8B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--DCAgent2--GLM-4.7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k/snapshots/e209a88db18950c3ce4e72a45a6088561d99d1bf_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": 5.12016799029668,
"achieved_tflops_per_gpu_theoretical": 216.82589202068274,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.07740560173988342,
"mfu_percent": 0.5177116269258523,
"mfu_percent_theoretical": 21.923750457096332,
"total_flos": 2.6502668329167094e+18,
"train_loss": 0.3043324818911333,
"train_runtime": 64701.6572,
"train_samples_per_second": 1.021,
"train_steps_per_second": 0.064,
"valid_targets_mean": 6206.0,
"valid_targets_min": 3223
}

89
chat_template.jinja Normal file
View File

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

68
config.json Normal file
View File

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

1
configuration.json Normal file
View File

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

12
generation_config.json Normal file
View File

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

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

Binary file not shown.

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3ecef380ff336f223c6aac4756c6d6fd6d21e9d319ee46b8ebcd4cb69a29271a
size 4902257696

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4fd971690d2521796d3975f5f0559681e59ee4d0a63e1d95cbb1a77cf98595f6
size 4915960368

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1397a6fad7e9c237f3b76e4686aaa2c19d12832293a6cdcf726258a2dc0fffea
size 4983068496

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fb69283d1ca34768ff64e3ae89f233bbc5522913aa832d6a7e53bc98dbad5ffe
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": "e209a88db18950c3ce4e72a45a6088561d99d1bf_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--DCAgent2--GLM-4.7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k/snapshots/e209a88db18950c3ce4e72a45a6088561d99d1bf_thinking_preprocessed",
"training_type": "SFT",
"training_parameters": "https://huggingface.co/laion/GLM-4_7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k-fixthink/blob/main/config.json",
"wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/sft_GLM-4-7-swesmith-sandboxes-with_tests-oracle_verified_120s-maxeps-131k_Qwen3-8B",
"traces_location_s3": null
}

31
special_tokens_map.json Normal file
View File

@@ -0,0 +1,31 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

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

Binary file not shown.

240
tokenizer_config.json Normal file
View File

@@ -0,0 +1,240 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 32768,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

16
train_results.json Normal file
View File

@@ -0,0 +1,16 @@
{
"achieved_tflops_per_gpu": 5.12016799029668,
"achieved_tflops_per_gpu_theoretical": 216.82589202068274,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.07740560173988342,
"mfu_percent": 0.5177116269258523,
"mfu_percent_theoretical": 21.923750457096332,
"total_flos": 2.6502668329167094e+18,
"train_loss": 0.3043324818911333,
"train_runtime": 64701.6572,
"train_samples_per_second": 1.021,
"train_steps_per_second": 0.064,
"valid_targets_mean": 6206.0,
"valid_targets_min": 3223
}

827
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,827 @@
{"current_steps": 5, "total_steps": 4130, "loss": 0.8805, "lr": 3.8740920096852305e-07, "epoch": 0.00847457627118644, "percentage": 0.12, "elapsed_time": "0:01:22", "remaining_time": "18:55:17"}
{"current_steps": 10, "total_steps": 4130, "loss": 0.8479, "lr": 8.716707021791768e-07, "epoch": 0.01694915254237288, "percentage": 0.24, "elapsed_time": "0:02:44", "remaining_time": "18:51:57"}
{"current_steps": 15, "total_steps": 4130, "loss": 0.7925, "lr": 1.3559322033898307e-06, "epoch": 0.025423728813559324, "percentage": 0.36, "elapsed_time": "0:04:05", "remaining_time": "18:41:22"}
{"current_steps": 20, "total_steps": 4130, "loss": 0.7771, "lr": 1.8401937046004845e-06, "epoch": 0.03389830508474576, "percentage": 0.48, "elapsed_time": "0:05:27", "remaining_time": "18:42:01"}
{"current_steps": 25, "total_steps": 4130, "loss": 0.6944, "lr": 2.324455205811138e-06, "epoch": 0.0423728813559322, "percentage": 0.61, "elapsed_time": "0:06:46", "remaining_time": "18:33:48"}
{"current_steps": 30, "total_steps": 4130, "loss": 0.681, "lr": 2.808716707021792e-06, "epoch": 0.05084745762711865, "percentage": 0.73, "elapsed_time": "0:08:08", "remaining_time": "18:32:42"}
{"current_steps": 35, "total_steps": 4130, "loss": 0.6805, "lr": 3.2929782082324455e-06, "epoch": 0.059322033898305086, "percentage": 0.85, "elapsed_time": "0:09:30", "remaining_time": "18:32:59"}
{"current_steps": 40, "total_steps": 4130, "loss": 0.5617, "lr": 3.7772397094430994e-06, "epoch": 0.06779661016949153, "percentage": 0.97, "elapsed_time": "0:10:49", "remaining_time": "18:27:13"}
{"current_steps": 45, "total_steps": 4130, "loss": 0.6141, "lr": 4.261501210653753e-06, "epoch": 0.07627118644067797, "percentage": 1.09, "elapsed_time": "0:12:09", "remaining_time": "18:23:55"}
{"current_steps": 50, "total_steps": 4130, "loss": 0.5575, "lr": 4.745762711864408e-06, "epoch": 0.0847457627118644, "percentage": 1.21, "elapsed_time": "0:13:29", "remaining_time": "18:21:35"}
{"current_steps": 55, "total_steps": 4130, "loss": 0.5185, "lr": 5.230024213075061e-06, "epoch": 0.09322033898305085, "percentage": 1.33, "elapsed_time": "0:14:46", "remaining_time": "18:14:13"}
{"current_steps": 60, "total_steps": 4130, "loss": 0.5227, "lr": 5.7142857142857145e-06, "epoch": 0.1016949152542373, "percentage": 1.45, "elapsed_time": "0:16:07", "remaining_time": "18:14:01"}
{"current_steps": 65, "total_steps": 4130, "loss": 0.5268, "lr": 6.198547215496369e-06, "epoch": 0.11016949152542373, "percentage": 1.57, "elapsed_time": "0:17:25", "remaining_time": "18:09:55"}
{"current_steps": 70, "total_steps": 4130, "loss": 0.5186, "lr": 6.682808716707022e-06, "epoch": 0.11864406779661017, "percentage": 1.69, "elapsed_time": "0:18:44", "remaining_time": "18:07:13"}
{"current_steps": 75, "total_steps": 4130, "loss": 0.5181, "lr": 7.1670702179176766e-06, "epoch": 0.1271186440677966, "percentage": 1.82, "elapsed_time": "0:20:02", "remaining_time": "18:03:40"}
{"current_steps": 80, "total_steps": 4130, "loss": 0.4839, "lr": 7.65133171912833e-06, "epoch": 0.13559322033898305, "percentage": 1.94, "elapsed_time": "0:21:18", "remaining_time": "17:58:30"}
{"current_steps": 85, "total_steps": 4130, "loss": 0.5197, "lr": 8.135593220338983e-06, "epoch": 0.1440677966101695, "percentage": 2.06, "elapsed_time": "0:22:40", "remaining_time": "17:59:19"}
{"current_steps": 90, "total_steps": 4130, "loss": 0.517, "lr": 8.619854721549637e-06, "epoch": 0.15254237288135594, "percentage": 2.18, "elapsed_time": "0:24:01", "remaining_time": "17:58:24"}
{"current_steps": 95, "total_steps": 4130, "loss": 0.4704, "lr": 9.10411622276029e-06, "epoch": 0.16101694915254236, "percentage": 2.3, "elapsed_time": "0:25:24", "remaining_time": "17:59:02"}
{"current_steps": 100, "total_steps": 4130, "loss": 0.4631, "lr": 9.588377723970946e-06, "epoch": 0.1694915254237288, "percentage": 2.42, "elapsed_time": "0:26:42", "remaining_time": "17:56:31"}
{"current_steps": 105, "total_steps": 4130, "loss": 0.4495, "lr": 1.0072639225181599e-05, "epoch": 0.17796610169491525, "percentage": 2.54, "elapsed_time": "0:28:04", "remaining_time": "17:56:09"}
{"current_steps": 110, "total_steps": 4130, "loss": 0.4323, "lr": 1.0556900726392252e-05, "epoch": 0.1864406779661017, "percentage": 2.66, "elapsed_time": "0:29:27", "remaining_time": "17:56:22"}
{"current_steps": 115, "total_steps": 4130, "loss": 0.4595, "lr": 1.1041162227602906e-05, "epoch": 0.19491525423728814, "percentage": 2.78, "elapsed_time": "0:30:48", "remaining_time": "17:55:43"}
{"current_steps": 120, "total_steps": 4130, "loss": 0.4257, "lr": 1.1525423728813561e-05, "epoch": 0.2033898305084746, "percentage": 2.91, "elapsed_time": "0:32:05", "remaining_time": "17:52:08"}
{"current_steps": 125, "total_steps": 4130, "loss": 0.4552, "lr": 1.2009685230024215e-05, "epoch": 0.211864406779661, "percentage": 3.03, "elapsed_time": "0:33:24", "remaining_time": "17:50:20"}
{"current_steps": 130, "total_steps": 4130, "loss": 0.4537, "lr": 1.2493946731234868e-05, "epoch": 0.22033898305084745, "percentage": 3.15, "elapsed_time": "0:34:42", "remaining_time": "17:47:48"}
{"current_steps": 135, "total_steps": 4130, "loss": 0.4045, "lr": 1.2978208232445521e-05, "epoch": 0.2288135593220339, "percentage": 3.27, "elapsed_time": "0:36:01", "remaining_time": "17:46:06"}
{"current_steps": 140, "total_steps": 4130, "loss": 0.4456, "lr": 1.3462469733656177e-05, "epoch": 0.23728813559322035, "percentage": 3.39, "elapsed_time": "0:37:22", "remaining_time": "17:45:07"}
{"current_steps": 145, "total_steps": 4130, "loss": 0.4839, "lr": 1.3946731234866828e-05, "epoch": 0.2457627118644068, "percentage": 3.51, "elapsed_time": "0:38:44", "remaining_time": "17:44:51"}
{"current_steps": 150, "total_steps": 4130, "loss": 0.3795, "lr": 1.4430992736077482e-05, "epoch": 0.2542372881355932, "percentage": 3.63, "elapsed_time": "0:40:07", "remaining_time": "17:44:35"}
{"current_steps": 155, "total_steps": 4130, "loss": 0.422, "lr": 1.4915254237288137e-05, "epoch": 0.2627118644067797, "percentage": 3.75, "elapsed_time": "0:41:28", "remaining_time": "17:43:32"}
{"current_steps": 160, "total_steps": 4130, "loss": 0.3944, "lr": 1.5399515738498792e-05, "epoch": 0.2711864406779661, "percentage": 3.87, "elapsed_time": "0:42:46", "remaining_time": "17:41:32"}
{"current_steps": 165, "total_steps": 4130, "loss": 0.3938, "lr": 1.5883777239709442e-05, "epoch": 0.2796610169491525, "percentage": 4.0, "elapsed_time": "0:44:08", "remaining_time": "17:40:38"}
{"current_steps": 170, "total_steps": 4130, "loss": 0.4304, "lr": 1.63680387409201e-05, "epoch": 0.288135593220339, "percentage": 4.12, "elapsed_time": "0:45:30", "remaining_time": "17:40:03"}
{"current_steps": 175, "total_steps": 4130, "loss": 0.3997, "lr": 1.6852300242130752e-05, "epoch": 0.2966101694915254, "percentage": 4.24, "elapsed_time": "0:46:48", "remaining_time": "17:37:56"}
{"current_steps": 180, "total_steps": 4130, "loss": 0.4092, "lr": 1.7336561743341406e-05, "epoch": 0.3050847457627119, "percentage": 4.36, "elapsed_time": "0:48:10", "remaining_time": "17:37:17"}
{"current_steps": 185, "total_steps": 4130, "loss": 0.4097, "lr": 1.782082324455206e-05, "epoch": 0.3135593220338983, "percentage": 4.48, "elapsed_time": "0:49:27", "remaining_time": "17:34:48"}
{"current_steps": 190, "total_steps": 4130, "loss": 0.4365, "lr": 1.8305084745762713e-05, "epoch": 0.3220338983050847, "percentage": 4.6, "elapsed_time": "0:50:50", "remaining_time": "17:34:08"}
{"current_steps": 195, "total_steps": 4130, "loss": 0.3837, "lr": 1.8789346246973366e-05, "epoch": 0.3305084745762712, "percentage": 4.72, "elapsed_time": "0:52:10", "remaining_time": "17:32:50"}
{"current_steps": 200, "total_steps": 4130, "loss": 0.4048, "lr": 1.927360774818402e-05, "epoch": 0.3389830508474576, "percentage": 4.84, "elapsed_time": "0:53:31", "remaining_time": "17:31:55"}
{"current_steps": 205, "total_steps": 4130, "loss": 0.4291, "lr": 1.9757869249394673e-05, "epoch": 0.3474576271186441, "percentage": 4.96, "elapsed_time": "0:54:54", "remaining_time": "17:31:14"}
{"current_steps": 210, "total_steps": 4130, "loss": 0.3686, "lr": 2.0242130750605327e-05, "epoch": 0.3559322033898305, "percentage": 5.08, "elapsed_time": "0:56:15", "remaining_time": "17:30:12"}
{"current_steps": 215, "total_steps": 4130, "loss": 0.3826, "lr": 2.072639225181598e-05, "epoch": 0.3644067796610169, "percentage": 5.21, "elapsed_time": "0:57:29", "remaining_time": "17:26:54"}
{"current_steps": 220, "total_steps": 4130, "loss": 0.3656, "lr": 2.1210653753026637e-05, "epoch": 0.3728813559322034, "percentage": 5.33, "elapsed_time": "0:58:47", "remaining_time": "17:24:59"}
{"current_steps": 225, "total_steps": 4130, "loss": 0.3937, "lr": 2.169491525423729e-05, "epoch": 0.3813559322033898, "percentage": 5.45, "elapsed_time": "1:00:02", "remaining_time": "17:22:03"}
{"current_steps": 230, "total_steps": 4130, "loss": 0.3614, "lr": 2.2179176755447944e-05, "epoch": 0.3898305084745763, "percentage": 5.57, "elapsed_time": "1:01:20", "remaining_time": "17:20:11"}
{"current_steps": 235, "total_steps": 4130, "loss": 0.4322, "lr": 2.2663438256658597e-05, "epoch": 0.3983050847457627, "percentage": 5.69, "elapsed_time": "1:02:41", "remaining_time": "17:19:11"}
{"current_steps": 240, "total_steps": 4130, "loss": 0.3513, "lr": 2.3147699757869254e-05, "epoch": 0.4067796610169492, "percentage": 5.81, "elapsed_time": "1:04:02", "remaining_time": "17:17:54"}
{"current_steps": 245, "total_steps": 4130, "loss": 0.3925, "lr": 2.3631961259079904e-05, "epoch": 0.4152542372881356, "percentage": 5.93, "elapsed_time": "1:05:22", "remaining_time": "17:16:37"}
{"current_steps": 250, "total_steps": 4130, "loss": 0.3952, "lr": 2.4116222760290558e-05, "epoch": 0.423728813559322, "percentage": 6.05, "elapsed_time": "1:06:44", "remaining_time": "17:15:42"}
{"current_steps": 255, "total_steps": 4130, "loss": 0.3749, "lr": 2.460048426150121e-05, "epoch": 0.4322033898305085, "percentage": 6.17, "elapsed_time": "1:08:05", "remaining_time": "17:14:39"}
{"current_steps": 260, "total_steps": 4130, "loss": 0.3864, "lr": 2.5084745762711865e-05, "epoch": 0.4406779661016949, "percentage": 6.3, "elapsed_time": "1:09:21", "remaining_time": "17:12:27"}
{"current_steps": 265, "total_steps": 4130, "loss": 0.3826, "lr": 2.556900726392252e-05, "epoch": 0.4491525423728814, "percentage": 6.42, "elapsed_time": "1:10:39", "remaining_time": "17:10:25"}
{"current_steps": 270, "total_steps": 4130, "loss": 0.3712, "lr": 2.6053268765133175e-05, "epoch": 0.4576271186440678, "percentage": 6.54, "elapsed_time": "1:11:57", "remaining_time": "17:08:48"}
{"current_steps": 275, "total_steps": 4130, "loss": 0.4284, "lr": 2.653753026634383e-05, "epoch": 0.4661016949152542, "percentage": 6.66, "elapsed_time": "1:13:20", "remaining_time": "17:08:00"}
{"current_steps": 280, "total_steps": 4130, "loss": 0.4028, "lr": 2.702179176755448e-05, "epoch": 0.4745762711864407, "percentage": 6.78, "elapsed_time": "1:14:39", "remaining_time": "17:06:38"}
{"current_steps": 285, "total_steps": 4130, "loss": 0.3862, "lr": 2.7506053268765135e-05, "epoch": 0.4830508474576271, "percentage": 6.9, "elapsed_time": "1:16:00", "remaining_time": "17:05:32"}
{"current_steps": 290, "total_steps": 4130, "loss": 0.3911, "lr": 2.799031476997579e-05, "epoch": 0.4915254237288136, "percentage": 7.02, "elapsed_time": "1:17:20", "remaining_time": "17:04:12"}
{"current_steps": 295, "total_steps": 4130, "loss": 0.3677, "lr": 2.8474576271186442e-05, "epoch": 0.5, "percentage": 7.14, "elapsed_time": "1:18:39", "remaining_time": "17:02:38"}
{"current_steps": 300, "total_steps": 4130, "loss": 0.3671, "lr": 2.8958837772397096e-05, "epoch": 0.5084745762711864, "percentage": 7.26, "elapsed_time": "1:19:58", "remaining_time": "17:01:04"}
{"current_steps": 305, "total_steps": 4130, "loss": 0.3601, "lr": 2.9443099273607753e-05, "epoch": 0.5169491525423728, "percentage": 7.38, "elapsed_time": "1:21:17", "remaining_time": "16:59:33"}
{"current_steps": 310, "total_steps": 4130, "loss": 0.3657, "lr": 2.9927360774818406e-05, "epoch": 0.5254237288135594, "percentage": 7.51, "elapsed_time": "1:22:36", "remaining_time": "16:57:51"}
{"current_steps": 315, "total_steps": 4130, "loss": 0.3619, "lr": 3.041162227602906e-05, "epoch": 0.5338983050847458, "percentage": 7.63, "elapsed_time": "1:23:55", "remaining_time": "16:56:28"}
{"current_steps": 320, "total_steps": 4130, "loss": 0.3822, "lr": 3.089588377723971e-05, "epoch": 0.5423728813559322, "percentage": 7.75, "elapsed_time": "1:25:15", "remaining_time": "16:55:04"}
{"current_steps": 325, "total_steps": 4130, "loss": 0.3587, "lr": 3.138014527845036e-05, "epoch": 0.5508474576271186, "percentage": 7.87, "elapsed_time": "1:26:36", "remaining_time": "16:54:00"}
{"current_steps": 330, "total_steps": 4130, "loss": 0.357, "lr": 3.186440677966102e-05, "epoch": 0.559322033898305, "percentage": 7.99, "elapsed_time": "1:27:52", "remaining_time": "16:51:49"}
{"current_steps": 335, "total_steps": 4130, "loss": 0.3714, "lr": 3.234866828087168e-05, "epoch": 0.5677966101694916, "percentage": 8.11, "elapsed_time": "1:29:13", "remaining_time": "16:50:41"}
{"current_steps": 340, "total_steps": 4130, "loss": 0.3821, "lr": 3.283292978208233e-05, "epoch": 0.576271186440678, "percentage": 8.23, "elapsed_time": "1:30:33", "remaining_time": "16:49:27"}
{"current_steps": 345, "total_steps": 4130, "loss": 0.388, "lr": 3.3317191283292984e-05, "epoch": 0.5847457627118644, "percentage": 8.35, "elapsed_time": "1:31:50", "remaining_time": "16:47:37"}
{"current_steps": 350, "total_steps": 4130, "loss": 0.3823, "lr": 3.3801452784503634e-05, "epoch": 0.5932203389830508, "percentage": 8.47, "elapsed_time": "1:33:08", "remaining_time": "16:45:55"}
{"current_steps": 355, "total_steps": 4130, "loss": 0.3749, "lr": 3.4285714285714284e-05, "epoch": 0.6016949152542372, "percentage": 8.6, "elapsed_time": "1:34:29", "remaining_time": "16:44:44"}
{"current_steps": 360, "total_steps": 4130, "loss": 0.3682, "lr": 3.476997578692494e-05, "epoch": 0.6101694915254238, "percentage": 8.72, "elapsed_time": "1:35:50", "remaining_time": "16:43:42"}
{"current_steps": 365, "total_steps": 4130, "loss": 0.3903, "lr": 3.52542372881356e-05, "epoch": 0.6186440677966102, "percentage": 8.84, "elapsed_time": "1:37:11", "remaining_time": "16:42:37"}
{"current_steps": 370, "total_steps": 4130, "loss": 0.3743, "lr": 3.573849878934625e-05, "epoch": 0.6271186440677966, "percentage": 8.96, "elapsed_time": "1:38:32", "remaining_time": "16:41:26"}
{"current_steps": 375, "total_steps": 4130, "loss": 0.3868, "lr": 3.6222760290556904e-05, "epoch": 0.635593220338983, "percentage": 9.08, "elapsed_time": "1:39:51", "remaining_time": "16:39:53"}
{"current_steps": 380, "total_steps": 4130, "loss": 0.3817, "lr": 3.670702179176756e-05, "epoch": 0.6440677966101694, "percentage": 9.2, "elapsed_time": "1:41:10", "remaining_time": "16:38:28"}
{"current_steps": 385, "total_steps": 4130, "loss": 0.4001, "lr": 3.719128329297821e-05, "epoch": 0.652542372881356, "percentage": 9.32, "elapsed_time": "1:42:30", "remaining_time": "16:37:11"}
{"current_steps": 390, "total_steps": 4130, "loss": 0.3746, "lr": 3.767554479418886e-05, "epoch": 0.6610169491525424, "percentage": 9.44, "elapsed_time": "1:43:48", "remaining_time": "16:35:29"}
{"current_steps": 395, "total_steps": 4130, "loss": 0.3509, "lr": 3.815980629539952e-05, "epoch": 0.6694915254237288, "percentage": 9.56, "elapsed_time": "1:45:06", "remaining_time": "16:33:52"}
{"current_steps": 400, "total_steps": 4130, "loss": 0.3717, "lr": 3.8644067796610175e-05, "epoch": 0.6779661016949152, "percentage": 9.69, "elapsed_time": "1:46:27", "remaining_time": "16:32:46"}
{"current_steps": 405, "total_steps": 4130, "loss": 0.3594, "lr": 3.9128329297820825e-05, "epoch": 0.6864406779661016, "percentage": 9.81, "elapsed_time": "1:47:40", "remaining_time": "16:30:19"}
{"current_steps": 410, "total_steps": 4130, "loss": 0.3868, "lr": 3.961259079903148e-05, "epoch": 0.6949152542372882, "percentage": 9.93, "elapsed_time": "1:48:57", "remaining_time": "16:28:38"}
{"current_steps": 415, "total_steps": 4130, "loss": 0.351, "lr": 3.9999992856441635e-05, "epoch": 0.7033898305084746, "percentage": 10.05, "elapsed_time": "1:50:17", "remaining_time": "16:27:14"}
{"current_steps": 420, "total_steps": 4130, "loss": 0.366, "lr": 3.999974283243472e-05, "epoch": 0.711864406779661, "percentage": 10.17, "elapsed_time": "1:51:38", "remaining_time": "16:26:06"}
{"current_steps": 425, "total_steps": 4130, "loss": 0.4029, "lr": 3.9999135635612606e-05, "epoch": 0.7203389830508474, "percentage": 10.29, "elapsed_time": "1:52:59", "remaining_time": "16:25:00"}
{"current_steps": 430, "total_steps": 4130, "loss": 0.3795, "lr": 3.999817127681917e-05, "epoch": 0.7288135593220338, "percentage": 10.41, "elapsed_time": "1:54:19", "remaining_time": "16:23:44"}
{"current_steps": 435, "total_steps": 4130, "loss": 0.3473, "lr": 3.9996849773276764e-05, "epoch": 0.7372881355932204, "percentage": 10.53, "elapsed_time": "1:55:36", "remaining_time": "16:21:59"}
{"current_steps": 440, "total_steps": 4130, "loss": 0.3192, "lr": 3.9995171148585944e-05, "epoch": 0.7457627118644068, "percentage": 10.65, "elapsed_time": "1:56:53", "remaining_time": "16:20:17"}
{"current_steps": 445, "total_steps": 4130, "loss": 0.3584, "lr": 3.999313543272505e-05, "epoch": 0.7542372881355932, "percentage": 10.77, "elapsed_time": "1:58:10", "remaining_time": "16:18:37"}
{"current_steps": 450, "total_steps": 4130, "loss": 0.3279, "lr": 3.999074266204967e-05, "epoch": 0.7627118644067796, "percentage": 10.9, "elapsed_time": "1:59:26", "remaining_time": "16:16:48"}
{"current_steps": 455, "total_steps": 4130, "loss": 0.3391, "lr": 3.998799287929199e-05, "epoch": 0.7711864406779662, "percentage": 11.02, "elapsed_time": "2:00:47", "remaining_time": "16:15:34"}
{"current_steps": 460, "total_steps": 4130, "loss": 0.3482, "lr": 3.998488613356002e-05, "epoch": 0.7796610169491526, "percentage": 11.14, "elapsed_time": "2:02:05", "remaining_time": "16:14:07"}
{"current_steps": 465, "total_steps": 4130, "loss": 0.3809, "lr": 3.998142248033673e-05, "epoch": 0.788135593220339, "percentage": 11.26, "elapsed_time": "2:03:26", "remaining_time": "16:12:55"}
{"current_steps": 470, "total_steps": 4130, "loss": 0.3509, "lr": 3.997760198147904e-05, "epoch": 0.7966101694915254, "percentage": 11.38, "elapsed_time": "2:04:43", "remaining_time": "16:11:13"}
{"current_steps": 475, "total_steps": 4130, "loss": 0.3805, "lr": 3.9973424705216774e-05, "epoch": 0.8050847457627118, "percentage": 11.5, "elapsed_time": "2:05:59", "remaining_time": "16:09:28"}
{"current_steps": 480, "total_steps": 4130, "loss": 0.3276, "lr": 3.996889072615134e-05, "epoch": 0.8135593220338984, "percentage": 11.62, "elapsed_time": "2:07:19", "remaining_time": "16:08:14"}
{"current_steps": 485, "total_steps": 4130, "loss": 0.3765, "lr": 3.99640001252545e-05, "epoch": 0.8220338983050848, "percentage": 11.74, "elapsed_time": "2:08:40", "remaining_time": "16:07:02"}
{"current_steps": 490, "total_steps": 4130, "loss": 0.3689, "lr": 3.9958752989866856e-05, "epoch": 0.8305084745762712, "percentage": 11.86, "elapsed_time": "2:09:58", "remaining_time": "16:05:35"}
{"current_steps": 495, "total_steps": 4130, "loss": 0.3401, "lr": 3.995314941369631e-05, "epoch": 0.8389830508474576, "percentage": 11.99, "elapsed_time": "2:11:09", "remaining_time": "16:03:09"}
{"current_steps": 500, "total_steps": 4130, "loss": 0.3257, "lr": 3.994718949681642e-05, "epoch": 0.847457627118644, "percentage": 12.11, "elapsed_time": "2:12:26", "remaining_time": "16:01:27"}
{"current_steps": 505, "total_steps": 4130, "loss": 0.3487, "lr": 3.994087334566455e-05, "epoch": 0.8559322033898306, "percentage": 12.23, "elapsed_time": "2:13:43", "remaining_time": "15:59:52"}
{"current_steps": 510, "total_steps": 4130, "loss": 0.3608, "lr": 3.9934201073040035e-05, "epoch": 0.864406779661017, "percentage": 12.35, "elapsed_time": "2:15:02", "remaining_time": "15:58:33"}
{"current_steps": 515, "total_steps": 4130, "loss": 0.3558, "lr": 3.992717279810213e-05, "epoch": 0.8728813559322034, "percentage": 12.47, "elapsed_time": "2:16:21", "remaining_time": "15:57:11"}
{"current_steps": 520, "total_steps": 4130, "loss": 0.344, "lr": 3.991978864636788e-05, "epoch": 0.8813559322033898, "percentage": 12.59, "elapsed_time": "2:17:39", "remaining_time": "15:55:42"}
{"current_steps": 525, "total_steps": 4130, "loss": 0.3512, "lr": 3.9912048749709896e-05, "epoch": 0.8898305084745762, "percentage": 12.71, "elapsed_time": "2:18:58", "remaining_time": "15:54:17"}
{"current_steps": 530, "total_steps": 4130, "loss": 0.3311, "lr": 3.990395324635399e-05, "epoch": 0.8983050847457628, "percentage": 12.83, "elapsed_time": "2:20:18", "remaining_time": "15:53:03"}
{"current_steps": 535, "total_steps": 4130, "loss": 0.3513, "lr": 3.989550228087671e-05, "epoch": 0.9067796610169492, "percentage": 12.95, "elapsed_time": "2:21:38", "remaining_time": "15:51:43"}
{"current_steps": 540, "total_steps": 4130, "loss": 0.3215, "lr": 3.988669600420275e-05, "epoch": 0.9152542372881356, "percentage": 13.08, "elapsed_time": "2:22:57", "remaining_time": "15:50:24"}
{"current_steps": 545, "total_steps": 4130, "loss": 0.3634, "lr": 3.9877534573602254e-05, "epoch": 0.923728813559322, "percentage": 13.2, "elapsed_time": "2:24:14", "remaining_time": "15:48:49"}
{"current_steps": 550, "total_steps": 4130, "loss": 0.3573, "lr": 3.9868018152688044e-05, "epoch": 0.9322033898305084, "percentage": 13.32, "elapsed_time": "2:25:34", "remaining_time": "15:47:31"}
{"current_steps": 555, "total_steps": 4130, "loss": 0.3615, "lr": 3.985814691141263e-05, "epoch": 0.940677966101695, "percentage": 13.44, "elapsed_time": "2:26:51", "remaining_time": "15:45:57"}
{"current_steps": 560, "total_steps": 4130, "loss": 0.3839, "lr": 3.984792102606524e-05, "epoch": 0.9491525423728814, "percentage": 13.56, "elapsed_time": "2:28:06", "remaining_time": "15:44:12"}
{"current_steps": 565, "total_steps": 4130, "loss": 0.3165, "lr": 3.9837340679268634e-05, "epoch": 0.9576271186440678, "percentage": 13.68, "elapsed_time": "2:29:26", "remaining_time": "15:42:58"}
{"current_steps": 570, "total_steps": 4130, "loss": 0.3308, "lr": 3.982640605997585e-05, "epoch": 0.9661016949152542, "percentage": 13.8, "elapsed_time": "2:30:47", "remaining_time": "15:41:48"}
{"current_steps": 575, "total_steps": 4130, "loss": 0.353, "lr": 3.981511736346684e-05, "epoch": 0.9745762711864406, "percentage": 13.92, "elapsed_time": "2:32:02", "remaining_time": "15:40:03"}
{"current_steps": 580, "total_steps": 4130, "loss": 0.3341, "lr": 3.980347479134498e-05, "epoch": 0.9830508474576272, "percentage": 14.04, "elapsed_time": "2:33:23", "remaining_time": "15:38:52"}
{"current_steps": 585, "total_steps": 4130, "loss": 0.3257, "lr": 3.9791478551533435e-05, "epoch": 0.9915254237288136, "percentage": 14.16, "elapsed_time": "2:34:40", "remaining_time": "15:37:20"}
{"current_steps": 590, "total_steps": 4130, "loss": 0.3438, "lr": 3.977912885827151e-05, "epoch": 1.0, "percentage": 14.29, "elapsed_time": "2:35:56", "remaining_time": "15:35:39"}
{"current_steps": 595, "total_steps": 4130, "loss": 0.3632, "lr": 3.976642593211079e-05, "epoch": 1.0084745762711864, "percentage": 14.41, "elapsed_time": "2:37:16", "remaining_time": "15:34:23"}
{"current_steps": 600, "total_steps": 4130, "loss": 0.3324, "lr": 3.9753369999911166e-05, "epoch": 1.0169491525423728, "percentage": 14.53, "elapsed_time": "2:38:34", "remaining_time": "15:32:59"}
{"current_steps": 605, "total_steps": 4130, "loss": 0.3188, "lr": 3.973996129483684e-05, "epoch": 1.0254237288135593, "percentage": 14.65, "elapsed_time": "2:39:54", "remaining_time": "15:31:42"}
{"current_steps": 610, "total_steps": 4130, "loss": 0.2951, "lr": 3.972620005635216e-05, "epoch": 1.0338983050847457, "percentage": 14.77, "elapsed_time": "2:41:06", "remaining_time": "15:29:38"}
{"current_steps": 615, "total_steps": 4130, "loss": 0.3193, "lr": 3.971208653021727e-05, "epoch": 1.042372881355932, "percentage": 14.89, "elapsed_time": "2:42:25", "remaining_time": "15:28:19"}
{"current_steps": 620, "total_steps": 4130, "loss": 0.3693, "lr": 3.969762096848383e-05, "epoch": 1.0508474576271187, "percentage": 15.01, "elapsed_time": "2:43:46", "remaining_time": "15:27:09"}
{"current_steps": 625, "total_steps": 4130, "loss": 0.3308, "lr": 3.968280362949042e-05, "epoch": 1.0593220338983051, "percentage": 15.13, "elapsed_time": "2:44:59", "remaining_time": "15:25:17"}
{"current_steps": 630, "total_steps": 4130, "loss": 0.3605, "lr": 3.9667634777857975e-05, "epoch": 1.0677966101694916, "percentage": 15.25, "elapsed_time": "2:46:19", "remaining_time": "15:24:00"}
{"current_steps": 635, "total_steps": 4130, "loss": 0.3408, "lr": 3.965211468448505e-05, "epoch": 1.076271186440678, "percentage": 15.38, "elapsed_time": "2:47:37", "remaining_time": "15:22:34"}
{"current_steps": 640, "total_steps": 4130, "loss": 0.3339, "lr": 3.963624362654299e-05, "epoch": 1.0847457627118644, "percentage": 15.5, "elapsed_time": "2:48:57", "remaining_time": "15:21:21"}
{"current_steps": 645, "total_steps": 4130, "loss": 0.3253, "lr": 3.962002188747096e-05, "epoch": 1.0932203389830508, "percentage": 15.62, "elapsed_time": "2:50:12", "remaining_time": "15:19:40"}
{"current_steps": 650, "total_steps": 4130, "loss": 0.3232, "lr": 3.9603449756970877e-05, "epoch": 1.1016949152542372, "percentage": 15.74, "elapsed_time": "2:51:33", "remaining_time": "15:18:30"}
{"current_steps": 655, "total_steps": 4130, "loss": 0.3291, "lr": 3.95865275310023e-05, "epoch": 1.1101694915254237, "percentage": 15.86, "elapsed_time": "2:52:51", "remaining_time": "15:17:05"}
{"current_steps": 660, "total_steps": 4130, "loss": 0.3269, "lr": 3.9569255511777054e-05, "epoch": 1.11864406779661, "percentage": 15.98, "elapsed_time": "2:54:10", "remaining_time": "15:15:41"}
{"current_steps": 665, "total_steps": 4130, "loss": 0.3623, "lr": 3.955163400775389e-05, "epoch": 1.1271186440677967, "percentage": 16.1, "elapsed_time": "2:55:28", "remaining_time": "15:14:19"}
{"current_steps": 670, "total_steps": 4130, "loss": 0.324, "lr": 3.953366333363297e-05, "epoch": 1.1355932203389831, "percentage": 16.22, "elapsed_time": "2:56:42", "remaining_time": "15:12:35"}
{"current_steps": 675, "total_steps": 4130, "loss": 0.3109, "lr": 3.9515343810350236e-05, "epoch": 1.1440677966101696, "percentage": 16.34, "elapsed_time": "2:57:58", "remaining_time": "15:11:00"}
{"current_steps": 680, "total_steps": 4130, "loss": 0.3356, "lr": 3.949667576507168e-05, "epoch": 1.152542372881356, "percentage": 16.46, "elapsed_time": "2:59:13", "remaining_time": "15:09:20"}
{"current_steps": 685, "total_steps": 4130, "loss": 0.3321, "lr": 3.9477659531187484e-05, "epoch": 1.1610169491525424, "percentage": 16.59, "elapsed_time": "3:00:31", "remaining_time": "15:07:52"}
{"current_steps": 690, "total_steps": 4130, "loss": 0.329, "lr": 3.9458295448306134e-05, "epoch": 1.1694915254237288, "percentage": 16.71, "elapsed_time": "3:01:46", "remaining_time": "15:06:14"}
{"current_steps": 695, "total_steps": 4130, "loss": 0.3561, "lr": 3.943858386224825e-05, "epoch": 1.1779661016949152, "percentage": 16.83, "elapsed_time": "3:03:05", "remaining_time": "15:04:56"}
{"current_steps": 700, "total_steps": 4130, "loss": 0.3091, "lr": 3.941852512504052e-05, "epoch": 1.1864406779661016, "percentage": 16.95, "elapsed_time": "3:04:22", "remaining_time": "15:03:24"}
{"current_steps": 705, "total_steps": 4130, "loss": 0.3206, "lr": 3.939811959490931e-05, "epoch": 1.194915254237288, "percentage": 17.07, "elapsed_time": "3:05:38", "remaining_time": "15:01:50"}
{"current_steps": 710, "total_steps": 4130, "loss": 0.3178, "lr": 3.937736763627435e-05, "epoch": 1.2033898305084745, "percentage": 17.19, "elapsed_time": "3:06:55", "remaining_time": "15:00:23"}
{"current_steps": 715, "total_steps": 4130, "loss": 0.3624, "lr": 3.935626961974217e-05, "epoch": 1.211864406779661, "percentage": 17.31, "elapsed_time": "3:08:15", "remaining_time": "14:59:10"}
{"current_steps": 720, "total_steps": 4130, "loss": 0.3332, "lr": 3.933482592209951e-05, "epoch": 1.2203389830508475, "percentage": 17.43, "elapsed_time": "3:09:31", "remaining_time": "14:57:36"}
{"current_steps": 725, "total_steps": 4130, "loss": 0.3116, "lr": 3.931303692630661e-05, "epoch": 1.228813559322034, "percentage": 17.55, "elapsed_time": "3:10:51", "remaining_time": "14:56:23"}
{"current_steps": 730, "total_steps": 4130, "loss": 0.3284, "lr": 3.92909030214903e-05, "epoch": 1.2372881355932204, "percentage": 17.68, "elapsed_time": "3:12:10", "remaining_time": "14:55:04"}
{"current_steps": 735, "total_steps": 4130, "loss": 0.3215, "lr": 3.9268424602937124e-05, "epoch": 1.2457627118644068, "percentage": 17.8, "elapsed_time": "3:13:29", "remaining_time": "14:53:43"}
{"current_steps": 740, "total_steps": 4130, "loss": 0.3755, "lr": 3.9245602072086246e-05, "epoch": 1.2542372881355932, "percentage": 17.92, "elapsed_time": "3:14:44", "remaining_time": "14:52:05"}
{"current_steps": 745, "total_steps": 4130, "loss": 0.3391, "lr": 3.9222435836522286e-05, "epoch": 1.2627118644067796, "percentage": 18.04, "elapsed_time": "3:16:04", "remaining_time": "14:50:53"}
{"current_steps": 750, "total_steps": 4130, "loss": 0.3372, "lr": 3.919892630996804e-05, "epoch": 1.271186440677966, "percentage": 18.16, "elapsed_time": "3:17:20", "remaining_time": "14:49:22"}
{"current_steps": 755, "total_steps": 4130, "loss": 0.307, "lr": 3.9175073912277107e-05, "epoch": 1.2796610169491525, "percentage": 18.28, "elapsed_time": "3:18:39", "remaining_time": "14:48:01"}
{"current_steps": 760, "total_steps": 4130, "loss": 0.3215, "lr": 3.915087906942635e-05, "epoch": 1.288135593220339, "percentage": 18.4, "elapsed_time": "3:19:52", "remaining_time": "14:46:19"}
{"current_steps": 765, "total_steps": 4130, "loss": 0.3504, "lr": 3.912634221350834e-05, "epoch": 1.2966101694915255, "percentage": 18.52, "elapsed_time": "3:21:10", "remaining_time": "14:44:56"}
{"current_steps": 770, "total_steps": 4130, "loss": 0.3183, "lr": 3.910146378272361e-05, "epoch": 1.305084745762712, "percentage": 18.64, "elapsed_time": "3:22:27", "remaining_time": "14:43:27"}
{"current_steps": 775, "total_steps": 4130, "loss": 0.323, "lr": 3.9076244221372824e-05, "epoch": 1.3135593220338984, "percentage": 18.77, "elapsed_time": "3:23:44", "remaining_time": "14:41:58"}
{"current_steps": 780, "total_steps": 4130, "loss": 0.3181, "lr": 3.905068397984886e-05, "epoch": 1.3220338983050848, "percentage": 18.89, "elapsed_time": "3:25:03", "remaining_time": "14:40:43"}
{"current_steps": 785, "total_steps": 4130, "loss": 0.3586, "lr": 3.9024783514628765e-05, "epoch": 1.3305084745762712, "percentage": 19.01, "elapsed_time": "3:26:22", "remaining_time": "14:39:25"}
{"current_steps": 790, "total_steps": 4130, "loss": 0.3441, "lr": 3.899854328826559e-05, "epoch": 1.3389830508474576, "percentage": 19.13, "elapsed_time": "3:27:38", "remaining_time": "14:37:51"}
{"current_steps": 795, "total_steps": 4130, "loss": 0.3201, "lr": 3.897196376938013e-05, "epoch": 1.347457627118644, "percentage": 19.25, "elapsed_time": "3:28:55", "remaining_time": "14:36:24"}
{"current_steps": 800, "total_steps": 4130, "loss": 0.3419, "lr": 3.8945045432652575e-05, "epoch": 1.3559322033898304, "percentage": 19.37, "elapsed_time": "3:30:09", "remaining_time": "14:34:46"}
{"current_steps": 805, "total_steps": 4130, "loss": 0.3191, "lr": 3.8917788758814e-05, "epoch": 1.3644067796610169, "percentage": 19.49, "elapsed_time": "3:31:27", "remaining_time": "14:33:23"}
{"current_steps": 810, "total_steps": 4130, "loss": 0.3171, "lr": 3.889019423463783e-05, "epoch": 1.3728813559322033, "percentage": 19.61, "elapsed_time": "3:32:46", "remaining_time": "14:32:05"}
{"current_steps": 815, "total_steps": 4130, "loss": 0.3312, "lr": 3.8862262352931075e-05, "epoch": 1.3813559322033897, "percentage": 19.73, "elapsed_time": "3:34:03", "remaining_time": "14:30:42"}
{"current_steps": 820, "total_steps": 4130, "loss": 0.3178, "lr": 3.88339936125256e-05, "epoch": 1.3898305084745763, "percentage": 19.85, "elapsed_time": "3:35:24", "remaining_time": "14:29:31"}
{"current_steps": 825, "total_steps": 4130, "loss": 0.2978, "lr": 3.8805388518269184e-05, "epoch": 1.3983050847457628, "percentage": 19.98, "elapsed_time": "3:36:42", "remaining_time": "14:28:09"}
{"current_steps": 830, "total_steps": 4130, "loss": 0.3173, "lr": 3.877644758101648e-05, "epoch": 1.4067796610169492, "percentage": 20.1, "elapsed_time": "3:38:03", "remaining_time": "14:26:57"}
{"current_steps": 835, "total_steps": 4130, "loss": 0.3159, "lr": 3.8747171317619955e-05, "epoch": 1.4152542372881356, "percentage": 20.22, "elapsed_time": "3:39:14", "remaining_time": "14:25:10"}
{"current_steps": 840, "total_steps": 4130, "loss": 0.3505, "lr": 3.871756025092059e-05, "epoch": 1.423728813559322, "percentage": 20.34, "elapsed_time": "3:40:34", "remaining_time": "14:23:53"}
{"current_steps": 845, "total_steps": 4130, "loss": 0.3087, "lr": 3.868761490973859e-05, "epoch": 1.4322033898305084, "percentage": 20.46, "elapsed_time": "3:41:53", "remaining_time": "14:22:37"}
{"current_steps": 850, "total_steps": 4130, "loss": 0.3337, "lr": 3.8657335828863924e-05, "epoch": 1.4406779661016949, "percentage": 20.58, "elapsed_time": "3:43:13", "remaining_time": "14:21:24"}
{"current_steps": 855, "total_steps": 4130, "loss": 0.3289, "lr": 3.8626723549046774e-05, "epoch": 1.4491525423728815, "percentage": 20.7, "elapsed_time": "3:44:30", "remaining_time": "14:19:56"}
{"current_steps": 860, "total_steps": 4130, "loss": 0.2938, "lr": 3.859577861698787e-05, "epoch": 1.457627118644068, "percentage": 20.82, "elapsed_time": "3:45:38", "remaining_time": "14:17:59"}
{"current_steps": 865, "total_steps": 4130, "loss": 0.3247, "lr": 3.856450158532875e-05, "epoch": 1.4661016949152543, "percentage": 20.94, "elapsed_time": "3:46:57", "remaining_time": "14:16:40"}
{"current_steps": 870, "total_steps": 4130, "loss": 0.3374, "lr": 3.853289301264187e-05, "epoch": 1.4745762711864407, "percentage": 21.07, "elapsed_time": "3:48:12", "remaining_time": "14:15:06"}
{"current_steps": 875, "total_steps": 4130, "loss": 0.3295, "lr": 3.850095346342064e-05, "epoch": 1.4830508474576272, "percentage": 21.19, "elapsed_time": "3:49:29", "remaining_time": "14:13:42"}
{"current_steps": 880, "total_steps": 4130, "loss": 0.3117, "lr": 3.84686835080693e-05, "epoch": 1.4915254237288136, "percentage": 21.31, "elapsed_time": "3:50:45", "remaining_time": "14:12:15"}
{"current_steps": 885, "total_steps": 4130, "loss": 0.329, "lr": 3.843608372289283e-05, "epoch": 1.5, "percentage": 21.43, "elapsed_time": "3:52:04", "remaining_time": "14:10:56"}
{"current_steps": 890, "total_steps": 4130, "loss": 0.3383, "lr": 3.8403154690086564e-05, "epoch": 1.5084745762711864, "percentage": 21.55, "elapsed_time": "3:53:22", "remaining_time": "14:09:33"}
{"current_steps": 895, "total_steps": 4130, "loss": 0.3245, "lr": 3.836989699772582e-05, "epoch": 1.5169491525423728, "percentage": 21.67, "elapsed_time": "3:54:38", "remaining_time": "14:08:08"}
{"current_steps": 900, "total_steps": 4130, "loss": 0.3638, "lr": 3.8336311239755424e-05, "epoch": 1.5254237288135593, "percentage": 21.79, "elapsed_time": "3:55:59", "remaining_time": "14:06:55"}
{"current_steps": 905, "total_steps": 4130, "loss": 0.3142, "lr": 3.830239801597907e-05, "epoch": 1.5338983050847457, "percentage": 21.91, "elapsed_time": "3:57:15", "remaining_time": "14:05:28"}
{"current_steps": 910, "total_steps": 4130, "loss": 0.3029, "lr": 3.826815793204863e-05, "epoch": 1.542372881355932, "percentage": 22.03, "elapsed_time": "3:58:34", "remaining_time": "14:04:11"}
{"current_steps": 915, "total_steps": 4130, "loss": 0.3208, "lr": 3.823359159945332e-05, "epoch": 1.5508474576271185, "percentage": 22.15, "elapsed_time": "3:59:53", "remaining_time": "14:02:53"}
{"current_steps": 920, "total_steps": 4130, "loss": 0.2998, "lr": 3.8198699635508805e-05, "epoch": 1.559322033898305, "percentage": 22.28, "elapsed_time": "4:01:10", "remaining_time": "14:01:29"}
{"current_steps": 925, "total_steps": 4130, "loss": 0.3202, "lr": 3.816348266334614e-05, "epoch": 1.5677966101694916, "percentage": 22.4, "elapsed_time": "4:02:30", "remaining_time": "14:00:15"}
{"current_steps": 930, "total_steps": 4130, "loss": 0.3326, "lr": 3.812794131190066e-05, "epoch": 1.576271186440678, "percentage": 22.52, "elapsed_time": "4:03:50", "remaining_time": "13:59:01"}
{"current_steps": 935, "total_steps": 4130, "loss": 0.3042, "lr": 3.8092076215900765e-05, "epoch": 1.5847457627118644, "percentage": 22.64, "elapsed_time": "4:05:06", "remaining_time": "13:57:32"}
{"current_steps": 940, "total_steps": 4130, "loss": 0.3207, "lr": 3.805588801585654e-05, "epoch": 1.5932203389830508, "percentage": 22.76, "elapsed_time": "4:06:26", "remaining_time": "13:56:19"}
{"current_steps": 945, "total_steps": 4130, "loss": 0.3457, "lr": 3.801937735804838e-05, "epoch": 1.6016949152542372, "percentage": 22.88, "elapsed_time": "4:07:46", "remaining_time": "13:55:05"}
{"current_steps": 950, "total_steps": 4130, "loss": 0.3241, "lr": 3.798254489451539e-05, "epoch": 1.6101694915254239, "percentage": 23.0, "elapsed_time": "4:09:05", "remaining_time": "13:53:49"}
{"current_steps": 955, "total_steps": 4130, "loss": 0.3342, "lr": 3.794539128304374e-05, "epoch": 1.6186440677966103, "percentage": 23.12, "elapsed_time": "4:10:24", "remaining_time": "13:52:31"}
{"current_steps": 960, "total_steps": 4130, "loss": 0.3383, "lr": 3.790791718715498e-05, "epoch": 1.6271186440677967, "percentage": 23.24, "elapsed_time": "4:11:45", "remaining_time": "13:51:19"}
{"current_steps": 965, "total_steps": 4130, "loss": 0.308, "lr": 3.7870123276094134e-05, "epoch": 1.6355932203389831, "percentage": 23.37, "elapsed_time": "4:13:03", "remaining_time": "13:49:58"}
{"current_steps": 970, "total_steps": 4130, "loss": 0.3088, "lr": 3.783201022481775e-05, "epoch": 1.6440677966101696, "percentage": 23.49, "elapsed_time": "4:14:16", "remaining_time": "13:48:20"}
{"current_steps": 975, "total_steps": 4130, "loss": 0.2726, "lr": 3.7793578713981876e-05, "epoch": 1.652542372881356, "percentage": 23.61, "elapsed_time": "4:15:28", "remaining_time": "13:46:43"}
{"current_steps": 980, "total_steps": 4130, "loss": 0.2978, "lr": 3.775482942992989e-05, "epoch": 1.6610169491525424, "percentage": 23.73, "elapsed_time": "4:16:39", "remaining_time": "13:44:59"}
{"current_steps": 985, "total_steps": 4130, "loss": 0.3333, "lr": 3.771576306468022e-05, "epoch": 1.6694915254237288, "percentage": 23.85, "elapsed_time": "4:17:58", "remaining_time": "13:43:41"}
{"current_steps": 990, "total_steps": 4130, "loss": 0.3329, "lr": 3.7676380315914025e-05, "epoch": 1.6779661016949152, "percentage": 23.97, "elapsed_time": "4:19:16", "remaining_time": "13:42:19"}
{"current_steps": 995, "total_steps": 4130, "loss": 0.3682, "lr": 3.7636681886962724e-05, "epoch": 1.6864406779661016, "percentage": 24.09, "elapsed_time": "4:20:36", "remaining_time": "13:41:07"}
{"current_steps": 1000, "total_steps": 4130, "loss": 0.3052, "lr": 3.759666848679539e-05, "epoch": 1.694915254237288, "percentage": 24.21, "elapsed_time": "4:21:53", "remaining_time": "13:39:44"}
{"current_steps": 1005, "total_steps": 4130, "loss": 0.331, "lr": 3.755634083000617e-05, "epoch": 1.7033898305084745, "percentage": 24.33, "elapsed_time": "4:23:13", "remaining_time": "13:38:29"}
{"current_steps": 1010, "total_steps": 4130, "loss": 0.2965, "lr": 3.751569963680146e-05, "epoch": 1.711864406779661, "percentage": 24.46, "elapsed_time": "4:24:31", "remaining_time": "13:37:09"}
{"current_steps": 1015, "total_steps": 4130, "loss": 0.3306, "lr": 3.747474563298705e-05, "epoch": 1.7203389830508473, "percentage": 24.58, "elapsed_time": "4:25:50", "remaining_time": "13:35:51"}
{"current_steps": 1020, "total_steps": 4130, "loss": 0.3287, "lr": 3.743347954995519e-05, "epoch": 1.7288135593220337, "percentage": 24.7, "elapsed_time": "4:27:07", "remaining_time": "13:34:28"}
{"current_steps": 1025, "total_steps": 4130, "loss": 0.3264, "lr": 3.7391902124671516e-05, "epoch": 1.7372881355932204, "percentage": 24.82, "elapsed_time": "4:28:27", "remaining_time": "13:33:14"}
{"current_steps": 1030, "total_steps": 4130, "loss": 0.3084, "lr": 3.7350014099661874e-05, "epoch": 1.7457627118644068, "percentage": 24.94, "elapsed_time": "4:29:46", "remaining_time": "13:31:56"}
{"current_steps": 1035, "total_steps": 4130, "loss": 0.3232, "lr": 3.730781622299907e-05, "epoch": 1.7542372881355932, "percentage": 25.06, "elapsed_time": "4:31:02", "remaining_time": "13:30:31"}
{"current_steps": 1040, "total_steps": 4130, "loss": 0.3472, "lr": 3.7265309248289516e-05, "epoch": 1.7627118644067796, "percentage": 25.18, "elapsed_time": "4:32:17", "remaining_time": "13:29:02"}
{"current_steps": 1045, "total_steps": 4130, "loss": 0.3486, "lr": 3.7222493934659765e-05, "epoch": 1.7711864406779663, "percentage": 25.3, "elapsed_time": "4:33:38", "remaining_time": "13:27:49"}
{"current_steps": 1050, "total_steps": 4130, "loss": 0.2993, "lr": 3.717937104674296e-05, "epoch": 1.7796610169491527, "percentage": 25.42, "elapsed_time": "4:34:55", "remaining_time": "13:26:27"}
{"current_steps": 1055, "total_steps": 4130, "loss": 0.3245, "lr": 3.713594135466515e-05, "epoch": 1.788135593220339, "percentage": 25.54, "elapsed_time": "4:36:11", "remaining_time": "13:25:01"}
{"current_steps": 1060, "total_steps": 4130, "loss": 0.3495, "lr": 3.7092205634031595e-05, "epoch": 1.7966101694915255, "percentage": 25.67, "elapsed_time": "4:37:26", "remaining_time": "13:23:31"}
{"current_steps": 1065, "total_steps": 4130, "loss": 0.3181, "lr": 3.704816466591286e-05, "epoch": 1.805084745762712, "percentage": 25.79, "elapsed_time": "4:38:43", "remaining_time": "13:22:07"}
{"current_steps": 1070, "total_steps": 4130, "loss": 0.3383, "lr": 3.700381923683087e-05, "epoch": 1.8135593220338984, "percentage": 25.91, "elapsed_time": "4:40:03", "remaining_time": "13:20:54"}
{"current_steps": 1075, "total_steps": 4130, "loss": 0.2844, "lr": 3.695917013874491e-05, "epoch": 1.8220338983050848, "percentage": 26.03, "elapsed_time": "4:41:23", "remaining_time": "13:19:39"}
{"current_steps": 1080, "total_steps": 4130, "loss": 0.3396, "lr": 3.691421816903744e-05, "epoch": 1.8305084745762712, "percentage": 26.15, "elapsed_time": "4:42:42", "remaining_time": "13:18:22"}
{"current_steps": 1085, "total_steps": 4130, "loss": 0.2903, "lr": 3.686896413049985e-05, "epoch": 1.8389830508474576, "percentage": 26.27, "elapsed_time": "4:44:01", "remaining_time": "13:17:07"}
{"current_steps": 1090, "total_steps": 4130, "loss": 0.3118, "lr": 3.6823408831318154e-05, "epoch": 1.847457627118644, "percentage": 26.39, "elapsed_time": "4:45:22", "remaining_time": "13:15:53"}
{"current_steps": 1095, "total_steps": 4130, "loss": 0.344, "lr": 3.677755308505854e-05, "epoch": 1.8559322033898304, "percentage": 26.51, "elapsed_time": "4:46:39", "remaining_time": "13:14:32"}
{"current_steps": 1100, "total_steps": 4130, "loss": 0.3249, "lr": 3.673139771065282e-05, "epoch": 1.8644067796610169, "percentage": 26.63, "elapsed_time": "4:47:57", "remaining_time": "13:13:12"}
{"current_steps": 1105, "total_steps": 4130, "loss": 0.3469, "lr": 3.6684943532383866e-05, "epoch": 1.8728813559322033, "percentage": 26.76, "elapsed_time": "4:49:16", "remaining_time": "13:11:55"}
{"current_steps": 1110, "total_steps": 4130, "loss": 0.3365, "lr": 3.663819137987081e-05, "epoch": 1.8813559322033897, "percentage": 26.88, "elapsed_time": "4:50:37", "remaining_time": "13:10:42"}
{"current_steps": 1115, "total_steps": 4130, "loss": 0.3122, "lr": 3.65911420880543e-05, "epoch": 1.8898305084745761, "percentage": 27.0, "elapsed_time": "4:51:55", "remaining_time": "13:09:22"}
{"current_steps": 1120, "total_steps": 4130, "loss": 0.3077, "lr": 3.654379649718153e-05, "epoch": 1.8983050847457628, "percentage": 27.12, "elapsed_time": "4:53:10", "remaining_time": "13:07:54"}
{"current_steps": 1125, "total_steps": 4130, "loss": 0.3467, "lr": 3.649615545279127e-05, "epoch": 1.9067796610169492, "percentage": 27.24, "elapsed_time": "4:54:30", "remaining_time": "13:06:40"}
{"current_steps": 1130, "total_steps": 4130, "loss": 0.3308, "lr": 3.644821980569876e-05, "epoch": 1.9152542372881356, "percentage": 27.36, "elapsed_time": "4:55:48", "remaining_time": "13:05:21"}
{"current_steps": 1135, "total_steps": 4130, "loss": 0.312, "lr": 3.639999041198051e-05, "epoch": 1.923728813559322, "percentage": 27.48, "elapsed_time": "4:57:03", "remaining_time": "13:03:52"}
{"current_steps": 1140, "total_steps": 4130, "loss": 0.3366, "lr": 3.635146813295902e-05, "epoch": 1.9322033898305084, "percentage": 27.6, "elapsed_time": "4:58:20", "remaining_time": "13:02:28"}
{"current_steps": 1145, "total_steps": 4130, "loss": 0.3165, "lr": 3.6302653835187366e-05, "epoch": 1.940677966101695, "percentage": 27.72, "elapsed_time": "4:59:34", "remaining_time": "13:00:59"}
{"current_steps": 1150, "total_steps": 4130, "loss": 0.2881, "lr": 3.625354839043377e-05, "epoch": 1.9491525423728815, "percentage": 27.85, "elapsed_time": "5:00:53", "remaining_time": "12:59:43"}
{"current_steps": 1155, "total_steps": 4130, "loss": 0.3325, "lr": 3.620415267566601e-05, "epoch": 1.957627118644068, "percentage": 27.97, "elapsed_time": "5:02:14", "remaining_time": "12:58:29"}
{"current_steps": 1160, "total_steps": 4130, "loss": 0.324, "lr": 3.615446757303575e-05, "epoch": 1.9661016949152543, "percentage": 28.09, "elapsed_time": "5:03:34", "remaining_time": "12:57:15"}
{"current_steps": 1165, "total_steps": 4130, "loss": 0.3102, "lr": 3.610449396986281e-05, "epoch": 1.9745762711864407, "percentage": 28.21, "elapsed_time": "5:04:50", "remaining_time": "12:55:50"}
{"current_steps": 1170, "total_steps": 4130, "loss": 0.3178, "lr": 3.6054232758619274e-05, "epoch": 1.9830508474576272, "percentage": 28.33, "elapsed_time": "5:06:05", "remaining_time": "12:54:24"}
{"current_steps": 1175, "total_steps": 4130, "loss": 0.3299, "lr": 3.600368483691361e-05, "epoch": 1.9915254237288136, "percentage": 28.45, "elapsed_time": "5:07:26", "remaining_time": "12:53:10"}
{"current_steps": 1180, "total_steps": 4130, "loss": 0.3012, "lr": 3.59528511074746e-05, "epoch": 2.0, "percentage": 28.57, "elapsed_time": "5:08:43", "remaining_time": "12:51:49"}
{"current_steps": 1185, "total_steps": 4130, "loss": 0.3156, "lr": 3.5901732478135235e-05, "epoch": 2.0084745762711864, "percentage": 28.69, "elapsed_time": "5:09:59", "remaining_time": "12:50:25"}
{"current_steps": 1190, "total_steps": 4130, "loss": 0.2836, "lr": 3.5850329861816475e-05, "epoch": 2.016949152542373, "percentage": 28.81, "elapsed_time": "5:11:14", "remaining_time": "12:48:56"}
{"current_steps": 1195, "total_steps": 4130, "loss": 0.2993, "lr": 3.5798644176511e-05, "epoch": 2.0254237288135593, "percentage": 28.93, "elapsed_time": "5:12:30", "remaining_time": "12:47:31"}
{"current_steps": 1200, "total_steps": 4130, "loss": 0.3142, "lr": 3.574667634526676e-05, "epoch": 2.0338983050847457, "percentage": 29.06, "elapsed_time": "5:13:45", "remaining_time": "12:46:05"}
{"current_steps": 1205, "total_steps": 4130, "loss": 0.3068, "lr": 3.5694427296170514e-05, "epoch": 2.042372881355932, "percentage": 29.18, "elapsed_time": "5:15:01", "remaining_time": "12:44:42"}
{"current_steps": 1210, "total_steps": 4130, "loss": 0.316, "lr": 3.564189796233125e-05, "epoch": 2.0508474576271185, "percentage": 29.3, "elapsed_time": "5:16:21", "remaining_time": "12:43:27"}
{"current_steps": 1215, "total_steps": 4130, "loss": 0.2988, "lr": 3.5589089281863547e-05, "epoch": 2.059322033898305, "percentage": 29.42, "elapsed_time": "5:17:37", "remaining_time": "12:42:02"}
{"current_steps": 1220, "total_steps": 4130, "loss": 0.2926, "lr": 3.553600219787079e-05, "epoch": 2.0677966101694913, "percentage": 29.54, "elapsed_time": "5:18:56", "remaining_time": "12:40:44"}
{"current_steps": 1225, "total_steps": 4130, "loss": 0.2965, "lr": 3.5482637658428315e-05, "epoch": 2.0762711864406778, "percentage": 29.66, "elapsed_time": "5:20:13", "remaining_time": "12:39:22"}
{"current_steps": 1230, "total_steps": 4130, "loss": 0.3234, "lr": 3.542899661656653e-05, "epoch": 2.084745762711864, "percentage": 29.78, "elapsed_time": "5:21:33", "remaining_time": "12:38:09"}
{"current_steps": 1235, "total_steps": 4130, "loss": 0.3451, "lr": 3.5375080030253826e-05, "epoch": 2.093220338983051, "percentage": 29.9, "elapsed_time": "5:22:54", "remaining_time": "12:36:55"}
{"current_steps": 1240, "total_steps": 4130, "loss": 0.304, "lr": 3.532088886237956e-05, "epoch": 2.1016949152542375, "percentage": 30.02, "elapsed_time": "5:24:11", "remaining_time": "12:35:35"}
{"current_steps": 1245, "total_steps": 4130, "loss": 0.3092, "lr": 3.5266424080736765e-05, "epoch": 2.110169491525424, "percentage": 30.15, "elapsed_time": "5:25:30", "remaining_time": "12:34:17"}
{"current_steps": 1250, "total_steps": 4130, "loss": 0.3236, "lr": 3.521168665800491e-05, "epoch": 2.1186440677966103, "percentage": 30.27, "elapsed_time": "5:26:50", "remaining_time": "12:33:03"}
{"current_steps": 1255, "total_steps": 4130, "loss": 0.2971, "lr": 3.515667757173254e-05, "epoch": 2.1271186440677967, "percentage": 30.39, "elapsed_time": "5:28:09", "remaining_time": "12:31:44"}
{"current_steps": 1260, "total_steps": 4130, "loss": 0.2878, "lr": 3.5101397804319794e-05, "epoch": 2.135593220338983, "percentage": 30.51, "elapsed_time": "5:29:25", "remaining_time": "12:30:20"}
{"current_steps": 1265, "total_steps": 4130, "loss": 0.2871, "lr": 3.5045848343000876e-05, "epoch": 2.1440677966101696, "percentage": 30.63, "elapsed_time": "5:30:41", "remaining_time": "12:28:56"}
{"current_steps": 1270, "total_steps": 4130, "loss": 0.3271, "lr": 3.4990030179826414e-05, "epoch": 2.152542372881356, "percentage": 30.75, "elapsed_time": "5:31:57", "remaining_time": "12:27:32"}
{"current_steps": 1275, "total_steps": 4130, "loss": 0.2948, "lr": 3.493394431164576e-05, "epoch": 2.1610169491525424, "percentage": 30.87, "elapsed_time": "5:33:16", "remaining_time": "12:26:17"}
{"current_steps": 1280, "total_steps": 4130, "loss": 0.3051, "lr": 3.4877591740089144e-05, "epoch": 2.169491525423729, "percentage": 30.99, "elapsed_time": "5:34:37", "remaining_time": "12:25:03"}
{"current_steps": 1285, "total_steps": 4130, "loss": 0.2968, "lr": 3.482097347154986e-05, "epoch": 2.1779661016949152, "percentage": 31.11, "elapsed_time": "5:35:52", "remaining_time": "12:23:38"}
{"current_steps": 1290, "total_steps": 4130, "loss": 0.3091, "lr": 3.476409051716621e-05, "epoch": 2.1864406779661016, "percentage": 31.23, "elapsed_time": "5:37:11", "remaining_time": "12:22:20"}
{"current_steps": 1295, "total_steps": 4130, "loss": 0.2911, "lr": 3.470694389280352e-05, "epoch": 2.194915254237288, "percentage": 31.36, "elapsed_time": "5:38:25", "remaining_time": "12:20:51"}
{"current_steps": 1300, "total_steps": 4130, "loss": 0.283, "lr": 3.464953461903593e-05, "epoch": 2.2033898305084745, "percentage": 31.48, "elapsed_time": "5:39:39", "remaining_time": "12:19:24"}
{"current_steps": 1305, "total_steps": 4130, "loss": 0.308, "lr": 3.459186372112824e-05, "epoch": 2.211864406779661, "percentage": 31.6, "elapsed_time": "5:40:54", "remaining_time": "12:17:58"}
{"current_steps": 1310, "total_steps": 4130, "loss": 0.3253, "lr": 3.453393222901753e-05, "epoch": 2.2203389830508473, "percentage": 31.72, "elapsed_time": "5:42:12", "remaining_time": "12:16:39"}
{"current_steps": 1315, "total_steps": 4130, "loss": 0.3152, "lr": 3.44757411772948e-05, "epoch": 2.2288135593220337, "percentage": 31.84, "elapsed_time": "5:43:31", "remaining_time": "12:15:22"}
{"current_steps": 1320, "total_steps": 4130, "loss": 0.3282, "lr": 3.441729160518652e-05, "epoch": 2.23728813559322, "percentage": 31.96, "elapsed_time": "5:44:50", "remaining_time": "12:14:05"}
{"current_steps": 1325, "total_steps": 4130, "loss": 0.3084, "lr": 3.435858455653601e-05, "epoch": 2.2457627118644066, "percentage": 32.08, "elapsed_time": "5:46:10", "remaining_time": "12:12:51"}
{"current_steps": 1330, "total_steps": 4130, "loss": 0.3119, "lr": 3.429962107978485e-05, "epoch": 2.2542372881355934, "percentage": 32.2, "elapsed_time": "5:47:29", "remaining_time": "12:11:34"}
{"current_steps": 1335, "total_steps": 4130, "loss": 0.303, "lr": 3.424040222795412e-05, "epoch": 2.26271186440678, "percentage": 32.32, "elapsed_time": "5:48:47", "remaining_time": "12:10:14"}
{"current_steps": 1340, "total_steps": 4130, "loss": 0.294, "lr": 3.418092905862563e-05, "epoch": 2.2711864406779663, "percentage": 32.45, "elapsed_time": "5:50:06", "remaining_time": "12:08:56"}
{"current_steps": 1345, "total_steps": 4130, "loss": 0.2951, "lr": 3.412120263392301e-05, "epoch": 2.2796610169491527, "percentage": 32.57, "elapsed_time": "5:51:25", "remaining_time": "12:07:41"}
{"current_steps": 1350, "total_steps": 4130, "loss": 0.3212, "lr": 3.406122402049272e-05, "epoch": 2.288135593220339, "percentage": 32.69, "elapsed_time": "5:52:44", "remaining_time": "12:06:23"}
{"current_steps": 1355, "total_steps": 4130, "loss": 0.2984, "lr": 3.400099428948505e-05, "epoch": 2.2966101694915255, "percentage": 32.81, "elapsed_time": "5:54:04", "remaining_time": "12:05:08"}
{"current_steps": 1360, "total_steps": 4130, "loss": 0.3003, "lr": 3.394051451653496e-05, "epoch": 2.305084745762712, "percentage": 32.93, "elapsed_time": "5:55:23", "remaining_time": "12:03:50"}
{"current_steps": 1365, "total_steps": 4130, "loss": 0.3187, "lr": 3.3879785781742875e-05, "epoch": 2.3135593220338984, "percentage": 33.05, "elapsed_time": "5:56:41", "remaining_time": "12:02:31"}
{"current_steps": 1370, "total_steps": 4130, "loss": 0.2955, "lr": 3.381880916965541e-05, "epoch": 2.3220338983050848, "percentage": 33.17, "elapsed_time": "5:57:55", "remaining_time": "12:01:04"}
{"current_steps": 1375, "total_steps": 4130, "loss": 0.3139, "lr": 3.3757585769245964e-05, "epoch": 2.330508474576271, "percentage": 33.29, "elapsed_time": "5:59:15", "remaining_time": "11:59:49"}
{"current_steps": 1380, "total_steps": 4130, "loss": 0.3236, "lr": 3.3696116673895314e-05, "epoch": 2.3389830508474576, "percentage": 33.41, "elapsed_time": "6:00:36", "remaining_time": "11:58:35"}
{"current_steps": 1385, "total_steps": 4130, "loss": 0.3091, "lr": 3.363440298137207e-05, "epoch": 2.347457627118644, "percentage": 33.54, "elapsed_time": "6:01:52", "remaining_time": "11:57:13"}
{"current_steps": 1390, "total_steps": 4130, "loss": 0.2928, "lr": 3.357244579381306e-05, "epoch": 2.3559322033898304, "percentage": 33.66, "elapsed_time": "6:03:11", "remaining_time": "11:55:55"}
{"current_steps": 1395, "total_steps": 4130, "loss": 0.3004, "lr": 3.351024621770369e-05, "epoch": 2.364406779661017, "percentage": 33.78, "elapsed_time": "6:04:25", "remaining_time": "11:54:28"}
{"current_steps": 1400, "total_steps": 4130, "loss": 0.2874, "lr": 3.34478053638581e-05, "epoch": 2.3728813559322033, "percentage": 33.9, "elapsed_time": "6:05:44", "remaining_time": "11:53:11"}
{"current_steps": 1405, "total_steps": 4130, "loss": 0.2771, "lr": 3.3385124347399415e-05, "epoch": 2.3813559322033897, "percentage": 34.02, "elapsed_time": "6:07:01", "remaining_time": "11:51:50"}
{"current_steps": 1410, "total_steps": 4130, "loss": 0.3024, "lr": 3.33222042877398e-05, "epoch": 2.389830508474576, "percentage": 34.14, "elapsed_time": "6:08:20", "remaining_time": "11:50:32"}
{"current_steps": 1415, "total_steps": 4130, "loss": 0.2977, "lr": 3.325904630856042e-05, "epoch": 2.3983050847457625, "percentage": 34.26, "elapsed_time": "6:09:40", "remaining_time": "11:49:17"}
{"current_steps": 1420, "total_steps": 4130, "loss": 0.3493, "lr": 3.319565153779146e-05, "epoch": 2.406779661016949, "percentage": 34.38, "elapsed_time": "6:10:55", "remaining_time": "11:47:53"}
{"current_steps": 1425, "total_steps": 4130, "loss": 0.3226, "lr": 3.31320211075919e-05, "epoch": 2.415254237288136, "percentage": 34.5, "elapsed_time": "6:12:11", "remaining_time": "11:46:31"}
{"current_steps": 1430, "total_steps": 4130, "loss": 0.3404, "lr": 3.306815615432936e-05, "epoch": 2.423728813559322, "percentage": 34.62, "elapsed_time": "6:13:32", "remaining_time": "11:45:17"}
{"current_steps": 1435, "total_steps": 4130, "loss": 0.2958, "lr": 3.300405781855975e-05, "epoch": 2.4322033898305087, "percentage": 34.75, "elapsed_time": "6:14:48", "remaining_time": "11:43:54"}
{"current_steps": 1440, "total_steps": 4130, "loss": 0.3017, "lr": 3.2939727245006956e-05, "epoch": 2.440677966101695, "percentage": 34.87, "elapsed_time": "6:16:05", "remaining_time": "11:42:33"}
{"current_steps": 1445, "total_steps": 4130, "loss": 0.3066, "lr": 3.2875165582542347e-05, "epoch": 2.4491525423728815, "percentage": 34.99, "elapsed_time": "6:17:23", "remaining_time": "11:41:14"}
{"current_steps": 1450, "total_steps": 4130, "loss": 0.2713, "lr": 3.281037398416427e-05, "epoch": 2.457627118644068, "percentage": 35.11, "elapsed_time": "6:18:41", "remaining_time": "11:39:54"}
{"current_steps": 1455, "total_steps": 4130, "loss": 0.3181, "lr": 3.2745353606977506e-05, "epoch": 2.4661016949152543, "percentage": 35.23, "elapsed_time": "6:19:58", "remaining_time": "11:38:34"}
{"current_steps": 1460, "total_steps": 4130, "loss": 0.3097, "lr": 3.268010561217253e-05, "epoch": 2.4745762711864407, "percentage": 35.35, "elapsed_time": "6:21:14", "remaining_time": "11:37:12"}
{"current_steps": 1465, "total_steps": 4130, "loss": 0.2961, "lr": 3.261463116500483e-05, "epoch": 2.483050847457627, "percentage": 35.47, "elapsed_time": "6:22:32", "remaining_time": "11:35:53"}
{"current_steps": 1470, "total_steps": 4130, "loss": 0.2933, "lr": 3.254893143477408e-05, "epoch": 2.4915254237288136, "percentage": 35.59, "elapsed_time": "6:23:49", "remaining_time": "11:34:32"}
{"current_steps": 1475, "total_steps": 4130, "loss": 0.3205, "lr": 3.248300759480323e-05, "epoch": 2.5, "percentage": 35.71, "elapsed_time": "6:25:09", "remaining_time": "11:33:17"}
{"current_steps": 1480, "total_steps": 4130, "loss": 0.2873, "lr": 3.241686082241761e-05, "epoch": 2.5084745762711864, "percentage": 35.84, "elapsed_time": "6:26:30", "remaining_time": "11:32:02"}
{"current_steps": 1485, "total_steps": 4130, "loss": 0.2667, "lr": 3.235049229892384e-05, "epoch": 2.516949152542373, "percentage": 35.96, "elapsed_time": "6:27:48", "remaining_time": "11:30:44"}
{"current_steps": 1490, "total_steps": 4130, "loss": 0.3194, "lr": 3.2283903209588795e-05, "epoch": 2.5254237288135593, "percentage": 36.08, "elapsed_time": "6:29:07", "remaining_time": "11:29:28"}
{"current_steps": 1495, "total_steps": 4130, "loss": 0.3028, "lr": 3.221709474361838e-05, "epoch": 2.5338983050847457, "percentage": 36.2, "elapsed_time": "6:30:23", "remaining_time": "11:28:04"}
{"current_steps": 1500, "total_steps": 4130, "loss": 0.3209, "lr": 3.215006809413633e-05, "epoch": 2.542372881355932, "percentage": 36.32, "elapsed_time": "6:31:43", "remaining_time": "11:26:49"}
{"current_steps": 1505, "total_steps": 4130, "loss": 0.2896, "lr": 3.20828244581629e-05, "epoch": 2.5508474576271185, "percentage": 36.44, "elapsed_time": "6:33:40", "remaining_time": "11:26:38"}
{"current_steps": 1510, "total_steps": 4130, "loss": 0.3325, "lr": 3.2015365036593466e-05, "epoch": 2.559322033898305, "percentage": 36.56, "elapsed_time": "6:35:01", "remaining_time": "11:25:23"}
{"current_steps": 1515, "total_steps": 4130, "loss": 0.2919, "lr": 3.194769103417709e-05, "epoch": 2.5677966101694913, "percentage": 36.68, "elapsed_time": "6:36:19", "remaining_time": "11:24:05"}
{"current_steps": 1520, "total_steps": 4130, "loss": 0.2994, "lr": 3.1879803659495015e-05, "epoch": 2.576271186440678, "percentage": 36.8, "elapsed_time": "6:37:39", "remaining_time": "11:22:49"}
{"current_steps": 1525, "total_steps": 4130, "loss": 0.2972, "lr": 3.181170412493906e-05, "epoch": 2.584745762711864, "percentage": 36.92, "elapsed_time": "6:38:56", "remaining_time": "11:21:28"}
{"current_steps": 1530, "total_steps": 4130, "loss": 0.2709, "lr": 3.1743393646689996e-05, "epoch": 2.593220338983051, "percentage": 37.05, "elapsed_time": "6:40:10", "remaining_time": "11:20:02"}
{"current_steps": 1535, "total_steps": 4130, "loss": 0.2859, "lr": 3.1674873444695804e-05, "epoch": 2.601694915254237, "percentage": 37.17, "elapsed_time": "6:41:30", "remaining_time": "11:18:46"}
{"current_steps": 1540, "total_steps": 4130, "loss": 0.2991, "lr": 3.1606144742649875e-05, "epoch": 2.610169491525424, "percentage": 37.29, "elapsed_time": "6:42:50", "remaining_time": "11:17:30"}
{"current_steps": 1545, "total_steps": 4130, "loss": 0.271, "lr": 3.15372087679692e-05, "epoch": 2.6186440677966103, "percentage": 37.41, "elapsed_time": "6:44:06", "remaining_time": "11:16:07"}
{"current_steps": 1550, "total_steps": 4130, "loss": 0.3008, "lr": 3.1468066751772415e-05, "epoch": 2.6271186440677967, "percentage": 37.53, "elapsed_time": "6:45:23", "remaining_time": "11:14:47"}
{"current_steps": 1555, "total_steps": 4130, "loss": 0.2868, "lr": 3.1398719928857834e-05, "epoch": 2.635593220338983, "percentage": 37.65, "elapsed_time": "6:46:37", "remaining_time": "11:13:20"}
{"current_steps": 1560, "total_steps": 4130, "loss": 0.2862, "lr": 3.132916953768137e-05, "epoch": 2.6440677966101696, "percentage": 37.77, "elapsed_time": "6:47:54", "remaining_time": "11:12:00"}
{"current_steps": 1565, "total_steps": 4130, "loss": 0.2933, "lr": 3.1259416820334446e-05, "epoch": 2.652542372881356, "percentage": 37.89, "elapsed_time": "6:49:11", "remaining_time": "11:10:39"}
{"current_steps": 1570, "total_steps": 4130, "loss": 0.2766, "lr": 3.118946302252181e-05, "epoch": 2.6610169491525424, "percentage": 38.01, "elapsed_time": "6:50:26", "remaining_time": "11:09:14"}
{"current_steps": 1575, "total_steps": 4130, "loss": 0.278, "lr": 3.1119309393539256e-05, "epoch": 2.669491525423729, "percentage": 38.14, "elapsed_time": "6:51:42", "remaining_time": "11:07:53"}
{"current_steps": 1580, "total_steps": 4130, "loss": 0.2893, "lr": 3.104895718625136e-05, "epoch": 2.6779661016949152, "percentage": 38.26, "elapsed_time": "6:53:02", "remaining_time": "11:06:37"}
{"current_steps": 1585, "total_steps": 4130, "loss": 0.3102, "lr": 3.097840765706908e-05, "epoch": 2.6864406779661016, "percentage": 38.38, "elapsed_time": "6:54:21", "remaining_time": "11:05:20"}
{"current_steps": 1590, "total_steps": 4130, "loss": 0.3017, "lr": 3.0907662065927297e-05, "epoch": 2.694915254237288, "percentage": 38.5, "elapsed_time": "6:55:40", "remaining_time": "11:04:02"}
{"current_steps": 1595, "total_steps": 4130, "loss": 0.308, "lr": 3.083672167626237e-05, "epoch": 2.7033898305084745, "percentage": 38.62, "elapsed_time": "6:57:01", "remaining_time": "11:02:47"}
{"current_steps": 1600, "total_steps": 4130, "loss": 0.2901, "lr": 3.0765587754989516e-05, "epoch": 2.711864406779661, "percentage": 38.74, "elapsed_time": "6:58:21", "remaining_time": "11:01:31"}
{"current_steps": 1605, "total_steps": 4130, "loss": 0.2903, "lr": 3.069426157248022e-05, "epoch": 2.7203389830508473, "percentage": 38.86, "elapsed_time": "6:59:34", "remaining_time": "11:00:05"}
{"current_steps": 1610, "total_steps": 4130, "loss": 0.3259, "lr": 3.062274440253953e-05, "epoch": 2.7288135593220337, "percentage": 38.98, "elapsed_time": "7:00:54", "remaining_time": "10:58:49"}
{"current_steps": 1615, "total_steps": 4130, "loss": 0.3096, "lr": 3.0551037522383325e-05, "epoch": 2.7372881355932206, "percentage": 39.1, "elapsed_time": "7:02:13", "remaining_time": "10:57:30"}
{"current_steps": 1620, "total_steps": 4130, "loss": 0.3053, "lr": 3.0479142212615457e-05, "epoch": 2.7457627118644066, "percentage": 39.23, "elapsed_time": "7:03:33", "remaining_time": "10:56:14"}
{"current_steps": 1625, "total_steps": 4130, "loss": 0.3126, "lr": 3.0407059757204968e-05, "epoch": 2.7542372881355934, "percentage": 39.35, "elapsed_time": "7:04:54", "remaining_time": "10:55:00"}
{"current_steps": 1630, "total_steps": 4130, "loss": 0.3394, "lr": 3.033479144346308e-05, "epoch": 2.7627118644067794, "percentage": 39.47, "elapsed_time": "7:06:14", "remaining_time": "10:53:44"}
{"current_steps": 1635, "total_steps": 4130, "loss": 0.3046, "lr": 3.0262338562020246e-05, "epoch": 2.7711864406779663, "percentage": 39.59, "elapsed_time": "7:07:34", "remaining_time": "10:52:29"}
{"current_steps": 1640, "total_steps": 4130, "loss": 0.3088, "lr": 3.018970240680308e-05, "epoch": 2.7796610169491527, "percentage": 39.71, "elapsed_time": "7:08:54", "remaining_time": "10:51:12"}
{"current_steps": 1645, "total_steps": 4130, "loss": 0.3076, "lr": 3.011688427501126e-05, "epoch": 2.788135593220339, "percentage": 39.83, "elapsed_time": "7:10:11", "remaining_time": "10:49:52"}
{"current_steps": 1650, "total_steps": 4130, "loss": 0.314, "lr": 3.0043885467094382e-05, "epoch": 2.7966101694915255, "percentage": 39.95, "elapsed_time": "7:11:31", "remaining_time": "10:48:36"}
{"current_steps": 1655, "total_steps": 4130, "loss": 0.3015, "lr": 2.9970707286728676e-05, "epoch": 2.805084745762712, "percentage": 40.07, "elapsed_time": "7:12:50", "remaining_time": "10:47:17"}
{"current_steps": 1660, "total_steps": 4130, "loss": 0.2792, "lr": 2.9897351040793786e-05, "epoch": 2.8135593220338984, "percentage": 40.19, "elapsed_time": "7:14:05", "remaining_time": "10:45:54"}
{"current_steps": 1665, "total_steps": 4130, "loss": 0.2803, "lr": 2.9823818039349407e-05, "epoch": 2.8220338983050848, "percentage": 40.31, "elapsed_time": "7:15:23", "remaining_time": "10:44:35"}
{"current_steps": 1670, "total_steps": 4130, "loss": 0.29, "lr": 2.9750109595611884e-05, "epoch": 2.830508474576271, "percentage": 40.44, "elapsed_time": "7:16:41", "remaining_time": "10:43:16"}
{"current_steps": 1675, "total_steps": 4130, "loss": 0.287, "lr": 2.967622702593074e-05, "epoch": 2.8389830508474576, "percentage": 40.56, "elapsed_time": "7:18:02", "remaining_time": "10:42:01"}
{"current_steps": 1680, "total_steps": 4130, "loss": 0.3084, "lr": 2.9602171649765235e-05, "epoch": 2.847457627118644, "percentage": 40.68, "elapsed_time": "7:19:20", "remaining_time": "10:40:42"}
{"current_steps": 1685, "total_steps": 4130, "loss": 0.2907, "lr": 2.9527944789660732e-05, "epoch": 2.8559322033898304, "percentage": 40.8, "elapsed_time": "7:20:40", "remaining_time": "10:39:25"}
{"current_steps": 1690, "total_steps": 4130, "loss": 0.2887, "lr": 2.9453547771225088e-05, "epoch": 2.864406779661017, "percentage": 40.92, "elapsed_time": "7:21:58", "remaining_time": "10:38:07"}
{"current_steps": 1695, "total_steps": 4130, "loss": 0.2823, "lr": 2.9378981923105026e-05, "epoch": 2.8728813559322033, "percentage": 41.04, "elapsed_time": "7:23:17", "remaining_time": "10:36:49"}
{"current_steps": 1700, "total_steps": 4130, "loss": 0.3211, "lr": 2.930424857696236e-05, "epoch": 2.8813559322033897, "percentage": 41.16, "elapsed_time": "7:24:33", "remaining_time": "10:35:27"}
{"current_steps": 1705, "total_steps": 4130, "loss": 0.3209, "lr": 2.922934906745024e-05, "epoch": 2.889830508474576, "percentage": 41.28, "elapsed_time": "7:25:52", "remaining_time": "10:34:10"}
{"current_steps": 1710, "total_steps": 4130, "loss": 0.3164, "lr": 2.9154284732189285e-05, "epoch": 2.898305084745763, "percentage": 41.4, "elapsed_time": "7:27:11", "remaining_time": "10:32:52"}
{"current_steps": 1715, "total_steps": 4130, "loss": 0.2904, "lr": 2.907905691174374e-05, "epoch": 2.906779661016949, "percentage": 41.53, "elapsed_time": "7:28:32", "remaining_time": "10:31:36"}
{"current_steps": 1720, "total_steps": 4130, "loss": 0.3213, "lr": 2.90036669495975e-05, "epoch": 2.915254237288136, "percentage": 41.65, "elapsed_time": "7:29:50", "remaining_time": "10:30:18"}
{"current_steps": 1725, "total_steps": 4130, "loss": 0.3215, "lr": 2.8928116192130127e-05, "epoch": 2.923728813559322, "percentage": 41.77, "elapsed_time": "7:31:10", "remaining_time": "10:29:01"}
{"current_steps": 1730, "total_steps": 4130, "loss": 0.2815, "lr": 2.8852405988592802e-05, "epoch": 2.9322033898305087, "percentage": 41.89, "elapsed_time": "7:32:28", "remaining_time": "10:27:42"}
{"current_steps": 1735, "total_steps": 4130, "loss": 0.2986, "lr": 2.8776537691084247e-05, "epoch": 2.940677966101695, "percentage": 42.01, "elapsed_time": "7:33:41", "remaining_time": "10:26:16"}
{"current_steps": 1740, "total_steps": 4130, "loss": 0.3046, "lr": 2.8700512654526543e-05, "epoch": 2.9491525423728815, "percentage": 42.13, "elapsed_time": "7:35:00", "remaining_time": "10:24:58"}
{"current_steps": 1745, "total_steps": 4130, "loss": 0.2869, "lr": 2.8624332236640975e-05, "epoch": 2.957627118644068, "percentage": 42.25, "elapsed_time": "7:36:14", "remaining_time": "10:23:34"}
{"current_steps": 1750, "total_steps": 4130, "loss": 0.2825, "lr": 2.854799779792375e-05, "epoch": 2.9661016949152543, "percentage": 42.37, "elapsed_time": "7:37:35", "remaining_time": "10:22:19"}
{"current_steps": 1755, "total_steps": 4130, "loss": 0.2853, "lr": 2.8471510701621708e-05, "epoch": 2.9745762711864407, "percentage": 42.49, "elapsed_time": "7:38:56", "remaining_time": "10:21:04"}
{"current_steps": 1760, "total_steps": 4130, "loss": 0.3144, "lr": 2.8394872313707998e-05, "epoch": 2.983050847457627, "percentage": 42.62, "elapsed_time": "7:40:16", "remaining_time": "10:19:48"}
{"current_steps": 1765, "total_steps": 4130, "loss": 0.3017, "lr": 2.8318084002857654e-05, "epoch": 2.9915254237288136, "percentage": 42.74, "elapsed_time": "7:41:35", "remaining_time": "10:18:30"}
{"current_steps": 1770, "total_steps": 4130, "loss": 0.2819, "lr": 2.824114714042317e-05, "epoch": 3.0, "percentage": 42.86, "elapsed_time": "7:42:52", "remaining_time": "10:17:10"}
{"current_steps": 1775, "total_steps": 4130, "loss": 0.3075, "lr": 2.8164063100409992e-05, "epoch": 3.0084745762711864, "percentage": 42.98, "elapsed_time": "7:44:13", "remaining_time": "10:15:54"}
{"current_steps": 1780, "total_steps": 4130, "loss": 0.2576, "lr": 2.8086833259452006e-05, "epoch": 3.016949152542373, "percentage": 43.1, "elapsed_time": "7:45:28", "remaining_time": "10:14:31"}
{"current_steps": 1785, "total_steps": 4130, "loss": 0.2891, "lr": 2.8009458996786934e-05, "epoch": 3.0254237288135593, "percentage": 43.22, "elapsed_time": "7:46:47", "remaining_time": "10:13:14"}
{"current_steps": 1790, "total_steps": 4130, "loss": 0.3207, "lr": 2.7931941694231705e-05, "epoch": 3.0338983050847457, "percentage": 43.34, "elapsed_time": "7:48:08", "remaining_time": "10:11:58"}
{"current_steps": 1795, "total_steps": 4130, "loss": 0.2785, "lr": 2.7854282736157777e-05, "epoch": 3.042372881355932, "percentage": 43.46, "elapsed_time": "7:49:25", "remaining_time": "10:10:38"}
{"current_steps": 1800, "total_steps": 4130, "loss": 0.3067, "lr": 2.777648350946642e-05, "epoch": 3.0508474576271185, "percentage": 43.58, "elapsed_time": "7:50:43", "remaining_time": "10:09:20"}
{"current_steps": 1805, "total_steps": 4130, "loss": 0.2858, "lr": 2.7698545403563934e-05, "epoch": 3.059322033898305, "percentage": 43.7, "elapsed_time": "7:52:01", "remaining_time": "10:08:00"}
{"current_steps": 1810, "total_steps": 4130, "loss": 0.2608, "lr": 2.7620469810336854e-05, "epoch": 3.0677966101694913, "percentage": 43.83, "elapsed_time": "7:53:17", "remaining_time": "10:06:38"}
{"current_steps": 1815, "total_steps": 4130, "loss": 0.2882, "lr": 2.754225812412708e-05, "epoch": 3.0762711864406778, "percentage": 43.95, "elapsed_time": "7:54:29", "remaining_time": "10:05:12"}
{"current_steps": 1820, "total_steps": 4130, "loss": 0.3186, "lr": 2.7463911741706982e-05, "epoch": 3.084745762711864, "percentage": 44.07, "elapsed_time": "7:55:50", "remaining_time": "10:03:56"}
{"current_steps": 1825, "total_steps": 4130, "loss": 0.3186, "lr": 2.738543206225445e-05, "epoch": 3.093220338983051, "percentage": 44.19, "elapsed_time": "7:57:06", "remaining_time": "10:02:35"}
{"current_steps": 1830, "total_steps": 4130, "loss": 0.2562, "lr": 2.7306820487327906e-05, "epoch": 3.1016949152542375, "percentage": 44.31, "elapsed_time": "7:58:22", "remaining_time": "10:01:14"}
{"current_steps": 1835, "total_steps": 4130, "loss": 0.2873, "lr": 2.7228078420841277e-05, "epoch": 3.110169491525424, "percentage": 44.43, "elapsed_time": "7:59:41", "remaining_time": "9:59:56"}
{"current_steps": 1840, "total_steps": 4130, "loss": 0.2612, "lr": 2.714920726903892e-05, "epoch": 3.1186440677966103, "percentage": 44.55, "elapsed_time": "8:01:01", "remaining_time": "9:58:39"}
{"current_steps": 1845, "total_steps": 4130, "loss": 0.3008, "lr": 2.7070208440470525e-05, "epoch": 3.1271186440677967, "percentage": 44.67, "elapsed_time": "8:02:19", "remaining_time": "9:57:21"}
{"current_steps": 1850, "total_steps": 4130, "loss": 0.2956, "lr": 2.699108334596592e-05, "epoch": 3.135593220338983, "percentage": 44.79, "elapsed_time": "8:03:35", "remaining_time": "9:56:00"}
{"current_steps": 1855, "total_steps": 4130, "loss": 0.2518, "lr": 2.6911833398609923e-05, "epoch": 3.1440677966101696, "percentage": 44.92, "elapsed_time": "8:04:47", "remaining_time": "9:54:33"}
{"current_steps": 1860, "total_steps": 4130, "loss": 0.2862, "lr": 2.683246001371706e-05, "epoch": 3.152542372881356, "percentage": 45.04, "elapsed_time": "8:06:08", "remaining_time": "9:53:17"}
{"current_steps": 1865, "total_steps": 4130, "loss": 0.2854, "lr": 2.6752964608806338e-05, "epoch": 3.1610169491525424, "percentage": 45.16, "elapsed_time": "8:07:27", "remaining_time": "9:52:00"}
{"current_steps": 1870, "total_steps": 4130, "loss": 0.2775, "lr": 2.6673348603575884e-05, "epoch": 3.169491525423729, "percentage": 45.28, "elapsed_time": "8:08:46", "remaining_time": "9:50:42"}
{"current_steps": 1875, "total_steps": 4130, "loss": 0.2927, "lr": 2.6593613419877615e-05, "epoch": 3.1779661016949152, "percentage": 45.4, "elapsed_time": "8:10:02", "remaining_time": "9:49:20"}
{"current_steps": 1880, "total_steps": 4130, "loss": 0.3094, "lr": 2.6513760481691842e-05, "epoch": 3.1864406779661016, "percentage": 45.52, "elapsed_time": "8:11:23", "remaining_time": "9:48:05"}
{"current_steps": 1885, "total_steps": 4130, "loss": 0.2881, "lr": 2.6433791215101848e-05, "epoch": 3.194915254237288, "percentage": 45.64, "elapsed_time": "8:12:37", "remaining_time": "9:46:42"}
{"current_steps": 1890, "total_steps": 4130, "loss": 0.3341, "lr": 2.6353707048268397e-05, "epoch": 3.2033898305084745, "percentage": 45.76, "elapsed_time": "8:13:57", "remaining_time": "9:45:26"}
{"current_steps": 1895, "total_steps": 4130, "loss": 0.2995, "lr": 2.6273509411404234e-05, "epoch": 3.211864406779661, "percentage": 45.88, "elapsed_time": "8:15:17", "remaining_time": "9:44:09"}
{"current_steps": 1900, "total_steps": 4130, "loss": 0.2862, "lr": 2.6193199736748572e-05, "epoch": 3.2203389830508473, "percentage": 46.0, "elapsed_time": "8:16:35", "remaining_time": "9:42:50"}
{"current_steps": 1905, "total_steps": 4130, "loss": 0.3022, "lr": 2.611277945854148e-05, "epoch": 3.2288135593220337, "percentage": 46.13, "elapsed_time": "8:17:52", "remaining_time": "9:41:30"}
{"current_steps": 1910, "total_steps": 4130, "loss": 0.3021, "lr": 2.603225001299829e-05, "epoch": 3.23728813559322, "percentage": 46.25, "elapsed_time": "8:19:10", "remaining_time": "9:40:11"}
{"current_steps": 1915, "total_steps": 4130, "loss": 0.3117, "lr": 2.595161283828392e-05, "epoch": 3.2457627118644066, "percentage": 46.37, "elapsed_time": "8:20:28", "remaining_time": "9:38:52"}
{"current_steps": 1920, "total_steps": 4130, "loss": 0.2706, "lr": 2.5870869374487227e-05, "epoch": 3.2542372881355934, "percentage": 46.49, "elapsed_time": "8:21:45", "remaining_time": "9:37:32"}
{"current_steps": 1925, "total_steps": 4130, "loss": 0.2969, "lr": 2.579002106359527e-05, "epoch": 3.26271186440678, "percentage": 46.61, "elapsed_time": "8:23:04", "remaining_time": "9:36:15"}
{"current_steps": 1930, "total_steps": 4130, "loss": 0.3404, "lr": 2.5709069349467562e-05, "epoch": 3.2711864406779663, "percentage": 46.73, "elapsed_time": "8:24:25", "remaining_time": "9:34:59"}
{"current_steps": 1935, "total_steps": 4130, "loss": 0.3009, "lr": 2.562801567781026e-05, "epoch": 3.2796610169491527, "percentage": 46.85, "elapsed_time": "8:25:45", "remaining_time": "9:33:43"}
{"current_steps": 1940, "total_steps": 4130, "loss": 0.2584, "lr": 2.554686149615038e-05, "epoch": 3.288135593220339, "percentage": 46.97, "elapsed_time": "8:27:00", "remaining_time": "9:32:20"}
{"current_steps": 1945, "total_steps": 4130, "loss": 0.2659, "lr": 2.5465608253809944e-05, "epoch": 3.2966101694915255, "percentage": 47.09, "elapsed_time": "8:28:17", "remaining_time": "9:31:01"}
{"current_steps": 1950, "total_steps": 4130, "loss": 0.2707, "lr": 2.5384257401880077e-05, "epoch": 3.305084745762712, "percentage": 47.22, "elapsed_time": "8:29:36", "remaining_time": "9:29:42"}
{"current_steps": 1955, "total_steps": 4130, "loss": 0.2552, "lr": 2.530281039319509e-05, "epoch": 3.3135593220338984, "percentage": 47.34, "elapsed_time": "8:30:51", "remaining_time": "9:28:20"}
{"current_steps": 1960, "total_steps": 4130, "loss": 0.2629, "lr": 2.5221268682306565e-05, "epoch": 3.3220338983050848, "percentage": 47.46, "elapsed_time": "8:32:08", "remaining_time": "9:27:01"}
{"current_steps": 1965, "total_steps": 4130, "loss": 0.3055, "lr": 2.5139633725457345e-05, "epoch": 3.330508474576271, "percentage": 47.58, "elapsed_time": "8:33:27", "remaining_time": "9:25:42"}
{"current_steps": 1970, "total_steps": 4130, "loss": 0.2804, "lr": 2.505790698055554e-05, "epoch": 3.3389830508474576, "percentage": 47.7, "elapsed_time": "8:34:41", "remaining_time": "9:24:20"}
{"current_steps": 1975, "total_steps": 4130, "loss": 0.2928, "lr": 2.49760899071485e-05, "epoch": 3.347457627118644, "percentage": 47.82, "elapsed_time": "8:36:01", "remaining_time": "9:23:03"}
{"current_steps": 1980, "total_steps": 4130, "loss": 0.2705, "lr": 2.4894183966396735e-05, "epoch": 3.3559322033898304, "percentage": 47.94, "elapsed_time": "8:37:17", "remaining_time": "9:21:42"}
{"current_steps": 1985, "total_steps": 4130, "loss": 0.2963, "lr": 2.4812190621047822e-05, "epoch": 3.364406779661017, "percentage": 48.06, "elapsed_time": "8:38:38", "remaining_time": "9:20:26"}
{"current_steps": 1990, "total_steps": 4130, "loss": 0.3058, "lr": 2.4730111335410298e-05, "epoch": 3.3728813559322033, "percentage": 48.18, "elapsed_time": "8:39:58", "remaining_time": "9:19:10"}
{"current_steps": 1995, "total_steps": 4130, "loss": 0.2798, "lr": 2.4647947575327468e-05, "epoch": 3.3813559322033897, "percentage": 48.31, "elapsed_time": "8:41:14", "remaining_time": "9:17:49"}
{"current_steps": 2000, "total_steps": 4130, "loss": 0.2525, "lr": 2.4565700808151297e-05, "epoch": 3.389830508474576, "percentage": 48.43, "elapsed_time": "8:42:29", "remaining_time": "9:16:27"}
{"current_steps": 2005, "total_steps": 4130, "loss": 0.282, "lr": 2.4483372502716124e-05, "epoch": 3.3983050847457625, "percentage": 48.55, "elapsed_time": "8:43:48", "remaining_time": "9:15:09"}
{"current_steps": 2010, "total_steps": 4130, "loss": 0.29, "lr": 2.44009641293125e-05, "epoch": 3.406779661016949, "percentage": 48.67, "elapsed_time": "8:45:07", "remaining_time": "9:13:52"}
{"current_steps": 2015, "total_steps": 4130, "loss": 0.2811, "lr": 2.431847715966087e-05, "epoch": 3.415254237288136, "percentage": 48.79, "elapsed_time": "8:46:27", "remaining_time": "9:12:35"}
{"current_steps": 2020, "total_steps": 4130, "loss": 0.2722, "lr": 2.423591306688534e-05, "epoch": 3.423728813559322, "percentage": 48.91, "elapsed_time": "8:47:42", "remaining_time": "9:11:12"}
{"current_steps": 2025, "total_steps": 4130, "loss": 0.2813, "lr": 2.4153273325487346e-05, "epoch": 3.4322033898305087, "percentage": 49.03, "elapsed_time": "8:48:58", "remaining_time": "9:09:52"}
{"current_steps": 2030, "total_steps": 4130, "loss": 0.2675, "lr": 2.407055941131932e-05, "epoch": 3.440677966101695, "percentage": 49.15, "elapsed_time": "8:50:18", "remaining_time": "9:08:36"}
{"current_steps": 2035, "total_steps": 4130, "loss": 0.2873, "lr": 2.3987772801558328e-05, "epoch": 3.4491525423728815, "percentage": 49.27, "elapsed_time": "8:51:36", "remaining_time": "9:07:16"}
{"current_steps": 2040, "total_steps": 4130, "loss": 0.2845, "lr": 2.3904914974679705e-05, "epoch": 3.457627118644068, "percentage": 49.39, "elapsed_time": "8:52:56", "remaining_time": "9:05:59"}
{"current_steps": 2045, "total_steps": 4130, "loss": 0.2671, "lr": 2.3821987410430646e-05, "epoch": 3.4661016949152543, "percentage": 49.52, "elapsed_time": "8:54:12", "remaining_time": "9:04:39"}
{"current_steps": 2050, "total_steps": 4130, "loss": 0.2978, "lr": 2.3738991589803783e-05, "epoch": 3.4745762711864407, "percentage": 49.64, "elapsed_time": "8:55:30", "remaining_time": "9:03:20"}
{"current_steps": 2055, "total_steps": 4130, "loss": 0.281, "lr": 2.36559289950107e-05, "epoch": 3.483050847457627, "percentage": 49.76, "elapsed_time": "8:56:49", "remaining_time": "9:02:03"}
{"current_steps": 2060, "total_steps": 4130, "loss": 0.2985, "lr": 2.357280110945552e-05, "epoch": 3.4915254237288136, "percentage": 49.88, "elapsed_time": "8:58:03", "remaining_time": "9:00:40"}
{"current_steps": 2065, "total_steps": 4130, "loss": 0.3108, "lr": 2.3489609417708383e-05, "epoch": 3.5, "percentage": 50.0, "elapsed_time": "8:59:21", "remaining_time": "8:59:21"}
{"current_steps": 2070, "total_steps": 4130, "loss": 0.2611, "lr": 2.340635540547892e-05, "epoch": 3.5084745762711864, "percentage": 50.12, "elapsed_time": "9:00:37", "remaining_time": "8:58:00"}
{"current_steps": 2075, "total_steps": 4130, "loss": 0.2853, "lr": 2.3323040559589755e-05, "epoch": 3.516949152542373, "percentage": 50.24, "elapsed_time": "9:01:57", "remaining_time": "8:56:44"}
{"current_steps": 2080, "total_steps": 4130, "loss": 0.2843, "lr": 2.3239666367949917e-05, "epoch": 3.5254237288135593, "percentage": 50.36, "elapsed_time": "9:03:15", "remaining_time": "8:55:24"}
{"current_steps": 2085, "total_steps": 4130, "loss": 0.2665, "lr": 2.3156234319528295e-05, "epoch": 3.5338983050847457, "percentage": 50.48, "elapsed_time": "9:04:34", "remaining_time": "8:54:07"}
{"current_steps": 2090, "total_steps": 4130, "loss": 0.2958, "lr": 2.3072745904327015e-05, "epoch": 3.542372881355932, "percentage": 50.61, "elapsed_time": "9:05:50", "remaining_time": "8:52:47"}
{"current_steps": 2095, "total_steps": 4130, "loss": 0.2588, "lr": 2.298920261335488e-05, "epoch": 3.5508474576271185, "percentage": 50.73, "elapsed_time": "9:07:11", "remaining_time": "8:51:30"}
{"current_steps": 2100, "total_steps": 4130, "loss": 0.2911, "lr": 2.2905605938600685e-05, "epoch": 3.559322033898305, "percentage": 50.85, "elapsed_time": "9:08:26", "remaining_time": "8:50:09"}
{"current_steps": 2105, "total_steps": 4130, "loss": 0.2634, "lr": 2.2821957373006617e-05, "epoch": 3.5677966101694913, "percentage": 50.97, "elapsed_time": "9:09:46", "remaining_time": "8:48:52"}
{"current_steps": 2110, "total_steps": 4130, "loss": 0.2958, "lr": 2.273825841044156e-05, "epoch": 3.576271186440678, "percentage": 51.09, "elapsed_time": "9:11:04", "remaining_time": "8:47:34"}
{"current_steps": 2115, "total_steps": 4130, "loss": 0.2788, "lr": 2.2654510545674442e-05, "epoch": 3.584745762711864, "percentage": 51.21, "elapsed_time": "9:12:20", "remaining_time": "8:46:13"}
{"current_steps": 2120, "total_steps": 4130, "loss": 0.2984, "lr": 2.257071527434753e-05, "epoch": 3.593220338983051, "percentage": 51.33, "elapsed_time": "9:13:33", "remaining_time": "8:44:50"}
{"current_steps": 2125, "total_steps": 4130, "loss": 0.2826, "lr": 2.2486874092949708e-05, "epoch": 3.601694915254237, "percentage": 51.45, "elapsed_time": "9:14:54", "remaining_time": "8:43:33"}
{"current_steps": 2130, "total_steps": 4130, "loss": 0.2928, "lr": 2.2402988498789767e-05, "epoch": 3.610169491525424, "percentage": 51.57, "elapsed_time": "9:16:14", "remaining_time": "8:42:17"}
{"current_steps": 2135, "total_steps": 4130, "loss": 0.2946, "lr": 2.2319059989969668e-05, "epoch": 3.6186440677966103, "percentage": 51.69, "elapsed_time": "9:17:34", "remaining_time": "8:41:00"}
{"current_steps": 2140, "total_steps": 4130, "loss": 0.296, "lr": 2.2235090065357773e-05, "epoch": 3.6271186440677967, "percentage": 51.82, "elapsed_time": "9:18:52", "remaining_time": "8:39:41"}
{"current_steps": 2145, "total_steps": 4130, "loss": 0.3039, "lr": 2.215108022456208e-05, "epoch": 3.635593220338983, "percentage": 51.94, "elapsed_time": "9:20:10", "remaining_time": "8:38:23"}
{"current_steps": 2150, "total_steps": 4130, "loss": 0.2561, "lr": 2.2067031967903443e-05, "epoch": 3.6440677966101696, "percentage": 52.06, "elapsed_time": "9:21:30", "remaining_time": "8:37:06"}
{"current_steps": 2155, "total_steps": 4130, "loss": 0.3076, "lr": 2.1982946796388788e-05, "epoch": 3.652542372881356, "percentage": 52.18, "elapsed_time": "9:22:43", "remaining_time": "8:35:43"}
{"current_steps": 2160, "total_steps": 4130, "loss": 0.2756, "lr": 2.1898826211684297e-05, "epoch": 3.6610169491525424, "percentage": 52.3, "elapsed_time": "9:23:58", "remaining_time": "8:34:21"}
{"current_steps": 2165, "total_steps": 4130, "loss": 0.3082, "lr": 2.1814671716088593e-05, "epoch": 3.669491525423729, "percentage": 52.42, "elapsed_time": "9:25:14", "remaining_time": "8:33:01"}
{"current_steps": 2170, "total_steps": 4130, "loss": 0.294, "lr": 2.17304848125059e-05, "epoch": 3.6779661016949152, "percentage": 52.54, "elapsed_time": "9:26:31", "remaining_time": "8:31:41"}
{"current_steps": 2175, "total_steps": 4130, "loss": 0.2758, "lr": 2.1646267004419218e-05, "epoch": 3.6864406779661016, "percentage": 52.66, "elapsed_time": "9:27:51", "remaining_time": "8:30:25"}
{"current_steps": 2180, "total_steps": 4130, "loss": 0.2974, "lr": 2.1562019795863463e-05, "epoch": 3.694915254237288, "percentage": 52.78, "elapsed_time": "9:29:10", "remaining_time": "8:29:07"}
{"current_steps": 2185, "total_steps": 4130, "loss": 0.2534, "lr": 2.147774469139863e-05, "epoch": 3.7033898305084745, "percentage": 52.91, "elapsed_time": "9:30:30", "remaining_time": "8:27:50"}
{"current_steps": 2190, "total_steps": 4130, "loss": 0.2851, "lr": 2.1393443196082867e-05, "epoch": 3.711864406779661, "percentage": 53.03, "elapsed_time": "9:31:46", "remaining_time": "8:26:29"}
{"current_steps": 2195, "total_steps": 4130, "loss": 0.2772, "lr": 2.1309116815445665e-05, "epoch": 3.7203389830508473, "percentage": 53.15, "elapsed_time": "9:32:59", "remaining_time": "8:25:07"}
{"current_steps": 2200, "total_steps": 4130, "loss": 0.2984, "lr": 2.1224767055460922e-05, "epoch": 3.7288135593220337, "percentage": 53.27, "elapsed_time": "9:34:20", "remaining_time": "8:23:51"}
{"current_steps": 2205, "total_steps": 4130, "loss": 0.3004, "lr": 2.114039542252008e-05, "epoch": 3.7372881355932206, "percentage": 53.39, "elapsed_time": "9:35:40", "remaining_time": "8:22:34"}
{"current_steps": 2210, "total_steps": 4130, "loss": 0.3037, "lr": 2.1056003423405178e-05, "epoch": 3.7457627118644066, "percentage": 53.51, "elapsed_time": "9:37:00", "remaining_time": "8:21:17"}
{"current_steps": 2215, "total_steps": 4130, "loss": 0.2938, "lr": 2.0971592565262005e-05, "epoch": 3.7542372881355934, "percentage": 53.63, "elapsed_time": "9:38:17", "remaining_time": "8:19:58"}
{"current_steps": 2220, "total_steps": 4130, "loss": 0.2809, "lr": 2.088716435557313e-05, "epoch": 3.7627118644067794, "percentage": 53.75, "elapsed_time": "9:39:36", "remaining_time": "8:18:40"}
{"current_steps": 2225, "total_steps": 4130, "loss": 0.3082, "lr": 2.0802720302131016e-05, "epoch": 3.7711864406779663, "percentage": 53.87, "elapsed_time": "9:40:57", "remaining_time": "8:17:23"}
{"current_steps": 2230, "total_steps": 4130, "loss": 0.2891, "lr": 2.0718261913011055e-05, "epoch": 3.7796610169491527, "percentage": 54.0, "elapsed_time": "9:42:17", "remaining_time": "8:16:07"}
{"current_steps": 2235, "total_steps": 4130, "loss": 0.2434, "lr": 2.063379069654468e-05, "epoch": 3.788135593220339, "percentage": 54.12, "elapsed_time": "9:43:32", "remaining_time": "8:14:46"}
{"current_steps": 2240, "total_steps": 4130, "loss": 0.3023, "lr": 2.0549308161292405e-05, "epoch": 3.7966101694915255, "percentage": 54.24, "elapsed_time": "9:44:47", "remaining_time": "8:13:24"}
{"current_steps": 2245, "total_steps": 4130, "loss": 0.2698, "lr": 2.0464815816016866e-05, "epoch": 3.805084745762712, "percentage": 54.36, "elapsed_time": "9:46:04", "remaining_time": "8:12:05"}
{"current_steps": 2250, "total_steps": 4130, "loss": 0.3099, "lr": 2.0380315169655905e-05, "epoch": 3.8135593220338984, "percentage": 54.48, "elapsed_time": "9:47:23", "remaining_time": "8:10:48"}
{"current_steps": 2255, "total_steps": 4130, "loss": 0.2861, "lr": 2.0295807731295628e-05, "epoch": 3.8220338983050848, "percentage": 54.6, "elapsed_time": "9:48:40", "remaining_time": "8:09:28"}
{"current_steps": 2260, "total_steps": 4130, "loss": 0.2637, "lr": 2.021129501014342e-05, "epoch": 3.830508474576271, "percentage": 54.72, "elapsed_time": "9:50:00", "remaining_time": "8:08:11"}
{"current_steps": 2265, "total_steps": 4130, "loss": 0.2859, "lr": 2.0126778515501e-05, "epoch": 3.8389830508474576, "percentage": 54.84, "elapsed_time": "9:51:19", "remaining_time": "8:06:53"}
{"current_steps": 2270, "total_steps": 4130, "loss": 0.3067, "lr": 2.0042259756737508e-05, "epoch": 3.847457627118644, "percentage": 54.96, "elapsed_time": "9:52:36", "remaining_time": "8:05:34"}
{"current_steps": 2275, "total_steps": 4130, "loss": 0.2925, "lr": 1.99577402432625e-05, "epoch": 3.8559322033898304, "percentage": 55.08, "elapsed_time": "9:53:54", "remaining_time": "8:04:16"}
{"current_steps": 2280, "total_steps": 4130, "loss": 0.2674, "lr": 1.9873221484499006e-05, "epoch": 3.864406779661017, "percentage": 55.21, "elapsed_time": "9:55:12", "remaining_time": "8:02:57"}
{"current_steps": 2285, "total_steps": 4130, "loss": 0.2946, "lr": 1.978870498985659e-05, "epoch": 3.8728813559322033, "percentage": 55.33, "elapsed_time": "9:56:29", "remaining_time": "8:01:37"}
{"current_steps": 2290, "total_steps": 4130, "loss": 0.2703, "lr": 1.9704192268704372e-05, "epoch": 3.8813559322033897, "percentage": 55.45, "elapsed_time": "9:57:48", "remaining_time": "8:00:20"}
{"current_steps": 2295, "total_steps": 4130, "loss": 0.2871, "lr": 1.96196848303441e-05, "epoch": 3.889830508474576, "percentage": 55.57, "elapsed_time": "9:59:03", "remaining_time": "7:58:59"}
{"current_steps": 2300, "total_steps": 4130, "loss": 0.2751, "lr": 1.953518418398314e-05, "epoch": 3.898305084745763, "percentage": 55.69, "elapsed_time": "10:00:23", "remaining_time": "7:57:42"}
{"current_steps": 2305, "total_steps": 4130, "loss": 0.284, "lr": 1.94506918387076e-05, "epoch": 3.906779661016949, "percentage": 55.81, "elapsed_time": "10:01:43", "remaining_time": "7:56:25"}
{"current_steps": 2310, "total_steps": 4130, "loss": 0.2901, "lr": 1.9366209303455322e-05, "epoch": 3.915254237288136, "percentage": 55.93, "elapsed_time": "10:03:01", "remaining_time": "7:55:06"}
{"current_steps": 2315, "total_steps": 4130, "loss": 0.2884, "lr": 1.928173808698895e-05, "epoch": 3.923728813559322, "percentage": 56.05, "elapsed_time": "10:04:17", "remaining_time": "7:53:46"}
{"current_steps": 2320, "total_steps": 4130, "loss": 0.2848, "lr": 1.919727969786899e-05, "epoch": 3.9322033898305087, "percentage": 56.17, "elapsed_time": "10:05:38", "remaining_time": "7:52:30"}
{"current_steps": 2325, "total_steps": 4130, "loss": 0.2735, "lr": 1.911283564442687e-05, "epoch": 3.940677966101695, "percentage": 56.3, "elapsed_time": "10:06:56", "remaining_time": "7:51:11"}
{"current_steps": 2330, "total_steps": 4130, "loss": 0.2789, "lr": 1.9028407434737998e-05, "epoch": 3.9491525423728815, "percentage": 56.42, "elapsed_time": "10:08:14", "remaining_time": "7:49:53"}
{"current_steps": 2335, "total_steps": 4130, "loss": 0.2846, "lr": 1.894399657659483e-05, "epoch": 3.957627118644068, "percentage": 56.54, "elapsed_time": "10:09:32", "remaining_time": "7:48:34"}
{"current_steps": 2340, "total_steps": 4130, "loss": 0.2699, "lr": 1.8859604577479927e-05, "epoch": 3.9661016949152543, "percentage": 56.66, "elapsed_time": "10:10:50", "remaining_time": "7:47:16"}
{"current_steps": 2345, "total_steps": 4130, "loss": 0.2759, "lr": 1.877523294453908e-05, "epoch": 3.9745762711864407, "percentage": 56.78, "elapsed_time": "10:12:07", "remaining_time": "7:45:56"}
{"current_steps": 2350, "total_steps": 4130, "loss": 0.284, "lr": 1.869088318455434e-05, "epoch": 3.983050847457627, "percentage": 56.9, "elapsed_time": "10:13:27", "remaining_time": "7:44:39"}
{"current_steps": 2355, "total_steps": 4130, "loss": 0.2346, "lr": 1.8606556803917136e-05, "epoch": 3.9915254237288136, "percentage": 57.02, "elapsed_time": "10:14:43", "remaining_time": "7:43:19"}
{"current_steps": 2360, "total_steps": 4130, "loss": 0.2733, "lr": 1.8522255308601378e-05, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "10:15:59", "remaining_time": "7:41:59"}
{"current_steps": 2365, "total_steps": 4130, "loss": 0.2855, "lr": 1.8437980204136537e-05, "epoch": 4.008474576271187, "percentage": 57.26, "elapsed_time": "10:17:15", "remaining_time": "7:40:39"}
{"current_steps": 2370, "total_steps": 4130, "loss": 0.248, "lr": 1.8353732995580786e-05, "epoch": 4.016949152542373, "percentage": 57.38, "elapsed_time": "10:18:35", "remaining_time": "7:39:22"}
{"current_steps": 2375, "total_steps": 4130, "loss": 0.2807, "lr": 1.826951518749411e-05, "epoch": 4.02542372881356, "percentage": 57.51, "elapsed_time": "10:19:53", "remaining_time": "7:38:03"}
{"current_steps": 2380, "total_steps": 4130, "loss": 0.2649, "lr": 1.8185328283911417e-05, "epoch": 4.033898305084746, "percentage": 57.63, "elapsed_time": "10:21:13", "remaining_time": "7:36:46"}
{"current_steps": 2385, "total_steps": 4130, "loss": 0.3013, "lr": 1.8101173788315707e-05, "epoch": 4.0423728813559325, "percentage": 57.75, "elapsed_time": "10:22:30", "remaining_time": "7:35:27"}
{"current_steps": 2390, "total_steps": 4130, "loss": 0.2583, "lr": 1.8017053203611215e-05, "epoch": 4.0508474576271185, "percentage": 57.87, "elapsed_time": "10:23:49", "remaining_time": "7:34:09"}
{"current_steps": 2395, "total_steps": 4130, "loss": 0.2779, "lr": 1.7932968032096564e-05, "epoch": 4.059322033898305, "percentage": 57.99, "elapsed_time": "10:25:06", "remaining_time": "7:32:50"}
{"current_steps": 2400, "total_steps": 4130, "loss": 0.2679, "lr": 1.7848919775437924e-05, "epoch": 4.067796610169491, "percentage": 58.11, "elapsed_time": "10:26:17", "remaining_time": "7:31:27"}
{"current_steps": 2405, "total_steps": 4130, "loss": 0.2886, "lr": 1.776490993464223e-05, "epoch": 4.076271186440678, "percentage": 58.23, "elapsed_time": "10:27:38", "remaining_time": "7:30:10"}
{"current_steps": 2410, "total_steps": 4130, "loss": 0.2592, "lr": 1.768094001003033e-05, "epoch": 4.084745762711864, "percentage": 58.35, "elapsed_time": "10:28:56", "remaining_time": "7:28:52"}
{"current_steps": 2415, "total_steps": 4130, "loss": 0.2474, "lr": 1.759701150121024e-05, "epoch": 4.093220338983051, "percentage": 58.47, "elapsed_time": "10:30:12", "remaining_time": "7:27:32"}
{"current_steps": 2420, "total_steps": 4130, "loss": 0.2916, "lr": 1.7513125907050302e-05, "epoch": 4.101694915254237, "percentage": 58.6, "elapsed_time": "10:31:28", "remaining_time": "7:26:12"}
{"current_steps": 2425, "total_steps": 4130, "loss": 0.2718, "lr": 1.742928472565248e-05, "epoch": 4.110169491525424, "percentage": 58.72, "elapsed_time": "10:32:43", "remaining_time": "7:24:51"}
{"current_steps": 2430, "total_steps": 4130, "loss": 0.2717, "lr": 1.7345489454325564e-05, "epoch": 4.11864406779661, "percentage": 58.84, "elapsed_time": "10:34:00", "remaining_time": "7:23:32"}
{"current_steps": 2435, "total_steps": 4130, "loss": 0.2892, "lr": 1.7261741589558448e-05, "epoch": 4.127118644067797, "percentage": 58.96, "elapsed_time": "10:35:19", "remaining_time": "7:22:14"}
{"current_steps": 2440, "total_steps": 4130, "loss": 0.273, "lr": 1.717804262699339e-05, "epoch": 4.135593220338983, "percentage": 59.08, "elapsed_time": "10:36:39", "remaining_time": "7:20:58"}
{"current_steps": 2445, "total_steps": 4130, "loss": 0.2589, "lr": 1.7094394061399318e-05, "epoch": 4.1440677966101696, "percentage": 59.2, "elapsed_time": "10:37:57", "remaining_time": "7:19:39"}
{"current_steps": 2450, "total_steps": 4130, "loss": 0.2622, "lr": 1.701079738664512e-05, "epoch": 4.1525423728813555, "percentage": 59.32, "elapsed_time": "10:39:13", "remaining_time": "7:18:19"}
{"current_steps": 2455, "total_steps": 4130, "loss": 0.266, "lr": 1.6927254095672992e-05, "epoch": 4.161016949152542, "percentage": 59.44, "elapsed_time": "10:40:31", "remaining_time": "7:17:01"}
{"current_steps": 2460, "total_steps": 4130, "loss": 0.2761, "lr": 1.6843765680471715e-05, "epoch": 4.169491525423728, "percentage": 59.56, "elapsed_time": "10:41:48", "remaining_time": "7:15:41"}
{"current_steps": 2465, "total_steps": 4130, "loss": 0.2851, "lr": 1.6760333632050086e-05, "epoch": 4.177966101694915, "percentage": 59.69, "elapsed_time": "10:43:06", "remaining_time": "7:14:23"}
{"current_steps": 2470, "total_steps": 4130, "loss": 0.2744, "lr": 1.667695944041025e-05, "epoch": 4.186440677966102, "percentage": 59.81, "elapsed_time": "10:44:26", "remaining_time": "7:13:06"}
{"current_steps": 2475, "total_steps": 4130, "loss": 0.301, "lr": 1.6593644594521082e-05, "epoch": 4.194915254237288, "percentage": 59.93, "elapsed_time": "10:45:44", "remaining_time": "7:11:47"}
{"current_steps": 2480, "total_steps": 4130, "loss": 0.2627, "lr": 1.6510390582291624e-05, "epoch": 4.203389830508475, "percentage": 60.05, "elapsed_time": "10:47:03", "remaining_time": "7:10:30"}
{"current_steps": 2485, "total_steps": 4130, "loss": 0.27, "lr": 1.6427198890544483e-05, "epoch": 4.211864406779661, "percentage": 60.17, "elapsed_time": "10:48:23", "remaining_time": "7:09:13"}
{"current_steps": 2490, "total_steps": 4130, "loss": 0.2656, "lr": 1.634407100498931e-05, "epoch": 4.220338983050848, "percentage": 60.29, "elapsed_time": "10:49:37", "remaining_time": "7:07:51"}
{"current_steps": 2495, "total_steps": 4130, "loss": 0.2649, "lr": 1.626100841019623e-05, "epoch": 4.228813559322034, "percentage": 60.41, "elapsed_time": "10:50:56", "remaining_time": "7:06:34"}
{"current_steps": 2500, "total_steps": 4130, "loss": 0.29, "lr": 1.6178012589569358e-05, "epoch": 4.237288135593221, "percentage": 60.53, "elapsed_time": "10:52:14", "remaining_time": "7:05:15"}
{"current_steps": 2505, "total_steps": 4130, "loss": 0.2792, "lr": 1.60950850253203e-05, "epoch": 4.245762711864407, "percentage": 60.65, "elapsed_time": "10:53:32", "remaining_time": "7:03:57"}
{"current_steps": 2510, "total_steps": 4130, "loss": 0.2614, "lr": 1.601222719844168e-05, "epoch": 4.254237288135593, "percentage": 60.77, "elapsed_time": "10:54:50", "remaining_time": "7:02:39"}
{"current_steps": 2515, "total_steps": 4130, "loss": 0.2405, "lr": 1.5929440588680688e-05, "epoch": 4.262711864406779, "percentage": 60.9, "elapsed_time": "10:56:08", "remaining_time": "7:01:20"}
{"current_steps": 2520, "total_steps": 4130, "loss": 0.2487, "lr": 1.5846726674512654e-05, "epoch": 4.271186440677966, "percentage": 61.02, "elapsed_time": "10:57:23", "remaining_time": "7:00:00"}
{"current_steps": 2525, "total_steps": 4130, "loss": 0.269, "lr": 1.576408693311466e-05, "epoch": 4.279661016949152, "percentage": 61.14, "elapsed_time": "10:58:42", "remaining_time": "6:58:42"}
{"current_steps": 2530, "total_steps": 4130, "loss": 0.2741, "lr": 1.5681522840339143e-05, "epoch": 4.288135593220339, "percentage": 61.26, "elapsed_time": "11:00:00", "remaining_time": "6:57:23"}
{"current_steps": 2535, "total_steps": 4130, "loss": 0.2872, "lr": 1.5599035870687515e-05, "epoch": 4.296610169491525, "percentage": 61.38, "elapsed_time": "11:01:18", "remaining_time": "6:56:05"}
{"current_steps": 2540, "total_steps": 4130, "loss": 0.2769, "lr": 1.5516627497283882e-05, "epoch": 4.305084745762712, "percentage": 61.5, "elapsed_time": "11:02:38", "remaining_time": "6:54:48"}
{"current_steps": 2545, "total_steps": 4130, "loss": 0.2819, "lr": 1.5434299191848713e-05, "epoch": 4.313559322033898, "percentage": 61.62, "elapsed_time": "11:03:58", "remaining_time": "6:53:31"}
{"current_steps": 2550, "total_steps": 4130, "loss": 0.2662, "lr": 1.5352052424672535e-05, "epoch": 4.322033898305085, "percentage": 61.74, "elapsed_time": "11:05:15", "remaining_time": "6:52:11"}
{"current_steps": 2555, "total_steps": 4130, "loss": 0.2604, "lr": 1.5269888664589712e-05, "epoch": 4.330508474576272, "percentage": 61.86, "elapsed_time": "11:06:32", "remaining_time": "6:50:52"}
{"current_steps": 2560, "total_steps": 4130, "loss": 0.2572, "lr": 1.5187809378952182e-05, "epoch": 4.338983050847458, "percentage": 61.99, "elapsed_time": "11:07:43", "remaining_time": "6:49:30"}
{"current_steps": 2565, "total_steps": 4130, "loss": 0.2446, "lr": 1.5105816033603266e-05, "epoch": 4.3474576271186445, "percentage": 62.11, "elapsed_time": "11:08:59", "remaining_time": "6:48:10"}
{"current_steps": 2570, "total_steps": 4130, "loss": 0.2713, "lr": 1.5023910092851509e-05, "epoch": 4.3559322033898304, "percentage": 62.23, "elapsed_time": "11:10:17", "remaining_time": "6:46:52"}
{"current_steps": 2575, "total_steps": 4130, "loss": 0.2729, "lr": 1.4942093019444468e-05, "epoch": 4.364406779661017, "percentage": 62.35, "elapsed_time": "11:11:37", "remaining_time": "6:45:35"}
{"current_steps": 2580, "total_steps": 4130, "loss": 0.2594, "lr": 1.4860366274542663e-05, "epoch": 4.372881355932203, "percentage": 62.47, "elapsed_time": "11:12:54", "remaining_time": "6:44:15"}
{"current_steps": 2585, "total_steps": 4130, "loss": 0.249, "lr": 1.4778731317693442e-05, "epoch": 4.38135593220339, "percentage": 62.59, "elapsed_time": "11:14:13", "remaining_time": "6:42:58"}
{"current_steps": 2590, "total_steps": 4130, "loss": 0.2504, "lr": 1.4697189606804914e-05, "epoch": 4.389830508474576, "percentage": 62.71, "elapsed_time": "11:15:33", "remaining_time": "6:41:41"}
{"current_steps": 2595, "total_steps": 4130, "loss": 0.2638, "lr": 1.4615742598119927e-05, "epoch": 4.398305084745763, "percentage": 62.83, "elapsed_time": "11:16:52", "remaining_time": "6:40:22"}
{"current_steps": 2600, "total_steps": 4130, "loss": 0.2781, "lr": 1.4534391746190056e-05, "epoch": 4.406779661016949, "percentage": 62.95, "elapsed_time": "11:18:09", "remaining_time": "6:39:04"}
{"current_steps": 2605, "total_steps": 4130, "loss": 0.3089, "lr": 1.4453138503849622e-05, "epoch": 4.415254237288136, "percentage": 63.08, "elapsed_time": "11:19:26", "remaining_time": "6:37:45"}
{"current_steps": 2610, "total_steps": 4130, "loss": 0.266, "lr": 1.4371984322189754e-05, "epoch": 4.423728813559322, "percentage": 63.2, "elapsed_time": "11:20:44", "remaining_time": "6:36:26"}
{"current_steps": 2615, "total_steps": 4130, "loss": 0.2693, "lr": 1.4290930650532448e-05, "epoch": 4.432203389830509, "percentage": 63.32, "elapsed_time": "11:22:03", "remaining_time": "6:35:08"}
{"current_steps": 2620, "total_steps": 4130, "loss": 0.2896, "lr": 1.4209978936404731e-05, "epoch": 4.440677966101695, "percentage": 63.44, "elapsed_time": "11:23:23", "remaining_time": "6:33:51"}
{"current_steps": 2625, "total_steps": 4130, "loss": 0.2989, "lr": 1.4129130625512776e-05, "epoch": 4.4491525423728815, "percentage": 63.56, "elapsed_time": "11:24:44", "remaining_time": "6:32:35"}
{"current_steps": 2630, "total_steps": 4130, "loss": 0.2752, "lr": 1.4048387161716086e-05, "epoch": 4.4576271186440675, "percentage": 63.68, "elapsed_time": "11:26:05", "remaining_time": "6:31:18"}
{"current_steps": 2635, "total_steps": 4130, "loss": 0.2661, "lr": 1.3967749987001717e-05, "epoch": 4.466101694915254, "percentage": 63.8, "elapsed_time": "11:27:25", "remaining_time": "6:30:01"}
{"current_steps": 2640, "total_steps": 4130, "loss": 0.2741, "lr": 1.3887220541458521e-05, "epoch": 4.47457627118644, "percentage": 63.92, "elapsed_time": "11:28:45", "remaining_time": "6:28:43"}
{"current_steps": 2645, "total_steps": 4130, "loss": 0.2373, "lr": 1.380680026325143e-05, "epoch": 4.483050847457627, "percentage": 64.04, "elapsed_time": "11:29:59", "remaining_time": "6:27:23"}
{"current_steps": 2650, "total_steps": 4130, "loss": 0.2693, "lr": 1.3726490588595776e-05, "epoch": 4.491525423728813, "percentage": 64.16, "elapsed_time": "11:31:16", "remaining_time": "6:26:04"}
{"current_steps": 2655, "total_steps": 4130, "loss": 0.2637, "lr": 1.3646292951731615e-05, "epoch": 4.5, "percentage": 64.29, "elapsed_time": "11:32:36", "remaining_time": "6:24:46"}
{"current_steps": 2660, "total_steps": 4130, "loss": 0.2708, "lr": 1.3566208784898157e-05, "epoch": 4.508474576271187, "percentage": 64.41, "elapsed_time": "11:33:56", "remaining_time": "6:23:29"}
{"current_steps": 2665, "total_steps": 4130, "loss": 0.2614, "lr": 1.348623951830816e-05, "epoch": 4.516949152542373, "percentage": 64.53, "elapsed_time": "11:35:16", "remaining_time": "6:22:12"}
{"current_steps": 2670, "total_steps": 4130, "loss": 0.2893, "lr": 1.3406386580122389e-05, "epoch": 4.52542372881356, "percentage": 64.65, "elapsed_time": "11:36:34", "remaining_time": "6:20:54"}
{"current_steps": 2675, "total_steps": 4130, "loss": 0.2752, "lr": 1.332665139642412e-05, "epoch": 4.533898305084746, "percentage": 64.77, "elapsed_time": "11:37:55", "remaining_time": "6:19:37"}
{"current_steps": 2680, "total_steps": 4130, "loss": 0.269, "lr": 1.3247035391193664e-05, "epoch": 4.5423728813559325, "percentage": 64.89, "elapsed_time": "11:39:12", "remaining_time": "6:18:18"}
{"current_steps": 2685, "total_steps": 4130, "loss": 0.2426, "lr": 1.3167539986282938e-05, "epoch": 4.5508474576271185, "percentage": 65.01, "elapsed_time": "11:40:28", "remaining_time": "6:16:58"}
{"current_steps": 2690, "total_steps": 4130, "loss": 0.2769, "lr": 1.3088166601390087e-05, "epoch": 4.559322033898305, "percentage": 65.13, "elapsed_time": "11:41:47", "remaining_time": "6:15:40"}
{"current_steps": 2695, "total_steps": 4130, "loss": 0.3127, "lr": 1.3008916654034085e-05, "epoch": 4.567796610169491, "percentage": 65.25, "elapsed_time": "11:43:04", "remaining_time": "6:14:21"}
{"current_steps": 2700, "total_steps": 4130, "loss": 0.2956, "lr": 1.2929791559529484e-05, "epoch": 4.576271186440678, "percentage": 65.38, "elapsed_time": "11:44:25", "remaining_time": "6:13:04"}
{"current_steps": 2705, "total_steps": 4130, "loss": 0.2884, "lr": 1.2850792730961082e-05, "epoch": 4.584745762711864, "percentage": 65.5, "elapsed_time": "11:45:45", "remaining_time": "6:11:47"}
{"current_steps": 2710, "total_steps": 4130, "loss": 0.2869, "lr": 1.2771921579158728e-05, "epoch": 4.593220338983051, "percentage": 65.62, "elapsed_time": "11:46:57", "remaining_time": "6:10:25"}
{"current_steps": 2715, "total_steps": 4130, "loss": 0.2668, "lr": 1.26931795126721e-05, "epoch": 4.601694915254237, "percentage": 65.74, "elapsed_time": "11:48:13", "remaining_time": "6:09:06"}
{"current_steps": 2720, "total_steps": 4130, "loss": 0.276, "lr": 1.2614567937745554e-05, "epoch": 4.610169491525424, "percentage": 65.86, "elapsed_time": "11:49:33", "remaining_time": "6:07:49"}
{"current_steps": 2725, "total_steps": 4130, "loss": 0.2745, "lr": 1.2536088258293018e-05, "epoch": 4.61864406779661, "percentage": 65.98, "elapsed_time": "11:50:51", "remaining_time": "6:06:31"}
{"current_steps": 2730, "total_steps": 4130, "loss": 0.2664, "lr": 1.2457741875872928e-05, "epoch": 4.627118644067797, "percentage": 66.1, "elapsed_time": "11:52:12", "remaining_time": "6:05:13"}
{"current_steps": 2735, "total_steps": 4130, "loss": 0.2709, "lr": 1.2379530189663156e-05, "epoch": 4.635593220338983, "percentage": 66.22, "elapsed_time": "11:53:31", "remaining_time": "6:03:56"}
{"current_steps": 2740, "total_steps": 4130, "loss": 0.2594, "lr": 1.2301454596436076e-05, "epoch": 4.6440677966101696, "percentage": 66.34, "elapsed_time": "11:54:50", "remaining_time": "6:02:38"}
{"current_steps": 2745, "total_steps": 4130, "loss": 0.2476, "lr": 1.222351649053359e-05, "epoch": 4.652542372881356, "percentage": 66.46, "elapsed_time": "11:56:10", "remaining_time": "6:01:21"}
{"current_steps": 2750, "total_steps": 4130, "loss": 0.2767, "lr": 1.2145717263842228e-05, "epoch": 4.661016949152542, "percentage": 66.59, "elapsed_time": "11:57:30", "remaining_time": "6:00:03"}
{"current_steps": 2755, "total_steps": 4130, "loss": 0.2791, "lr": 1.2068058305768298e-05, "epoch": 4.669491525423728, "percentage": 66.71, "elapsed_time": "11:58:50", "remaining_time": "5:58:45"}
{"current_steps": 2760, "total_steps": 4130, "loss": 0.28, "lr": 1.1990541003213072e-05, "epoch": 4.677966101694915, "percentage": 66.83, "elapsed_time": "12:00:06", "remaining_time": "5:57:26"}
{"current_steps": 2765, "total_steps": 4130, "loss": 0.2634, "lr": 1.1913166740547999e-05, "epoch": 4.686440677966102, "percentage": 66.95, "elapsed_time": "12:01:26", "remaining_time": "5:56:09"}
{"current_steps": 2770, "total_steps": 4130, "loss": 0.2779, "lr": 1.1835936899590017e-05, "epoch": 4.694915254237288, "percentage": 67.07, "elapsed_time": "12:02:45", "remaining_time": "5:54:51"}
{"current_steps": 2775, "total_steps": 4130, "loss": 0.2816, "lr": 1.1758852859576842e-05, "epoch": 4.703389830508475, "percentage": 67.19, "elapsed_time": "12:04:06", "remaining_time": "5:53:34"}
{"current_steps": 2780, "total_steps": 4130, "loss": 0.2716, "lr": 1.1681915997142354e-05, "epoch": 4.711864406779661, "percentage": 67.31, "elapsed_time": "12:05:20", "remaining_time": "5:52:14"}
{"current_steps": 2785, "total_steps": 4130, "loss": 0.2706, "lr": 1.1605127686292009e-05, "epoch": 4.720338983050848, "percentage": 67.43, "elapsed_time": "12:06:40", "remaining_time": "5:50:56"}
{"current_steps": 2790, "total_steps": 4130, "loss": 0.2803, "lr": 1.15284892983783e-05, "epoch": 4.728813559322034, "percentage": 67.55, "elapsed_time": "12:07:59", "remaining_time": "5:49:38"}
{"current_steps": 2795, "total_steps": 4130, "loss": 0.2907, "lr": 1.1452002202076256e-05, "epoch": 4.737288135593221, "percentage": 67.68, "elapsed_time": "12:09:19", "remaining_time": "5:48:21"}
{"current_steps": 2800, "total_steps": 4130, "loss": 0.2662, "lr": 1.1375667763359031e-05, "epoch": 4.745762711864407, "percentage": 67.8, "elapsed_time": "12:10:35", "remaining_time": "5:47:02"}
{"current_steps": 2805, "total_steps": 4130, "loss": 0.2793, "lr": 1.1299487345473457e-05, "epoch": 4.754237288135593, "percentage": 67.92, "elapsed_time": "12:11:56", "remaining_time": "5:45:44"}
{"current_steps": 2810, "total_steps": 4130, "loss": 0.2785, "lr": 1.1223462308915767e-05, "epoch": 4.762711864406779, "percentage": 68.04, "elapsed_time": "12:13:15", "remaining_time": "5:44:26"}
{"current_steps": 2815, "total_steps": 4130, "loss": 0.2935, "lr": 1.1147594011407203e-05, "epoch": 4.771186440677966, "percentage": 68.16, "elapsed_time": "12:14:35", "remaining_time": "5:43:09"}
{"current_steps": 2820, "total_steps": 4130, "loss": 0.2785, "lr": 1.1071883807869886e-05, "epoch": 4.779661016949152, "percentage": 68.28, "elapsed_time": "12:15:54", "remaining_time": "5:41:51"}
{"current_steps": 2825, "total_steps": 4130, "loss": 0.291, "lr": 1.0996333050402503e-05, "epoch": 4.788135593220339, "percentage": 68.4, "elapsed_time": "12:17:14", "remaining_time": "5:40:34"}
{"current_steps": 2830, "total_steps": 4130, "loss": 0.2941, "lr": 1.0920943088256266e-05, "epoch": 4.796610169491525, "percentage": 68.52, "elapsed_time": "12:18:33", "remaining_time": "5:39:15"}
{"current_steps": 2835, "total_steps": 4130, "loss": 0.2702, "lr": 1.0845715267810716e-05, "epoch": 4.805084745762712, "percentage": 68.64, "elapsed_time": "12:19:49", "remaining_time": "5:37:56"}
{"current_steps": 2840, "total_steps": 4130, "loss": 0.2785, "lr": 1.0770650932549768e-05, "epoch": 4.813559322033898, "percentage": 68.77, "elapsed_time": "12:21:07", "remaining_time": "5:36:38"}
{"current_steps": 2845, "total_steps": 4130, "loss": 0.2612, "lr": 1.0695751423037639e-05, "epoch": 4.822033898305085, "percentage": 68.89, "elapsed_time": "12:22:24", "remaining_time": "5:35:19"}
{"current_steps": 2850, "total_steps": 4130, "loss": 0.271, "lr": 1.0621018076894984e-05, "epoch": 4.830508474576272, "percentage": 69.01, "elapsed_time": "12:23:39", "remaining_time": "5:33:59"}
{"current_steps": 2855, "total_steps": 4130, "loss": 0.2955, "lr": 1.0546452228774919e-05, "epoch": 4.838983050847458, "percentage": 69.13, "elapsed_time": "12:24:59", "remaining_time": "5:32:42"}
{"current_steps": 2860, "total_steps": 4130, "loss": 0.2676, "lr": 1.047205521033928e-05, "epoch": 4.847457627118644, "percentage": 69.25, "elapsed_time": "12:26:14", "remaining_time": "5:31:22"}
{"current_steps": 2865, "total_steps": 4130, "loss": 0.2733, "lr": 1.0397828350234765e-05, "epoch": 4.8559322033898304, "percentage": 69.37, "elapsed_time": "12:27:31", "remaining_time": "5:30:03"}
{"current_steps": 2870, "total_steps": 4130, "loss": 0.2686, "lr": 1.032377297406926e-05, "epoch": 4.864406779661017, "percentage": 69.49, "elapsed_time": "12:28:52", "remaining_time": "5:28:46"}
{"current_steps": 2875, "total_steps": 4130, "loss": 0.2786, "lr": 1.0249890404388121e-05, "epoch": 4.872881355932203, "percentage": 69.61, "elapsed_time": "12:30:07", "remaining_time": "5:27:26"}
{"current_steps": 2880, "total_steps": 4130, "loss": 0.2617, "lr": 1.0176181960650595e-05, "epoch": 4.88135593220339, "percentage": 69.73, "elapsed_time": "12:31:27", "remaining_time": "5:26:09"}
{"current_steps": 2885, "total_steps": 4130, "loss": 0.2485, "lr": 1.0102648959206212e-05, "epoch": 4.889830508474576, "percentage": 69.85, "elapsed_time": "12:32:47", "remaining_time": "5:24:51"}
{"current_steps": 2890, "total_steps": 4130, "loss": 0.2661, "lr": 1.0029292713271334e-05, "epoch": 4.898305084745763, "percentage": 69.98, "elapsed_time": "12:34:04", "remaining_time": "5:23:32"}
{"current_steps": 2895, "total_steps": 4130, "loss": 0.3071, "lr": 9.956114532905625e-06, "epoch": 4.906779661016949, "percentage": 70.1, "elapsed_time": "12:35:21", "remaining_time": "5:22:13"}
{"current_steps": 2900, "total_steps": 4130, "loss": 0.2764, "lr": 9.883115724988743e-06, "epoch": 4.915254237288136, "percentage": 70.22, "elapsed_time": "12:36:38", "remaining_time": "5:20:55"}
{"current_steps": 2905, "total_steps": 4130, "loss": 0.2858, "lr": 9.810297593196922e-06, "epoch": 4.923728813559322, "percentage": 70.34, "elapsed_time": "12:37:55", "remaining_time": "5:19:36"}
{"current_steps": 2910, "total_steps": 4130, "loss": 0.2991, "lr": 9.73766143797976e-06, "epoch": 4.932203389830509, "percentage": 70.46, "elapsed_time": "12:39:13", "remaining_time": "5:18:17"}
{"current_steps": 2915, "total_steps": 4130, "loss": 0.2572, "lr": 9.665208556536918e-06, "epoch": 4.940677966101695, "percentage": 70.58, "elapsed_time": "12:40:31", "remaining_time": "5:16:59"}
{"current_steps": 2920, "total_steps": 4130, "loss": 0.2705, "lr": 9.592940242795035e-06, "epoch": 4.9491525423728815, "percentage": 70.7, "elapsed_time": "12:41:50", "remaining_time": "5:15:41"}
{"current_steps": 2925, "total_steps": 4130, "loss": 0.2931, "lr": 9.520857787384548e-06, "epoch": 4.9576271186440675, "percentage": 70.82, "elapsed_time": "12:43:10", "remaining_time": "5:14:24"}
{"current_steps": 2930, "total_steps": 4130, "loss": 0.288, "lr": 9.44896247761669e-06, "epoch": 4.966101694915254, "percentage": 70.94, "elapsed_time": "12:44:29", "remaining_time": "5:13:06"}
{"current_steps": 2935, "total_steps": 4130, "loss": 0.2711, "lr": 9.377255597460469e-06, "epoch": 4.97457627118644, "percentage": 71.07, "elapsed_time": "12:45:47", "remaining_time": "5:11:47"}
{"current_steps": 2940, "total_steps": 4130, "loss": 0.2963, "lr": 9.305738427519782e-06, "epoch": 4.983050847457627, "percentage": 71.19, "elapsed_time": "12:47:06", "remaining_time": "5:10:29"}
{"current_steps": 2945, "total_steps": 4130, "loss": 0.2432, "lr": 9.234412245010482e-06, "epoch": 4.991525423728813, "percentage": 71.31, "elapsed_time": "12:48:25", "remaining_time": "5:09:11"}
{"current_steps": 2950, "total_steps": 4130, "loss": 0.2877, "lr": 9.163278323737635e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "12:49:46", "remaining_time": "5:07:54"}
{"current_steps": 2955, "total_steps": 4130, "loss": 0.2718, "lr": 9.092337934072703e-06, "epoch": 5.008474576271187, "percentage": 71.55, "elapsed_time": "12:51:04", "remaining_time": "5:06:36"}
{"current_steps": 2960, "total_steps": 4130, "loss": 0.2325, "lr": 9.021592342930928e-06, "epoch": 5.016949152542373, "percentage": 71.67, "elapsed_time": "12:52:19", "remaining_time": "5:05:16"}
{"current_steps": 2965, "total_steps": 4130, "loss": 0.2686, "lr": 8.951042813748645e-06, "epoch": 5.02542372881356, "percentage": 71.79, "elapsed_time": "12:53:37", "remaining_time": "5:03:58"}
{"current_steps": 2970, "total_steps": 4130, "loss": 0.2938, "lr": 8.880690606460754e-06, "epoch": 5.033898305084746, "percentage": 71.91, "elapsed_time": "12:54:57", "remaining_time": "5:02:40"}
{"current_steps": 2975, "total_steps": 4130, "loss": 0.2736, "lr": 8.8105369774782e-06, "epoch": 5.0423728813559325, "percentage": 72.03, "elapsed_time": "12:56:17", "remaining_time": "5:01:23"}
{"current_steps": 2980, "total_steps": 4130, "loss": 0.2502, "lr": 8.74058317966556e-06, "epoch": 5.0508474576271185, "percentage": 72.15, "elapsed_time": "12:57:35", "remaining_time": "5:00:04"}
{"current_steps": 2985, "total_steps": 4130, "loss": 0.2536, "lr": 8.670830462318633e-06, "epoch": 5.059322033898305, "percentage": 72.28, "elapsed_time": "12:58:54", "remaining_time": "4:58:46"}
{"current_steps": 2990, "total_steps": 4130, "loss": 0.2721, "lr": 8.60128007114217e-06, "epoch": 5.067796610169491, "percentage": 72.4, "elapsed_time": "13:00:14", "remaining_time": "4:57:28"}
{"current_steps": 2995, "total_steps": 4130, "loss": 0.2402, "lr": 8.531933248227582e-06, "epoch": 5.076271186440678, "percentage": 72.52, "elapsed_time": "13:01:31", "remaining_time": "4:56:10"}
{"current_steps": 3000, "total_steps": 4130, "loss": 0.2775, "lr": 8.462791232030803e-06, "epoch": 5.084745762711864, "percentage": 72.64, "elapsed_time": "13:02:50", "remaining_time": "4:54:52"}
{"current_steps": 3005, "total_steps": 4130, "loss": 0.253, "lr": 8.393855257350132e-06, "epoch": 5.093220338983051, "percentage": 72.76, "elapsed_time": "13:04:49", "remaining_time": "4:53:49"}
{"current_steps": 3010, "total_steps": 4130, "loss": 0.2628, "lr": 8.325126555304208e-06, "epoch": 5.101694915254237, "percentage": 72.88, "elapsed_time": "13:06:07", "remaining_time": "4:52:30"}
{"current_steps": 3015, "total_steps": 4130, "loss": 0.2487, "lr": 8.256606353310003e-06, "epoch": 5.110169491525424, "percentage": 73.0, "elapsed_time": "13:07:26", "remaining_time": "4:51:12"}
{"current_steps": 3020, "total_steps": 4130, "loss": 0.2767, "lr": 8.188295875060943e-06, "epoch": 5.11864406779661, "percentage": 73.12, "elapsed_time": "13:08:46", "remaining_time": "4:49:54"}
{"current_steps": 3025, "total_steps": 4130, "loss": 0.2284, "lr": 8.12019634050499e-06, "epoch": 5.127118644067797, "percentage": 73.24, "elapsed_time": "13:10:00", "remaining_time": "4:48:34"}
{"current_steps": 3030, "total_steps": 4130, "loss": 0.2484, "lr": 8.052308965822916e-06, "epoch": 5.135593220338983, "percentage": 73.37, "elapsed_time": "13:11:20", "remaining_time": "4:47:17"}
{"current_steps": 3035, "total_steps": 4130, "loss": 0.2513, "lr": 7.984634963406537e-06, "epoch": 5.1440677966101696, "percentage": 73.49, "elapsed_time": "13:12:34", "remaining_time": "4:45:57"}
{"current_steps": 3040, "total_steps": 4130, "loss": 0.2862, "lr": 7.917175541837101e-06, "epoch": 5.1525423728813555, "percentage": 73.61, "elapsed_time": "13:13:55", "remaining_time": "4:44:39"}
{"current_steps": 3045, "total_steps": 4130, "loss": 0.29, "lr": 7.849931905863672e-06, "epoch": 5.161016949152542, "percentage": 73.73, "elapsed_time": "13:15:12", "remaining_time": "4:43:20"}
{"current_steps": 3050, "total_steps": 4130, "loss": 0.259, "lr": 7.78290525638163e-06, "epoch": 5.169491525423728, "percentage": 73.85, "elapsed_time": "13:16:29", "remaining_time": "4:42:02"}
{"current_steps": 3055, "total_steps": 4130, "loss": 0.252, "lr": 7.71609679041121e-06, "epoch": 5.177966101694915, "percentage": 73.97, "elapsed_time": "13:17:49", "remaining_time": "4:40:44"}
{"current_steps": 3060, "total_steps": 4130, "loss": 0.264, "lr": 7.649507701076164e-06, "epoch": 5.186440677966102, "percentage": 74.09, "elapsed_time": "13:19:07", "remaining_time": "4:39:26"}
{"current_steps": 3065, "total_steps": 4130, "loss": 0.2651, "lr": 7.583139177582395e-06, "epoch": 5.194915254237288, "percentage": 74.21, "elapsed_time": "13:20:27", "remaining_time": "4:38:08"}
{"current_steps": 3070, "total_steps": 4130, "loss": 0.2671, "lr": 7.516992405196772e-06, "epoch": 5.203389830508475, "percentage": 74.33, "elapsed_time": "13:21:47", "remaining_time": "4:36:50"}
{"current_steps": 3075, "total_steps": 4130, "loss": 0.2698, "lr": 7.45106856522593e-06, "epoch": 5.211864406779661, "percentage": 74.46, "elapsed_time": "13:23:07", "remaining_time": "4:35:32"}
{"current_steps": 3080, "total_steps": 4130, "loss": 0.2312, "lr": 7.385368834995168e-06, "epoch": 5.220338983050848, "percentage": 74.58, "elapsed_time": "13:24:25", "remaining_time": "4:34:14"}
{"current_steps": 3085, "total_steps": 4130, "loss": 0.2531, "lr": 7.319894387827473e-06, "epoch": 5.228813559322034, "percentage": 74.7, "elapsed_time": "13:25:40", "remaining_time": "4:32:54"}
{"current_steps": 3090, "total_steps": 4130, "loss": 0.2826, "lr": 7.254646393022502e-06, "epoch": 5.237288135593221, "percentage": 74.82, "elapsed_time": "13:26:58", "remaining_time": "4:31:36"}
{"current_steps": 3095, "total_steps": 4130, "loss": 0.2851, "lr": 7.189626015835733e-06, "epoch": 5.245762711864407, "percentage": 74.94, "elapsed_time": "13:28:18", "remaining_time": "4:30:18"}
{"current_steps": 3100, "total_steps": 4130, "loss": 0.2511, "lr": 7.124834417457664e-06, "epoch": 5.254237288135593, "percentage": 75.06, "elapsed_time": "13:29:29", "remaining_time": "4:28:57"}
{"current_steps": 3105, "total_steps": 4130, "loss": 0.2538, "lr": 7.060272754993051e-06, "epoch": 5.262711864406779, "percentage": 75.18, "elapsed_time": "13:30:45", "remaining_time": "4:27:38"}
{"current_steps": 3110, "total_steps": 4130, "loss": 0.2703, "lr": 6.9959421814402494e-06, "epoch": 5.271186440677966, "percentage": 75.3, "elapsed_time": "13:32:04", "remaining_time": "4:26:20"}
{"current_steps": 3115, "total_steps": 4130, "loss": 0.2802, "lr": 6.931843845670647e-06, "epoch": 5.279661016949152, "percentage": 75.42, "elapsed_time": "13:33:19", "remaining_time": "4:25:01"}
{"current_steps": 3120, "total_steps": 4130, "loss": 0.2827, "lr": 6.867978892408101e-06, "epoch": 5.288135593220339, "percentage": 75.54, "elapsed_time": "13:34:38", "remaining_time": "4:23:42"}
{"current_steps": 3125, "total_steps": 4130, "loss": 0.2517, "lr": 6.804348462208548e-06, "epoch": 5.296610169491525, "percentage": 75.67, "elapsed_time": "13:35:55", "remaining_time": "4:22:24"}
{"current_steps": 3130, "total_steps": 4130, "loss": 0.2565, "lr": 6.7409536914395866e-06, "epoch": 5.305084745762712, "percentage": 75.79, "elapsed_time": "13:37:13", "remaining_time": "4:21:05"}
{"current_steps": 3135, "total_steps": 4130, "loss": 0.2706, "lr": 6.677795712260206e-06, "epoch": 5.313559322033898, "percentage": 75.91, "elapsed_time": "13:38:31", "remaining_time": "4:19:47"}
{"current_steps": 3140, "total_steps": 4130, "loss": 0.2646, "lr": 6.6148756526005855e-06, "epoch": 5.322033898305085, "percentage": 76.03, "elapsed_time": "13:39:49", "remaining_time": "4:18:28"}
{"current_steps": 3145, "total_steps": 4130, "loss": 0.2458, "lr": 6.552194636141909e-06, "epoch": 5.330508474576272, "percentage": 76.15, "elapsed_time": "13:41:02", "remaining_time": "4:17:08"}
{"current_steps": 3150, "total_steps": 4130, "loss": 0.2616, "lr": 6.489753782296315e-06, "epoch": 5.338983050847458, "percentage": 76.27, "elapsed_time": "13:42:16", "remaining_time": "4:15:49"}
{"current_steps": 3155, "total_steps": 4130, "loss": 0.2611, "lr": 6.427554206186939e-06, "epoch": 5.3474576271186445, "percentage": 76.39, "elapsed_time": "13:43:36", "remaining_time": "4:14:31"}
{"current_steps": 3160, "total_steps": 4130, "loss": 0.2804, "lr": 6.3655970186279314e-06, "epoch": 5.3559322033898304, "percentage": 76.51, "elapsed_time": "13:44:55", "remaining_time": "4:13:13"}
{"current_steps": 3165, "total_steps": 4130, "loss": 0.2494, "lr": 6.30388332610469e-06, "epoch": 5.364406779661017, "percentage": 76.63, "elapsed_time": "13:46:10", "remaining_time": "4:11:54"}
{"current_steps": 3170, "total_steps": 4130, "loss": 0.2668, "lr": 6.242414230754044e-06, "epoch": 5.372881355932203, "percentage": 76.76, "elapsed_time": "13:47:30", "remaining_time": "4:10:35"}
{"current_steps": 3175, "total_steps": 4130, "loss": 0.2883, "lr": 6.181190830344601e-06, "epoch": 5.38135593220339, "percentage": 76.88, "elapsed_time": "13:48:50", "remaining_time": "4:09:18"}
{"current_steps": 3180, "total_steps": 4130, "loss": 0.2572, "lr": 6.120214218257128e-06, "epoch": 5.389830508474576, "percentage": 77.0, "elapsed_time": "13:50:10", "remaining_time": "4:08:00"}
{"current_steps": 3185, "total_steps": 4130, "loss": 0.2501, "lr": 6.059485483465048e-06, "epoch": 5.398305084745763, "percentage": 77.12, "elapsed_time": "13:51:28", "remaining_time": "4:06:42"}
{"current_steps": 3190, "total_steps": 4130, "loss": 0.2464, "lr": 5.999005710514956e-06, "epoch": 5.406779661016949, "percentage": 77.24, "elapsed_time": "13:52:41", "remaining_time": "4:05:22"}
{"current_steps": 3195, "total_steps": 4130, "loss": 0.2645, "lr": 5.938775979507287e-06, "epoch": 5.415254237288136, "percentage": 77.36, "elapsed_time": "13:53:59", "remaining_time": "4:04:03"}
{"current_steps": 3200, "total_steps": 4130, "loss": 0.2437, "lr": 5.878797366076994e-06, "epoch": 5.423728813559322, "percentage": 77.48, "elapsed_time": "13:55:19", "remaining_time": "4:02:45"}
{"current_steps": 3205, "total_steps": 4130, "loss": 0.2493, "lr": 5.819070941374368e-06, "epoch": 5.432203389830509, "percentage": 77.6, "elapsed_time": "13:56:35", "remaining_time": "4:01:27"}
{"current_steps": 3210, "total_steps": 4130, "loss": 0.2822, "lr": 5.759597772045882e-06, "epoch": 5.440677966101695, "percentage": 77.72, "elapsed_time": "13:57:50", "remaining_time": "4:00:07"}
{"current_steps": 3215, "total_steps": 4130, "loss": 0.2749, "lr": 5.700378920215159e-06, "epoch": 5.4491525423728815, "percentage": 77.85, "elapsed_time": "13:59:06", "remaining_time": "3:58:48"}
{"current_steps": 3220, "total_steps": 4130, "loss": 0.263, "lr": 5.641415443463994e-06, "epoch": 5.4576271186440675, "percentage": 77.97, "elapsed_time": "14:00:26", "remaining_time": "3:57:31"}
{"current_steps": 3225, "total_steps": 4130, "loss": 0.2835, "lr": 5.5827083948134876e-06, "epoch": 5.466101694915254, "percentage": 78.09, "elapsed_time": "14:01:47", "remaining_time": "3:56:13"}
{"current_steps": 3230, "total_steps": 4130, "loss": 0.231, "lr": 5.524258822705202e-06, "epoch": 5.47457627118644, "percentage": 78.21, "elapsed_time": "14:02:59", "remaining_time": "3:54:53"}
{"current_steps": 3235, "total_steps": 4130, "loss": 0.2954, "lr": 5.466067770982482e-06, "epoch": 5.483050847457627, "percentage": 78.33, "elapsed_time": "14:04:15", "remaining_time": "3:53:34"}
{"current_steps": 3240, "total_steps": 4130, "loss": 0.2926, "lr": 5.4081362788717625e-06, "epoch": 5.491525423728813, "percentage": 78.45, "elapsed_time": "14:05:34", "remaining_time": "3:52:16"}
{"current_steps": 3245, "total_steps": 4130, "loss": 0.2708, "lr": 5.350465380964076e-06, "epoch": 5.5, "percentage": 78.57, "elapsed_time": "14:06:52", "remaining_time": "3:50:57"}
{"current_steps": 3250, "total_steps": 4130, "loss": 0.2832, "lr": 5.293056107196488e-06, "epoch": 5.508474576271187, "percentage": 78.69, "elapsed_time": "14:08:11", "remaining_time": "3:49:39"}
{"current_steps": 3255, "total_steps": 4130, "loss": 0.2734, "lr": 5.235909482833797e-06, "epoch": 5.516949152542373, "percentage": 78.81, "elapsed_time": "14:09:28", "remaining_time": "3:48:21"}
{"current_steps": 3260, "total_steps": 4130, "loss": 0.2656, "lr": 5.179026528450146e-06, "epoch": 5.52542372881356, "percentage": 78.93, "elapsed_time": "14:10:43", "remaining_time": "3:47:01"}
{"current_steps": 3265, "total_steps": 4130, "loss": 0.2453, "lr": 5.1224082599108584e-06, "epoch": 5.533898305084746, "percentage": 79.06, "elapsed_time": "14:12:02", "remaining_time": "3:45:43"}
{"current_steps": 3270, "total_steps": 4130, "loss": 0.2778, "lr": 5.066055688354246e-06, "epoch": 5.5423728813559325, "percentage": 79.18, "elapsed_time": "14:13:22", "remaining_time": "3:44:26"}
{"current_steps": 3275, "total_steps": 4130, "loss": 0.2627, "lr": 5.0099698201735855e-06, "epoch": 5.5508474576271185, "percentage": 79.3, "elapsed_time": "14:14:41", "remaining_time": "3:43:07"}
{"current_steps": 3280, "total_steps": 4130, "loss": 0.2614, "lr": 4.954151656999122e-06, "epoch": 5.559322033898305, "percentage": 79.42, "elapsed_time": "14:15:56", "remaining_time": "3:41:48"}
{"current_steps": 3285, "total_steps": 4130, "loss": 0.2586, "lr": 4.898602195680214e-06, "epoch": 5.567796610169491, "percentage": 79.54, "elapsed_time": "14:17:10", "remaining_time": "3:40:29"}
{"current_steps": 3290, "total_steps": 4130, "loss": 0.2595, "lr": 4.843322428267465e-06, "epoch": 5.576271186440678, "percentage": 79.66, "elapsed_time": "14:18:27", "remaining_time": "3:39:10"}
{"current_steps": 3295, "total_steps": 4130, "loss": 0.3024, "lr": 4.788313341995096e-06, "epoch": 5.584745762711864, "percentage": 79.78, "elapsed_time": "14:19:47", "remaining_time": "3:37:53"}
{"current_steps": 3300, "total_steps": 4130, "loss": 0.2738, "lr": 4.733575919263238e-06, "epoch": 5.593220338983051, "percentage": 79.9, "elapsed_time": "14:21:05", "remaining_time": "3:36:34"}
{"current_steps": 3305, "total_steps": 4130, "loss": 0.2778, "lr": 4.679111137620442e-06, "epoch": 5.601694915254237, "percentage": 80.02, "elapsed_time": "14:22:20", "remaining_time": "3:35:15"}
{"current_steps": 3310, "total_steps": 4130, "loss": 0.2771, "lr": 4.624919969746171e-06, "epoch": 5.610169491525424, "percentage": 80.15, "elapsed_time": "14:23:36", "remaining_time": "3:33:56"}
{"current_steps": 3315, "total_steps": 4130, "loss": 0.2915, "lr": 4.571003383433481e-06, "epoch": 5.61864406779661, "percentage": 80.27, "elapsed_time": "14:24:56", "remaining_time": "3:32:38"}
{"current_steps": 3320, "total_steps": 4130, "loss": 0.2775, "lr": 4.517362341571687e-06, "epoch": 5.627118644067797, "percentage": 80.39, "elapsed_time": "14:26:17", "remaining_time": "3:31:21"}
{"current_steps": 3325, "total_steps": 4130, "loss": 0.3019, "lr": 4.463997802129221e-06, "epoch": 5.635593220338983, "percentage": 80.51, "elapsed_time": "14:27:35", "remaining_time": "3:30:02"}
{"current_steps": 3330, "total_steps": 4130, "loss": 0.2666, "lr": 4.410910718136454e-06, "epoch": 5.6440677966101696, "percentage": 80.63, "elapsed_time": "14:28:53", "remaining_time": "3:28:44"}
{"current_steps": 3335, "total_steps": 4130, "loss": 0.2634, "lr": 4.3581020376687566e-06, "epoch": 5.652542372881356, "percentage": 80.75, "elapsed_time": "14:30:09", "remaining_time": "3:27:25"}
{"current_steps": 3340, "total_steps": 4130, "loss": 0.2525, "lr": 4.305572703829495e-06, "epoch": 5.661016949152542, "percentage": 80.87, "elapsed_time": "14:31:27", "remaining_time": "3:26:07"}
{"current_steps": 3345, "total_steps": 4130, "loss": 0.268, "lr": 4.253323654733248e-06, "epoch": 5.669491525423728, "percentage": 80.99, "elapsed_time": "14:32:42", "remaining_time": "3:24:48"}
{"current_steps": 3350, "total_steps": 4130, "loss": 0.2693, "lr": 4.201355823488999e-06, "epoch": 5.677966101694915, "percentage": 81.11, "elapsed_time": "14:34:02", "remaining_time": "3:23:30"}
{"current_steps": 3355, "total_steps": 4130, "loss": 0.252, "lr": 4.149670138183526e-06, "epoch": 5.686440677966102, "percentage": 81.23, "elapsed_time": "14:35:19", "remaining_time": "3:22:12"}
{"current_steps": 3360, "total_steps": 4130, "loss": 0.2404, "lr": 4.098267521864772e-06, "epoch": 5.694915254237288, "percentage": 81.36, "elapsed_time": "14:36:30", "remaining_time": "3:20:52"}
{"current_steps": 3365, "total_steps": 4130, "loss": 0.2303, "lr": 4.047148892525403e-06, "epoch": 5.703389830508475, "percentage": 81.48, "elapsed_time": "14:37:47", "remaining_time": "3:19:33"}
{"current_steps": 3370, "total_steps": 4130, "loss": 0.2597, "lr": 3.996315163086391e-06, "epoch": 5.711864406779661, "percentage": 81.6, "elapsed_time": "14:39:05", "remaining_time": "3:18:15"}
{"current_steps": 3375, "total_steps": 4130, "loss": 0.2911, "lr": 3.945767241380732e-06, "epoch": 5.720338983050848, "percentage": 81.72, "elapsed_time": "14:40:25", "remaining_time": "3:16:57"}
{"current_steps": 3380, "total_steps": 4130, "loss": 0.2489, "lr": 3.895506030137195e-06, "epoch": 5.728813559322034, "percentage": 81.84, "elapsed_time": "14:41:40", "remaining_time": "3:15:38"}
{"current_steps": 3385, "total_steps": 4130, "loss": 0.2523, "lr": 3.845532426964252e-06, "epoch": 5.737288135593221, "percentage": 81.96, "elapsed_time": "14:43:00", "remaining_time": "3:14:20"}
{"current_steps": 3390, "total_steps": 4130, "loss": 0.2838, "lr": 3.79584732433399e-06, "epoch": 5.745762711864407, "percentage": 82.08, "elapsed_time": "14:44:18", "remaining_time": "3:13:02"}
{"current_steps": 3395, "total_steps": 4130, "loss": 0.2682, "lr": 3.746451609566233e-06, "epoch": 5.754237288135593, "percentage": 82.2, "elapsed_time": "14:45:33", "remaining_time": "3:11:43"}
{"current_steps": 3400, "total_steps": 4130, "loss": 0.2436, "lr": 3.697346164812643e-06, "epoch": 5.762711864406779, "percentage": 82.32, "elapsed_time": "14:46:48", "remaining_time": "3:10:24"}
{"current_steps": 3405, "total_steps": 4130, "loss": 0.263, "lr": 3.6485318670409896e-06, "epoch": 5.771186440677966, "percentage": 82.45, "elapsed_time": "14:48:04", "remaining_time": "3:09:05"}
{"current_steps": 3410, "total_steps": 4130, "loss": 0.2997, "lr": 3.6000095880194905e-06, "epoch": 5.779661016949152, "percentage": 82.57, "elapsed_time": "14:49:24", "remaining_time": "3:07:47"}
{"current_steps": 3415, "total_steps": 4130, "loss": 0.2655, "lr": 3.5517801943012443e-06, "epoch": 5.788135593220339, "percentage": 82.69, "elapsed_time": "14:50:44", "remaining_time": "3:06:29"}
{"current_steps": 3420, "total_steps": 4130, "loss": 0.2769, "lr": 3.5038445472087324e-06, "epoch": 5.796610169491525, "percentage": 82.81, "elapsed_time": "14:52:05", "remaining_time": "3:05:11"}
{"current_steps": 3425, "total_steps": 4130, "loss": 0.2603, "lr": 3.456203502818476e-06, "epoch": 5.805084745762712, "percentage": 82.93, "elapsed_time": "14:53:24", "remaining_time": "3:03:53"}
{"current_steps": 3430, "total_steps": 4130, "loss": 0.292, "lr": 3.408857911945702e-06, "epoch": 5.813559322033898, "percentage": 83.05, "elapsed_time": "14:54:44", "remaining_time": "3:02:36"}
{"current_steps": 3435, "total_steps": 4130, "loss": 0.2665, "lr": 3.36180862012919e-06, "epoch": 5.822033898305085, "percentage": 83.17, "elapsed_time": "14:56:04", "remaining_time": "3:01:18"}
{"current_steps": 3440, "total_steps": 4130, "loss": 0.2371, "lr": 3.3150564676161402e-06, "epoch": 5.830508474576272, "percentage": 83.29, "elapsed_time": "14:57:23", "remaining_time": "2:59:59"}
{"current_steps": 3445, "total_steps": 4130, "loss": 0.2585, "lr": 3.268602289347185e-06, "epoch": 5.838983050847458, "percentage": 83.41, "elapsed_time": "14:58:40", "remaining_time": "2:58:41"}
{"current_steps": 3450, "total_steps": 4130, "loss": 0.2765, "lr": 3.222446914941468e-06, "epoch": 5.847457627118644, "percentage": 83.54, "elapsed_time": "15:00:00", "remaining_time": "2:57:23"}
{"current_steps": 3455, "total_steps": 4130, "loss": 0.2596, "lr": 3.176591168681851e-06, "epoch": 5.8559322033898304, "percentage": 83.66, "elapsed_time": "15:01:18", "remaining_time": "2:56:05"}
{"current_steps": 3460, "total_steps": 4130, "loss": 0.2477, "lr": 3.131035869500152e-06, "epoch": 5.864406779661017, "percentage": 83.78, "elapsed_time": "15:02:30", "remaining_time": "2:54:45"}
{"current_steps": 3465, "total_steps": 4130, "loss": 0.2613, "lr": 3.085781830962564e-06, "epoch": 5.872881355932203, "percentage": 83.9, "elapsed_time": "15:03:48", "remaining_time": "2:53:27"}
{"current_steps": 3470, "total_steps": 4130, "loss": 0.2359, "lr": 3.0408298612550878e-06, "epoch": 5.88135593220339, "percentage": 84.02, "elapsed_time": "15:05:06", "remaining_time": "2:52:09"}
{"current_steps": 3475, "total_steps": 4130, "loss": 0.2515, "lr": 2.996180763169132e-06, "epoch": 5.889830508474576, "percentage": 84.14, "elapsed_time": "15:06:21", "remaining_time": "2:50:50"}
{"current_steps": 3480, "total_steps": 4130, "loss": 0.2575, "lr": 2.95183533408715e-06, "epoch": 5.898305084745763, "percentage": 84.26, "elapsed_time": "15:07:39", "remaining_time": "2:49:32"}
{"current_steps": 3485, "total_steps": 4130, "loss": 0.2625, "lr": 2.907794365968413e-06, "epoch": 5.906779661016949, "percentage": 84.38, "elapsed_time": "15:08:58", "remaining_time": "2:48:13"}
{"current_steps": 3490, "total_steps": 4130, "loss": 0.2456, "lr": 2.864058645334853e-06, "epoch": 5.915254237288136, "percentage": 84.5, "elapsed_time": "15:10:17", "remaining_time": "2:46:55"}
{"current_steps": 3495, "total_steps": 4130, "loss": 0.2739, "lr": 2.820628953257052e-06, "epoch": 5.923728813559322, "percentage": 84.62, "elapsed_time": "15:11:37", "remaining_time": "2:45:37"}
{"current_steps": 3500, "total_steps": 4130, "loss": 0.2747, "lr": 2.7775060653402387e-06, "epoch": 5.932203389830509, "percentage": 84.75, "elapsed_time": "15:12:53", "remaining_time": "2:44:19"}
{"current_steps": 3505, "total_steps": 4130, "loss": 0.2957, "lr": 2.7346907517104894e-06, "epoch": 5.940677966101695, "percentage": 84.87, "elapsed_time": "15:14:13", "remaining_time": "2:43:01"}
{"current_steps": 3510, "total_steps": 4130, "loss": 0.2679, "lr": 2.692183777000932e-06, "epoch": 5.9491525423728815, "percentage": 84.99, "elapsed_time": "15:15:34", "remaining_time": "2:41:43"}
{"current_steps": 3515, "total_steps": 4130, "loss": 0.27, "lr": 2.64998590033813e-06, "epoch": 5.9576271186440675, "percentage": 85.11, "elapsed_time": "15:16:52", "remaining_time": "2:40:25"}
{"current_steps": 3520, "total_steps": 4130, "loss": 0.2487, "lr": 2.608097875328488e-06, "epoch": 5.966101694915254, "percentage": 85.23, "elapsed_time": "15:18:12", "remaining_time": "2:39:07"}
{"current_steps": 3525, "total_steps": 4130, "loss": 0.2494, "lr": 2.5665204500448137e-06, "epoch": 5.97457627118644, "percentage": 85.35, "elapsed_time": "15:19:27", "remaining_time": "2:37:48"}
{"current_steps": 3530, "total_steps": 4130, "loss": 0.2695, "lr": 2.525254367012955e-06, "epoch": 5.983050847457627, "percentage": 85.47, "elapsed_time": "15:20:45", "remaining_time": "2:36:30"}
{"current_steps": 3535, "total_steps": 4130, "loss": 0.2968, "lr": 2.4843003631985486e-06, "epoch": 5.991525423728813, "percentage": 85.59, "elapsed_time": "15:22:02", "remaining_time": "2:35:11"}
{"current_steps": 3540, "total_steps": 4130, "loss": 0.2477, "lr": 2.4436591699938305e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "15:23:20", "remaining_time": "2:33:53"}
{"current_steps": 3545, "total_steps": 4130, "loss": 0.2467, "lr": 2.403331513204612e-06, "epoch": 6.008474576271187, "percentage": 85.84, "elapsed_time": "15:24:40", "remaining_time": "2:32:35"}
{"current_steps": 3550, "total_steps": 4130, "loss": 0.2437, "lr": 2.363318113037283e-06, "epoch": 6.016949152542373, "percentage": 85.96, "elapsed_time": "15:25:57", "remaining_time": "2:31:17"}
{"current_steps": 3555, "total_steps": 4130, "loss": 0.2427, "lr": 2.323619684085976e-06, "epoch": 6.02542372881356, "percentage": 86.08, "elapsed_time": "15:27:17", "remaining_time": "2:29:58"}
{"current_steps": 3560, "total_steps": 4130, "loss": 0.2412, "lr": 2.2842369353197858e-06, "epoch": 6.033898305084746, "percentage": 86.2, "elapsed_time": "15:28:34", "remaining_time": "2:28:40"}
{"current_steps": 3565, "total_steps": 4130, "loss": 0.2457, "lr": 2.2451705700701185e-06, "epoch": 6.0423728813559325, "percentage": 86.32, "elapsed_time": "15:29:51", "remaining_time": "2:27:22"}
{"current_steps": 3570, "total_steps": 4130, "loss": 0.2364, "lr": 2.2064212860181258e-06, "epoch": 6.0508474576271185, "percentage": 86.44, "elapsed_time": "15:31:07", "remaining_time": "2:26:03"}
{"current_steps": 3575, "total_steps": 4130, "loss": 0.2462, "lr": 2.1679897751822532e-06, "epoch": 6.059322033898305, "percentage": 86.56, "elapsed_time": "15:32:27", "remaining_time": "2:24:45"}
{"current_steps": 3580, "total_steps": 4130, "loss": 0.2797, "lr": 2.1298767239058684e-06, "epoch": 6.067796610169491, "percentage": 86.68, "elapsed_time": "15:33:45", "remaining_time": "2:23:27"}
{"current_steps": 3585, "total_steps": 4130, "loss": 0.2426, "lr": 2.0920828128450197e-06, "epoch": 6.076271186440678, "percentage": 86.8, "elapsed_time": "15:35:03", "remaining_time": "2:22:09"}
{"current_steps": 3590, "total_steps": 4130, "loss": 0.2509, "lr": 2.054608716956259e-06, "epoch": 6.084745762711864, "percentage": 86.92, "elapsed_time": "15:36:23", "remaining_time": "2:20:50"}
{"current_steps": 3595, "total_steps": 4130, "loss": 0.2423, "lr": 2.0174551054846158e-06, "epoch": 6.093220338983051, "percentage": 87.05, "elapsed_time": "15:37:38", "remaining_time": "2:19:32"}
{"current_steps": 3600, "total_steps": 4130, "loss": 0.286, "lr": 1.9806226419516195e-06, "epoch": 6.101694915254237, "percentage": 87.17, "elapsed_time": "15:38:58", "remaining_time": "2:18:14"}
{"current_steps": 3605, "total_steps": 4130, "loss": 0.2674, "lr": 1.94411198414346e-06, "epoch": 6.110169491525424, "percentage": 87.29, "elapsed_time": "15:40:17", "remaining_time": "2:16:56"}
{"current_steps": 3610, "total_steps": 4130, "loss": 0.2341, "lr": 1.9079237840992416e-06, "epoch": 6.11864406779661, "percentage": 87.41, "elapsed_time": "15:41:36", "remaining_time": "2:15:37"}
{"current_steps": 3615, "total_steps": 4130, "loss": 0.2768, "lr": 1.8720586880993452e-06, "epoch": 6.127118644067797, "percentage": 87.53, "elapsed_time": "15:42:56", "remaining_time": "2:14:20"}
{"current_steps": 3620, "total_steps": 4130, "loss": 0.3004, "lr": 1.8365173366538647e-06, "epoch": 6.135593220338983, "percentage": 87.65, "elapsed_time": "15:44:13", "remaining_time": "2:13:01"}
{"current_steps": 3625, "total_steps": 4130, "loss": 0.2891, "lr": 1.8013003644911987e-06, "epoch": 6.1440677966101696, "percentage": 87.77, "elapsed_time": "15:45:33", "remaining_time": "2:11:43"}
{"current_steps": 3630, "total_steps": 4130, "loss": 0.2599, "lr": 1.7664084005466796e-06, "epoch": 6.1525423728813555, "percentage": 87.89, "elapsed_time": "15:46:52", "remaining_time": "2:10:25"}
{"current_steps": 3635, "total_steps": 4130, "loss": 0.2685, "lr": 1.7318420679513725e-06, "epoch": 6.161016949152542, "percentage": 88.01, "elapsed_time": "15:48:13", "remaining_time": "2:09:07"}
{"current_steps": 3640, "total_steps": 4130, "loss": 0.2503, "lr": 1.6976019840209334e-06, "epoch": 6.169491525423728, "percentage": 88.14, "elapsed_time": "15:49:33", "remaining_time": "2:07:49"}
{"current_steps": 3645, "total_steps": 4130, "loss": 0.2503, "lr": 1.6636887602445839e-06, "epoch": 6.177966101694915, "percentage": 88.26, "elapsed_time": "15:50:50", "remaining_time": "2:06:31"}
{"current_steps": 3650, "total_steps": 4130, "loss": 0.2667, "lr": 1.6301030022741837e-06, "epoch": 6.186440677966102, "percentage": 88.38, "elapsed_time": "15:52:10", "remaining_time": "2:05:13"}
{"current_steps": 3655, "total_steps": 4130, "loss": 0.2781, "lr": 1.596845309913444e-06, "epoch": 6.194915254237288, "percentage": 88.5, "elapsed_time": "15:53:30", "remaining_time": "2:03:55"}
{"current_steps": 3660, "total_steps": 4130, "loss": 0.2598, "lr": 1.5639162771071736e-06, "epoch": 6.203389830508475, "percentage": 88.62, "elapsed_time": "15:54:47", "remaining_time": "2:02:36"}
{"current_steps": 3665, "total_steps": 4130, "loss": 0.2644, "lr": 1.5313164919307033e-06, "epoch": 6.211864406779661, "percentage": 88.74, "elapsed_time": "15:56:04", "remaining_time": "2:01:18"}
{"current_steps": 3670, "total_steps": 4130, "loss": 0.2837, "lr": 1.499046536579374e-06, "epoch": 6.220338983050848, "percentage": 88.86, "elapsed_time": "15:57:25", "remaining_time": "2:00:00"}
{"current_steps": 3675, "total_steps": 4130, "loss": 0.2868, "lr": 1.4671069873581312e-06, "epoch": 6.228813559322034, "percentage": 88.98, "elapsed_time": "15:58:42", "remaining_time": "1:58:41"}
{"current_steps": 3680, "total_steps": 4130, "loss": 0.2643, "lr": 1.4354984146712503e-06, "epoch": 6.237288135593221, "percentage": 89.1, "elapsed_time": "16:00:02", "remaining_time": "1:57:23"}
{"current_steps": 3685, "total_steps": 4130, "loss": 0.2519, "lr": 1.4042213830121344e-06, "epoch": 6.245762711864407, "percentage": 89.23, "elapsed_time": "16:01:19", "remaining_time": "1:56:05"}
{"current_steps": 3690, "total_steps": 4130, "loss": 0.2585, "lr": 1.3732764509532316e-06, "epoch": 6.254237288135593, "percentage": 89.35, "elapsed_time": "16:02:40", "remaining_time": "1:54:47"}
{"current_steps": 3695, "total_steps": 4130, "loss": 0.2557, "lr": 1.3426641711360788e-06, "epoch": 6.262711864406779, "percentage": 89.47, "elapsed_time": "16:04:00", "remaining_time": "1:53:29"}
{"current_steps": 3700, "total_steps": 4130, "loss": 0.2447, "lr": 1.3123850902614143e-06, "epoch": 6.271186440677966, "percentage": 89.59, "elapsed_time": "16:05:17", "remaining_time": "1:52:10"}
{"current_steps": 3705, "total_steps": 4130, "loss": 0.2811, "lr": 1.2824397490794115e-06, "epoch": 6.279661016949152, "percentage": 89.71, "elapsed_time": "16:06:37", "remaining_time": "1:50:52"}
{"current_steps": 3710, "total_steps": 4130, "loss": 0.2507, "lr": 1.2528286823800495e-06, "epoch": 6.288135593220339, "percentage": 89.83, "elapsed_time": "16:07:52", "remaining_time": "1:49:34"}
{"current_steps": 3715, "total_steps": 4130, "loss": 0.2665, "lr": 1.223552418983518e-06, "epoch": 6.296610169491525, "percentage": 89.95, "elapsed_time": "16:09:11", "remaining_time": "1:48:16"}
{"current_steps": 3720, "total_steps": 4130, "loss": 0.2466, "lr": 1.1946114817308207e-06, "epoch": 6.305084745762712, "percentage": 90.07, "elapsed_time": "16:10:31", "remaining_time": "1:46:57"}
{"current_steps": 3725, "total_steps": 4130, "loss": 0.2446, "lr": 1.166006387474401e-06, "epoch": 6.313559322033898, "percentage": 90.19, "elapsed_time": "16:11:49", "remaining_time": "1:45:39"}
{"current_steps": 3730, "total_steps": 4130, "loss": 0.2735, "lr": 1.1377376470689328e-06, "epoch": 6.322033898305085, "percentage": 90.31, "elapsed_time": "16:13:09", "remaining_time": "1:44:21"}
{"current_steps": 3735, "total_steps": 4130, "loss": 0.2554, "lr": 1.1098057653621775e-06, "epoch": 6.330508474576272, "percentage": 90.44, "elapsed_time": "16:14:29", "remaining_time": "1:43:03"}
{"current_steps": 3740, "total_steps": 4130, "loss": 0.2669, "lr": 1.0822112411860042e-06, "epoch": 6.338983050847458, "percentage": 90.56, "elapsed_time": "16:15:48", "remaining_time": "1:41:45"}
{"current_steps": 3745, "total_steps": 4130, "loss": 0.2473, "lr": 1.0549545673474304e-06, "epoch": 6.3474576271186445, "percentage": 90.68, "elapsed_time": "16:17:07", "remaining_time": "1:40:27"}
{"current_steps": 3750, "total_steps": 4130, "loss": 0.2618, "lr": 1.0280362306198732e-06, "epoch": 6.3559322033898304, "percentage": 90.8, "elapsed_time": "16:18:24", "remaining_time": "1:39:08"}
{"current_steps": 3755, "total_steps": 4130, "loss": 0.2702, "lr": 1.0014567117344121e-06, "epoch": 6.364406779661017, "percentage": 90.92, "elapsed_time": "16:19:44", "remaining_time": "1:37:50"}
{"current_steps": 3760, "total_steps": 4130, "loss": 0.2445, "lr": 9.752164853712355e-07, "epoch": 6.372881355932203, "percentage": 91.04, "elapsed_time": "16:21:04", "remaining_time": "1:36:32"}
{"current_steps": 3765, "total_steps": 4130, "loss": 0.2669, "lr": 9.493160201511409e-07, "epoch": 6.38135593220339, "percentage": 91.16, "elapsed_time": "16:22:24", "remaining_time": "1:35:14"}
{"current_steps": 3770, "total_steps": 4130, "loss": 0.2653, "lr": 9.2375577862718e-07, "epoch": 6.389830508474576, "percentage": 91.28, "elapsed_time": "16:23:38", "remaining_time": "1:33:55"}
{"current_steps": 3775, "total_steps": 4130, "loss": 0.2463, "lr": 8.985362172763933e-07, "epoch": 6.398305084745763, "percentage": 91.4, "elapsed_time": "16:24:57", "remaining_time": "1:32:37"}
{"current_steps": 3780, "total_steps": 4130, "loss": 0.2513, "lr": 8.736577864916617e-07, "epoch": 6.406779661016949, "percentage": 91.53, "elapsed_time": "16:26:17", "remaining_time": "1:31:19"}
{"current_steps": 3785, "total_steps": 4130, "loss": 0.2546, "lr": 8.491209305736525e-07, "epoch": 6.415254237288136, "percentage": 91.65, "elapsed_time": "16:27:36", "remaining_time": "1:30:01"}
{"current_steps": 3790, "total_steps": 4130, "loss": 0.2876, "lr": 8.249260877228993e-07, "epoch": 6.423728813559322, "percentage": 91.77, "elapsed_time": "16:28:56", "remaining_time": "1:28:43"}
{"current_steps": 3795, "total_steps": 4130, "loss": 0.274, "lr": 8.010736900319615e-07, "epoch": 6.432203389830509, "percentage": 91.89, "elapsed_time": "16:30:15", "remaining_time": "1:27:24"}
{"current_steps": 3800, "total_steps": 4130, "loss": 0.2621, "lr": 7.775641634777198e-07, "epoch": 6.440677966101695, "percentage": 92.01, "elapsed_time": "16:31:36", "remaining_time": "1:26:06"}
{"current_steps": 3805, "total_steps": 4130, "loss": 0.2596, "lr": 7.543979279137592e-07, "epoch": 6.4491525423728815, "percentage": 92.13, "elapsed_time": "16:32:56", "remaining_time": "1:24:48"}
{"current_steps": 3810, "total_steps": 4130, "loss": 0.2499, "lr": 7.315753970628825e-07, "epoch": 6.4576271186440675, "percentage": 92.25, "elapsed_time": "16:34:12", "remaining_time": "1:23:30"}
{"current_steps": 3815, "total_steps": 4130, "loss": 0.2659, "lr": 7.090969785097046e-07, "epoch": 6.466101694915254, "percentage": 92.37, "elapsed_time": "16:35:33", "remaining_time": "1:22:12"}
{"current_steps": 3820, "total_steps": 4130, "loss": 0.2437, "lr": 6.869630736933963e-07, "epoch": 6.47457627118644, "percentage": 92.49, "elapsed_time": "16:36:49", "remaining_time": "1:20:53"}
{"current_steps": 3825, "total_steps": 4130, "loss": 0.2665, "lr": 6.651740779004878e-07, "epoch": 6.483050847457627, "percentage": 92.62, "elapsed_time": "16:38:02", "remaining_time": "1:19:34"}
{"current_steps": 3830, "total_steps": 4130, "loss": 0.2636, "lr": 6.437303802578365e-07, "epoch": 6.491525423728813, "percentage": 92.74, "elapsed_time": "16:39:21", "remaining_time": "1:18:16"}
{"current_steps": 3835, "total_steps": 4130, "loss": 0.2584, "lr": 6.226323637256592e-07, "epoch": 6.5, "percentage": 92.86, "elapsed_time": "16:40:38", "remaining_time": "1:16:58"}
{"current_steps": 3840, "total_steps": 4130, "loss": 0.2607, "lr": 6.018804050906957e-07, "epoch": 6.508474576271187, "percentage": 92.98, "elapsed_time": "16:41:55", "remaining_time": "1:15:40"}
{"current_steps": 3845, "total_steps": 4130, "loss": 0.2934, "lr": 5.814748749594845e-07, "epoch": 6.516949152542373, "percentage": 93.1, "elapsed_time": "16:43:16", "remaining_time": "1:14:21"}
{"current_steps": 3850, "total_steps": 4130, "loss": 0.2407, "lr": 5.614161377517491e-07, "epoch": 6.52542372881356, "percentage": 93.22, "elapsed_time": "16:44:36", "remaining_time": "1:13:03"}
{"current_steps": 3855, "total_steps": 4130, "loss": 0.262, "lr": 5.417045516938712e-07, "epoch": 6.533898305084746, "percentage": 93.34, "elapsed_time": "16:45:56", "remaining_time": "1:11:45"}
{"current_steps": 3860, "total_steps": 4130, "loss": 0.266, "lr": 5.223404688125189e-07, "epoch": 6.5423728813559325, "percentage": 93.46, "elapsed_time": "16:47:12", "remaining_time": "1:10:27"}
{"current_steps": 3865, "total_steps": 4130, "loss": 0.2479, "lr": 5.033242349283307e-07, "epoch": 6.5508474576271185, "percentage": 93.58, "elapsed_time": "16:48:31", "remaining_time": "1:09:08"}
{"current_steps": 3870, "total_steps": 4130, "loss": 0.2898, "lr": 4.846561896497682e-07, "epoch": 6.559322033898305, "percentage": 93.7, "elapsed_time": "16:49:51", "remaining_time": "1:07:50"}
{"current_steps": 3875, "total_steps": 4130, "loss": 0.2574, "lr": 4.6633666636703325e-07, "epoch": 6.567796610169491, "percentage": 93.83, "elapsed_time": "16:51:10", "remaining_time": "1:06:32"}
{"current_steps": 3880, "total_steps": 4130, "loss": 0.2534, "lr": 4.4836599224611586e-07, "epoch": 6.576271186440678, "percentage": 93.95, "elapsed_time": "16:52:28", "remaining_time": "1:05:14"}
{"current_steps": 3885, "total_steps": 4130, "loss": 0.2677, "lr": 4.3074448822295165e-07, "epoch": 6.584745762711864, "percentage": 94.07, "elapsed_time": "16:53:47", "remaining_time": "1:03:55"}
{"current_steps": 3890, "total_steps": 4130, "loss": 0.2531, "lr": 4.1347246899770435e-07, "epoch": 6.593220338983051, "percentage": 94.19, "elapsed_time": "16:55:00", "remaining_time": "1:02:37"}
{"current_steps": 3895, "total_steps": 4130, "loss": 0.2603, "lr": 3.965502430291235e-07, "epoch": 6.601694915254237, "percentage": 94.31, "elapsed_time": "16:56:21", "remaining_time": "1:01:19"}
{"current_steps": 3900, "total_steps": 4130, "loss": 0.2469, "lr": 3.7997811252905135e-07, "epoch": 6.610169491525424, "percentage": 94.43, "elapsed_time": "16:57:39", "remaining_time": "1:00:00"}
{"current_steps": 3905, "total_steps": 4130, "loss": 0.2932, "lr": 3.6375637345701376e-07, "epoch": 6.61864406779661, "percentage": 94.55, "elapsed_time": "16:59:00", "remaining_time": "0:58:42"}
{"current_steps": 3910, "total_steps": 4130, "loss": 0.2353, "lr": 3.4788531551495307e-07, "epoch": 6.627118644067797, "percentage": 94.67, "elapsed_time": "17:00:15", "remaining_time": "0:57:24"}
{"current_steps": 3915, "total_steps": 4130, "loss": 0.2673, "lr": 3.323652221420326e-07, "epoch": 6.635593220338983, "percentage": 94.79, "elapsed_time": "17:01:35", "remaining_time": "0:56:06"}
{"current_steps": 3920, "total_steps": 4130, "loss": 0.2459, "lr": 3.1719637050958706e-07, "epoch": 6.6440677966101696, "percentage": 94.92, "elapsed_time": "17:02:53", "remaining_time": "0:54:47"}
{"current_steps": 3925, "total_steps": 4130, "loss": 0.2355, "lr": 3.023790315161734e-07, "epoch": 6.652542372881356, "percentage": 95.04, "elapsed_time": "17:04:12", "remaining_time": "0:53:29"}
{"current_steps": 3930, "total_steps": 4130, "loss": 0.2474, "lr": 2.8791346978273015e-07, "epoch": 6.661016949152542, "percentage": 95.16, "elapsed_time": "17:05:29", "remaining_time": "0:52:11"}
{"current_steps": 3935, "total_steps": 4130, "loss": 0.2761, "lr": 2.7379994364784556e-07, "epoch": 6.669491525423728, "percentage": 95.28, "elapsed_time": "17:06:47", "remaining_time": "0:50:52"}
{"current_steps": 3940, "total_steps": 4130, "loss": 0.247, "lr": 2.60038705163157e-07, "epoch": 6.677966101694915, "percentage": 95.4, "elapsed_time": "17:08:06", "remaining_time": "0:49:34"}
{"current_steps": 3945, "total_steps": 4130, "loss": 0.2969, "lr": 2.4663000008883664e-07, "epoch": 6.686440677966102, "percentage": 95.52, "elapsed_time": "17:09:26", "remaining_time": "0:48:16"}
{"current_steps": 3950, "total_steps": 4130, "loss": 0.2584, "lr": 2.335740678892129e-07, "epoch": 6.694915254237288, "percentage": 95.64, "elapsed_time": "17:10:40", "remaining_time": "0:46:58"}
{"current_steps": 3955, "total_steps": 4130, "loss": 0.2768, "lr": 2.20871141728487e-07, "epoch": 6.703389830508475, "percentage": 95.76, "elapsed_time": "17:11:57", "remaining_time": "0:45:39"}
{"current_steps": 3960, "total_steps": 4130, "loss": 0.2552, "lr": 2.0852144846656764e-07, "epoch": 6.711864406779661, "percentage": 95.88, "elapsed_time": "17:13:15", "remaining_time": "0:44:21"}
{"current_steps": 3965, "total_steps": 4130, "loss": 0.268, "lr": 1.9652520865502734e-07, "epoch": 6.720338983050848, "percentage": 96.0, "elapsed_time": "17:14:33", "remaining_time": "0:43:03"}
{"current_steps": 3970, "total_steps": 4130, "loss": 0.2741, "lr": 1.848826365331613e-07, "epoch": 6.728813559322034, "percentage": 96.13, "elapsed_time": "17:15:50", "remaining_time": "0:41:44"}
{"current_steps": 3975, "total_steps": 4130, "loss": 0.255, "lr": 1.7359394002415265e-07, "epoch": 6.737288135593221, "percentage": 96.25, "elapsed_time": "17:17:10", "remaining_time": "0:40:26"}
{"current_steps": 3980, "total_steps": 4130, "loss": 0.2504, "lr": 1.626593207313709e-07, "epoch": 6.745762711864407, "percentage": 96.37, "elapsed_time": "17:18:29", "remaining_time": "0:39:08"}
{"current_steps": 3985, "total_steps": 4130, "loss": 0.2742, "lr": 1.520789739347617e-07, "epoch": 6.754237288135593, "percentage": 96.49, "elapsed_time": "17:19:49", "remaining_time": "0:37:50"}
{"current_steps": 3990, "total_steps": 4130, "loss": 0.2872, "lr": 1.4185308858737367e-07, "epoch": 6.762711864406779, "percentage": 96.61, "elapsed_time": "17:21:09", "remaining_time": "0:36:31"}
{"current_steps": 3995, "total_steps": 4130, "loss": 0.2565, "lr": 1.3198184731196162e-07, "epoch": 6.771186440677966, "percentage": 96.73, "elapsed_time": "17:22:24", "remaining_time": "0:35:13"}
{"current_steps": 4000, "total_steps": 4130, "loss": 0.2911, "lr": 1.2246542639774871e-07, "epoch": 6.779661016949152, "percentage": 96.85, "elapsed_time": "17:23:43", "remaining_time": "0:33:55"}
{"current_steps": 4005, "total_steps": 4130, "loss": 0.2516, "lr": 1.1330399579725814e-07, "epoch": 6.788135593220339, "percentage": 96.97, "elapsed_time": "17:25:01", "remaining_time": "0:32:36"}
{"current_steps": 4010, "total_steps": 4130, "loss": 0.2692, "lr": 1.0449771912329543e-07, "epoch": 6.796610169491525, "percentage": 97.09, "elapsed_time": "17:26:20", "remaining_time": "0:31:18"}
{"current_steps": 4015, "total_steps": 4130, "loss": 0.2814, "lr": 9.604675364601079e-08, "epoch": 6.805084745762712, "percentage": 97.22, "elapsed_time": "17:27:41", "remaining_time": "0:30:00"}
{"current_steps": 4020, "total_steps": 4130, "loss": 0.2358, "lr": 8.795125029010587e-08, "epoch": 6.813559322033898, "percentage": 97.34, "elapsed_time": "17:28:58", "remaining_time": "0:28:42"}
{"current_steps": 4025, "total_steps": 4130, "loss": 0.2683, "lr": 8.021135363212252e-08, "epoch": 6.822033898305085, "percentage": 97.46, "elapsed_time": "17:30:16", "remaining_time": "0:27:23"}
{"current_steps": 4030, "total_steps": 4130, "loss": 0.2589, "lr": 7.282720189787374e-08, "epoch": 6.830508474576272, "percentage": 97.58, "elapsed_time": "17:31:36", "remaining_time": "0:26:05"}
{"current_steps": 4035, "total_steps": 4130, "loss": 0.2547, "lr": 6.579892695996571e-08, "epoch": 6.838983050847458, "percentage": 97.7, "elapsed_time": "17:32:53", "remaining_time": "0:24:47"}
{"current_steps": 4040, "total_steps": 4130, "loss": 0.2601, "lr": 5.912665433545517e-08, "epoch": 6.847457627118644, "percentage": 97.82, "elapsed_time": "17:34:13", "remaining_time": "0:23:29"}
{"current_steps": 4045, "total_steps": 4130, "loss": 0.2419, "lr": 5.281050318358683e-08, "epoch": 6.8559322033898304, "percentage": 97.94, "elapsed_time": "17:35:32", "remaining_time": "0:22:10"}
{"current_steps": 4050, "total_steps": 4130, "loss": 0.2775, "lr": 4.685058630369055e-08, "epoch": 6.864406779661017, "percentage": 98.06, "elapsed_time": "17:36:52", "remaining_time": "0:20:52"}
{"current_steps": 4055, "total_steps": 4130, "loss": 0.2836, "lr": 4.124701013314969e-08, "epoch": 6.872881355932203, "percentage": 98.18, "elapsed_time": "17:38:12", "remaining_time": "0:19:34"}
{"current_steps": 4060, "total_steps": 4130, "loss": 0.2677, "lr": 3.599987474550259e-08, "epoch": 6.88135593220339, "percentage": 98.31, "elapsed_time": "17:39:31", "remaining_time": "0:18:16"}
{"current_steps": 4065, "total_steps": 4130, "loss": 0.2785, "lr": 3.110927384865958e-08, "epoch": 6.889830508474576, "percentage": 98.43, "elapsed_time": "17:40:49", "remaining_time": "0:16:57"}
{"current_steps": 4070, "total_steps": 4130, "loss": 0.2329, "lr": 2.6575294783230954e-08, "epoch": 6.898305084745763, "percentage": 98.55, "elapsed_time": "17:42:01", "remaining_time": "0:15:39"}
{"current_steps": 4075, "total_steps": 4130, "loss": 0.2457, "lr": 2.239801852095935e-08, "epoch": 6.906779661016949, "percentage": 98.67, "elapsed_time": "17:43:11", "remaining_time": "0:14:20"}
{"current_steps": 4080, "total_steps": 4130, "loss": 0.2409, "lr": 1.8577519663278697e-08, "epoch": 6.915254237288136, "percentage": 98.79, "elapsed_time": "17:44:24", "remaining_time": "0:13:02"}
{"current_steps": 4085, "total_steps": 4130, "loss": 0.285, "lr": 1.5113866439986357e-08, "epoch": 6.923728813559322, "percentage": 98.91, "elapsed_time": "17:45:40", "remaining_time": "0:11:44"}
{"current_steps": 4090, "total_steps": 4130, "loss": 0.2731, "lr": 1.2007120708015241e-08, "epoch": 6.932203389830509, "percentage": 99.03, "elapsed_time": "17:46:59", "remaining_time": "0:10:26"}
{"current_steps": 4095, "total_steps": 4130, "loss": 0.2669, "lr": 9.257337950332456e-09, "epoch": 6.940677966101695, "percentage": 99.15, "elapsed_time": "17:48:19", "remaining_time": "0:09:07"}
{"current_steps": 4100, "total_steps": 4130, "loss": 0.2706, "lr": 6.864567274955658e-09, "epoch": 6.9491525423728815, "percentage": 99.27, "elapsed_time": "17:49:39", "remaining_time": "0:07:49"}
{"current_steps": 4105, "total_steps": 4130, "loss": 0.2787, "lr": 4.828851414062641e-09, "epoch": 6.9576271186440675, "percentage": 99.39, "elapsed_time": "17:50:59", "remaining_time": "0:06:31"}
{"current_steps": 4110, "total_steps": 4130, "loss": 0.2701, "lr": 3.150226723243055e-09, "epoch": 6.966101694915254, "percentage": 99.52, "elapsed_time": "17:52:20", "remaining_time": "0:05:13"}
{"current_steps": 4115, "total_steps": 4130, "loss": 0.2611, "lr": 1.8287231808322702e-09, "epoch": 6.97457627118644, "percentage": 99.64, "elapsed_time": "17:53:38", "remaining_time": "0:03:54"}
{"current_steps": 4120, "total_steps": 4130, "loss": 0.246, "lr": 8.643643873962326e-10, "epoch": 6.983050847457627, "percentage": 99.76, "elapsed_time": "17:54:57", "remaining_time": "0:02:36"}
{"current_steps": 4125, "total_steps": 4130, "loss": 0.2559, "lr": 2.5716756528959553e-10, "epoch": 6.991525423728813, "percentage": 99.88, "elapsed_time": "17:56:16", "remaining_time": "0:01:18"}
{"current_steps": 4130, "total_steps": 4130, "loss": 0.2482, "lr": 7.143558364841597e-12, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "17:57:36", "remaining_time": "0:00:00"}
{"current_steps": 4130, "total_steps": 4130, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "17:58:18", "remaining_time": "0:00:00"}

9133
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 sha256:97d37e47ed5eac05f9f6a646a54c3a5a323532c34828ca9b08de854750a34393
size 8785

BIN
training_loss.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 46 KiB

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

Binary file not shown.