初始化项目,由ModelHub XC社区提供模型

Model: DCAgent/b1_top32
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-08 00:58:17 +08:00
commit affad8f16a
20 changed files with 153173 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_b1_top32__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_b1_top32__Qwen3-8B
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /scratch/08134/negin/hub/datasets--DCAgent--b1_top32/snapshots/672f249bde596b1bd0c44d2ba49e33deda128ebd 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 4.57.3
- Pytorch 2.9.0+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1

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": 0.003474978304056853,
"achieved_tflops_per_gpu_theoretical": 535.2889209260605,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.19787049293518066,
"mfu_percent": 0.0002455815055870568,
"mfu_percent_theoretical": 37.82960571915622,
"total_flos": 1348271671738368.0,
"train_loss": 0.27422133954395106,
"train_runtime": 24249.6419,
"train_samples_per_second": 2.525,
"train_steps_per_second": 0.158,
"valid_targets_mean": 4679.4,
"valid_targets_min": 1998
}

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": "4.57.3",
"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": "4.57.3"
}

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 sha256:3c645898cc7c45c2d1a776fe5b2516b47ca022db085dc3cd299ee41a11470a01
size 4902257696

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a9ecbbb8c0925e61923200a55891a61aca6bf06d1985dace9697cd7413e1c663
size 4915960368

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:43265f2147c730b72e14c230b19d194976098788828116b9e69d9ba20eb8226e
size 4983068496

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3986d7045bd3411ea9a8b19c6603b3dc3760c6aa612bfc114242eea8ca27dc55
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"
}
}

31
special_tokens_map.json Normal file
View File

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

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

Binary file not shown.

240
tokenizer_config.json Normal file
View File

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

16
train_results.json Normal file
View File

@@ -0,0 +1,16 @@
{
"achieved_tflops_per_gpu": 0.003474978304056853,
"achieved_tflops_per_gpu_theoretical": 535.2889209260605,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.19787049293518066,
"mfu_percent": 0.0002455815055870568,
"mfu_percent_theoretical": 37.82960571915622,
"total_flos": 1348271671738368.0,
"train_loss": 0.27422133954395106,
"train_runtime": 24249.6419,
"train_samples_per_second": 2.525,
"train_steps_per_second": 0.158,
"valid_targets_mean": 4679.4,
"valid_targets_min": 1998
}

766
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,766 @@
{"current_steps": 5, "total_steps": 3829, "loss": 0.7861, "lr": 4.1775456919060057e-07, "epoch": 0.009140767824497258, "percentage": 0.13, "elapsed_time": "0:00:45", "remaining_time": "9:33:46"}
{"current_steps": 10, "total_steps": 3829, "loss": 0.7398, "lr": 9.399477806788513e-07, "epoch": 0.018281535648994516, "percentage": 0.26, "elapsed_time": "0:01:15", "remaining_time": "8:00:36"}
{"current_steps": 15, "total_steps": 3829, "loss": 0.7225, "lr": 1.462140992167102e-06, "epoch": 0.027422303473491772, "percentage": 0.39, "elapsed_time": "0:01:52", "remaining_time": "7:57:19"}
{"current_steps": 20, "total_steps": 3829, "loss": 0.7583, "lr": 1.9843342036553527e-06, "epoch": 0.03656307129798903, "percentage": 0.52, "elapsed_time": "0:02:21", "remaining_time": "7:27:54"}
{"current_steps": 25, "total_steps": 3829, "loss": 0.6645, "lr": 2.506527415143603e-06, "epoch": 0.04570383912248629, "percentage": 0.65, "elapsed_time": "0:02:49", "remaining_time": "7:10:50"}
{"current_steps": 30, "total_steps": 3829, "loss": 0.7116, "lr": 3.0287206266318544e-06, "epoch": 0.054844606946983544, "percentage": 0.78, "elapsed_time": "0:03:20", "remaining_time": "7:02:17"}
{"current_steps": 35, "total_steps": 3829, "loss": 0.6084, "lr": 3.550913838120105e-06, "epoch": 0.06398537477148081, "percentage": 0.91, "elapsed_time": "0:03:53", "remaining_time": "7:01:28"}
{"current_steps": 40, "total_steps": 3829, "loss": 0.5772, "lr": 4.073107049608356e-06, "epoch": 0.07312614259597806, "percentage": 1.04, "elapsed_time": "0:04:26", "remaining_time": "7:01:13"}
{"current_steps": 45, "total_steps": 3829, "loss": 0.536, "lr": 4.5953002610966065e-06, "epoch": 0.08226691042047532, "percentage": 1.18, "elapsed_time": "0:04:52", "remaining_time": "6:50:28"}
{"current_steps": 50, "total_steps": 3829, "loss": 0.589, "lr": 5.1174934725848565e-06, "epoch": 0.09140767824497258, "percentage": 1.31, "elapsed_time": "0:05:23", "remaining_time": "6:47:54"}
{"current_steps": 55, "total_steps": 3829, "loss": 0.5383, "lr": 5.639686684073108e-06, "epoch": 0.10054844606946983, "percentage": 1.44, "elapsed_time": "0:05:54", "remaining_time": "6:45:54"}
{"current_steps": 60, "total_steps": 3829, "loss": 0.5153, "lr": 6.161879895561358e-06, "epoch": 0.10968921389396709, "percentage": 1.57, "elapsed_time": "0:06:23", "remaining_time": "6:41:11"}
{"current_steps": 65, "total_steps": 3829, "loss": 0.5182, "lr": 6.684073107049609e-06, "epoch": 0.11882998171846434, "percentage": 1.7, "elapsed_time": "0:06:59", "remaining_time": "6:44:27"}
{"current_steps": 70, "total_steps": 3829, "loss": 0.5091, "lr": 7.20626631853786e-06, "epoch": 0.12797074954296161, "percentage": 1.83, "elapsed_time": "0:07:25", "remaining_time": "6:38:58"}
{"current_steps": 75, "total_steps": 3829, "loss": 0.4447, "lr": 7.72845953002611e-06, "epoch": 0.13711151736745886, "percentage": 1.96, "elapsed_time": "0:07:52", "remaining_time": "6:34:18"}
{"current_steps": 80, "total_steps": 3829, "loss": 0.4844, "lr": 8.25065274151436e-06, "epoch": 0.14625228519195613, "percentage": 2.09, "elapsed_time": "0:08:29", "remaining_time": "6:38:02"}
{"current_steps": 85, "total_steps": 3829, "loss": 0.4375, "lr": 8.772845953002612e-06, "epoch": 0.15539305301645337, "percentage": 2.22, "elapsed_time": "0:08:59", "remaining_time": "6:35:46"}
{"current_steps": 90, "total_steps": 3829, "loss": 0.4088, "lr": 9.295039164490863e-06, "epoch": 0.16453382084095064, "percentage": 2.35, "elapsed_time": "0:09:31", "remaining_time": "6:35:27"}
{"current_steps": 95, "total_steps": 3829, "loss": 0.4275, "lr": 9.817232375979113e-06, "epoch": 0.1736745886654479, "percentage": 2.48, "elapsed_time": "0:10:04", "remaining_time": "6:35:56"}
{"current_steps": 100, "total_steps": 3829, "loss": 0.4132, "lr": 1.0339425587467364e-05, "epoch": 0.18281535648994515, "percentage": 2.61, "elapsed_time": "0:10:34", "remaining_time": "6:34:02"}
{"current_steps": 105, "total_steps": 3829, "loss": 0.4388, "lr": 1.0861618798955615e-05, "epoch": 0.19195612431444242, "percentage": 2.74, "elapsed_time": "0:11:04", "remaining_time": "6:32:34"}
{"current_steps": 110, "total_steps": 3829, "loss": 0.4143, "lr": 1.1383812010443864e-05, "epoch": 0.20109689213893966, "percentage": 2.87, "elapsed_time": "0:11:35", "remaining_time": "6:32:10"}
{"current_steps": 115, "total_steps": 3829, "loss": 0.4438, "lr": 1.1906005221932115e-05, "epoch": 0.21023765996343693, "percentage": 3.0, "elapsed_time": "0:12:02", "remaining_time": "6:28:48"}
{"current_steps": 120, "total_steps": 3829, "loss": 0.4722, "lr": 1.2428198433420366e-05, "epoch": 0.21937842778793418, "percentage": 3.13, "elapsed_time": "0:12:36", "remaining_time": "6:29:35"}
{"current_steps": 125, "total_steps": 3829, "loss": 0.4012, "lr": 1.2950391644908617e-05, "epoch": 0.22851919561243145, "percentage": 3.26, "elapsed_time": "0:13:04", "remaining_time": "6:27:18"}
{"current_steps": 130, "total_steps": 3829, "loss": 0.4081, "lr": 1.347258485639687e-05, "epoch": 0.2376599634369287, "percentage": 3.4, "elapsed_time": "0:13:32", "remaining_time": "6:25:27"}
{"current_steps": 135, "total_steps": 3829, "loss": 0.4355, "lr": 1.399477806788512e-05, "epoch": 0.24680073126142596, "percentage": 3.53, "elapsed_time": "0:14:05", "remaining_time": "6:25:24"}
{"current_steps": 140, "total_steps": 3829, "loss": 0.427, "lr": 1.451697127937337e-05, "epoch": 0.25594149908592323, "percentage": 3.66, "elapsed_time": "0:14:36", "remaining_time": "6:24:45"}
{"current_steps": 145, "total_steps": 3829, "loss": 0.4014, "lr": 1.503916449086162e-05, "epoch": 0.26508226691042047, "percentage": 3.79, "elapsed_time": "0:15:11", "remaining_time": "6:25:52"}
{"current_steps": 150, "total_steps": 3829, "loss": 0.3968, "lr": 1.556135770234987e-05, "epoch": 0.2742230347349177, "percentage": 3.92, "elapsed_time": "0:15:43", "remaining_time": "6:25:30"}
{"current_steps": 155, "total_steps": 3829, "loss": 0.3951, "lr": 1.608355091383812e-05, "epoch": 0.283363802559415, "percentage": 4.05, "elapsed_time": "0:16:14", "remaining_time": "6:25:03"}
{"current_steps": 160, "total_steps": 3829, "loss": 0.3738, "lr": 1.6605744125326374e-05, "epoch": 0.29250457038391225, "percentage": 4.18, "elapsed_time": "0:16:43", "remaining_time": "6:23:35"}
{"current_steps": 165, "total_steps": 3829, "loss": 0.3703, "lr": 1.7127937336814622e-05, "epoch": 0.3016453382084095, "percentage": 4.31, "elapsed_time": "0:17:13", "remaining_time": "6:22:30"}
{"current_steps": 170, "total_steps": 3829, "loss": 0.4089, "lr": 1.7650130548302873e-05, "epoch": 0.31078610603290674, "percentage": 4.44, "elapsed_time": "0:17:41", "remaining_time": "6:20:56"}
{"current_steps": 175, "total_steps": 3829, "loss": 0.3787, "lr": 1.8172323759791124e-05, "epoch": 0.31992687385740404, "percentage": 4.57, "elapsed_time": "0:18:16", "remaining_time": "6:21:24"}
{"current_steps": 180, "total_steps": 3829, "loss": 0.4023, "lr": 1.8694516971279374e-05, "epoch": 0.3290676416819013, "percentage": 4.7, "elapsed_time": "0:18:48", "remaining_time": "6:21:19"}
{"current_steps": 185, "total_steps": 3829, "loss": 0.3848, "lr": 1.9216710182767625e-05, "epoch": 0.3382084095063985, "percentage": 4.83, "elapsed_time": "0:19:19", "remaining_time": "6:20:41"}
{"current_steps": 190, "total_steps": 3829, "loss": 0.3813, "lr": 1.9738903394255876e-05, "epoch": 0.3473491773308958, "percentage": 4.96, "elapsed_time": "0:19:48", "remaining_time": "6:19:25"}
{"current_steps": 195, "total_steps": 3829, "loss": 0.4099, "lr": 2.0261096605744127e-05, "epoch": 0.35648994515539306, "percentage": 5.09, "elapsed_time": "0:20:18", "remaining_time": "6:18:34"}
{"current_steps": 200, "total_steps": 3829, "loss": 0.3799, "lr": 2.0783289817232378e-05, "epoch": 0.3656307129798903, "percentage": 5.22, "elapsed_time": "0:20:48", "remaining_time": "6:17:33"}
{"current_steps": 205, "total_steps": 3829, "loss": 0.3477, "lr": 2.130548302872063e-05, "epoch": 0.37477148080438755, "percentage": 5.35, "elapsed_time": "0:21:20", "remaining_time": "6:17:15"}
{"current_steps": 210, "total_steps": 3829, "loss": 0.3457, "lr": 2.1827676240208876e-05, "epoch": 0.38391224862888484, "percentage": 5.48, "elapsed_time": "0:21:48", "remaining_time": "6:15:54"}
{"current_steps": 215, "total_steps": 3829, "loss": 0.4134, "lr": 2.234986945169713e-05, "epoch": 0.3930530164533821, "percentage": 5.62, "elapsed_time": "0:22:21", "remaining_time": "6:15:49"}
{"current_steps": 220, "total_steps": 3829, "loss": 0.3416, "lr": 2.2872062663185378e-05, "epoch": 0.40219378427787933, "percentage": 5.75, "elapsed_time": "0:22:51", "remaining_time": "6:14:52"}
{"current_steps": 225, "total_steps": 3829, "loss": 0.3863, "lr": 2.3394255874673632e-05, "epoch": 0.4113345521023766, "percentage": 5.88, "elapsed_time": "0:23:20", "remaining_time": "6:13:47"}
{"current_steps": 230, "total_steps": 3829, "loss": 0.3504, "lr": 2.3916449086161883e-05, "epoch": 0.42047531992687387, "percentage": 6.01, "elapsed_time": "0:23:57", "remaining_time": "6:14:59"}
{"current_steps": 235, "total_steps": 3829, "loss": 0.3868, "lr": 2.4438642297650134e-05, "epoch": 0.4296160877513711, "percentage": 6.14, "elapsed_time": "0:24:32", "remaining_time": "6:15:16"}
{"current_steps": 240, "total_steps": 3829, "loss": 0.358, "lr": 2.4960835509138385e-05, "epoch": 0.43875685557586835, "percentage": 6.27, "elapsed_time": "0:25:08", "remaining_time": "6:15:51"}
{"current_steps": 245, "total_steps": 3829, "loss": 0.3916, "lr": 2.5483028720626632e-05, "epoch": 0.44789762340036565, "percentage": 6.4, "elapsed_time": "0:25:44", "remaining_time": "6:16:28"}
{"current_steps": 250, "total_steps": 3829, "loss": 0.3777, "lr": 2.6005221932114886e-05, "epoch": 0.4570383912248629, "percentage": 6.53, "elapsed_time": "0:26:14", "remaining_time": "6:15:42"}
{"current_steps": 255, "total_steps": 3829, "loss": 0.4024, "lr": 2.6527415143603134e-05, "epoch": 0.46617915904936014, "percentage": 6.66, "elapsed_time": "0:26:47", "remaining_time": "6:15:23"}
{"current_steps": 260, "total_steps": 3829, "loss": 0.3776, "lr": 2.7049608355091388e-05, "epoch": 0.4753199268738574, "percentage": 6.79, "elapsed_time": "0:27:21", "remaining_time": "6:15:32"}
{"current_steps": 265, "total_steps": 3829, "loss": 0.3556, "lr": 2.7571801566579636e-05, "epoch": 0.4844606946983547, "percentage": 6.92, "elapsed_time": "0:27:52", "remaining_time": "6:14:59"}
{"current_steps": 270, "total_steps": 3829, "loss": 0.3461, "lr": 2.8093994778067886e-05, "epoch": 0.4936014625228519, "percentage": 7.05, "elapsed_time": "0:28:29", "remaining_time": "6:15:28"}
{"current_steps": 275, "total_steps": 3829, "loss": 0.3723, "lr": 2.8616187989556137e-05, "epoch": 0.5027422303473492, "percentage": 7.18, "elapsed_time": "0:29:00", "remaining_time": "6:14:49"}
{"current_steps": 280, "total_steps": 3829, "loss": 0.3796, "lr": 2.9138381201044388e-05, "epoch": 0.5118829981718465, "percentage": 7.31, "elapsed_time": "0:29:30", "remaining_time": "6:13:58"}
{"current_steps": 285, "total_steps": 3829, "loss": 0.3895, "lr": 2.9660574412532642e-05, "epoch": 0.5210237659963437, "percentage": 7.44, "elapsed_time": "0:30:00", "remaining_time": "6:13:03"}
{"current_steps": 290, "total_steps": 3829, "loss": 0.3693, "lr": 3.018276762402089e-05, "epoch": 0.5301645338208409, "percentage": 7.57, "elapsed_time": "0:30:34", "remaining_time": "6:13:03"}
{"current_steps": 295, "total_steps": 3829, "loss": 0.3712, "lr": 3.070496083550914e-05, "epoch": 0.5393053016453382, "percentage": 7.7, "elapsed_time": "0:31:04", "remaining_time": "6:12:12"}
{"current_steps": 300, "total_steps": 3829, "loss": 0.3916, "lr": 3.122715404699739e-05, "epoch": 0.5484460694698354, "percentage": 7.83, "elapsed_time": "0:31:36", "remaining_time": "6:11:43"}
{"current_steps": 305, "total_steps": 3829, "loss": 0.3367, "lr": 3.174934725848564e-05, "epoch": 0.5575868372943327, "percentage": 7.97, "elapsed_time": "0:32:05", "remaining_time": "6:10:48"}
{"current_steps": 310, "total_steps": 3829, "loss": 0.3823, "lr": 3.227154046997389e-05, "epoch": 0.56672760511883, "percentage": 8.1, "elapsed_time": "0:32:41", "remaining_time": "6:11:06"}
{"current_steps": 315, "total_steps": 3829, "loss": 0.3583, "lr": 3.2793733681462144e-05, "epoch": 0.5758683729433273, "percentage": 8.23, "elapsed_time": "0:33:14", "remaining_time": "6:10:45"}
{"current_steps": 320, "total_steps": 3829, "loss": 0.356, "lr": 3.3315926892950395e-05, "epoch": 0.5850091407678245, "percentage": 8.36, "elapsed_time": "0:33:52", "remaining_time": "6:11:28"}
{"current_steps": 325, "total_steps": 3829, "loss": 0.3571, "lr": 3.3838120104438646e-05, "epoch": 0.5941499085923218, "percentage": 8.49, "elapsed_time": "0:34:24", "remaining_time": "6:11:02"}
{"current_steps": 330, "total_steps": 3829, "loss": 0.3714, "lr": 3.43603133159269e-05, "epoch": 0.603290676416819, "percentage": 8.62, "elapsed_time": "0:34:57", "remaining_time": "6:10:37"}
{"current_steps": 335, "total_steps": 3829, "loss": 0.3816, "lr": 3.488250652741515e-05, "epoch": 0.6124314442413162, "percentage": 8.75, "elapsed_time": "0:35:29", "remaining_time": "6:10:13"}
{"current_steps": 340, "total_steps": 3829, "loss": 0.3448, "lr": 3.54046997389034e-05, "epoch": 0.6215722120658135, "percentage": 8.88, "elapsed_time": "0:36:03", "remaining_time": "6:09:59"}
{"current_steps": 345, "total_steps": 3829, "loss": 0.3841, "lr": 3.592689295039165e-05, "epoch": 0.6307129798903108, "percentage": 9.01, "elapsed_time": "0:36:29", "remaining_time": "6:08:33"}
{"current_steps": 350, "total_steps": 3829, "loss": 0.3397, "lr": 3.64490861618799e-05, "epoch": 0.6398537477148081, "percentage": 9.14, "elapsed_time": "0:36:55", "remaining_time": "6:07:05"}
{"current_steps": 355, "total_steps": 3829, "loss": 0.3381, "lr": 3.6971279373368144e-05, "epoch": 0.6489945155393053, "percentage": 9.27, "elapsed_time": "0:37:22", "remaining_time": "6:05:46"}
{"current_steps": 360, "total_steps": 3829, "loss": 0.3814, "lr": 3.74934725848564e-05, "epoch": 0.6581352833638026, "percentage": 9.4, "elapsed_time": "0:37:49", "remaining_time": "6:04:33"}
{"current_steps": 365, "total_steps": 3829, "loss": 0.3765, "lr": 3.801566579634465e-05, "epoch": 0.6672760511882998, "percentage": 9.53, "elapsed_time": "0:38:24", "remaining_time": "6:04:28"}
{"current_steps": 370, "total_steps": 3829, "loss": 0.3401, "lr": 3.8537859007832904e-05, "epoch": 0.676416819012797, "percentage": 9.66, "elapsed_time": "0:38:55", "remaining_time": "6:03:53"}
{"current_steps": 375, "total_steps": 3829, "loss": 0.3285, "lr": 3.9060052219321154e-05, "epoch": 0.6855575868372943, "percentage": 9.79, "elapsed_time": "0:39:28", "remaining_time": "6:03:31"}
{"current_steps": 380, "total_steps": 3829, "loss": 0.3664, "lr": 3.95822454308094e-05, "epoch": 0.6946983546617916, "percentage": 9.92, "elapsed_time": "0:39:59", "remaining_time": "6:02:58"}
{"current_steps": 385, "total_steps": 3829, "loss": 0.3384, "lr": 3.999999168869598e-05, "epoch": 0.7038391224862889, "percentage": 10.05, "elapsed_time": "0:40:29", "remaining_time": "6:02:11"}
{"current_steps": 390, "total_steps": 3829, "loss": 0.3477, "lr": 3.9999700793780334e-05, "epoch": 0.7129798903107861, "percentage": 10.19, "elapsed_time": "0:41:04", "remaining_time": "6:02:09"}
{"current_steps": 395, "total_steps": 3829, "loss": 0.3545, "lr": 3.999899434057108e-05, "epoch": 0.7221206581352834, "percentage": 10.32, "elapsed_time": "0:41:32", "remaining_time": "6:01:12"}
{"current_steps": 400, "total_steps": 3829, "loss": 0.3392, "lr": 3.999787234374705e-05, "epoch": 0.7312614259597806, "percentage": 10.45, "elapsed_time": "0:42:03", "remaining_time": "6:00:35"}
{"current_steps": 405, "total_steps": 3829, "loss": 0.357, "lr": 3.999633482662136e-05, "epoch": 0.7404021937842779, "percentage": 10.58, "elapsed_time": "0:42:30", "remaining_time": "5:59:21"}
{"current_steps": 410, "total_steps": 3829, "loss": 0.3328, "lr": 3.999438182114087e-05, "epoch": 0.7495429616087751, "percentage": 10.71, "elapsed_time": "0:43:03", "remaining_time": "5:59:06"}
{"current_steps": 415, "total_steps": 3829, "loss": 0.4001, "lr": 3.999201336788558e-05, "epoch": 0.7586837294332724, "percentage": 10.84, "elapsed_time": "0:43:34", "remaining_time": "5:58:27"}
{"current_steps": 420, "total_steps": 3829, "loss": 0.3224, "lr": 3.9989229516067745e-05, "epoch": 0.7678244972577697, "percentage": 10.97, "elapsed_time": "0:44:09", "remaining_time": "5:58:24"}
{"current_steps": 425, "total_steps": 3829, "loss": 0.3339, "lr": 3.998603032353087e-05, "epoch": 0.7769652650822669, "percentage": 11.1, "elapsed_time": "0:44:39", "remaining_time": "5:57:41"}
{"current_steps": 430, "total_steps": 3829, "loss": 0.324, "lr": 3.998241585674849e-05, "epoch": 0.7861060329067642, "percentage": 11.23, "elapsed_time": "0:45:09", "remaining_time": "5:57:00"}
{"current_steps": 435, "total_steps": 3829, "loss": 0.3258, "lr": 3.9978386190822806e-05, "epoch": 0.7952468007312614, "percentage": 11.36, "elapsed_time": "0:45:40", "remaining_time": "5:56:18"}
{"current_steps": 440, "total_steps": 3829, "loss": 0.3563, "lr": 3.997394140948314e-05, "epoch": 0.8043875685557587, "percentage": 11.49, "elapsed_time": "0:46:09", "remaining_time": "5:55:30"}
{"current_steps": 445, "total_steps": 3829, "loss": 0.3336, "lr": 3.9969081605084164e-05, "epoch": 0.8135283363802559, "percentage": 11.62, "elapsed_time": "0:46:37", "remaining_time": "5:54:37"}
{"current_steps": 450, "total_steps": 3829, "loss": 0.3329, "lr": 3.996380687860397e-05, "epoch": 0.8226691042047533, "percentage": 11.75, "elapsed_time": "0:47:07", "remaining_time": "5:53:49"}
{"current_steps": 455, "total_steps": 3829, "loss": 0.333, "lr": 3.9958117339642024e-05, "epoch": 0.8318098720292505, "percentage": 11.88, "elapsed_time": "0:47:38", "remaining_time": "5:53:19"}
{"current_steps": 460, "total_steps": 3829, "loss": 0.3436, "lr": 3.995201310641686e-05, "epoch": 0.8409506398537477, "percentage": 12.01, "elapsed_time": "0:48:17", "remaining_time": "5:53:42"}
{"current_steps": 465, "total_steps": 3829, "loss": 0.3467, "lr": 3.9945494305763596e-05, "epoch": 0.850091407678245, "percentage": 12.14, "elapsed_time": "0:48:51", "remaining_time": "5:53:30"}
{"current_steps": 470, "total_steps": 3829, "loss": 0.3489, "lr": 3.993856107313136e-05, "epoch": 0.8592321755027422, "percentage": 12.27, "elapsed_time": "0:49:22", "remaining_time": "5:52:52"}
{"current_steps": 475, "total_steps": 3829, "loss": 0.3504, "lr": 3.99312135525804e-05, "epoch": 0.8683729433272395, "percentage": 12.41, "elapsed_time": "0:49:51", "remaining_time": "5:52:05"}
{"current_steps": 480, "total_steps": 3829, "loss": 0.3347, "lr": 3.9923451896779176e-05, "epoch": 0.8775137111517367, "percentage": 12.54, "elapsed_time": "0:50:19", "remaining_time": "5:51:06"}
{"current_steps": 485, "total_steps": 3829, "loss": 0.354, "lr": 3.991527626700111e-05, "epoch": 0.886654478976234, "percentage": 12.67, "elapsed_time": "0:50:46", "remaining_time": "5:50:06"}
{"current_steps": 490, "total_steps": 3829, "loss": 0.3192, "lr": 3.9906686833121295e-05, "epoch": 0.8957952468007313, "percentage": 12.8, "elapsed_time": "0:51:15", "remaining_time": "5:49:18"}
{"current_steps": 495, "total_steps": 3829, "loss": 0.3394, "lr": 3.989768377361291e-05, "epoch": 0.9049360146252285, "percentage": 12.93, "elapsed_time": "0:51:46", "remaining_time": "5:48:41"}
{"current_steps": 500, "total_steps": 3829, "loss": 0.3349, "lr": 3.9888267275543564e-05, "epoch": 0.9140767824497258, "percentage": 13.06, "elapsed_time": "0:52:14", "remaining_time": "5:47:52"}
{"current_steps": 505, "total_steps": 3829, "loss": 0.349, "lr": 3.987843753457137e-05, "epoch": 0.923217550274223, "percentage": 13.19, "elapsed_time": "0:52:46", "remaining_time": "5:47:21"}
{"current_steps": 510, "total_steps": 3829, "loss": 0.3037, "lr": 3.986819475494092e-05, "epoch": 0.9323583180987203, "percentage": 13.32, "elapsed_time": "0:53:19", "remaining_time": "5:47:04"}
{"current_steps": 515, "total_steps": 3829, "loss": 0.3503, "lr": 3.985753914947898e-05, "epoch": 0.9414990859232175, "percentage": 13.45, "elapsed_time": "0:53:54", "remaining_time": "5:46:51"}
{"current_steps": 520, "total_steps": 3829, "loss": 0.3341, "lr": 3.984647093959014e-05, "epoch": 0.9506398537477148, "percentage": 13.58, "elapsed_time": "0:54:25", "remaining_time": "5:46:21"}
{"current_steps": 525, "total_steps": 3829, "loss": 0.3236, "lr": 3.9834990355252144e-05, "epoch": 0.9597806215722121, "percentage": 13.71, "elapsed_time": "0:54:57", "remaining_time": "5:45:54"}
{"current_steps": 530, "total_steps": 3829, "loss": 0.3635, "lr": 3.9823097635011175e-05, "epoch": 0.9689213893967094, "percentage": 13.84, "elapsed_time": "0:55:30", "remaining_time": "5:45:33"}
{"current_steps": 535, "total_steps": 3829, "loss": 0.3296, "lr": 3.981079302597685e-05, "epoch": 0.9780621572212066, "percentage": 13.97, "elapsed_time": "0:56:11", "remaining_time": "5:45:56"}
{"current_steps": 540, "total_steps": 3829, "loss": 0.3265, "lr": 3.979807678381712e-05, "epoch": 0.9872029250457038, "percentage": 14.1, "elapsed_time": "0:56:45", "remaining_time": "5:45:41"}
{"current_steps": 545, "total_steps": 3829, "loss": 0.3416, "lr": 3.978494917275292e-05, "epoch": 0.9963436928702011, "percentage": 14.23, "elapsed_time": "0:57:15", "remaining_time": "5:45:02"}
{"current_steps": 550, "total_steps": 3829, "loss": 0.299, "lr": 3.9771410465552724e-05, "epoch": 1.0054844606946984, "percentage": 14.36, "elapsed_time": "0:57:49", "remaining_time": "5:44:47"}
{"current_steps": 555, "total_steps": 3829, "loss": 0.3577, "lr": 3.9757460943526836e-05, "epoch": 1.0146252285191957, "percentage": 14.49, "elapsed_time": "0:58:23", "remaining_time": "5:44:25"}
{"current_steps": 560, "total_steps": 3829, "loss": 0.311, "lr": 3.9743100896521575e-05, "epoch": 1.023765996343693, "percentage": 14.63, "elapsed_time": "0:58:56", "remaining_time": "5:44:02"}
{"current_steps": 565, "total_steps": 3829, "loss": 0.331, "lr": 3.972833062291323e-05, "epoch": 1.0329067641681902, "percentage": 14.76, "elapsed_time": "0:59:26", "remaining_time": "5:43:23"}
{"current_steps": 570, "total_steps": 3829, "loss": 0.3284, "lr": 3.9713150429601885e-05, "epoch": 1.0420475319926874, "percentage": 14.89, "elapsed_time": "0:59:56", "remaining_time": "5:42:41"}
{"current_steps": 575, "total_steps": 3829, "loss": 0.2863, "lr": 3.9697560632005016e-05, "epoch": 1.0511882998171846, "percentage": 15.02, "elapsed_time": "1:00:27", "remaining_time": "5:42:10"}
{"current_steps": 580, "total_steps": 3829, "loss": 0.3485, "lr": 3.9681561554050956e-05, "epoch": 1.0603290676416819, "percentage": 15.15, "elapsed_time": "1:00:59", "remaining_time": "5:41:40"}
{"current_steps": 585, "total_steps": 3829, "loss": 0.3092, "lr": 3.966515352817216e-05, "epoch": 1.0694698354661791, "percentage": 15.28, "elapsed_time": "1:01:33", "remaining_time": "5:41:22"}
{"current_steps": 590, "total_steps": 3829, "loss": 0.3439, "lr": 3.964833689529827e-05, "epoch": 1.0786106032906764, "percentage": 15.41, "elapsed_time": "1:02:01", "remaining_time": "5:40:30"}
{"current_steps": 595, "total_steps": 3829, "loss": 0.3065, "lr": 3.96311120048491e-05, "epoch": 1.0877513711151736, "percentage": 15.54, "elapsed_time": "1:02:39", "remaining_time": "5:40:32"}
{"current_steps": 600, "total_steps": 3829, "loss": 0.3048, "lr": 3.9613479214727296e-05, "epoch": 1.0968921389396709, "percentage": 15.67, "elapsed_time": "1:03:11", "remaining_time": "5:40:06"}
{"current_steps": 605, "total_steps": 3829, "loss": 0.3384, "lr": 3.959543889131095e-05, "epoch": 1.106032906764168, "percentage": 15.8, "elapsed_time": "1:03:45", "remaining_time": "5:39:45"}
{"current_steps": 610, "total_steps": 3829, "loss": 0.3174, "lr": 3.9576991409445975e-05, "epoch": 1.1151736745886653, "percentage": 15.93, "elapsed_time": "1:04:14", "remaining_time": "5:38:59"}
{"current_steps": 615, "total_steps": 3829, "loss": 0.3541, "lr": 3.95581371524383e-05, "epoch": 1.1243144424131628, "percentage": 16.06, "elapsed_time": "1:04:44", "remaining_time": "5:38:19"}
{"current_steps": 620, "total_steps": 3829, "loss": 0.3159, "lr": 3.9538876512045934e-05, "epoch": 1.13345521023766, "percentage": 16.19, "elapsed_time": "1:05:12", "remaining_time": "5:37:32"}
{"current_steps": 625, "total_steps": 3829, "loss": 0.3256, "lr": 3.951920988847081e-05, "epoch": 1.1425959780621573, "percentage": 16.32, "elapsed_time": "1:05:37", "remaining_time": "5:36:25"}
{"current_steps": 630, "total_steps": 3829, "loss": 0.312, "lr": 3.949913769035047e-05, "epoch": 1.1517367458866545, "percentage": 16.45, "elapsed_time": "1:06:09", "remaining_time": "5:35:55"}
{"current_steps": 635, "total_steps": 3829, "loss": 0.3183, "lr": 3.9478660334749565e-05, "epoch": 1.1608775137111518, "percentage": 16.58, "elapsed_time": "1:06:39", "remaining_time": "5:35:17"}
{"current_steps": 640, "total_steps": 3829, "loss": 0.3238, "lr": 3.945777824715122e-05, "epoch": 1.170018281535649, "percentage": 16.71, "elapsed_time": "1:07:13", "remaining_time": "5:34:58"}
{"current_steps": 645, "total_steps": 3829, "loss": 0.3067, "lr": 3.943649186144815e-05, "epoch": 1.1791590493601463, "percentage": 16.85, "elapsed_time": "1:07:43", "remaining_time": "5:34:18"}
{"current_steps": 650, "total_steps": 3829, "loss": 0.317, "lr": 3.941480161993368e-05, "epoch": 1.1882998171846435, "percentage": 16.98, "elapsed_time": "1:08:15", "remaining_time": "5:33:48"}
{"current_steps": 655, "total_steps": 3829, "loss": 0.309, "lr": 3.939270797329254e-05, "epoch": 1.1974405850091407, "percentage": 17.11, "elapsed_time": "1:08:44", "remaining_time": "5:33:08"}
{"current_steps": 660, "total_steps": 3829, "loss": 0.3278, "lr": 3.93702113805915e-05, "epoch": 1.206581352833638, "percentage": 17.24, "elapsed_time": "1:09:16", "remaining_time": "5:32:36"}
{"current_steps": 665, "total_steps": 3829, "loss": 0.3354, "lr": 3.934731230926984e-05, "epoch": 1.2157221206581352, "percentage": 17.37, "elapsed_time": "1:09:47", "remaining_time": "5:32:04"}
{"current_steps": 670, "total_steps": 3829, "loss": 0.2972, "lr": 3.932401123512963e-05, "epoch": 1.2248628884826325, "percentage": 17.5, "elapsed_time": "1:10:20", "remaining_time": "5:31:39"}
{"current_steps": 675, "total_steps": 3829, "loss": 0.3359, "lr": 3.930030864232585e-05, "epoch": 1.2340036563071297, "percentage": 17.63, "elapsed_time": "1:10:52", "remaining_time": "5:31:12"}
{"current_steps": 680, "total_steps": 3829, "loss": 0.3321, "lr": 3.9276205023356306e-05, "epoch": 1.2431444241316272, "percentage": 17.76, "elapsed_time": "1:11:22", "remaining_time": "5:30:32"}
{"current_steps": 685, "total_steps": 3829, "loss": 0.3295, "lr": 3.925170087905143e-05, "epoch": 1.2522851919561244, "percentage": 17.89, "elapsed_time": "1:11:51", "remaining_time": "5:29:47"}
{"current_steps": 690, "total_steps": 3829, "loss": 0.3349, "lr": 3.922679671856387e-05, "epoch": 1.2614259597806217, "percentage": 18.02, "elapsed_time": "1:12:23", "remaining_time": "5:29:18"}
{"current_steps": 695, "total_steps": 3829, "loss": 0.3255, "lr": 3.9201493059357875e-05, "epoch": 1.270566727605119, "percentage": 18.15, "elapsed_time": "1:12:57", "remaining_time": "5:28:59"}
{"current_steps": 700, "total_steps": 3829, "loss": 0.3164, "lr": 3.91757904271986e-05, "epoch": 1.2797074954296161, "percentage": 18.28, "elapsed_time": "1:13:34", "remaining_time": "5:28:50"}
{"current_steps": 705, "total_steps": 3829, "loss": 0.3068, "lr": 3.9149689356141114e-05, "epoch": 1.2888482632541134, "percentage": 18.41, "elapsed_time": "1:14:07", "remaining_time": "5:28:26"}
{"current_steps": 710, "total_steps": 3829, "loss": 0.3081, "lr": 3.912319038851937e-05, "epoch": 1.2979890310786106, "percentage": 18.54, "elapsed_time": "1:14:37", "remaining_time": "5:27:50"}
{"current_steps": 715, "total_steps": 3829, "loss": 0.2951, "lr": 3.909629407493489e-05, "epoch": 1.3071297989031079, "percentage": 18.67, "elapsed_time": "1:15:11", "remaining_time": "5:27:30"}
{"current_steps": 720, "total_steps": 3829, "loss": 0.3454, "lr": 3.906900097424534e-05, "epoch": 1.3162705667276051, "percentage": 18.8, "elapsed_time": "1:15:44", "remaining_time": "5:27:01"}
{"current_steps": 725, "total_steps": 3829, "loss": 0.3108, "lr": 3.904131165355293e-05, "epoch": 1.3254113345521024, "percentage": 18.93, "elapsed_time": "1:16:15", "remaining_time": "5:26:29"}
{"current_steps": 730, "total_steps": 3829, "loss": 0.3106, "lr": 3.9013226688192605e-05, "epoch": 1.3345521023765996, "percentage": 19.07, "elapsed_time": "1:16:51", "remaining_time": "5:26:15"}
{"current_steps": 735, "total_steps": 3829, "loss": 0.2997, "lr": 3.898474666172011e-05, "epoch": 1.3436928702010968, "percentage": 19.2, "elapsed_time": "1:17:26", "remaining_time": "5:26:00"}
{"current_steps": 740, "total_steps": 3829, "loss": 0.3158, "lr": 3.8955872165899854e-05, "epoch": 1.352833638025594, "percentage": 19.33, "elapsed_time": "1:18:01", "remaining_time": "5:25:40"}
{"current_steps": 745, "total_steps": 3829, "loss": 0.3043, "lr": 3.8926603800692624e-05, "epoch": 1.3619744058500913, "percentage": 19.46, "elapsed_time": "1:18:36", "remaining_time": "5:25:26"}
{"current_steps": 750, "total_steps": 3829, "loss": 0.3079, "lr": 3.889694217424312e-05, "epoch": 1.3711151736745886, "percentage": 19.59, "elapsed_time": "1:19:08", "remaining_time": "5:24:53"}
{"current_steps": 755, "total_steps": 3829, "loss": 0.3245, "lr": 3.88668879028673e-05, "epoch": 1.3802559414990858, "percentage": 19.72, "elapsed_time": "1:19:41", "remaining_time": "5:24:29"}
{"current_steps": 760, "total_steps": 3829, "loss": 0.304, "lr": 3.88364416110396e-05, "epoch": 1.389396709323583, "percentage": 19.85, "elapsed_time": "1:20:09", "remaining_time": "5:23:43"}
{"current_steps": 765, "total_steps": 3829, "loss": 0.3266, "lr": 3.8805603931379934e-05, "epoch": 1.3985374771480805, "percentage": 19.98, "elapsed_time": "1:20:42", "remaining_time": "5:23:15"}
{"current_steps": 770, "total_steps": 3829, "loss": 0.317, "lr": 3.877437550464056e-05, "epoch": 1.4076782449725778, "percentage": 20.11, "elapsed_time": "1:21:11", "remaining_time": "5:22:33"}
{"current_steps": 775, "total_steps": 3829, "loss": 0.3281, "lr": 3.874275697969277e-05, "epoch": 1.416819012797075, "percentage": 20.24, "elapsed_time": "1:21:43", "remaining_time": "5:22:01"}
{"current_steps": 780, "total_steps": 3829, "loss": 0.3246, "lr": 3.871074901351342e-05, "epoch": 1.4259597806215722, "percentage": 20.37, "elapsed_time": "1:22:12", "remaining_time": "5:21:21"}
{"current_steps": 785, "total_steps": 3829, "loss": 0.2983, "lr": 3.867835227117124e-05, "epoch": 1.4351005484460695, "percentage": 20.5, "elapsed_time": "1:22:42", "remaining_time": "5:20:41"}
{"current_steps": 790, "total_steps": 3829, "loss": 0.3143, "lr": 3.864556742581305e-05, "epoch": 1.4442413162705667, "percentage": 20.63, "elapsed_time": "1:23:14", "remaining_time": "5:20:13"}
{"current_steps": 795, "total_steps": 3829, "loss": 0.2988, "lr": 3.8612395158649755e-05, "epoch": 1.453382084095064, "percentage": 20.76, "elapsed_time": "1:23:48", "remaining_time": "5:19:52"}
{"current_steps": 800, "total_steps": 3829, "loss": 0.3157, "lr": 3.857883615894221e-05, "epoch": 1.4625228519195612, "percentage": 20.89, "elapsed_time": "1:24:19", "remaining_time": "5:19:16"}
{"current_steps": 805, "total_steps": 3829, "loss": 0.3146, "lr": 3.854489112398689e-05, "epoch": 1.4716636197440585, "percentage": 21.02, "elapsed_time": "1:24:48", "remaining_time": "5:18:34"}
{"current_steps": 810, "total_steps": 3829, "loss": 0.3084, "lr": 3.851056075910137e-05, "epoch": 1.4808043875685557, "percentage": 21.15, "elapsed_time": "1:25:23", "remaining_time": "5:18:16"}
{"current_steps": 815, "total_steps": 3829, "loss": 0.2957, "lr": 3.847584577760972e-05, "epoch": 1.489945155393053, "percentage": 21.28, "elapsed_time": "1:25:53", "remaining_time": "5:17:39"}
{"current_steps": 820, "total_steps": 3829, "loss": 0.3114, "lr": 3.8440746900827656e-05, "epoch": 1.4990859232175504, "percentage": 21.42, "elapsed_time": "1:26:23", "remaining_time": "5:17:00"}
{"current_steps": 825, "total_steps": 3829, "loss": 0.3034, "lr": 3.840526485804756e-05, "epoch": 1.5082266910420477, "percentage": 21.55, "elapsed_time": "1:26:53", "remaining_time": "5:16:25"}
{"current_steps": 830, "total_steps": 3829, "loss": 0.2981, "lr": 3.8369400386523305e-05, "epoch": 1.517367458866545, "percentage": 21.68, "elapsed_time": "1:27:24", "remaining_time": "5:15:49"}
{"current_steps": 835, "total_steps": 3829, "loss": 0.3023, "lr": 3.833315423145498e-05, "epoch": 1.5265082266910421, "percentage": 21.81, "elapsed_time": "1:27:56", "remaining_time": "5:15:17"}
{"current_steps": 840, "total_steps": 3829, "loss": 0.3189, "lr": 3.8296527145973364e-05, "epoch": 1.5356489945155394, "percentage": 21.94, "elapsed_time": "1:28:28", "remaining_time": "5:14:48"}
{"current_steps": 845, "total_steps": 3829, "loss": 0.3037, "lr": 3.8259519891124306e-05, "epoch": 1.5447897623400366, "percentage": 22.07, "elapsed_time": "1:28:57", "remaining_time": "5:14:09"}
{"current_steps": 850, "total_steps": 3829, "loss": 0.3053, "lr": 3.8222133235852893e-05, "epoch": 1.5539305301645339, "percentage": 22.2, "elapsed_time": "1:29:24", "remaining_time": "5:13:22"}
{"current_steps": 855, "total_steps": 3829, "loss": 0.2924, "lr": 3.8184367956987476e-05, "epoch": 1.563071297989031, "percentage": 22.33, "elapsed_time": "1:29:58", "remaining_time": "5:12:58"}
{"current_steps": 860, "total_steps": 3829, "loss": 0.302, "lr": 3.814622483922353e-05, "epoch": 1.5722120658135283, "percentage": 22.46, "elapsed_time": "1:30:27", "remaining_time": "5:12:15"}
{"current_steps": 865, "total_steps": 3829, "loss": 0.3332, "lr": 3.8107704675107375e-05, "epoch": 1.5813528336380256, "percentage": 22.59, "elapsed_time": "1:30:59", "remaining_time": "5:11:46"}
{"current_steps": 870, "total_steps": 3829, "loss": 0.3252, "lr": 3.8068808265019654e-05, "epoch": 1.5904936014625228, "percentage": 22.72, "elapsed_time": "1:31:32", "remaining_time": "5:11:21"}
{"current_steps": 875, "total_steps": 3829, "loss": 0.3161, "lr": 3.802953641715876e-05, "epoch": 1.59963436928702, "percentage": 22.85, "elapsed_time": "1:31:59", "remaining_time": "5:10:33"}
{"current_steps": 880, "total_steps": 3829, "loss": 0.3382, "lr": 3.7989889947524e-05, "epoch": 1.6087751371115173, "percentage": 22.98, "elapsed_time": "1:32:30", "remaining_time": "5:10:00"}
{"current_steps": 885, "total_steps": 3829, "loss": 0.2936, "lr": 3.7949869679898645e-05, "epoch": 1.6179159049360146, "percentage": 23.11, "elapsed_time": "1:33:00", "remaining_time": "5:09:23"}
{"current_steps": 890, "total_steps": 3829, "loss": 0.3288, "lr": 3.7909476445832866e-05, "epoch": 1.6270566727605118, "percentage": 23.24, "elapsed_time": "1:33:30", "remaining_time": "5:08:45"}
{"current_steps": 895, "total_steps": 3829, "loss": 0.3204, "lr": 3.786871108462638e-05, "epoch": 1.636197440585009, "percentage": 23.37, "elapsed_time": "1:34:06", "remaining_time": "5:08:30"}
{"current_steps": 900, "total_steps": 3829, "loss": 0.3185, "lr": 3.782757444331106e-05, "epoch": 1.6453382084095063, "percentage": 23.5, "elapsed_time": "1:34:35", "remaining_time": "5:07:50"}
{"current_steps": 905, "total_steps": 3829, "loss": 0.3115, "lr": 3.7786067376633305e-05, "epoch": 1.6544789762340035, "percentage": 23.64, "elapsed_time": "1:35:02", "remaining_time": "5:07:05"}
{"current_steps": 910, "total_steps": 3829, "loss": 0.3017, "lr": 3.774419074703632e-05, "epoch": 1.6636197440585008, "percentage": 23.77, "elapsed_time": "1:35:38", "remaining_time": "5:06:46"}
{"current_steps": 915, "total_steps": 3829, "loss": 0.2969, "lr": 3.7701945424642155e-05, "epoch": 1.672760511882998, "percentage": 23.9, "elapsed_time": "1:36:08", "remaining_time": "5:06:09"}
{"current_steps": 920, "total_steps": 3829, "loss": 0.2931, "lr": 3.7659332287233644e-05, "epoch": 1.6819012797074955, "percentage": 24.03, "elapsed_time": "1:36:40", "remaining_time": "5:05:39"}
{"current_steps": 925, "total_steps": 3829, "loss": 0.2956, "lr": 3.761635222023617e-05, "epoch": 1.6910420475319927, "percentage": 24.16, "elapsed_time": "1:37:11", "remaining_time": "5:05:08"}
{"current_steps": 930, "total_steps": 3829, "loss": 0.2759, "lr": 3.757300611669926e-05, "epoch": 1.70018281535649, "percentage": 24.29, "elapsed_time": "1:37:39", "remaining_time": "5:04:26"}
{"current_steps": 935, "total_steps": 3829, "loss": 0.2981, "lr": 3.7529294877278024e-05, "epoch": 1.7093235831809872, "percentage": 24.42, "elapsed_time": "1:38:12", "remaining_time": "5:03:57"}
{"current_steps": 940, "total_steps": 3829, "loss": 0.2909, "lr": 3.7485219410214455e-05, "epoch": 1.7184643510054844, "percentage": 24.55, "elapsed_time": "1:38:46", "remaining_time": "5:03:34"}
{"current_steps": 945, "total_steps": 3829, "loss": 0.3186, "lr": 3.7440780631318546e-05, "epoch": 1.7276051188299817, "percentage": 24.68, "elapsed_time": "1:39:11", "remaining_time": "5:02:44"}
{"current_steps": 950, "total_steps": 3829, "loss": 0.3091, "lr": 3.739597946394928e-05, "epoch": 1.736745886654479, "percentage": 24.81, "elapsed_time": "1:39:44", "remaining_time": "5:02:15"}
{"current_steps": 955, "total_steps": 3829, "loss": 0.3131, "lr": 3.735081683899539e-05, "epoch": 1.7458866544789764, "percentage": 24.94, "elapsed_time": "1:40:17", "remaining_time": "5:01:49"}
{"current_steps": 960, "total_steps": 3829, "loss": 0.2841, "lr": 3.730529369485611e-05, "epoch": 1.7550274223034736, "percentage": 25.07, "elapsed_time": "1:40:45", "remaining_time": "5:01:07"}
{"current_steps": 965, "total_steps": 3829, "loss": 0.3219, "lr": 3.725941097742158e-05, "epoch": 1.7641681901279709, "percentage": 25.2, "elapsed_time": "1:41:19", "remaining_time": "5:00:44"}
{"current_steps": 970, "total_steps": 3829, "loss": 0.2958, "lr": 3.721316964005326e-05, "epoch": 1.7733089579524681, "percentage": 25.33, "elapsed_time": "1:41:49", "remaining_time": "5:00:06"}
{"current_steps": 975, "total_steps": 3829, "loss": 0.291, "lr": 3.7166570643564075e-05, "epoch": 1.7824497257769654, "percentage": 25.46, "elapsed_time": "1:42:19", "remaining_time": "4:59:30"}
{"current_steps": 980, "total_steps": 3829, "loss": 0.2987, "lr": 3.7119614956198494e-05, "epoch": 1.7915904936014626, "percentage": 25.59, "elapsed_time": "1:42:48", "remaining_time": "4:58:54"}
{"current_steps": 985, "total_steps": 3829, "loss": 0.3025, "lr": 3.7072303553612375e-05, "epoch": 1.8007312614259599, "percentage": 25.72, "elapsed_time": "1:43:17", "remaining_time": "4:58:13"}
{"current_steps": 990, "total_steps": 3829, "loss": 0.3142, "lr": 3.702463741885271e-05, "epoch": 1.809872029250457, "percentage": 25.86, "elapsed_time": "1:43:47", "remaining_time": "4:57:39"}
{"current_steps": 995, "total_steps": 3829, "loss": 0.3109, "lr": 3.697661754233719e-05, "epoch": 1.8190127970749543, "percentage": 25.99, "elapsed_time": "1:44:20", "remaining_time": "4:57:11"}
{"current_steps": 1000, "total_steps": 3829, "loss": 0.316, "lr": 3.6928244921833665e-05, "epoch": 1.8281535648994516, "percentage": 26.12, "elapsed_time": "1:44:53", "remaining_time": "4:56:42"}
{"current_steps": 1005, "total_steps": 3829, "loss": 0.2883, "lr": 3.687952056243932e-05, "epoch": 1.8372943327239488, "percentage": 26.25, "elapsed_time": "1:45:23", "remaining_time": "4:56:08"}
{"current_steps": 1010, "total_steps": 3829, "loss": 0.29, "lr": 3.683044547655991e-05, "epoch": 1.846435100548446, "percentage": 26.38, "elapsed_time": "1:45:53", "remaining_time": "4:55:33"}
{"current_steps": 1015, "total_steps": 3829, "loss": 0.3, "lr": 3.678102068388862e-05, "epoch": 1.8555758683729433, "percentage": 26.51, "elapsed_time": "1:46:29", "remaining_time": "4:55:13"}
{"current_steps": 1020, "total_steps": 3829, "loss": 0.3487, "lr": 3.6731247211384946e-05, "epoch": 1.8647166361974405, "percentage": 26.64, "elapsed_time": "1:47:00", "remaining_time": "4:54:42"}
{"current_steps": 1025, "total_steps": 3829, "loss": 0.3175, "lr": 3.668112609325333e-05, "epoch": 1.8738574040219378, "percentage": 26.77, "elapsed_time": "1:47:36", "remaining_time": "4:54:22"}
{"current_steps": 1030, "total_steps": 3829, "loss": 0.2968, "lr": 3.6630658370921664e-05, "epoch": 1.882998171846435, "percentage": 26.9, "elapsed_time": "1:48:05", "remaining_time": "4:53:43"}
{"current_steps": 1035, "total_steps": 3829, "loss": 0.3198, "lr": 3.6579845093019655e-05, "epoch": 1.8921389396709323, "percentage": 27.03, "elapsed_time": "1:48:33", "remaining_time": "4:53:04"}
{"current_steps": 1040, "total_steps": 3829, "loss": 0.3223, "lr": 3.652868731535706e-05, "epoch": 1.9012797074954295, "percentage": 27.16, "elapsed_time": "1:49:06", "remaining_time": "4:52:35"}
{"current_steps": 1045, "total_steps": 3829, "loss": 0.2947, "lr": 3.647718610090172e-05, "epoch": 1.9104204753199268, "percentage": 27.29, "elapsed_time": "1:49:32", "remaining_time": "4:51:49"}
{"current_steps": 1050, "total_steps": 3829, "loss": 0.2931, "lr": 3.642534251975749e-05, "epoch": 1.919561243144424, "percentage": 27.42, "elapsed_time": "1:50:05", "remaining_time": "4:51:23"}
{"current_steps": 1055, "total_steps": 3829, "loss": 0.2667, "lr": 3.637315764914198e-05, "epoch": 1.9287020109689212, "percentage": 27.55, "elapsed_time": "1:50:38", "remaining_time": "4:50:55"}
{"current_steps": 1060, "total_steps": 3829, "loss": 0.2793, "lr": 3.632063257336421e-05, "epoch": 1.9378427787934185, "percentage": 27.68, "elapsed_time": "1:51:10", "remaining_time": "4:50:26"}
{"current_steps": 1065, "total_steps": 3829, "loss": 0.3296, "lr": 3.6267768383802044e-05, "epoch": 1.946983546617916, "percentage": 27.81, "elapsed_time": "1:51:39", "remaining_time": "4:49:47"}
{"current_steps": 1070, "total_steps": 3829, "loss": 0.3218, "lr": 3.621456617887954e-05, "epoch": 1.9561243144424132, "percentage": 27.94, "elapsed_time": "1:52:15", "remaining_time": "4:49:27"}
{"current_steps": 1075, "total_steps": 3829, "loss": 0.2939, "lr": 3.616102706404411e-05, "epoch": 1.9652650822669104, "percentage": 28.08, "elapsed_time": "1:52:50", "remaining_time": "4:49:05"}
{"current_steps": 1080, "total_steps": 3829, "loss": 0.3083, "lr": 3.610715215174355e-05, "epoch": 1.9744058500914077, "percentage": 28.21, "elapsed_time": "1:53:21", "remaining_time": "4:48:33"}
{"current_steps": 1085, "total_steps": 3829, "loss": 0.3423, "lr": 3.605294256140295e-05, "epoch": 1.983546617915905, "percentage": 28.34, "elapsed_time": "1:53:53", "remaining_time": "4:48:01"}
{"current_steps": 1090, "total_steps": 3829, "loss": 0.2982, "lr": 3.599839941940139e-05, "epoch": 1.9926873857404022, "percentage": 28.47, "elapsed_time": "1:54:24", "remaining_time": "4:47:28"}
{"current_steps": 1095, "total_steps": 3829, "loss": 0.3092, "lr": 3.594352385904859e-05, "epoch": 2.0018281535648996, "percentage": 28.6, "elapsed_time": "1:54:54", "remaining_time": "4:46:54"}
{"current_steps": 1100, "total_steps": 3829, "loss": 0.2776, "lr": 3.5888317020561304e-05, "epoch": 2.010968921389397, "percentage": 28.73, "elapsed_time": "1:55:31", "remaining_time": "4:46:36"}
{"current_steps": 1105, "total_steps": 3829, "loss": 0.273, "lr": 3.583278005103969e-05, "epoch": 2.020109689213894, "percentage": 28.86, "elapsed_time": "1:56:05", "remaining_time": "4:46:11"}
{"current_steps": 1110, "total_steps": 3829, "loss": 0.2778, "lr": 3.5776914104443416e-05, "epoch": 2.0292504570383914, "percentage": 28.99, "elapsed_time": "1:56:37", "remaining_time": "4:45:40"}
{"current_steps": 1115, "total_steps": 3829, "loss": 0.3042, "lr": 3.5720720341567716e-05, "epoch": 2.0383912248628886, "percentage": 29.12, "elapsed_time": "1:57:09", "remaining_time": "4:45:11"}
{"current_steps": 1120, "total_steps": 3829, "loss": 0.2712, "lr": 3.566419993001927e-05, "epoch": 2.047531992687386, "percentage": 29.25, "elapsed_time": "1:57:48", "remaining_time": "4:44:57"}
{"current_steps": 1125, "total_steps": 3829, "loss": 0.2836, "lr": 3.5607354044191947e-05, "epoch": 2.056672760511883, "percentage": 29.38, "elapsed_time": "1:58:14", "remaining_time": "4:44:12"}
{"current_steps": 1130, "total_steps": 3829, "loss": 0.3009, "lr": 3.555018386524237e-05, "epoch": 2.0658135283363803, "percentage": 29.51, "elapsed_time": "1:58:48", "remaining_time": "4:43:47"}
{"current_steps": 1135, "total_steps": 3829, "loss": 0.2768, "lr": 3.549269058106542e-05, "epoch": 2.0749542961608776, "percentage": 29.64, "elapsed_time": "1:59:16", "remaining_time": "4:43:06"}
{"current_steps": 1140, "total_steps": 3829, "loss": 0.2997, "lr": 3.5434875386269514e-05, "epoch": 2.084095063985375, "percentage": 29.77, "elapsed_time": "1:59:47", "remaining_time": "4:42:32"}
{"current_steps": 1145, "total_steps": 3829, "loss": 0.298, "lr": 3.537673948215182e-05, "epoch": 2.093235831809872, "percentage": 29.9, "elapsed_time": "2:00:17", "remaining_time": "4:41:58"}
{"current_steps": 1150, "total_steps": 3829, "loss": 0.2557, "lr": 3.531828407667325e-05, "epoch": 2.1023765996343693, "percentage": 30.03, "elapsed_time": "2:00:48", "remaining_time": "4:41:25"}
{"current_steps": 1155, "total_steps": 3829, "loss": 0.2997, "lr": 3.5259510384433415e-05, "epoch": 2.1115173674588665, "percentage": 30.16, "elapsed_time": "2:01:22", "remaining_time": "4:40:59"}
{"current_steps": 1160, "total_steps": 3829, "loss": 0.2761, "lr": 3.520041962664533e-05, "epoch": 2.1206581352833638, "percentage": 30.3, "elapsed_time": "2:01:53", "remaining_time": "4:40:26"}
{"current_steps": 1165, "total_steps": 3829, "loss": 0.2954, "lr": 3.5141013031110114e-05, "epoch": 2.129798903107861, "percentage": 30.43, "elapsed_time": "2:02:24", "remaining_time": "4:39:54"}
{"current_steps": 1170, "total_steps": 3829, "loss": 0.2913, "lr": 3.508129183219139e-05, "epoch": 2.1389396709323583, "percentage": 30.56, "elapsed_time": "2:02:56", "remaining_time": "4:39:24"}
{"current_steps": 1175, "total_steps": 3829, "loss": 0.2427, "lr": 3.50212572707897e-05, "epoch": 2.1480804387568555, "percentage": 30.69, "elapsed_time": "2:03:25", "remaining_time": "4:38:47"}
{"current_steps": 1180, "total_steps": 3829, "loss": 0.2936, "lr": 3.49609105943167e-05, "epoch": 2.1572212065813527, "percentage": 30.82, "elapsed_time": "2:03:57", "remaining_time": "4:38:15"}
{"current_steps": 1185, "total_steps": 3829, "loss": 0.273, "lr": 3.490025305666925e-05, "epoch": 2.16636197440585, "percentage": 30.95, "elapsed_time": "2:04:29", "remaining_time": "4:37:45"}
{"current_steps": 1190, "total_steps": 3829, "loss": 0.2744, "lr": 3.4839285918203335e-05, "epoch": 2.1755027422303472, "percentage": 31.08, "elapsed_time": "2:05:04", "remaining_time": "4:37:22"}
{"current_steps": 1195, "total_steps": 3829, "loss": 0.2588, "lr": 3.477801044570792e-05, "epoch": 2.1846435100548445, "percentage": 31.21, "elapsed_time": "2:05:38", "remaining_time": "4:36:56"}
{"current_steps": 1200, "total_steps": 3829, "loss": 0.2682, "lr": 3.4716427912378584e-05, "epoch": 2.1937842778793417, "percentage": 31.34, "elapsed_time": "2:06:07", "remaining_time": "4:36:19"}
{"current_steps": 1205, "total_steps": 3829, "loss": 0.2641, "lr": 3.46545395977911e-05, "epoch": 2.202925045703839, "percentage": 31.47, "elapsed_time": "2:06:42", "remaining_time": "4:35:56"}
{"current_steps": 1210, "total_steps": 3829, "loss": 0.2614, "lr": 3.459234678787482e-05, "epoch": 2.212065813528336, "percentage": 31.6, "elapsed_time": "2:07:15", "remaining_time": "4:35:27"}
{"current_steps": 1215, "total_steps": 3829, "loss": 0.3086, "lr": 3.4529850774885973e-05, "epoch": 2.2212065813528334, "percentage": 31.73, "elapsed_time": "2:07:51", "remaining_time": "4:35:05"}
{"current_steps": 1220, "total_steps": 3829, "loss": 0.2844, "lr": 3.446705285738082e-05, "epoch": 2.2303473491773307, "percentage": 31.86, "elapsed_time": "2:08:22", "remaining_time": "4:34:32"}
{"current_steps": 1225, "total_steps": 3829, "loss": 0.2961, "lr": 3.440395434018865e-05, "epoch": 2.2394881170018284, "percentage": 31.99, "elapsed_time": "2:08:51", "remaining_time": "4:33:55"}
{"current_steps": 1230, "total_steps": 3829, "loss": 0.283, "lr": 3.434055653438468e-05, "epoch": 2.2486288848263256, "percentage": 32.12, "elapsed_time": "2:09:26", "remaining_time": "4:33:30"}
{"current_steps": 1235, "total_steps": 3829, "loss": 0.2689, "lr": 3.427686075726282e-05, "epoch": 2.257769652650823, "percentage": 32.25, "elapsed_time": "2:09:56", "remaining_time": "4:32:55"}
{"current_steps": 1240, "total_steps": 3829, "loss": 0.2887, "lr": 3.4212868332308296e-05, "epoch": 2.26691042047532, "percentage": 32.38, "elapsed_time": "2:10:21", "remaining_time": "4:32:10"}
{"current_steps": 1245, "total_steps": 3829, "loss": 0.2976, "lr": 3.4148580589170144e-05, "epoch": 2.2760511882998173, "percentage": 32.52, "elapsed_time": "2:10:54", "remaining_time": "4:31:42"}
{"current_steps": 1250, "total_steps": 3829, "loss": 0.2896, "lr": 3.408399886363358e-05, "epoch": 2.2851919561243146, "percentage": 32.65, "elapsed_time": "2:11:26", "remaining_time": "4:31:11"}
{"current_steps": 1255, "total_steps": 3829, "loss": 0.316, "lr": 3.4019124497592276e-05, "epoch": 2.294332723948812, "percentage": 32.78, "elapsed_time": "2:12:02", "remaining_time": "4:30:49"}
{"current_steps": 1260, "total_steps": 3829, "loss": 0.2718, "lr": 3.395395883902044e-05, "epoch": 2.303473491773309, "percentage": 32.91, "elapsed_time": "2:12:36", "remaining_time": "4:30:23"}
{"current_steps": 1265, "total_steps": 3829, "loss": 0.2735, "lr": 3.388850324194481e-05, "epoch": 2.3126142595978063, "percentage": 33.04, "elapsed_time": "2:13:08", "remaining_time": "4:29:52"}
{"current_steps": 1270, "total_steps": 3829, "loss": 0.2776, "lr": 3.382275906641656e-05, "epoch": 2.3217550274223036, "percentage": 33.17, "elapsed_time": "2:13:39", "remaining_time": "4:29:18"}
{"current_steps": 1275, "total_steps": 3829, "loss": 0.2894, "lr": 3.375672767848298e-05, "epoch": 2.330895795246801, "percentage": 33.3, "elapsed_time": "2:14:12", "remaining_time": "4:28:49"}
{"current_steps": 1280, "total_steps": 3829, "loss": 0.2829, "lr": 3.3690410450159156e-05, "epoch": 2.340036563071298, "percentage": 33.43, "elapsed_time": "2:14:42", "remaining_time": "4:28:16"}
{"current_steps": 1285, "total_steps": 3829, "loss": 0.3147, "lr": 3.36238087593994e-05, "epoch": 2.3491773308957953, "percentage": 33.56, "elapsed_time": "2:15:10", "remaining_time": "4:27:36"}
{"current_steps": 1290, "total_steps": 3829, "loss": 0.2707, "lr": 3.355692399006867e-05, "epoch": 2.3583180987202925, "percentage": 33.69, "elapsed_time": "2:15:40", "remaining_time": "4:27:03"}
{"current_steps": 1295, "total_steps": 3829, "loss": 0.2845, "lr": 3.34897575319138e-05, "epoch": 2.3674588665447898, "percentage": 33.82, "elapsed_time": "2:16:09", "remaining_time": "4:26:25"}
{"current_steps": 1300, "total_steps": 3829, "loss": 0.2653, "lr": 3.342231078053458e-05, "epoch": 2.376599634369287, "percentage": 33.95, "elapsed_time": "2:16:39", "remaining_time": "4:25:51"}
{"current_steps": 1305, "total_steps": 3829, "loss": 0.2759, "lr": 3.335458513735485e-05, "epoch": 2.3857404021937842, "percentage": 34.08, "elapsed_time": "2:17:12", "remaining_time": "4:25:22"}
{"current_steps": 1310, "total_steps": 3829, "loss": 0.2867, "lr": 3.328658200959327e-05, "epoch": 2.3948811700182815, "percentage": 34.21, "elapsed_time": "2:17:42", "remaining_time": "4:24:48"}
{"current_steps": 1315, "total_steps": 3829, "loss": 0.2627, "lr": 3.321830281023418e-05, "epoch": 2.4040219378427787, "percentage": 34.34, "elapsed_time": "2:18:09", "remaining_time": "4:24:08"}
{"current_steps": 1320, "total_steps": 3829, "loss": 0.3043, "lr": 3.314974895799819e-05, "epoch": 2.413162705667276, "percentage": 34.47, "elapsed_time": "2:18:46", "remaining_time": "4:23:47"}
{"current_steps": 1325, "total_steps": 3829, "loss": 0.283, "lr": 3.308092187731269e-05, "epoch": 2.422303473491773, "percentage": 34.6, "elapsed_time": "2:19:18", "remaining_time": "4:23:16"}
{"current_steps": 1330, "total_steps": 3829, "loss": 0.2789, "lr": 3.301182299828229e-05, "epoch": 2.4314442413162705, "percentage": 34.73, "elapsed_time": "2:19:52", "remaining_time": "4:22:48"}
{"current_steps": 1335, "total_steps": 3829, "loss": 0.261, "lr": 3.294245375665908e-05, "epoch": 2.4405850091407677, "percentage": 34.87, "elapsed_time": "2:20:21", "remaining_time": "4:22:11"}
{"current_steps": 1340, "total_steps": 3829, "loss": 0.2866, "lr": 3.287281559381281e-05, "epoch": 2.449725776965265, "percentage": 35.0, "elapsed_time": "2:20:51", "remaining_time": "4:21:37"}
{"current_steps": 1345, "total_steps": 3829, "loss": 0.2942, "lr": 3.2802909956700934e-05, "epoch": 2.458866544789762, "percentage": 35.13, "elapsed_time": "2:21:25", "remaining_time": "4:21:11"}
{"current_steps": 1350, "total_steps": 3829, "loss": 0.2916, "lr": 3.2732738297838546e-05, "epoch": 2.4680073126142594, "percentage": 35.26, "elapsed_time": "2:21:56", "remaining_time": "4:20:39"}
{"current_steps": 1355, "total_steps": 3829, "loss": 0.2837, "lr": 3.2662302075268194e-05, "epoch": 2.4771480804387567, "percentage": 35.39, "elapsed_time": "2:22:31", "remaining_time": "4:20:14"}
{"current_steps": 1360, "total_steps": 3829, "loss": 0.2745, "lr": 3.25916027525296e-05, "epoch": 2.4862888482632544, "percentage": 35.52, "elapsed_time": "2:23:02", "remaining_time": "4:19:40"}
{"current_steps": 1365, "total_steps": 3829, "loss": 0.2837, "lr": 3.2520641798629236e-05, "epoch": 2.495429616087751, "percentage": 35.65, "elapsed_time": "2:23:33", "remaining_time": "4:19:08"}
{"current_steps": 1370, "total_steps": 3829, "loss": 0.2726, "lr": 3.244942068800981e-05, "epoch": 2.504570383912249, "percentage": 35.78, "elapsed_time": "2:24:06", "remaining_time": "4:18:39"}
{"current_steps": 1375, "total_steps": 3829, "loss": 0.2643, "lr": 3.237794090051962e-05, "epoch": 2.5137111517367456, "percentage": 35.91, "elapsed_time": "2:24:34", "remaining_time": "4:18:02"}
{"current_steps": 1380, "total_steps": 3829, "loss": 0.2908, "lr": 3.23062039213818e-05, "epoch": 2.5228519195612433, "percentage": 36.04, "elapsed_time": "2:25:03", "remaining_time": "4:17:24"}
{"current_steps": 1385, "total_steps": 3829, "loss": 0.2918, "lr": 3.2234211241163494e-05, "epoch": 2.53199268738574, "percentage": 36.17, "elapsed_time": "2:25:35", "remaining_time": "4:16:55"}
{"current_steps": 1390, "total_steps": 3829, "loss": 0.2841, "lr": 3.2161964355744835e-05, "epoch": 2.541133455210238, "percentage": 36.3, "elapsed_time": "2:26:05", "remaining_time": "4:16:21"}
{"current_steps": 1395, "total_steps": 3829, "loss": 0.2528, "lr": 3.208946476628792e-05, "epoch": 2.550274223034735, "percentage": 36.43, "elapsed_time": "2:26:38", "remaining_time": "4:15:52"}
{"current_steps": 1400, "total_steps": 3829, "loss": 0.2941, "lr": 3.201671397920556e-05, "epoch": 2.5594149908592323, "percentage": 36.56, "elapsed_time": "2:27:11", "remaining_time": "4:15:22"}
{"current_steps": 1405, "total_steps": 3829, "loss": 0.2831, "lr": 3.1943713506130015e-05, "epoch": 2.5685557586837295, "percentage": 36.69, "elapsed_time": "2:27:44", "remaining_time": "4:14:53"}
{"current_steps": 1410, "total_steps": 3829, "loss": 0.2671, "lr": 3.187046486388158e-05, "epoch": 2.577696526508227, "percentage": 36.82, "elapsed_time": "2:28:18", "remaining_time": "4:14:26"}
{"current_steps": 1415, "total_steps": 3829, "loss": 0.2495, "lr": 3.1796969574437066e-05, "epoch": 2.586837294332724, "percentage": 36.95, "elapsed_time": "2:28:48", "remaining_time": "4:13:52"}
{"current_steps": 1420, "total_steps": 3829, "loss": 0.2808, "lr": 3.1723229164898166e-05, "epoch": 2.5959780621572213, "percentage": 37.09, "elapsed_time": "2:29:17", "remaining_time": "4:13:17"}
{"current_steps": 1425, "total_steps": 3829, "loss": 0.2589, "lr": 3.164924516745974e-05, "epoch": 2.6051188299817185, "percentage": 37.22, "elapsed_time": "2:29:45", "remaining_time": "4:12:38"}
{"current_steps": 1430, "total_steps": 3829, "loss": 0.2682, "lr": 3.1575019119377985e-05, "epoch": 2.6142595978062158, "percentage": 37.35, "elapsed_time": "2:30:11", "remaining_time": "4:11:58"}
{"current_steps": 1435, "total_steps": 3829, "loss": 0.2802, "lr": 3.150055256293846e-05, "epoch": 2.623400365630713, "percentage": 37.48, "elapsed_time": "2:30:42", "remaining_time": "4:11:26"}
{"current_steps": 1440, "total_steps": 3829, "loss": 0.2758, "lr": 3.142584704542406e-05, "epoch": 2.6325411334552102, "percentage": 37.61, "elapsed_time": "2:31:16", "remaining_time": "4:10:58"}
{"current_steps": 1445, "total_steps": 3829, "loss": 0.2845, "lr": 3.1350904119082894e-05, "epoch": 2.6416819012797075, "percentage": 37.74, "elapsed_time": "2:31:47", "remaining_time": "4:10:25"}
{"current_steps": 1450, "total_steps": 3829, "loss": 0.3027, "lr": 3.127572534109598e-05, "epoch": 2.6508226691042047, "percentage": 37.87, "elapsed_time": "2:32:24", "remaining_time": "4:10:02"}
{"current_steps": 1455, "total_steps": 3829, "loss": 0.2705, "lr": 3.120031227354491e-05, "epoch": 2.659963436928702, "percentage": 38.0, "elapsed_time": "2:32:56", "remaining_time": "4:09:32"}
{"current_steps": 1460, "total_steps": 3829, "loss": 0.2931, "lr": 3.112466648337942e-05, "epoch": 2.669104204753199, "percentage": 38.13, "elapsed_time": "2:33:28", "remaining_time": "4:09:01"}
{"current_steps": 1465, "total_steps": 3829, "loss": 0.2819, "lr": 3.1048789542384805e-05, "epoch": 2.6782449725776964, "percentage": 38.26, "elapsed_time": "2:33:59", "remaining_time": "4:08:28"}
{"current_steps": 1470, "total_steps": 3829, "loss": 0.2738, "lr": 3.097268302714925e-05, "epoch": 2.6873857404021937, "percentage": 38.39, "elapsed_time": "2:34:25", "remaining_time": "4:07:49"}
{"current_steps": 1475, "total_steps": 3829, "loss": 0.2604, "lr": 3.089634851903109e-05, "epoch": 2.696526508226691, "percentage": 38.52, "elapsed_time": "2:34:56", "remaining_time": "4:07:16"}
{"current_steps": 1480, "total_steps": 3829, "loss": 0.2837, "lr": 3.081978760412595e-05, "epoch": 2.705667276051188, "percentage": 38.65, "elapsed_time": "2:35:32", "remaining_time": "4:06:52"}
{"current_steps": 1485, "total_steps": 3829, "loss": 0.2849, "lr": 3.07430018732338e-05, "epoch": 2.7148080438756854, "percentage": 38.78, "elapsed_time": "2:36:02", "remaining_time": "4:06:17"}
{"current_steps": 1490, "total_steps": 3829, "loss": 0.2921, "lr": 3.0665992921825854e-05, "epoch": 2.7239488117001827, "percentage": 38.91, "elapsed_time": "2:36:40", "remaining_time": "4:05:56"}
{"current_steps": 1495, "total_steps": 3829, "loss": 0.2859, "lr": 3.0588762350011494e-05, "epoch": 2.7330895795246803, "percentage": 39.04, "elapsed_time": "2:37:10", "remaining_time": "4:05:23"}
{"current_steps": 1500, "total_steps": 3829, "loss": 0.3009, "lr": 3.0511311762504935e-05, "epoch": 2.742230347349177, "percentage": 39.17, "elapsed_time": "2:37:43", "remaining_time": "4:04:54"}
{"current_steps": 1505, "total_steps": 3829, "loss": 0.2809, "lr": 3.0433642768591975e-05, "epoch": 2.751371115173675, "percentage": 39.31, "elapsed_time": "2:38:41", "remaining_time": "4:05:03"}
{"current_steps": 1510, "total_steps": 3829, "loss": 0.2668, "lr": 3.0355756982096475e-05, "epoch": 2.7605118829981716, "percentage": 39.44, "elapsed_time": "2:39:10", "remaining_time": "4:04:27"}
{"current_steps": 1515, "total_steps": 3829, "loss": 0.2793, "lr": 3.0277656021346863e-05, "epoch": 2.7696526508226693, "percentage": 39.57, "elapsed_time": "2:39:46", "remaining_time": "4:04:02"}
{"current_steps": 1520, "total_steps": 3829, "loss": 0.2715, "lr": 3.019934150914253e-05, "epoch": 2.778793418647166, "percentage": 39.7, "elapsed_time": "2:40:14", "remaining_time": "4:03:25"}
{"current_steps": 1525, "total_steps": 3829, "loss": 0.2776, "lr": 3.0120815072720068e-05, "epoch": 2.787934186471664, "percentage": 39.83, "elapsed_time": "2:40:45", "remaining_time": "4:02:52"}
{"current_steps": 1530, "total_steps": 3829, "loss": 0.288, "lr": 3.004207834371948e-05, "epoch": 2.797074954296161, "percentage": 39.96, "elapsed_time": "2:41:17", "remaining_time": "4:02:21"}
{"current_steps": 1535, "total_steps": 3829, "loss": 0.267, "lr": 2.9963132958150285e-05, "epoch": 2.8062157221206583, "percentage": 40.09, "elapsed_time": "2:41:48", "remaining_time": "4:01:48"}
{"current_steps": 1540, "total_steps": 3829, "loss": 0.2665, "lr": 2.9883980556357507e-05, "epoch": 2.8153564899451555, "percentage": 40.22, "elapsed_time": "2:42:20", "remaining_time": "4:01:18"}
{"current_steps": 1545, "total_steps": 3829, "loss": 0.3111, "lr": 2.9804622782987596e-05, "epoch": 2.8244972577696528, "percentage": 40.35, "elapsed_time": "2:42:57", "remaining_time": "4:00:53"}
{"current_steps": 1550, "total_steps": 3829, "loss": 0.2553, "lr": 2.9725061286954265e-05, "epoch": 2.83363802559415, "percentage": 40.48, "elapsed_time": "2:43:23", "remaining_time": "4:00:14"}
{"current_steps": 1555, "total_steps": 3829, "loss": 0.2703, "lr": 2.9645297721404237e-05, "epoch": 2.8427787934186473, "percentage": 40.61, "elapsed_time": "2:43:54", "remaining_time": "3:59:42"}
{"current_steps": 1560, "total_steps": 3829, "loss": 0.2764, "lr": 2.9565333743682846e-05, "epoch": 2.8519195612431445, "percentage": 40.74, "elapsed_time": "2:44:27", "remaining_time": "3:59:12"}
{"current_steps": 1565, "total_steps": 3829, "loss": 0.2767, "lr": 2.9485171015299666e-05, "epoch": 2.8610603290676417, "percentage": 40.87, "elapsed_time": "2:44:57", "remaining_time": "3:58:38"}
{"current_steps": 1570, "total_steps": 3829, "loss": 0.2849, "lr": 2.940481120189395e-05, "epoch": 2.870201096892139, "percentage": 41.0, "elapsed_time": "2:45:30", "remaining_time": "3:58:09"}
{"current_steps": 1575, "total_steps": 3829, "loss": 0.2884, "lr": 2.9324255973200012e-05, "epoch": 2.8793418647166362, "percentage": 41.13, "elapsed_time": "2:45:59", "remaining_time": "3:57:33"}
{"current_steps": 1580, "total_steps": 3829, "loss": 0.2749, "lr": 2.924350700301257e-05, "epoch": 2.8884826325411335, "percentage": 41.26, "elapsed_time": "2:46:35", "remaining_time": "3:57:08"}
{"current_steps": 1585, "total_steps": 3829, "loss": 0.283, "lr": 2.9162565969151932e-05, "epoch": 2.8976234003656307, "percentage": 41.39, "elapsed_time": "2:47:08", "remaining_time": "3:56:37"}
{"current_steps": 1590, "total_steps": 3829, "loss": 0.2791, "lr": 2.9081434553429165e-05, "epoch": 2.906764168190128, "percentage": 41.53, "elapsed_time": "2:47:37", "remaining_time": "3:56:02"}
{"current_steps": 1595, "total_steps": 3829, "loss": 0.2678, "lr": 2.900011444161111e-05, "epoch": 2.915904936014625, "percentage": 41.66, "elapsed_time": "2:48:11", "remaining_time": "3:55:34"}
{"current_steps": 1600, "total_steps": 3829, "loss": 0.281, "lr": 2.8918607323385403e-05, "epoch": 2.9250457038391224, "percentage": 41.79, "elapsed_time": "2:48:41", "remaining_time": "3:55:00"}
{"current_steps": 1605, "total_steps": 3829, "loss": 0.2849, "lr": 2.883691489232531e-05, "epoch": 2.9341864716636197, "percentage": 41.92, "elapsed_time": "2:49:14", "remaining_time": "3:54:30"}
{"current_steps": 1610, "total_steps": 3829, "loss": 0.2697, "lr": 2.875503884585461e-05, "epoch": 2.943327239488117, "percentage": 42.05, "elapsed_time": "2:49:44", "remaining_time": "3:53:56"}
{"current_steps": 1615, "total_steps": 3829, "loss": 0.2478, "lr": 2.8672980885212246e-05, "epoch": 2.952468007312614, "percentage": 42.18, "elapsed_time": "2:50:13", "remaining_time": "3:53:21"}
{"current_steps": 1620, "total_steps": 3829, "loss": 0.2735, "lr": 2.859074271541704e-05, "epoch": 2.9616087751371114, "percentage": 42.31, "elapsed_time": "2:50:42", "remaining_time": "3:52:46"}
{"current_steps": 1625, "total_steps": 3829, "loss": 0.2658, "lr": 2.8508326045232224e-05, "epoch": 2.9707495429616086, "percentage": 42.44, "elapsed_time": "2:51:14", "remaining_time": "3:52:15"}
{"current_steps": 1630, "total_steps": 3829, "loss": 0.2699, "lr": 2.842573258712997e-05, "epoch": 2.979890310786106, "percentage": 42.57, "elapsed_time": "2:51:45", "remaining_time": "3:51:43"}
{"current_steps": 1635, "total_steps": 3829, "loss": 0.2793, "lr": 2.834296405725576e-05, "epoch": 2.989031078610603, "percentage": 42.7, "elapsed_time": "2:52:17", "remaining_time": "3:51:11"}
{"current_steps": 1640, "total_steps": 3829, "loss": 0.2832, "lr": 2.826002217539279e-05, "epoch": 2.998171846435101, "percentage": 42.83, "elapsed_time": "2:52:52", "remaining_time": "3:50:44"}
{"current_steps": 1645, "total_steps": 3829, "loss": 0.2612, "lr": 2.8176908664926173e-05, "epoch": 3.0073126142595976, "percentage": 42.96, "elapsed_time": "2:53:24", "remaining_time": "3:50:14"}
{"current_steps": 1650, "total_steps": 3829, "loss": 0.2567, "lr": 2.8093625252807188e-05, "epoch": 3.016453382084095, "percentage": 43.09, "elapsed_time": "2:53:54", "remaining_time": "3:49:39"}
{"current_steps": 1655, "total_steps": 3829, "loss": 0.2679, "lr": 2.801017366951735e-05, "epoch": 3.025594149908592, "percentage": 43.22, "elapsed_time": "2:54:28", "remaining_time": "3:49:11"}
{"current_steps": 1660, "total_steps": 3829, "loss": 0.2532, "lr": 2.7926555649032475e-05, "epoch": 3.03473491773309, "percentage": 43.35, "elapsed_time": "2:54:57", "remaining_time": "3:48:36"}
{"current_steps": 1665, "total_steps": 3829, "loss": 0.2541, "lr": 2.7842772928786654e-05, "epoch": 3.043875685557587, "percentage": 43.48, "elapsed_time": "2:55:32", "remaining_time": "3:48:09"}
{"current_steps": 1670, "total_steps": 3829, "loss": 0.252, "lr": 2.775882724963614e-05, "epoch": 3.0530164533820843, "percentage": 43.61, "elapsed_time": "2:56:01", "remaining_time": "3:47:34"}
{"current_steps": 1675, "total_steps": 3829, "loss": 0.2401, "lr": 2.7674720355823192e-05, "epoch": 3.0621572212065815, "percentage": 43.75, "elapsed_time": "2:56:31", "remaining_time": "3:47:00"}
{"current_steps": 1680, "total_steps": 3829, "loss": 0.2572, "lr": 2.759045399493981e-05, "epoch": 3.0712979890310788, "percentage": 43.88, "elapsed_time": "2:57:08", "remaining_time": "3:46:36"}
{"current_steps": 1685, "total_steps": 3829, "loss": 0.2474, "lr": 2.750602991789145e-05, "epoch": 3.080438756855576, "percentage": 44.01, "elapsed_time": "2:57:39", "remaining_time": "3:46:02"}
{"current_steps": 1690, "total_steps": 3829, "loss": 0.276, "lr": 2.7421449878860633e-05, "epoch": 3.0895795246800732, "percentage": 44.14, "elapsed_time": "2:58:09", "remaining_time": "3:45:29"}
{"current_steps": 1695, "total_steps": 3829, "loss": 0.243, "lr": 2.7336715635270468e-05, "epoch": 3.0987202925045705, "percentage": 44.27, "elapsed_time": "2:58:38", "remaining_time": "3:44:53"}
{"current_steps": 1700, "total_steps": 3829, "loss": 0.2675, "lr": 2.7251828947748192e-05, "epoch": 3.1078610603290677, "percentage": 44.4, "elapsed_time": "2:59:09", "remaining_time": "3:44:21"}
{"current_steps": 1705, "total_steps": 3829, "loss": 0.2371, "lr": 2.7166791580088533e-05, "epoch": 3.117001828153565, "percentage": 44.53, "elapsed_time": "2:59:38", "remaining_time": "3:43:47"}
{"current_steps": 1710, "total_steps": 3829, "loss": 0.2499, "lr": 2.7081605299217108e-05, "epoch": 3.126142595978062, "percentage": 44.66, "elapsed_time": "3:00:09", "remaining_time": "3:43:14"}
{"current_steps": 1715, "total_steps": 3829, "loss": 0.2336, "lr": 2.699627187515366e-05, "epoch": 3.1352833638025595, "percentage": 44.79, "elapsed_time": "3:00:38", "remaining_time": "3:42:39"}
{"current_steps": 1720, "total_steps": 3829, "loss": 0.243, "lr": 2.6910793080975327e-05, "epoch": 3.1444241316270567, "percentage": 44.92, "elapsed_time": "3:01:05", "remaining_time": "3:42:03"}
{"current_steps": 1725, "total_steps": 3829, "loss": 0.2415, "lr": 2.682517069277977e-05, "epoch": 3.153564899451554, "percentage": 45.05, "elapsed_time": "3:01:40", "remaining_time": "3:41:35"}
{"current_steps": 1730, "total_steps": 3829, "loss": 0.2613, "lr": 2.673940648964828e-05, "epoch": 3.162705667276051, "percentage": 45.18, "elapsed_time": "3:02:13", "remaining_time": "3:41:05"}
{"current_steps": 1735, "total_steps": 3829, "loss": 0.2363, "lr": 2.6653502253608817e-05, "epoch": 3.1718464351005484, "percentage": 45.31, "elapsed_time": "3:02:41", "remaining_time": "3:40:29"}
{"current_steps": 1740, "total_steps": 3829, "loss": 0.2474, "lr": 2.656745976959896e-05, "epoch": 3.1809872029250457, "percentage": 45.44, "elapsed_time": "3:03:13", "remaining_time": "3:39:58"}
{"current_steps": 1745, "total_steps": 3829, "loss": 0.2389, "lr": 2.6481280825428862e-05, "epoch": 3.190127970749543, "percentage": 45.57, "elapsed_time": "3:03:45", "remaining_time": "3:39:27"}
{"current_steps": 1750, "total_steps": 3829, "loss": 0.2683, "lr": 2.639496721174405e-05, "epoch": 3.19926873857404, "percentage": 45.7, "elapsed_time": "3:04:12", "remaining_time": "3:38:50"}
{"current_steps": 1755, "total_steps": 3829, "loss": 0.2677, "lr": 2.6308520721988257e-05, "epoch": 3.2084095063985374, "percentage": 45.83, "elapsed_time": "3:04:41", "remaining_time": "3:38:15"}
{"current_steps": 1760, "total_steps": 3829, "loss": 0.2667, "lr": 2.622194315236615e-05, "epoch": 3.2175502742230346, "percentage": 45.97, "elapsed_time": "3:05:08", "remaining_time": "3:37:39"}
{"current_steps": 1765, "total_steps": 3829, "loss": 0.2484, "lr": 2.613523630180599e-05, "epoch": 3.226691042047532, "percentage": 46.1, "elapsed_time": "3:05:41", "remaining_time": "3:37:09"}
{"current_steps": 1770, "total_steps": 3829, "loss": 0.2367, "lr": 2.604840197192227e-05, "epoch": 3.235831809872029, "percentage": 46.23, "elapsed_time": "3:06:15", "remaining_time": "3:36:40"}
{"current_steps": 1775, "total_steps": 3829, "loss": 0.2728, "lr": 2.596144196697829e-05, "epoch": 3.2449725776965264, "percentage": 46.36, "elapsed_time": "3:06:42", "remaining_time": "3:36:03"}
{"current_steps": 1780, "total_steps": 3829, "loss": 0.2687, "lr": 2.587435809384864e-05, "epoch": 3.2541133455210236, "percentage": 46.49, "elapsed_time": "3:07:15", "remaining_time": "3:35:33"}
{"current_steps": 1785, "total_steps": 3829, "loss": 0.2295, "lr": 2.5787152161981666e-05, "epoch": 3.263254113345521, "percentage": 46.62, "elapsed_time": "3:07:47", "remaining_time": "3:35:02"}
{"current_steps": 1790, "total_steps": 3829, "loss": 0.2426, "lr": 2.5699825983361907e-05, "epoch": 3.272394881170018, "percentage": 46.75, "elapsed_time": "3:08:19", "remaining_time": "3:34:30"}
{"current_steps": 1795, "total_steps": 3829, "loss": 0.2469, "lr": 2.5612381372472378e-05, "epoch": 3.2815356489945158, "percentage": 46.88, "elapsed_time": "3:08:45", "remaining_time": "3:33:53"}
{"current_steps": 1800, "total_steps": 3829, "loss": 0.2531, "lr": 2.552482014625694e-05, "epoch": 3.2906764168190126, "percentage": 47.01, "elapsed_time": "3:09:18", "remaining_time": "3:33:23"}
{"current_steps": 1805, "total_steps": 3829, "loss": 0.2593, "lr": 2.5437144124082488e-05, "epoch": 3.2998171846435103, "percentage": 47.14, "elapsed_time": "3:09:46", "remaining_time": "3:32:48"}
{"current_steps": 1810, "total_steps": 3829, "loss": 0.2523, "lr": 2.53493551277012e-05, "epoch": 3.3089579524680075, "percentage": 47.27, "elapsed_time": "3:10:17", "remaining_time": "3:32:15"}
{"current_steps": 1815, "total_steps": 3829, "loss": 0.2414, "lr": 2.5261454981212622e-05, "epoch": 3.3180987202925047, "percentage": 47.4, "elapsed_time": "3:10:54", "remaining_time": "3:31:50"}
{"current_steps": 1820, "total_steps": 3829, "loss": 0.2376, "lr": 2.5173445511025834e-05, "epoch": 3.327239488117002, "percentage": 47.53, "elapsed_time": "3:11:21", "remaining_time": "3:31:13"}
{"current_steps": 1825, "total_steps": 3829, "loss": 0.2729, "lr": 2.5085328545821453e-05, "epoch": 3.3363802559414992, "percentage": 47.66, "elapsed_time": "3:11:48", "remaining_time": "3:30:37"}
{"current_steps": 1830, "total_steps": 3829, "loss": 0.2466, "lr": 2.499710591651366e-05, "epoch": 3.3455210237659965, "percentage": 47.79, "elapsed_time": "3:12:25", "remaining_time": "3:30:11"}
{"current_steps": 1835, "total_steps": 3829, "loss": 0.2583, "lr": 2.4908779456212132e-05, "epoch": 3.3546617915904937, "percentage": 47.92, "elapsed_time": "3:12:59", "remaining_time": "3:29:42"}
{"current_steps": 1840, "total_steps": 3829, "loss": 0.2341, "lr": 2.482035100018399e-05, "epoch": 3.363802559414991, "percentage": 48.05, "elapsed_time": "3:13:28", "remaining_time": "3:29:08"}
{"current_steps": 1845, "total_steps": 3829, "loss": 0.2509, "lr": 2.473182238581564e-05, "epoch": 3.372943327239488, "percentage": 48.18, "elapsed_time": "3:14:00", "remaining_time": "3:28:37"}
{"current_steps": 1850, "total_steps": 3829, "loss": 0.2391, "lr": 2.4643195452574587e-05, "epoch": 3.3820840950639854, "percentage": 48.32, "elapsed_time": "3:14:29", "remaining_time": "3:28:03"}
{"current_steps": 1855, "total_steps": 3829, "loss": 0.2614, "lr": 2.455447204197125e-05, "epoch": 3.3912248628884827, "percentage": 48.45, "elapsed_time": "3:15:02", "remaining_time": "3:27:33"}
{"current_steps": 1860, "total_steps": 3829, "loss": 0.2656, "lr": 2.4465653997520642e-05, "epoch": 3.40036563071298, "percentage": 48.58, "elapsed_time": "3:15:35", "remaining_time": "3:27:03"}
{"current_steps": 1865, "total_steps": 3829, "loss": 0.2713, "lr": 2.4376743164704148e-05, "epoch": 3.409506398537477, "percentage": 48.71, "elapsed_time": "3:16:06", "remaining_time": "3:26:31"}
{"current_steps": 1870, "total_steps": 3829, "loss": 0.2461, "lr": 2.4287741390931096e-05, "epoch": 3.4186471663619744, "percentage": 48.84, "elapsed_time": "3:16:34", "remaining_time": "3:25:56"}
{"current_steps": 1875, "total_steps": 3829, "loss": 0.2409, "lr": 2.4198650525500402e-05, "epoch": 3.4277879341864717, "percentage": 48.97, "elapsed_time": "3:17:05", "remaining_time": "3:25:23"}
{"current_steps": 1880, "total_steps": 3829, "loss": 0.2235, "lr": 2.4109472419562175e-05, "epoch": 3.436928702010969, "percentage": 49.1, "elapsed_time": "3:17:33", "remaining_time": "3:24:48"}
{"current_steps": 1885, "total_steps": 3829, "loss": 0.2479, "lr": 2.4020208926079206e-05, "epoch": 3.446069469835466, "percentage": 49.23, "elapsed_time": "3:18:01", "remaining_time": "3:24:13"}
{"current_steps": 1890, "total_steps": 3829, "loss": 0.2651, "lr": 2.3930861899788495e-05, "epoch": 3.4552102376599634, "percentage": 49.36, "elapsed_time": "3:18:29", "remaining_time": "3:23:38"}
{"current_steps": 1895, "total_steps": 3829, "loss": 0.2595, "lr": 2.3841433197162706e-05, "epoch": 3.4643510054844606, "percentage": 49.49, "elapsed_time": "3:19:00", "remaining_time": "3:23:06"}
{"current_steps": 1900, "total_steps": 3829, "loss": 0.2568, "lr": 2.3751924676371588e-05, "epoch": 3.473491773308958, "percentage": 49.62, "elapsed_time": "3:19:28", "remaining_time": "3:22:31"}
{"current_steps": 1905, "total_steps": 3829, "loss": 0.2491, "lr": 2.3662338197243378e-05, "epoch": 3.482632541133455, "percentage": 49.75, "elapsed_time": "3:19:59", "remaining_time": "3:21:59"}
{"current_steps": 1910, "total_steps": 3829, "loss": 0.2519, "lr": 2.357267562122614e-05, "epoch": 3.4917733089579523, "percentage": 49.88, "elapsed_time": "3:20:32", "remaining_time": "3:21:28"}
{"current_steps": 1915, "total_steps": 3829, "loss": 0.2605, "lr": 2.3482938811349095e-05, "epoch": 3.5009140767824496, "percentage": 50.01, "elapsed_time": "3:21:05", "remaining_time": "3:20:59"}
{"current_steps": 1920, "total_steps": 3829, "loss": 0.2441, "lr": 2.3393129632183932e-05, "epoch": 3.510054844606947, "percentage": 50.14, "elapsed_time": "3:21:35", "remaining_time": "3:20:26"}
{"current_steps": 1925, "total_steps": 3829, "loss": 0.2671, "lr": 2.3303249949806014e-05, "epoch": 3.519195612431444, "percentage": 50.27, "elapsed_time": "3:22:08", "remaining_time": "3:19:55"}
{"current_steps": 1930, "total_steps": 3829, "loss": 0.2549, "lr": 2.3213301631755664e-05, "epoch": 3.5283363802559418, "percentage": 50.4, "elapsed_time": "3:22:43", "remaining_time": "3:19:28"}
{"current_steps": 1935, "total_steps": 3829, "loss": 0.2437, "lr": 2.312328654699931e-05, "epoch": 3.5374771480804386, "percentage": 50.54, "elapsed_time": "3:23:13", "remaining_time": "3:18:55"}
{"current_steps": 1940, "total_steps": 3829, "loss": 0.246, "lr": 2.303320656589069e-05, "epoch": 3.5466179159049362, "percentage": 50.67, "elapsed_time": "3:23:47", "remaining_time": "3:18:26"}
{"current_steps": 1945, "total_steps": 3829, "loss": 0.2356, "lr": 2.2943063560131967e-05, "epoch": 3.555758683729433, "percentage": 50.8, "elapsed_time": "3:24:21", "remaining_time": "3:17:56"}
{"current_steps": 1950, "total_steps": 3829, "loss": 0.2686, "lr": 2.2852859402734843e-05, "epoch": 3.5648994515539307, "percentage": 50.93, "elapsed_time": "3:24:57", "remaining_time": "3:17:30"}
{"current_steps": 1955, "total_steps": 3829, "loss": 0.2375, "lr": 2.2762595967981643e-05, "epoch": 3.5740402193784275, "percentage": 51.06, "elapsed_time": "3:25:29", "remaining_time": "3:16:58"}
{"current_steps": 1960, "total_steps": 3829, "loss": 0.2584, "lr": 2.2672275131386375e-05, "epoch": 3.583180987202925, "percentage": 51.19, "elapsed_time": "3:26:00", "remaining_time": "3:16:26"}
{"current_steps": 1965, "total_steps": 3829, "loss": 0.2701, "lr": 2.258189876965575e-05, "epoch": 3.5923217550274225, "percentage": 51.32, "elapsed_time": "3:26:37", "remaining_time": "3:15:59"}
{"current_steps": 1970, "total_steps": 3829, "loss": 0.2749, "lr": 2.2491468760650205e-05, "epoch": 3.6014625228519197, "percentage": 51.45, "elapsed_time": "3:27:10", "remaining_time": "3:15:29"}
{"current_steps": 1975, "total_steps": 3829, "loss": 0.2458, "lr": 2.2400986983344834e-05, "epoch": 3.610603290676417, "percentage": 51.58, "elapsed_time": "3:27:36", "remaining_time": "3:14:53"}
{"current_steps": 1980, "total_steps": 3829, "loss": 0.2732, "lr": 2.2310455317790444e-05, "epoch": 3.619744058500914, "percentage": 51.71, "elapsed_time": "3:28:13", "remaining_time": "3:14:26"}
{"current_steps": 1985, "total_steps": 3829, "loss": 0.274, "lr": 2.221987564507438e-05, "epoch": 3.6288848263254114, "percentage": 51.84, "elapsed_time": "3:28:45", "remaining_time": "3:13:55"}
{"current_steps": 1990, "total_steps": 3829, "loss": 0.2699, "lr": 2.2129249847281513e-05, "epoch": 3.6380255941499087, "percentage": 51.97, "elapsed_time": "3:29:19", "remaining_time": "3:13:26"}
{"current_steps": 1995, "total_steps": 3829, "loss": 0.2753, "lr": 2.2038579807455115e-05, "epoch": 3.647166361974406, "percentage": 52.1, "elapsed_time": "3:29:55", "remaining_time": "3:12:58"}
{"current_steps": 2000, "total_steps": 3829, "loss": 0.2811, "lr": 2.1947867409557713e-05, "epoch": 3.656307129798903, "percentage": 52.23, "elapsed_time": "3:30:26", "remaining_time": "3:12:26"}
{"current_steps": 2005, "total_steps": 3829, "loss": 0.2575, "lr": 2.1857114538431973e-05, "epoch": 3.6654478976234004, "percentage": 52.36, "elapsed_time": "3:30:59", "remaining_time": "3:11:57"}
{"current_steps": 2010, "total_steps": 3829, "loss": 0.2619, "lr": 2.1766323079761523e-05, "epoch": 3.6745886654478976, "percentage": 52.49, "elapsed_time": "3:31:31", "remaining_time": "3:11:25"}
{"current_steps": 2015, "total_steps": 3829, "loss": 0.2542, "lr": 2.1675494920031768e-05, "epoch": 3.683729433272395, "percentage": 52.62, "elapsed_time": "3:32:04", "remaining_time": "3:10:54"}
{"current_steps": 2020, "total_steps": 3829, "loss": 0.2826, "lr": 2.1584631946490683e-05, "epoch": 3.692870201096892, "percentage": 52.76, "elapsed_time": "3:32:39", "remaining_time": "3:10:26"}
{"current_steps": 2025, "total_steps": 3829, "loss": 0.2514, "lr": 2.149373604710964e-05, "epoch": 3.7020109689213894, "percentage": 52.89, "elapsed_time": "3:33:12", "remaining_time": "3:09:56"}
{"current_steps": 2030, "total_steps": 3829, "loss": 0.2675, "lr": 2.1402809110544118e-05, "epoch": 3.7111517367458866, "percentage": 53.02, "elapsed_time": "3:33:41", "remaining_time": "3:09:22"}
{"current_steps": 2035, "total_steps": 3829, "loss": 0.2692, "lr": 2.1311853026094537e-05, "epoch": 3.720292504570384, "percentage": 53.15, "elapsed_time": "3:34:15", "remaining_time": "3:08:52"}
{"current_steps": 2040, "total_steps": 3829, "loss": 0.2385, "lr": 2.1220869683666906e-05, "epoch": 3.729433272394881, "percentage": 53.28, "elapsed_time": "3:34:46", "remaining_time": "3:08:20"}
{"current_steps": 2045, "total_steps": 3829, "loss": 0.2565, "lr": 2.112986097373365e-05, "epoch": 3.7385740402193783, "percentage": 53.41, "elapsed_time": "3:35:16", "remaining_time": "3:07:47"}
{"current_steps": 2050, "total_steps": 3829, "loss": 0.2472, "lr": 2.1038828787294257e-05, "epoch": 3.7477148080438756, "percentage": 53.54, "elapsed_time": "3:35:53", "remaining_time": "3:07:21"}
{"current_steps": 2055, "total_steps": 3829, "loss": 0.2395, "lr": 2.094777501583605e-05, "epoch": 3.756855575868373, "percentage": 53.67, "elapsed_time": "3:36:25", "remaining_time": "3:06:49"}
{"current_steps": 2060, "total_steps": 3829, "loss": 0.2551, "lr": 2.0856701551294805e-05, "epoch": 3.76599634369287, "percentage": 53.8, "elapsed_time": "3:36:56", "remaining_time": "3:06:17"}
{"current_steps": 2065, "total_steps": 3829, "loss": 0.2461, "lr": 2.076561028601552e-05, "epoch": 3.7751371115173673, "percentage": 53.93, "elapsed_time": "3:37:26", "remaining_time": "3:05:45"}
{"current_steps": 2070, "total_steps": 3829, "loss": 0.2392, "lr": 2.0674503112713036e-05, "epoch": 3.7842778793418645, "percentage": 54.06, "elapsed_time": "3:37:59", "remaining_time": "3:05:14"}
{"current_steps": 2075, "total_steps": 3829, "loss": 0.2753, "lr": 2.0583381924432763e-05, "epoch": 3.7934186471663622, "percentage": 54.19, "elapsed_time": "3:38:36", "remaining_time": "3:04:47"}
{"current_steps": 2080, "total_steps": 3829, "loss": 0.2488, "lr": 2.0492248614511288e-05, "epoch": 3.802559414990859, "percentage": 54.32, "elapsed_time": "3:39:06", "remaining_time": "3:04:14"}
{"current_steps": 2085, "total_steps": 3829, "loss": 0.248, "lr": 2.0401105076537088e-05, "epoch": 3.8117001828153567, "percentage": 54.45, "elapsed_time": "3:39:36", "remaining_time": "3:03:41"}
{"current_steps": 2090, "total_steps": 3829, "loss": 0.2666, "lr": 2.030995320431115e-05, "epoch": 3.8208409506398535, "percentage": 54.58, "elapsed_time": "3:40:05", "remaining_time": "3:03:07"}
{"current_steps": 2095, "total_steps": 3829, "loss": 0.2596, "lr": 2.021879489180762e-05, "epoch": 3.829981718464351, "percentage": 54.71, "elapsed_time": "3:40:39", "remaining_time": "3:02:38"}
{"current_steps": 2100, "total_steps": 3829, "loss": 0.2696, "lr": 2.0127632033134493e-05, "epoch": 3.839122486288848, "percentage": 54.84, "elapsed_time": "3:41:10", "remaining_time": "3:02:06"}
{"current_steps": 2105, "total_steps": 3829, "loss": 0.2507, "lr": 2.0036466522494192e-05, "epoch": 3.8482632541133457, "percentage": 54.98, "elapsed_time": "3:41:38", "remaining_time": "3:01:31"}
{"current_steps": 2110, "total_steps": 3829, "loss": 0.228, "lr": 1.9945300254144267e-05, "epoch": 3.857404021937843, "percentage": 55.11, "elapsed_time": "3:42:10", "remaining_time": "3:01:00"}
{"current_steps": 2115, "total_steps": 3829, "loss": 0.2429, "lr": 1.985413512235799e-05, "epoch": 3.86654478976234, "percentage": 55.24, "elapsed_time": "3:42:41", "remaining_time": "3:00:28"}
{"current_steps": 2120, "total_steps": 3829, "loss": 0.2623, "lr": 1.9762973021385044e-05, "epoch": 3.8756855575868374, "percentage": 55.37, "elapsed_time": "3:43:17", "remaining_time": "2:59:59"}
{"current_steps": 2125, "total_steps": 3829, "loss": 0.2477, "lr": 1.9671815845412107e-05, "epoch": 3.8848263254113347, "percentage": 55.5, "elapsed_time": "3:43:47", "remaining_time": "2:59:27"}
{"current_steps": 2130, "total_steps": 3829, "loss": 0.2775, "lr": 1.9580665488523564e-05, "epoch": 3.893967093235832, "percentage": 55.63, "elapsed_time": "3:44:19", "remaining_time": "2:58:56"}
{"current_steps": 2135, "total_steps": 3829, "loss": 0.2596, "lr": 1.948952384466206e-05, "epoch": 3.903107861060329, "percentage": 55.76, "elapsed_time": "3:44:48", "remaining_time": "2:58:22"}
{"current_steps": 2140, "total_steps": 3829, "loss": 0.2581, "lr": 1.9398392807589244e-05, "epoch": 3.9122486288848264, "percentage": 55.89, "elapsed_time": "3:45:21", "remaining_time": "2:57:52"}
{"current_steps": 2145, "total_steps": 3829, "loss": 0.2619, "lr": 1.9307274270846357e-05, "epoch": 3.9213893967093236, "percentage": 56.02, "elapsed_time": "3:45:56", "remaining_time": "2:57:23"}
{"current_steps": 2150, "total_steps": 3829, "loss": 0.2258, "lr": 1.921617012771489e-05, "epoch": 3.930530164533821, "percentage": 56.15, "elapsed_time": "3:46:23", "remaining_time": "2:56:48"}
{"current_steps": 2155, "total_steps": 3829, "loss": 0.2642, "lr": 1.9125082271177295e-05, "epoch": 3.939670932358318, "percentage": 56.28, "elapsed_time": "3:46:56", "remaining_time": "2:56:17"}
{"current_steps": 2160, "total_steps": 3829, "loss": 0.2447, "lr": 1.9034012593877578e-05, "epoch": 3.9488117001828154, "percentage": 56.41, "elapsed_time": "3:47:30", "remaining_time": "2:55:47"}
{"current_steps": 2165, "total_steps": 3829, "loss": 0.2587, "lr": 1.894296298808206e-05, "epoch": 3.9579524680073126, "percentage": 56.54, "elapsed_time": "3:48:02", "remaining_time": "2:55:16"}
{"current_steps": 2170, "total_steps": 3829, "loss": 0.2676, "lr": 1.8851935345639957e-05, "epoch": 3.96709323583181, "percentage": 56.67, "elapsed_time": "3:48:35", "remaining_time": "2:54:45"}
{"current_steps": 2175, "total_steps": 3829, "loss": 0.2734, "lr": 1.876093155794417e-05, "epoch": 3.976234003656307, "percentage": 56.8, "elapsed_time": "3:49:05", "remaining_time": "2:54:12"}
{"current_steps": 2180, "total_steps": 3829, "loss": 0.2696, "lr": 1.866995351589191e-05, "epoch": 3.9853747714808043, "percentage": 56.93, "elapsed_time": "3:49:38", "remaining_time": "2:53:42"}
{"current_steps": 2185, "total_steps": 3829, "loss": 0.2531, "lr": 1.8579003109845473e-05, "epoch": 3.9945155393053016, "percentage": 57.06, "elapsed_time": "3:50:08", "remaining_time": "2:53:09"}
{"current_steps": 2190, "total_steps": 3829, "loss": 0.2371, "lr": 1.848808222959289e-05, "epoch": 4.003656307129799, "percentage": 57.2, "elapsed_time": "3:50:41", "remaining_time": "2:52:39"}
{"current_steps": 2195, "total_steps": 3829, "loss": 0.1997, "lr": 1.8397192764308723e-05, "epoch": 4.012797074954296, "percentage": 57.33, "elapsed_time": "3:51:13", "remaining_time": "2:52:07"}
{"current_steps": 2200, "total_steps": 3829, "loss": 0.2201, "lr": 1.8306336602514786e-05, "epoch": 4.021937842778794, "percentage": 57.46, "elapsed_time": "3:51:49", "remaining_time": "2:51:39"}
{"current_steps": 2205, "total_steps": 3829, "loss": 0.2303, "lr": 1.8215515632040884e-05, "epoch": 4.0310786106032905, "percentage": 57.59, "elapsed_time": "3:52:15", "remaining_time": "2:51:03"}
{"current_steps": 2210, "total_steps": 3829, "loss": 0.2312, "lr": 1.8124731739985632e-05, "epoch": 4.040219378427788, "percentage": 57.72, "elapsed_time": "3:52:53", "remaining_time": "2:50:36"}
{"current_steps": 2215, "total_steps": 3829, "loss": 0.2359, "lr": 1.803398681267722e-05, "epoch": 4.049360146252285, "percentage": 57.85, "elapsed_time": "3:53:25", "remaining_time": "2:50:05"}
{"current_steps": 2220, "total_steps": 3829, "loss": 0.2346, "lr": 1.7943282735634212e-05, "epoch": 4.058500914076783, "percentage": 57.98, "elapsed_time": "3:53:53", "remaining_time": "2:49:30"}
{"current_steps": 2225, "total_steps": 3829, "loss": 0.2603, "lr": 1.7852621393526367e-05, "epoch": 4.0676416819012795, "percentage": 58.11, "elapsed_time": "3:54:25", "remaining_time": "2:49:00"}
{"current_steps": 2230, "total_steps": 3829, "loss": 0.2116, "lr": 1.7762004670135508e-05, "epoch": 4.076782449725777, "percentage": 58.24, "elapsed_time": "3:54:56", "remaining_time": "2:48:27"}
{"current_steps": 2235, "total_steps": 3829, "loss": 0.2165, "lr": 1.7671434448316346e-05, "epoch": 4.085923217550274, "percentage": 58.37, "elapsed_time": "3:55:25", "remaining_time": "2:47:54"}
{"current_steps": 2240, "total_steps": 3829, "loss": 0.2253, "lr": 1.7580912609957373e-05, "epoch": 4.095063985374772, "percentage": 58.5, "elapsed_time": "3:55:53", "remaining_time": "2:47:20"}
{"current_steps": 2245, "total_steps": 3829, "loss": 0.2176, "lr": 1.749044103594177e-05, "epoch": 4.1042047531992685, "percentage": 58.63, "elapsed_time": "3:56:25", "remaining_time": "2:46:48"}
{"current_steps": 2250, "total_steps": 3829, "loss": 0.2119, "lr": 1.74000216061083e-05, "epoch": 4.113345521023766, "percentage": 58.76, "elapsed_time": "3:56:58", "remaining_time": "2:46:18"}
{"current_steps": 2255, "total_steps": 3829, "loss": 0.2433, "lr": 1.7309656199212274e-05, "epoch": 4.122486288848263, "percentage": 58.89, "elapsed_time": "3:57:29", "remaining_time": "2:45:46"}
{"current_steps": 2260, "total_steps": 3829, "loss": 0.2257, "lr": 1.721934669288649e-05, "epoch": 4.131627056672761, "percentage": 59.02, "elapsed_time": "3:57:56", "remaining_time": "2:45:11"}
{"current_steps": 2265, "total_steps": 3829, "loss": 0.2343, "lr": 1.7129094963602237e-05, "epoch": 4.140767824497257, "percentage": 59.15, "elapsed_time": "3:58:29", "remaining_time": "2:44:41"}
{"current_steps": 2270, "total_steps": 3829, "loss": 0.2658, "lr": 1.7038902886630304e-05, "epoch": 4.149908592321755, "percentage": 59.28, "elapsed_time": "3:59:01", "remaining_time": "2:44:09"}
{"current_steps": 2275, "total_steps": 3829, "loss": 0.2417, "lr": 1.6948772336002015e-05, "epoch": 4.159049360146252, "percentage": 59.41, "elapsed_time": "3:59:31", "remaining_time": "2:43:36"}
{"current_steps": 2280, "total_steps": 3829, "loss": 0.2381, "lr": 1.6858705184470266e-05, "epoch": 4.16819012797075, "percentage": 59.55, "elapsed_time": "3:59:59", "remaining_time": "2:43:03"}
{"current_steps": 2285, "total_steps": 3829, "loss": 0.2488, "lr": 1.676870330347064e-05, "epoch": 4.177330895795246, "percentage": 59.68, "elapsed_time": "4:00:35", "remaining_time": "2:42:33"}
{"current_steps": 2290, "total_steps": 3829, "loss": 0.2478, "lr": 1.6678768563082546e-05, "epoch": 4.186471663619744, "percentage": 59.81, "elapsed_time": "4:01:05", "remaining_time": "2:42:01"}
{"current_steps": 2295, "total_steps": 3829, "loss": 0.2348, "lr": 1.658890283199027e-05, "epoch": 4.195612431444241, "percentage": 59.94, "elapsed_time": "4:01:43", "remaining_time": "2:41:34"}
{"current_steps": 2300, "total_steps": 3829, "loss": 0.2493, "lr": 1.6499107977444256e-05, "epoch": 4.204753199268739, "percentage": 60.07, "elapsed_time": "4:02:15", "remaining_time": "2:41:03"}
{"current_steps": 2305, "total_steps": 3829, "loss": 0.24, "lr": 1.640938586522224e-05, "epoch": 4.213893967093236, "percentage": 60.2, "elapsed_time": "4:02:48", "remaining_time": "2:40:32"}
{"current_steps": 2310, "total_steps": 3829, "loss": 0.234, "lr": 1.6319738359590514e-05, "epoch": 4.223034734917733, "percentage": 60.33, "elapsed_time": "4:03:18", "remaining_time": "2:39:59"}
{"current_steps": 2315, "total_steps": 3829, "loss": 0.2487, "lr": 1.623016732326515e-05, "epoch": 4.232175502742231, "percentage": 60.46, "elapsed_time": "4:03:47", "remaining_time": "2:39:26"}
{"current_steps": 2320, "total_steps": 3829, "loss": 0.2349, "lr": 1.6140674617373355e-05, "epoch": 4.2413162705667276, "percentage": 60.59, "elapsed_time": "4:04:17", "remaining_time": "2:38:53"}
{"current_steps": 2325, "total_steps": 3829, "loss": 0.2401, "lr": 1.605126210141475e-05, "epoch": 4.250457038391225, "percentage": 60.72, "elapsed_time": "4:04:48", "remaining_time": "2:38:21"}
{"current_steps": 2330, "total_steps": 3829, "loss": 0.227, "lr": 1.5961931633222768e-05, "epoch": 4.259597806215722, "percentage": 60.85, "elapsed_time": "4:05:16", "remaining_time": "2:37:47"}
{"current_steps": 2335, "total_steps": 3829, "loss": 0.2595, "lr": 1.5872685068926005e-05, "epoch": 4.26873857404022, "percentage": 60.98, "elapsed_time": "4:05:52", "remaining_time": "2:37:18"}
{"current_steps": 2340, "total_steps": 3829, "loss": 0.2248, "lr": 1.5783524262909707e-05, "epoch": 4.2778793418647165, "percentage": 61.11, "elapsed_time": "4:06:22", "remaining_time": "2:36:46"}
{"current_steps": 2345, "total_steps": 3829, "loss": 0.2382, "lr": 1.5694451067777225e-05, "epoch": 4.287020109689214, "percentage": 61.24, "elapsed_time": "4:06:54", "remaining_time": "2:36:15"}
{"current_steps": 2350, "total_steps": 3829, "loss": 0.2275, "lr": 1.560546733431148e-05, "epoch": 4.296160877513711, "percentage": 61.37, "elapsed_time": "4:07:24", "remaining_time": "2:35:42"}
{"current_steps": 2355, "total_steps": 3829, "loss": 0.2451, "lr": 1.551657491143656e-05, "epoch": 4.305301645338209, "percentage": 61.5, "elapsed_time": "4:07:53", "remaining_time": "2:35:09"}
{"current_steps": 2360, "total_steps": 3829, "loss": 0.2253, "lr": 1.542777564617927e-05, "epoch": 4.3144424131627055, "percentage": 61.63, "elapsed_time": "4:08:23", "remaining_time": "2:34:36"}
{"current_steps": 2365, "total_steps": 3829, "loss": 0.226, "lr": 1.5339071383630787e-05, "epoch": 4.323583180987203, "percentage": 61.77, "elapsed_time": "4:08:52", "remaining_time": "2:34:03"}
{"current_steps": 2370, "total_steps": 3829, "loss": 0.2206, "lr": 1.525046396690826e-05, "epoch": 4.3327239488117, "percentage": 61.9, "elapsed_time": "4:09:22", "remaining_time": "2:33:31"}
{"current_steps": 2375, "total_steps": 3829, "loss": 0.2543, "lr": 1.5161955237116592e-05, "epoch": 4.341864716636198, "percentage": 62.03, "elapsed_time": "4:09:56", "remaining_time": "2:33:00"}
{"current_steps": 2380, "total_steps": 3829, "loss": 0.2364, "lr": 1.5073547033310134e-05, "epoch": 4.3510054844606945, "percentage": 62.16, "elapsed_time": "4:10:29", "remaining_time": "2:32:30"}
{"current_steps": 2385, "total_steps": 3829, "loss": 0.2165, "lr": 1.4985241192454477e-05, "epoch": 4.360146252285192, "percentage": 62.29, "elapsed_time": "4:11:00", "remaining_time": "2:31:58"}
{"current_steps": 2390, "total_steps": 3829, "loss": 0.2591, "lr": 1.489703954938829e-05, "epoch": 4.369287020109689, "percentage": 62.42, "elapsed_time": "4:11:33", "remaining_time": "2:31:27"}
{"current_steps": 2395, "total_steps": 3829, "loss": 0.2161, "lr": 1.480894393678522e-05, "epoch": 4.378427787934187, "percentage": 62.55, "elapsed_time": "4:11:58", "remaining_time": "2:30:52"}
{"current_steps": 2400, "total_steps": 3829, "loss": 0.2414, "lr": 1.472095618511577e-05, "epoch": 4.387568555758683, "percentage": 62.68, "elapsed_time": "4:12:24", "remaining_time": "2:30:17"}
{"current_steps": 2405, "total_steps": 3829, "loss": 0.2202, "lr": 1.4633078122609283e-05, "epoch": 4.396709323583181, "percentage": 62.81, "elapsed_time": "4:12:53", "remaining_time": "2:29:44"}
{"current_steps": 2410, "total_steps": 3829, "loss": 0.2309, "lr": 1.4545311575215966e-05, "epoch": 4.405850091407678, "percentage": 62.94, "elapsed_time": "4:13:26", "remaining_time": "2:29:13"}
{"current_steps": 2415, "total_steps": 3829, "loss": 0.2276, "lr": 1.4457658366568925e-05, "epoch": 4.414990859232176, "percentage": 63.07, "elapsed_time": "4:13:57", "remaining_time": "2:28:41"}
{"current_steps": 2420, "total_steps": 3829, "loss": 0.2467, "lr": 1.4370120317946312e-05, "epoch": 4.424131627056672, "percentage": 63.2, "elapsed_time": "4:14:28", "remaining_time": "2:28:09"}
{"current_steps": 2425, "total_steps": 3829, "loss": 0.2268, "lr": 1.4282699248233436e-05, "epoch": 4.43327239488117, "percentage": 63.33, "elapsed_time": "4:14:56", "remaining_time": "2:27:36"}
{"current_steps": 2430, "total_steps": 3829, "loss": 0.2207, "lr": 1.4195396973884998e-05, "epoch": 4.442413162705667, "percentage": 63.46, "elapsed_time": "4:15:24", "remaining_time": "2:27:02"}
{"current_steps": 2435, "total_steps": 3829, "loss": 0.2333, "lr": 1.4108215308887352e-05, "epoch": 4.451553930530165, "percentage": 63.59, "elapsed_time": "4:15:57", "remaining_time": "2:26:32"}
{"current_steps": 2440, "total_steps": 3829, "loss": 0.2345, "lr": 1.4021156064720783e-05, "epoch": 4.460694698354661, "percentage": 63.72, "elapsed_time": "4:16:34", "remaining_time": "2:26:03"}
{"current_steps": 2445, "total_steps": 3829, "loss": 0.2382, "lr": 1.3934221050321904e-05, "epoch": 4.469835466179159, "percentage": 63.85, "elapsed_time": "4:17:06", "remaining_time": "2:25:32"}
{"current_steps": 2450, "total_steps": 3829, "loss": 0.2247, "lr": 1.3847412072046056e-05, "epoch": 4.478976234003657, "percentage": 63.99, "elapsed_time": "4:17:40", "remaining_time": "2:25:01"}
{"current_steps": 2455, "total_steps": 3829, "loss": 0.2209, "lr": 1.376073093362977e-05, "epoch": 4.4881170018281535, "percentage": 64.12, "elapsed_time": "4:18:13", "remaining_time": "2:24:31"}
{"current_steps": 2460, "total_steps": 3829, "loss": 0.2551, "lr": 1.3674179436153278e-05, "epoch": 4.497257769652651, "percentage": 64.25, "elapsed_time": "4:18:49", "remaining_time": "2:24:02"}
{"current_steps": 2465, "total_steps": 3829, "loss": 0.238, "lr": 1.3587759378003118e-05, "epoch": 4.506398537477148, "percentage": 64.38, "elapsed_time": "4:19:23", "remaining_time": "2:23:32"}
{"current_steps": 2470, "total_steps": 3829, "loss": 0.2289, "lr": 1.3501472554834764e-05, "epoch": 4.515539305301646, "percentage": 64.51, "elapsed_time": "4:19:50", "remaining_time": "2:22:58"}
{"current_steps": 2475, "total_steps": 3829, "loss": 0.2403, "lr": 1.3415320759535262e-05, "epoch": 4.5246800731261425, "percentage": 64.64, "elapsed_time": "4:20:22", "remaining_time": "2:22:26"}
{"current_steps": 2480, "total_steps": 3829, "loss": 0.2198, "lr": 1.3329305782186061e-05, "epoch": 4.53382084095064, "percentage": 64.77, "elapsed_time": "4:20:52", "remaining_time": "2:21:54"}
{"current_steps": 2485, "total_steps": 3829, "loss": 0.2794, "lr": 1.3243429410025758e-05, "epoch": 4.542961608775137, "percentage": 64.9, "elapsed_time": "4:21:23", "remaining_time": "2:21:22"}
{"current_steps": 2490, "total_steps": 3829, "loss": 0.2309, "lr": 1.3157693427412985e-05, "epoch": 4.552102376599635, "percentage": 65.03, "elapsed_time": "4:21:55", "remaining_time": "2:20:50"}
{"current_steps": 2495, "total_steps": 3829, "loss": 0.2118, "lr": 1.3072099615789306e-05, "epoch": 4.5612431444241315, "percentage": 65.16, "elapsed_time": "4:22:30", "remaining_time": "2:20:21"}
{"current_steps": 2500, "total_steps": 3829, "loss": 0.2368, "lr": 1.2986649753642263e-05, "epoch": 4.570383912248629, "percentage": 65.29, "elapsed_time": "4:23:00", "remaining_time": "2:19:49"}
{"current_steps": 2505, "total_steps": 3829, "loss": 0.2372, "lr": 1.2901345616468357e-05, "epoch": 4.579524680073126, "percentage": 65.42, "elapsed_time": "4:23:36", "remaining_time": "2:19:19"}
{"current_steps": 2510, "total_steps": 3829, "loss": 0.2341, "lr": 1.281618897673619e-05, "epoch": 4.588665447897624, "percentage": 65.55, "elapsed_time": "4:24:04", "remaining_time": "2:18:46"}
{"current_steps": 2515, "total_steps": 3829, "loss": 0.2369, "lr": 1.2731181603849623e-05, "epoch": 4.5978062157221204, "percentage": 65.68, "elapsed_time": "4:24:35", "remaining_time": "2:18:14"}
{"current_steps": 2520, "total_steps": 3829, "loss": 0.2482, "lr": 1.2646325264111019e-05, "epoch": 4.606946983546618, "percentage": 65.81, "elapsed_time": "4:25:09", "remaining_time": "2:17:44"}
{"current_steps": 2525, "total_steps": 3829, "loss": 0.2405, "lr": 1.2561621720684559e-05, "epoch": 4.616087751371115, "percentage": 65.94, "elapsed_time": "4:25:44", "remaining_time": "2:17:14"}
{"current_steps": 2530, "total_steps": 3829, "loss": 0.2348, "lr": 1.247707273355955e-05, "epoch": 4.625228519195613, "percentage": 66.07, "elapsed_time": "4:26:13", "remaining_time": "2:16:41"}
{"current_steps": 2535, "total_steps": 3829, "loss": 0.2401, "lr": 1.2392680059513928e-05, "epoch": 4.634369287020109, "percentage": 66.21, "elapsed_time": "4:26:46", "remaining_time": "2:16:10"}
{"current_steps": 2540, "total_steps": 3829, "loss": 0.252, "lr": 1.23084454520777e-05, "epoch": 4.643510054844607, "percentage": 66.34, "elapsed_time": "4:27:17", "remaining_time": "2:15:38"}
{"current_steps": 2545, "total_steps": 3829, "loss": 0.2371, "lr": 1.2224370661496554e-05, "epoch": 4.652650822669104, "percentage": 66.47, "elapsed_time": "4:27:49", "remaining_time": "2:15:07"}
{"current_steps": 2550, "total_steps": 3829, "loss": 0.2443, "lr": 1.2140457434695426e-05, "epoch": 4.661791590493602, "percentage": 66.6, "elapsed_time": "4:28:25", "remaining_time": "2:14:37"}
{"current_steps": 2555, "total_steps": 3829, "loss": 0.2192, "lr": 1.2056707515242278e-05, "epoch": 4.670932358318098, "percentage": 66.73, "elapsed_time": "4:28:56", "remaining_time": "2:14:06"}
{"current_steps": 2560, "total_steps": 3829, "loss": 0.2279, "lr": 1.1973122643311834e-05, "epoch": 4.680073126142596, "percentage": 66.86, "elapsed_time": "4:29:28", "remaining_time": "2:13:34"}
{"current_steps": 2565, "total_steps": 3829, "loss": 0.2426, "lr": 1.18897045556494e-05, "epoch": 4.689213893967093, "percentage": 66.99, "elapsed_time": "4:29:57", "remaining_time": "2:13:02"}
{"current_steps": 2570, "total_steps": 3829, "loss": 0.2637, "lr": 1.1806454985534817e-05, "epoch": 4.698354661791591, "percentage": 67.12, "elapsed_time": "4:30:30", "remaining_time": "2:12:31"}
{"current_steps": 2575, "total_steps": 3829, "loss": 0.2401, "lr": 1.1723375662746425e-05, "epoch": 4.707495429616088, "percentage": 67.25, "elapsed_time": "4:30:58", "remaining_time": "2:11:57"}
{"current_steps": 2580, "total_steps": 3829, "loss": 0.2357, "lr": 1.1640468313525153e-05, "epoch": 4.716636197440585, "percentage": 67.38, "elapsed_time": "4:31:35", "remaining_time": "2:11:28"}
{"current_steps": 2585, "total_steps": 3829, "loss": 0.263, "lr": 1.1557734660538572e-05, "epoch": 4.725776965265082, "percentage": 67.51, "elapsed_time": "4:32:06", "remaining_time": "2:10:57"}
{"current_steps": 2590, "total_steps": 3829, "loss": 0.2337, "lr": 1.1475176422845187e-05, "epoch": 4.7349177330895795, "percentage": 67.64, "elapsed_time": "4:32:40", "remaining_time": "2:10:26"}
{"current_steps": 2595, "total_steps": 3829, "loss": 0.2424, "lr": 1.1392795315858693e-05, "epoch": 4.744058500914077, "percentage": 67.77, "elapsed_time": "4:33:09", "remaining_time": "2:09:53"}
{"current_steps": 2600, "total_steps": 3829, "loss": 0.238, "lr": 1.1310593051312315e-05, "epoch": 4.753199268738574, "percentage": 67.9, "elapsed_time": "4:33:42", "remaining_time": "2:09:22"}
{"current_steps": 2605, "total_steps": 3829, "loss": 0.2327, "lr": 1.1228571337223224e-05, "epoch": 4.762340036563071, "percentage": 68.03, "elapsed_time": "4:34:15", "remaining_time": "2:08:51"}
{"current_steps": 2610, "total_steps": 3829, "loss": 0.2229, "lr": 1.1146731877857097e-05, "epoch": 4.7714808043875685, "percentage": 68.16, "elapsed_time": "4:34:44", "remaining_time": "2:08:19"}
{"current_steps": 2615, "total_steps": 3829, "loss": 0.2172, "lr": 1.1065076373692703e-05, "epoch": 4.780621572212066, "percentage": 68.29, "elapsed_time": "4:35:18", "remaining_time": "2:07:48"}
{"current_steps": 2620, "total_steps": 3829, "loss": 0.2494, "lr": 1.0983606521386495e-05, "epoch": 4.789762340036563, "percentage": 68.43, "elapsed_time": "4:35:46", "remaining_time": "2:07:15"}
{"current_steps": 2625, "total_steps": 3829, "loss": 0.2182, "lr": 1.090232401373745e-05, "epoch": 4.798903107861061, "percentage": 68.56, "elapsed_time": "4:36:20", "remaining_time": "2:06:44"}
{"current_steps": 2630, "total_steps": 3829, "loss": 0.2307, "lr": 1.0821230539651837e-05, "epoch": 4.8080438756855575, "percentage": 68.69, "elapsed_time": "4:36:51", "remaining_time": "2:06:12"}
{"current_steps": 2635, "total_steps": 3829, "loss": 0.2526, "lr": 1.0740327784108157e-05, "epoch": 4.817184643510055, "percentage": 68.82, "elapsed_time": "4:37:23", "remaining_time": "2:05:41"}
{"current_steps": 2640, "total_steps": 3829, "loss": 0.2317, "lr": 1.065961742812211e-05, "epoch": 4.826325411334552, "percentage": 68.95, "elapsed_time": "4:37:56", "remaining_time": "2:05:10"}
{"current_steps": 2645, "total_steps": 3829, "loss": 0.2357, "lr": 1.057910114871167e-05, "epoch": 4.83546617915905, "percentage": 69.08, "elapsed_time": "4:38:29", "remaining_time": "2:04:39"}
{"current_steps": 2650, "total_steps": 3829, "loss": 0.2353, "lr": 1.0498780618862257e-05, "epoch": 4.844606946983546, "percentage": 69.21, "elapsed_time": "4:39:03", "remaining_time": "2:04:09"}
{"current_steps": 2655, "total_steps": 3829, "loss": 0.2235, "lr": 1.0418657507491945e-05, "epoch": 4.853747714808044, "percentage": 69.34, "elapsed_time": "4:39:35", "remaining_time": "2:03:37"}
{"current_steps": 2660, "total_steps": 3829, "loss": 0.228, "lr": 1.033873347941682e-05, "epoch": 4.862888482632541, "percentage": 69.47, "elapsed_time": "4:40:08", "remaining_time": "2:03:06"}
{"current_steps": 2665, "total_steps": 3829, "loss": 0.248, "lr": 1.0259010195316362e-05, "epoch": 4.872029250457039, "percentage": 69.6, "elapsed_time": "4:40:39", "remaining_time": "2:02:35"}
{"current_steps": 2670, "total_steps": 3829, "loss": 0.2385, "lr": 1.0179489311698942e-05, "epoch": 4.881170018281535, "percentage": 69.73, "elapsed_time": "4:41:14", "remaining_time": "2:02:05"}
{"current_steps": 2675, "total_steps": 3829, "loss": 0.2429, "lr": 1.0100172480867421e-05, "epoch": 4.890310786106033, "percentage": 69.86, "elapsed_time": "4:41:46", "remaining_time": "2:01:33"}
{"current_steps": 2680, "total_steps": 3829, "loss": 0.229, "lr": 1.0021061350884796e-05, "epoch": 4.89945155393053, "percentage": 69.99, "elapsed_time": "4:42:18", "remaining_time": "2:01:02"}
{"current_steps": 2685, "total_steps": 3829, "loss": 0.2189, "lr": 9.942157565539965e-06, "epoch": 4.908592321755028, "percentage": 70.12, "elapsed_time": "4:42:47", "remaining_time": "2:00:29"}
{"current_steps": 2690, "total_steps": 3829, "loss": 0.231, "lr": 9.863462764313586e-06, "epoch": 4.917733089579524, "percentage": 70.25, "elapsed_time": "4:43:23", "remaining_time": "1:59:59"}
{"current_steps": 2695, "total_steps": 3829, "loss": 0.2187, "lr": 9.784978582343962e-06, "epoch": 4.926873857404022, "percentage": 70.38, "elapsed_time": "4:43:52", "remaining_time": "1:59:26"}
{"current_steps": 2700, "total_steps": 3829, "loss": 0.2453, "lr": 9.70670665039315e-06, "epoch": 4.936014625228519, "percentage": 70.51, "elapsed_time": "4:44:30", "remaining_time": "1:58:57"}
{"current_steps": 2705, "total_steps": 3829, "loss": 0.2163, "lr": 9.628648594813006e-06, "epoch": 4.9451553930530165, "percentage": 70.65, "elapsed_time": "4:45:04", "remaining_time": "1:58:27"}
{"current_steps": 2710, "total_steps": 3829, "loss": 0.2683, "lr": 9.550806037511396e-06, "epoch": 4.954296160877513, "percentage": 70.78, "elapsed_time": "4:45:34", "remaining_time": "1:57:54"}
{"current_steps": 2715, "total_steps": 3829, "loss": 0.2536, "lr": 9.473180595918534e-06, "epoch": 4.963436928702011, "percentage": 70.91, "elapsed_time": "4:46:09", "remaining_time": "1:57:24"}
{"current_steps": 2720, "total_steps": 3829, "loss": 0.2384, "lr": 9.395773882953363e-06, "epoch": 4.972577696526509, "percentage": 71.04, "elapsed_time": "4:46:38", "remaining_time": "1:56:52"}
{"current_steps": 2725, "total_steps": 3829, "loss": 0.2237, "lr": 9.318587506990026e-06, "epoch": 4.9817184643510055, "percentage": 71.17, "elapsed_time": "4:47:06", "remaining_time": "1:56:18"}
{"current_steps": 2730, "total_steps": 3829, "loss": 0.221, "lr": 9.241623071824438e-06, "epoch": 4.990859232175502, "percentage": 71.3, "elapsed_time": "4:47:38", "remaining_time": "1:55:47"}
{"current_steps": 2735, "total_steps": 3829, "loss": 0.2486, "lr": 9.16488217664099e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "4:48:10", "remaining_time": "1:55:16"}
{"current_steps": 2740, "total_steps": 3829, "loss": 0.2164, "lr": 9.088366415979317e-06, "epoch": 5.009140767824498, "percentage": 71.56, "elapsed_time": "4:48:39", "remaining_time": "1:54:43"}
{"current_steps": 2745, "total_steps": 3829, "loss": 0.2164, "lr": 9.012077379701147e-06, "epoch": 5.0182815356489945, "percentage": 71.69, "elapsed_time": "4:49:05", "remaining_time": "1:54:09"}
{"current_steps": 2750, "total_steps": 3829, "loss": 0.2219, "lr": 8.936016652957283e-06, "epoch": 5.027422303473492, "percentage": 71.82, "elapsed_time": "4:49:41", "remaining_time": "1:53:40"}
{"current_steps": 2755, "total_steps": 3829, "loss": 0.2252, "lr": 8.860185816154659e-06, "epoch": 5.036563071297989, "percentage": 71.95, "elapsed_time": "4:50:12", "remaining_time": "1:53:08"}
{"current_steps": 2760, "total_steps": 3829, "loss": 0.195, "lr": 8.784586444923499e-06, "epoch": 5.045703839122487, "percentage": 72.08, "elapsed_time": "4:50:41", "remaining_time": "1:52:35"}
{"current_steps": 2765, "total_steps": 3829, "loss": 0.2241, "lr": 8.709220110084597e-06, "epoch": 5.0548446069469835, "percentage": 72.21, "elapsed_time": "4:51:13", "remaining_time": "1:52:03"}
{"current_steps": 2770, "total_steps": 3829, "loss": 0.2156, "lr": 8.634088377616649e-06, "epoch": 5.063985374771481, "percentage": 72.34, "elapsed_time": "4:51:47", "remaining_time": "1:51:33"}
{"current_steps": 2775, "total_steps": 3829, "loss": 0.1991, "lr": 8.559192808623743e-06, "epoch": 5.073126142595978, "percentage": 72.47, "elapsed_time": "4:52:13", "remaining_time": "1:50:59"}
{"current_steps": 2780, "total_steps": 3829, "loss": 0.2187, "lr": 8.484534959302895e-06, "epoch": 5.082266910420476, "percentage": 72.6, "elapsed_time": "4:52:50", "remaining_time": "1:50:29"}
{"current_steps": 2785, "total_steps": 3829, "loss": 0.2401, "lr": 8.41011638091174e-06, "epoch": 5.091407678244972, "percentage": 72.73, "elapsed_time": "4:53:23", "remaining_time": "1:49:58"}
{"current_steps": 2790, "total_steps": 3829, "loss": 0.2126, "lr": 8.335938619736284e-06, "epoch": 5.10054844606947, "percentage": 72.86, "elapsed_time": "4:53:55", "remaining_time": "1:49:27"}
{"current_steps": 2795, "total_steps": 3829, "loss": 0.2266, "lr": 8.262003217058782e-06, "epoch": 5.109689213893967, "percentage": 73.0, "elapsed_time": "4:54:20", "remaining_time": "1:48:53"}
{"current_steps": 2800, "total_steps": 3829, "loss": 0.2193, "lr": 8.18831170912569e-06, "epoch": 5.118829981718465, "percentage": 73.13, "elapsed_time": "4:54:56", "remaining_time": "1:48:23"}
{"current_steps": 2805, "total_steps": 3829, "loss": 0.205, "lr": 8.114865627115793e-06, "epoch": 5.127970749542961, "percentage": 73.26, "elapsed_time": "4:55:26", "remaining_time": "1:47:51"}
{"current_steps": 2810, "total_steps": 3829, "loss": 0.2252, "lr": 8.041666497108344e-06, "epoch": 5.137111517367459, "percentage": 73.39, "elapsed_time": "4:55:57", "remaining_time": "1:47:19"}
{"current_steps": 2815, "total_steps": 3829, "loss": 0.226, "lr": 7.968715840051385e-06, "epoch": 5.146252285191956, "percentage": 73.52, "elapsed_time": "4:56:26", "remaining_time": "1:46:47"}
{"current_steps": 2820, "total_steps": 3829, "loss": 0.2337, "lr": 7.896015171730094e-06, "epoch": 5.155393053016454, "percentage": 73.65, "elapsed_time": "4:57:02", "remaining_time": "1:46:16"}
{"current_steps": 2825, "total_steps": 3829, "loss": 0.2165, "lr": 7.823566002735377e-06, "epoch": 5.16453382084095, "percentage": 73.78, "elapsed_time": "4:57:36", "remaining_time": "1:45:46"}
{"current_steps": 2830, "total_steps": 3829, "loss": 0.2139, "lr": 7.751369838432407e-06, "epoch": 5.173674588665448, "percentage": 73.91, "elapsed_time": "4:58:06", "remaining_time": "1:45:13"}
{"current_steps": 2835, "total_steps": 3829, "loss": 0.2355, "lr": 7.679428178929355e-06, "epoch": 5.182815356489945, "percentage": 74.04, "elapsed_time": "4:58:44", "remaining_time": "1:44:44"}
{"current_steps": 2840, "total_steps": 3829, "loss": 0.2128, "lr": 7.607742519046255e-06, "epoch": 5.1919561243144425, "percentage": 74.17, "elapsed_time": "4:59:20", "remaining_time": "1:44:14"}
{"current_steps": 2845, "total_steps": 3829, "loss": 0.2422, "lr": 7.536314348283906e-06, "epoch": 5.201096892138939, "percentage": 74.3, "elapsed_time": "4:59:49", "remaining_time": "1:43:42"}
{"current_steps": 2850, "total_steps": 3829, "loss": 0.2415, "lr": 7.46514515079297e-06, "epoch": 5.210237659963437, "percentage": 74.43, "elapsed_time": "5:00:18", "remaining_time": "1:43:09"}
{"current_steps": 2855, "total_steps": 3829, "loss": 0.1987, "lr": 7.394236405343063e-06, "epoch": 5.219378427787934, "percentage": 74.56, "elapsed_time": "5:00:44", "remaining_time": "1:42:36"}
{"current_steps": 2860, "total_steps": 3829, "loss": 0.2121, "lr": 7.323589585292097e-06, "epoch": 5.2285191956124315, "percentage": 74.69, "elapsed_time": "5:01:16", "remaining_time": "1:42:04"}
{"current_steps": 2865, "total_steps": 3829, "loss": 0.2222, "lr": 7.253206158555626e-06, "epoch": 5.237659963436928, "percentage": 74.82, "elapsed_time": "5:01:47", "remaining_time": "1:41:32"}
{"current_steps": 2870, "total_steps": 3829, "loss": 0.2482, "lr": 7.183087587576383e-06, "epoch": 5.246800731261426, "percentage": 74.95, "elapsed_time": "5:02:20", "remaining_time": "1:41:01"}
{"current_steps": 2875, "total_steps": 3829, "loss": 0.2096, "lr": 7.11323532929383e-06, "epoch": 5.255941499085923, "percentage": 75.08, "elapsed_time": "5:02:53", "remaining_time": "1:40:30"}
{"current_steps": 2880, "total_steps": 3829, "loss": 0.2319, "lr": 7.0436508351139535e-06, "epoch": 5.2650822669104205, "percentage": 75.22, "elapsed_time": "5:03:26", "remaining_time": "1:39:59"}
{"current_steps": 2885, "total_steps": 3829, "loss": 0.2242, "lr": 6.974335550879061e-06, "epoch": 5.274223034734918, "percentage": 75.35, "elapsed_time": "5:03:57", "remaining_time": "1:39:27"}
{"current_steps": 2890, "total_steps": 3829, "loss": 0.2225, "lr": 6.905290916837763e-06, "epoch": 5.283363802559415, "percentage": 75.48, "elapsed_time": "5:04:32", "remaining_time": "1:38:56"}
{"current_steps": 2895, "total_steps": 3829, "loss": 0.2071, "lr": 6.836518367615039e-06, "epoch": 5.292504570383913, "percentage": 75.61, "elapsed_time": "5:05:00", "remaining_time": "1:38:24"}
{"current_steps": 2900, "total_steps": 3829, "loss": 0.2179, "lr": 6.768019332182427e-06, "epoch": 5.301645338208409, "percentage": 75.74, "elapsed_time": "5:05:30", "remaining_time": "1:37:52"}
{"current_steps": 2905, "total_steps": 3829, "loss": 0.214, "lr": 6.69979523382833e-06, "epoch": 5.310786106032907, "percentage": 75.87, "elapsed_time": "5:06:05", "remaining_time": "1:37:21"}
{"current_steps": 2910, "total_steps": 3829, "loss": 0.2188, "lr": 6.631847490128456e-06, "epoch": 5.319926873857404, "percentage": 76.0, "elapsed_time": "5:06:34", "remaining_time": "1:36:49"}
{"current_steps": 2915, "total_steps": 3829, "loss": 0.2176, "lr": 6.5641775129163435e-06, "epoch": 5.329067641681902, "percentage": 76.13, "elapsed_time": "5:07:06", "remaining_time": "1:36:17"}
{"current_steps": 2920, "total_steps": 3829, "loss": 0.2065, "lr": 6.496786708254046e-06, "epoch": 5.338208409506398, "percentage": 76.26, "elapsed_time": "5:07:41", "remaining_time": "1:35:47"}
{"current_steps": 2925, "total_steps": 3829, "loss": 0.2075, "lr": 6.429676476402886e-06, "epoch": 5.347349177330896, "percentage": 76.39, "elapsed_time": "5:08:09", "remaining_time": "1:35:14"}
{"current_steps": 2930, "total_steps": 3829, "loss": 0.2521, "lr": 6.362848211794414e-06, "epoch": 5.356489945155393, "percentage": 76.52, "elapsed_time": "5:08:40", "remaining_time": "1:34:42"}
{"current_steps": 2935, "total_steps": 3829, "loss": 0.2189, "lr": 6.296303303001376e-06, "epoch": 5.365630712979891, "percentage": 76.65, "elapsed_time": "5:09:14", "remaining_time": "1:34:11"}
{"current_steps": 2940, "total_steps": 3829, "loss": 0.2086, "lr": 6.230043132708903e-06, "epoch": 5.374771480804387, "percentage": 76.78, "elapsed_time": "5:09:44", "remaining_time": "1:33:39"}
{"current_steps": 2945, "total_steps": 3829, "loss": 0.2098, "lr": 6.164069077685744e-06, "epoch": 5.383912248628885, "percentage": 76.91, "elapsed_time": "5:10:20", "remaining_time": "1:33:09"}
{"current_steps": 2950, "total_steps": 3829, "loss": 0.2027, "lr": 6.098382508755691e-06, "epoch": 5.393053016453382, "percentage": 77.04, "elapsed_time": "5:10:50", "remaining_time": "1:32:37"}
{"current_steps": 2955, "total_steps": 3829, "loss": 0.1918, "lr": 6.032984790769103e-06, "epoch": 5.4021937842778796, "percentage": 77.17, "elapsed_time": "5:11:19", "remaining_time": "1:32:04"}
{"current_steps": 2960, "total_steps": 3829, "loss": 0.2023, "lr": 5.967877282574512e-06, "epoch": 5.411334552102376, "percentage": 77.3, "elapsed_time": "5:11:50", "remaining_time": "1:31:33"}
{"current_steps": 2965, "total_steps": 3829, "loss": 0.2191, "lr": 5.9030613369903965e-06, "epoch": 5.420475319926874, "percentage": 77.44, "elapsed_time": "5:12:26", "remaining_time": "1:31:02"}
{"current_steps": 2970, "total_steps": 3829, "loss": 0.2028, "lr": 5.838538300777088e-06, "epoch": 5.429616087751371, "percentage": 77.57, "elapsed_time": "5:12:53", "remaining_time": "1:30:29"}
{"current_steps": 2975, "total_steps": 3829, "loss": 0.2137, "lr": 5.774309514608807e-06, "epoch": 5.4387568555758685, "percentage": 77.7, "elapsed_time": "5:13:28", "remaining_time": "1:29:59"}
{"current_steps": 2980, "total_steps": 3829, "loss": 0.205, "lr": 5.710376313045738e-06, "epoch": 5.447897623400365, "percentage": 77.83, "elapsed_time": "5:14:04", "remaining_time": "1:29:28"}
{"current_steps": 2985, "total_steps": 3829, "loss": 0.2113, "lr": 5.646740024506367e-06, "epoch": 5.457038391224863, "percentage": 77.96, "elapsed_time": "5:14:35", "remaining_time": "1:28:56"}
{"current_steps": 2990, "total_steps": 3829, "loss": 0.2425, "lr": 5.58340197123985e-06, "epoch": 5.46617915904936, "percentage": 78.09, "elapsed_time": "5:15:10", "remaining_time": "1:28:26"}
{"current_steps": 2995, "total_steps": 3829, "loss": 0.2126, "lr": 5.520363469298542e-06, "epoch": 5.4753199268738575, "percentage": 78.22, "elapsed_time": "5:15:41", "remaining_time": "1:27:54"}
{"current_steps": 3000, "total_steps": 3829, "loss": 0.2589, "lr": 5.457625828510655e-06, "epoch": 5.484460694698354, "percentage": 78.35, "elapsed_time": "5:16:09", "remaining_time": "1:27:21"}
{"current_steps": 3005, "total_steps": 3829, "loss": 0.2104, "lr": 5.395190352453037e-06, "epoch": 5.493601462522852, "percentage": 78.48, "elapsed_time": "5:17:05", "remaining_time": "1:26:56"}
{"current_steps": 3010, "total_steps": 3829, "loss": 0.2263, "lr": 5.333058338424091e-06, "epoch": 5.50274223034735, "percentage": 78.61, "elapsed_time": "5:17:29", "remaining_time": "1:26:23"}
{"current_steps": 3015, "total_steps": 3829, "loss": 0.2274, "lr": 5.271231077416816e-06, "epoch": 5.5118829981718465, "percentage": 78.74, "elapsed_time": "5:18:00", "remaining_time": "1:25:51"}
{"current_steps": 3020, "total_steps": 3829, "loss": 0.2352, "lr": 5.209709854091987e-06, "epoch": 5.521023765996343, "percentage": 78.87, "elapsed_time": "5:18:33", "remaining_time": "1:25:20"}
{"current_steps": 3025, "total_steps": 3829, "loss": 0.204, "lr": 5.148495946751457e-06, "epoch": 5.530164533820841, "percentage": 79.0, "elapsed_time": "5:19:03", "remaining_time": "1:24:48"}
{"current_steps": 3030, "total_steps": 3829, "loss": 0.2307, "lr": 5.0875906273116024e-06, "epoch": 5.539305301645339, "percentage": 79.13, "elapsed_time": "5:19:37", "remaining_time": "1:24:16"}
{"current_steps": 3035, "total_steps": 3829, "loss": 0.2138, "lr": 5.026995161276869e-06, "epoch": 5.548446069469835, "percentage": 79.26, "elapsed_time": "5:20:06", "remaining_time": "1:23:44"}
{"current_steps": 3040, "total_steps": 3829, "loss": 0.2369, "lr": 4.966710807713535e-06, "epoch": 5.557586837294332, "percentage": 79.39, "elapsed_time": "5:20:38", "remaining_time": "1:23:13"}
{"current_steps": 3045, "total_steps": 3829, "loss": 0.2256, "lr": 4.906738819223489e-06, "epoch": 5.56672760511883, "percentage": 79.52, "elapsed_time": "5:21:04", "remaining_time": "1:22:40"}
{"current_steps": 3050, "total_steps": 3829, "loss": 0.2275, "lr": 4.847080441918237e-06, "epoch": 5.575868372943328, "percentage": 79.66, "elapsed_time": "5:21:40", "remaining_time": "1:22:09"}
{"current_steps": 3055, "total_steps": 3829, "loss": 0.2089, "lr": 4.787736915392982e-06, "epoch": 5.585009140767824, "percentage": 79.79, "elapsed_time": "5:22:05", "remaining_time": "1:21:36"}
{"current_steps": 3060, "total_steps": 3829, "loss": 0.2178, "lr": 4.728709472700919e-06, "epoch": 5.594149908592322, "percentage": 79.92, "elapsed_time": "5:22:37", "remaining_time": "1:21:04"}
{"current_steps": 3065, "total_steps": 3829, "loss": 0.214, "lr": 4.6699993403275645e-06, "epoch": 5.603290676416819, "percentage": 80.05, "elapsed_time": "5:23:08", "remaining_time": "1:20:32"}
{"current_steps": 3070, "total_steps": 3829, "loss": 0.2454, "lr": 4.6116077381652755e-06, "epoch": 5.612431444241317, "percentage": 80.18, "elapsed_time": "5:23:42", "remaining_time": "1:20:01"}
{"current_steps": 3075, "total_steps": 3829, "loss": 0.2165, "lr": 4.5535358794879426e-06, "epoch": 5.621572212065813, "percentage": 80.31, "elapsed_time": "5:24:11", "remaining_time": "1:19:29"}
{"current_steps": 3080, "total_steps": 3829, "loss": 0.2508, "lr": 4.49578497092573e-06, "epoch": 5.630712979890311, "percentage": 80.44, "elapsed_time": "5:24:44", "remaining_time": "1:18:58"}
{"current_steps": 3085, "total_steps": 3829, "loss": 0.2176, "lr": 4.438356212440063e-06, "epoch": 5.639853747714808, "percentage": 80.57, "elapsed_time": "5:25:11", "remaining_time": "1:18:25"}
{"current_steps": 3090, "total_steps": 3829, "loss": 0.2072, "lr": 4.3812507972986155e-06, "epoch": 5.6489945155393055, "percentage": 80.7, "elapsed_time": "5:25:42", "remaining_time": "1:17:53"}
{"current_steps": 3095, "total_steps": 3829, "loss": 0.2115, "lr": 4.324469912050591e-06, "epoch": 5.658135283363802, "percentage": 80.83, "elapsed_time": "5:26:15", "remaining_time": "1:17:22"}
{"current_steps": 3100, "total_steps": 3829, "loss": 0.2015, "lr": 4.268014736502024e-06, "epoch": 5.6672760511883, "percentage": 80.96, "elapsed_time": "5:26:46", "remaining_time": "1:16:50"}
{"current_steps": 3105, "total_steps": 3829, "loss": 0.2397, "lr": 4.211886443691298e-06, "epoch": 5.676416819012797, "percentage": 81.09, "elapsed_time": "5:27:17", "remaining_time": "1:16:18"}
{"current_steps": 3110, "total_steps": 3829, "loss": 0.2175, "lr": 4.1560861998647236e-06, "epoch": 5.6855575868372945, "percentage": 81.22, "elapsed_time": "5:27:43", "remaining_time": "1:15:46"}
{"current_steps": 3115, "total_steps": 3829, "loss": 0.2252, "lr": 4.100615164452359e-06, "epoch": 5.694698354661791, "percentage": 81.35, "elapsed_time": "5:28:15", "remaining_time": "1:15:14"}
{"current_steps": 3120, "total_steps": 3829, "loss": 0.2279, "lr": 4.045474490043888e-06, "epoch": 5.703839122486289, "percentage": 81.48, "elapsed_time": "5:28:46", "remaining_time": "1:14:42"}
{"current_steps": 3125, "total_steps": 3829, "loss": 0.2282, "lr": 3.99066532236468e-06, "epoch": 5.712979890310786, "percentage": 81.61, "elapsed_time": "5:29:12", "remaining_time": "1:14:09"}
{"current_steps": 3130, "total_steps": 3829, "loss": 0.2334, "lr": 3.9361888002519785e-06, "epoch": 5.7221206581352835, "percentage": 81.74, "elapsed_time": "5:29:46", "remaining_time": "1:13:38"}
{"current_steps": 3135, "total_steps": 3829, "loss": 0.232, "lr": 3.882046055631248e-06, "epoch": 5.73126142595978, "percentage": 81.88, "elapsed_time": "5:30:15", "remaining_time": "1:13:06"}
{"current_steps": 3140, "total_steps": 3829, "loss": 0.2299, "lr": 3.82823821349265e-06, "epoch": 5.740402193784278, "percentage": 82.01, "elapsed_time": "5:30:49", "remaining_time": "1:12:35"}
{"current_steps": 3145, "total_steps": 3829, "loss": 0.2038, "lr": 3.774766391867659e-06, "epoch": 5.749542961608775, "percentage": 82.14, "elapsed_time": "5:31:18", "remaining_time": "1:12:03"}
{"current_steps": 3150, "total_steps": 3829, "loss": 0.2159, "lr": 3.7216317018058457e-06, "epoch": 5.7586837294332724, "percentage": 82.27, "elapsed_time": "5:31:51", "remaining_time": "1:11:32"}
{"current_steps": 3155, "total_steps": 3829, "loss": 0.2233, "lr": 3.668835247351792e-06, "epoch": 5.76782449725777, "percentage": 82.4, "elapsed_time": "5:32:26", "remaining_time": "1:11:01"}
{"current_steps": 3160, "total_steps": 3829, "loss": 0.2245, "lr": 3.6163781255221153e-06, "epoch": 5.776965265082267, "percentage": 82.53, "elapsed_time": "5:32:58", "remaining_time": "1:10:29"}
{"current_steps": 3165, "total_steps": 3829, "loss": 0.2174, "lr": 3.5642614262827425e-06, "epoch": 5.786106032906764, "percentage": 82.66, "elapsed_time": "5:33:22", "remaining_time": "1:09:56"}
{"current_steps": 3170, "total_steps": 3829, "loss": 0.2418, "lr": 3.512486232526198e-06, "epoch": 5.795246800731261, "percentage": 82.79, "elapsed_time": "5:34:00", "remaining_time": "1:09:26"}
{"current_steps": 3175, "total_steps": 3829, "loss": 0.2235, "lr": 3.4610536200491394e-06, "epoch": 5.804387568555759, "percentage": 82.92, "elapsed_time": "5:34:26", "remaining_time": "1:08:53"}
{"current_steps": 3180, "total_steps": 3829, "loss": 0.2119, "lr": 3.4099646575299783e-06, "epoch": 5.813528336380256, "percentage": 83.05, "elapsed_time": "5:34:55", "remaining_time": "1:08:21"}
{"current_steps": 3185, "total_steps": 3829, "loss": 0.2156, "lr": 3.3592204065067003e-06, "epoch": 5.822669104204754, "percentage": 83.18, "elapsed_time": "5:35:27", "remaining_time": "1:07:49"}
{"current_steps": 3190, "total_steps": 3829, "loss": 0.2178, "lr": 3.308821921354808e-06, "epoch": 5.83180987202925, "percentage": 83.31, "elapsed_time": "5:36:02", "remaining_time": "1:07:18"}
{"current_steps": 3195, "total_steps": 3829, "loss": 0.251, "lr": 3.2587702492653907e-06, "epoch": 5.840950639853748, "percentage": 83.44, "elapsed_time": "5:36:35", "remaining_time": "1:06:47"}
{"current_steps": 3200, "total_steps": 3829, "loss": 0.2195, "lr": 3.209066430223369e-06, "epoch": 5.850091407678245, "percentage": 83.57, "elapsed_time": "5:37:05", "remaining_time": "1:06:15"}
{"current_steps": 3205, "total_steps": 3829, "loss": 0.2192, "lr": 3.1597114969859067e-06, "epoch": 5.859232175502743, "percentage": 83.7, "elapsed_time": "5:37:39", "remaining_time": "1:05:44"}
{"current_steps": 3210, "total_steps": 3829, "loss": 0.2407, "lr": 3.1107064750609517e-06, "epoch": 5.868372943327239, "percentage": 83.83, "elapsed_time": "5:38:13", "remaining_time": "1:05:13"}
{"current_steps": 3215, "total_steps": 3829, "loss": 0.2068, "lr": 3.062052382685887e-06, "epoch": 5.877513711151737, "percentage": 83.96, "elapsed_time": "5:38:45", "remaining_time": "1:04:41"}
{"current_steps": 3220, "total_steps": 3829, "loss": 0.2198, "lr": 3.01375023080642e-06, "epoch": 5.886654478976234, "percentage": 84.1, "elapsed_time": "5:39:15", "remaining_time": "1:04:09"}
{"current_steps": 3225, "total_steps": 3829, "loss": 0.2211, "lr": 2.965801023055559e-06, "epoch": 5.8957952468007315, "percentage": 84.23, "elapsed_time": "5:39:50", "remaining_time": "1:03:38"}
{"current_steps": 3230, "total_steps": 3829, "loss": 0.2258, "lr": 2.9182057557327547e-06, "epoch": 5.904936014625228, "percentage": 84.36, "elapsed_time": "5:40:17", "remaining_time": "1:03:06"}
{"current_steps": 3235, "total_steps": 3829, "loss": 0.244, "lr": 2.8709654177832047e-06, "epoch": 5.914076782449726, "percentage": 84.49, "elapsed_time": "5:40:52", "remaining_time": "1:02:35"}
{"current_steps": 3240, "total_steps": 3829, "loss": 0.2414, "lr": 2.824080990777307e-06, "epoch": 5.923217550274223, "percentage": 84.62, "elapsed_time": "5:41:24", "remaining_time": "1:02:03"}
{"current_steps": 3245, "total_steps": 3829, "loss": 0.2254, "lr": 2.77755344889026e-06, "epoch": 5.9323583180987205, "percentage": 84.75, "elapsed_time": "5:41:57", "remaining_time": "1:01:32"}
{"current_steps": 3250, "total_steps": 3829, "loss": 0.2202, "lr": 2.7313837588818206e-06, "epoch": 5.941499085923217, "percentage": 84.88, "elapsed_time": "5:42:29", "remaining_time": "1:01:00"}
{"current_steps": 3255, "total_steps": 3829, "loss": 0.2085, "lr": 2.6855728800762216e-06, "epoch": 5.950639853747715, "percentage": 85.01, "elapsed_time": "5:43:04", "remaining_time": "1:00:30"}
{"current_steps": 3260, "total_steps": 3829, "loss": 0.2176, "lr": 2.640121764342234e-06, "epoch": 5.959780621572212, "percentage": 85.14, "elapsed_time": "5:43:40", "remaining_time": "0:59:59"}
{"current_steps": 3265, "total_steps": 3829, "loss": 0.1926, "lr": 2.59503135607339e-06, "epoch": 5.9689213893967095, "percentage": 85.27, "elapsed_time": "5:44:09", "remaining_time": "0:59:27"}
{"current_steps": 3270, "total_steps": 3829, "loss": 0.1965, "lr": 2.5503025921683656e-06, "epoch": 5.978062157221206, "percentage": 85.4, "elapsed_time": "5:44:39", "remaining_time": "0:58:55"}
{"current_steps": 3275, "total_steps": 3829, "loss": 0.2143, "lr": 2.5059364020114995e-06, "epoch": 5.987202925045704, "percentage": 85.53, "elapsed_time": "5:45:06", "remaining_time": "0:58:22"}
{"current_steps": 3280, "total_steps": 3829, "loss": 0.2259, "lr": 2.461933707453501e-06, "epoch": 5.996343692870201, "percentage": 85.66, "elapsed_time": "5:45:41", "remaining_time": "0:57:51"}
{"current_steps": 3285, "total_steps": 3829, "loss": 0.2152, "lr": 2.418295422792285e-06, "epoch": 6.005484460694698, "percentage": 85.79, "elapsed_time": "5:46:15", "remaining_time": "0:57:20"}
{"current_steps": 3290, "total_steps": 3829, "loss": 0.2346, "lr": 2.3750224547539568e-06, "epoch": 6.014625228519195, "percentage": 85.92, "elapsed_time": "5:46:46", "remaining_time": "0:56:48"}
{"current_steps": 3295, "total_steps": 3829, "loss": 0.2301, "lr": 2.3321157024740205e-06, "epoch": 6.023765996343693, "percentage": 86.05, "elapsed_time": "5:47:22", "remaining_time": "0:56:17"}
{"current_steps": 3300, "total_steps": 3829, "loss": 0.1998, "lr": 2.289576057478653e-06, "epoch": 6.03290676416819, "percentage": 86.18, "elapsed_time": "5:47:54", "remaining_time": "0:55:46"}
{"current_steps": 3305, "total_steps": 3829, "loss": 0.2214, "lr": 2.2474044036661802e-06, "epoch": 6.042047531992687, "percentage": 86.31, "elapsed_time": "5:48:22", "remaining_time": "0:55:14"}
{"current_steps": 3310, "total_steps": 3829, "loss": 0.2157, "lr": 2.2056016172887374e-06, "epoch": 6.051188299817184, "percentage": 86.45, "elapsed_time": "5:49:00", "remaining_time": "0:54:43"}
{"current_steps": 3315, "total_steps": 3829, "loss": 0.2165, "lr": 2.164168566934055e-06, "epoch": 6.060329067641682, "percentage": 86.58, "elapsed_time": "5:49:33", "remaining_time": "0:54:12"}
{"current_steps": 3320, "total_steps": 3829, "loss": 0.2133, "lr": 2.1231061135074004e-06, "epoch": 6.06946983546618, "percentage": 86.71, "elapsed_time": "5:50:07", "remaining_time": "0:53:40"}
{"current_steps": 3325, "total_steps": 3829, "loss": 0.2174, "lr": 2.0824151102136824e-06, "epoch": 6.078610603290676, "percentage": 86.84, "elapsed_time": "5:50:39", "remaining_time": "0:53:09"}
{"current_steps": 3330, "total_steps": 3829, "loss": 0.2001, "lr": 2.042096402539746e-06, "epoch": 6.087751371115174, "percentage": 86.97, "elapsed_time": "5:51:07", "remaining_time": "0:52:37"}
{"current_steps": 3335, "total_steps": 3829, "loss": 0.2072, "lr": 2.0021508282367974e-06, "epoch": 6.096892138939671, "percentage": 87.1, "elapsed_time": "5:51:40", "remaining_time": "0:52:05"}
{"current_steps": 3340, "total_steps": 3829, "loss": 0.1997, "lr": 1.9625792173029824e-06, "epoch": 6.1060329067641685, "percentage": 87.23, "elapsed_time": "5:52:08", "remaining_time": "0:51:33"}
{"current_steps": 3345, "total_steps": 3829, "loss": 0.2099, "lr": 1.923382391966162e-06, "epoch": 6.115173674588665, "percentage": 87.36, "elapsed_time": "5:52:41", "remaining_time": "0:51:01"}
{"current_steps": 3350, "total_steps": 3829, "loss": 0.206, "lr": 1.8845611666668117e-06, "epoch": 6.124314442413163, "percentage": 87.49, "elapsed_time": "5:53:13", "remaining_time": "0:50:30"}
{"current_steps": 3355, "total_steps": 3829, "loss": 0.2223, "lr": 1.8461163480411048e-06, "epoch": 6.13345521023766, "percentage": 87.62, "elapsed_time": "5:53:44", "remaining_time": "0:49:58"}
{"current_steps": 3360, "total_steps": 3829, "loss": 0.2268, "lr": 1.808048734904153e-06, "epoch": 6.1425959780621575, "percentage": 87.75, "elapsed_time": "5:54:17", "remaining_time": "0:49:27"}
{"current_steps": 3365, "total_steps": 3829, "loss": 0.1869, "lr": 1.7703591182334113e-06, "epoch": 6.151736745886654, "percentage": 87.88, "elapsed_time": "5:54:49", "remaining_time": "0:48:55"}
{"current_steps": 3370, "total_steps": 3829, "loss": 0.1853, "lr": 1.733048281152232e-06, "epoch": 6.160877513711152, "percentage": 88.01, "elapsed_time": "5:55:24", "remaining_time": "0:48:24"}
{"current_steps": 3375, "total_steps": 3829, "loss": 0.2355, "lr": 1.6961169989136017e-06, "epoch": 6.170018281535649, "percentage": 88.14, "elapsed_time": "5:55:59", "remaining_time": "0:47:53"}
{"current_steps": 3380, "total_steps": 3829, "loss": 0.1985, "lr": 1.6595660388840352e-06, "epoch": 6.1791590493601465, "percentage": 88.27, "elapsed_time": "5:56:31", "remaining_time": "0:47:21"}
{"current_steps": 3385, "total_steps": 3829, "loss": 0.2313, "lr": 1.6233961605276194e-06, "epoch": 6.188299817184643, "percentage": 88.4, "elapsed_time": "5:57:09", "remaining_time": "0:46:50"}
{"current_steps": 3390, "total_steps": 3829, "loss": 0.1998, "lr": 1.5876081153902511e-06, "epoch": 6.197440585009141, "percentage": 88.53, "elapsed_time": "5:57:39", "remaining_time": "0:46:18"}
{"current_steps": 3395, "total_steps": 3829, "loss": 0.2255, "lr": 1.5522026470839913e-06, "epoch": 6.206581352833638, "percentage": 88.67, "elapsed_time": "5:58:12", "remaining_time": "0:45:47"}
{"current_steps": 3400, "total_steps": 3829, "loss": 0.2153, "lr": 1.5171804912716548e-06, "epoch": 6.2157221206581355, "percentage": 88.8, "elapsed_time": "5:58:46", "remaining_time": "0:45:16"}
{"current_steps": 3405, "total_steps": 3829, "loss": 0.1969, "lr": 1.4825423756514923e-06, "epoch": 6.224862888482632, "percentage": 88.93, "elapsed_time": "5:59:17", "remaining_time": "0:44:44"}
{"current_steps": 3410, "total_steps": 3829, "loss": 0.1999, "lr": 1.448289019942084e-06, "epoch": 6.23400365630713, "percentage": 89.06, "elapsed_time": "5:59:48", "remaining_time": "0:44:12"}
{"current_steps": 3415, "total_steps": 3829, "loss": 0.1998, "lr": 1.4144211358673743e-06, "epoch": 6.243144424131627, "percentage": 89.19, "elapsed_time": "6:00:21", "remaining_time": "0:43:41"}
{"current_steps": 3420, "total_steps": 3829, "loss": 0.228, "lr": 1.3809394271418964e-06, "epoch": 6.252285191956124, "percentage": 89.32, "elapsed_time": "6:00:52", "remaining_time": "0:43:09"}
{"current_steps": 3425, "total_steps": 3829, "loss": 0.1863, "lr": 1.3478445894561553e-06, "epoch": 6.261425959780621, "percentage": 89.45, "elapsed_time": "6:01:22", "remaining_time": "0:42:37"}
{"current_steps": 3430, "total_steps": 3829, "loss": 0.2212, "lr": 1.31513731046214e-06, "epoch": 6.270566727605119, "percentage": 89.58, "elapsed_time": "6:01:55", "remaining_time": "0:42:06"}
{"current_steps": 3435, "total_steps": 3829, "loss": 0.2271, "lr": 1.2828182697590784e-06, "epoch": 6.279707495429616, "percentage": 89.71, "elapsed_time": "6:02:25", "remaining_time": "0:41:34"}
{"current_steps": 3440, "total_steps": 3829, "loss": 0.2235, "lr": 1.2508881388792781e-06, "epoch": 6.288848263254113, "percentage": 89.84, "elapsed_time": "6:02:59", "remaining_time": "0:41:02"}
{"current_steps": 3445, "total_steps": 3829, "loss": 0.2234, "lr": 1.2193475812742128e-06, "epoch": 6.29798903107861, "percentage": 89.97, "elapsed_time": "6:03:32", "remaining_time": "0:40:31"}
{"current_steps": 3450, "total_steps": 3829, "loss": 0.2289, "lr": 1.1881972523006934e-06, "epoch": 6.307129798903108, "percentage": 90.1, "elapsed_time": "6:04:05", "remaining_time": "0:39:59"}
{"current_steps": 3455, "total_steps": 3829, "loss": 0.2157, "lr": 1.1574377992072795e-06, "epoch": 6.316270566727605, "percentage": 90.23, "elapsed_time": "6:04:30", "remaining_time": "0:39:27"}
{"current_steps": 3460, "total_steps": 3829, "loss": 0.2167, "lr": 1.1270698611208242e-06, "epoch": 6.325411334552102, "percentage": 90.36, "elapsed_time": "6:05:04", "remaining_time": "0:38:56"}
{"current_steps": 3465, "total_steps": 3829, "loss": 0.2109, "lr": 1.0970940690332044e-06, "epoch": 6.3345521023766, "percentage": 90.49, "elapsed_time": "6:05:34", "remaining_time": "0:38:24"}
{"current_steps": 3470, "total_steps": 3829, "loss": 0.2112, "lr": 1.0675110457881765e-06, "epoch": 6.343692870201097, "percentage": 90.62, "elapsed_time": "6:06:02", "remaining_time": "0:37:52"}
{"current_steps": 3475, "total_steps": 3829, "loss": 0.2438, "lr": 1.038321406068472e-06, "epoch": 6.3528336380255945, "percentage": 90.75, "elapsed_time": "6:06:37", "remaining_time": "0:37:20"}
{"current_steps": 3480, "total_steps": 3829, "loss": 0.2152, "lr": 1.0095257563830119e-06, "epoch": 6.361974405850091, "percentage": 90.89, "elapsed_time": "6:07:05", "remaining_time": "0:36:48"}
{"current_steps": 3485, "total_steps": 3829, "loss": 0.2389, "lr": 9.811246950542962e-07, "epoch": 6.371115173674589, "percentage": 91.02, "elapsed_time": "6:07:34", "remaining_time": "0:36:16"}
{"current_steps": 3490, "total_steps": 3829, "loss": 0.2082, "lr": 9.531188122059864e-07, "epoch": 6.380255941499086, "percentage": 91.15, "elapsed_time": "6:08:05", "remaining_time": "0:35:45"}
{"current_steps": 3495, "total_steps": 3829, "loss": 0.2053, "lr": 9.255086897506271e-07, "epoch": 6.3893967093235835, "percentage": 91.28, "elapsed_time": "6:08:38", "remaining_time": "0:35:13"}
{"current_steps": 3500, "total_steps": 3829, "loss": 0.1996, "lr": 8.982949013775743e-07, "epoch": 6.39853747714808, "percentage": 91.41, "elapsed_time": "6:09:12", "remaining_time": "0:34:42"}
{"current_steps": 3505, "total_steps": 3829, "loss": 0.2067, "lr": 8.714780125410561e-07, "epoch": 6.407678244972578, "percentage": 91.54, "elapsed_time": "6:09:38", "remaining_time": "0:34:10"}
{"current_steps": 3510, "total_steps": 3829, "loss": 0.2106, "lr": 8.450585804484412e-07, "epoch": 6.416819012797075, "percentage": 91.67, "elapsed_time": "6:10:07", "remaining_time": "0:33:38"}
{"current_steps": 3515, "total_steps": 3829, "loss": 0.2068, "lr": 8.190371540486474e-07, "epoch": 6.4259597806215725, "percentage": 91.8, "elapsed_time": "6:10:38", "remaining_time": "0:33:06"}
{"current_steps": 3520, "total_steps": 3829, "loss": 0.2086, "lr": 7.934142740207362e-07, "epoch": 6.435100548446069, "percentage": 91.93, "elapsed_time": "6:11:15", "remaining_time": "0:32:35"}
{"current_steps": 3525, "total_steps": 3829, "loss": 0.2258, "lr": 7.681904727626888e-07, "epoch": 6.444241316270567, "percentage": 92.06, "elapsed_time": "6:11:54", "remaining_time": "0:32:04"}
{"current_steps": 3530, "total_steps": 3829, "loss": 0.2257, "lr": 7.433662743803394e-07, "epoch": 6.453382084095064, "percentage": 92.19, "elapsed_time": "6:12:30", "remaining_time": "0:31:33"}
{"current_steps": 3535, "total_steps": 3829, "loss": 0.2205, "lr": 7.189421946764841e-07, "epoch": 6.462522851919561, "percentage": 92.32, "elapsed_time": "6:13:01", "remaining_time": "0:31:01"}
{"current_steps": 3540, "total_steps": 3829, "loss": 0.2118, "lr": 6.949187411401515e-07, "epoch": 6.471663619744058, "percentage": 92.45, "elapsed_time": "6:13:27", "remaining_time": "0:30:29"}
{"current_steps": 3545, "total_steps": 3829, "loss": 0.2231, "lr": 6.712964129360778e-07, "epoch": 6.480804387568556, "percentage": 92.58, "elapsed_time": "6:13:57", "remaining_time": "0:29:57"}
{"current_steps": 3550, "total_steps": 3829, "loss": 0.2112, "lr": 6.480757008943328e-07, "epoch": 6.489945155393053, "percentage": 92.71, "elapsed_time": "6:14:30", "remaining_time": "0:29:25"}
{"current_steps": 3555, "total_steps": 3829, "loss": 0.2203, "lr": 6.252570875001041e-07, "epoch": 6.49908592321755, "percentage": 92.84, "elapsed_time": "6:14:58", "remaining_time": "0:28:54"}
{"current_steps": 3560, "total_steps": 3829, "loss": 0.2177, "lr": 6.028410468836865e-07, "epoch": 6.508226691042047, "percentage": 92.97, "elapsed_time": "6:15:31", "remaining_time": "0:28:22"}
{"current_steps": 3565, "total_steps": 3829, "loss": 0.2342, "lr": 5.808280448106263e-07, "epoch": 6.517367458866545, "percentage": 93.11, "elapsed_time": "6:15:59", "remaining_time": "0:27:50"}
{"current_steps": 3570, "total_steps": 3829, "loss": 0.2343, "lr": 5.592185386720483e-07, "epoch": 6.526508226691042, "percentage": 93.24, "elapsed_time": "6:16:28", "remaining_time": "0:27:18"}
{"current_steps": 3575, "total_steps": 3829, "loss": 0.2133, "lr": 5.380129774751419e-07, "epoch": 6.535648994515539, "percentage": 93.37, "elapsed_time": "6:17:07", "remaining_time": "0:26:47"}
{"current_steps": 3580, "total_steps": 3829, "loss": 0.2, "lr": 5.172118018338412e-07, "epoch": 6.544789762340036, "percentage": 93.5, "elapsed_time": "6:17:40", "remaining_time": "0:26:16"}
{"current_steps": 3585, "total_steps": 3829, "loss": 0.2121, "lr": 4.968154439596662e-07, "epoch": 6.553930530164534, "percentage": 93.63, "elapsed_time": "6:18:13", "remaining_time": "0:25:44"}
{"current_steps": 3590, "total_steps": 3829, "loss": 0.2106, "lr": 4.7682432765274067e-07, "epoch": 6.5630712979890315, "percentage": 93.76, "elapsed_time": "6:18:42", "remaining_time": "0:25:12"}
{"current_steps": 3595, "total_steps": 3829, "loss": 0.2028, "lr": 4.5723886829298404e-07, "epoch": 6.572212065813528, "percentage": 93.89, "elapsed_time": "6:19:13", "remaining_time": "0:24:41"}
{"current_steps": 3600, "total_steps": 3829, "loss": 0.2167, "lr": 4.3805947283149353e-07, "epoch": 6.581352833638025, "percentage": 94.02, "elapsed_time": "6:19:42", "remaining_time": "0:24:09"}
{"current_steps": 3605, "total_steps": 3829, "loss": 0.2207, "lr": 4.192865397820689e-07, "epoch": 6.590493601462523, "percentage": 94.15, "elapsed_time": "6:20:15", "remaining_time": "0:23:37"}
{"current_steps": 3610, "total_steps": 3829, "loss": 0.2164, "lr": 4.009204592129501e-07, "epoch": 6.5996343692870205, "percentage": 94.28, "elapsed_time": "6:20:40", "remaining_time": "0:23:05"}
{"current_steps": 3615, "total_steps": 3829, "loss": 0.2203, "lr": 3.8296161273869924e-07, "epoch": 6.608775137111517, "percentage": 94.41, "elapsed_time": "6:21:10", "remaining_time": "0:22:33"}
{"current_steps": 3620, "total_steps": 3829, "loss": 0.1983, "lr": 3.6541037351228046e-07, "epoch": 6.617915904936015, "percentage": 94.54, "elapsed_time": "6:21:41", "remaining_time": "0:22:02"}
{"current_steps": 3625, "total_steps": 3829, "loss": 0.2175, "lr": 3.4826710621729933e-07, "epoch": 6.627056672760512, "percentage": 94.67, "elapsed_time": "6:22:18", "remaining_time": "0:21:30"}
{"current_steps": 3630, "total_steps": 3829, "loss": 0.2266, "lr": 3.315321670604288e-07, "epoch": 6.6361974405850095, "percentage": 94.8, "elapsed_time": "6:22:49", "remaining_time": "0:20:59"}
{"current_steps": 3635, "total_steps": 3829, "loss": 0.2199, "lr": 3.1520590376401095e-07, "epoch": 6.645338208409506, "percentage": 94.93, "elapsed_time": "6:23:20", "remaining_time": "0:20:27"}
{"current_steps": 3640, "total_steps": 3829, "loss": 0.2247, "lr": 2.9928865555882704e-07, "epoch": 6.654478976234004, "percentage": 95.06, "elapsed_time": "6:23:51", "remaining_time": "0:19:55"}
{"current_steps": 3645, "total_steps": 3829, "loss": 0.2174, "lr": 2.83780753177052e-07, "epoch": 6.663619744058501, "percentage": 95.19, "elapsed_time": "6:24:23", "remaining_time": "0:19:24"}
{"current_steps": 3650, "total_steps": 3829, "loss": 0.2178, "lr": 2.686825188453712e-07, "epoch": 6.6727605118829985, "percentage": 95.33, "elapsed_time": "6:24:53", "remaining_time": "0:18:52"}
{"current_steps": 3655, "total_steps": 3829, "loss": 0.2187, "lr": 2.539942662783079e-07, "epoch": 6.681901279707495, "percentage": 95.46, "elapsed_time": "6:25:26", "remaining_time": "0:18:20"}
{"current_steps": 3660, "total_steps": 3829, "loss": 0.22, "lr": 2.397163006716907e-07, "epoch": 6.691042047531993, "percentage": 95.59, "elapsed_time": "6:25:55", "remaining_time": "0:17:49"}
{"current_steps": 3665, "total_steps": 3829, "loss": 0.2174, "lr": 2.2584891869630089e-07, "epoch": 6.70018281535649, "percentage": 95.72, "elapsed_time": "6:26:26", "remaining_time": "0:17:17"}
{"current_steps": 3670, "total_steps": 3829, "loss": 0.1958, "lr": 2.1239240849173504e-07, "epoch": 6.709323583180987, "percentage": 95.85, "elapsed_time": "6:27:01", "remaining_time": "0:16:46"}
{"current_steps": 3675, "total_steps": 3829, "loss": 0.214, "lr": 1.9934704966039e-07, "epoch": 6.718464351005484, "percentage": 95.98, "elapsed_time": "6:27:32", "remaining_time": "0:16:14"}
{"current_steps": 3680, "total_steps": 3829, "loss": 0.1927, "lr": 1.8671311326168283e-07, "epoch": 6.727605118829982, "percentage": 96.11, "elapsed_time": "6:28:06", "remaining_time": "0:15:42"}
{"current_steps": 3685, "total_steps": 3829, "loss": 0.2093, "lr": 1.7449086180638674e-07, "epoch": 6.736745886654479, "percentage": 96.24, "elapsed_time": "6:28:36", "remaining_time": "0:15:11"}
{"current_steps": 3690, "total_steps": 3829, "loss": 0.2104, "lr": 1.626805492511996e-07, "epoch": 6.745886654478976, "percentage": 96.37, "elapsed_time": "6:29:05", "remaining_time": "0:14:39"}
{"current_steps": 3695, "total_steps": 3829, "loss": 0.1989, "lr": 1.512824209934638e-07, "epoch": 6.755027422303473, "percentage": 96.5, "elapsed_time": "6:29:36", "remaining_time": "0:14:07"}
{"current_steps": 3700, "total_steps": 3829, "loss": 0.2283, "lr": 1.402967138660527e-07, "epoch": 6.764168190127971, "percentage": 96.63, "elapsed_time": "6:30:09", "remaining_time": "0:13:36"}
{"current_steps": 3705, "total_steps": 3829, "loss": 0.223, "lr": 1.2972365613246994e-07, "epoch": 6.773308957952468, "percentage": 96.76, "elapsed_time": "6:30:37", "remaining_time": "0:13:04"}
{"current_steps": 3710, "total_steps": 3829, "loss": 0.2408, "lr": 1.1956346748209335e-07, "epoch": 6.782449725776965, "percentage": 96.89, "elapsed_time": "6:31:11", "remaining_time": "0:12:32"}
{"current_steps": 3715, "total_steps": 3829, "loss": 0.209, "lr": 1.0981635902561405e-07, "epoch": 6.791590493601462, "percentage": 97.02, "elapsed_time": "6:31:42", "remaining_time": "0:12:01"}
{"current_steps": 3720, "total_steps": 3829, "loss": 0.202, "lr": 1.0048253329065116e-07, "epoch": 6.80073126142596, "percentage": 97.15, "elapsed_time": "6:32:08", "remaining_time": "0:11:29"}
{"current_steps": 3725, "total_steps": 3829, "loss": 0.2051, "lr": 9.156218421753737e-08, "epoch": 6.809872029250457, "percentage": 97.28, "elapsed_time": "6:32:39", "remaining_time": "0:10:57"}
{"current_steps": 3730, "total_steps": 3829, "loss": 0.2074, "lr": 8.305549715529992e-08, "epoch": 6.819012797074954, "percentage": 97.41, "elapsed_time": "6:33:09", "remaining_time": "0:10:26"}
{"current_steps": 3735, "total_steps": 3829, "loss": 0.2435, "lr": 7.496264885780146e-08, "epoch": 6.828153564899452, "percentage": 97.55, "elapsed_time": "6:33:35", "remaining_time": "0:09:54"}
{"current_steps": 3740, "total_steps": 3829, "loss": 0.2188, "lr": 6.728380748006746e-08, "epoch": 6.837294332723949, "percentage": 97.68, "elapsed_time": "6:34:07", "remaining_time": "0:09:22"}
{"current_steps": 3745, "total_steps": 3829, "loss": 0.2065, "lr": 6.001913257479786e-08, "epoch": 6.846435100548446, "percentage": 97.81, "elapsed_time": "6:34:39", "remaining_time": "0:08:51"}
{"current_steps": 3750, "total_steps": 3829, "loss": 0.2195, "lr": 5.3168775089045274e-08, "epoch": 6.855575868372943, "percentage": 97.94, "elapsed_time": "6:35:06", "remaining_time": "0:08:19"}
{"current_steps": 3755, "total_steps": 3829, "loss": 0.2072, "lr": 4.673287736108201e-08, "epoch": 6.864716636197441, "percentage": 98.07, "elapsed_time": "6:35:41", "remaining_time": "0:07:47"}
{"current_steps": 3760, "total_steps": 3829, "loss": 0.2179, "lr": 4.0711573117442336e-08, "epoch": 6.873857404021938, "percentage": 98.2, "elapsed_time": "6:36:16", "remaining_time": "0:07:16"}
{"current_steps": 3765, "total_steps": 3829, "loss": 0.2051, "lr": 3.510498747014479e-08, "epoch": 6.8829981718464355, "percentage": 98.33, "elapsed_time": "6:36:45", "remaining_time": "0:06:44"}
{"current_steps": 3770, "total_steps": 3829, "loss": 0.2164, "lr": 2.991323691408976e-08, "epoch": 6.892138939670932, "percentage": 98.46, "elapsed_time": "6:37:13", "remaining_time": "0:06:12"}
{"current_steps": 3775, "total_steps": 3829, "loss": 0.1976, "lr": 2.5136429324643663e-08, "epoch": 6.90127970749543, "percentage": 98.59, "elapsed_time": "6:37:47", "remaining_time": "0:05:41"}
{"current_steps": 3780, "total_steps": 3829, "loss": 0.2161, "lr": 2.0774663955387408e-08, "epoch": 6.910420475319927, "percentage": 98.72, "elapsed_time": "6:38:18", "remaining_time": "0:05:09"}
{"current_steps": 3785, "total_steps": 3829, "loss": 0.224, "lr": 1.6828031436066928e-08, "epoch": 6.9195612431444244, "percentage": 98.85, "elapsed_time": "6:38:49", "remaining_time": "0:04:38"}
{"current_steps": 3790, "total_steps": 3829, "loss": 0.2076, "lr": 1.3296613770705792e-08, "epoch": 6.928702010968921, "percentage": 98.98, "elapsed_time": "6:39:25", "remaining_time": "0:04:06"}
{"current_steps": 3795, "total_steps": 3829, "loss": 0.2031, "lr": 1.0180484335893247e-08, "epoch": 6.937842778793419, "percentage": 99.11, "elapsed_time": "6:39:58", "remaining_time": "0:03:35"}
{"current_steps": 3800, "total_steps": 3829, "loss": 0.2065, "lr": 7.479707879272102e-09, "epoch": 6.946983546617916, "percentage": 99.24, "elapsed_time": "6:40:30", "remaining_time": "0:03:03"}
{"current_steps": 3805, "total_steps": 3829, "loss": 0.2334, "lr": 5.194340518182017e-09, "epoch": 6.956124314442413, "percentage": 99.37, "elapsed_time": "6:41:01", "remaining_time": "0:02:31"}
{"current_steps": 3810, "total_steps": 3829, "loss": 0.2203, "lr": 3.3244297385026657e-09, "epoch": 6.96526508226691, "percentage": 99.5, "elapsed_time": "6:41:36", "remaining_time": "0:02:00"}
{"current_steps": 3815, "total_steps": 3829, "loss": 0.2141, "lr": 1.8700143936634106e-09, "epoch": 6.974405850091408, "percentage": 99.63, "elapsed_time": "6:42:06", "remaining_time": "0:01:28"}
{"current_steps": 3820, "total_steps": 3829, "loss": 0.1958, "lr": 8.311247038328418e-10, "epoch": 6.983546617915905, "percentage": 99.76, "elapsed_time": "6:42:42", "remaining_time": "0:00:56"}
{"current_steps": 3825, "total_steps": 3829, "loss": 0.2182, "lr": 2.0778225529483053e-10, "epoch": 6.992687385740402, "percentage": 99.9, "elapsed_time": "6:43:16", "remaining_time": "0:00:25"}
{"current_steps": 3829, "total_steps": 3829, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "6:44:07", "remaining_time": "0:00:00"}

BIN
training_loss.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 45 KiB

1
vocab.json Normal file

File diff suppressed because one or more lines are too long