初始化项目,由ModelHub XC社区提供模型

Model: DCAgent/a1-glaive_code_assistant
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-02 03:47:11 +08:00
commit 260fb6905e
23 changed files with 162526 additions and 0 deletions

36
.gitattributes vendored Normal file
View File

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

60
README.md Normal file
View File

@@ -0,0 +1,60 @@
---
library_name: transformers
license: other
base_model: Qwen/Qwen3-8B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: sft_a1_glaive_code_assistant__Qwen3-8B
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# sft_a1_glaive_code_assistant__Qwen3-8B
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--glaive-code-assistant-sandboxes_glm_4.7_traces_jupiter/snapshots/97fe95da75d8c1a44caaee0f03b4fa44a26bee49_thinking_preprocessed dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 16
- total_train_batch_size: 16
- total_eval_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7.0
### Training results
### Framework versions
- Transformers 4.57.6
- Pytorch 2.9.1+cu130
- Datasets 4.7.0
- Tokenizers 0.22.2

28
added_tokens.json Normal file
View File

@@ -0,0 +1,28 @@
{
"</think>": 151668,
"</tool_call>": 151658,
"</tool_response>": 151666,
"<think>": 151667,
"<tool_call>": 151657,
"<tool_response>": 151665,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

16
all_results.json Normal file
View File

@@ -0,0 +1,16 @@
{
"achieved_tflops_per_gpu": 0.0026581291027928545,
"achieved_tflops_per_gpu_theoretical": 809.7091905147371,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.16129948198795319,
"mfu_percent": 0.00018785364684048442,
"mfu_percent_theoretical": 57.223264347331245,
"total_flos": 746122008920064.0,
"train_loss": 0.22925819348185836,
"train_runtime": 17543.4013,
"train_samples_per_second": 3.821,
"train_steps_per_second": 0.239,
"valid_targets_mean": 1733.8,
"valid_targets_min": 533
}

89
chat_template.jinja Normal file
View File

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

68
config.json Normal file
View File

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

12
generation_config.json Normal file
View File

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

151388
merges.txt Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2ea6145b407ab4d962fbbddb8381a66a3a6e24888828df6beba3a8de1c004943
size 4902257696

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2534f090f229c779f9fc17ae91060cda7905b09c3bc0421778cc880ffd25dc4d
size 4915960368

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2ddac105d7d418ad13d012cbe40fd16dda1c1a3514c7a17a5da54c894070acc8
size 4983068496

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b2b9db0fa5376451bcbcdfd36296fe3c79188a7260da71814ae19dc1599a905e
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": "97fe95da75d8c1a44caaee0f03b4fa44a26bee49_thinking_preprocessed",
"training_start": null,
"training_end": null,
"created_by": "raoof1",
"base_model_name": "Qwen/Qwen3-8B",
"dataset_name": "/e/scratch/jureap59/raoof1/sft_data/hf_hub/datasets--DCAgent--glaive-code-assistant-sandboxes_glm_4.7_traces_jupiter/snapshots/97fe95da75d8c1a44caaee0f03b4fa44a26bee49_thinking_preprocessed",
"training_type": "SFT",
"training_parameters": "https://huggingface.co/DCAgent/a1-glaive_code_assistant/blob/main/config.json",
"wandb_link": null,
"traces_location_s3": null
}

31
special_tokens_map.json Normal file
View File

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

3
tokenizer.json Normal file
View File

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

240
tokenizer_config.json Normal file
View File

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

16
train_results.json Normal file
View File

@@ -0,0 +1,16 @@
{
"achieved_tflops_per_gpu": 0.0026581291027928545,
"achieved_tflops_per_gpu_theoretical": 809.7091905147371,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.16129948198795319,
"mfu_percent": 0.00018785364684048442,
"mfu_percent_theoretical": 57.223264347331245,
"total_flos": 746122008920064.0,
"train_loss": 0.22925819348185836,
"train_runtime": 17543.4013,
"train_samples_per_second": 3.821,
"train_steps_per_second": 0.239,
"valid_targets_mean": 1733.8,
"valid_targets_min": 533
}

839
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,839 @@
{"current_steps": 5, "total_steps": 4193, "loss": 0.8516, "lr": 3.80952380952381e-07, "epoch": 0.008347245409015025, "percentage": 0.12, "elapsed_time": "0:00:28", "remaining_time": "6:41:27"}
{"current_steps": 10, "total_steps": 4193, "loss": 0.8348, "lr": 8.571428571428572e-07, "epoch": 0.01669449081803005, "percentage": 0.24, "elapsed_time": "0:00:52", "remaining_time": "6:02:59"}
{"current_steps": 15, "total_steps": 4193, "loss": 0.8539, "lr": 1.3333333333333334e-06, "epoch": 0.025041736227045076, "percentage": 0.36, "elapsed_time": "0:01:16", "remaining_time": "5:54:49"}
{"current_steps": 20, "total_steps": 4193, "loss": 0.7723, "lr": 1.8095238095238097e-06, "epoch": 0.0333889816360601, "percentage": 0.48, "elapsed_time": "0:01:38", "remaining_time": "5:42:35"}
{"current_steps": 25, "total_steps": 4193, "loss": 0.7356, "lr": 2.285714285714286e-06, "epoch": 0.041736227045075125, "percentage": 0.6, "elapsed_time": "0:01:55", "remaining_time": "5:21:16"}
{"current_steps": 30, "total_steps": 4193, "loss": 0.6733, "lr": 2.7619047619047625e-06, "epoch": 0.05008347245409015, "percentage": 0.72, "elapsed_time": "0:02:14", "remaining_time": "5:11:13"}
{"current_steps": 35, "total_steps": 4193, "loss": 0.6114, "lr": 3.2380952380952385e-06, "epoch": 0.05843071786310518, "percentage": 0.83, "elapsed_time": "0:02:34", "remaining_time": "5:06:13"}
{"current_steps": 40, "total_steps": 4193, "loss": 0.5837, "lr": 3.7142857142857146e-06, "epoch": 0.0667779632721202, "percentage": 0.95, "elapsed_time": "0:02:57", "remaining_time": "5:07:04"}
{"current_steps": 45, "total_steps": 4193, "loss": 0.5074, "lr": 4.190476190476191e-06, "epoch": 0.07512520868113523, "percentage": 1.07, "elapsed_time": "0:03:17", "remaining_time": "5:02:41"}
{"current_steps": 50, "total_steps": 4193, "loss": 0.5153, "lr": 4.666666666666667e-06, "epoch": 0.08347245409015025, "percentage": 1.19, "elapsed_time": "0:03:33", "remaining_time": "4:55:09"}
{"current_steps": 55, "total_steps": 4193, "loss": 0.4827, "lr": 5.142857142857142e-06, "epoch": 0.09181969949916527, "percentage": 1.31, "elapsed_time": "0:03:52", "remaining_time": "4:51:44"}
{"current_steps": 60, "total_steps": 4193, "loss": 0.4912, "lr": 5.619047619047619e-06, "epoch": 0.1001669449081803, "percentage": 1.43, "elapsed_time": "0:04:20", "remaining_time": "4:59:02"}
{"current_steps": 65, "total_steps": 4193, "loss": 0.4612, "lr": 6.095238095238096e-06, "epoch": 0.10851419031719532, "percentage": 1.55, "elapsed_time": "0:04:43", "remaining_time": "5:00:01"}
{"current_steps": 70, "total_steps": 4193, "loss": 0.453, "lr": 6.571428571428572e-06, "epoch": 0.11686143572621036, "percentage": 1.67, "elapsed_time": "0:05:09", "remaining_time": "5:03:59"}
{"current_steps": 75, "total_steps": 4193, "loss": 0.4407, "lr": 7.047619047619048e-06, "epoch": 0.12520868113522537, "percentage": 1.79, "elapsed_time": "0:05:31", "remaining_time": "5:03:29"}
{"current_steps": 80, "total_steps": 4193, "loss": 0.4638, "lr": 7.523809523809524e-06, "epoch": 0.1335559265442404, "percentage": 1.91, "elapsed_time": "0:05:55", "remaining_time": "5:05:01"}
{"current_steps": 85, "total_steps": 4193, "loss": 0.4303, "lr": 8.000000000000001e-06, "epoch": 0.1419031719532554, "percentage": 2.03, "elapsed_time": "0:06:26", "remaining_time": "5:10:59"}
{"current_steps": 90, "total_steps": 4193, "loss": 0.44, "lr": 8.476190476190477e-06, "epoch": 0.15025041736227046, "percentage": 2.15, "elapsed_time": "0:06:49", "remaining_time": "5:10:47"}
{"current_steps": 95, "total_steps": 4193, "loss": 0.412, "lr": 8.952380952380953e-06, "epoch": 0.15859766277128548, "percentage": 2.27, "elapsed_time": "0:07:12", "remaining_time": "5:10:49"}
{"current_steps": 100, "total_steps": 4193, "loss": 0.4115, "lr": 9.42857142857143e-06, "epoch": 0.1669449081803005, "percentage": 2.38, "elapsed_time": "0:07:39", "remaining_time": "5:13:06"}
{"current_steps": 105, "total_steps": 4193, "loss": 0.4165, "lr": 9.904761904761906e-06, "epoch": 0.17529215358931552, "percentage": 2.5, "elapsed_time": "0:07:55", "remaining_time": "5:08:34"}
{"current_steps": 110, "total_steps": 4193, "loss": 0.4088, "lr": 1.0380952380952383e-05, "epoch": 0.18363939899833054, "percentage": 2.62, "elapsed_time": "0:08:24", "remaining_time": "5:12:03"}
{"current_steps": 115, "total_steps": 4193, "loss": 0.3967, "lr": 1.0857142857142858e-05, "epoch": 0.19198664440734559, "percentage": 2.74, "elapsed_time": "0:08:47", "remaining_time": "5:11:45"}
{"current_steps": 120, "total_steps": 4193, "loss": 0.3976, "lr": 1.1333333333333334e-05, "epoch": 0.2003338898163606, "percentage": 2.86, "elapsed_time": "0:09:10", "remaining_time": "5:11:23"}
{"current_steps": 125, "total_steps": 4193, "loss": 0.4056, "lr": 1.180952380952381e-05, "epoch": 0.20868113522537562, "percentage": 2.98, "elapsed_time": "0:09:28", "remaining_time": "5:08:33"}
{"current_steps": 130, "total_steps": 4193, "loss": 0.3699, "lr": 1.2285714285714288e-05, "epoch": 0.21702838063439064, "percentage": 3.1, "elapsed_time": "0:09:43", "remaining_time": "5:04:05"}
{"current_steps": 135, "total_steps": 4193, "loss": 0.3785, "lr": 1.2761904761904762e-05, "epoch": 0.22537562604340566, "percentage": 3.22, "elapsed_time": "0:10:07", "remaining_time": "5:04:30"}
{"current_steps": 140, "total_steps": 4193, "loss": 0.393, "lr": 1.3238095238095238e-05, "epoch": 0.2337228714524207, "percentage": 3.34, "elapsed_time": "0:10:36", "remaining_time": "5:06:57"}
{"current_steps": 145, "total_steps": 4193, "loss": 0.3822, "lr": 1.3714285714285716e-05, "epoch": 0.24207011686143573, "percentage": 3.46, "elapsed_time": "0:10:54", "remaining_time": "5:04:37"}
{"current_steps": 150, "total_steps": 4193, "loss": 0.3885, "lr": 1.4190476190476192e-05, "epoch": 0.25041736227045075, "percentage": 3.58, "elapsed_time": "0:11:21", "remaining_time": "5:05:56"}
{"current_steps": 155, "total_steps": 4193, "loss": 0.3746, "lr": 1.4666666666666666e-05, "epoch": 0.2587646076794658, "percentage": 3.7, "elapsed_time": "0:11:41", "remaining_time": "5:04:32"}
{"current_steps": 160, "total_steps": 4193, "loss": 0.3811, "lr": 1.5142857142857144e-05, "epoch": 0.2671118530884808, "percentage": 3.82, "elapsed_time": "0:12:03", "remaining_time": "5:04:05"}
{"current_steps": 165, "total_steps": 4193, "loss": 0.3796, "lr": 1.5619047619047622e-05, "epoch": 0.27545909849749584, "percentage": 3.94, "elapsed_time": "0:12:23", "remaining_time": "5:02:28"}
{"current_steps": 170, "total_steps": 4193, "loss": 0.3553, "lr": 1.6095238095238096e-05, "epoch": 0.2838063439065108, "percentage": 4.05, "elapsed_time": "0:12:45", "remaining_time": "5:01:46"}
{"current_steps": 175, "total_steps": 4193, "loss": 0.356, "lr": 1.6571428571428574e-05, "epoch": 0.2921535893155259, "percentage": 4.17, "elapsed_time": "0:13:06", "remaining_time": "5:01:02"}
{"current_steps": 180, "total_steps": 4193, "loss": 0.3957, "lr": 1.704761904761905e-05, "epoch": 0.3005008347245409, "percentage": 4.29, "elapsed_time": "0:13:28", "remaining_time": "5:00:32"}
{"current_steps": 185, "total_steps": 4193, "loss": 0.3614, "lr": 1.7523809523809526e-05, "epoch": 0.3088480801335559, "percentage": 4.41, "elapsed_time": "0:13:45", "remaining_time": "4:57:59"}
{"current_steps": 190, "total_steps": 4193, "loss": 0.3721, "lr": 1.8e-05, "epoch": 0.31719532554257096, "percentage": 4.53, "elapsed_time": "0:14:16", "remaining_time": "5:00:45"}
{"current_steps": 195, "total_steps": 4193, "loss": 0.3463, "lr": 1.8476190476190478e-05, "epoch": 0.32554257095158595, "percentage": 4.65, "elapsed_time": "0:14:36", "remaining_time": "4:59:29"}
{"current_steps": 200, "total_steps": 4193, "loss": 0.3586, "lr": 1.8952380952380953e-05, "epoch": 0.333889816360601, "percentage": 4.77, "elapsed_time": "0:14:55", "remaining_time": "4:58:08"}
{"current_steps": 205, "total_steps": 4193, "loss": 0.3613, "lr": 1.942857142857143e-05, "epoch": 0.34223706176961605, "percentage": 4.89, "elapsed_time": "0:15:22", "remaining_time": "4:59:00"}
{"current_steps": 210, "total_steps": 4193, "loss": 0.3793, "lr": 1.9904761904761908e-05, "epoch": 0.35058430717863104, "percentage": 5.01, "elapsed_time": "0:15:42", "remaining_time": "4:57:58"}
{"current_steps": 215, "total_steps": 4193, "loss": 0.3352, "lr": 2.0380952380952382e-05, "epoch": 0.3589315525876461, "percentage": 5.13, "elapsed_time": "0:16:03", "remaining_time": "4:57:10"}
{"current_steps": 220, "total_steps": 4193, "loss": 0.3404, "lr": 2.085714285714286e-05, "epoch": 0.3672787979966611, "percentage": 5.25, "elapsed_time": "0:16:28", "remaining_time": "4:57:31"}
{"current_steps": 225, "total_steps": 4193, "loss": 0.3582, "lr": 2.1333333333333335e-05, "epoch": 0.3756260434056761, "percentage": 5.37, "elapsed_time": "0:16:46", "remaining_time": "4:55:57"}
{"current_steps": 230, "total_steps": 4193, "loss": 0.3583, "lr": 2.180952380952381e-05, "epoch": 0.38397328881469117, "percentage": 5.49, "elapsed_time": "0:17:10", "remaining_time": "4:56:00"}
{"current_steps": 235, "total_steps": 4193, "loss": 0.3721, "lr": 2.2285714285714287e-05, "epoch": 0.39232053422370616, "percentage": 5.6, "elapsed_time": "0:17:26", "remaining_time": "4:53:49"}
{"current_steps": 240, "total_steps": 4193, "loss": 0.3278, "lr": 2.2761904761904765e-05, "epoch": 0.4006677796327212, "percentage": 5.72, "elapsed_time": "0:17:48", "remaining_time": "4:53:22"}
{"current_steps": 245, "total_steps": 4193, "loss": 0.3536, "lr": 2.3238095238095242e-05, "epoch": 0.4090150250417362, "percentage": 5.84, "elapsed_time": "0:18:15", "remaining_time": "4:54:19"}
{"current_steps": 250, "total_steps": 4193, "loss": 0.3656, "lr": 2.3714285714285717e-05, "epoch": 0.41736227045075125, "percentage": 5.96, "elapsed_time": "0:18:35", "remaining_time": "4:53:07"}
{"current_steps": 255, "total_steps": 4193, "loss": 0.3244, "lr": 2.419047619047619e-05, "epoch": 0.4257095158597663, "percentage": 6.08, "elapsed_time": "0:18:56", "remaining_time": "4:52:33"}
{"current_steps": 260, "total_steps": 4193, "loss": 0.3575, "lr": 2.466666666666667e-05, "epoch": 0.4340567612687813, "percentage": 6.2, "elapsed_time": "0:19:24", "remaining_time": "4:53:40"}
{"current_steps": 265, "total_steps": 4193, "loss": 0.344, "lr": 2.5142857142857143e-05, "epoch": 0.44240400667779634, "percentage": 6.32, "elapsed_time": "0:19:45", "remaining_time": "4:52:48"}
{"current_steps": 270, "total_steps": 4193, "loss": 0.3727, "lr": 2.5619047619047618e-05, "epoch": 0.4507512520868113, "percentage": 6.44, "elapsed_time": "0:20:06", "remaining_time": "4:52:09"}
{"current_steps": 275, "total_steps": 4193, "loss": 0.3385, "lr": 2.60952380952381e-05, "epoch": 0.4590984974958264, "percentage": 6.56, "elapsed_time": "0:20:28", "remaining_time": "4:51:41"}
{"current_steps": 280, "total_steps": 4193, "loss": 0.3546, "lr": 2.6571428571428573e-05, "epoch": 0.4674457429048414, "percentage": 6.68, "elapsed_time": "0:20:50", "remaining_time": "4:51:16"}
{"current_steps": 285, "total_steps": 4193, "loss": 0.3281, "lr": 2.704761904761905e-05, "epoch": 0.4757929883138564, "percentage": 6.8, "elapsed_time": "0:21:17", "remaining_time": "4:51:50"}
{"current_steps": 290, "total_steps": 4193, "loss": 0.3384, "lr": 2.7523809523809525e-05, "epoch": 0.48414023372287146, "percentage": 6.92, "elapsed_time": "0:21:33", "remaining_time": "4:50:03"}
{"current_steps": 295, "total_steps": 4193, "loss": 0.343, "lr": 2.8e-05, "epoch": 0.49248747913188645, "percentage": 7.04, "elapsed_time": "0:21:57", "remaining_time": "4:50:09"}
{"current_steps": 300, "total_steps": 4193, "loss": 0.3463, "lr": 2.847619047619048e-05, "epoch": 0.5008347245409015, "percentage": 7.15, "elapsed_time": "0:22:15", "remaining_time": "4:48:47"}
{"current_steps": 305, "total_steps": 4193, "loss": 0.327, "lr": 2.8952380952380955e-05, "epoch": 0.5091819699499165, "percentage": 7.27, "elapsed_time": "0:22:41", "remaining_time": "4:49:10"}
{"current_steps": 310, "total_steps": 4193, "loss": 0.3425, "lr": 2.9428571428571433e-05, "epoch": 0.5175292153589316, "percentage": 7.39, "elapsed_time": "0:23:03", "remaining_time": "4:48:52"}
{"current_steps": 315, "total_steps": 4193, "loss": 0.3908, "lr": 2.9904761904761907e-05, "epoch": 0.5258764607679466, "percentage": 7.51, "elapsed_time": "0:23:31", "remaining_time": "4:49:33"}
{"current_steps": 320, "total_steps": 4193, "loss": 0.324, "lr": 3.038095238095238e-05, "epoch": 0.5342237061769616, "percentage": 7.63, "elapsed_time": "0:23:49", "remaining_time": "4:48:23"}
{"current_steps": 325, "total_steps": 4193, "loss": 0.3154, "lr": 3.085714285714286e-05, "epoch": 0.5425709515859767, "percentage": 7.75, "elapsed_time": "0:24:12", "remaining_time": "4:48:04"}
{"current_steps": 330, "total_steps": 4193, "loss": 0.3392, "lr": 3.1333333333333334e-05, "epoch": 0.5509181969949917, "percentage": 7.87, "elapsed_time": "0:24:32", "remaining_time": "4:47:12"}
{"current_steps": 335, "total_steps": 4193, "loss": 0.3457, "lr": 3.180952380952381e-05, "epoch": 0.5592654424040067, "percentage": 7.99, "elapsed_time": "0:24:54", "remaining_time": "4:46:46"}
{"current_steps": 340, "total_steps": 4193, "loss": 0.3495, "lr": 3.228571428571429e-05, "epoch": 0.5676126878130217, "percentage": 8.11, "elapsed_time": "0:25:10", "remaining_time": "4:45:19"}
{"current_steps": 345, "total_steps": 4193, "loss": 0.3416, "lr": 3.276190476190477e-05, "epoch": 0.5759599332220368, "percentage": 8.23, "elapsed_time": "0:25:39", "remaining_time": "4:46:05"}
{"current_steps": 350, "total_steps": 4193, "loss": 0.3309, "lr": 3.3238095238095245e-05, "epoch": 0.5843071786310517, "percentage": 8.35, "elapsed_time": "0:25:57", "remaining_time": "4:44:59"}
{"current_steps": 355, "total_steps": 4193, "loss": 0.3336, "lr": 3.3714285714285716e-05, "epoch": 0.5926544240400667, "percentage": 8.47, "elapsed_time": "0:26:15", "remaining_time": "4:43:54"}
{"current_steps": 360, "total_steps": 4193, "loss": 0.3441, "lr": 3.4190476190476194e-05, "epoch": 0.6010016694490818, "percentage": 8.59, "elapsed_time": "0:26:40", "remaining_time": "4:43:56"}
{"current_steps": 365, "total_steps": 4193, "loss": 0.3189, "lr": 3.466666666666667e-05, "epoch": 0.6093489148580968, "percentage": 8.7, "elapsed_time": "0:27:00", "remaining_time": "4:43:12"}
{"current_steps": 370, "total_steps": 4193, "loss": 0.342, "lr": 3.514285714285714e-05, "epoch": 0.6176961602671118, "percentage": 8.82, "elapsed_time": "0:27:19", "remaining_time": "4:42:16"}
{"current_steps": 375, "total_steps": 4193, "loss": 0.323, "lr": 3.561904761904762e-05, "epoch": 0.6260434056761269, "percentage": 8.94, "elapsed_time": "0:27:43", "remaining_time": "4:42:16"}
{"current_steps": 380, "total_steps": 4193, "loss": 0.3082, "lr": 3.60952380952381e-05, "epoch": 0.6343906510851419, "percentage": 9.06, "elapsed_time": "0:28:08", "remaining_time": "4:42:18"}
{"current_steps": 385, "total_steps": 4193, "loss": 0.3528, "lr": 3.6571428571428576e-05, "epoch": 0.6427378964941569, "percentage": 9.18, "elapsed_time": "0:28:27", "remaining_time": "4:41:32"}
{"current_steps": 390, "total_steps": 4193, "loss": 0.3536, "lr": 3.704761904761905e-05, "epoch": 0.6510851419031719, "percentage": 9.3, "elapsed_time": "0:28:46", "remaining_time": "4:40:40"}
{"current_steps": 395, "total_steps": 4193, "loss": 0.3302, "lr": 3.7523809523809524e-05, "epoch": 0.659432387312187, "percentage": 9.42, "elapsed_time": "0:29:06", "remaining_time": "4:39:54"}
{"current_steps": 400, "total_steps": 4193, "loss": 0.3549, "lr": 3.8e-05, "epoch": 0.667779632721202, "percentage": 9.54, "elapsed_time": "0:29:22", "remaining_time": "4:38:34"}
{"current_steps": 405, "total_steps": 4193, "loss": 0.3136, "lr": 3.847619047619048e-05, "epoch": 0.676126878130217, "percentage": 9.66, "elapsed_time": "0:29:44", "remaining_time": "4:38:08"}
{"current_steps": 410, "total_steps": 4193, "loss": 0.315, "lr": 3.895238095238096e-05, "epoch": 0.6844741235392321, "percentage": 9.78, "elapsed_time": "0:30:02", "remaining_time": "4:37:07"}
{"current_steps": 415, "total_steps": 4193, "loss": 0.3122, "lr": 3.9428571428571435e-05, "epoch": 0.6928213689482471, "percentage": 9.9, "elapsed_time": "0:30:24", "remaining_time": "4:36:45"}
{"current_steps": 420, "total_steps": 4193, "loss": 0.3219, "lr": 3.9904761904761906e-05, "epoch": 0.7011686143572621, "percentage": 10.02, "elapsed_time": "0:30:51", "remaining_time": "4:37:14"}
{"current_steps": 425, "total_steps": 4193, "loss": 0.3401, "lr": 3.999988907084209e-05, "epoch": 0.7095158597662772, "percentage": 10.14, "elapsed_time": "0:31:09", "remaining_time": "4:36:14"}
{"current_steps": 430, "total_steps": 4193, "loss": 0.3475, "lr": 3.9999438423247035e-05, "epoch": 0.7178631051752922, "percentage": 10.26, "elapsed_time": "0:31:41", "remaining_time": "4:37:21"}
{"current_steps": 435, "total_steps": 4193, "loss": 0.3259, "lr": 3.999864113194738e-05, "epoch": 0.7262103505843072, "percentage": 10.37, "elapsed_time": "0:32:05", "remaining_time": "4:37:17"}
{"current_steps": 440, "total_steps": 4193, "loss": 0.3005, "lr": 3.999749721076231e-05, "epoch": 0.7345575959933222, "percentage": 10.49, "elapsed_time": "0:32:25", "remaining_time": "4:36:30"}
{"current_steps": 445, "total_steps": 4193, "loss": 0.3109, "lr": 3.9996006679519054e-05, "epoch": 0.7429048414023373, "percentage": 10.61, "elapsed_time": "0:32:49", "remaining_time": "4:36:31"}
{"current_steps": 450, "total_steps": 4193, "loss": 0.3027, "lr": 3.9994169564052486e-05, "epoch": 0.7512520868113522, "percentage": 10.73, "elapsed_time": "0:33:11", "remaining_time": "4:36:04"}
{"current_steps": 455, "total_steps": 4193, "loss": 0.3655, "lr": 3.999198589620473e-05, "epoch": 0.7595993322203672, "percentage": 10.85, "elapsed_time": "0:33:30", "remaining_time": "4:35:15"}
{"current_steps": 460, "total_steps": 4193, "loss": 0.3167, "lr": 3.998945571382458e-05, "epoch": 0.7679465776293823, "percentage": 10.97, "elapsed_time": "0:33:49", "remaining_time": "4:34:32"}
{"current_steps": 465, "total_steps": 4193, "loss": 0.3321, "lr": 3.9986579060766866e-05, "epoch": 0.7762938230383973, "percentage": 11.09, "elapsed_time": "0:34:08", "remaining_time": "4:33:45"}
{"current_steps": 470, "total_steps": 4193, "loss": 0.3146, "lr": 3.9983355986891664e-05, "epoch": 0.7846410684474123, "percentage": 11.21, "elapsed_time": "0:34:26", "remaining_time": "4:32:49"}
{"current_steps": 475, "total_steps": 4193, "loss": 0.2902, "lr": 3.9979786548063454e-05, "epoch": 0.7929883138564274, "percentage": 11.33, "elapsed_time": "0:34:48", "remaining_time": "4:32:25"}
{"current_steps": 480, "total_steps": 4193, "loss": 0.3406, "lr": 3.997587080615016e-05, "epoch": 0.8013355592654424, "percentage": 11.45, "elapsed_time": "0:35:06", "remaining_time": "4:31:34"}
{"current_steps": 485, "total_steps": 4193, "loss": 0.3143, "lr": 3.9971608829022036e-05, "epoch": 0.8096828046744574, "percentage": 11.57, "elapsed_time": "0:35:29", "remaining_time": "4:31:18"}
{"current_steps": 490, "total_steps": 4193, "loss": 0.3028, "lr": 3.996700069055054e-05, "epoch": 0.8180300500834724, "percentage": 11.69, "elapsed_time": "0:35:48", "remaining_time": "4:30:36"}
{"current_steps": 495, "total_steps": 4193, "loss": 0.3143, "lr": 3.9962046470607034e-05, "epoch": 0.8263772954924875, "percentage": 11.81, "elapsed_time": "0:36:11", "remaining_time": "4:30:25"}
{"current_steps": 500, "total_steps": 4193, "loss": 0.3197, "lr": 3.995674625506137e-05, "epoch": 0.8347245409015025, "percentage": 11.92, "elapsed_time": "0:36:30", "remaining_time": "4:29:38"}
{"current_steps": 505, "total_steps": 4193, "loss": 0.3213, "lr": 3.995110013578046e-05, "epoch": 0.8430717863105175, "percentage": 12.04, "elapsed_time": "0:36:49", "remaining_time": "4:28:53"}
{"current_steps": 510, "total_steps": 4193, "loss": 0.308, "lr": 3.9945108210626635e-05, "epoch": 0.8514190317195326, "percentage": 12.16, "elapsed_time": "0:37:10", "remaining_time": "4:28:29"}
{"current_steps": 515, "total_steps": 4193, "loss": 0.3308, "lr": 3.9938770583455955e-05, "epoch": 0.8597662771285476, "percentage": 12.28, "elapsed_time": "0:37:25", "remaining_time": "4:27:15"}
{"current_steps": 520, "total_steps": 4193, "loss": 0.3297, "lr": 3.9932087364116446e-05, "epoch": 0.8681135225375626, "percentage": 12.4, "elapsed_time": "0:37:51", "remaining_time": "4:27:22"}
{"current_steps": 525, "total_steps": 4193, "loss": 0.2943, "lr": 3.992505866844615e-05, "epoch": 0.8764607679465777, "percentage": 12.52, "elapsed_time": "0:38:17", "remaining_time": "4:27:29"}
{"current_steps": 530, "total_steps": 4193, "loss": 0.3308, "lr": 3.991768461827114e-05, "epoch": 0.8848080133555927, "percentage": 12.64, "elapsed_time": "0:38:36", "remaining_time": "4:26:51"}
{"current_steps": 535, "total_steps": 4193, "loss": 0.3254, "lr": 3.990996534140342e-05, "epoch": 0.8931552587646077, "percentage": 12.76, "elapsed_time": "0:38:50", "remaining_time": "4:25:35"}
{"current_steps": 540, "total_steps": 4193, "loss": 0.2939, "lr": 3.990190097163867e-05, "epoch": 0.9015025041736227, "percentage": 12.88, "elapsed_time": "0:39:17", "remaining_time": "4:25:46"}
{"current_steps": 545, "total_steps": 4193, "loss": 0.3053, "lr": 3.989349164875397e-05, "epoch": 0.9098497495826378, "percentage": 13.0, "elapsed_time": "0:39:34", "remaining_time": "4:24:52"}
{"current_steps": 550, "total_steps": 4193, "loss": 0.3111, "lr": 3.988473751850536e-05, "epoch": 0.9181969949916527, "percentage": 13.12, "elapsed_time": "0:39:56", "remaining_time": "4:24:31"}
{"current_steps": 555, "total_steps": 4193, "loss": 0.3181, "lr": 3.98756387326253e-05, "epoch": 0.9265442404006677, "percentage": 13.24, "elapsed_time": "0:40:17", "remaining_time": "4:24:05"}
{"current_steps": 560, "total_steps": 4193, "loss": 0.3122, "lr": 3.9866195448820066e-05, "epoch": 0.9348914858096828, "percentage": 13.36, "elapsed_time": "0:40:34", "remaining_time": "4:23:15"}
{"current_steps": 565, "total_steps": 4193, "loss": 0.313, "lr": 3.985640783076699e-05, "epoch": 0.9432387312186978, "percentage": 13.47, "elapsed_time": "0:40:58", "remaining_time": "4:23:05"}
{"current_steps": 570, "total_steps": 4193, "loss": 0.3201, "lr": 3.984627604811166e-05, "epoch": 0.9515859766277128, "percentage": 13.59, "elapsed_time": "0:41:17", "remaining_time": "4:22:30"}
{"current_steps": 575, "total_steps": 4193, "loss": 0.292, "lr": 3.983580027646492e-05, "epoch": 0.9599332220367279, "percentage": 13.71, "elapsed_time": "0:41:37", "remaining_time": "4:21:52"}
{"current_steps": 580, "total_steps": 4193, "loss": 0.3159, "lr": 3.9824980697399906e-05, "epoch": 0.9682804674457429, "percentage": 13.83, "elapsed_time": "0:42:10", "remaining_time": "4:22:43"}
{"current_steps": 585, "total_steps": 4193, "loss": 0.3347, "lr": 3.981381749844882e-05, "epoch": 0.9766277128547579, "percentage": 13.95, "elapsed_time": "0:42:38", "remaining_time": "4:22:59"}
{"current_steps": 590, "total_steps": 4193, "loss": 0.3182, "lr": 3.980231087309971e-05, "epoch": 0.9849749582637729, "percentage": 14.07, "elapsed_time": "0:43:02", "remaining_time": "4:22:51"}
{"current_steps": 595, "total_steps": 4193, "loss": 0.3082, "lr": 3.9790461020793166e-05, "epoch": 0.993322203672788, "percentage": 14.19, "elapsed_time": "0:43:23", "remaining_time": "4:22:22"}
{"current_steps": 600, "total_steps": 4193, "loss": 0.3179, "lr": 3.977826814691878e-05, "epoch": 1.001669449081803, "percentage": 14.31, "elapsed_time": "0:43:41", "remaining_time": "4:21:40"}
{"current_steps": 605, "total_steps": 4193, "loss": 0.284, "lr": 3.9765732462811625e-05, "epoch": 1.010016694490818, "percentage": 14.43, "elapsed_time": "0:44:02", "remaining_time": "4:21:14"}
{"current_steps": 610, "total_steps": 4193, "loss": 0.3081, "lr": 3.975285418574862e-05, "epoch": 1.018363939899833, "percentage": 14.55, "elapsed_time": "0:44:26", "remaining_time": "4:21:03"}
{"current_steps": 615, "total_steps": 4193, "loss": 0.2998, "lr": 3.97396335389447e-05, "epoch": 1.026711185308848, "percentage": 14.67, "elapsed_time": "0:44:48", "remaining_time": "4:20:42"}
{"current_steps": 620, "total_steps": 4193, "loss": 0.3004, "lr": 3.972607075154901e-05, "epoch": 1.0350584307178632, "percentage": 14.79, "elapsed_time": "0:45:09", "remaining_time": "4:20:15"}
{"current_steps": 625, "total_steps": 4193, "loss": 0.3073, "lr": 3.971216605864087e-05, "epoch": 1.0434056761268782, "percentage": 14.91, "elapsed_time": "0:45:31", "remaining_time": "4:19:54"}
{"current_steps": 630, "total_steps": 4193, "loss": 0.2973, "lr": 3.969791970122579e-05, "epoch": 1.0517529215358932, "percentage": 15.03, "elapsed_time": "0:45:48", "remaining_time": "4:19:03"}
{"current_steps": 635, "total_steps": 4193, "loss": 0.2848, "lr": 3.96833319262312e-05, "epoch": 1.0601001669449082, "percentage": 15.14, "elapsed_time": "0:46:12", "remaining_time": "4:18:56"}
{"current_steps": 640, "total_steps": 4193, "loss": 0.2771, "lr": 3.9668402986502214e-05, "epoch": 1.0684474123539232, "percentage": 15.26, "elapsed_time": "0:46:30", "remaining_time": "4:18:09"}
{"current_steps": 645, "total_steps": 4193, "loss": 0.2866, "lr": 3.9653133140797244e-05, "epoch": 1.0767946577629381, "percentage": 15.38, "elapsed_time": "0:46:51", "remaining_time": "4:17:47"}
{"current_steps": 650, "total_steps": 4193, "loss": 0.2926, "lr": 3.963752265378352e-05, "epoch": 1.0851419031719534, "percentage": 15.5, "elapsed_time": "0:47:13", "remaining_time": "4:17:26"}
{"current_steps": 655, "total_steps": 4193, "loss": 0.2934, "lr": 3.962157179603249e-05, "epoch": 1.0934891485809684, "percentage": 15.62, "elapsed_time": "0:47:35", "remaining_time": "4:17:04"}
{"current_steps": 660, "total_steps": 4193, "loss": 0.2955, "lr": 3.960528084401515e-05, "epoch": 1.1018363939899833, "percentage": 15.74, "elapsed_time": "0:47:52", "remaining_time": "4:16:15"}
{"current_steps": 665, "total_steps": 4193, "loss": 0.3056, "lr": 3.9588650080097196e-05, "epoch": 1.1101836393989983, "percentage": 15.86, "elapsed_time": "0:48:08", "remaining_time": "4:15:25"}
{"current_steps": 670, "total_steps": 4193, "loss": 0.2988, "lr": 3.957167979253424e-05, "epoch": 1.1185308848080133, "percentage": 15.98, "elapsed_time": "0:48:37", "remaining_time": "4:15:39"}
{"current_steps": 675, "total_steps": 4193, "loss": 0.289, "lr": 3.955437027546668e-05, "epoch": 1.1268781302170283, "percentage": 16.1, "elapsed_time": "0:48:56", "remaining_time": "4:15:03"}
{"current_steps": 680, "total_steps": 4193, "loss": 0.2718, "lr": 3.953672182891471e-05, "epoch": 1.1352253756260433, "percentage": 16.22, "elapsed_time": "0:49:19", "remaining_time": "4:14:47"}
{"current_steps": 685, "total_steps": 4193, "loss": 0.2864, "lr": 3.951873475877306e-05, "epoch": 1.1435726210350585, "percentage": 16.34, "elapsed_time": "0:49:45", "remaining_time": "4:14:51"}
{"current_steps": 690, "total_steps": 4193, "loss": 0.2789, "lr": 3.950040937680572e-05, "epoch": 1.1519198664440735, "percentage": 16.46, "elapsed_time": "0:50:12", "remaining_time": "4:14:53"}
{"current_steps": 695, "total_steps": 4193, "loss": 0.2639, "lr": 3.948174600064051e-05, "epoch": 1.1602671118530885, "percentage": 16.58, "elapsed_time": "0:50:37", "remaining_time": "4:14:45"}
{"current_steps": 700, "total_steps": 4193, "loss": 0.2964, "lr": 3.946274495376362e-05, "epoch": 1.1686143572621035, "percentage": 16.69, "elapsed_time": "0:51:04", "remaining_time": "4:14:53"}
{"current_steps": 705, "total_steps": 4193, "loss": 0.2963, "lr": 3.9443406565513963e-05, "epoch": 1.1769616026711185, "percentage": 16.81, "elapsed_time": "0:51:30", "remaining_time": "4:14:52"}
{"current_steps": 710, "total_steps": 4193, "loss": 0.3017, "lr": 3.9423731171077465e-05, "epoch": 1.1853088480801335, "percentage": 16.93, "elapsed_time": "0:51:54", "remaining_time": "4:14:40"}
{"current_steps": 715, "total_steps": 4193, "loss": 0.2882, "lr": 3.9403719111481295e-05, "epoch": 1.1936560934891487, "percentage": 17.05, "elapsed_time": "0:52:18", "remaining_time": "4:14:25"}
{"current_steps": 720, "total_steps": 4193, "loss": 0.2731, "lr": 3.9383370733587905e-05, "epoch": 1.2020033388981637, "percentage": 17.17, "elapsed_time": "0:52:45", "remaining_time": "4:14:28"}
{"current_steps": 725, "total_steps": 4193, "loss": 0.272, "lr": 3.936268639008906e-05, "epoch": 1.2103505843071787, "percentage": 17.29, "elapsed_time": "0:53:08", "remaining_time": "4:14:13"}
{"current_steps": 730, "total_steps": 4193, "loss": 0.2921, "lr": 3.93416664394997e-05, "epoch": 1.2186978297161937, "percentage": 17.41, "elapsed_time": "0:53:27", "remaining_time": "4:13:33"}
{"current_steps": 735, "total_steps": 4193, "loss": 0.279, "lr": 3.932031124615172e-05, "epoch": 1.2270450751252087, "percentage": 17.53, "elapsed_time": "0:53:46", "remaining_time": "4:13:00"}
{"current_steps": 740, "total_steps": 4193, "loss": 0.2719, "lr": 3.92986211801877e-05, "epoch": 1.2353923205342237, "percentage": 17.65, "elapsed_time": "0:54:07", "remaining_time": "4:12:31"}
{"current_steps": 745, "total_steps": 4193, "loss": 0.2912, "lr": 3.927659661755442e-05, "epoch": 1.2437395659432386, "percentage": 17.77, "elapsed_time": "0:54:23", "remaining_time": "4:11:43"}
{"current_steps": 750, "total_steps": 4193, "loss": 0.2739, "lr": 3.925423793999641e-05, "epoch": 1.2520868113522536, "percentage": 17.89, "elapsed_time": "0:54:46", "remaining_time": "4:11:26"}
{"current_steps": 755, "total_steps": 4193, "loss": 0.2764, "lr": 3.923154553504929e-05, "epoch": 1.2604340567612689, "percentage": 18.01, "elapsed_time": "0:55:04", "remaining_time": "4:10:45"}
{"current_steps": 760, "total_steps": 4193, "loss": 0.2993, "lr": 3.920851979603306e-05, "epoch": 1.2687813021702838, "percentage": 18.13, "elapsed_time": "0:55:28", "remaining_time": "4:10:33"}
{"current_steps": 765, "total_steps": 4193, "loss": 0.2984, "lr": 3.918516112204532e-05, "epoch": 1.2771285475792988, "percentage": 18.24, "elapsed_time": "0:55:47", "remaining_time": "4:09:59"}
{"current_steps": 770, "total_steps": 4193, "loss": 0.3162, "lr": 3.9161469917954273e-05, "epoch": 1.2854757929883138, "percentage": 18.36, "elapsed_time": "0:56:03", "remaining_time": "4:09:11"}
{"current_steps": 775, "total_steps": 4193, "loss": 0.2742, "lr": 3.913744659439181e-05, "epoch": 1.2938230383973288, "percentage": 18.48, "elapsed_time": "0:56:23", "remaining_time": "4:08:40"}
{"current_steps": 780, "total_steps": 4193, "loss": 0.2749, "lr": 3.911309156774631e-05, "epoch": 1.302170283806344, "percentage": 18.6, "elapsed_time": "0:56:41", "remaining_time": "4:08:03"}
{"current_steps": 785, "total_steps": 4193, "loss": 0.2811, "lr": 3.908840526015547e-05, "epoch": 1.310517529215359, "percentage": 18.72, "elapsed_time": "0:56:59", "remaining_time": "4:07:24"}
{"current_steps": 790, "total_steps": 4193, "loss": 0.3044, "lr": 3.906338809949893e-05, "epoch": 1.318864774624374, "percentage": 18.84, "elapsed_time": "0:57:20", "remaining_time": "4:07:01"}
{"current_steps": 795, "total_steps": 4193, "loss": 0.2998, "lr": 3.903804051939096e-05, "epoch": 1.327212020033389, "percentage": 18.96, "elapsed_time": "0:57:42", "remaining_time": "4:06:40"}
{"current_steps": 800, "total_steps": 4193, "loss": 0.3111, "lr": 3.9012362959172834e-05, "epoch": 1.335559265442404, "percentage": 19.08, "elapsed_time": "0:58:05", "remaining_time": "4:06:22"}
{"current_steps": 805, "total_steps": 4193, "loss": 0.2954, "lr": 3.898635586390528e-05, "epoch": 1.343906510851419, "percentage": 19.2, "elapsed_time": "0:58:29", "remaining_time": "4:06:11"}
{"current_steps": 810, "total_steps": 4193, "loss": 0.2763, "lr": 3.8960019684360756e-05, "epoch": 1.352253756260434, "percentage": 19.32, "elapsed_time": "0:58:53", "remaining_time": "4:05:59"}
{"current_steps": 815, "total_steps": 4193, "loss": 0.3138, "lr": 3.8933354877015606e-05, "epoch": 1.360601001669449, "percentage": 19.44, "elapsed_time": "0:59:16", "remaining_time": "4:05:39"}
{"current_steps": 820, "total_steps": 4193, "loss": 0.2804, "lr": 3.89063619040422e-05, "epoch": 1.3689482470784642, "percentage": 19.56, "elapsed_time": "0:59:29", "remaining_time": "4:04:42"}
{"current_steps": 825, "total_steps": 4193, "loss": 0.2748, "lr": 3.887904123330088e-05, "epoch": 1.3772954924874792, "percentage": 19.68, "elapsed_time": "0:59:48", "remaining_time": "4:04:11"}
{"current_steps": 830, "total_steps": 4193, "loss": 0.2967, "lr": 3.885139333833186e-05, "epoch": 1.3856427378964942, "percentage": 19.79, "elapsed_time": "1:00:13", "remaining_time": "4:04:01"}
{"current_steps": 835, "total_steps": 4193, "loss": 0.2512, "lr": 3.882341869834704e-05, "epoch": 1.3939899833055092, "percentage": 19.91, "elapsed_time": "1:00:31", "remaining_time": "4:03:25"}
{"current_steps": 840, "total_steps": 4193, "loss": 0.2858, "lr": 3.879511779822168e-05, "epoch": 1.4023372287145242, "percentage": 20.03, "elapsed_time": "1:00:54", "remaining_time": "4:03:06"}
{"current_steps": 845, "total_steps": 4193, "loss": 0.2756, "lr": 3.8766491128486e-05, "epoch": 1.4106844741235394, "percentage": 20.15, "elapsed_time": "1:01:16", "remaining_time": "4:02:45"}
{"current_steps": 850, "total_steps": 4193, "loss": 0.2852, "lr": 3.873753918531666e-05, "epoch": 1.4190317195325544, "percentage": 20.27, "elapsed_time": "1:01:36", "remaining_time": "4:02:19"}
{"current_steps": 855, "total_steps": 4193, "loss": 0.2852, "lr": 3.87082624705282e-05, "epoch": 1.4273789649415694, "percentage": 20.39, "elapsed_time": "1:02:00", "remaining_time": "4:02:04"}
{"current_steps": 860, "total_steps": 4193, "loss": 0.2701, "lr": 3.867866149156431e-05, "epoch": 1.4357262103505843, "percentage": 20.51, "elapsed_time": "1:02:22", "remaining_time": "4:01:43"}
{"current_steps": 865, "total_steps": 4193, "loss": 0.3007, "lr": 3.8648736761489043e-05, "epoch": 1.4440734557595993, "percentage": 20.63, "elapsed_time": "1:02:45", "remaining_time": "4:01:26"}
{"current_steps": 870, "total_steps": 4193, "loss": 0.2999, "lr": 3.861848879897794e-05, "epoch": 1.4524207011686143, "percentage": 20.75, "elapsed_time": "1:03:04", "remaining_time": "4:00:56"}
{"current_steps": 875, "total_steps": 4193, "loss": 0.2732, "lr": 3.8587918128309e-05, "epoch": 1.4607679465776293, "percentage": 20.87, "elapsed_time": "1:03:30", "remaining_time": "4:00:48"}
{"current_steps": 880, "total_steps": 4193, "loss": 0.2951, "lr": 3.855702527935363e-05, "epoch": 1.4691151919866443, "percentage": 20.99, "elapsed_time": "1:03:56", "remaining_time": "4:00:43"}
{"current_steps": 885, "total_steps": 4193, "loss": 0.3166, "lr": 3.852581078756745e-05, "epoch": 1.4774624373956593, "percentage": 21.11, "elapsed_time": "1:04:15", "remaining_time": "4:00:11"}
{"current_steps": 890, "total_steps": 4193, "loss": 0.2845, "lr": 3.8494275193981e-05, "epoch": 1.4858096828046745, "percentage": 21.23, "elapsed_time": "1:04:34", "remaining_time": "3:59:38"}
{"current_steps": 895, "total_steps": 4193, "loss": 0.3106, "lr": 3.8462419045190385e-05, "epoch": 1.4941569282136895, "percentage": 21.35, "elapsed_time": "1:05:01", "remaining_time": "3:59:36"}
{"current_steps": 900, "total_steps": 4193, "loss": 0.2842, "lr": 3.8430242893347765e-05, "epoch": 1.5025041736227045, "percentage": 21.46, "elapsed_time": "1:05:17", "remaining_time": "3:58:51"}
{"current_steps": 905, "total_steps": 4193, "loss": 0.296, "lr": 3.839774729615184e-05, "epoch": 1.5108514190317195, "percentage": 21.58, "elapsed_time": "1:05:45", "remaining_time": "3:58:53"}
{"current_steps": 910, "total_steps": 4193, "loss": 0.2883, "lr": 3.8364932816838124e-05, "epoch": 1.5191986644407347, "percentage": 21.7, "elapsed_time": "1:06:04", "remaining_time": "3:58:22"}
{"current_steps": 915, "total_steps": 4193, "loss": 0.2858, "lr": 3.833180002416922e-05, "epoch": 1.5275459098497497, "percentage": 21.82, "elapsed_time": "1:06:23", "remaining_time": "3:57:50"}
{"current_steps": 920, "total_steps": 4193, "loss": 0.2702, "lr": 3.829834949242496e-05, "epoch": 1.5358931552587647, "percentage": 21.94, "elapsed_time": "1:06:41", "remaining_time": "3:57:16"}
{"current_steps": 925, "total_steps": 4193, "loss": 0.2723, "lr": 3.826458180139244e-05, "epoch": 1.5442404006677797, "percentage": 22.06, "elapsed_time": "1:07:00", "remaining_time": "3:56:45"}
{"current_steps": 930, "total_steps": 4193, "loss": 0.3098, "lr": 3.823049753635596e-05, "epoch": 1.5525876460767947, "percentage": 22.18, "elapsed_time": "1:07:21", "remaining_time": "3:56:19"}
{"current_steps": 935, "total_steps": 4193, "loss": 0.2658, "lr": 3.81960972880869e-05, "epoch": 1.5609348914858097, "percentage": 22.3, "elapsed_time": "1:07:37", "remaining_time": "3:55:37"}
{"current_steps": 940, "total_steps": 4193, "loss": 0.2831, "lr": 3.8161381652833485e-05, "epoch": 1.5692821368948247, "percentage": 22.42, "elapsed_time": "1:08:01", "remaining_time": "3:55:23"}
{"current_steps": 945, "total_steps": 4193, "loss": 0.2813, "lr": 3.812635123231043e-05, "epoch": 1.5776293823038396, "percentage": 22.54, "elapsed_time": "1:08:24", "remaining_time": "3:55:08"}
{"current_steps": 950, "total_steps": 4193, "loss": 0.2678, "lr": 3.809100663368852e-05, "epoch": 1.5859766277128546, "percentage": 22.66, "elapsed_time": "1:08:47", "remaining_time": "3:54:49"}
{"current_steps": 955, "total_steps": 4193, "loss": 0.2855, "lr": 3.805534846958408e-05, "epoch": 1.5943238731218696, "percentage": 22.78, "elapsed_time": "1:09:13", "remaining_time": "3:54:42"}
{"current_steps": 960, "total_steps": 4193, "loss": 0.3016, "lr": 3.801937735804838e-05, "epoch": 1.6026711185308848, "percentage": 22.9, "elapsed_time": "1:09:35", "remaining_time": "3:54:20"}
{"current_steps": 965, "total_steps": 4193, "loss": 0.2758, "lr": 3.79830939225569e-05, "epoch": 1.6110183639398998, "percentage": 23.01, "elapsed_time": "1:09:54", "remaining_time": "3:53:52"}
{"current_steps": 970, "total_steps": 4193, "loss": 0.281, "lr": 3.79464987919985e-05, "epoch": 1.6193656093489148, "percentage": 23.13, "elapsed_time": "1:10:11", "remaining_time": "3:53:14"}
{"current_steps": 975, "total_steps": 4193, "loss": 0.2919, "lr": 3.790959260066459e-05, "epoch": 1.62771285475793, "percentage": 23.25, "elapsed_time": "1:10:30", "remaining_time": "3:52:42"}
{"current_steps": 980, "total_steps": 4193, "loss": 0.2713, "lr": 3.7872375988238075e-05, "epoch": 1.636060100166945, "percentage": 23.37, "elapsed_time": "1:10:48", "remaining_time": "3:52:08"}
{"current_steps": 985, "total_steps": 4193, "loss": 0.2898, "lr": 3.783484959978228e-05, "epoch": 1.64440734557596, "percentage": 23.49, "elapsed_time": "1:11:01", "remaining_time": "3:51:18"}
{"current_steps": 990, "total_steps": 4193, "loss": 0.2683, "lr": 3.7797014085729786e-05, "epoch": 1.652754590984975, "percentage": 23.61, "elapsed_time": "1:11:21", "remaining_time": "3:50:53"}
{"current_steps": 995, "total_steps": 4193, "loss": 0.2636, "lr": 3.7758870101871155e-05, "epoch": 1.66110183639399, "percentage": 23.73, "elapsed_time": "1:11:42", "remaining_time": "3:50:29"}
{"current_steps": 1000, "total_steps": 4193, "loss": 0.2722, "lr": 3.772041830934352e-05, "epoch": 1.669449081803005, "percentage": 23.85, "elapsed_time": "1:12:03", "remaining_time": "3:50:04"}
{"current_steps": 1005, "total_steps": 4193, "loss": 0.2955, "lr": 3.7681659374619216e-05, "epoch": 1.67779632721202, "percentage": 23.97, "elapsed_time": "1:12:22", "remaining_time": "3:49:35"}
{"current_steps": 1010, "total_steps": 4193, "loss": 0.2861, "lr": 3.764259396949412e-05, "epoch": 1.686143572621035, "percentage": 24.09, "elapsed_time": "1:12:43", "remaining_time": "3:49:11"}
{"current_steps": 1015, "total_steps": 4193, "loss": 0.292, "lr": 3.7603222771076094e-05, "epoch": 1.69449081803005, "percentage": 24.21, "elapsed_time": "1:13:06", "remaining_time": "3:48:53"}
{"current_steps": 1020, "total_steps": 4193, "loss": 0.2744, "lr": 3.75635464617732e-05, "epoch": 1.702838063439065, "percentage": 24.33, "elapsed_time": "1:13:29", "remaining_time": "3:48:37"}
{"current_steps": 1025, "total_steps": 4193, "loss": 0.2703, "lr": 3.752356572928189e-05, "epoch": 1.7111853088480802, "percentage": 24.45, "elapsed_time": "1:13:47", "remaining_time": "3:48:04"}
{"current_steps": 1030, "total_steps": 4193, "loss": 0.2806, "lr": 3.748328126657508e-05, "epoch": 1.7195325542570952, "percentage": 24.56, "elapsed_time": "1:14:08", "remaining_time": "3:47:41"}
{"current_steps": 1035, "total_steps": 4193, "loss": 0.2671, "lr": 3.7442693771890134e-05, "epoch": 1.7278797996661102, "percentage": 24.68, "elapsed_time": "1:14:23", "remaining_time": "3:46:58"}
{"current_steps": 1040, "total_steps": 4193, "loss": 0.2722, "lr": 3.740180394871681e-05, "epoch": 1.7362270450751254, "percentage": 24.8, "elapsed_time": "1:14:42", "remaining_time": "3:46:29"}
{"current_steps": 1045, "total_steps": 4193, "loss": 0.2753, "lr": 3.736061250578498e-05, "epoch": 1.7445742904841404, "percentage": 24.92, "elapsed_time": "1:15:08", "remaining_time": "3:46:20"}
{"current_steps": 1050, "total_steps": 4193, "loss": 0.2575, "lr": 3.7319120157052405e-05, "epoch": 1.7529215358931554, "percentage": 25.04, "elapsed_time": "1:15:25", "remaining_time": "3:45:47"}
{"current_steps": 1055, "total_steps": 4193, "loss": 0.2853, "lr": 3.727732762169236e-05, "epoch": 1.7612687813021703, "percentage": 25.16, "elapsed_time": "1:15:51", "remaining_time": "3:45:38"}
{"current_steps": 1060, "total_steps": 4193, "loss": 0.2644, "lr": 3.7235235624081144e-05, "epoch": 1.7696160267111853, "percentage": 25.28, "elapsed_time": "1:16:12", "remaining_time": "3:45:13"}
{"current_steps": 1065, "total_steps": 4193, "loss": 0.2737, "lr": 3.719284489378555e-05, "epoch": 1.7779632721202003, "percentage": 25.4, "elapsed_time": "1:16:30", "remaining_time": "3:44:41"}
{"current_steps": 1070, "total_steps": 4193, "loss": 0.3061, "lr": 3.715015616555019e-05, "epoch": 1.7863105175292153, "percentage": 25.52, "elapsed_time": "1:16:47", "remaining_time": "3:44:09"}
{"current_steps": 1075, "total_steps": 4193, "loss": 0.2834, "lr": 3.710717017928479e-05, "epoch": 1.7946577629382303, "percentage": 25.64, "elapsed_time": "1:17:11", "remaining_time": "3:43:53"}
{"current_steps": 1080, "total_steps": 4193, "loss": 0.259, "lr": 3.7063887680051346e-05, "epoch": 1.8030050083472453, "percentage": 25.76, "elapsed_time": "1:17:32", "remaining_time": "3:43:29"}
{"current_steps": 1085, "total_steps": 4193, "loss": 0.2852, "lr": 3.702030941805122e-05, "epoch": 1.8113522537562603, "percentage": 25.88, "elapsed_time": "1:17:54", "remaining_time": "3:43:11"}
{"current_steps": 1090, "total_steps": 4193, "loss": 0.2949, "lr": 3.697643614861212e-05, "epoch": 1.8196994991652755, "percentage": 26.0, "elapsed_time": "1:18:19", "remaining_time": "3:42:57"}
{"current_steps": 1095, "total_steps": 4193, "loss": 0.2929, "lr": 3.6932268632175035e-05, "epoch": 1.8280467445742905, "percentage": 26.11, "elapsed_time": "1:18:43", "remaining_time": "3:42:44"}
{"current_steps": 1100, "total_steps": 4193, "loss": 0.2794, "lr": 3.6887807634281034e-05, "epoch": 1.8363939899833055, "percentage": 26.23, "elapsed_time": "1:19:00", "remaining_time": "3:42:08"}
{"current_steps": 1105, "total_steps": 4193, "loss": 0.2854, "lr": 3.684305392555802e-05, "epoch": 1.8447412353923205, "percentage": 26.35, "elapsed_time": "1:19:25", "remaining_time": "3:41:56"}
{"current_steps": 1110, "total_steps": 4193, "loss": 0.2586, "lr": 3.6798008281707326e-05, "epoch": 1.8530884808013357, "percentage": 26.47, "elapsed_time": "1:19:50", "remaining_time": "3:41:45"}
{"current_steps": 1115, "total_steps": 4193, "loss": 0.2673, "lr": 3.675267148349033e-05, "epoch": 1.8614357262103507, "percentage": 26.59, "elapsed_time": "1:20:19", "remaining_time": "3:41:43"}
{"current_steps": 1120, "total_steps": 4193, "loss": 0.2736, "lr": 3.670704431671487e-05, "epoch": 1.8697829716193657, "percentage": 26.71, "elapsed_time": "1:20:37", "remaining_time": "3:41:13"}
{"current_steps": 1125, "total_steps": 4193, "loss": 0.27, "lr": 3.6661127572221674e-05, "epoch": 1.8781302170283807, "percentage": 26.83, "elapsed_time": "1:20:55", "remaining_time": "3:40:42"}
{"current_steps": 1130, "total_steps": 4193, "loss": 0.2945, "lr": 3.661492204587059e-05, "epoch": 1.8864774624373957, "percentage": 26.95, "elapsed_time": "1:21:18", "remaining_time": "3:40:24"}
{"current_steps": 1135, "total_steps": 4193, "loss": 0.2693, "lr": 3.656842853852686e-05, "epoch": 1.8948247078464107, "percentage": 27.07, "elapsed_time": "1:21:33", "remaining_time": "3:39:44"}
{"current_steps": 1140, "total_steps": 4193, "loss": 0.273, "lr": 3.652164785604718e-05, "epoch": 1.9031719532554257, "percentage": 27.19, "elapsed_time": "1:21:47", "remaining_time": "3:39:03"}
{"current_steps": 1145, "total_steps": 4193, "loss": 0.2662, "lr": 3.647458080926579e-05, "epoch": 1.9115191986644406, "percentage": 27.31, "elapsed_time": "1:22:09", "remaining_time": "3:38:42"}
{"current_steps": 1150, "total_steps": 4193, "loss": 0.3147, "lr": 3.642722821398036e-05, "epoch": 1.9198664440734556, "percentage": 27.43, "elapsed_time": "1:22:36", "remaining_time": "3:38:35"}
{"current_steps": 1155, "total_steps": 4193, "loss": 0.2565, "lr": 3.637959089093788e-05, "epoch": 1.9282136894824706, "percentage": 27.55, "elapsed_time": "1:22:56", "remaining_time": "3:38:08"}
{"current_steps": 1160, "total_steps": 4193, "loss": 0.2729, "lr": 3.633166966582046e-05, "epoch": 1.9365609348914858, "percentage": 27.67, "elapsed_time": "1:23:16", "remaining_time": "3:37:43"}
{"current_steps": 1165, "total_steps": 4193, "loss": 0.2587, "lr": 3.6283465369230955e-05, "epoch": 1.9449081803005008, "percentage": 27.78, "elapsed_time": "1:23:30", "remaining_time": "3:37:04"}
{"current_steps": 1170, "total_steps": 4193, "loss": 0.2942, "lr": 3.6234978836678635e-05, "epoch": 1.9532554257095158, "percentage": 27.9, "elapsed_time": "1:23:54", "remaining_time": "3:36:46"}
{"current_steps": 1175, "total_steps": 4193, "loss": 0.2713, "lr": 3.618621090856465e-05, "epoch": 1.961602671118531, "percentage": 28.02, "elapsed_time": "1:24:17", "remaining_time": "3:36:29"}
{"current_steps": 1180, "total_steps": 4193, "loss": 0.2715, "lr": 3.6137162430167505e-05, "epoch": 1.969949916527546, "percentage": 28.14, "elapsed_time": "1:24:39", "remaining_time": "3:36:10"}
{"current_steps": 1185, "total_steps": 4193, "loss": 0.2775, "lr": 3.608783425162837e-05, "epoch": 1.978297161936561, "percentage": 28.26, "elapsed_time": "1:25:06", "remaining_time": "3:36:01"}
{"current_steps": 1190, "total_steps": 4193, "loss": 0.2683, "lr": 3.603822722793641e-05, "epoch": 1.986644407345576, "percentage": 28.38, "elapsed_time": "1:25:25", "remaining_time": "3:35:33"}
{"current_steps": 1195, "total_steps": 4193, "loss": 0.3039, "lr": 3.598834221891386e-05, "epoch": 1.994991652754591, "percentage": 28.5, "elapsed_time": "1:25:55", "remaining_time": "3:35:33"}
{"current_steps": 1200, "total_steps": 4193, "loss": 0.2469, "lr": 3.5938180089201236e-05, "epoch": 2.003338898163606, "percentage": 28.62, "elapsed_time": "1:26:16", "remaining_time": "3:35:11"}
{"current_steps": 1205, "total_steps": 4193, "loss": 0.2559, "lr": 3.588774170824225e-05, "epoch": 2.011686143572621, "percentage": 28.74, "elapsed_time": "1:26:43", "remaining_time": "3:35:02"}
{"current_steps": 1210, "total_steps": 4193, "loss": 0.2352, "lr": 3.5837027950268845e-05, "epoch": 2.020033388981636, "percentage": 28.86, "elapsed_time": "1:27:05", "remaining_time": "3:34:42"}
{"current_steps": 1215, "total_steps": 4193, "loss": 0.2314, "lr": 3.578603969428592e-05, "epoch": 2.028380634390651, "percentage": 28.98, "elapsed_time": "1:27:18", "remaining_time": "3:34:00"}
{"current_steps": 1220, "total_steps": 4193, "loss": 0.2476, "lr": 3.57347778240562e-05, "epoch": 2.036727879799666, "percentage": 29.1, "elapsed_time": "1:27:40", "remaining_time": "3:33:39"}
{"current_steps": 1225, "total_steps": 4193, "loss": 0.2559, "lr": 3.568324322808486e-05, "epoch": 2.045075125208681, "percentage": 29.22, "elapsed_time": "1:28:05", "remaining_time": "3:33:25"}
{"current_steps": 1230, "total_steps": 4193, "loss": 0.2435, "lr": 3.563143679960415e-05, "epoch": 2.053422370617696, "percentage": 29.33, "elapsed_time": "1:28:23", "remaining_time": "3:32:56"}
{"current_steps": 1235, "total_steps": 4193, "loss": 0.2225, "lr": 3.557935943655789e-05, "epoch": 2.0617696160267114, "percentage": 29.45, "elapsed_time": "1:28:45", "remaining_time": "3:32:35"}
{"current_steps": 1240, "total_steps": 4193, "loss": 0.2537, "lr": 3.5527012041585936e-05, "epoch": 2.0701168614357264, "percentage": 29.57, "elapsed_time": "1:29:05", "remaining_time": "3:32:09"}
{"current_steps": 1245, "total_steps": 4193, "loss": 0.2527, "lr": 3.5474395522008496e-05, "epoch": 2.0784641068447414, "percentage": 29.69, "elapsed_time": "1:29:22", "remaining_time": "3:31:36"}
{"current_steps": 1250, "total_steps": 4193, "loss": 0.232, "lr": 3.542151078981046e-05, "epoch": 2.0868113522537564, "percentage": 29.81, "elapsed_time": "1:29:42", "remaining_time": "3:31:13"}
{"current_steps": 1255, "total_steps": 4193, "loss": 0.2492, "lr": 3.5368358761625514e-05, "epoch": 2.0951585976627713, "percentage": 29.93, "elapsed_time": "1:29:57", "remaining_time": "3:30:34"}
{"current_steps": 1260, "total_steps": 4193, "loss": 0.2438, "lr": 3.5314940358720356e-05, "epoch": 2.1035058430717863, "percentage": 30.05, "elapsed_time": "1:30:16", "remaining_time": "3:30:07"}
{"current_steps": 1265, "total_steps": 4193, "loss": 0.2494, "lr": 3.5261256506978615e-05, "epoch": 2.1118530884808013, "percentage": 30.17, "elapsed_time": "1:30:39", "remaining_time": "3:29:50"}
{"current_steps": 1270, "total_steps": 4193, "loss": 0.2297, "lr": 3.5207308136884894e-05, "epoch": 2.1202003338898163, "percentage": 30.29, "elapsed_time": "1:31:08", "remaining_time": "3:29:45"}
{"current_steps": 1275, "total_steps": 4193, "loss": 0.2542, "lr": 3.515309618350858e-05, "epoch": 2.1285475792988313, "percentage": 30.41, "elapsed_time": "1:31:34", "remaining_time": "3:29:34"}
{"current_steps": 1280, "total_steps": 4193, "loss": 0.251, "lr": 3.509862158648768e-05, "epoch": 2.1368948247078463, "percentage": 30.53, "elapsed_time": "1:31:53", "remaining_time": "3:29:07"}
{"current_steps": 1285, "total_steps": 4193, "loss": 0.2477, "lr": 3.504388529001252e-05, "epoch": 2.1452420701168613, "percentage": 30.65, "elapsed_time": "1:32:13", "remaining_time": "3:28:42"}
{"current_steps": 1290, "total_steps": 4193, "loss": 0.2291, "lr": 3.498888824280935e-05, "epoch": 2.1535893155258763, "percentage": 30.77, "elapsed_time": "1:32:31", "remaining_time": "3:28:13"}
{"current_steps": 1295, "total_steps": 4193, "loss": 0.2432, "lr": 3.4933631398123956e-05, "epoch": 2.1619365609348913, "percentage": 30.88, "elapsed_time": "1:32:45", "remaining_time": "3:27:34"}
{"current_steps": 1300, "total_steps": 4193, "loss": 0.2365, "lr": 3.487811571370509e-05, "epoch": 2.1702838063439067, "percentage": 31.0, "elapsed_time": "1:33:07", "remaining_time": "3:27:13"}
{"current_steps": 1305, "total_steps": 4193, "loss": 0.2313, "lr": 3.482234215178791e-05, "epoch": 2.1786310517529217, "percentage": 31.12, "elapsed_time": "1:33:33", "remaining_time": "3:27:02"}
{"current_steps": 1310, "total_steps": 4193, "loss": 0.2199, "lr": 3.476631167907727e-05, "epoch": 2.1869782971619367, "percentage": 31.24, "elapsed_time": "1:33:54", "remaining_time": "3:26:40"}
{"current_steps": 1315, "total_steps": 4193, "loss": 0.264, "lr": 3.471002526673094e-05, "epoch": 2.1953255425709517, "percentage": 31.36, "elapsed_time": "1:34:16", "remaining_time": "3:26:19"}
{"current_steps": 1320, "total_steps": 4193, "loss": 0.2474, "lr": 3.465348389034287e-05, "epoch": 2.2036727879799667, "percentage": 31.48, "elapsed_time": "1:34:34", "remaining_time": "3:25:51"}
{"current_steps": 1325, "total_steps": 4193, "loss": 0.2378, "lr": 3.459668852992617e-05, "epoch": 2.2120200333889817, "percentage": 31.6, "elapsed_time": "1:34:59", "remaining_time": "3:25:37"}
{"current_steps": 1330, "total_steps": 4193, "loss": 0.2362, "lr": 3.453964016989619e-05, "epoch": 2.2203672787979967, "percentage": 31.72, "elapsed_time": "1:35:19", "remaining_time": "3:25:11"}
{"current_steps": 1335, "total_steps": 4193, "loss": 0.2425, "lr": 3.4482339799053444e-05, "epoch": 2.2287145242070117, "percentage": 31.84, "elapsed_time": "1:35:35", "remaining_time": "3:24:38"}
{"current_steps": 1340, "total_steps": 4193, "loss": 0.2316, "lr": 3.4424788410566455e-05, "epoch": 2.2370617696160267, "percentage": 31.96, "elapsed_time": "1:36:01", "remaining_time": "3:24:25"}
{"current_steps": 1345, "total_steps": 4193, "loss": 0.238, "lr": 3.4366987001954555e-05, "epoch": 2.2454090150250416, "percentage": 32.08, "elapsed_time": "1:36:22", "remaining_time": "3:24:05"}
{"current_steps": 1350, "total_steps": 4193, "loss": 0.232, "lr": 3.43089365750706e-05, "epoch": 2.2537562604340566, "percentage": 32.2, "elapsed_time": "1:36:43", "remaining_time": "3:23:42"}
{"current_steps": 1355, "total_steps": 4193, "loss": 0.2424, "lr": 3.425063813608359e-05, "epoch": 2.2621035058430716, "percentage": 32.32, "elapsed_time": "1:37:00", "remaining_time": "3:23:10"}
{"current_steps": 1360, "total_steps": 4193, "loss": 0.2455, "lr": 3.419209269546125e-05, "epoch": 2.2704507512520866, "percentage": 32.44, "elapsed_time": "1:37:18", "remaining_time": "3:22:42"}
{"current_steps": 1365, "total_steps": 4193, "loss": 0.2318, "lr": 3.4133301267952486e-05, "epoch": 2.278797996661102, "percentage": 32.55, "elapsed_time": "1:37:39", "remaining_time": "3:22:19"}
{"current_steps": 1370, "total_steps": 4193, "loss": 0.2605, "lr": 3.407426487256982e-05, "epoch": 2.287145242070117, "percentage": 32.67, "elapsed_time": "1:38:00", "remaining_time": "3:21:57"}
{"current_steps": 1375, "total_steps": 4193, "loss": 0.2515, "lr": 3.401498453257172e-05, "epoch": 2.295492487479132, "percentage": 32.79, "elapsed_time": "1:38:16", "remaining_time": "3:21:23"}
{"current_steps": 1380, "total_steps": 4193, "loss": 0.2379, "lr": 3.395546127544489e-05, "epoch": 2.303839732888147, "percentage": 32.91, "elapsed_time": "1:38:39", "remaining_time": "3:21:07"}
{"current_steps": 1385, "total_steps": 4193, "loss": 0.2546, "lr": 3.389569613288641e-05, "epoch": 2.312186978297162, "percentage": 33.03, "elapsed_time": "1:39:04", "remaining_time": "3:20:53"}
{"current_steps": 1390, "total_steps": 4193, "loss": 0.2448, "lr": 3.383569014078587e-05, "epoch": 2.320534223706177, "percentage": 33.15, "elapsed_time": "1:39:32", "remaining_time": "3:20:44"}
{"current_steps": 1395, "total_steps": 4193, "loss": 0.2311, "lr": 3.3775444339207465e-05, "epoch": 2.328881469115192, "percentage": 33.27, "elapsed_time": "1:39:50", "remaining_time": "3:20:16"}
{"current_steps": 1400, "total_steps": 4193, "loss": 0.2211, "lr": 3.3714959772371885e-05, "epoch": 2.337228714524207, "percentage": 33.39, "elapsed_time": "1:40:14", "remaining_time": "3:19:59"}
{"current_steps": 1405, "total_steps": 4193, "loss": 0.2338, "lr": 3.3654237488638306e-05, "epoch": 2.345575959933222, "percentage": 33.51, "elapsed_time": "1:40:33", "remaining_time": "3:19:32"}
{"current_steps": 1410, "total_steps": 4193, "loss": 0.2258, "lr": 3.3593278540486135e-05, "epoch": 2.353923205342237, "percentage": 33.63, "elapsed_time": "1:40:53", "remaining_time": "3:19:08"}
{"current_steps": 1415, "total_steps": 4193, "loss": 0.2497, "lr": 3.353208398449683e-05, "epoch": 2.362270450751252, "percentage": 33.75, "elapsed_time": "1:41:17", "remaining_time": "3:18:51"}
{"current_steps": 1420, "total_steps": 4193, "loss": 0.2489, "lr": 3.347065488133555e-05, "epoch": 2.370617696160267, "percentage": 33.87, "elapsed_time": "1:41:39", "remaining_time": "3:18:31"}
{"current_steps": 1425, "total_steps": 4193, "loss": 0.236, "lr": 3.340899229573278e-05, "epoch": 2.378964941569282, "percentage": 33.99, "elapsed_time": "1:41:55", "remaining_time": "3:17:59"}
{"current_steps": 1430, "total_steps": 4193, "loss": 0.2504, "lr": 3.334709729646589e-05, "epoch": 2.3873121869782974, "percentage": 34.1, "elapsed_time": "1:42:16", "remaining_time": "3:17:35"}
{"current_steps": 1435, "total_steps": 4193, "loss": 0.2388, "lr": 3.32849709563406e-05, "epoch": 2.395659432387312, "percentage": 34.22, "elapsed_time": "1:42:38", "remaining_time": "3:17:16"}
{"current_steps": 1440, "total_steps": 4193, "loss": 0.2663, "lr": 3.322261435217237e-05, "epoch": 2.4040066777963274, "percentage": 34.34, "elapsed_time": "1:43:05", "remaining_time": "3:17:04"}
{"current_steps": 1445, "total_steps": 4193, "loss": 0.2436, "lr": 3.316002856476776e-05, "epoch": 2.4123539232053424, "percentage": 34.46, "elapsed_time": "1:43:27", "remaining_time": "3:16:45"}
{"current_steps": 1450, "total_steps": 4193, "loss": 0.2428, "lr": 3.309721467890571e-05, "epoch": 2.4207011686143574, "percentage": 34.58, "elapsed_time": "1:43:46", "remaining_time": "3:16:18"}
{"current_steps": 1455, "total_steps": 4193, "loss": 0.2411, "lr": 3.303417378331867e-05, "epoch": 2.4290484140233723, "percentage": 34.7, "elapsed_time": "1:43:58", "remaining_time": "3:15:40"}
{"current_steps": 1460, "total_steps": 4193, "loss": 0.2357, "lr": 3.2970906970673814e-05, "epoch": 2.4373956594323873, "percentage": 34.82, "elapsed_time": "1:44:14", "remaining_time": "3:15:08"}
{"current_steps": 1465, "total_steps": 4193, "loss": 0.2418, "lr": 3.2907415337554045e-05, "epoch": 2.4457429048414023, "percentage": 34.94, "elapsed_time": "1:44:39", "remaining_time": "3:14:52"}
{"current_steps": 1470, "total_steps": 4193, "loss": 0.2505, "lr": 3.284369998443901e-05, "epoch": 2.4540901502504173, "percentage": 35.06, "elapsed_time": "1:45:01", "remaining_time": "3:14:33"}
{"current_steps": 1475, "total_steps": 4193, "loss": 0.2295, "lr": 3.277976201568603e-05, "epoch": 2.4624373956594323, "percentage": 35.18, "elapsed_time": "1:45:19", "remaining_time": "3:14:04"}
{"current_steps": 1480, "total_steps": 4193, "loss": 0.2542, "lr": 3.2715602539510915e-05, "epoch": 2.4707846410684473, "percentage": 35.3, "elapsed_time": "1:45:37", "remaining_time": "3:13:37"}
{"current_steps": 1485, "total_steps": 4193, "loss": 0.2647, "lr": 3.265122266796884e-05, "epoch": 2.4791318864774623, "percentage": 35.42, "elapsed_time": "1:46:03", "remaining_time": "3:13:23"}
{"current_steps": 1490, "total_steps": 4193, "loss": 0.2315, "lr": 3.258662351693498e-05, "epoch": 2.4874791318864773, "percentage": 35.54, "elapsed_time": "1:46:31", "remaining_time": "3:13:15"}
{"current_steps": 1495, "total_steps": 4193, "loss": 0.2424, "lr": 3.252180620608524e-05, "epoch": 2.4958263772954927, "percentage": 35.65, "elapsed_time": "1:46:51", "remaining_time": "3:12:51"}
{"current_steps": 1500, "total_steps": 4193, "loss": 0.2345, "lr": 3.245677185887678e-05, "epoch": 2.5041736227045073, "percentage": 35.77, "elapsed_time": "1:47:12", "remaining_time": "3:12:29"}
{"current_steps": 1505, "total_steps": 4193, "loss": 0.2513, "lr": 3.2391521602528634e-05, "epoch": 2.5125208681135227, "percentage": 35.89, "elapsed_time": "1:47:45", "remaining_time": "3:12:28"}
{"current_steps": 1510, "total_steps": 4193, "loss": 0.2239, "lr": 3.232605656800207e-05, "epoch": 2.5208681135225377, "percentage": 36.01, "elapsed_time": "1:48:05", "remaining_time": "3:12:04"}
{"current_steps": 1515, "total_steps": 4193, "loss": 0.2466, "lr": 3.226037788998105e-05, "epoch": 2.5292153589315527, "percentage": 36.13, "elapsed_time": "1:48:31", "remaining_time": "3:11:50"}
{"current_steps": 1520, "total_steps": 4193, "loss": 0.2511, "lr": 3.219448670685256e-05, "epoch": 2.5375626043405677, "percentage": 36.25, "elapsed_time": "1:48:55", "remaining_time": "3:11:32"}
{"current_steps": 1525, "total_steps": 4193, "loss": 0.2504, "lr": 3.212838416068685e-05, "epoch": 2.5459098497495827, "percentage": 36.37, "elapsed_time": "1:49:20", "remaining_time": "3:11:17"}
{"current_steps": 1530, "total_steps": 4193, "loss": 0.2368, "lr": 3.206207139721768e-05, "epoch": 2.5542570951585977, "percentage": 36.49, "elapsed_time": "1:49:39", "remaining_time": "3:10:52"}
{"current_steps": 1535, "total_steps": 4193, "loss": 0.2429, "lr": 3.199554956582241e-05, "epoch": 2.5626043405676127, "percentage": 36.61, "elapsed_time": "1:50:02", "remaining_time": "3:10:33"}
{"current_steps": 1540, "total_steps": 4193, "loss": 0.2293, "lr": 3.192881981950212e-05, "epoch": 2.5709515859766277, "percentage": 36.73, "elapsed_time": "1:50:24", "remaining_time": "3:10:11"}
{"current_steps": 1545, "total_steps": 4193, "loss": 0.2451, "lr": 3.1861883314861616e-05, "epoch": 2.5792988313856426, "percentage": 36.85, "elapsed_time": "1:50:47", "remaining_time": "3:09:53"}
{"current_steps": 1550, "total_steps": 4193, "loss": 0.2384, "lr": 3.179474121208937e-05, "epoch": 2.5876460767946576, "percentage": 36.97, "elapsed_time": "1:51:06", "remaining_time": "3:09:26"}
{"current_steps": 1555, "total_steps": 4193, "loss": 0.239, "lr": 3.172739467493741e-05, "epoch": 2.5959933222036726, "percentage": 37.09, "elapsed_time": "1:51:26", "remaining_time": "3:09:04"}
{"current_steps": 1560, "total_steps": 4193, "loss": 0.2362, "lr": 3.165984487070118e-05, "epoch": 2.604340567612688, "percentage": 37.2, "elapsed_time": "1:51:49", "remaining_time": "3:08:44"}
{"current_steps": 1565, "total_steps": 4193, "loss": 0.2258, "lr": 3.1592092970199266e-05, "epoch": 2.6126878130217026, "percentage": 37.32, "elapsed_time": "1:52:07", "remaining_time": "3:08:16"}
{"current_steps": 1570, "total_steps": 4193, "loss": 0.262, "lr": 3.152414014775315e-05, "epoch": 2.621035058430718, "percentage": 37.44, "elapsed_time": "1:52:27", "remaining_time": "3:07:53"}
{"current_steps": 1575, "total_steps": 4193, "loss": 0.2464, "lr": 3.1455987581166784e-05, "epoch": 2.629382303839733, "percentage": 37.56, "elapsed_time": "1:52:47", "remaining_time": "3:07:28"}
{"current_steps": 1580, "total_steps": 4193, "loss": 0.2301, "lr": 3.138763645170626e-05, "epoch": 2.637729549248748, "percentage": 37.68, "elapsed_time": "1:53:02", "remaining_time": "3:06:56"}
{"current_steps": 1585, "total_steps": 4193, "loss": 0.2553, "lr": 3.1319087944079275e-05, "epoch": 2.646076794657763, "percentage": 37.8, "elapsed_time": "1:53:24", "remaining_time": "3:06:37"}
{"current_steps": 1590, "total_steps": 4193, "loss": 0.2492, "lr": 3.125034324641462e-05, "epoch": 2.654424040066778, "percentage": 37.92, "elapsed_time": "1:53:43", "remaining_time": "3:06:11"}
{"current_steps": 1595, "total_steps": 4193, "loss": 0.2539, "lr": 3.118140355024159e-05, "epoch": 2.662771285475793, "percentage": 38.04, "elapsed_time": "1:54:02", "remaining_time": "3:05:44"}
{"current_steps": 1600, "total_steps": 4193, "loss": 0.2472, "lr": 3.111227005046932e-05, "epoch": 2.671118530884808, "percentage": 38.16, "elapsed_time": "1:54:18", "remaining_time": "3:05:15"}
{"current_steps": 1605, "total_steps": 4193, "loss": 0.2384, "lr": 3.104294394536608e-05, "epoch": 2.679465776293823, "percentage": 38.28, "elapsed_time": "1:54:39", "remaining_time": "3:04:53"}
{"current_steps": 1610, "total_steps": 4193, "loss": 0.2448, "lr": 3.097342643653849e-05, "epoch": 2.687813021702838, "percentage": 38.4, "elapsed_time": "1:55:02", "remaining_time": "3:04:34"}
{"current_steps": 1615, "total_steps": 4193, "loss": 0.2269, "lr": 3.090371872891074e-05, "epoch": 2.696160267111853, "percentage": 38.52, "elapsed_time": "1:55:23", "remaining_time": "3:04:11"}
{"current_steps": 1620, "total_steps": 4193, "loss": 0.2471, "lr": 3.083382203070365e-05, "epoch": 2.704507512520868, "percentage": 38.64, "elapsed_time": "1:55:47", "remaining_time": "3:03:54"}
{"current_steps": 1625, "total_steps": 4193, "loss": 0.2305, "lr": 3.0763737553413766e-05, "epoch": 2.7128547579298834, "percentage": 38.76, "elapsed_time": "1:56:15", "remaining_time": "3:03:44"}
{"current_steps": 1630, "total_steps": 4193, "loss": 0.2227, "lr": 3.069346651179233e-05, "epoch": 2.721202003338898, "percentage": 38.87, "elapsed_time": "1:56:38", "remaining_time": "3:03:24"}
{"current_steps": 1635, "total_steps": 4193, "loss": 0.2654, "lr": 3.0623010123824245e-05, "epoch": 2.7295492487479134, "percentage": 38.99, "elapsed_time": "1:56:57", "remaining_time": "3:02:58"}
{"current_steps": 1640, "total_steps": 4193, "loss": 0.2359, "lr": 3.0552369610706985e-05, "epoch": 2.7378964941569284, "percentage": 39.11, "elapsed_time": "1:57:14", "remaining_time": "3:02:30"}
{"current_steps": 1645, "total_steps": 4193, "loss": 0.2327, "lr": 3.0481546196829375e-05, "epoch": 2.7462437395659434, "percentage": 39.23, "elapsed_time": "1:57:34", "remaining_time": "3:02:07"}
{"current_steps": 1650, "total_steps": 4193, "loss": 0.242, "lr": 3.041054110975041e-05, "epoch": 2.7545909849749584, "percentage": 39.35, "elapsed_time": "1:57:57", "remaining_time": "3:01:48"}
{"current_steps": 1655, "total_steps": 4193, "loss": 0.2685, "lr": 3.033935558017797e-05, "epoch": 2.7629382303839733, "percentage": 39.47, "elapsed_time": "1:58:20", "remaining_time": "3:01:28"}
{"current_steps": 1660, "total_steps": 4193, "loss": 0.2542, "lr": 3.0267990841947492e-05, "epoch": 2.7712854757929883, "percentage": 39.59, "elapsed_time": "1:58:45", "remaining_time": "3:01:12"}
{"current_steps": 1665, "total_steps": 4193, "loss": 0.2462, "lr": 3.0196448132000563e-05, "epoch": 2.7796327212020033, "percentage": 39.71, "elapsed_time": "1:59:05", "remaining_time": "3:00:49"}
{"current_steps": 1670, "total_steps": 4193, "loss": 0.251, "lr": 3.0124728690363504e-05, "epoch": 2.7879799666110183, "percentage": 39.83, "elapsed_time": "1:59:25", "remaining_time": "3:00:24"}
{"current_steps": 1675, "total_steps": 4193, "loss": 0.2562, "lr": 3.0052833760125864e-05, "epoch": 2.7963272120200333, "percentage": 39.95, "elapsed_time": "1:59:43", "remaining_time": "2:59:58"}
{"current_steps": 1680, "total_steps": 4193, "loss": 0.2452, "lr": 2.9980764587418885e-05, "epoch": 2.8046744574290483, "percentage": 40.07, "elapsed_time": "2:00:02", "remaining_time": "2:59:34"}
{"current_steps": 1685, "total_steps": 4193, "loss": 0.2319, "lr": 2.990852242139389e-05, "epoch": 2.8130217028380633, "percentage": 40.19, "elapsed_time": "2:00:24", "remaining_time": "2:59:13"}
{"current_steps": 1690, "total_steps": 4193, "loss": 0.2472, "lr": 2.983610851420064e-05, "epoch": 2.8213689482470787, "percentage": 40.31, "elapsed_time": "2:00:39", "remaining_time": "2:58:42"}
{"current_steps": 1695, "total_steps": 4193, "loss": 0.2444, "lr": 2.976352412096563e-05, "epoch": 2.8297161936560933, "percentage": 40.42, "elapsed_time": "2:01:04", "remaining_time": "2:58:25"}
{"current_steps": 1700, "total_steps": 4193, "loss": 0.2711, "lr": 2.969077049977034e-05, "epoch": 2.8380634390651087, "percentage": 40.54, "elapsed_time": "2:01:30", "remaining_time": "2:58:11"}
{"current_steps": 1705, "total_steps": 4193, "loss": 0.2602, "lr": 2.9617848911629402e-05, "epoch": 2.8464106844741233, "percentage": 40.66, "elapsed_time": "2:01:49", "remaining_time": "2:57:46"}
{"current_steps": 1710, "total_steps": 4193, "loss": 0.2281, "lr": 2.9544760620468794e-05, "epoch": 2.8547579298831387, "percentage": 40.78, "elapsed_time": "2:02:07", "remaining_time": "2:57:20"}
{"current_steps": 1715, "total_steps": 4193, "loss": 0.2361, "lr": 2.9471506893103883e-05, "epoch": 2.8631051752921537, "percentage": 40.9, "elapsed_time": "2:02:32", "remaining_time": "2:57:03"}
{"current_steps": 1720, "total_steps": 4193, "loss": 0.246, "lr": 2.939808899921749e-05, "epoch": 2.8714524207011687, "percentage": 41.02, "elapsed_time": "2:02:57", "remaining_time": "2:56:46"}
{"current_steps": 1725, "total_steps": 4193, "loss": 0.2483, "lr": 2.932450821133788e-05, "epoch": 2.8797996661101837, "percentage": 41.14, "elapsed_time": "2:03:21", "remaining_time": "2:56:30"}
{"current_steps": 1730, "total_steps": 4193, "loss": 0.2307, "lr": 2.9250765804816712e-05, "epoch": 2.8881469115191987, "percentage": 41.26, "elapsed_time": "2:03:44", "remaining_time": "2:56:10"}
{"current_steps": 1735, "total_steps": 4193, "loss": 0.235, "lr": 2.917686305780692e-05, "epoch": 2.8964941569282137, "percentage": 41.38, "elapsed_time": "2:04:02", "remaining_time": "2:55:43"}
{"current_steps": 1740, "total_steps": 4193, "loss": 0.2323, "lr": 2.9102801251240575e-05, "epoch": 2.9048414023372287, "percentage": 41.5, "elapsed_time": "2:04:21", "remaining_time": "2:55:19"}
{"current_steps": 1745, "total_steps": 4193, "loss": 0.247, "lr": 2.902858166880667e-05, "epoch": 2.9131886477462436, "percentage": 41.62, "elapsed_time": "2:04:42", "remaining_time": "2:54:57"}
{"current_steps": 1750, "total_steps": 4193, "loss": 0.2516, "lr": 2.8954205596928873e-05, "epoch": 2.9215358931552586, "percentage": 41.74, "elapsed_time": "2:05:08", "remaining_time": "2:54:41"}
{"current_steps": 1755, "total_steps": 4193, "loss": 0.2363, "lr": 2.8879674324743246e-05, "epoch": 2.9298831385642736, "percentage": 41.86, "elapsed_time": "2:05:29", "remaining_time": "2:54:20"}
{"current_steps": 1760, "total_steps": 4193, "loss": 0.2495, "lr": 2.880498914407587e-05, "epoch": 2.9382303839732886, "percentage": 41.97, "elapsed_time": "2:05:46", "remaining_time": "2:53:52"}
{"current_steps": 1765, "total_steps": 4193, "loss": 0.2467, "lr": 2.8730151349420475e-05, "epoch": 2.946577629382304, "percentage": 42.09, "elapsed_time": "2:06:05", "remaining_time": "2:53:27"}
{"current_steps": 1770, "total_steps": 4193, "loss": 0.2575, "lr": 2.865516223791601e-05, "epoch": 2.9549248747913186, "percentage": 42.21, "elapsed_time": "2:06:26", "remaining_time": "2:53:04"}
{"current_steps": 1775, "total_steps": 4193, "loss": 0.2339, "lr": 2.8580023109324137e-05, "epoch": 2.963272120200334, "percentage": 42.33, "elapsed_time": "2:06:49", "remaining_time": "2:52:45"}
{"current_steps": 1780, "total_steps": 4193, "loss": 0.2358, "lr": 2.8504735266006717e-05, "epoch": 2.971619365609349, "percentage": 42.45, "elapsed_time": "2:07:13", "remaining_time": "2:52:28"}
{"current_steps": 1785, "total_steps": 4193, "loss": 0.2492, "lr": 2.8429300012903245e-05, "epoch": 2.979966611018364, "percentage": 42.57, "elapsed_time": "2:07:29", "remaining_time": "2:51:59"}
{"current_steps": 1790, "total_steps": 4193, "loss": 0.2311, "lr": 2.8353718657508206e-05, "epoch": 2.988313856427379, "percentage": 42.69, "elapsed_time": "2:07:55", "remaining_time": "2:51:44"}
{"current_steps": 1795, "total_steps": 4193, "loss": 0.238, "lr": 2.827799250984844e-05, "epoch": 2.996661101836394, "percentage": 42.81, "elapsed_time": "2:08:13", "remaining_time": "2:51:17"}
{"current_steps": 1800, "total_steps": 4193, "loss": 0.2211, "lr": 2.8202122882460418e-05, "epoch": 3.005008347245409, "percentage": 42.93, "elapsed_time": "2:08:38", "remaining_time": "2:51:01"}
{"current_steps": 1805, "total_steps": 4193, "loss": 0.2056, "lr": 2.81261110903675e-05, "epoch": 3.013355592654424, "percentage": 43.05, "elapsed_time": "2:09:04", "remaining_time": "2:50:46"}
{"current_steps": 1810, "total_steps": 4193, "loss": 0.205, "lr": 2.804995845105714e-05, "epoch": 3.021702838063439, "percentage": 43.17, "elapsed_time": "2:09:24", "remaining_time": "2:50:22"}
{"current_steps": 1815, "total_steps": 4193, "loss": 0.2187, "lr": 2.7973666284458048e-05, "epoch": 3.030050083472454, "percentage": 43.29, "elapsed_time": "2:09:43", "remaining_time": "2:49:57"}
{"current_steps": 1820, "total_steps": 4193, "loss": 0.1907, "lr": 2.7897235912917318e-05, "epoch": 3.038397328881469, "percentage": 43.41, "elapsed_time": "2:09:59", "remaining_time": "2:49:28"}
{"current_steps": 1825, "total_steps": 4193, "loss": 0.217, "lr": 2.7820668661177505e-05, "epoch": 3.046744574290484, "percentage": 43.52, "elapsed_time": "2:10:18", "remaining_time": "2:49:04"}
{"current_steps": 1830, "total_steps": 4193, "loss": 0.2242, "lr": 2.7743965856353666e-05, "epoch": 3.0550918196994994, "percentage": 43.64, "elapsed_time": "2:10:35", "remaining_time": "2:48:37"}
{"current_steps": 1835, "total_steps": 4193, "loss": 0.207, "lr": 2.7667128827910343e-05, "epoch": 3.0634390651085144, "percentage": 43.76, "elapsed_time": "2:10:52", "remaining_time": "2:48:10"}
{"current_steps": 1840, "total_steps": 4193, "loss": 0.2063, "lr": 2.7590158907638552e-05, "epoch": 3.0717863105175294, "percentage": 43.88, "elapsed_time": "2:11:11", "remaining_time": "2:47:46"}
{"current_steps": 1845, "total_steps": 4193, "loss": 0.1963, "lr": 2.7513057429632656e-05, "epoch": 3.0801335559265444, "percentage": 44.0, "elapsed_time": "2:11:31", "remaining_time": "2:47:22"}
{"current_steps": 1850, "total_steps": 4193, "loss": 0.2136, "lr": 2.7435825730267285e-05, "epoch": 3.0884808013355594, "percentage": 44.12, "elapsed_time": "2:11:58", "remaining_time": "2:47:08"}
{"current_steps": 1855, "total_steps": 4193, "loss": 0.2054, "lr": 2.7358465148174143e-05, "epoch": 3.0968280467445743, "percentage": 44.24, "elapsed_time": "2:12:23", "remaining_time": "2:46:51"}
{"current_steps": 1860, "total_steps": 4193, "loss": 0.1986, "lr": 2.728097702421882e-05, "epoch": 3.1051752921535893, "percentage": 44.36, "elapsed_time": "2:12:50", "remaining_time": "2:46:37"}
{"current_steps": 1865, "total_steps": 4193, "loss": 0.2102, "lr": 2.720336270147754e-05, "epoch": 3.1135225375626043, "percentage": 44.48, "elapsed_time": "2:13:06", "remaining_time": "2:46:09"}
{"current_steps": 1870, "total_steps": 4193, "loss": 0.202, "lr": 2.71256235252139e-05, "epoch": 3.1218697829716193, "percentage": 44.6, "elapsed_time": "2:13:25", "remaining_time": "2:45:44"}
{"current_steps": 1875, "total_steps": 4193, "loss": 0.2185, "lr": 2.7047760842855536e-05, "epoch": 3.1302170283806343, "percentage": 44.72, "elapsed_time": "2:13:45", "remaining_time": "2:45:21"}
{"current_steps": 1880, "total_steps": 4193, "loss": 0.2061, "lr": 2.6969776003970777e-05, "epoch": 3.1385642737896493, "percentage": 44.84, "elapsed_time": "2:14:02", "remaining_time": "2:44:55"}
{"current_steps": 1885, "total_steps": 4193, "loss": 0.2275, "lr": 2.6891670360245244e-05, "epoch": 3.1469115191986643, "percentage": 44.96, "elapsed_time": "2:14:24", "remaining_time": "2:44:34"}
{"current_steps": 1890, "total_steps": 4193, "loss": 0.2047, "lr": 2.6813445265458438e-05, "epoch": 3.1552587646076793, "percentage": 45.08, "elapsed_time": "2:14:40", "remaining_time": "2:44:06"}
{"current_steps": 1895, "total_steps": 4193, "loss": 0.1918, "lr": 2.6735102075460257e-05, "epoch": 3.1636060100166947, "percentage": 45.19, "elapsed_time": "2:14:55", "remaining_time": "2:43:37"}
{"current_steps": 1900, "total_steps": 4193, "loss": 0.2015, "lr": 2.665664214814752e-05, "epoch": 3.1719532554257097, "percentage": 45.31, "elapsed_time": "2:15:22", "remaining_time": "2:43:22"}
{"current_steps": 1905, "total_steps": 4193, "loss": 0.1981, "lr": 2.65780668434404e-05, "epoch": 3.1803005008347247, "percentage": 45.43, "elapsed_time": "2:15:41", "remaining_time": "2:42:58"}
{"current_steps": 1910, "total_steps": 4193, "loss": 0.2133, "lr": 2.649937752325887e-05, "epoch": 3.1886477462437397, "percentage": 45.55, "elapsed_time": "2:16:04", "remaining_time": "2:42:39"}
{"current_steps": 1915, "total_steps": 4193, "loss": 0.2235, "lr": 2.64205755514991e-05, "epoch": 3.1969949916527547, "percentage": 45.67, "elapsed_time": "2:16:26", "remaining_time": "2:42:18"}
{"current_steps": 1920, "total_steps": 4193, "loss": 0.2435, "lr": 2.634166229400982e-05, "epoch": 3.2053422370617697, "percentage": 45.79, "elapsed_time": "2:16:52", "remaining_time": "2:42:01"}
{"current_steps": 1925, "total_steps": 4193, "loss": 0.1944, "lr": 2.626263911856863e-05, "epoch": 3.2136894824707847, "percentage": 45.91, "elapsed_time": "2:17:18", "remaining_time": "2:41:46"}
{"current_steps": 1930, "total_steps": 4193, "loss": 0.2288, "lr": 2.6183507394858296e-05, "epoch": 3.2220367278797997, "percentage": 46.03, "elapsed_time": "2:17:36", "remaining_time": "2:41:20"}
{"current_steps": 1935, "total_steps": 4193, "loss": 0.2167, "lr": 2.6104268494443027e-05, "epoch": 3.2303839732888147, "percentage": 46.15, "elapsed_time": "2:18:04", "remaining_time": "2:41:07"}
{"current_steps": 1940, "total_steps": 4193, "loss": 0.192, "lr": 2.6024923790744686e-05, "epoch": 3.2387312186978297, "percentage": 46.27, "elapsed_time": "2:18:27", "remaining_time": "2:40:47"}
{"current_steps": 1945, "total_steps": 4193, "loss": 0.1997, "lr": 2.594547465901899e-05, "epoch": 3.2470784641068446, "percentage": 46.39, "elapsed_time": "2:18:46", "remaining_time": "2:40:23"}
{"current_steps": 1950, "total_steps": 4193, "loss": 0.215, "lr": 2.5865922476331674e-05, "epoch": 3.2554257095158596, "percentage": 46.51, "elapsed_time": "2:19:04", "remaining_time": "2:39:58"}
{"current_steps": 1955, "total_steps": 4193, "loss": 0.2001, "lr": 2.5786268621534626e-05, "epoch": 3.2637729549248746, "percentage": 46.63, "elapsed_time": "2:19:25", "remaining_time": "2:39:36"}
{"current_steps": 1960, "total_steps": 4193, "loss": 0.2131, "lr": 2.5706514475241964e-05, "epoch": 3.27212020033389, "percentage": 46.74, "elapsed_time": "2:19:48", "remaining_time": "2:39:16"}
{"current_steps": 1965, "total_steps": 4193, "loss": 0.2101, "lr": 2.5626661419806147e-05, "epoch": 3.2804674457429046, "percentage": 46.86, "elapsed_time": "2:20:06", "remaining_time": "2:38:51"}
{"current_steps": 1970, "total_steps": 4193, "loss": 0.2142, "lr": 2.5546710839293988e-05, "epoch": 3.28881469115192, "percentage": 46.98, "elapsed_time": "2:20:27", "remaining_time": "2:38:30"}
{"current_steps": 1975, "total_steps": 4193, "loss": 0.1928, "lr": 2.5466664119462667e-05, "epoch": 3.297161936560935, "percentage": 47.1, "elapsed_time": "2:20:45", "remaining_time": "2:38:04"}
{"current_steps": 1980, "total_steps": 4193, "loss": 0.1978, "lr": 2.5386522647735712e-05, "epoch": 3.30550918196995, "percentage": 47.22, "elapsed_time": "2:21:05", "remaining_time": "2:37:41"}
{"current_steps": 1985, "total_steps": 4193, "loss": 0.201, "lr": 2.530628781317896e-05, "epoch": 3.313856427378965, "percentage": 47.34, "elapsed_time": "2:21:28", "remaining_time": "2:37:21"}
{"current_steps": 1990, "total_steps": 4193, "loss": 0.1999, "lr": 2.5225961006476484e-05, "epoch": 3.32220367278798, "percentage": 47.46, "elapsed_time": "2:21:48", "remaining_time": "2:36:59"}
{"current_steps": 1995, "total_steps": 4193, "loss": 0.194, "lr": 2.5145543619906456e-05, "epoch": 3.330550918196995, "percentage": 47.58, "elapsed_time": "2:22:14", "remaining_time": "2:36:42"}
{"current_steps": 2000, "total_steps": 4193, "loss": 0.207, "lr": 2.5065037047317066e-05, "epoch": 3.33889816360601, "percentage": 47.7, "elapsed_time": "2:22:34", "remaining_time": "2:36:20"}
{"current_steps": 2005, "total_steps": 4193, "loss": 0.2022, "lr": 2.4984442684102307e-05, "epoch": 3.347245409015025, "percentage": 47.82, "elapsed_time": "2:22:57", "remaining_time": "2:35:59"}
{"current_steps": 2010, "total_steps": 4193, "loss": 0.2206, "lr": 2.4903761927177853e-05, "epoch": 3.35559265442404, "percentage": 47.94, "elapsed_time": "2:23:16", "remaining_time": "2:35:36"}
{"current_steps": 2015, "total_steps": 4193, "loss": 0.2106, "lr": 2.482299617495678e-05, "epoch": 3.363939899833055, "percentage": 48.06, "elapsed_time": "2:23:38", "remaining_time": "2:35:15"}
{"current_steps": 2020, "total_steps": 4193, "loss": 0.2113, "lr": 2.474214682732538e-05, "epoch": 3.37228714524207, "percentage": 48.18, "elapsed_time": "2:23:59", "remaining_time": "2:34:54"}
{"current_steps": 2025, "total_steps": 4193, "loss": 0.1837, "lr": 2.466121528561887e-05, "epoch": 3.380634390651085, "percentage": 48.29, "elapsed_time": "2:24:13", "remaining_time": "2:34:24"}
{"current_steps": 2030, "total_steps": 4193, "loss": 0.2141, "lr": 2.4580202952597106e-05, "epoch": 3.3889816360601, "percentage": 48.41, "elapsed_time": "2:24:31", "remaining_time": "2:33:59"}
{"current_steps": 2035, "total_steps": 4193, "loss": 0.2172, "lr": 2.4499111232420275e-05, "epoch": 3.3973288814691154, "percentage": 48.53, "elapsed_time": "2:24:52", "remaining_time": "2:33:38"}
{"current_steps": 2040, "total_steps": 4193, "loss": 0.2193, "lr": 2.441794153062457e-05, "epoch": 3.4056761268781304, "percentage": 48.65, "elapsed_time": "2:25:16", "remaining_time": "2:33:18"}
{"current_steps": 2045, "total_steps": 4193, "loss": 0.1954, "lr": 2.4336695254097782e-05, "epoch": 3.4140233722871454, "percentage": 48.77, "elapsed_time": "2:25:35", "remaining_time": "2:32:55"}
{"current_steps": 2050, "total_steps": 4193, "loss": 0.2036, "lr": 2.425537381105498e-05, "epoch": 3.4223706176961604, "percentage": 48.89, "elapsed_time": "2:26:00", "remaining_time": "2:32:37"}
{"current_steps": 2055, "total_steps": 4193, "loss": 0.2172, "lr": 2.4173978611014053e-05, "epoch": 3.4307178631051753, "percentage": 49.01, "elapsed_time": "2:26:19", "remaining_time": "2:32:14"}
{"current_steps": 2060, "total_steps": 4193, "loss": 0.1978, "lr": 2.40925110647713e-05, "epoch": 3.4390651085141903, "percentage": 49.13, "elapsed_time": "2:26:37", "remaining_time": "2:31:49"}
{"current_steps": 2065, "total_steps": 4193, "loss": 0.2191, "lr": 2.4010972584376963e-05, "epoch": 3.4474123539232053, "percentage": 49.25, "elapsed_time": "2:27:07", "remaining_time": "2:31:36"}
{"current_steps": 2070, "total_steps": 4193, "loss": 0.1942, "lr": 2.392936458311078e-05, "epoch": 3.4557595993322203, "percentage": 49.37, "elapsed_time": "2:27:30", "remaining_time": "2:31:16"}
{"current_steps": 2075, "total_steps": 4193, "loss": 0.1966, "lr": 2.3847688475457455e-05, "epoch": 3.4641068447412353, "percentage": 49.49, "elapsed_time": "2:27:49", "remaining_time": "2:30:53"}
{"current_steps": 2080, "total_steps": 4193, "loss": 0.2088, "lr": 2.3765945677082168e-05, "epoch": 3.4724540901502503, "percentage": 49.61, "elapsed_time": "2:28:11", "remaining_time": "2:30:32"}
{"current_steps": 2085, "total_steps": 4193, "loss": 0.1878, "lr": 2.368413760480603e-05, "epoch": 3.4808013355592653, "percentage": 49.73, "elapsed_time": "2:28:42", "remaining_time": "2:30:20"}
{"current_steps": 2090, "total_steps": 4193, "loss": 0.1925, "lr": 2.360226567658151e-05, "epoch": 3.4891485809682803, "percentage": 49.84, "elapsed_time": "2:29:02", "remaining_time": "2:29:57"}
{"current_steps": 2095, "total_steps": 4193, "loss": 0.2207, "lr": 2.3520331311467883e-05, "epoch": 3.4974958263772953, "percentage": 49.96, "elapsed_time": "2:29:25", "remaining_time": "2:29:38"}
{"current_steps": 2100, "total_steps": 4193, "loss": 0.2322, "lr": 2.3438335929606613e-05, "epoch": 3.5058430717863107, "percentage": 50.08, "elapsed_time": "2:29:45", "remaining_time": "2:29:15"}
{"current_steps": 2105, "total_steps": 4193, "loss": 0.2015, "lr": 2.3356280952196757e-05, "epoch": 3.5141903171953257, "percentage": 50.2, "elapsed_time": "2:30:10", "remaining_time": "2:28:57"}
{"current_steps": 2110, "total_steps": 4193, "loss": 0.2026, "lr": 2.3274167801470314e-05, "epoch": 3.5225375626043407, "percentage": 50.32, "elapsed_time": "2:30:28", "remaining_time": "2:28:33"}
{"current_steps": 2115, "total_steps": 4193, "loss": 0.2247, "lr": 2.3191997900667588e-05, "epoch": 3.5308848080133557, "percentage": 50.44, "elapsed_time": "2:30:41", "remaining_time": "2:28:02"}
{"current_steps": 2120, "total_steps": 4193, "loss": 0.2059, "lr": 2.310977267401251e-05, "epoch": 3.5392320534223707, "percentage": 50.56, "elapsed_time": "2:30:57", "remaining_time": "2:27:37"}
{"current_steps": 2125, "total_steps": 4193, "loss": 0.2094, "lr": 2.302749354668795e-05, "epoch": 3.5475792988313857, "percentage": 50.68, "elapsed_time": "2:31:21", "remaining_time": "2:27:18"}
{"current_steps": 2130, "total_steps": 4193, "loss": 0.2033, "lr": 2.2945161944811038e-05, "epoch": 3.5559265442404007, "percentage": 50.8, "elapsed_time": "2:31:39", "remaining_time": "2:26:53"}
{"current_steps": 2135, "total_steps": 4193, "loss": 0.2123, "lr": 2.2862779295408405e-05, "epoch": 3.5642737896494157, "percentage": 50.92, "elapsed_time": "2:32:04", "remaining_time": "2:26:35"}
{"current_steps": 2140, "total_steps": 4193, "loss": 0.2176, "lr": 2.2780347026391495e-05, "epoch": 3.5726210350584306, "percentage": 51.04, "elapsed_time": "2:32:25", "remaining_time": "2:26:14"}
{"current_steps": 2145, "total_steps": 4193, "loss": 0.211, "lr": 2.2697866566531775e-05, "epoch": 3.5809682804674456, "percentage": 51.16, "elapsed_time": "2:32:43", "remaining_time": "2:25:48"}
{"current_steps": 2150, "total_steps": 4193, "loss": 0.2119, "lr": 2.2615339345436e-05, "epoch": 3.5893155258764606, "percentage": 51.28, "elapsed_time": "2:33:07", "remaining_time": "2:25:30"}
{"current_steps": 2155, "total_steps": 4193, "loss": 0.2221, "lr": 2.2532766793521413e-05, "epoch": 3.597662771285476, "percentage": 51.4, "elapsed_time": "2:33:26", "remaining_time": "2:25:06"}
{"current_steps": 2160, "total_steps": 4193, "loss": 0.227, "lr": 2.245015034199097e-05, "epoch": 3.6060100166944906, "percentage": 51.51, "elapsed_time": "2:33:42", "remaining_time": "2:24:40"}
{"current_steps": 2165, "total_steps": 4193, "loss": 0.2047, "lr": 2.2367491422808514e-05, "epoch": 3.614357262103506, "percentage": 51.63, "elapsed_time": "2:34:00", "remaining_time": "2:24:15"}
{"current_steps": 2170, "total_steps": 4193, "loss": 0.1997, "lr": 2.228479146867397e-05, "epoch": 3.6227045075125206, "percentage": 51.75, "elapsed_time": "2:34:21", "remaining_time": "2:23:53"}
{"current_steps": 2175, "total_steps": 4193, "loss": 0.1889, "lr": 2.2202051912998516e-05, "epoch": 3.631051752921536, "percentage": 51.87, "elapsed_time": "2:34:39", "remaining_time": "2:23:29"}
{"current_steps": 2180, "total_steps": 4193, "loss": 0.2095, "lr": 2.2119274189879727e-05, "epoch": 3.639398998330551, "percentage": 51.99, "elapsed_time": "2:35:01", "remaining_time": "2:23:09"}
{"current_steps": 2185, "total_steps": 4193, "loss": 0.2021, "lr": 2.2036459734076715e-05, "epoch": 3.647746243739566, "percentage": 52.11, "elapsed_time": "2:35:22", "remaining_time": "2:22:47"}
{"current_steps": 2190, "total_steps": 4193, "loss": 0.1971, "lr": 2.1953609980985266e-05, "epoch": 3.656093489148581, "percentage": 52.23, "elapsed_time": "2:35:39", "remaining_time": "2:22:22"}
{"current_steps": 2195, "total_steps": 4193, "loss": 0.2327, "lr": 2.1870726366612978e-05, "epoch": 3.664440734557596, "percentage": 52.35, "elapsed_time": "2:36:00", "remaining_time": "2:22:00"}
{"current_steps": 2200, "total_steps": 4193, "loss": 0.2046, "lr": 2.1787810327554345e-05, "epoch": 3.672787979966611, "percentage": 52.47, "elapsed_time": "2:36:19", "remaining_time": "2:21:37"}
{"current_steps": 2205, "total_steps": 4193, "loss": 0.1936, "lr": 2.170486330096586e-05, "epoch": 3.681135225375626, "percentage": 52.59, "elapsed_time": "2:36:42", "remaining_time": "2:21:16"}
{"current_steps": 2210, "total_steps": 4193, "loss": 0.2034, "lr": 2.1621886724541126e-05, "epoch": 3.689482470784641, "percentage": 52.71, "elapsed_time": "2:36:59", "remaining_time": "2:20:51"}
{"current_steps": 2215, "total_steps": 4193, "loss": 0.2038, "lr": 2.1538882036485923e-05, "epoch": 3.697829716193656, "percentage": 52.83, "elapsed_time": "2:37:18", "remaining_time": "2:20:28"}
{"current_steps": 2220, "total_steps": 4193, "loss": 0.2076, "lr": 2.1455850675493267e-05, "epoch": 3.706176961602671, "percentage": 52.95, "elapsed_time": "2:37:35", "remaining_time": "2:20:03"}
{"current_steps": 2225, "total_steps": 4193, "loss": 0.2029, "lr": 2.1372794080718506e-05, "epoch": 3.714524207011686, "percentage": 53.06, "elapsed_time": "2:37:49", "remaining_time": "2:19:35"}
{"current_steps": 2230, "total_steps": 4193, "loss": 0.2218, "lr": 2.1289713691754338e-05, "epoch": 3.7228714524207014, "percentage": 53.18, "elapsed_time": "2:38:08", "remaining_time": "2:19:12"}
{"current_steps": 2235, "total_steps": 4193, "loss": 0.2105, "lr": 2.1206610948605894e-05, "epoch": 3.731218697829716, "percentage": 53.3, "elapsed_time": "2:38:27", "remaining_time": "2:18:48"}
{"current_steps": 2240, "total_steps": 4193, "loss": 0.1937, "lr": 2.1123487291665753e-05, "epoch": 3.7395659432387314, "percentage": 53.42, "elapsed_time": "2:38:49", "remaining_time": "2:18:28"}
{"current_steps": 2245, "total_steps": 4193, "loss": 0.24, "lr": 2.104034416168899e-05, "epoch": 3.7479131886477464, "percentage": 53.54, "elapsed_time": "2:39:09", "remaining_time": "2:18:05"}
{"current_steps": 2250, "total_steps": 4193, "loss": 0.2017, "lr": 2.0957182999768198e-05, "epoch": 3.7562604340567614, "percentage": 53.66, "elapsed_time": "2:39:28", "remaining_time": "2:17:42"}
{"current_steps": 2255, "total_steps": 4193, "loss": 0.2227, "lr": 2.0874005247308512e-05, "epoch": 3.7646076794657763, "percentage": 53.78, "elapsed_time": "2:39:53", "remaining_time": "2:17:24"}
{"current_steps": 2260, "total_steps": 4193, "loss": 0.1936, "lr": 2.0790812346002626e-05, "epoch": 3.7729549248747913, "percentage": 53.9, "elapsed_time": "2:40:08", "remaining_time": "2:16:58"}
{"current_steps": 2265, "total_steps": 4193, "loss": 0.2117, "lr": 2.0707605737805797e-05, "epoch": 3.7813021702838063, "percentage": 54.02, "elapsed_time": "2:40:26", "remaining_time": "2:16:33"}
{"current_steps": 2270, "total_steps": 4193, "loss": 0.2091, "lr": 2.0624386864910876e-05, "epoch": 3.7896494156928213, "percentage": 54.14, "elapsed_time": "2:40:43", "remaining_time": "2:16:09"}
{"current_steps": 2275, "total_steps": 4193, "loss": 0.2004, "lr": 2.054115716972328e-05, "epoch": 3.7979966611018363, "percentage": 54.26, "elapsed_time": "2:40:55", "remaining_time": "2:15:40"}
{"current_steps": 2280, "total_steps": 4193, "loss": 0.2253, "lr": 2.045791809483601e-05, "epoch": 3.8063439065108513, "percentage": 54.38, "elapsed_time": "2:41:16", "remaining_time": "2:15:18"}
{"current_steps": 2285, "total_steps": 4193, "loss": 0.1952, "lr": 2.0374671083004642e-05, "epoch": 3.8146911519198663, "percentage": 54.5, "elapsed_time": "2:41:31", "remaining_time": "2:14:52"}
{"current_steps": 2290, "total_steps": 4193, "loss": 0.2051, "lr": 2.0291417577122314e-05, "epoch": 3.8230383973288813, "percentage": 54.61, "elapsed_time": "2:41:49", "remaining_time": "2:14:28"}
{"current_steps": 2295, "total_steps": 4193, "loss": 0.2085, "lr": 2.0208159020194734e-05, "epoch": 3.8313856427378967, "percentage": 54.73, "elapsed_time": "2:42:13", "remaining_time": "2:14:09"}
{"current_steps": 2300, "total_steps": 4193, "loss": 0.1886, "lr": 2.012489685531515e-05, "epoch": 3.8397328881469113, "percentage": 54.85, "elapsed_time": "2:42:32", "remaining_time": "2:13:47"}
{"current_steps": 2305, "total_steps": 4193, "loss": 0.2162, "lr": 2.0041632525639356e-05, "epoch": 3.8480801335559267, "percentage": 54.97, "elapsed_time": "2:42:56", "remaining_time": "2:13:27"}
{"current_steps": 2310, "total_steps": 4193, "loss": 0.2083, "lr": 1.9958367474360648e-05, "epoch": 3.8564273789649417, "percentage": 55.09, "elapsed_time": "2:43:20", "remaining_time": "2:13:08"}
{"current_steps": 2315, "total_steps": 4193, "loss": 0.1935, "lr": 1.9875103144684852e-05, "epoch": 3.8647746243739567, "percentage": 55.21, "elapsed_time": "2:43:48", "remaining_time": "2:12:53"}
{"current_steps": 2320, "total_steps": 4193, "loss": 0.2087, "lr": 1.979184097980527e-05, "epoch": 3.8731218697829717, "percentage": 55.33, "elapsed_time": "2:44:15", "remaining_time": "2:12:36"}
{"current_steps": 2325, "total_steps": 4193, "loss": 0.2197, "lr": 1.9708582422877693e-05, "epoch": 3.8814691151919867, "percentage": 55.45, "elapsed_time": "2:44:31", "remaining_time": "2:12:11"}
{"current_steps": 2330, "total_steps": 4193, "loss": 0.1999, "lr": 1.9625328916995365e-05, "epoch": 3.8898163606010017, "percentage": 55.57, "elapsed_time": "2:44:45", "remaining_time": "2:11:43"}
{"current_steps": 2335, "total_steps": 4193, "loss": 0.2004, "lr": 1.9542081905163997e-05, "epoch": 3.8981636060100167, "percentage": 55.69, "elapsed_time": "2:45:08", "remaining_time": "2:11:24"}
{"current_steps": 2340, "total_steps": 4193, "loss": 0.2263, "lr": 1.9458842830276724e-05, "epoch": 3.9065108514190316, "percentage": 55.81, "elapsed_time": "2:45:33", "remaining_time": "2:11:06"}
{"current_steps": 2345, "total_steps": 4193, "loss": 0.1994, "lr": 1.937561313508913e-05, "epoch": 3.9148580968280466, "percentage": 55.93, "elapsed_time": "2:45:58", "remaining_time": "2:10:47"}
{"current_steps": 2350, "total_steps": 4193, "loss": 0.222, "lr": 1.9292394262194213e-05, "epoch": 3.9232053422370616, "percentage": 56.05, "elapsed_time": "2:46:13", "remaining_time": "2:10:21"}
{"current_steps": 2355, "total_steps": 4193, "loss": 0.2111, "lr": 1.9209187653997385e-05, "epoch": 3.9315525876460766, "percentage": 56.17, "elapsed_time": "2:46:32", "remaining_time": "2:09:59"}
{"current_steps": 2360, "total_steps": 4193, "loss": 0.1927, "lr": 1.91259947526915e-05, "epoch": 3.939899833055092, "percentage": 56.28, "elapsed_time": "2:46:47", "remaining_time": "2:09:32"}
{"current_steps": 2365, "total_steps": 4193, "loss": 0.209, "lr": 1.904281700023181e-05, "epoch": 3.9482470784641066, "percentage": 56.4, "elapsed_time": "2:47:17", "remaining_time": "2:09:18"}
{"current_steps": 2370, "total_steps": 4193, "loss": 0.2101, "lr": 1.895965583831102e-05, "epoch": 3.956594323873122, "percentage": 56.52, "elapsed_time": "2:47:31", "remaining_time": "2:08:51"}
{"current_steps": 2375, "total_steps": 4193, "loss": 0.2127, "lr": 1.887651270833425e-05, "epoch": 3.964941569282137, "percentage": 56.64, "elapsed_time": "2:47:48", "remaining_time": "2:08:26"}
{"current_steps": 2380, "total_steps": 4193, "loss": 0.2034, "lr": 1.8793389051394116e-05, "epoch": 3.973288814691152, "percentage": 56.76, "elapsed_time": "2:48:09", "remaining_time": "2:08:06"}
{"current_steps": 2385, "total_steps": 4193, "loss": 0.203, "lr": 1.8710286308245665e-05, "epoch": 3.981636060100167, "percentage": 56.88, "elapsed_time": "2:48:28", "remaining_time": "2:07:43"}
{"current_steps": 2390, "total_steps": 4193, "loss": 0.2083, "lr": 1.8627205919281507e-05, "epoch": 3.989983305509182, "percentage": 57.0, "elapsed_time": "2:48:50", "remaining_time": "2:07:22"}
{"current_steps": 2395, "total_steps": 4193, "loss": 0.2144, "lr": 1.8544149324506736e-05, "epoch": 3.998330550918197, "percentage": 57.12, "elapsed_time": "2:49:16", "remaining_time": "2:07:04"}
{"current_steps": 2400, "total_steps": 4193, "loss": 0.1808, "lr": 1.8461117963514087e-05, "epoch": 4.006677796327212, "percentage": 57.24, "elapsed_time": "2:49:35", "remaining_time": "2:06:42"}
{"current_steps": 2405, "total_steps": 4193, "loss": 0.1843, "lr": 1.8378113275458877e-05, "epoch": 4.015025041736227, "percentage": 57.36, "elapsed_time": "2:49:56", "remaining_time": "2:06:20"}
{"current_steps": 2410, "total_steps": 4193, "loss": 0.1922, "lr": 1.8295136699034152e-05, "epoch": 4.023372287145242, "percentage": 57.48, "elapsed_time": "2:50:13", "remaining_time": "2:05:56"}
{"current_steps": 2415, "total_steps": 4193, "loss": 0.1579, "lr": 1.8212189672445665e-05, "epoch": 4.031719532554257, "percentage": 57.6, "elapsed_time": "2:50:40", "remaining_time": "2:05:39"}
{"current_steps": 2420, "total_steps": 4193, "loss": 0.1811, "lr": 1.812927363338703e-05, "epoch": 4.040066777963272, "percentage": 57.72, "elapsed_time": "2:50:58", "remaining_time": "2:05:15"}
{"current_steps": 2425, "total_steps": 4193, "loss": 0.1705, "lr": 1.8046390019014738e-05, "epoch": 4.048414023372287, "percentage": 57.83, "elapsed_time": "2:51:21", "remaining_time": "2:04:56"}
{"current_steps": 2430, "total_steps": 4193, "loss": 0.169, "lr": 1.7963540265923298e-05, "epoch": 4.056761268781302, "percentage": 57.95, "elapsed_time": "2:51:43", "remaining_time": "2:04:35"}
{"current_steps": 2435, "total_steps": 4193, "loss": 0.205, "lr": 1.788072581012028e-05, "epoch": 4.065108514190317, "percentage": 58.07, "elapsed_time": "2:52:14", "remaining_time": "2:04:20"}
{"current_steps": 2440, "total_steps": 4193, "loss": 0.1715, "lr": 1.779794808700149e-05, "epoch": 4.073455759599332, "percentage": 58.19, "elapsed_time": "2:52:34", "remaining_time": "2:03:59"}
{"current_steps": 2445, "total_steps": 4193, "loss": 0.1822, "lr": 1.7715208531326032e-05, "epoch": 4.081803005008347, "percentage": 58.31, "elapsed_time": "2:52:54", "remaining_time": "2:03:37"}
{"current_steps": 2450, "total_steps": 4193, "loss": 0.1923, "lr": 1.76325085771915e-05, "epoch": 4.090150250417362, "percentage": 58.43, "elapsed_time": "2:53:18", "remaining_time": "2:03:17"}
{"current_steps": 2455, "total_steps": 4193, "loss": 0.1706, "lr": 1.7549849658009037e-05, "epoch": 4.098497495826377, "percentage": 58.55, "elapsed_time": "2:53:40", "remaining_time": "2:02:57"}
{"current_steps": 2460, "total_steps": 4193, "loss": 0.165, "lr": 1.7467233206478597e-05, "epoch": 4.106844741235392, "percentage": 58.67, "elapsed_time": "2:54:02", "remaining_time": "2:02:36"}
{"current_steps": 2465, "total_steps": 4193, "loss": 0.1763, "lr": 1.7384660654564006e-05, "epoch": 4.115191986644407, "percentage": 58.79, "elapsed_time": "2:54:21", "remaining_time": "2:02:13"}
{"current_steps": 2470, "total_steps": 4193, "loss": 0.1896, "lr": 1.7302133433468232e-05, "epoch": 4.123539232053423, "percentage": 58.91, "elapsed_time": "2:54:40", "remaining_time": "2:01:51"}
{"current_steps": 2475, "total_steps": 4193, "loss": 0.1744, "lr": 1.7219652973608512e-05, "epoch": 4.131886477462437, "percentage": 59.03, "elapsed_time": "2:55:00", "remaining_time": "2:01:29"}
{"current_steps": 2480, "total_steps": 4193, "loss": 0.1844, "lr": 1.7137220704591605e-05, "epoch": 4.140233722871453, "percentage": 59.15, "elapsed_time": "2:55:20", "remaining_time": "2:01:06"}
{"current_steps": 2485, "total_steps": 4193, "loss": 0.175, "lr": 1.7054838055188972e-05, "epoch": 4.148580968280467, "percentage": 59.27, "elapsed_time": "2:55:41", "remaining_time": "2:00:45"}
{"current_steps": 2490, "total_steps": 4193, "loss": 0.169, "lr": 1.6972506453312057e-05, "epoch": 4.156928213689483, "percentage": 59.38, "elapsed_time": "2:56:03", "remaining_time": "2:00:24"}
{"current_steps": 2495, "total_steps": 4193, "loss": 0.1789, "lr": 1.6890227325987498e-05, "epoch": 4.165275459098497, "percentage": 59.5, "elapsed_time": "2:56:24", "remaining_time": "2:00:03"}
{"current_steps": 2500, "total_steps": 4193, "loss": 0.1748, "lr": 1.6808002099332422e-05, "epoch": 4.173622704507513, "percentage": 59.62, "elapsed_time": "2:56:42", "remaining_time": "1:59:40"}
{"current_steps": 2505, "total_steps": 4193, "loss": 0.1855, "lr": 1.672583219852969e-05, "epoch": 4.181969949916527, "percentage": 59.74, "elapsed_time": "2:57:01", "remaining_time": "1:59:17"}
{"current_steps": 2510, "total_steps": 4193, "loss": 0.2099, "lr": 1.6643719047803243e-05, "epoch": 4.190317195325543, "percentage": 59.86, "elapsed_time": "2:57:24", "remaining_time": "1:58:57"}
{"current_steps": 2515, "total_steps": 4193, "loss": 0.1703, "lr": 1.656166407039339e-05, "epoch": 4.198664440734557, "percentage": 59.98, "elapsed_time": "2:57:37", "remaining_time": "1:58:30"}
{"current_steps": 2520, "total_steps": 4193, "loss": 0.1797, "lr": 1.647966868853212e-05, "epoch": 4.207011686143573, "percentage": 60.1, "elapsed_time": "2:57:58", "remaining_time": "1:58:09"}
{"current_steps": 2525, "total_steps": 4193, "loss": 0.1927, "lr": 1.6397734323418494e-05, "epoch": 4.215358931552587, "percentage": 60.22, "elapsed_time": "2:58:19", "remaining_time": "1:57:48"}
{"current_steps": 2530, "total_steps": 4193, "loss": 0.1587, "lr": 1.6315862395193972e-05, "epoch": 4.223706176961603, "percentage": 60.34, "elapsed_time": "2:58:37", "remaining_time": "1:57:24"}
{"current_steps": 2535, "total_steps": 4193, "loss": 0.1826, "lr": 1.6234054322917835e-05, "epoch": 4.232053422370618, "percentage": 60.46, "elapsed_time": "2:58:58", "remaining_time": "1:57:03"}
{"current_steps": 2540, "total_steps": 4193, "loss": 0.1696, "lr": 1.615231152454255e-05, "epoch": 4.240400667779633, "percentage": 60.58, "elapsed_time": "2:59:16", "remaining_time": "1:56:40"}
{"current_steps": 2545, "total_steps": 4193, "loss": 0.1799, "lr": 1.6070635416889228e-05, "epoch": 4.248747913188648, "percentage": 60.7, "elapsed_time": "2:59:34", "remaining_time": "1:56:16"}
{"current_steps": 2550, "total_steps": 4193, "loss": 0.1735, "lr": 1.598902741562304e-05, "epoch": 4.257095158597663, "percentage": 60.82, "elapsed_time": "2:59:51", "remaining_time": "1:55:53"}
{"current_steps": 2555, "total_steps": 4193, "loss": 0.1904, "lr": 1.590748893522871e-05, "epoch": 4.265442404006678, "percentage": 60.93, "elapsed_time": "3:00:12", "remaining_time": "1:55:32"}
{"current_steps": 2560, "total_steps": 4193, "loss": 0.1878, "lr": 1.5826021388985947e-05, "epoch": 4.273789649415693, "percentage": 61.05, "elapsed_time": "3:00:30", "remaining_time": "1:55:08"}
{"current_steps": 2565, "total_steps": 4193, "loss": 0.1642, "lr": 1.5744626188945023e-05, "epoch": 4.282136894824708, "percentage": 61.17, "elapsed_time": "3:00:53", "remaining_time": "1:54:48"}
{"current_steps": 2570, "total_steps": 4193, "loss": 0.1749, "lr": 1.5663304745902218e-05, "epoch": 4.290484140233723, "percentage": 61.29, "elapsed_time": "3:01:16", "remaining_time": "1:54:28"}
{"current_steps": 2575, "total_steps": 4193, "loss": 0.1632, "lr": 1.558205846937544e-05, "epoch": 4.298831385642738, "percentage": 61.41, "elapsed_time": "3:01:36", "remaining_time": "1:54:06"}
{"current_steps": 2580, "total_steps": 4193, "loss": 0.1771, "lr": 1.5500888767579722e-05, "epoch": 4.307178631051753, "percentage": 61.53, "elapsed_time": "3:01:59", "remaining_time": "1:53:46"}
{"current_steps": 2585, "total_steps": 4193, "loss": 0.1714, "lr": 1.5419797047402897e-05, "epoch": 4.315525876460768, "percentage": 61.65, "elapsed_time": "3:02:16", "remaining_time": "1:53:23"}
{"current_steps": 2590, "total_steps": 4193, "loss": 0.1889, "lr": 1.533878471438113e-05, "epoch": 4.323873121869783, "percentage": 61.77, "elapsed_time": "3:02:35", "remaining_time": "1:53:00"}
{"current_steps": 2595, "total_steps": 4193, "loss": 0.1722, "lr": 1.5257853172674622e-05, "epoch": 4.332220367278798, "percentage": 61.89, "elapsed_time": "3:02:56", "remaining_time": "1:52:39"}
{"current_steps": 2600, "total_steps": 4193, "loss": 0.1902, "lr": 1.517700382504322e-05, "epoch": 4.340567612687813, "percentage": 62.01, "elapsed_time": "3:03:14", "remaining_time": "1:52:16"}
{"current_steps": 2605, "total_steps": 4193, "loss": 0.1889, "lr": 1.5096238072822153e-05, "epoch": 4.348914858096828, "percentage": 62.13, "elapsed_time": "3:03:36", "remaining_time": "1:51:55"}
{"current_steps": 2610, "total_steps": 4193, "loss": 0.1763, "lr": 1.5015557315897693e-05, "epoch": 4.357262103505843, "percentage": 62.25, "elapsed_time": "3:03:52", "remaining_time": "1:51:31"}
{"current_steps": 2615, "total_steps": 4193, "loss": 0.1726, "lr": 1.4934962952682943e-05, "epoch": 4.365609348914858, "percentage": 62.37, "elapsed_time": "3:04:09", "remaining_time": "1:51:07"}
{"current_steps": 2620, "total_steps": 4193, "loss": 0.1844, "lr": 1.4854456380093544e-05, "epoch": 4.373956594323873, "percentage": 62.49, "elapsed_time": "3:04:39", "remaining_time": "1:50:52"}
{"current_steps": 2625, "total_steps": 4193, "loss": 0.1676, "lr": 1.4774038993523523e-05, "epoch": 4.382303839732888, "percentage": 62.6, "elapsed_time": "3:05:07", "remaining_time": "1:50:34"}
{"current_steps": 2630, "total_steps": 4193, "loss": 0.1816, "lr": 1.4693712186821039e-05, "epoch": 4.390651085141903, "percentage": 62.72, "elapsed_time": "3:05:20", "remaining_time": "1:50:08"}
{"current_steps": 2635, "total_steps": 4193, "loss": 0.1851, "lr": 1.4613477352264293e-05, "epoch": 4.398998330550918, "percentage": 62.84, "elapsed_time": "3:05:36", "remaining_time": "1:49:44"}
{"current_steps": 2640, "total_steps": 4193, "loss": 0.1788, "lr": 1.4533335880537336e-05, "epoch": 4.407345575959933, "percentage": 62.96, "elapsed_time": "3:05:57", "remaining_time": "1:49:23"}
{"current_steps": 2645, "total_steps": 4193, "loss": 0.171, "lr": 1.4453289160706017e-05, "epoch": 4.415692821368948, "percentage": 63.08, "elapsed_time": "3:06:13", "remaining_time": "1:48:59"}
{"current_steps": 2650, "total_steps": 4193, "loss": 0.173, "lr": 1.4373338580193853e-05, "epoch": 4.424040066777963, "percentage": 63.2, "elapsed_time": "3:06:31", "remaining_time": "1:48:36"}
{"current_steps": 2655, "total_steps": 4193, "loss": 0.1815, "lr": 1.4293485524758045e-05, "epoch": 4.432387312186978, "percentage": 63.32, "elapsed_time": "3:06:51", "remaining_time": "1:48:14"}
{"current_steps": 2660, "total_steps": 4193, "loss": 0.1727, "lr": 1.4213731378465379e-05, "epoch": 4.440734557595993, "percentage": 63.44, "elapsed_time": "3:07:14", "remaining_time": "1:47:54"}
{"current_steps": 2665, "total_steps": 4193, "loss": 0.1922, "lr": 1.4134077523668327e-05, "epoch": 4.449081803005008, "percentage": 63.56, "elapsed_time": "3:07:35", "remaining_time": "1:47:33"}
{"current_steps": 2670, "total_steps": 4193, "loss": 0.1926, "lr": 1.405452534098101e-05, "epoch": 4.457429048414023, "percentage": 63.68, "elapsed_time": "3:07:58", "remaining_time": "1:47:13"}
{"current_steps": 2675, "total_steps": 4193, "loss": 0.1716, "lr": 1.3975076209255321e-05, "epoch": 4.465776293823039, "percentage": 63.8, "elapsed_time": "3:08:19", "remaining_time": "1:46:51"}
{"current_steps": 2680, "total_steps": 4193, "loss": 0.1837, "lr": 1.3895731505556978e-05, "epoch": 4.474123539232053, "percentage": 63.92, "elapsed_time": "3:08:44", "remaining_time": "1:46:33"}
{"current_steps": 2685, "total_steps": 4193, "loss": 0.1953, "lr": 1.3816492605141712e-05, "epoch": 4.482470784641069, "percentage": 64.04, "elapsed_time": "3:09:07", "remaining_time": "1:46:13"}
{"current_steps": 2690, "total_steps": 4193, "loss": 0.1788, "lr": 1.3737360881431374e-05, "epoch": 4.490818030050083, "percentage": 64.15, "elapsed_time": "3:09:32", "remaining_time": "1:45:54"}
{"current_steps": 2695, "total_steps": 4193, "loss": 0.168, "lr": 1.3658337705990185e-05, "epoch": 4.499165275459099, "percentage": 64.27, "elapsed_time": "3:09:54", "remaining_time": "1:45:33"}
{"current_steps": 2700, "total_steps": 4193, "loss": 0.1743, "lr": 1.3579424448500901e-05, "epoch": 4.507512520868113, "percentage": 64.39, "elapsed_time": "3:10:16", "remaining_time": "1:45:12"}
{"current_steps": 2705, "total_steps": 4193, "loss": 0.1854, "lr": 1.3500622476741142e-05, "epoch": 4.515859766277129, "percentage": 64.51, "elapsed_time": "3:10:33", "remaining_time": "1:44:49"}
{"current_steps": 2710, "total_steps": 4193, "loss": 0.1949, "lr": 1.3421933156559605e-05, "epoch": 4.524207011686143, "percentage": 64.63, "elapsed_time": "3:10:51", "remaining_time": "1:44:26"}
{"current_steps": 2715, "total_steps": 4193, "loss": 0.1661, "lr": 1.3343357851852488e-05, "epoch": 4.532554257095159, "percentage": 64.75, "elapsed_time": "3:11:12", "remaining_time": "1:44:05"}
{"current_steps": 2720, "total_steps": 4193, "loss": 0.1868, "lr": 1.3264897924539746e-05, "epoch": 4.540901502504173, "percentage": 64.87, "elapsed_time": "3:11:34", "remaining_time": "1:43:45"}
{"current_steps": 2725, "total_steps": 4193, "loss": 0.1749, "lr": 1.3186554734541574e-05, "epoch": 4.549248747913189, "percentage": 64.99, "elapsed_time": "3:11:52", "remaining_time": "1:43:21"}
{"current_steps": 2730, "total_steps": 4193, "loss": 0.182, "lr": 1.3108329639754765e-05, "epoch": 4.557595993322204, "percentage": 65.11, "elapsed_time": "3:12:09", "remaining_time": "1:42:58"}
{"current_steps": 2735, "total_steps": 4193, "loss": 0.178, "lr": 1.3030223996029237e-05, "epoch": 4.565943238731219, "percentage": 65.23, "elapsed_time": "3:12:24", "remaining_time": "1:42:34"}
{"current_steps": 2740, "total_steps": 4193, "loss": 0.1697, "lr": 1.295223915714447e-05, "epoch": 4.574290484140234, "percentage": 65.35, "elapsed_time": "3:12:40", "remaining_time": "1:42:10"}
{"current_steps": 2745, "total_steps": 4193, "loss": 0.1655, "lr": 1.287437647478611e-05, "epoch": 4.582637729549249, "percentage": 65.47, "elapsed_time": "3:13:04", "remaining_time": "1:41:50"}
{"current_steps": 2750, "total_steps": 4193, "loss": 0.1656, "lr": 1.2796637298522466e-05, "epoch": 4.590984974958264, "percentage": 65.59, "elapsed_time": "3:13:21", "remaining_time": "1:41:27"}
{"current_steps": 2755, "total_steps": 4193, "loss": 0.1834, "lr": 1.271902297578119e-05, "epoch": 4.599332220367279, "percentage": 65.7, "elapsed_time": "3:13:41", "remaining_time": "1:41:05"}
{"current_steps": 2760, "total_steps": 4193, "loss": 0.1901, "lr": 1.2641534851825865e-05, "epoch": 4.607679465776294, "percentage": 65.82, "elapsed_time": "3:13:57", "remaining_time": "1:40:42"}
{"current_steps": 2765, "total_steps": 4193, "loss": 0.1783, "lr": 1.256417426973272e-05, "epoch": 4.616026711185309, "percentage": 65.94, "elapsed_time": "3:14:15", "remaining_time": "1:40:19"}
{"current_steps": 2770, "total_steps": 4193, "loss": 0.1727, "lr": 1.248694257036735e-05, "epoch": 4.624373956594324, "percentage": 66.06, "elapsed_time": "3:14:37", "remaining_time": "1:39:58"}
{"current_steps": 2775, "total_steps": 4193, "loss": 0.1855, "lr": 1.2409841092361457e-05, "epoch": 4.632721202003339, "percentage": 66.18, "elapsed_time": "3:15:04", "remaining_time": "1:39:40"}
{"current_steps": 2780, "total_steps": 4193, "loss": 0.1765, "lr": 1.233287117208966e-05, "epoch": 4.641068447412354, "percentage": 66.3, "elapsed_time": "3:15:24", "remaining_time": "1:39:19"}
{"current_steps": 2785, "total_steps": 4193, "loss": 0.1765, "lr": 1.2256034143646341e-05, "epoch": 4.649415692821369, "percentage": 66.42, "elapsed_time": "3:15:43", "remaining_time": "1:38:56"}
{"current_steps": 2790, "total_steps": 4193, "loss": 0.1656, "lr": 1.2179331338822498e-05, "epoch": 4.657762938230384, "percentage": 66.54, "elapsed_time": "3:16:05", "remaining_time": "1:38:36"}
{"current_steps": 2795, "total_steps": 4193, "loss": 0.1834, "lr": 1.2102764087082685e-05, "epoch": 4.666110183639399, "percentage": 66.66, "elapsed_time": "3:16:24", "remaining_time": "1:38:14"}
{"current_steps": 2800, "total_steps": 4193, "loss": 0.193, "lr": 1.2026333715541959e-05, "epoch": 4.674457429048414, "percentage": 66.78, "elapsed_time": "3:16:42", "remaining_time": "1:37:51"}
{"current_steps": 2805, "total_steps": 4193, "loss": 0.168, "lr": 1.1950041548942867e-05, "epoch": 4.682804674457429, "percentage": 66.9, "elapsed_time": "3:17:03", "remaining_time": "1:37:30"}
{"current_steps": 2810, "total_steps": 4193, "loss": 0.1888, "lr": 1.1873888909632508e-05, "epoch": 4.691151919866444, "percentage": 67.02, "elapsed_time": "3:17:19", "remaining_time": "1:37:07"}
{"current_steps": 2815, "total_steps": 4193, "loss": 0.1997, "lr": 1.1797877117539587e-05, "epoch": 4.699499165275459, "percentage": 67.14, "elapsed_time": "3:17:42", "remaining_time": "1:36:46"}
{"current_steps": 2820, "total_steps": 4193, "loss": 0.1697, "lr": 1.1722007490151566e-05, "epoch": 4.707846410684474, "percentage": 67.25, "elapsed_time": "3:18:00", "remaining_time": "1:36:24"}
{"current_steps": 2825, "total_steps": 4193, "loss": 0.1732, "lr": 1.16462813424918e-05, "epoch": 4.716193656093489, "percentage": 67.37, "elapsed_time": "3:18:21", "remaining_time": "1:36:03"}
{"current_steps": 2830, "total_steps": 4193, "loss": 0.1884, "lr": 1.1570699987096763e-05, "epoch": 4.724540901502504, "percentage": 67.49, "elapsed_time": "3:18:43", "remaining_time": "1:35:42"}
{"current_steps": 2835, "total_steps": 4193, "loss": 0.1664, "lr": 1.1495264733993288e-05, "epoch": 4.732888146911519, "percentage": 67.61, "elapsed_time": "3:19:00", "remaining_time": "1:35:19"}
{"current_steps": 2840, "total_steps": 4193, "loss": 0.1812, "lr": 1.141997689067587e-05, "epoch": 4.741235392320534, "percentage": 67.73, "elapsed_time": "3:19:17", "remaining_time": "1:34:56"}
{"current_steps": 2845, "total_steps": 4193, "loss": 0.1651, "lr": 1.1344837762083997e-05, "epoch": 4.749582637729549, "percentage": 67.85, "elapsed_time": "3:19:38", "remaining_time": "1:34:35"}
{"current_steps": 2850, "total_steps": 4193, "loss": 0.1665, "lr": 1.1269848650579532e-05, "epoch": 4.757929883138564, "percentage": 67.97, "elapsed_time": "3:20:00", "remaining_time": "1:34:14"}
{"current_steps": 2855, "total_steps": 4193, "loss": 0.1851, "lr": 1.1195010855924138e-05, "epoch": 4.766277128547579, "percentage": 68.09, "elapsed_time": "3:20:18", "remaining_time": "1:33:52"}
{"current_steps": 2860, "total_steps": 4193, "loss": 0.1909, "lr": 1.112032567525676e-05, "epoch": 4.774624373956595, "percentage": 68.21, "elapsed_time": "3:20:34", "remaining_time": "1:33:29"}
{"current_steps": 2865, "total_steps": 4193, "loss": 0.1822, "lr": 1.1045794403071133e-05, "epoch": 4.782971619365609, "percentage": 68.33, "elapsed_time": "3:20:49", "remaining_time": "1:33:05"}
{"current_steps": 2870, "total_steps": 4193, "loss": 0.1665, "lr": 1.0971418331193337e-05, "epoch": 4.791318864774624, "percentage": 68.45, "elapsed_time": "3:21:06", "remaining_time": "1:32:42"}
{"current_steps": 2875, "total_steps": 4193, "loss": 0.1801, "lr": 1.0897198748759435e-05, "epoch": 4.799666110183639, "percentage": 68.57, "elapsed_time": "3:21:32", "remaining_time": "1:32:23"}
{"current_steps": 2880, "total_steps": 4193, "loss": 0.1953, "lr": 1.0823136942193089e-05, "epoch": 4.808013355592655, "percentage": 68.69, "elapsed_time": "3:21:58", "remaining_time": "1:32:04"}
{"current_steps": 2885, "total_steps": 4193, "loss": 0.176, "lr": 1.07492341951833e-05, "epoch": 4.816360601001669, "percentage": 68.81, "elapsed_time": "3:22:19", "remaining_time": "1:31:43"}
{"current_steps": 2890, "total_steps": 4193, "loss": 0.1958, "lr": 1.0675491788662132e-05, "epoch": 4.824707846410685, "percentage": 68.92, "elapsed_time": "3:22:41", "remaining_time": "1:31:23"}
{"current_steps": 2895, "total_steps": 4193, "loss": 0.18, "lr": 1.060191100078252e-05, "epoch": 4.833055091819699, "percentage": 69.04, "elapsed_time": "3:23:07", "remaining_time": "1:31:04"}
{"current_steps": 2900, "total_steps": 4193, "loss": 0.1782, "lr": 1.0528493106896126e-05, "epoch": 4.841402337228715, "percentage": 69.16, "elapsed_time": "3:23:28", "remaining_time": "1:30:43"}
{"current_steps": 2905, "total_steps": 4193, "loss": 0.1808, "lr": 1.0455239379531213e-05, "epoch": 4.849749582637729, "percentage": 69.28, "elapsed_time": "3:23:49", "remaining_time": "1:30:22"}
{"current_steps": 2910, "total_steps": 4193, "loss": 0.1886, "lr": 1.0382151088370605e-05, "epoch": 4.858096828046745, "percentage": 69.4, "elapsed_time": "3:24:08", "remaining_time": "1:30:00"}
{"current_steps": 2915, "total_steps": 4193, "loss": 0.1723, "lr": 1.0309229500229665e-05, "epoch": 4.866444073455759, "percentage": 69.52, "elapsed_time": "3:24:30", "remaining_time": "1:29:39"}
{"current_steps": 2920, "total_steps": 4193, "loss": 0.1828, "lr": 1.023647587903438e-05, "epoch": 4.874791318864775, "percentage": 69.64, "elapsed_time": "3:25:01", "remaining_time": "1:29:22"}
{"current_steps": 2925, "total_steps": 4193, "loss": 0.184, "lr": 1.0163891485799362e-05, "epoch": 4.883138564273789, "percentage": 69.76, "elapsed_time": "3:25:20", "remaining_time": "1:29:00"}
{"current_steps": 2930, "total_steps": 4193, "loss": 0.1687, "lr": 1.0091477578606121e-05, "epoch": 4.891485809682805, "percentage": 69.88, "elapsed_time": "3:25:38", "remaining_time": "1:28:38"}
{"current_steps": 2935, "total_steps": 4193, "loss": 0.1812, "lr": 1.0019235412581117e-05, "epoch": 4.89983305509182, "percentage": 70.0, "elapsed_time": "3:25:58", "remaining_time": "1:28:16"}
{"current_steps": 2940, "total_steps": 4193, "loss": 0.173, "lr": 9.947166239874144e-06, "epoch": 4.908180300500835, "percentage": 70.12, "elapsed_time": "3:26:19", "remaining_time": "1:27:56"}
{"current_steps": 2945, "total_steps": 4193, "loss": 0.1764, "lr": 9.875271309636498e-06, "epoch": 4.91652754590985, "percentage": 70.24, "elapsed_time": "3:26:43", "remaining_time": "1:27:36"}
{"current_steps": 2950, "total_steps": 4193, "loss": 0.2114, "lr": 9.803551867999445e-06, "epoch": 4.924874791318865, "percentage": 70.36, "elapsed_time": "3:27:02", "remaining_time": "1:27:14"}
{"current_steps": 2955, "total_steps": 4193, "loss": 0.1819, "lr": 9.732009158052508e-06, "epoch": 4.93322203672788, "percentage": 70.47, "elapsed_time": "3:27:26", "remaining_time": "1:26:54"}
{"current_steps": 2960, "total_steps": 4193, "loss": 0.1966, "lr": 9.660644419822037e-06, "epoch": 4.941569282136895, "percentage": 70.59, "elapsed_time": "3:27:46", "remaining_time": "1:26:32"}
{"current_steps": 2965, "total_steps": 4193, "loss": 0.1975, "lr": 9.589458890249595e-06, "epoch": 4.94991652754591, "percentage": 70.71, "elapsed_time": "3:28:07", "remaining_time": "1:26:11"}
{"current_steps": 2970, "total_steps": 4193, "loss": 0.1846, "lr": 9.518453803170637e-06, "epoch": 4.958263772954925, "percentage": 70.83, "elapsed_time": "3:28:27", "remaining_time": "1:25:50"}
{"current_steps": 2975, "total_steps": 4193, "loss": 0.1931, "lr": 9.447630389293017e-06, "epoch": 4.96661101836394, "percentage": 70.95, "elapsed_time": "3:28:42", "remaining_time": "1:25:27"}
{"current_steps": 2980, "total_steps": 4193, "loss": 0.1887, "lr": 9.37698987617576e-06, "epoch": 4.974958263772955, "percentage": 71.07, "elapsed_time": "3:29:07", "remaining_time": "1:25:07"}
{"current_steps": 2985, "total_steps": 4193, "loss": 0.1766, "lr": 9.306533488207671e-06, "epoch": 4.98330550918197, "percentage": 71.19, "elapsed_time": "3:29:28", "remaining_time": "1:24:46"}
{"current_steps": 2990, "total_steps": 4193, "loss": 0.1892, "lr": 9.236262446586239e-06, "epoch": 4.9916527545909855, "percentage": 71.31, "elapsed_time": "3:29:48", "remaining_time": "1:24:25"}
{"current_steps": 2995, "total_steps": 4193, "loss": 0.1865, "lr": 9.166177969296343e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "3:30:08", "remaining_time": "1:24:03"}
{"current_steps": 3000, "total_steps": 4193, "loss": 0.1798, "lr": 9.096281271089264e-06, "epoch": 5.008347245409015, "percentage": 71.55, "elapsed_time": "3:30:32", "remaining_time": "1:23:43"}
{"current_steps": 3005, "total_steps": 4193, "loss": 0.149, "lr": 9.02657356346151e-06, "epoch": 5.01669449081803, "percentage": 71.67, "elapsed_time": "3:31:03", "remaining_time": "1:23:26"}
{"current_steps": 3010, "total_steps": 4193, "loss": 0.1486, "lr": 8.957056054633934e-06, "epoch": 5.025041736227045, "percentage": 71.79, "elapsed_time": "3:31:26", "remaining_time": "1:23:05"}
{"current_steps": 3015, "total_steps": 4193, "loss": 0.1482, "lr": 8.887729949530682e-06, "epoch": 5.03338898163606, "percentage": 71.91, "elapsed_time": "3:31:45", "remaining_time": "1:22:44"}
{"current_steps": 3020, "total_steps": 4193, "loss": 0.1647, "lr": 8.818596449758416e-06, "epoch": 5.041736227045075, "percentage": 72.02, "elapsed_time": "3:32:05", "remaining_time": "1:22:22"}
{"current_steps": 3025, "total_steps": 4193, "loss": 0.1667, "lr": 8.749656753585379e-06, "epoch": 5.05008347245409, "percentage": 72.14, "elapsed_time": "3:32:27", "remaining_time": "1:22:01"}
{"current_steps": 3030, "total_steps": 4193, "loss": 0.1549, "lr": 8.680912055920734e-06, "epoch": 5.058430717863105, "percentage": 72.26, "elapsed_time": "3:32:49", "remaining_time": "1:21:41"}
{"current_steps": 3035, "total_steps": 4193, "loss": 0.15, "lr": 8.612363548293744e-06, "epoch": 5.06677796327212, "percentage": 72.38, "elapsed_time": "3:33:14", "remaining_time": "1:21:21"}
{"current_steps": 3040, "total_steps": 4193, "loss": 0.1592, "lr": 8.54401241883322e-06, "epoch": 5.075125208681135, "percentage": 72.5, "elapsed_time": "3:33:38", "remaining_time": "1:21:01"}
{"current_steps": 3045, "total_steps": 4193, "loss": 0.1614, "lr": 8.475859852246854e-06, "epoch": 5.08347245409015, "percentage": 72.62, "elapsed_time": "3:34:01", "remaining_time": "1:20:41"}
{"current_steps": 3050, "total_steps": 4193, "loss": 0.1641, "lr": 8.407907029800732e-06, "epoch": 5.091819699499165, "percentage": 72.74, "elapsed_time": "3:34:17", "remaining_time": "1:20:18"}
{"current_steps": 3055, "total_steps": 4193, "loss": 0.1801, "lr": 8.340155129298824e-06, "epoch": 5.10016694490818, "percentage": 72.86, "elapsed_time": "3:34:42", "remaining_time": "1:19:58"}
{"current_steps": 3060, "total_steps": 4193, "loss": 0.1596, "lr": 8.272605325062595e-06, "epoch": 5.108514190317195, "percentage": 72.98, "elapsed_time": "3:35:00", "remaining_time": "1:19:36"}
{"current_steps": 3065, "total_steps": 4193, "loss": 0.1521, "lr": 8.205258787910636e-06, "epoch": 5.116861435726211, "percentage": 73.1, "elapsed_time": "3:35:25", "remaining_time": "1:19:17"}
{"current_steps": 3070, "total_steps": 4193, "loss": 0.1588, "lr": 8.138116685138386e-06, "epoch": 5.125208681135225, "percentage": 73.22, "elapsed_time": "3:35:49", "remaining_time": "1:18:56"}
{"current_steps": 3075, "total_steps": 4193, "loss": 0.1438, "lr": 8.07118018049788e-06, "epoch": 5.133555926544241, "percentage": 73.34, "elapsed_time": "3:36:07", "remaining_time": "1:18:34"}
{"current_steps": 3080, "total_steps": 4193, "loss": 0.1502, "lr": 8.00445043417759e-06, "epoch": 5.141903171953255, "percentage": 73.46, "elapsed_time": "3:36:25", "remaining_time": "1:18:12"}
{"current_steps": 3085, "total_steps": 4193, "loss": 0.1516, "lr": 7.93792860278232e-06, "epoch": 5.150250417362271, "percentage": 73.58, "elapsed_time": "3:36:50", "remaining_time": "1:17:52"}
{"current_steps": 3090, "total_steps": 4193, "loss": 0.1528, "lr": 7.871615839313147e-06, "epoch": 5.158597662771285, "percentage": 73.69, "elapsed_time": "3:37:11", "remaining_time": "1:17:31"}
{"current_steps": 3095, "total_steps": 4193, "loss": 0.1468, "lr": 7.805513293147441e-06, "epoch": 5.166944908180301, "percentage": 73.81, "elapsed_time": "3:37:29", "remaining_time": "1:17:09"}
{"current_steps": 3100, "total_steps": 4193, "loss": 0.1608, "lr": 7.739622110018951e-06, "epoch": 5.175292153589315, "percentage": 73.93, "elapsed_time": "3:37:47", "remaining_time": "1:16:47"}
{"current_steps": 3105, "total_steps": 4193, "loss": 0.1797, "lr": 7.673943431997935e-06, "epoch": 5.183639398998331, "percentage": 74.05, "elapsed_time": "3:38:03", "remaining_time": "1:16:24"}
{"current_steps": 3110, "total_steps": 4193, "loss": 0.1621, "lr": 7.608478397471366e-06, "epoch": 5.191986644407345, "percentage": 74.17, "elapsed_time": "3:38:23", "remaining_time": "1:16:03"}
{"current_steps": 3115, "total_steps": 4193, "loss": 0.1515, "lr": 7.543228141123217e-06, "epoch": 5.200333889816361, "percentage": 74.29, "elapsed_time": "3:38:52", "remaining_time": "1:15:44"}
{"current_steps": 3120, "total_steps": 4193, "loss": 0.1642, "lr": 7.478193793914767e-06, "epoch": 5.208681135225375, "percentage": 74.41, "elapsed_time": "3:39:07", "remaining_time": "1:15:21"}
{"current_steps": 3125, "total_steps": 4193, "loss": 0.149, "lr": 7.4133764830650246e-06, "epoch": 5.217028380634391, "percentage": 74.53, "elapsed_time": "3:39:29", "remaining_time": "1:15:00"}
{"current_steps": 3130, "total_steps": 4193, "loss": 0.1507, "lr": 7.348777332031168e-06, "epoch": 5.225375626043405, "percentage": 74.65, "elapsed_time": "3:39:50", "remaining_time": "1:14:39"}
{"current_steps": 3135, "total_steps": 4193, "loss": 0.171, "lr": 7.28439746048909e-06, "epoch": 5.233722871452421, "percentage": 74.77, "elapsed_time": "3:40:19", "remaining_time": "1:14:21"}
{"current_steps": 3140, "total_steps": 4193, "loss": 0.1441, "lr": 7.22023798431398e-06, "epoch": 5.242070116861436, "percentage": 74.89, "elapsed_time": "3:40:37", "remaining_time": "1:13:59"}
{"current_steps": 3145, "total_steps": 4193, "loss": 0.1669, "lr": 7.156300015560993e-06, "epoch": 5.250417362270451, "percentage": 75.01, "elapsed_time": "3:40:59", "remaining_time": "1:13:38"}
{"current_steps": 3150, "total_steps": 4193, "loss": 0.1526, "lr": 7.092584662445958e-06, "epoch": 5.258764607679466, "percentage": 75.13, "elapsed_time": "3:41:20", "remaining_time": "1:13:17"}
{"current_steps": 3155, "total_steps": 4193, "loss": 0.1705, "lr": 7.029093029326191e-06, "epoch": 5.267111853088481, "percentage": 75.24, "elapsed_time": "3:41:40", "remaining_time": "1:12:56"}
{"current_steps": 3160, "total_steps": 4193, "loss": 0.1577, "lr": 6.965826216681337e-06, "epoch": 5.275459098497496, "percentage": 75.36, "elapsed_time": "3:42:05", "remaining_time": "1:12:35"}
{"current_steps": 3165, "total_steps": 4193, "loss": 0.1666, "lr": 6.902785321094301e-06, "epoch": 5.283806343906511, "percentage": 75.48, "elapsed_time": "3:42:19", "remaining_time": "1:12:12"}
{"current_steps": 3170, "total_steps": 4193, "loss": 0.1655, "lr": 6.8399714352322424e-06, "epoch": 5.292153589315526, "percentage": 75.6, "elapsed_time": "3:42:45", "remaining_time": "1:11:53"}
{"current_steps": 3175, "total_steps": 4193, "loss": 0.1488, "lr": 6.777385647827639e-06, "epoch": 5.300500834724541, "percentage": 75.72, "elapsed_time": "3:43:02", "remaining_time": "1:11:30"}
{"current_steps": 3180, "total_steps": 4193, "loss": 0.1485, "lr": 6.715029043659409e-06, "epoch": 5.308848080133556, "percentage": 75.84, "elapsed_time": "3:43:23", "remaining_time": "1:11:09"}
{"current_steps": 3185, "total_steps": 4193, "loss": 0.159, "lr": 6.652902703534114e-06, "epoch": 5.317195325542571, "percentage": 75.96, "elapsed_time": "3:43:40", "remaining_time": "1:10:47"}
{"current_steps": 3190, "total_steps": 4193, "loss": 0.1605, "lr": 6.5910077042672246e-06, "epoch": 5.325542570951586, "percentage": 76.08, "elapsed_time": "3:43:58", "remaining_time": "1:10:25"}
{"current_steps": 3195, "total_steps": 4193, "loss": 0.1396, "lr": 6.5293451186644566e-06, "epoch": 5.333889816360601, "percentage": 76.2, "elapsed_time": "3:44:17", "remaining_time": "1:10:03"}
{"current_steps": 3200, "total_steps": 4193, "loss": 0.1528, "lr": 6.467916015503173e-06, "epoch": 5.342237061769616, "percentage": 76.32, "elapsed_time": "3:44:35", "remaining_time": "1:09:41"}
{"current_steps": 3205, "total_steps": 4193, "loss": 0.1614, "lr": 6.406721459513865e-06, "epoch": 5.350584307178631, "percentage": 76.44, "elapsed_time": "3:44:55", "remaining_time": "1:09:20"}
{"current_steps": 3210, "total_steps": 4193, "loss": 0.1783, "lr": 6.3457625113616995e-06, "epoch": 5.358931552587646, "percentage": 76.56, "elapsed_time": "3:45:10", "remaining_time": "1:08:57"}
{"current_steps": 3215, "total_steps": 4193, "loss": 0.1518, "lr": 6.2850402276281184e-06, "epoch": 5.367278797996661, "percentage": 76.68, "elapsed_time": "3:45:32", "remaining_time": "1:08:36"}
{"current_steps": 3220, "total_steps": 4193, "loss": 0.1474, "lr": 6.224555660792546e-06, "epoch": 5.375626043405676, "percentage": 76.79, "elapsed_time": "3:45:52", "remaining_time": "1:08:15"}
{"current_steps": 3225, "total_steps": 4193, "loss": 0.1591, "lr": 6.164309859214135e-06, "epoch": 5.383973288814691, "percentage": 76.91, "elapsed_time": "3:46:09", "remaining_time": "1:07:52"}
{"current_steps": 3230, "total_steps": 4193, "loss": 0.1636, "lr": 6.104303867113599e-06, "epoch": 5.392320534223706, "percentage": 77.03, "elapsed_time": "3:46:30", "remaining_time": "1:07:32"}
{"current_steps": 3235, "total_steps": 4193, "loss": 0.1696, "lr": 6.044538724555109e-06, "epoch": 5.400667779632721, "percentage": 77.15, "elapsed_time": "3:46:53", "remaining_time": "1:07:11"}
{"current_steps": 3240, "total_steps": 4193, "loss": 0.1597, "lr": 5.9850154674282766e-06, "epoch": 5.409015025041736, "percentage": 77.27, "elapsed_time": "3:47:07", "remaining_time": "1:06:48"}
{"current_steps": 3245, "total_steps": 4193, "loss": 0.1508, "lr": 5.925735127430186e-06, "epoch": 5.417362270450751, "percentage": 77.39, "elapsed_time": "3:47:33", "remaining_time": "1:06:28"}
{"current_steps": 3250, "total_steps": 4193, "loss": 0.1867, "lr": 5.866698732047522e-06, "epoch": 5.425709515859766, "percentage": 77.51, "elapsed_time": "3:47:55", "remaining_time": "1:06:07"}
{"current_steps": 3255, "total_steps": 4193, "loss": 0.1708, "lr": 5.8079073045387555e-06, "epoch": 5.434056761268781, "percentage": 77.63, "elapsed_time": "3:48:17", "remaining_time": "1:05:47"}
{"current_steps": 3260, "total_steps": 4193, "loss": 0.1687, "lr": 5.7493618639164115e-06, "epoch": 5.442404006677796, "percentage": 77.75, "elapsed_time": "3:48:40", "remaining_time": "1:05:26"}
{"current_steps": 3265, "total_steps": 4193, "loss": 0.158, "lr": 5.691063424929406e-06, "epoch": 5.450751252086811, "percentage": 77.87, "elapsed_time": "3:49:02", "remaining_time": "1:05:05"}
{"current_steps": 3270, "total_steps": 4193, "loss": 0.1527, "lr": 5.633012998045451e-06, "epoch": 5.459098497495827, "percentage": 77.99, "elapsed_time": "3:49:27", "remaining_time": "1:04:46"}
{"current_steps": 3275, "total_steps": 4193, "loss": 0.1513, "lr": 5.575211589433554e-06, "epoch": 5.467445742904841, "percentage": 78.11, "elapsed_time": "3:49:49", "remaining_time": "1:04:25"}
{"current_steps": 3280, "total_steps": 4193, "loss": 0.1492, "lr": 5.517660200946562e-06, "epoch": 5.475792988313857, "percentage": 78.23, "elapsed_time": "3:50:05", "remaining_time": "1:04:02"}
{"current_steps": 3285, "total_steps": 4193, "loss": 0.1417, "lr": 5.4603598301038145e-06, "epoch": 5.484140233722871, "percentage": 78.34, "elapsed_time": "3:50:26", "remaining_time": "1:03:41"}
{"current_steps": 3290, "total_steps": 4193, "loss": 0.1498, "lr": 5.4033114700738375e-06, "epoch": 5.492487479131887, "percentage": 78.46, "elapsed_time": "3:50:47", "remaining_time": "1:03:20"}
{"current_steps": 3295, "total_steps": 4193, "loss": 0.1585, "lr": 5.346516109657136e-06, "epoch": 5.500834724540901, "percentage": 78.58, "elapsed_time": "3:51:08", "remaining_time": "1:02:59"}
{"current_steps": 3300, "total_steps": 4193, "loss": 0.1596, "lr": 5.289974733269063e-06, "epoch": 5.509181969949917, "percentage": 78.7, "elapsed_time": "3:51:29", "remaining_time": "1:02:38"}
{"current_steps": 3305, "total_steps": 4193, "loss": 0.1484, "lr": 5.233688320922741e-06, "epoch": 5.517529215358931, "percentage": 78.82, "elapsed_time": "3:51:47", "remaining_time": "1:02:16"}
{"current_steps": 3310, "total_steps": 4193, "loss": 0.1734, "lr": 5.177657848212092e-06, "epoch": 5.525876460767947, "percentage": 78.94, "elapsed_time": "3:52:02", "remaining_time": "1:01:53"}
{"current_steps": 3315, "total_steps": 4193, "loss": 0.1521, "lr": 5.1218842862949115e-06, "epoch": 5.534223706176961, "percentage": 79.06, "elapsed_time": "3:52:22", "remaining_time": "1:01:32"}
{"current_steps": 3320, "total_steps": 4193, "loss": 0.177, "lr": 5.066368601876048e-06, "epoch": 5.542570951585977, "percentage": 79.18, "elapsed_time": "3:52:41", "remaining_time": "1:01:11"}
{"current_steps": 3325, "total_steps": 4193, "loss": 0.1525, "lr": 5.011111757190661e-06, "epoch": 5.550918196994992, "percentage": 79.3, "elapsed_time": "3:53:06", "remaining_time": "1:00:51"}
{"current_steps": 3330, "total_steps": 4193, "loss": 0.1604, "lr": 4.956114709987488e-06, "epoch": 5.559265442404007, "percentage": 79.42, "elapsed_time": "3:53:33", "remaining_time": "1:00:31"}
{"current_steps": 3335, "total_steps": 4193, "loss": 0.1706, "lr": 4.901378413512325e-06, "epoch": 5.567612687813021, "percentage": 79.54, "elapsed_time": "3:53:53", "remaining_time": "1:00:10"}
{"current_steps": 3340, "total_steps": 4193, "loss": 0.1451, "lr": 4.846903816491419e-06, "epoch": 5.575959933222037, "percentage": 79.66, "elapsed_time": "3:54:17", "remaining_time": "0:59:50"}
{"current_steps": 3345, "total_steps": 4193, "loss": 0.1813, "lr": 4.792691863115113e-06, "epoch": 5.584307178631052, "percentage": 79.78, "elapsed_time": "3:54:32", "remaining_time": "0:59:27"}
{"current_steps": 3350, "total_steps": 4193, "loss": 0.164, "lr": 4.738743493021383e-06, "epoch": 5.592654424040067, "percentage": 79.9, "elapsed_time": "3:54:50", "remaining_time": "0:59:05"}
{"current_steps": 3355, "total_steps": 4193, "loss": 0.1644, "lr": 4.68505964127965e-06, "epoch": 5.601001669449082, "percentage": 80.01, "elapsed_time": "3:55:11", "remaining_time": "0:58:44"}
{"current_steps": 3360, "total_steps": 4193, "loss": 0.1617, "lr": 4.631641238374482e-06, "epoch": 5.609348914858097, "percentage": 80.13, "elapsed_time": "3:55:32", "remaining_time": "0:58:23"}
{"current_steps": 3365, "total_steps": 4193, "loss": 0.1489, "lr": 4.578489210189554e-06, "epoch": 5.617696160267112, "percentage": 80.25, "elapsed_time": "3:55:54", "remaining_time": "0:58:02"}
{"current_steps": 3370, "total_steps": 4193, "loss": 0.17, "lr": 4.525604477991505e-06, "epoch": 5.626043405676127, "percentage": 80.37, "elapsed_time": "3:56:20", "remaining_time": "0:57:43"}
{"current_steps": 3375, "total_steps": 4193, "loss": 0.1789, "lr": 4.472987958414077e-06, "epoch": 5.634390651085142, "percentage": 80.49, "elapsed_time": "3:56:49", "remaining_time": "0:57:24"}
{"current_steps": 3380, "total_steps": 4193, "loss": 0.1468, "lr": 4.420640563442111e-06, "epoch": 5.642737896494157, "percentage": 80.61, "elapsed_time": "3:57:09", "remaining_time": "0:57:02"}
{"current_steps": 3385, "total_steps": 4193, "loss": 0.1622, "lr": 4.368563200395859e-06, "epoch": 5.651085141903172, "percentage": 80.73, "elapsed_time": "3:57:26", "remaining_time": "0:56:40"}
{"current_steps": 3390, "total_steps": 4193, "loss": 0.1602, "lr": 4.31675677191514e-06, "epoch": 5.659432387312187, "percentage": 80.85, "elapsed_time": "3:57:47", "remaining_time": "0:56:19"}
{"current_steps": 3395, "total_steps": 4193, "loss": 0.1764, "lr": 4.265222175943808e-06, "epoch": 5.667779632721202, "percentage": 80.97, "elapsed_time": "3:58:03", "remaining_time": "0:55:57"}
{"current_steps": 3400, "total_steps": 4193, "loss": 0.1651, "lr": 4.213960305714082e-06, "epoch": 5.676126878130217, "percentage": 81.09, "elapsed_time": "3:58:20", "remaining_time": "0:55:35"}
{"current_steps": 3405, "total_steps": 4193, "loss": 0.1563, "lr": 4.162972049731164e-06, "epoch": 5.684474123539232, "percentage": 81.21, "elapsed_time": "3:58:36", "remaining_time": "0:55:13"}
{"current_steps": 3410, "total_steps": 4193, "loss": 0.1547, "lr": 4.112258291757747e-06, "epoch": 5.692821368948247, "percentage": 81.33, "elapsed_time": "3:58:58", "remaining_time": "0:54:52"}
{"current_steps": 3415, "total_steps": 4193, "loss": 0.1583, "lr": 4.061819910798777e-06, "epoch": 5.701168614357262, "percentage": 81.45, "elapsed_time": "3:59:24", "remaining_time": "0:54:32"}
{"current_steps": 3420, "total_steps": 4193, "loss": 0.1493, "lr": 4.01165778108614e-06, "epoch": 5.709515859766277, "percentage": 81.56, "elapsed_time": "3:59:45", "remaining_time": "0:54:11"}
{"current_steps": 3425, "total_steps": 4193, "loss": 0.1706, "lr": 3.961772772063599e-06, "epoch": 5.717863105175292, "percentage": 81.68, "elapsed_time": "4:00:03", "remaining_time": "0:53:49"}
{"current_steps": 3430, "total_steps": 4193, "loss": 0.1596, "lr": 3.912165748371626e-06, "epoch": 5.726210350584307, "percentage": 81.8, "elapsed_time": "4:00:24", "remaining_time": "0:53:28"}
{"current_steps": 3435, "total_steps": 4193, "loss": 0.1589, "lr": 3.8628375698325045e-06, "epoch": 5.734557595993322, "percentage": 81.92, "elapsed_time": "4:00:41", "remaining_time": "0:53:06"}
{"current_steps": 3440, "total_steps": 4193, "loss": 0.1618, "lr": 3.8137890914353535e-06, "epoch": 5.742904841402337, "percentage": 82.04, "elapsed_time": "4:01:06", "remaining_time": "0:52:46"}
{"current_steps": 3445, "total_steps": 4193, "loss": 0.1508, "lr": 3.765021163321374e-06, "epoch": 5.751252086811352, "percentage": 82.16, "elapsed_time": "4:01:24", "remaining_time": "0:52:25"}
{"current_steps": 3450, "total_steps": 4193, "loss": 0.169, "lr": 3.7165346307690466e-06, "epoch": 5.759599332220367, "percentage": 82.28, "elapsed_time": "4:01:46", "remaining_time": "0:52:04"}
{"current_steps": 3455, "total_steps": 4193, "loss": 0.1737, "lr": 3.6683303341795483e-06, "epoch": 5.767946577629383, "percentage": 82.4, "elapsed_time": "4:02:09", "remaining_time": "0:51:43"}
{"current_steps": 3460, "total_steps": 4193, "loss": 0.159, "lr": 3.6204091090621176e-06, "epoch": 5.776293823038397, "percentage": 82.52, "elapsed_time": "4:02:22", "remaining_time": "0:51:20"}
{"current_steps": 3465, "total_steps": 4193, "loss": 0.1719, "lr": 3.572771786019649e-06, "epoch": 5.784641068447412, "percentage": 82.64, "elapsed_time": "4:02:39", "remaining_time": "0:50:58"}
{"current_steps": 3470, "total_steps": 4193, "loss": 0.1464, "lr": 3.5254191907342117e-06, "epoch": 5.792988313856427, "percentage": 82.76, "elapsed_time": "4:03:05", "remaining_time": "0:50:39"}
{"current_steps": 3475, "total_steps": 4193, "loss": 0.1599, "lr": 3.4783521439528233e-06, "epoch": 5.801335559265443, "percentage": 82.88, "elapsed_time": "4:03:26", "remaining_time": "0:50:18"}
{"current_steps": 3480, "total_steps": 4193, "loss": 0.1769, "lr": 3.4315714614731467e-06, "epoch": 5.809682804674457, "percentage": 83.0, "elapsed_time": "4:03:40", "remaining_time": "0:49:55"}
{"current_steps": 3485, "total_steps": 4193, "loss": 0.1617, "lr": 3.385077954129421e-06, "epoch": 5.818030050083473, "percentage": 83.11, "elapsed_time": "4:03:58", "remaining_time": "0:49:33"}
{"current_steps": 3490, "total_steps": 4193, "loss": 0.1708, "lr": 3.3388724277783347e-06, "epoch": 5.826377295492487, "percentage": 83.23, "elapsed_time": "4:04:20", "remaining_time": "0:49:13"}
{"current_steps": 3495, "total_steps": 4193, "loss": 0.1665, "lr": 3.292955683285135e-06, "epoch": 5.834724540901503, "percentage": 83.35, "elapsed_time": "4:04:40", "remaining_time": "0:48:51"}
{"current_steps": 3500, "total_steps": 4193, "loss": 0.1564, "lr": 3.2473285165096736e-06, "epoch": 5.843071786310517, "percentage": 83.47, "elapsed_time": "4:04:59", "remaining_time": "0:48:30"}
{"current_steps": 3505, "total_steps": 4193, "loss": 0.1581, "lr": 3.2019917182926806e-06, "epoch": 5.851419031719533, "percentage": 83.59, "elapsed_time": "4:05:18", "remaining_time": "0:48:09"}
{"current_steps": 3510, "total_steps": 4193, "loss": 0.1523, "lr": 3.156946074441982e-06, "epoch": 5.859766277128547, "percentage": 83.71, "elapsed_time": "4:05:38", "remaining_time": "0:47:47"}
{"current_steps": 3515, "total_steps": 4193, "loss": 0.1724, "lr": 3.112192365718969e-06, "epoch": 5.868113522537563, "percentage": 83.83, "elapsed_time": "4:05:54", "remaining_time": "0:47:25"}
{"current_steps": 3520, "total_steps": 4193, "loss": 0.1436, "lr": 3.067731367824969e-06, "epoch": 5.876460767946577, "percentage": 83.95, "elapsed_time": "4:06:15", "remaining_time": "0:47:04"}
{"current_steps": 3525, "total_steps": 4193, "loss": 0.171, "lr": 3.023563851387885e-06, "epoch": 5.884808013355593, "percentage": 84.07, "elapsed_time": "4:06:40", "remaining_time": "0:46:44"}
{"current_steps": 3530, "total_steps": 4193, "loss": 0.1474, "lr": 2.979690581948784e-06, "epoch": 5.893155258764608, "percentage": 84.19, "elapsed_time": "4:06:57", "remaining_time": "0:46:23"}
{"current_steps": 3535, "total_steps": 4193, "loss": 0.176, "lr": 2.936112319948654e-06, "epoch": 5.901502504173623, "percentage": 84.31, "elapsed_time": "4:07:16", "remaining_time": "0:46:01"}
{"current_steps": 3540, "total_steps": 4193, "loss": 0.1605, "lr": 2.892829820715208e-06, "epoch": 5.909849749582638, "percentage": 84.43, "elapsed_time": "4:07:40", "remaining_time": "0:45:41"}
{"current_steps": 3545, "total_steps": 4193, "loss": 0.1568, "lr": 2.8498438344498103e-06, "epoch": 5.918196994991653, "percentage": 84.55, "elapsed_time": "4:07:59", "remaining_time": "0:45:19"}
{"current_steps": 3550, "total_steps": 4193, "loss": 0.1749, "lr": 2.8071551062144518e-06, "epoch": 5.926544240400668, "percentage": 84.66, "elapsed_time": "4:08:19", "remaining_time": "0:44:58"}
{"current_steps": 3555, "total_steps": 4193, "loss": 0.1592, "lr": 2.7647643759188557e-06, "epoch": 5.934891485809683, "percentage": 84.78, "elapsed_time": "4:08:38", "remaining_time": "0:44:37"}
{"current_steps": 3560, "total_steps": 4193, "loss": 0.1912, "lr": 2.7226723783076447e-06, "epoch": 5.943238731218698, "percentage": 84.9, "elapsed_time": "4:08:58", "remaining_time": "0:44:16"}
{"current_steps": 3565, "total_steps": 4193, "loss": 0.1628, "lr": 2.680879842947601e-06, "epoch": 5.951585976627713, "percentage": 85.02, "elapsed_time": "4:09:16", "remaining_time": "0:43:54"}
{"current_steps": 3570, "total_steps": 4193, "loss": 0.1544, "lr": 2.6393874942150268e-06, "epoch": 5.959933222036728, "percentage": 85.14, "elapsed_time": "4:09:44", "remaining_time": "0:43:34"}
{"current_steps": 3575, "total_steps": 4193, "loss": 0.1714, "lr": 2.598196051283193e-06, "epoch": 5.968280467445743, "percentage": 85.26, "elapsed_time": "4:10:04", "remaining_time": "0:43:13"}
{"current_steps": 3580, "total_steps": 4193, "loss": 0.1457, "lr": 2.5573062281098638e-06, "epoch": 5.976627712854758, "percentage": 85.38, "elapsed_time": "4:10:30", "remaining_time": "0:42:53"}
{"current_steps": 3585, "total_steps": 4193, "loss": 0.1465, "lr": 2.5167187334249277e-06, "epoch": 5.984974958263773, "percentage": 85.5, "elapsed_time": "4:10:51", "remaining_time": "0:42:32"}
{"current_steps": 3590, "total_steps": 4193, "loss": 0.1538, "lr": 2.4764342707181155e-06, "epoch": 5.993322203672788, "percentage": 85.62, "elapsed_time": "4:11:11", "remaining_time": "0:42:11"}
{"current_steps": 3595, "total_steps": 4193, "loss": 0.1598, "lr": 2.4364535382268017e-06, "epoch": 6.001669449081803, "percentage": 85.74, "elapsed_time": "4:11:28", "remaining_time": "0:41:49"}
{"current_steps": 3600, "total_steps": 4193, "loss": 0.1425, "lr": 2.3967772289239055e-06, "epoch": 6.010016694490818, "percentage": 85.86, "elapsed_time": "4:11:50", "remaining_time": "0:41:29"}
{"current_steps": 3605, "total_steps": 4193, "loss": 0.148, "lr": 2.357406030505878e-06, "epoch": 6.018363939899833, "percentage": 85.98, "elapsed_time": "4:12:12", "remaining_time": "0:41:08"}
{"current_steps": 3610, "total_steps": 4193, "loss": 0.1451, "lr": 2.318340625380786e-06, "epoch": 6.026711185308848, "percentage": 86.1, "elapsed_time": "4:12:28", "remaining_time": "0:40:46"}
{"current_steps": 3615, "total_steps": 4193, "loss": 0.1548, "lr": 2.279581690656476e-06, "epoch": 6.035058430717863, "percentage": 86.22, "elapsed_time": "4:12:42", "remaining_time": "0:40:24"}
{"current_steps": 3620, "total_steps": 4193, "loss": 0.1458, "lr": 2.241129898128851e-06, "epoch": 6.043405676126878, "percentage": 86.33, "elapsed_time": "4:13:01", "remaining_time": "0:40:03"}
{"current_steps": 3625, "total_steps": 4193, "loss": 0.159, "lr": 2.202985914270215e-06, "epoch": 6.051752921535893, "percentage": 86.45, "elapsed_time": "4:13:19", "remaining_time": "0:39:41"}
{"current_steps": 3630, "total_steps": 4193, "loss": 0.1615, "lr": 2.1651504002177236e-06, "epoch": 6.060100166944908, "percentage": 86.57, "elapsed_time": "4:13:36", "remaining_time": "0:39:20"}
{"current_steps": 3635, "total_steps": 4193, "loss": 0.1525, "lr": 2.1276240117619283e-06, "epoch": 6.068447412353923, "percentage": 86.69, "elapsed_time": "4:13:55", "remaining_time": "0:38:58"}
{"current_steps": 3640, "total_steps": 4193, "loss": 0.1574, "lr": 2.09040739933541e-06, "epoch": 6.076794657762938, "percentage": 86.81, "elapsed_time": "4:14:15", "remaining_time": "0:38:37"}
{"current_steps": 3645, "total_steps": 4193, "loss": 0.1455, "lr": 2.0535012080015006e-06, "epoch": 6.085141903171953, "percentage": 86.93, "elapsed_time": "4:14:37", "remaining_time": "0:38:16"}
{"current_steps": 3650, "total_steps": 4193, "loss": 0.1534, "lr": 2.016906077443106e-06, "epoch": 6.093489148580968, "percentage": 87.05, "elapsed_time": "4:15:03", "remaining_time": "0:37:56"}
{"current_steps": 3655, "total_steps": 4193, "loss": 0.1316, "lr": 1.9806226419516195e-06, "epoch": 6.101836393989983, "percentage": 87.17, "elapsed_time": "4:15:28", "remaining_time": "0:37:36"}
{"current_steps": 3660, "total_steps": 4193, "loss": 0.1767, "lr": 1.9446515304159198e-06, "epoch": 6.110183639398999, "percentage": 87.29, "elapsed_time": "4:15:54", "remaining_time": "0:37:16"}
{"current_steps": 3665, "total_steps": 4193, "loss": 0.1432, "lr": 1.9089933663114868e-06, "epoch": 6.118530884808013, "percentage": 87.41, "elapsed_time": "4:16:16", "remaining_time": "0:36:55"}
{"current_steps": 3670, "total_steps": 4193, "loss": 0.1445, "lr": 1.8736487676895754e-06, "epoch": 6.126878130217029, "percentage": 87.53, "elapsed_time": "4:16:33", "remaining_time": "0:36:33"}
{"current_steps": 3675, "total_steps": 4193, "loss": 0.1446, "lr": 1.8386183471665187e-06, "epoch": 6.135225375626043, "percentage": 87.65, "elapsed_time": "4:16:50", "remaining_time": "0:36:12"}
{"current_steps": 3680, "total_steps": 4193, "loss": 0.1646, "lr": 1.8039027119131057e-06, "epoch": 6.143572621035059, "percentage": 87.77, "elapsed_time": "4:17:16", "remaining_time": "0:35:51"}
{"current_steps": 3685, "total_steps": 4193, "loss": 0.1641, "lr": 1.7695024636440484e-06, "epoch": 6.151919866444073, "percentage": 87.88, "elapsed_time": "4:17:37", "remaining_time": "0:35:30"}
{"current_steps": 3690, "total_steps": 4193, "loss": 0.1628, "lr": 1.7354181986075635e-06, "epoch": 6.160267111853089, "percentage": 88.0, "elapsed_time": "4:18:00", "remaining_time": "0:35:10"}
{"current_steps": 3695, "total_steps": 4193, "loss": 0.1589, "lr": 1.701650507575039e-06, "epoch": 6.168614357262103, "percentage": 88.12, "elapsed_time": "4:18:23", "remaining_time": "0:34:49"}
{"current_steps": 3700, "total_steps": 4193, "loss": 0.1545, "lr": 1.6681999758307799e-06, "epoch": 6.176961602671119, "percentage": 88.24, "elapsed_time": "4:18:40", "remaining_time": "0:34:28"}
{"current_steps": 3705, "total_steps": 4193, "loss": 0.148, "lr": 1.6350671831618804e-06, "epoch": 6.185308848080133, "percentage": 88.36, "elapsed_time": "4:19:03", "remaining_time": "0:34:07"}
{"current_steps": 3710, "total_steps": 4193, "loss": 0.1575, "lr": 1.602252703848164e-06, "epoch": 6.193656093489149, "percentage": 88.48, "elapsed_time": "4:19:22", "remaining_time": "0:33:46"}
{"current_steps": 3715, "total_steps": 4193, "loss": 0.1421, "lr": 1.5697571066522321e-06, "epoch": 6.202003338898163, "percentage": 88.6, "elapsed_time": "4:19:39", "remaining_time": "0:33:24"}
{"current_steps": 3720, "total_steps": 4193, "loss": 0.1397, "lr": 1.5375809548096187e-06, "epoch": 6.210350584307179, "percentage": 88.72, "elapsed_time": "4:19:57", "remaining_time": "0:33:03"}
{"current_steps": 3725, "total_steps": 4193, "loss": 0.1525, "lr": 1.5057248060189956e-06, "epoch": 6.218697829716193, "percentage": 88.84, "elapsed_time": "4:20:18", "remaining_time": "0:32:42"}
{"current_steps": 3730, "total_steps": 4193, "loss": 0.1561, "lr": 1.4741892124325508e-06, "epoch": 6.227045075125209, "percentage": 88.96, "elapsed_time": "4:20:34", "remaining_time": "0:32:20"}
{"current_steps": 3735, "total_steps": 4193, "loss": 0.1634, "lr": 1.4429747206463662e-06, "epoch": 6.235392320534224, "percentage": 89.08, "elapsed_time": "4:20:51", "remaining_time": "0:31:59"}
{"current_steps": 3740, "total_steps": 4193, "loss": 0.1483, "lr": 1.4120818716910023e-06, "epoch": 6.243739565943239, "percentage": 89.2, "elapsed_time": "4:21:09", "remaining_time": "0:31:37"}
{"current_steps": 3745, "total_steps": 4193, "loss": 0.1434, "lr": 1.381511201022061e-06, "epoch": 6.252086811352254, "percentage": 89.32, "elapsed_time": "4:21:26", "remaining_time": "0:31:16"}
{"current_steps": 3750, "total_steps": 4193, "loss": 0.1462, "lr": 1.3512632385109582e-06, "epoch": 6.260434056761269, "percentage": 89.43, "elapsed_time": "4:21:53", "remaining_time": "0:30:56"}
{"current_steps": 3755, "total_steps": 4193, "loss": 0.1478, "lr": 1.3213385084356944e-06, "epoch": 6.268781302170284, "percentage": 89.55, "elapsed_time": "4:22:15", "remaining_time": "0:30:35"}
{"current_steps": 3760, "total_steps": 4193, "loss": 0.1529, "lr": 1.2917375294718083e-06, "epoch": 6.277128547579299, "percentage": 89.67, "elapsed_time": "4:22:38", "remaining_time": "0:30:14"}
{"current_steps": 3765, "total_steps": 4193, "loss": 0.1406, "lr": 1.262460814683344e-06, "epoch": 6.285475792988314, "percentage": 89.79, "elapsed_time": "4:22:50", "remaining_time": "0:29:52"}
{"current_steps": 3770, "total_steps": 4193, "loss": 0.1352, "lr": 1.2335088715140065e-06, "epoch": 6.293823038397329, "percentage": 89.91, "elapsed_time": "4:23:11", "remaining_time": "0:29:31"}
{"current_steps": 3775, "total_steps": 4193, "loss": 0.1676, "lr": 1.2048822017783168e-06, "epoch": 6.302170283806344, "percentage": 90.03, "elapsed_time": "4:23:31", "remaining_time": "0:29:10"}
{"current_steps": 3780, "total_steps": 4193, "loss": 0.1442, "lr": 1.1765813016529592e-06, "epoch": 6.310517529215359, "percentage": 90.15, "elapsed_time": "4:23:49", "remaining_time": "0:28:49"}
{"current_steps": 3785, "total_steps": 4193, "loss": 0.1448, "lr": 1.1486066616681413e-06, "epoch": 6.318864774624374, "percentage": 90.27, "elapsed_time": "4:24:14", "remaining_time": "0:28:29"}
{"current_steps": 3790, "total_steps": 4193, "loss": 0.1577, "lr": 1.1209587666991273e-06, "epoch": 6.3272120200333895, "percentage": 90.39, "elapsed_time": "4:24:36", "remaining_time": "0:28:08"}
{"current_steps": 3795, "total_steps": 4193, "loss": 0.1532, "lr": 1.093638095957803e-06, "epoch": 6.335559265442404, "percentage": 90.51, "elapsed_time": "4:24:56", "remaining_time": "0:27:47"}
{"current_steps": 3800, "total_steps": 4193, "loss": 0.1393, "lr": 1.0666451229844e-06, "epoch": 6.343906510851419, "percentage": 90.63, "elapsed_time": "4:25:17", "remaining_time": "0:27:26"}
{"current_steps": 3805, "total_steps": 4193, "loss": 0.1737, "lr": 1.0399803156392507e-06, "epoch": 6.352253756260434, "percentage": 90.75, "elapsed_time": "4:25:45", "remaining_time": "0:27:06"}
{"current_steps": 3810, "total_steps": 4193, "loss": 0.1485, "lr": 1.0136441360947247e-06, "epoch": 6.360601001669449, "percentage": 90.87, "elapsed_time": "4:26:04", "remaining_time": "0:26:44"}
{"current_steps": 3815, "total_steps": 4193, "loss": 0.149, "lr": 9.876370408271675e-07, "epoch": 6.368948247078464, "percentage": 90.98, "elapsed_time": "4:26:23", "remaining_time": "0:26:23"}
{"current_steps": 3820, "total_steps": 4193, "loss": 0.1432, "lr": 9.619594806090449e-07, "epoch": 6.377295492487479, "percentage": 91.1, "elapsed_time": "4:26:46", "remaining_time": "0:26:02"}
{"current_steps": 3825, "total_steps": 4193, "loss": 0.1533, "lr": 9.366119005010699e-07, "epoch": 6.385642737896494, "percentage": 91.22, "elapsed_time": "4:27:00", "remaining_time": "0:25:41"}
{"current_steps": 3830, "total_steps": 4193, "loss": 0.1566, "lr": 9.115947398445413e-07, "epoch": 6.393989983305509, "percentage": 91.34, "elapsed_time": "4:27:28", "remaining_time": "0:25:21"}
{"current_steps": 3835, "total_steps": 4193, "loss": 0.138, "lr": 8.869084322536881e-07, "epoch": 6.402337228714524, "percentage": 91.46, "elapsed_time": "4:27:55", "remaining_time": "0:25:00"}
{"current_steps": 3840, "total_steps": 4193, "loss": 0.1508, "lr": 8.62553405608193e-07, "epoch": 6.410684474123539, "percentage": 91.58, "elapsed_time": "4:28:15", "remaining_time": "0:24:39"}
{"current_steps": 3845, "total_steps": 4193, "loss": 0.1549, "lr": 8.385300820457276e-07, "epoch": 6.419031719532554, "percentage": 91.7, "elapsed_time": "4:28:35", "remaining_time": "0:24:18"}
{"current_steps": 3850, "total_steps": 4193, "loss": 0.1373, "lr": 8.148388779546912e-07, "epoch": 6.427378964941569, "percentage": 91.82, "elapsed_time": "4:28:52", "remaining_time": "0:23:57"}
{"current_steps": 3855, "total_steps": 4193, "loss": 0.1536, "lr": 7.914802039669412e-07, "epoch": 6.435726210350584, "percentage": 91.94, "elapsed_time": "4:29:13", "remaining_time": "0:23:36"}
{"current_steps": 3860, "total_steps": 4193, "loss": 0.1504, "lr": 7.684544649507164e-07, "epoch": 6.444073455759599, "percentage": 92.06, "elapsed_time": "4:29:33", "remaining_time": "0:23:15"}
{"current_steps": 3865, "total_steps": 4193, "loss": 0.1656, "lr": 7.457620600035898e-07, "epoch": 6.452420701168615, "percentage": 92.18, "elapsed_time": "4:29:49", "remaining_time": "0:22:53"}
{"current_steps": 3870, "total_steps": 4193, "loss": 0.1496, "lr": 7.234033824455821e-07, "epoch": 6.460767946577629, "percentage": 92.3, "elapsed_time": "4:30:20", "remaining_time": "0:22:33"}
{"current_steps": 3875, "total_steps": 4193, "loss": 0.1438, "lr": 7.01378819812304e-07, "epoch": 6.469115191986645, "percentage": 92.42, "elapsed_time": "4:30:41", "remaining_time": "0:22:12"}
{"current_steps": 3880, "total_steps": 4193, "loss": 0.138, "lr": 6.796887538482821e-07, "epoch": 6.477462437395659, "percentage": 92.54, "elapsed_time": "4:31:00", "remaining_time": "0:21:51"}
{"current_steps": 3885, "total_steps": 4193, "loss": 0.1415, "lr": 6.583335605003083e-07, "epoch": 6.485809682804675, "percentage": 92.65, "elapsed_time": "4:31:19", "remaining_time": "0:21:30"}
{"current_steps": 3890, "total_steps": 4193, "loss": 0.1438, "lr": 6.373136099109455e-07, "epoch": 6.494156928213689, "percentage": 92.77, "elapsed_time": "4:31:39", "remaining_time": "0:21:09"}
{"current_steps": 3895, "total_steps": 4193, "loss": 0.1482, "lr": 6.166292664120987e-07, "epoch": 6.502504173622705, "percentage": 92.89, "elapsed_time": "4:31:58", "remaining_time": "0:20:48"}
{"current_steps": 3900, "total_steps": 4193, "loss": 0.1524, "lr": 5.962808885187121e-07, "epoch": 6.510851419031719, "percentage": 93.01, "elapsed_time": "4:32:24", "remaining_time": "0:20:27"}
{"current_steps": 3905, "total_steps": 4193, "loss": 0.1383, "lr": 5.762688289225349e-07, "epoch": 6.519198664440735, "percentage": 93.13, "elapsed_time": "4:32:48", "remaining_time": "0:20:07"}
{"current_steps": 3910, "total_steps": 4193, "loss": 0.1545, "lr": 5.565934344860413e-07, "epoch": 6.527545909849749, "percentage": 93.25, "elapsed_time": "4:33:06", "remaining_time": "0:19:46"}
{"current_steps": 3915, "total_steps": 4193, "loss": 0.1451, "lr": 5.372550462363779e-07, "epoch": 6.535893155258765, "percentage": 93.37, "elapsed_time": "4:33:30", "remaining_time": "0:19:25"}
{"current_steps": 3920, "total_steps": 4193, "loss": 0.1569, "lr": 5.182539993594904e-07, "epoch": 6.54424040066778, "percentage": 93.49, "elapsed_time": "4:33:52", "remaining_time": "0:19:04"}
{"current_steps": 3925, "total_steps": 4193, "loss": 0.1643, "lr": 4.99590623194286e-07, "epoch": 6.552587646076795, "percentage": 93.61, "elapsed_time": "4:34:15", "remaining_time": "0:18:43"}
{"current_steps": 3930, "total_steps": 4193, "loss": 0.1561, "lr": 4.812652412269448e-07, "epoch": 6.560934891485809, "percentage": 93.73, "elapsed_time": "4:34:33", "remaining_time": "0:18:22"}
{"current_steps": 3935, "total_steps": 4193, "loss": 0.1607, "lr": 4.632781710852929e-07, "epoch": 6.569282136894825, "percentage": 93.85, "elapsed_time": "4:35:00", "remaining_time": "0:18:01"}
{"current_steps": 3940, "total_steps": 4193, "loss": 0.1488, "lr": 4.456297245333252e-07, "epoch": 6.57762938230384, "percentage": 93.97, "elapsed_time": "4:35:20", "remaining_time": "0:17:40"}
{"current_steps": 3945, "total_steps": 4193, "loss": 0.1515, "lr": 4.2832020746576666e-07, "epoch": 6.585976627712855, "percentage": 94.09, "elapsed_time": "4:35:40", "remaining_time": "0:17:19"}
{"current_steps": 3950, "total_steps": 4193, "loss": 0.1445, "lr": 4.113499199028037e-07, "epoch": 6.59432387312187, "percentage": 94.2, "elapsed_time": "4:35:58", "remaining_time": "0:16:58"}
{"current_steps": 3955, "total_steps": 4193, "loss": 0.1404, "lr": 3.9471915598485954e-07, "epoch": 6.602671118530885, "percentage": 94.32, "elapsed_time": "4:36:17", "remaining_time": "0:16:37"}
{"current_steps": 3960, "total_steps": 4193, "loss": 0.1498, "lr": 3.7842820396751134e-07, "epoch": 6.6110183639399, "percentage": 94.44, "elapsed_time": "4:36:34", "remaining_time": "0:16:16"}
{"current_steps": 3965, "total_steps": 4193, "loss": 0.1477, "lr": 3.62477346216481e-07, "epoch": 6.619365609348915, "percentage": 94.56, "elapsed_time": "4:36:52", "remaining_time": "0:15:55"}
{"current_steps": 3970, "total_steps": 4193, "loss": 0.1426, "lr": 3.468668592027613e-07, "epoch": 6.62771285475793, "percentage": 94.68, "elapsed_time": "4:37:10", "remaining_time": "0:15:34"}
{"current_steps": 3975, "total_steps": 4193, "loss": 0.1441, "lr": 3.3159701349779083e-07, "epoch": 6.636060100166945, "percentage": 94.8, "elapsed_time": "4:37:29", "remaining_time": "0:15:13"}
{"current_steps": 3980, "total_steps": 4193, "loss": 0.1527, "lr": 3.1666807376880436e-07, "epoch": 6.64440734557596, "percentage": 94.92, "elapsed_time": "4:37:52", "remaining_time": "0:14:52"}
{"current_steps": 3985, "total_steps": 4193, "loss": 0.1481, "lr": 3.0208029877420996e-07, "epoch": 6.652754590984975, "percentage": 95.04, "elapsed_time": "4:38:13", "remaining_time": "0:14:31"}
{"current_steps": 3990, "total_steps": 4193, "loss": 0.1576, "lr": 2.8783394135913245e-07, "epoch": 6.66110183639399, "percentage": 95.16, "elapsed_time": "4:38:28", "remaining_time": "0:14:10"}
{"current_steps": 3995, "total_steps": 4193, "loss": 0.1528, "lr": 2.7392924845100364e-07, "epoch": 6.669449081803005, "percentage": 95.28, "elapsed_time": "4:38:48", "remaining_time": "0:13:49"}
{"current_steps": 4000, "total_steps": 4193, "loss": 0.1481, "lr": 2.6036646105530804e-07, "epoch": 6.67779632721202, "percentage": 95.4, "elapsed_time": "4:39:07", "remaining_time": "0:13:28"}
{"current_steps": 4005, "total_steps": 4193, "loss": 0.1356, "lr": 2.471458142513861e-07, "epoch": 6.686143572621035, "percentage": 95.52, "elapsed_time": "4:39:27", "remaining_time": "0:13:07"}
{"current_steps": 4010, "total_steps": 4193, "loss": 0.1497, "lr": 2.3426753718837735e-07, "epoch": 6.69449081803005, "percentage": 95.64, "elapsed_time": "4:39:46", "remaining_time": "0:12:46"}
{"current_steps": 4015, "total_steps": 4193, "loss": 0.1683, "lr": 2.2173185308122624e-07, "epoch": 6.702838063439065, "percentage": 95.75, "elapsed_time": "4:40:01", "remaining_time": "0:12:24"}
{"current_steps": 4020, "total_steps": 4193, "loss": 0.1753, "lr": 2.0953897920683807e-07, "epoch": 6.71118530884808, "percentage": 95.87, "elapsed_time": "4:40:29", "remaining_time": "0:12:04"}
{"current_steps": 4025, "total_steps": 4193, "loss": 0.1337, "lr": 1.976891269002934e-07, "epoch": 6.719532554257095, "percentage": 95.99, "elapsed_time": "4:40:52", "remaining_time": "0:11:43"}
{"current_steps": 4030, "total_steps": 4193, "loss": 0.1534, "lr": 1.861825015511931e-07, "epoch": 6.72787979966611, "percentage": 96.11, "elapsed_time": "4:41:11", "remaining_time": "0:11:22"}
{"current_steps": 4035, "total_steps": 4193, "loss": 0.1676, "lr": 1.7501930260009902e-07, "epoch": 6.736227045075125, "percentage": 96.23, "elapsed_time": "4:41:31", "remaining_time": "0:11:01"}
{"current_steps": 4040, "total_steps": 4193, "loss": 0.1543, "lr": 1.6419972353507895e-07, "epoch": 6.74457429048414, "percentage": 96.35, "elapsed_time": "4:41:45", "remaining_time": "0:10:40"}
{"current_steps": 4045, "total_steps": 4193, "loss": 0.1474, "lr": 1.5372395188834265e-07, "epoch": 6.752921535893155, "percentage": 96.47, "elapsed_time": "4:42:04", "remaining_time": "0:10:19"}
{"current_steps": 4050, "total_steps": 4193, "loss": 0.1542, "lr": 1.435921692330089e-07, "epoch": 6.76126878130217, "percentage": 96.59, "elapsed_time": "4:42:22", "remaining_time": "0:09:58"}
{"current_steps": 4055, "total_steps": 4193, "loss": 0.1479, "lr": 1.3380455117993684e-07, "epoch": 6.769616026711185, "percentage": 96.71, "elapsed_time": "4:42:46", "remaining_time": "0:09:37"}
{"current_steps": 4060, "total_steps": 4193, "loss": 0.1479, "lr": 1.2436126737470189e-07, "epoch": 6.7779632721202, "percentage": 96.83, "elapsed_time": "4:43:09", "remaining_time": "0:09:16"}
{"current_steps": 4065, "total_steps": 4193, "loss": 0.1421, "lr": 1.1526248149464236e-07, "epoch": 6.786310517529215, "percentage": 96.95, "elapsed_time": "4:43:26", "remaining_time": "0:08:55"}
{"current_steps": 4070, "total_steps": 4193, "loss": 0.1513, "lr": 1.0650835124603076e-07, "epoch": 6.794657762938231, "percentage": 97.07, "elapsed_time": "4:43:50", "remaining_time": "0:08:34"}
{"current_steps": 4075, "total_steps": 4193, "loss": 0.1616, "lr": 9.809902836133367e-08, "epoch": 6.803005008347245, "percentage": 97.19, "elapsed_time": "4:44:11", "remaining_time": "0:08:13"}
{"current_steps": 4080, "total_steps": 4193, "loss": 0.1544, "lr": 9.0034658596585e-08, "epoch": 6.811352253756261, "percentage": 97.31, "elapsed_time": "4:44:28", "remaining_time": "0:07:52"}
{"current_steps": 4085, "total_steps": 4193, "loss": 0.1379, "lr": 8.231538172886133e-08, "epoch": 6.819699499165275, "percentage": 97.42, "elapsed_time": "4:44:47", "remaining_time": "0:07:31"}
{"current_steps": 4090, "total_steps": 4193, "loss": 0.1513, "lr": 7.494133155385497e-08, "epoch": 6.828046744574291, "percentage": 97.54, "elapsed_time": "4:45:04", "remaining_time": "0:07:10"}
{"current_steps": 4095, "total_steps": 4193, "loss": 0.148, "lr": 6.791263588355801e-08, "epoch": 6.836393989983305, "percentage": 97.66, "elapsed_time": "4:45:23", "remaining_time": "0:06:49"}
{"current_steps": 4100, "total_steps": 4193, "loss": 0.147, "lr": 6.122941654404635e-08, "epoch": 6.844741235392321, "percentage": 97.78, "elapsed_time": "4:45:44", "remaining_time": "0:06:28"}
{"current_steps": 4105, "total_steps": 4193, "loss": 0.1598, "lr": 5.489178937337025e-08, "epoch": 6.853088480801335, "percentage": 97.9, "elapsed_time": "4:46:09", "remaining_time": "0:06:08"}
{"current_steps": 4110, "total_steps": 4193, "loss": 0.1493, "lr": 4.88998642195404e-08, "epoch": 6.861435726210351, "percentage": 98.02, "elapsed_time": "4:46:37", "remaining_time": "0:05:47"}
{"current_steps": 4115, "total_steps": 4193, "loss": 0.1454, "lr": 4.325374493862944e-08, "epoch": 6.869782971619365, "percentage": 98.14, "elapsed_time": "4:46:51", "remaining_time": "0:05:26"}
{"current_steps": 4120, "total_steps": 4193, "loss": 0.1431, "lr": 3.795352939296892e-08, "epoch": 6.878130217028381, "percentage": 98.26, "elapsed_time": "4:47:13", "remaining_time": "0:05:05"}
{"current_steps": 4125, "total_steps": 4193, "loss": 0.1593, "lr": 3.2999309449459616e-08, "epoch": 6.886477462437396, "percentage": 98.38, "elapsed_time": "4:47:42", "remaining_time": "0:04:44"}
{"current_steps": 4130, "total_steps": 4193, "loss": 0.1398, "lr": 2.8391170977968287e-08, "epoch": 6.894824707846411, "percentage": 98.5, "elapsed_time": "4:48:02", "remaining_time": "0:04:23"}
{"current_steps": 4135, "total_steps": 4193, "loss": 0.1447, "lr": 2.4129193849848907e-08, "epoch": 6.903171953255426, "percentage": 98.62, "elapsed_time": "4:48:24", "remaining_time": "0:04:02"}
{"current_steps": 4140, "total_steps": 4193, "loss": 0.1373, "lr": 2.0213451936550445e-08, "epoch": 6.911519198664441, "percentage": 98.74, "elapsed_time": "4:48:42", "remaining_time": "0:03:41"}
{"current_steps": 4145, "total_steps": 4193, "loss": 0.1495, "lr": 1.6644013108342294e-08, "epoch": 6.919866444073456, "percentage": 98.86, "elapsed_time": "4:49:08", "remaining_time": "0:03:20"}
{"current_steps": 4150, "total_steps": 4193, "loss": 0.1498, "lr": 1.3420939233139696e-08, "epoch": 6.928213689482471, "percentage": 98.97, "elapsed_time": "4:49:25", "remaining_time": "0:02:59"}
{"current_steps": 4155, "total_steps": 4193, "loss": 0.1615, "lr": 1.0544286175422358e-08, "epoch": 6.936560934891486, "percentage": 99.09, "elapsed_time": "4:49:43", "remaining_time": "0:02:38"}
{"current_steps": 4160, "total_steps": 4193, "loss": 0.153, "lr": 8.01410379527301e-09, "epoch": 6.944908180300501, "percentage": 99.21, "elapsed_time": "4:49:58", "remaining_time": "0:02:18"}
{"current_steps": 4165, "total_steps": 4193, "loss": 0.164, "lr": 5.8304359475158665e-09, "epoch": 6.953255425709516, "percentage": 99.33, "elapsed_time": "4:50:22", "remaining_time": "0:01:57"}
{"current_steps": 4170, "total_steps": 4193, "loss": 0.1359, "lr": 3.993320480946139e-09, "epoch": 6.961602671118531, "percentage": 99.45, "elapsed_time": "4:50:46", "remaining_time": "0:01:36"}
{"current_steps": 4175, "total_steps": 4193, "loss": 0.1572, "lr": 2.5027892376860984e-09, "epoch": 6.969949916527546, "percentage": 99.57, "elapsed_time": "4:51:03", "remaining_time": "0:01:15"}
{"current_steps": 4180, "total_steps": 4193, "loss": 0.1533, "lr": 1.3588680526255282e-09, "epoch": 6.978297161936561, "percentage": 99.69, "elapsed_time": "4:51:23", "remaining_time": "0:00:54"}
{"current_steps": 4185, "total_steps": 4193, "loss": 0.1409, "lr": 5.615767529709715e-10, "epoch": 6.986644407345576, "percentage": 99.81, "elapsed_time": "4:51:42", "remaining_time": "0:00:33"}
{"current_steps": 4190, "total_steps": 4193, "loss": 0.1658, "lr": 1.1092915791266479e-10, "epoch": 6.994991652754591, "percentage": 99.93, "elapsed_time": "4:52:02", "remaining_time": "0:00:12"}
{"current_steps": 4193, "total_steps": 4193, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "4:52:21", "remaining_time": "0:00:00"}

9265
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:b21415033e2b9e89b0908ea49d440243eba32cb73ba7ee7e4ad4a74aaf885a4f
size 8593

BIN
training_loss.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 43 KiB

1
vocab.json Normal file

File diff suppressed because one or more lines are too long