初始化项目,由ModelHub XC社区提供模型

Model: hahayhe/DReP-SFT-Qwen3-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-30 01:24:19 +08:00
commit 40ac01788e
22 changed files with 159031 additions and 0 deletions

36
.gitattributes vendored Normal file
View File

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

61
README.md Normal file
View File

@@ -0,0 +1,61 @@
---
library_name: transformers
license: other
base_model: Qwen/Qwen3-8B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: drep_a_half_sft
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. -->
# drep_a_half_sft
This model is a fine-tuned version of [Qwen3-8B](Qwen3-8B) on the drep_a_half_sft 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: 1e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
### Training results
### Framework versions
- Transformers 4.57.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.22.2

28
added_tokens.json Normal file
View File

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

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 4.0,
"total_flos": 1671471016509440.0,
"train_loss": 0.5990438958973561,
"train_runtime": 156717.3164,
"train_samples_per_second": 0.671,
"train_steps_per_second": 0.005
}

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": "4.57.1",
"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": "4.57.1"
}

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 sha256:1d1350d3312cfc00c3c8d658999613794958cb4e8e816a55adabcb47ca739f24
size 4902257696

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1330a8dd3595a5739181164f688655c978f78f4db6c001c417975bd198fd8d77
size 4915960368

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ad9717926a802cd67af1eac1d7e3882d287838cf7c545fa1f16bdc4184a329d9
size 4983068496

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a323ad985b31c029260eb1c945c5b6270a4d563b75550618985a8ac32426e476
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": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 4.0,
"total_flos": 1671471016509440.0,
"train_loss": 0.5990438958973561,
"train_runtime": 156717.3164,
"train_samples_per_second": 0.671,
"train_steps_per_second": 0.005
}

825
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,825 @@
{"current_steps": 1, "total_steps": 824, "loss": 1.098, "lr": 0.0, "epoch": 0.00486470051687443, "percentage": 0.12, "elapsed_time": "0:03:20", "remaining_time": "1 day, 21:49:27"}
{"current_steps": 2, "total_steps": 824, "loss": 1.0752, "lr": 1.204819277108434e-07, "epoch": 0.00972940103374886, "percentage": 0.24, "elapsed_time": "0:06:05", "remaining_time": "1 day, 17:46:24"}
{"current_steps": 3, "total_steps": 824, "loss": 1.0455, "lr": 2.409638554216868e-07, "epoch": 0.01459410155062329, "percentage": 0.36, "elapsed_time": "0:08:45", "remaining_time": "1 day, 15:57:46"}
{"current_steps": 4, "total_steps": 824, "loss": 1.0596, "lr": 3.614457831325301e-07, "epoch": 0.01945880206749772, "percentage": 0.49, "elapsed_time": "0:11:50", "remaining_time": "1 day, 16:28:18"}
{"current_steps": 5, "total_steps": 824, "loss": 1.0663, "lr": 4.819277108433736e-07, "epoch": 0.024323502584372148, "percentage": 0.61, "elapsed_time": "0:14:27", "remaining_time": "1 day, 15:29:17"}
{"current_steps": 6, "total_steps": 824, "loss": 1.0698, "lr": 6.024096385542169e-07, "epoch": 0.02918820310124658, "percentage": 0.73, "elapsed_time": "0:17:36", "remaining_time": "1 day, 16:01:41"}
{"current_steps": 7, "total_steps": 824, "loss": 1.0578, "lr": 7.228915662650602e-07, "epoch": 0.03405290361812101, "percentage": 0.85, "elapsed_time": "0:20:07", "remaining_time": "1 day, 15:09:00"}
{"current_steps": 8, "total_steps": 824, "loss": 1.0742, "lr": 8.433734939759036e-07, "epoch": 0.03891760413499544, "percentage": 0.97, "elapsed_time": "0:23:32", "remaining_time": "1 day, 16:01:48"}
{"current_steps": 9, "total_steps": 824, "loss": 1.0415, "lr": 9.638554216867472e-07, "epoch": 0.04378230465186987, "percentage": 1.09, "elapsed_time": "0:26:47", "remaining_time": "1 day, 16:25:48"}
{"current_steps": 10, "total_steps": 824, "loss": 1.081, "lr": 1.0843373493975905e-06, "epoch": 0.048647005168744296, "percentage": 1.21, "elapsed_time": "0:29:55", "remaining_time": "1 day, 16:35:52"}
{"current_steps": 11, "total_steps": 824, "loss": 1.0091, "lr": 1.2048192771084338e-06, "epoch": 0.05351170568561873, "percentage": 1.33, "elapsed_time": "0:33:24", "remaining_time": "1 day, 17:08:34"}
{"current_steps": 12, "total_steps": 824, "loss": 1.0196, "lr": 1.3253012048192773e-06, "epoch": 0.05837640620249316, "percentage": 1.46, "elapsed_time": "0:36:35", "remaining_time": "1 day, 17:15:57"}
{"current_steps": 13, "total_steps": 824, "loss": 0.9819, "lr": 1.4457831325301204e-06, "epoch": 0.06324110671936758, "percentage": 1.58, "elapsed_time": "0:39:41", "remaining_time": "1 day, 17:16:07"}
{"current_steps": 14, "total_steps": 824, "loss": 0.9871, "lr": 1.566265060240964e-06, "epoch": 0.06810580723624202, "percentage": 1.7, "elapsed_time": "0:42:32", "remaining_time": "1 day, 17:01:34"}
{"current_steps": 15, "total_steps": 824, "loss": 0.9592, "lr": 1.6867469879518073e-06, "epoch": 0.07297050775311645, "percentage": 1.82, "elapsed_time": "0:45:56", "remaining_time": "1 day, 17:17:34"}
{"current_steps": 16, "total_steps": 824, "loss": 0.95, "lr": 1.8072289156626508e-06, "epoch": 0.07783520826999088, "percentage": 1.94, "elapsed_time": "0:50:00", "remaining_time": "1 day, 18:05:17"}
{"current_steps": 17, "total_steps": 824, "loss": 0.9221, "lr": 1.9277108433734943e-06, "epoch": 0.08269990878686531, "percentage": 2.06, "elapsed_time": "0:52:55", "remaining_time": "1 day, 17:52:30"}
{"current_steps": 18, "total_steps": 824, "loss": 0.8951, "lr": 2.0481927710843377e-06, "epoch": 0.08756460930373974, "percentage": 2.18, "elapsed_time": "0:55:48", "remaining_time": "1 day, 17:38:54"}
{"current_steps": 19, "total_steps": 824, "loss": 0.9424, "lr": 2.168674698795181e-06, "epoch": 0.09242930982061417, "percentage": 2.31, "elapsed_time": "0:57:57", "remaining_time": "1 day, 16:55:15"}
{"current_steps": 20, "total_steps": 824, "loss": 0.8866, "lr": 2.2891566265060243e-06, "epoch": 0.09729401033748859, "percentage": 2.43, "elapsed_time": "1:01:17", "remaining_time": "1 day, 17:03:57"}
{"current_steps": 21, "total_steps": 824, "loss": 0.9143, "lr": 2.4096385542168676e-06, "epoch": 0.10215871085436302, "percentage": 2.55, "elapsed_time": "1:04:41", "remaining_time": "1 day, 17:13:53"}
{"current_steps": 22, "total_steps": 824, "loss": 0.9122, "lr": 2.530120481927711e-06, "epoch": 0.10702341137123746, "percentage": 2.67, "elapsed_time": "1:07:11", "remaining_time": "1 day, 16:49:19"}
{"current_steps": 23, "total_steps": 824, "loss": 0.8947, "lr": 2.6506024096385547e-06, "epoch": 0.11188811188811189, "percentage": 2.79, "elapsed_time": "1:10:53", "remaining_time": "1 day, 17:08:52"}
{"current_steps": 24, "total_steps": 824, "loss": 0.8806, "lr": 2.771084337349398e-06, "epoch": 0.11675281240498632, "percentage": 2.91, "elapsed_time": "1:13:21", "remaining_time": "1 day, 16:45:19"}
{"current_steps": 25, "total_steps": 824, "loss": 0.8649, "lr": 2.891566265060241e-06, "epoch": 0.12161751292186075, "percentage": 3.03, "elapsed_time": "1:16:42", "remaining_time": "1 day, 16:51:45"}
{"current_steps": 26, "total_steps": 824, "loss": 0.8469, "lr": 3.012048192771085e-06, "epoch": 0.12648221343873517, "percentage": 3.16, "elapsed_time": "1:19:30", "remaining_time": "1 day, 16:40:05"}
{"current_steps": 27, "total_steps": 824, "loss": 0.8466, "lr": 3.132530120481928e-06, "epoch": 0.1313469139556096, "percentage": 3.28, "elapsed_time": "1:22:31", "remaining_time": "1 day, 16:35:51"}
{"current_steps": 28, "total_steps": 824, "loss": 0.8125, "lr": 3.2530120481927713e-06, "epoch": 0.13621161447248403, "percentage": 3.4, "elapsed_time": "1:25:54", "remaining_time": "1 day, 16:42:01"}
{"current_steps": 29, "total_steps": 824, "loss": 0.8017, "lr": 3.3734939759036146e-06, "epoch": 0.14107631498935846, "percentage": 3.52, "elapsed_time": "1:28:34", "remaining_time": "1 day, 16:28:17"}
{"current_steps": 30, "total_steps": 824, "loss": 0.8006, "lr": 3.4939759036144583e-06, "epoch": 0.1459410155062329, "percentage": 3.64, "elapsed_time": "1:31:31", "remaining_time": "1 day, 16:22:11"}
{"current_steps": 31, "total_steps": 824, "loss": 0.8126, "lr": 3.6144578313253016e-06, "epoch": 0.15080571602310733, "percentage": 3.76, "elapsed_time": "1:34:57", "remaining_time": "1 day, 16:29:14"}
{"current_steps": 32, "total_steps": 824, "loss": 0.8152, "lr": 3.7349397590361445e-06, "epoch": 0.15567041653998176, "percentage": 3.88, "elapsed_time": "1:38:38", "remaining_time": "1 day, 16:41:33"}
{"current_steps": 33, "total_steps": 824, "loss": 0.7862, "lr": 3.855421686746989e-06, "epoch": 0.1605351170568562, "percentage": 4.0, "elapsed_time": "1:41:50", "remaining_time": "1 day, 16:40:57"}
{"current_steps": 34, "total_steps": 824, "loss": 0.7801, "lr": 3.975903614457832e-06, "epoch": 0.16539981757373062, "percentage": 4.13, "elapsed_time": "1:44:36", "remaining_time": "1 day, 16:30:33"}
{"current_steps": 35, "total_steps": 824, "loss": 0.817, "lr": 4.096385542168675e-06, "epoch": 0.17026451809060505, "percentage": 4.25, "elapsed_time": "1:47:33", "remaining_time": "1 day, 16:24:40"}
{"current_steps": 36, "total_steps": 824, "loss": 0.7617, "lr": 4.216867469879519e-06, "epoch": 0.1751292186074795, "percentage": 4.37, "elapsed_time": "1:50:52", "remaining_time": "1 day, 16:26:50"}
{"current_steps": 37, "total_steps": 824, "loss": 0.7619, "lr": 4.337349397590362e-06, "epoch": 0.17999391912435392, "percentage": 4.49, "elapsed_time": "1:54:20", "remaining_time": "1 day, 16:31:56"}
{"current_steps": 38, "total_steps": 824, "loss": 0.7479, "lr": 4.457831325301205e-06, "epoch": 0.18485861964122835, "percentage": 4.61, "elapsed_time": "1:57:19", "remaining_time": "1 day, 16:26:40"}
{"current_steps": 39, "total_steps": 824, "loss": 0.7454, "lr": 4.578313253012049e-06, "epoch": 0.18972332015810275, "percentage": 4.73, "elapsed_time": "2:00:24", "remaining_time": "1 day, 16:23:38"}
{"current_steps": 40, "total_steps": 824, "loss": 0.7523, "lr": 4.698795180722892e-06, "epoch": 0.19458802067497719, "percentage": 4.85, "elapsed_time": "2:03:20", "remaining_time": "1 day, 16:17:36"}
{"current_steps": 41, "total_steps": 824, "loss": 0.7409, "lr": 4.819277108433735e-06, "epoch": 0.19945272119185162, "percentage": 4.98, "elapsed_time": "2:06:24", "remaining_time": "1 day, 16:13:57"}
{"current_steps": 42, "total_steps": 824, "loss": 0.7243, "lr": 4.939759036144578e-06, "epoch": 0.20431742170872605, "percentage": 5.1, "elapsed_time": "2:09:43", "remaining_time": "1 day, 16:15:26"}
{"current_steps": 43, "total_steps": 824, "loss": 0.7402, "lr": 5.060240963855422e-06, "epoch": 0.20918212222560048, "percentage": 5.22, "elapsed_time": "2:13:01", "remaining_time": "1 day, 16:15:57"}
{"current_steps": 44, "total_steps": 824, "loss": 0.7396, "lr": 5.180722891566266e-06, "epoch": 0.2140468227424749, "percentage": 5.34, "elapsed_time": "2:15:22", "remaining_time": "1 day, 15:59:47"}
{"current_steps": 45, "total_steps": 824, "loss": 0.7238, "lr": 5.301204819277109e-06, "epoch": 0.21891152325934934, "percentage": 5.46, "elapsed_time": "2:18:39", "remaining_time": "1 day, 16:00:26"}
{"current_steps": 46, "total_steps": 824, "loss": 0.7244, "lr": 5.421686746987952e-06, "epoch": 0.22377622377622378, "percentage": 5.58, "elapsed_time": "2:22:08", "remaining_time": "1 day, 16:04:02"}
{"current_steps": 47, "total_steps": 824, "loss": 0.7147, "lr": 5.542168674698796e-06, "epoch": 0.2286409242930982, "percentage": 5.7, "elapsed_time": "2:24:57", "remaining_time": "1 day, 15:56:21"}
{"current_steps": 48, "total_steps": 824, "loss": 0.7047, "lr": 5.66265060240964e-06, "epoch": 0.23350562480997264, "percentage": 5.83, "elapsed_time": "2:28:32", "remaining_time": "1 day, 16:01:23"}
{"current_steps": 49, "total_steps": 824, "loss": 0.7156, "lr": 5.783132530120482e-06, "epoch": 0.23837032532684707, "percentage": 5.95, "elapsed_time": "2:31:49", "remaining_time": "1 day, 16:01:13"}
{"current_steps": 50, "total_steps": 824, "loss": 0.6983, "lr": 5.9036144578313255e-06, "epoch": 0.2432350258437215, "percentage": 6.07, "elapsed_time": "2:35:00", "remaining_time": "1 day, 15:59:34"}
{"current_steps": 51, "total_steps": 824, "loss": 0.6989, "lr": 6.02409638554217e-06, "epoch": 0.24809972636059593, "percentage": 6.19, "elapsed_time": "2:38:03", "remaining_time": "1 day, 15:55:44"}
{"current_steps": 52, "total_steps": 824, "loss": 0.7309, "lr": 6.144578313253012e-06, "epoch": 0.25296442687747034, "percentage": 6.31, "elapsed_time": "2:41:06", "remaining_time": "1 day, 15:51:50"}
{"current_steps": 53, "total_steps": 824, "loss": 0.6957, "lr": 6.265060240963856e-06, "epoch": 0.25782912739434477, "percentage": 6.43, "elapsed_time": "2:44:36", "remaining_time": "1 day, 15:54:41"}
{"current_steps": 54, "total_steps": 824, "loss": 0.7156, "lr": 6.385542168674699e-06, "epoch": 0.2626938279112192, "percentage": 6.55, "elapsed_time": "2:47:40", "remaining_time": "1 day, 15:50:49"}
{"current_steps": 55, "total_steps": 824, "loss": 0.7272, "lr": 6.5060240963855425e-06, "epoch": 0.26755852842809363, "percentage": 6.67, "elapsed_time": "2:51:23", "remaining_time": "1 day, 15:56:25"}
{"current_steps": 56, "total_steps": 824, "loss": 0.6986, "lr": 6.626506024096386e-06, "epoch": 0.27242322894496807, "percentage": 6.8, "elapsed_time": "2:54:51", "remaining_time": "1 day, 15:58:03"}
{"current_steps": 57, "total_steps": 824, "loss": 0.6925, "lr": 6.746987951807229e-06, "epoch": 0.2772879294618425, "percentage": 6.92, "elapsed_time": "2:57:56", "remaining_time": "1 day, 15:54:28"}
{"current_steps": 58, "total_steps": 824, "loss": 0.6746, "lr": 6.867469879518073e-06, "epoch": 0.28215262997871693, "percentage": 7.04, "elapsed_time": "3:01:45", "remaining_time": "1 day, 16:00:29"}
{"current_steps": 59, "total_steps": 824, "loss": 0.6751, "lr": 6.987951807228917e-06, "epoch": 0.28701733049559136, "percentage": 7.16, "elapsed_time": "3:04:38", "remaining_time": "1 day, 15:54:00"}
{"current_steps": 60, "total_steps": 824, "loss": 0.6925, "lr": 7.1084337349397595e-06, "epoch": 0.2918820310124658, "percentage": 7.28, "elapsed_time": "3:07:50", "remaining_time": "1 day, 15:51:50"}
{"current_steps": 61, "total_steps": 824, "loss": 0.6892, "lr": 7.228915662650603e-06, "epoch": 0.2967467315293402, "percentage": 7.4, "elapsed_time": "3:10:56", "remaining_time": "1 day, 15:48:21"}
{"current_steps": 62, "total_steps": 824, "loss": 0.6879, "lr": 7.349397590361447e-06, "epoch": 0.30161143204621466, "percentage": 7.52, "elapsed_time": "3:13:54", "remaining_time": "1 day, 15:43:15"}
{"current_steps": 63, "total_steps": 824, "loss": 0.6598, "lr": 7.469879518072289e-06, "epoch": 0.3064761325630891, "percentage": 7.65, "elapsed_time": "3:16:54", "remaining_time": "1 day, 15:38:32"}
{"current_steps": 64, "total_steps": 824, "loss": 0.6695, "lr": 7.590361445783133e-06, "epoch": 0.3113408330799635, "percentage": 7.77, "elapsed_time": "3:20:29", "remaining_time": "1 day, 15:40:51"}
{"current_steps": 65, "total_steps": 824, "loss": 0.6839, "lr": 7.710843373493977e-06, "epoch": 0.31620553359683795, "percentage": 7.89, "elapsed_time": "3:24:26", "remaining_time": "1 day, 15:47:16"}
{"current_steps": 66, "total_steps": 824, "loss": 0.6669, "lr": 7.83132530120482e-06, "epoch": 0.3210702341137124, "percentage": 8.01, "elapsed_time": "3:27:24", "remaining_time": "1 day, 15:42:02"}
{"current_steps": 67, "total_steps": 824, "loss": 0.6666, "lr": 7.951807228915663e-06, "epoch": 0.3259349346305868, "percentage": 8.13, "elapsed_time": "3:31:00", "remaining_time": "1 day, 15:44:01"}
{"current_steps": 68, "total_steps": 824, "loss": 0.7033, "lr": 8.072289156626508e-06, "epoch": 0.33079963514746125, "percentage": 8.25, "elapsed_time": "3:35:13", "remaining_time": "1 day, 15:52:51"}
{"current_steps": 69, "total_steps": 824, "loss": 0.7107, "lr": 8.19277108433735e-06, "epoch": 0.3356643356643357, "percentage": 8.37, "elapsed_time": "3:38:35", "remaining_time": "1 day, 15:51:47"}
{"current_steps": 70, "total_steps": 824, "loss": 0.6713, "lr": 8.313253012048194e-06, "epoch": 0.3405290361812101, "percentage": 8.5, "elapsed_time": "3:41:52", "remaining_time": "1 day, 15:49:52"}
{"current_steps": 71, "total_steps": 824, "loss": 0.6544, "lr": 8.433734939759038e-06, "epoch": 0.34539373669808454, "percentage": 8.62, "elapsed_time": "3:45:00", "remaining_time": "1 day, 15:46:21"}
{"current_steps": 72, "total_steps": 824, "loss": 0.6748, "lr": 8.55421686746988e-06, "epoch": 0.350258437214959, "percentage": 8.74, "elapsed_time": "3:47:47", "remaining_time": "1 day, 15:39:09"}
{"current_steps": 73, "total_steps": 824, "loss": 0.6637, "lr": 8.674698795180724e-06, "epoch": 0.3551231377318334, "percentage": 8.86, "elapsed_time": "3:50:31", "remaining_time": "1 day, 15:31:35"}
{"current_steps": 74, "total_steps": 824, "loss": 0.6717, "lr": 8.795180722891567e-06, "epoch": 0.35998783824870784, "percentage": 8.98, "elapsed_time": "3:53:21", "remaining_time": "1 day, 15:25:02"}
{"current_steps": 75, "total_steps": 824, "loss": 0.6592, "lr": 8.91566265060241e-06, "epoch": 0.36485253876558227, "percentage": 9.1, "elapsed_time": "3:57:08", "remaining_time": "1 day, 15:28:17"}
{"current_steps": 76, "total_steps": 824, "loss": 0.6478, "lr": 9.036144578313254e-06, "epoch": 0.3697172392824567, "percentage": 9.22, "elapsed_time": "3:59:22", "remaining_time": "1 day, 15:16:01"}
{"current_steps": 77, "total_steps": 824, "loss": 0.6695, "lr": 9.156626506024097e-06, "epoch": 0.3745819397993311, "percentage": 9.34, "elapsed_time": "4:03:12", "remaining_time": "1 day, 15:19:27"}
{"current_steps": 78, "total_steps": 824, "loss": 0.694, "lr": 9.27710843373494e-06, "epoch": 0.3794466403162055, "percentage": 9.47, "elapsed_time": "4:06:09", "remaining_time": "1 day, 15:14:19"}
{"current_steps": 79, "total_steps": 824, "loss": 0.6842, "lr": 9.397590361445785e-06, "epoch": 0.38431134083307994, "percentage": 9.59, "elapsed_time": "4:09:12", "remaining_time": "1 day, 15:10:09"}
{"current_steps": 80, "total_steps": 824, "loss": 0.6735, "lr": 9.518072289156628e-06, "epoch": 0.38917604134995437, "percentage": 9.71, "elapsed_time": "4:12:18", "remaining_time": "1 day, 15:06:26"}
{"current_steps": 81, "total_steps": 824, "loss": 0.7076, "lr": 9.63855421686747e-06, "epoch": 0.3940407418668288, "percentage": 9.83, "elapsed_time": "4:15:32", "remaining_time": "1 day, 15:03:58"}
{"current_steps": 82, "total_steps": 824, "loss": 0.6481, "lr": 9.759036144578315e-06, "epoch": 0.39890544238370323, "percentage": 9.95, "elapsed_time": "4:18:17", "remaining_time": "1 day, 14:57:15"}
{"current_steps": 83, "total_steps": 824, "loss": 0.6628, "lr": 9.879518072289156e-06, "epoch": 0.40377014290057767, "percentage": 10.07, "elapsed_time": "4:22:12", "remaining_time": "1 day, 15:00:55"}
{"current_steps": 84, "total_steps": 824, "loss": 0.662, "lr": 1e-05, "epoch": 0.4086348434174521, "percentage": 10.19, "elapsed_time": "4:25:34", "remaining_time": "1 day, 14:59:39"}
{"current_steps": 85, "total_steps": 824, "loss": 0.6602, "lr": 9.99995506314361e-06, "epoch": 0.41349954393432653, "percentage": 10.32, "elapsed_time": "4:28:52", "remaining_time": "1 day, 14:57:39"}
{"current_steps": 86, "total_steps": 824, "loss": 0.6882, "lr": 9.99982025338217e-06, "epoch": 0.41836424445120096, "percentage": 10.44, "elapsed_time": "4:31:58", "remaining_time": "1 day, 14:53:59"}
{"current_steps": 87, "total_steps": 824, "loss": 0.6329, "lr": 9.999595573138845e-06, "epoch": 0.4232289449680754, "percentage": 10.56, "elapsed_time": "4:35:09", "remaining_time": "1 day, 14:50:57"}
{"current_steps": 88, "total_steps": 824, "loss": 0.6571, "lr": 9.99928102645221e-06, "epoch": 0.4280936454849498, "percentage": 10.68, "elapsed_time": "4:37:47", "remaining_time": "1 day, 14:43:19"}
{"current_steps": 89, "total_steps": 824, "loss": 0.6385, "lr": 9.99887661897616e-06, "epoch": 0.43295834600182426, "percentage": 10.8, "elapsed_time": "4:41:21", "remaining_time": "1 day, 14:43:31"}
{"current_steps": 90, "total_steps": 824, "loss": 0.6674, "lr": 9.99838235797981e-06, "epoch": 0.4378230465186987, "percentage": 10.92, "elapsed_time": "4:44:36", "remaining_time": "1 day, 14:41:04"}
{"current_steps": 91, "total_steps": 824, "loss": 0.6045, "lr": 9.997798252347382e-06, "epoch": 0.4426877470355731, "percentage": 11.04, "elapsed_time": "4:47:37", "remaining_time": "1 day, 14:36:50"}
{"current_steps": 92, "total_steps": 824, "loss": 0.6292, "lr": 9.99712431257802e-06, "epoch": 0.44755244755244755, "percentage": 11.17, "elapsed_time": "4:50:16", "remaining_time": "1 day, 14:29:36"}
{"current_steps": 93, "total_steps": 824, "loss": 0.6754, "lr": 9.996360550785619e-06, "epoch": 0.452417148069322, "percentage": 11.29, "elapsed_time": "4:53:51", "remaining_time": "1 day, 14:29:49"}
{"current_steps": 94, "total_steps": 824, "loss": 0.6515, "lr": 9.9955069806986e-06, "epoch": 0.4572818485861964, "percentage": 11.41, "elapsed_time": "4:57:49", "remaining_time": "1 day, 14:32:52"}
{"current_steps": 95, "total_steps": 824, "loss": 0.6487, "lr": 9.994563617659665e-06, "epoch": 0.46214654910307085, "percentage": 11.53, "elapsed_time": "5:01:08", "remaining_time": "1 day, 14:30:52"}
{"current_steps": 96, "total_steps": 824, "loss": 0.6463, "lr": 9.993530478625524e-06, "epoch": 0.4670112496199453, "percentage": 11.65, "elapsed_time": "5:05:11", "remaining_time": "1 day, 14:34:19"}
{"current_steps": 97, "total_steps": 824, "loss": 0.6144, "lr": 9.992407582166582e-06, "epoch": 0.4718759501368197, "percentage": 11.77, "elapsed_time": "5:08:41", "remaining_time": "1 day, 14:33:32"}
{"current_steps": 98, "total_steps": 824, "loss": 0.6583, "lr": 9.991194948466615e-06, "epoch": 0.47674065065369414, "percentage": 11.89, "elapsed_time": "5:11:53", "remaining_time": "1 day, 14:30:31"}
{"current_steps": 99, "total_steps": 824, "loss": 0.6366, "lr": 9.989892599322404e-06, "epoch": 0.4816053511705686, "percentage": 12.01, "elapsed_time": "5:14:44", "remaining_time": "1 day, 14:24:54"}
{"current_steps": 100, "total_steps": 824, "loss": 0.6683, "lr": 9.988500558143337e-06, "epoch": 0.486470051687443, "percentage": 12.14, "elapsed_time": "5:17:45", "remaining_time": "1 day, 14:20:33"}
{"current_steps": 101, "total_steps": 824, "loss": 0.6542, "lr": 9.987018849950996e-06, "epoch": 0.49133475220431744, "percentage": 12.26, "elapsed_time": "5:21:08", "remaining_time": "1 day, 14:18:53"}
{"current_steps": 102, "total_steps": 824, "loss": 0.6464, "lr": 9.985447501378706e-06, "epoch": 0.49619945272119187, "percentage": 12.38, "elapsed_time": "5:24:17", "remaining_time": "1 day, 14:15:25"}
{"current_steps": 103, "total_steps": 824, "loss": 0.6409, "lr": 9.983786540671052e-06, "epoch": 0.5010641532380663, "percentage": 12.5, "elapsed_time": "5:26:51", "remaining_time": "1 day, 14:07:58"}
{"current_steps": 104, "total_steps": 824, "loss": 0.6399, "lr": 9.982035997683372e-06, "epoch": 0.5059288537549407, "percentage": 12.62, "elapsed_time": "5:30:00", "remaining_time": "1 day, 14:04:42"}
{"current_steps": 105, "total_steps": 824, "loss": 0.6419, "lr": 9.980195903881231e-06, "epoch": 0.5107935542718152, "percentage": 12.74, "elapsed_time": "5:34:00", "remaining_time": "1 day, 14:07:10"}
{"current_steps": 106, "total_steps": 824, "loss": 0.6561, "lr": 9.978266292339838e-06, "epoch": 0.5156582547886895, "percentage": 12.86, "elapsed_time": "5:36:47", "remaining_time": "1 day, 14:01:20"}
{"current_steps": 107, "total_steps": 824, "loss": 0.6362, "lr": 9.976247197743465e-06, "epoch": 0.520522955305564, "percentage": 12.99, "elapsed_time": "5:40:32", "remaining_time": "1 day, 14:01:58"}
{"current_steps": 108, "total_steps": 824, "loss": 0.6346, "lr": 9.974138656384815e-06, "epoch": 0.5253876558224384, "percentage": 13.11, "elapsed_time": "5:44:01", "remaining_time": "1 day, 14:00:47"}
{"current_steps": 109, "total_steps": 824, "loss": 0.6398, "lr": 9.97194070616438e-06, "epoch": 0.5302523563393129, "percentage": 13.23, "elapsed_time": "5:46:41", "remaining_time": "1 day, 13:54:08"}
{"current_steps": 110, "total_steps": 824, "loss": 0.6455, "lr": 9.969653386589749e-06, "epoch": 0.5351170568561873, "percentage": 13.35, "elapsed_time": "5:49:44", "remaining_time": "1 day, 13:50:06"}
{"current_steps": 111, "total_steps": 824, "loss": 0.6372, "lr": 9.967276738774897e-06, "epoch": 0.5399817573730618, "percentage": 13.47, "elapsed_time": "5:53:29", "remaining_time": "1 day, 13:50:40"}
{"current_steps": 112, "total_steps": 824, "loss": 0.6495, "lr": 9.964810805439464e-06, "epoch": 0.5448464578899361, "percentage": 13.59, "elapsed_time": "5:57:00", "remaining_time": "1 day, 13:49:35"}
{"current_steps": 113, "total_steps": 824, "loss": 0.6604, "lr": 9.962255630907964e-06, "epoch": 0.5497111584068106, "percentage": 13.71, "elapsed_time": "5:59:49", "remaining_time": "1 day, 13:44:03"}
{"current_steps": 114, "total_steps": 824, "loss": 0.6268, "lr": 9.959611261108999e-06, "epoch": 0.554575858923685, "percentage": 13.83, "elapsed_time": "6:02:52", "remaining_time": "1 day, 13:40:01"}
{"current_steps": 115, "total_steps": 824, "loss": 0.657, "lr": 9.956877743574437e-06, "epoch": 0.5594405594405595, "percentage": 13.96, "elapsed_time": "6:05:57", "remaining_time": "1 day, 13:36:14"}
{"current_steps": 116, "total_steps": 824, "loss": 0.6326, "lr": 9.954055127438554e-06, "epoch": 0.5643052599574339, "percentage": 14.08, "elapsed_time": "6:10:06", "remaining_time": "1 day, 13:38:53"}
{"current_steps": 117, "total_steps": 824, "loss": 0.6171, "lr": 9.951143463437145e-06, "epoch": 0.5691699604743083, "percentage": 14.2, "elapsed_time": "6:13:19", "remaining_time": "1 day, 13:35:51"}
{"current_steps": 118, "total_steps": 824, "loss": 0.6416, "lr": 9.948142803906623e-06, "epoch": 0.5740346609911827, "percentage": 14.32, "elapsed_time": "6:16:19", "remaining_time": "1 day, 13:31:36"}
{"current_steps": 119, "total_steps": 824, "loss": 0.6509, "lr": 9.94505320278307e-06, "epoch": 0.5788993615080572, "percentage": 14.44, "elapsed_time": "6:19:26", "remaining_time": "1 day, 13:27:54"}
{"current_steps": 120, "total_steps": 824, "loss": 0.6386, "lr": 9.94187471560127e-06, "epoch": 0.5837640620249316, "percentage": 14.56, "elapsed_time": "6:22:09", "remaining_time": "1 day, 13:21:57"}
{"current_steps": 121, "total_steps": 824, "loss": 0.6398, "lr": 9.938607399493714e-06, "epoch": 0.5886287625418061, "percentage": 14.68, "elapsed_time": "6:25:31", "remaining_time": "1 day, 13:19:51"}
{"current_steps": 122, "total_steps": 824, "loss": 0.6712, "lr": 9.935251313189564e-06, "epoch": 0.5934934630586804, "percentage": 14.81, "elapsed_time": "6:28:21", "remaining_time": "1 day, 13:14:38"}
{"current_steps": 123, "total_steps": 824, "loss": 0.6457, "lr": 9.931806517013612e-06, "epoch": 0.5983581635755548, "percentage": 14.93, "elapsed_time": "6:31:08", "remaining_time": "1 day, 13:09:12"}
{"current_steps": 124, "total_steps": 824, "loss": 0.6619, "lr": 9.92827307288518e-06, "epoch": 0.6032228640924293, "percentage": 15.05, "elapsed_time": "6:34:33", "remaining_time": "1 day, 13:07:20"}
{"current_steps": 125, "total_steps": 824, "loss": 0.6303, "lr": 9.924651044317017e-06, "epoch": 0.6080875646093037, "percentage": 15.17, "elapsed_time": "6:37:30", "remaining_time": "1 day, 13:02:53"}
{"current_steps": 126, "total_steps": 824, "loss": 0.6276, "lr": 9.920940496414153e-06, "epoch": 0.6129522651261782, "percentage": 15.29, "elapsed_time": "6:41:23", "remaining_time": "1 day, 13:03:36"}
{"current_steps": 127, "total_steps": 824, "loss": 0.6373, "lr": 9.917141495872733e-06, "epoch": 0.6178169656430526, "percentage": 15.41, "elapsed_time": "6:44:40", "remaining_time": "1 day, 13:00:55"}
{"current_steps": 128, "total_steps": 824, "loss": 0.6494, "lr": 9.913254110978812e-06, "epoch": 0.622681666159927, "percentage": 15.53, "elapsed_time": "6:47:49", "remaining_time": "1 day, 12:57:34"}
{"current_steps": 129, "total_steps": 824, "loss": 0.6393, "lr": 9.909278411607134e-06, "epoch": 0.6275463666768014, "percentage": 15.66, "elapsed_time": "6:50:38", "remaining_time": "1 day, 12:52:24"}
{"current_steps": 130, "total_steps": 824, "loss": 0.609, "lr": 9.90521446921987e-06, "epoch": 0.6324110671936759, "percentage": 15.78, "elapsed_time": "6:53:13", "remaining_time": "1 day, 12:46:00"}
{"current_steps": 131, "total_steps": 824, "loss": 0.6486, "lr": 9.90106235686534e-06, "epoch": 0.6372757677105503, "percentage": 15.9, "elapsed_time": "6:57:26", "remaining_time": "1 day, 12:48:16"}
{"current_steps": 132, "total_steps": 824, "loss": 0.6556, "lr": 9.896822149176695e-06, "epoch": 0.6421404682274248, "percentage": 16.02, "elapsed_time": "7:00:21", "remaining_time": "1 day, 12:43:43"}
{"current_steps": 133, "total_steps": 824, "loss": 0.6393, "lr": 9.892493922370575e-06, "epoch": 0.6470051687442991, "percentage": 16.14, "elapsed_time": "7:03:50", "remaining_time": "1 day, 12:42:04"}
{"current_steps": 134, "total_steps": 824, "loss": 0.647, "lr": 9.888077754245741e-06, "epoch": 0.6518698692611736, "percentage": 16.26, "elapsed_time": "7:06:43", "remaining_time": "1 day, 12:37:20"}
{"current_steps": 135, "total_steps": 824, "loss": 0.6641, "lr": 9.883573724181683e-06, "epoch": 0.656734569778048, "percentage": 16.38, "elapsed_time": "7:09:48", "remaining_time": "1 day, 12:33:34"}
{"current_steps": 136, "total_steps": 824, "loss": 0.6357, "lr": 9.878981913137178e-06, "epoch": 0.6615992702949225, "percentage": 16.5, "elapsed_time": "7:13:00", "remaining_time": "1 day, 12:30:30"}
{"current_steps": 137, "total_steps": 824, "loss": 0.6414, "lr": 9.87430240364885e-06, "epoch": 0.6664639708117969, "percentage": 16.63, "elapsed_time": "7:16:35", "remaining_time": "1 day, 12:29:20"}
{"current_steps": 138, "total_steps": 824, "loss": 0.6373, "lr": 9.869535279829674e-06, "epoch": 0.6713286713286714, "percentage": 16.75, "elapsed_time": "7:19:36", "remaining_time": "1 day, 12:25:16"}
{"current_steps": 139, "total_steps": 824, "loss": 0.6444, "lr": 9.864680627367476e-06, "epoch": 0.6761933718455457, "percentage": 16.87, "elapsed_time": "7:23:55", "remaining_time": "1 day, 12:27:40"}
{"current_steps": 140, "total_steps": 824, "loss": 0.6342, "lr": 9.859738533523384e-06, "epoch": 0.6810580723624202, "percentage": 16.99, "elapsed_time": "7:27:01", "remaining_time": "1 day, 12:24:02"}
{"current_steps": 141, "total_steps": 824, "loss": 0.6343, "lr": 9.854709087130261e-06, "epoch": 0.6859227728792946, "percentage": 17.11, "elapsed_time": "7:30:08", "remaining_time": "1 day, 12:20:26"}
{"current_steps": 142, "total_steps": 824, "loss": 0.6535, "lr": 9.849592378591113e-06, "epoch": 0.6907874733961691, "percentage": 17.23, "elapsed_time": "7:32:55", "remaining_time": "1 day, 12:15:20"}
{"current_steps": 143, "total_steps": 824, "loss": 0.6356, "lr": 9.844388499877457e-06, "epoch": 0.6956521739130435, "percentage": 17.35, "elapsed_time": "7:36:20", "remaining_time": "1 day, 12:13:11"}
{"current_steps": 144, "total_steps": 824, "loss": 0.6205, "lr": 9.839097544527674e-06, "epoch": 0.700516874429918, "percentage": 17.48, "elapsed_time": "7:39:03", "remaining_time": "1 day, 12:07:44"}
{"current_steps": 145, "total_steps": 824, "loss": 0.6192, "lr": 9.833719607645325e-06, "epoch": 0.7053815749467923, "percentage": 17.6, "elapsed_time": "7:41:49", "remaining_time": "1 day, 12:02:38"}
{"current_steps": 146, "total_steps": 824, "loss": 0.637, "lr": 9.82825478589744e-06, "epoch": 0.7102462754636668, "percentage": 17.72, "elapsed_time": "7:45:19", "remaining_time": "1 day, 12:00:54"}
{"current_steps": 147, "total_steps": 824, "loss": 0.6507, "lr": 9.822703177512783e-06, "epoch": 0.7151109759805412, "percentage": 17.84, "elapsed_time": "7:49:18", "remaining_time": "1 day, 12:01:22"}
{"current_steps": 148, "total_steps": 824, "loss": 0.6221, "lr": 9.817064882280085e-06, "epoch": 0.7199756764974157, "percentage": 17.96, "elapsed_time": "7:52:24", "remaining_time": "1 day, 11:57:43"}
{"current_steps": 149, "total_steps": 824, "loss": 0.6237, "lr": 9.811340001546252e-06, "epoch": 0.72484037701429, "percentage": 18.08, "elapsed_time": "7:55:13", "remaining_time": "1 day, 11:52:49"}
{"current_steps": 150, "total_steps": 824, "loss": 0.6327, "lr": 9.805528638214543e-06, "epoch": 0.7297050775311645, "percentage": 18.2, "elapsed_time": "7:58:39", "remaining_time": "1 day, 11:50:45"}
{"current_steps": 151, "total_steps": 824, "loss": 0.6284, "lr": 9.799630896742716e-06, "epoch": 0.7345697780480389, "percentage": 18.33, "elapsed_time": "8:01:31", "remaining_time": "1 day, 11:46:08"}
{"current_steps": 152, "total_steps": 824, "loss": 0.6154, "lr": 9.793646883141155e-06, "epoch": 0.7394344785649134, "percentage": 18.45, "elapsed_time": "8:05:03", "remaining_time": "1 day, 11:44:29"}
{"current_steps": 153, "total_steps": 824, "loss": 0.6227, "lr": 9.787576704970965e-06, "epoch": 0.7442991790817878, "percentage": 18.57, "elapsed_time": "8:08:36", "remaining_time": "1 day, 11:42:50"}
{"current_steps": 154, "total_steps": 824, "loss": 0.6314, "lr": 9.781420471342035e-06, "epoch": 0.7491638795986622, "percentage": 18.69, "elapsed_time": "8:12:16", "remaining_time": "1 day, 11:41:42"}
{"current_steps": 155, "total_steps": 824, "loss": 0.6318, "lr": 9.77517829291108e-06, "epoch": 0.7540285801155366, "percentage": 18.81, "elapsed_time": "8:15:12", "remaining_time": "1 day, 11:37:21"}
{"current_steps": 156, "total_steps": 824, "loss": 0.6448, "lr": 9.768850281879651e-06, "epoch": 0.758893280632411, "percentage": 18.93, "elapsed_time": "8:17:47", "remaining_time": "1 day, 11:31:33"}
{"current_steps": 157, "total_steps": 824, "loss": 0.6343, "lr": 9.762436551992117e-06, "epoch": 0.7637579811492855, "percentage": 19.05, "elapsed_time": "8:20:27", "remaining_time": "1 day, 11:26:10"}
{"current_steps": 158, "total_steps": 824, "loss": 0.628, "lr": 9.755937218533622e-06, "epoch": 0.7686226816661599, "percentage": 19.17, "elapsed_time": "8:23:33", "remaining_time": "1 day, 11:22:36"}
{"current_steps": 159, "total_steps": 824, "loss": 0.6215, "lr": 9.74935239832801e-06, "epoch": 0.7734873821830344, "percentage": 19.3, "elapsed_time": "8:26:56", "remaining_time": "1 day, 11:20:14"}
{"current_steps": 160, "total_steps": 824, "loss": 0.6373, "lr": 9.742682209735727e-06, "epoch": 0.7783520826999087, "percentage": 19.42, "elapsed_time": "8:31:08", "remaining_time": "1 day, 11:21:12"}
{"current_steps": 161, "total_steps": 824, "loss": 0.6311, "lr": 9.735926772651703e-06, "epoch": 0.7832167832167832, "percentage": 19.54, "elapsed_time": "8:34:19", "remaining_time": "1 day, 11:18:00"}
{"current_steps": 162, "total_steps": 824, "loss": 0.6424, "lr": 9.729086208503174e-06, "epoch": 0.7880814837336576, "percentage": 19.66, "elapsed_time": "8:37:30", "remaining_time": "1 day, 11:14:47"}
{"current_steps": 163, "total_steps": 824, "loss": 0.5911, "lr": 9.722160640247523e-06, "epoch": 0.7929461842505321, "percentage": 19.78, "elapsed_time": "8:41:39", "remaining_time": "1 day, 11:15:26"}
{"current_steps": 164, "total_steps": 824, "loss": 0.6413, "lr": 9.715150192370054e-06, "epoch": 0.7978108847674065, "percentage": 19.9, "elapsed_time": "8:44:00", "remaining_time": "1 day, 11:08:48"}
{"current_steps": 165, "total_steps": 824, "loss": 0.6179, "lr": 9.708054990881763e-06, "epoch": 0.802675585284281, "percentage": 20.02, "elapsed_time": "8:47:00", "remaining_time": "1 day, 11:04:51"}
{"current_steps": 166, "total_steps": 824, "loss": 0.6237, "lr": 9.700875163317072e-06, "epoch": 0.8075402858011553, "percentage": 20.15, "elapsed_time": "8:50:17", "remaining_time": "1 day, 11:01:59"}
{"current_steps": 167, "total_steps": 824, "loss": 0.6079, "lr": 9.693610838731532e-06, "epoch": 0.8124049863180298, "percentage": 20.27, "elapsed_time": "8:53:47", "remaining_time": "1 day, 11:00:01"}
{"current_steps": 168, "total_steps": 824, "loss": 0.6257, "lr": 9.686262147699507e-06, "epoch": 0.8172696868349042, "percentage": 20.39, "elapsed_time": "8:56:53", "remaining_time": "1 day, 10:56:26"}
{"current_steps": 169, "total_steps": 824, "loss": 0.6209, "lr": 9.678829222311827e-06, "epoch": 0.8221343873517787, "percentage": 20.51, "elapsed_time": "8:59:59", "remaining_time": "1 day, 10:52:52"}
{"current_steps": 170, "total_steps": 824, "loss": 0.6409, "lr": 9.671312196173413e-06, "epoch": 0.8269990878686531, "percentage": 20.63, "elapsed_time": "9:03:29", "remaining_time": "1 day, 10:50:52"}
{"current_steps": 171, "total_steps": 824, "loss": 0.6232, "lr": 9.663711204400872e-06, "epoch": 0.8318637883855275, "percentage": 20.75, "elapsed_time": "9:06:22", "remaining_time": "1 day, 10:46:25"}
{"current_steps": 172, "total_steps": 824, "loss": 0.6353, "lr": 9.656026383620076e-06, "epoch": 0.8367284889024019, "percentage": 20.87, "elapsed_time": "9:08:53", "remaining_time": "1 day, 10:40:42"}
{"current_steps": 173, "total_steps": 824, "loss": 0.6433, "lr": 9.6482578719637e-06, "epoch": 0.8415931894192764, "percentage": 21.0, "elapsed_time": "9:11:55", "remaining_time": "1 day, 10:36:55"}
{"current_steps": 174, "total_steps": 824, "loss": 0.6336, "lr": 9.640405809068743e-06, "epoch": 0.8464578899361508, "percentage": 21.12, "elapsed_time": "9:15:05", "remaining_time": "1 day, 10:33:37"}
{"current_steps": 175, "total_steps": 824, "loss": 0.6284, "lr": 9.632470336074009e-06, "epoch": 0.8513225904530253, "percentage": 21.24, "elapsed_time": "9:18:10", "remaining_time": "1 day, 10:30:02"}
{"current_steps": 176, "total_steps": 824, "loss": 0.6222, "lr": 9.624451595617588e-06, "epoch": 0.8561872909698997, "percentage": 21.36, "elapsed_time": "9:21:04", "remaining_time": "1 day, 10:25:48"}
{"current_steps": 177, "total_steps": 824, "loss": 0.636, "lr": 9.616349731834271e-06, "epoch": 0.8610519914867741, "percentage": 21.48, "elapsed_time": "9:23:43", "remaining_time": "1 day, 10:20:36"}
{"current_steps": 178, "total_steps": 824, "loss": 0.6511, "lr": 9.608164890352977e-06, "epoch": 0.8659166920036485, "percentage": 21.6, "elapsed_time": "9:27:25", "remaining_time": "1 day, 10:19:18"}
{"current_steps": 179, "total_steps": 824, "loss": 0.611, "lr": 9.599897218294122e-06, "epoch": 0.870781392520523, "percentage": 21.72, "elapsed_time": "9:30:17", "remaining_time": "1 day, 10:14:57"}
{"current_steps": 180, "total_steps": 824, "loss": 0.6015, "lr": 9.591546864266983e-06, "epoch": 0.8756460930373974, "percentage": 21.84, "elapsed_time": "9:33:09", "remaining_time": "1 day, 10:10:36"}
{"current_steps": 181, "total_steps": 824, "loss": 0.6248, "lr": 9.583113978367026e-06, "epoch": 0.8805107935542719, "percentage": 21.97, "elapsed_time": "9:36:19", "remaining_time": "1 day, 10:07:24"}
{"current_steps": 182, "total_steps": 824, "loss": 0.6362, "lr": 9.574598712173202e-06, "epoch": 0.8853754940711462, "percentage": 22.09, "elapsed_time": "9:39:22", "remaining_time": "1 day, 10:03:43"}
{"current_steps": 183, "total_steps": 824, "loss": 0.627, "lr": 9.56600121874523e-06, "epoch": 0.8902401945880207, "percentage": 22.21, "elapsed_time": "9:42:44", "remaining_time": "1 day, 10:01:10"}
{"current_steps": 184, "total_steps": 824, "loss": 0.6395, "lr": 9.557321652620839e-06, "epoch": 0.8951048951048951, "percentage": 22.33, "elapsed_time": "9:45:53", "remaining_time": "1 day, 9:57:51"}
{"current_steps": 185, "total_steps": 824, "loss": 0.6329, "lr": 9.548560169812997e-06, "epoch": 0.8999695956217695, "percentage": 22.45, "elapsed_time": "9:49:14", "remaining_time": "1 day, 9:55:15"}
{"current_steps": 186, "total_steps": 824, "loss": 0.6296, "lr": 9.539716927807102e-06, "epoch": 0.904834296138644, "percentage": 22.57, "elapsed_time": "9:51:58", "remaining_time": "1 day, 9:50:33"}
{"current_steps": 187, "total_steps": 824, "loss": 0.6189, "lr": 9.530792085558151e-06, "epoch": 0.9096989966555183, "percentage": 22.69, "elapsed_time": "9:55:15", "remaining_time": "1 day, 9:47:41"}
{"current_steps": 188, "total_steps": 824, "loss": 0.6324, "lr": 9.521785803487888e-06, "epoch": 0.9145636971723928, "percentage": 22.82, "elapsed_time": "9:58:19", "remaining_time": "1 day, 9:44:08"}
{"current_steps": 189, "total_steps": 824, "loss": 0.6453, "lr": 9.512698243481914e-06, "epoch": 0.9194283976892672, "percentage": 22.94, "elapsed_time": "10:01:34", "remaining_time": "1 day, 9:41:08"}
{"current_steps": 190, "total_steps": 824, "loss": 0.6252, "lr": 9.50352956888678e-06, "epoch": 0.9242930982061417, "percentage": 23.06, "elapsed_time": "10:04:33", "remaining_time": "1 day, 9:37:17"}
{"current_steps": 191, "total_steps": 824, "loss": 0.6031, "lr": 9.49427994450705e-06, "epoch": 0.9291577987230161, "percentage": 23.18, "elapsed_time": "10:07:57", "remaining_time": "1 day, 9:34:51"}
{"current_steps": 192, "total_steps": 824, "loss": 0.6392, "lr": 9.484949536602343e-06, "epoch": 0.9340224992398906, "percentage": 23.3, "elapsed_time": "10:11:37", "remaining_time": "1 day, 9:33:16"}
{"current_steps": 193, "total_steps": 824, "loss": 0.6248, "lr": 9.47553851288434e-06, "epoch": 0.9388871997567649, "percentage": 23.42, "elapsed_time": "10:14:40", "remaining_time": "1 day, 9:29:39"}
{"current_steps": 194, "total_steps": 824, "loss": 0.6364, "lr": 9.466047042513767e-06, "epoch": 0.9437519002736394, "percentage": 23.54, "elapsed_time": "10:18:12", "remaining_time": "1 day, 9:27:33"}
{"current_steps": 195, "total_steps": 824, "loss": 0.6357, "lr": 9.45647529609736e-06, "epoch": 0.9486166007905138, "percentage": 23.67, "elapsed_time": "10:21:17", "remaining_time": "1 day, 9:24:03"}
{"current_steps": 196, "total_steps": 824, "loss": 0.6447, "lr": 9.4468234456848e-06, "epoch": 0.9534813013073883, "percentage": 23.79, "elapsed_time": "10:24:38", "remaining_time": "1 day, 9:21:23"}
{"current_steps": 197, "total_steps": 824, "loss": 0.5999, "lr": 9.437091664765611e-06, "epoch": 0.9583460018242627, "percentage": 23.91, "elapsed_time": "10:27:51", "remaining_time": "1 day, 9:18:20"}
{"current_steps": 198, "total_steps": 824, "loss": 0.6239, "lr": 9.427280128266049e-06, "epoch": 0.9632107023411371, "percentage": 24.03, "elapsed_time": "10:31:09", "remaining_time": "1 day, 9:15:27"}
{"current_steps": 199, "total_steps": 824, "loss": 0.6371, "lr": 9.41738901254596e-06, "epoch": 0.9680754028580115, "percentage": 24.15, "elapsed_time": "10:33:25", "remaining_time": "1 day, 9:09:25"}
{"current_steps": 200, "total_steps": 824, "loss": 0.6136, "lr": 9.4074184953956e-06, "epoch": 0.972940103374886, "percentage": 24.27, "elapsed_time": "10:36:15", "remaining_time": "1 day, 9:05:06"}
{"current_steps": 201, "total_steps": 824, "loss": 0.6263, "lr": 9.397368756032445e-06, "epoch": 0.9778048038917604, "percentage": 24.39, "elapsed_time": "10:39:36", "remaining_time": "1 day, 9:02:29"}
{"current_steps": 202, "total_steps": 824, "loss": 0.6209, "lr": 9.38723997509798e-06, "epoch": 0.9826695044086349, "percentage": 24.51, "elapsed_time": "10:42:59", "remaining_time": "1 day, 8:59:55"}
{"current_steps": 203, "total_steps": 824, "loss": 0.6302, "lr": 9.37703233465443e-06, "epoch": 0.9875342049255093, "percentage": 24.64, "elapsed_time": "10:46:23", "remaining_time": "1 day, 8:57:23"}
{"current_steps": 204, "total_steps": 824, "loss": 0.6341, "lr": 9.366746018181503e-06, "epoch": 0.9923989054423837, "percentage": 24.76, "elapsed_time": "10:48:55", "remaining_time": "1 day, 8:52:12"}
{"current_steps": 205, "total_steps": 824, "loss": 0.6035, "lr": 9.356381210573092e-06, "epoch": 0.9972636059592581, "percentage": 24.88, "elapsed_time": "10:52:16", "remaining_time": "1 day, 8:49:32"}
{"current_steps": 206, "total_steps": 824, "loss": 0.6018, "lr": 9.345938098133946e-06, "epoch": 1.0, "percentage": 25.0, "elapsed_time": "10:53:44", "remaining_time": "1 day, 8:41:13"}
{"current_steps": 207, "total_steps": 824, "loss": 0.5895, "lr": 9.33541686857632e-06, "epoch": 1.0048647005168745, "percentage": 25.12, "elapsed_time": "10:57:01", "remaining_time": "1 day, 8:38:22"}
{"current_steps": 208, "total_steps": 824, "loss": 0.5999, "lr": 9.324817711016609e-06, "epoch": 1.0097294010337488, "percentage": 25.24, "elapsed_time": "10:59:55", "remaining_time": "1 day, 8:34:23"}
{"current_steps": 209, "total_steps": 824, "loss": 0.5972, "lr": 9.31414081597194e-06, "epoch": 1.0145941015506232, "percentage": 25.36, "elapsed_time": "11:03:01", "remaining_time": "1 day, 8:30:59"}
{"current_steps": 210, "total_steps": 824, "loss": 0.5842, "lr": 9.303386375356752e-06, "epoch": 1.0194588020674977, "percentage": 25.49, "elapsed_time": "11:06:39", "remaining_time": "1 day, 8:29:11"}
{"current_steps": 211, "total_steps": 824, "loss": 0.5986, "lr": 9.292554582479349e-06, "epoch": 1.0243235025843722, "percentage": 25.61, "elapsed_time": "11:09:44", "remaining_time": "1 day, 8:25:43"}
{"current_steps": 212, "total_steps": 824, "loss": 0.6205, "lr": 9.281645632038417e-06, "epoch": 1.0291882031012465, "percentage": 25.73, "elapsed_time": "11:12:57", "remaining_time": "1 day, 8:22:41"}
{"current_steps": 213, "total_steps": 824, "loss": 0.596, "lr": 9.270659720119533e-06, "epoch": 1.034052903618121, "percentage": 25.85, "elapsed_time": "11:16:10", "remaining_time": "1 day, 8:19:37"}
{"current_steps": 214, "total_steps": 824, "loss": 0.5965, "lr": 9.259597044191635e-06, "epoch": 1.0389176041349955, "percentage": 25.97, "elapsed_time": "11:19:57", "remaining_time": "1 day, 8:18:11"}
{"current_steps": 215, "total_steps": 824, "loss": 0.5566, "lr": 9.248457803103476e-06, "epoch": 1.04378230465187, "percentage": 26.09, "elapsed_time": "11:23:17", "remaining_time": "1 day, 8:15:28"}
{"current_steps": 216, "total_steps": 824, "loss": 0.595, "lr": 9.237242197080045e-06, "epoch": 1.0486470051687442, "percentage": 26.21, "elapsed_time": "11:26:12", "remaining_time": "1 day, 8:11:32"}
{"current_steps": 217, "total_steps": 824, "loss": 0.614, "lr": 9.225950427718974e-06, "epoch": 1.0535117056856187, "percentage": 26.33, "elapsed_time": "11:28:34", "remaining_time": "1 day, 8:06:06"}
{"current_steps": 218, "total_steps": 824, "loss": 0.6024, "lr": 9.21458269798691e-06, "epoch": 1.0583764062024932, "percentage": 26.46, "elapsed_time": "11:31:38", "remaining_time": "1 day, 8:02:39"}
{"current_steps": 219, "total_steps": 824, "loss": 0.6353, "lr": 9.203139212215868e-06, "epoch": 1.0632411067193677, "percentage": 26.58, "elapsed_time": "11:34:33", "remaining_time": "1 day, 7:58:45"}
{"current_steps": 220, "total_steps": 824, "loss": 0.6171, "lr": 9.191620176099559e-06, "epoch": 1.068105807236242, "percentage": 26.7, "elapsed_time": "11:37:38", "remaining_time": "1 day, 7:55:19"}
{"current_steps": 221, "total_steps": 824, "loss": 0.6016, "lr": 9.180025796689692e-06, "epoch": 1.0729705077531164, "percentage": 26.82, "elapsed_time": "11:40:20", "remaining_time": "1 day, 7:50:52"}
{"current_steps": 222, "total_steps": 824, "loss": 0.5951, "lr": 9.168356282392253e-06, "epoch": 1.077835208269991, "percentage": 26.94, "elapsed_time": "11:43:20", "remaining_time": "1 day, 7:47:14"}
{"current_steps": 223, "total_steps": 824, "loss": 0.5952, "lr": 9.156611842963753e-06, "epoch": 1.0826999087868654, "percentage": 27.06, "elapsed_time": "11:46:15", "remaining_time": "1 day, 7:43:26"}
{"current_steps": 224, "total_steps": 824, "loss": 0.5851, "lr": 9.144792689507471e-06, "epoch": 1.0875646093037397, "percentage": 27.18, "elapsed_time": "11:49:17", "remaining_time": "1 day, 7:39:53"}
{"current_steps": 225, "total_steps": 824, "loss": 0.595, "lr": 9.132899034469648e-06, "epoch": 1.0924293098206141, "percentage": 27.31, "elapsed_time": "11:52:06", "remaining_time": "1 day, 7:35:48"}
{"current_steps": 226, "total_steps": 824, "loss": 0.6279, "lr": 9.120931091635669e-06, "epoch": 1.0972940103374886, "percentage": 27.43, "elapsed_time": "11:55:27", "remaining_time": "1 day, 7:33:06"}
{"current_steps": 227, "total_steps": 824, "loss": 0.5947, "lr": 9.108889076126226e-06, "epoch": 1.1021587108543631, "percentage": 27.55, "elapsed_time": "12:00:04", "remaining_time": "1 day, 7:33:44"}
{"current_steps": 228, "total_steps": 824, "loss": 0.6089, "lr": 9.09677320439345e-06, "epoch": 1.1070234113712374, "percentage": 27.67, "elapsed_time": "12:03:31", "remaining_time": "1 day, 7:31:19"}
{"current_steps": 229, "total_steps": 824, "loss": 0.5728, "lr": 9.084583694217012e-06, "epoch": 1.1118881118881119, "percentage": 27.79, "elapsed_time": "12:06:47", "remaining_time": "1 day, 7:28:22"}
{"current_steps": 230, "total_steps": 824, "loss": 0.5935, "lr": 9.072320764700223e-06, "epoch": 1.1167528124049864, "percentage": 27.91, "elapsed_time": "12:10:02", "remaining_time": "1 day, 7:25:23"}
{"current_steps": 231, "total_steps": 824, "loss": 0.5833, "lr": 9.059984636266082e-06, "epoch": 1.1216175129218608, "percentage": 28.03, "elapsed_time": "12:13:55", "remaining_time": "1 day, 7:24:04"}
{"current_steps": 232, "total_steps": 824, "loss": 0.6124, "lr": 9.047575530653324e-06, "epoch": 1.1264822134387351, "percentage": 28.16, "elapsed_time": "12:16:21", "remaining_time": "1 day, 7:18:59"}
{"current_steps": 233, "total_steps": 824, "loss": 0.5916, "lr": 9.035093670912424e-06, "epoch": 1.1313469139556096, "percentage": 28.28, "elapsed_time": "12:19:41", "remaining_time": "1 day, 7:16:13"}
{"current_steps": 234, "total_steps": 824, "loss": 0.6039, "lr": 9.022539281401601e-06, "epoch": 1.136211614472484, "percentage": 28.4, "elapsed_time": "12:23:16", "remaining_time": "1 day, 7:14:03"}
{"current_steps": 235, "total_steps": 824, "loss": 0.6029, "lr": 9.009912587782772e-06, "epoch": 1.1410763149893586, "percentage": 28.52, "elapsed_time": "12:26:31", "remaining_time": "1 day, 7:11:03"}
{"current_steps": 236, "total_steps": 824, "loss": 0.6168, "lr": 8.997213817017508e-06, "epoch": 1.1459410155062328, "percentage": 28.64, "elapsed_time": "12:30:26", "remaining_time": "1 day, 7:09:44"}
{"current_steps": 237, "total_steps": 824, "loss": 0.5731, "lr": 8.984443197362938e-06, "epoch": 1.1508057160231073, "percentage": 28.76, "elapsed_time": "12:34:13", "remaining_time": "1 day, 7:08:03"}
{"current_steps": 238, "total_steps": 824, "loss": 0.5871, "lr": 8.971600958367668e-06, "epoch": 1.1556704165399818, "percentage": 28.88, "elapsed_time": "12:37:20", "remaining_time": "1 day, 7:04:42"}
{"current_steps": 239, "total_steps": 824, "loss": 0.5925, "lr": 8.958687330867634e-06, "epoch": 1.160535117056856, "percentage": 29.0, "elapsed_time": "12:39:48", "remaining_time": "1 day, 6:59:46"}
{"current_steps": 240, "total_steps": 824, "loss": 0.587, "lr": 8.94570254698197e-06, "epoch": 1.1653998175737306, "percentage": 29.13, "elapsed_time": "12:44:23", "remaining_time": "1 day, 7:00:00"}
{"current_steps": 241, "total_steps": 824, "loss": 0.6001, "lr": 8.932646840108818e-06, "epoch": 1.170264518090605, "percentage": 29.25, "elapsed_time": "12:47:43", "remaining_time": "1 day, 6:57:11"}
{"current_steps": 242, "total_steps": 824, "loss": 0.6059, "lr": 8.919520444921153e-06, "epoch": 1.1751292186074795, "percentage": 29.37, "elapsed_time": "12:51:10", "remaining_time": "1 day, 6:54:37"}
{"current_steps": 243, "total_steps": 824, "loss": 0.5751, "lr": 8.906323597362547e-06, "epoch": 1.179993919124354, "percentage": 29.49, "elapsed_time": "12:54:40", "remaining_time": "1 day, 6:52:13"}
{"current_steps": 244, "total_steps": 824, "loss": 0.5532, "lr": 8.893056534642938e-06, "epoch": 1.1848586196412283, "percentage": 29.61, "elapsed_time": "12:58:32", "remaining_time": "1 day, 6:50:38"}
{"current_steps": 245, "total_steps": 824, "loss": 0.6032, "lr": 8.879719495234363e-06, "epoch": 1.1897233201581028, "percentage": 29.73, "elapsed_time": "13:01:55", "remaining_time": "1 day, 6:47:54"}
{"current_steps": 246, "total_steps": 824, "loss": 0.5915, "lr": 8.866312718866669e-06, "epoch": 1.1945880206749773, "percentage": 29.85, "elapsed_time": "13:05:40", "remaining_time": "1 day, 6:46:00"}
{"current_steps": 247, "total_steps": 824, "loss": 0.5814, "lr": 8.852836446523213e-06, "epoch": 1.1994527211918515, "percentage": 29.98, "elapsed_time": "13:09:01", "remaining_time": "1 day, 6:43:12"}
{"current_steps": 248, "total_steps": 824, "loss": 0.5888, "lr": 8.83929092043652e-06, "epoch": 1.204317421708726, "percentage": 30.1, "elapsed_time": "13:11:43", "remaining_time": "1 day, 6:38:50"}
{"current_steps": 249, "total_steps": 824, "loss": 0.5794, "lr": 8.825676384083936e-06, "epoch": 1.2091821222256005, "percentage": 30.22, "elapsed_time": "13:14:31", "remaining_time": "1 day, 6:34:44"}
{"current_steps": 250, "total_steps": 824, "loss": 0.5727, "lr": 8.811993082183243e-06, "epoch": 1.214046822742475, "percentage": 30.34, "elapsed_time": "13:17:19", "remaining_time": "1 day, 6:30:40"}
{"current_steps": 251, "total_steps": 824, "loss": 0.6089, "lr": 8.798241260688273e-06, "epoch": 1.2189115232593493, "percentage": 30.46, "elapsed_time": "13:21:28", "remaining_time": "1 day, 6:29:39"}
{"current_steps": 252, "total_steps": 824, "loss": 0.6078, "lr": 8.784421166784476e-06, "epoch": 1.2237762237762237, "percentage": 30.58, "elapsed_time": "13:24:21", "remaining_time": "1 day, 6:25:45"}
{"current_steps": 253, "total_steps": 824, "loss": 0.59, "lr": 8.770533048884483e-06, "epoch": 1.2286409242930982, "percentage": 30.7, "elapsed_time": "13:27:49", "remaining_time": "1 day, 6:23:12"}
{"current_steps": 254, "total_steps": 824, "loss": 0.6053, "lr": 8.756577156623636e-06, "epoch": 1.2335056248099727, "percentage": 30.83, "elapsed_time": "13:31:03", "remaining_time": "1 day, 6:20:06"}
{"current_steps": 255, "total_steps": 824, "loss": 0.5773, "lr": 8.742553740855507e-06, "epoch": 1.238370325326847, "percentage": 30.95, "elapsed_time": "13:34:30", "remaining_time": "1 day, 6:17:28"}
{"current_steps": 256, "total_steps": 824, "loss": 0.5917, "lr": 8.728463053647382e-06, "epoch": 1.2432350258437215, "percentage": 31.07, "elapsed_time": "13:37:06", "remaining_time": "1 day, 6:12:57"}
{"current_steps": 257, "total_steps": 824, "loss": 0.6053, "lr": 8.71430534827574e-06, "epoch": 1.248099726360596, "percentage": 31.19, "elapsed_time": "13:40:11", "remaining_time": "1 day, 6:09:31"}
{"current_steps": 258, "total_steps": 824, "loss": 0.5904, "lr": 8.700080879221689e-06, "epoch": 1.2529644268774702, "percentage": 31.31, "elapsed_time": "13:43:08", "remaining_time": "1 day, 6:05:48"}
{"current_steps": 259, "total_steps": 824, "loss": 0.6148, "lr": 8.685789902166395e-06, "epoch": 1.2578291273943447, "percentage": 31.43, "elapsed_time": "13:46:17", "remaining_time": "1 day, 6:02:30"}
{"current_steps": 260, "total_steps": 824, "loss": 0.5877, "lr": 8.671432673986493e-06, "epoch": 1.2626938279112192, "percentage": 31.55, "elapsed_time": "13:49:29", "remaining_time": "1 day, 5:59:22"}
{"current_steps": 261, "total_steps": 824, "loss": 0.6011, "lr": 8.657009452749466e-06, "epoch": 1.2675585284280937, "percentage": 31.67, "elapsed_time": "13:52:41", "remaining_time": "1 day, 5:56:11"}
{"current_steps": 262, "total_steps": 824, "loss": 0.5907, "lr": 8.642520497709001e-06, "epoch": 1.2724232289449682, "percentage": 31.8, "elapsed_time": "13:55:52", "remaining_time": "1 day, 5:52:59"}
{"current_steps": 263, "total_steps": 824, "loss": 0.6089, "lr": 8.627966069300332e-06, "epoch": 1.2772879294618424, "percentage": 31.92, "elapsed_time": "13:59:44", "remaining_time": "1 day, 5:51:13"}
{"current_steps": 264, "total_steps": 824, "loss": 0.5901, "lr": 8.613346429135567e-06, "epoch": 1.282152629978717, "percentage": 32.04, "elapsed_time": "14:02:46", "remaining_time": "1 day, 5:47:42"}
{"current_steps": 265, "total_steps": 824, "loss": 0.5828, "lr": 8.598661839998972e-06, "epoch": 1.2870173304955914, "percentage": 32.16, "elapsed_time": "14:05:39", "remaining_time": "1 day, 5:43:51"}
{"current_steps": 266, "total_steps": 824, "loss": 0.6162, "lr": 8.583912565842258e-06, "epoch": 1.2918820310124657, "percentage": 32.28, "elapsed_time": "14:08:15", "remaining_time": "1 day, 5:39:25"}
{"current_steps": 267, "total_steps": 824, "loss": 0.5783, "lr": 8.569098871779828e-06, "epoch": 1.2967467315293402, "percentage": 32.4, "elapsed_time": "14:11:38", "remaining_time": "1 day, 5:36:39"}
{"current_steps": 268, "total_steps": 824, "loss": 0.579, "lr": 8.554221024084019e-06, "epoch": 1.3016114320462147, "percentage": 32.52, "elapsed_time": "14:14:24", "remaining_time": "1 day, 5:32:34"}
{"current_steps": 269, "total_steps": 824, "loss": 0.6079, "lr": 8.539279290180315e-06, "epoch": 1.3064761325630891, "percentage": 32.65, "elapsed_time": "14:16:53", "remaining_time": "1 day, 5:27:56"}
{"current_steps": 270, "total_steps": 824, "loss": 0.5949, "lr": 8.524273938642539e-06, "epoch": 1.3113408330799636, "percentage": 32.77, "elapsed_time": "14:20:23", "remaining_time": "1 day, 5:25:24"}
{"current_steps": 271, "total_steps": 824, "loss": 0.6032, "lr": 8.509205239188017e-06, "epoch": 1.316205533596838, "percentage": 32.89, "elapsed_time": "14:23:49", "remaining_time": "1 day, 5:22:42"}
{"current_steps": 272, "total_steps": 824, "loss": 0.602, "lr": 8.494073462672743e-06, "epoch": 1.3210702341137124, "percentage": 33.01, "elapsed_time": "14:26:39", "remaining_time": "1 day, 5:18:49"}
{"current_steps": 273, "total_steps": 824, "loss": 0.6153, "lr": 8.478878881086505e-06, "epoch": 1.3259349346305869, "percentage": 33.13, "elapsed_time": "14:30:01", "remaining_time": "1 day, 5:15:59"}
{"current_steps": 274, "total_steps": 824, "loss": 0.6063, "lr": 8.463621767547998e-06, "epoch": 1.3307996351474611, "percentage": 33.25, "elapsed_time": "14:32:56", "remaining_time": "1 day, 5:12:15"}
{"current_steps": 275, "total_steps": 824, "loss": 0.6033, "lr": 8.448302396299906e-06, "epoch": 1.3356643356643356, "percentage": 33.37, "elapsed_time": "14:35:27", "remaining_time": "1 day, 5:07:44"}
{"current_steps": 276, "total_steps": 824, "loss": 0.5792, "lr": 8.432921042703985e-06, "epoch": 1.34052903618121, "percentage": 33.5, "elapsed_time": "14:37:58", "remaining_time": "1 day, 5:03:13"}
{"current_steps": 277, "total_steps": 824, "loss": 0.5993, "lr": 8.417477983236107e-06, "epoch": 1.3453937366980846, "percentage": 33.62, "elapsed_time": "14:41:09", "remaining_time": "1 day, 5:00:02"}
{"current_steps": 278, "total_steps": 824, "loss": 0.6305, "lr": 8.401973495481289e-06, "epoch": 1.350258437214959, "percentage": 33.74, "elapsed_time": "14:45:02", "remaining_time": "1 day, 4:58:15"}
{"current_steps": 279, "total_steps": 824, "loss": 0.6061, "lr": 8.386407858128707e-06, "epoch": 1.3551231377318333, "percentage": 33.86, "elapsed_time": "14:48:07", "remaining_time": "1 day, 4:54:52"}
{"current_steps": 280, "total_steps": 824, "loss": 0.5759, "lr": 8.370781350966683e-06, "epoch": 1.3599878382487078, "percentage": 33.98, "elapsed_time": "14:51:08", "remaining_time": "1 day, 4:51:22"}
{"current_steps": 281, "total_steps": 824, "loss": 0.595, "lr": 8.355094254877665e-06, "epoch": 1.3648525387655823, "percentage": 34.1, "elapsed_time": "14:54:42", "remaining_time": "1 day, 4:48:55"}
{"current_steps": 282, "total_steps": 824, "loss": 0.6118, "lr": 8.339346851833163e-06, "epoch": 1.3697172392824566, "percentage": 34.22, "elapsed_time": "14:57:49", "remaining_time": "1 day, 4:45:35"}
{"current_steps": 283, "total_steps": 824, "loss": 0.6, "lr": 8.323539424888695e-06, "epoch": 1.374581939799331, "percentage": 34.34, "elapsed_time": "15:00:50", "remaining_time": "1 day, 4:42:07"}
{"current_steps": 284, "total_steps": 824, "loss": 0.6154, "lr": 8.30767225817869e-06, "epoch": 1.3794466403162056, "percentage": 34.47, "elapsed_time": "15:03:29", "remaining_time": "1 day, 4:37:54"}
{"current_steps": 285, "total_steps": 824, "loss": 0.6138, "lr": 8.291745636911382e-06, "epoch": 1.3843113408330798, "percentage": 34.59, "elapsed_time": "15:06:23", "remaining_time": "1 day, 4:34:12"}
{"current_steps": 286, "total_steps": 824, "loss": 0.59, "lr": 8.27575984736369e-06, "epoch": 1.3891760413499543, "percentage": 34.71, "elapsed_time": "15:09:31", "remaining_time": "1 day, 4:30:55"}
{"current_steps": 287, "total_steps": 824, "loss": 0.5971, "lr": 8.259715176876069e-06, "epoch": 1.3940407418668288, "percentage": 34.83, "elapsed_time": "15:12:52", "remaining_time": "1 day, 4:28:03"}
{"current_steps": 288, "total_steps": 824, "loss": 0.5955, "lr": 8.243611913847337e-06, "epoch": 1.3989054423837033, "percentage": 34.95, "elapsed_time": "15:15:56", "remaining_time": "1 day, 4:24:40"}
{"current_steps": 289, "total_steps": 824, "loss": 0.5683, "lr": 8.2274503477295e-06, "epoch": 1.4037701429005778, "percentage": 35.07, "elapsed_time": "15:19:20", "remaining_time": "1 day, 4:21:53"}
{"current_steps": 290, "total_steps": 824, "loss": 0.5849, "lr": 8.211230769022552e-06, "epoch": 1.408634843417452, "percentage": 35.19, "elapsed_time": "15:22:34", "remaining_time": "1 day, 4:18:48"}
{"current_steps": 291, "total_steps": 824, "loss": 0.6184, "lr": 8.19495346926924e-06, "epoch": 1.4134995439343265, "percentage": 35.32, "elapsed_time": "15:26:13", "remaining_time": "1 day, 4:16:28"}
{"current_steps": 292, "total_steps": 824, "loss": 0.6052, "lr": 8.178618741049841e-06, "epoch": 1.418364244451201, "percentage": 35.44, "elapsed_time": "15:28:41", "remaining_time": "1 day, 4:11:59"}
{"current_steps": 293, "total_steps": 824, "loss": 0.5618, "lr": 8.162226877976886e-06, "epoch": 1.4232289449680753, "percentage": 35.56, "elapsed_time": "15:31:58", "remaining_time": "1 day, 4:09:00"}
{"current_steps": 294, "total_steps": 824, "loss": 0.6088, "lr": 8.145778174689897e-06, "epoch": 1.4280936454849498, "percentage": 35.68, "elapsed_time": "15:34:45", "remaining_time": "1 day, 4:05:06"}
{"current_steps": 295, "total_steps": 824, "loss": 0.5889, "lr": 8.129272926850079e-06, "epoch": 1.4329583460018243, "percentage": 35.8, "elapsed_time": "15:38:07", "remaining_time": "1 day, 4:02:15"}
{"current_steps": 296, "total_steps": 824, "loss": 0.611, "lr": 8.112711431135014e-06, "epoch": 1.4378230465186987, "percentage": 35.92, "elapsed_time": "15:41:24", "remaining_time": "1 day, 3:59:15"}
{"current_steps": 297, "total_steps": 824, "loss": 0.5923, "lr": 8.096093985233323e-06, "epoch": 1.4426877470355732, "percentage": 36.04, "elapsed_time": "15:44:46", "remaining_time": "1 day, 3:56:24"}
{"current_steps": 298, "total_steps": 824, "loss": 0.5786, "lr": 8.079420887839316e-06, "epoch": 1.4475524475524475, "percentage": 36.17, "elapsed_time": "15:47:33", "remaining_time": "1 day, 3:52:32"}
{"current_steps": 299, "total_steps": 824, "loss": 0.6102, "lr": 8.062692438647628e-06, "epoch": 1.452417148069322, "percentage": 36.29, "elapsed_time": "15:50:53", "remaining_time": "1 day, 3:49:36"}
{"current_steps": 300, "total_steps": 824, "loss": 0.5595, "lr": 8.045908938347828e-06, "epoch": 1.4572818485861965, "percentage": 36.41, "elapsed_time": "15:53:59", "remaining_time": "1 day, 3:46:18"}
{"current_steps": 301, "total_steps": 824, "loss": 0.5619, "lr": 8.029070688619013e-06, "epoch": 1.4621465491030707, "percentage": 36.53, "elapsed_time": "15:57:48", "remaining_time": "1 day, 3:44:14"}
{"current_steps": 302, "total_steps": 824, "loss": 0.5821, "lr": 8.012177992124385e-06, "epoch": 1.4670112496199452, "percentage": 36.65, "elapsed_time": "16:01:19", "remaining_time": "1 day, 3:41:38"}
{"current_steps": 303, "total_steps": 824, "loss": 0.5945, "lr": 7.995231152505815e-06, "epoch": 1.4718759501368197, "percentage": 36.77, "elapsed_time": "16:05:07", "remaining_time": "1 day, 3:39:30"}
{"current_steps": 304, "total_steps": 824, "loss": 0.5928, "lr": 7.978230474378383e-06, "epoch": 1.4767406506536942, "percentage": 36.89, "elapsed_time": "16:08:02", "remaining_time": "1 day, 3:35:51"}
{"current_steps": 305, "total_steps": 824, "loss": 0.621, "lr": 7.961176263324902e-06, "epoch": 1.4816053511705687, "percentage": 37.01, "elapsed_time": "16:11:33", "remaining_time": "1 day, 3:33:14"}
{"current_steps": 306, "total_steps": 824, "loss": 0.6374, "lr": 7.944068825890424e-06, "epoch": 1.486470051687443, "percentage": 37.14, "elapsed_time": "16:14:20", "remaining_time": "1 day, 3:29:22"}
{"current_steps": 307, "total_steps": 824, "loss": 0.5977, "lr": 7.92690846957673e-06, "epoch": 1.4913347522043174, "percentage": 37.26, "elapsed_time": "16:17:08", "remaining_time": "1 day, 3:25:32"}
{"current_steps": 308, "total_steps": 824, "loss": 0.6022, "lr": 7.909695502836814e-06, "epoch": 1.496199452721192, "percentage": 37.38, "elapsed_time": "16:20:20", "remaining_time": "1 day, 3:22:22"}
{"current_steps": 309, "total_steps": 824, "loss": 0.5955, "lr": 7.892430235069317e-06, "epoch": 1.5010641532380662, "percentage": 37.5, "elapsed_time": "16:24:10", "remaining_time": "1 day, 3:20:18"}
{"current_steps": 310, "total_steps": 824, "loss": 0.6092, "lr": 7.875112976612984e-06, "epoch": 1.5059288537549407, "percentage": 37.62, "elapsed_time": "16:27:28", "remaining_time": "1 day, 3:17:18"}
{"current_steps": 311, "total_steps": 824, "loss": 0.5984, "lr": 7.857744038741076e-06, "epoch": 1.5107935542718152, "percentage": 37.74, "elapsed_time": "16:30:49", "remaining_time": "1 day, 3:14:22"}
{"current_steps": 312, "total_steps": 824, "loss": 0.6159, "lr": 7.84032373365578e-06, "epoch": 1.5156582547886894, "percentage": 37.86, "elapsed_time": "16:33:19", "remaining_time": "1 day, 3:10:04"}
{"current_steps": 313, "total_steps": 824, "loss": 0.5836, "lr": 7.822852374482597e-06, "epoch": 1.5205229553055641, "percentage": 37.99, "elapsed_time": "16:37:00", "remaining_time": "1 day, 3:07:42"}
{"current_steps": 314, "total_steps": 824, "loss": 0.6095, "lr": 7.805330275264707e-06, "epoch": 1.5253876558224384, "percentage": 38.11, "elapsed_time": "16:40:17", "remaining_time": "1 day, 3:04:41"}
{"current_steps": 315, "total_steps": 824, "loss": 0.5763, "lr": 7.787757750957335e-06, "epoch": 1.530252356339313, "percentage": 38.23, "elapsed_time": "16:44:19", "remaining_time": "1 day, 3:02:50"}
{"current_steps": 316, "total_steps": 824, "loss": 0.5898, "lr": 7.77013511742208e-06, "epoch": 1.5351170568561874, "percentage": 38.35, "elapsed_time": "16:46:59", "remaining_time": "1 day, 2:58:50"}
{"current_steps": 317, "total_steps": 824, "loss": 0.6032, "lr": 7.752462691421245e-06, "epoch": 1.5399817573730616, "percentage": 38.47, "elapsed_time": "16:51:07", "remaining_time": "1 day, 2:57:08"}
{"current_steps": 318, "total_steps": 824, "loss": 0.5906, "lr": 7.734740790612137e-06, "epoch": 1.5448464578899361, "percentage": 38.59, "elapsed_time": "16:53:29", "remaining_time": "1 day, 2:52:40"}
{"current_steps": 319, "total_steps": 824, "loss": 0.6044, "lr": 7.716969733541357e-06, "epoch": 1.5497111584068106, "percentage": 38.71, "elapsed_time": "16:56:11", "remaining_time": "1 day, 2:48:42"}
{"current_steps": 320, "total_steps": 824, "loss": 0.5968, "lr": 7.699149839639086e-06, "epoch": 1.5545758589236849, "percentage": 38.83, "elapsed_time": "17:00:06", "remaining_time": "1 day, 2:46:40"}
{"current_steps": 321, "total_steps": 824, "loss": 0.5949, "lr": 7.681281429213328e-06, "epoch": 1.5594405594405596, "percentage": 38.96, "elapsed_time": "17:03:03", "remaining_time": "1 day, 2:43:06"}
{"current_steps": 322, "total_steps": 824, "loss": 0.5771, "lr": 7.663364823444157e-06, "epoch": 1.5643052599574339, "percentage": 39.08, "elapsed_time": "17:07:11", "remaining_time": "1 day, 2:41:23"}
{"current_steps": 323, "total_steps": 824, "loss": 0.5982, "lr": 7.645400344377953e-06, "epoch": 1.5691699604743083, "percentage": 39.2, "elapsed_time": "17:10:35", "remaining_time": "1 day, 2:38:32"}
{"current_steps": 324, "total_steps": 824, "loss": 0.599, "lr": 7.627388314921602e-06, "epoch": 1.5740346609911828, "percentage": 39.32, "elapsed_time": "17:13:29", "remaining_time": "1 day, 2:34:53"}
{"current_steps": 325, "total_steps": 824, "loss": 0.6208, "lr": 7.609329058836694e-06, "epoch": 1.578899361508057, "percentage": 39.44, "elapsed_time": "17:15:54", "remaining_time": "1 day, 2:30:31"}
{"current_steps": 326, "total_steps": 824, "loss": 0.5809, "lr": 7.59122290073371e-06, "epoch": 1.5837640620249316, "percentage": 39.56, "elapsed_time": "17:19:00", "remaining_time": "1 day, 2:27:12"}
{"current_steps": 327, "total_steps": 824, "loss": 0.579, "lr": 7.5730701660661795e-06, "epoch": 1.588628762541806, "percentage": 39.68, "elapsed_time": "17:22:20", "remaining_time": "1 day, 2:24:13"}
{"current_steps": 328, "total_steps": 824, "loss": 0.5597, "lr": 7.554871181124836e-06, "epoch": 1.5934934630586803, "percentage": 39.81, "elapsed_time": "17:25:22", "remaining_time": "1 day, 2:20:48"}
{"current_steps": 329, "total_steps": 824, "loss": 0.6057, "lr": 7.536626273031747e-06, "epoch": 1.5983581635755548, "percentage": 39.93, "elapsed_time": "17:28:13", "remaining_time": "1 day, 2:17:07"}
{"current_steps": 330, "total_steps": 824, "loss": 0.5954, "lr": 7.5183357697344395e-06, "epoch": 1.6032228640924293, "percentage": 40.05, "elapsed_time": "17:31:31", "remaining_time": "1 day, 2:14:05"}
{"current_steps": 331, "total_steps": 824, "loss": 0.6068, "lr": 7.500000000000001e-06, "epoch": 1.6080875646093036, "percentage": 40.17, "elapsed_time": "17:34:03", "remaining_time": "1 day, 2:09:56"}
{"current_steps": 332, "total_steps": 824, "loss": 0.5929, "lr": 7.481619293409173e-06, "epoch": 1.6129522651261783, "percentage": 40.29, "elapsed_time": "17:37:12", "remaining_time": "1 day, 2:06:43"}
{"current_steps": 333, "total_steps": 824, "loss": 0.5564, "lr": 7.4631939803504215e-06, "epoch": 1.6178169656430526, "percentage": 40.41, "elapsed_time": "17:40:51", "remaining_time": "1 day, 2:04:11"}
{"current_steps": 334, "total_steps": 824, "loss": 0.595, "lr": 7.44472439201401e-06, "epoch": 1.622681666159927, "percentage": 40.53, "elapsed_time": "17:43:54", "remaining_time": "1 day, 2:00:49"}
{"current_steps": 335, "total_steps": 824, "loss": 0.5914, "lr": 7.426210860386032e-06, "epoch": 1.6275463666768015, "percentage": 40.66, "elapsed_time": "17:46:37", "remaining_time": "1 day, 1:56:57"}
{"current_steps": 336, "total_steps": 824, "loss": 0.5451, "lr": 7.407653718242449e-06, "epoch": 1.6324110671936758, "percentage": 40.78, "elapsed_time": "17:49:56", "remaining_time": "1 day, 1:53:57"}
{"current_steps": 337, "total_steps": 824, "loss": 0.5884, "lr": 7.3890532991431174e-06, "epoch": 1.6372757677105503, "percentage": 40.9, "elapsed_time": "17:53:28", "remaining_time": "1 day, 1:51:16"}
{"current_steps": 338, "total_steps": 824, "loss": 0.5687, "lr": 7.370409937425781e-06, "epoch": 1.6421404682274248, "percentage": 41.02, "elapsed_time": "17:57:23", "remaining_time": "1 day, 1:49:08"}
{"current_steps": 339, "total_steps": 824, "loss": 0.5816, "lr": 7.3517239682000675e-06, "epoch": 1.647005168744299, "percentage": 41.14, "elapsed_time": "18:00:24", "remaining_time": "1 day, 1:45:42"}
{"current_steps": 340, "total_steps": 824, "loss": 0.6102, "lr": 7.332995727341462e-06, "epoch": 1.6518698692611737, "percentage": 41.26, "elapsed_time": "18:03:44", "remaining_time": "1 day, 1:42:44"}
{"current_steps": 341, "total_steps": 824, "loss": 0.5942, "lr": 7.314225551485273e-06, "epoch": 1.656734569778048, "percentage": 41.38, "elapsed_time": "18:06:56", "remaining_time": "1 day, 1:39:34"}
{"current_steps": 342, "total_steps": 824, "loss": 0.5703, "lr": 7.295413778020579e-06, "epoch": 1.6615992702949225, "percentage": 41.5, "elapsed_time": "18:09:56", "remaining_time": "1 day, 1:36:07"}
{"current_steps": 343, "total_steps": 824, "loss": 0.6009, "lr": 7.276560745084167e-06, "epoch": 1.666463970811797, "percentage": 41.63, "elapsed_time": "18:12:37", "remaining_time": "1 day, 1:32:13"}
{"current_steps": 344, "total_steps": 824, "loss": 0.6022, "lr": 7.257666791554448e-06, "epoch": 1.6713286713286712, "percentage": 41.75, "elapsed_time": "18:16:05", "remaining_time": "1 day, 1:29:25"}
{"current_steps": 345, "total_steps": 824, "loss": 0.5749, "lr": 7.2387322570453724e-06, "epoch": 1.6761933718455457, "percentage": 41.87, "elapsed_time": "18:19:01", "remaining_time": "1 day, 1:25:52"}
{"current_steps": 346, "total_steps": 824, "loss": 0.5779, "lr": 7.219757481900325e-06, "epoch": 1.6810580723624202, "percentage": 41.99, "elapsed_time": "18:22:48", "remaining_time": "1 day, 1:23:32"}
{"current_steps": 347, "total_steps": 824, "loss": 0.5961, "lr": 7.2007428071860045e-06, "epoch": 1.6859227728792945, "percentage": 42.11, "elapsed_time": "18:25:49", "remaining_time": "1 day, 1:20:07"}
{"current_steps": 348, "total_steps": 824, "loss": 0.566, "lr": 7.181688574686292e-06, "epoch": 1.6907874733961692, "percentage": 42.23, "elapsed_time": "18:29:25", "remaining_time": "1 day, 1:17:29"}
{"current_steps": 349, "total_steps": 824, "loss": 0.602, "lr": 7.162595126896111e-06, "epoch": 1.6956521739130435, "percentage": 42.35, "elapsed_time": "18:31:42", "remaining_time": "1 day, 1:13:04"}
{"current_steps": 350, "total_steps": 824, "loss": 0.6029, "lr": 7.143462807015271e-06, "epoch": 1.700516874429918, "percentage": 42.48, "elapsed_time": "18:34:32", "remaining_time": "1 day, 1:09:24"}
{"current_steps": 351, "total_steps": 824, "loss": 0.595, "lr": 7.1242919589422974e-06, "epoch": 1.7053815749467924, "percentage": 42.6, "elapsed_time": "18:37:36", "remaining_time": "1 day, 1:06:03"}
{"current_steps": 352, "total_steps": 824, "loss": 0.5894, "lr": 7.105082927268247e-06, "epoch": 1.7102462754636667, "percentage": 42.72, "elapsed_time": "18:41:30", "remaining_time": "1 day, 1:03:50"}
{"current_steps": 353, "total_steps": 824, "loss": 0.5914, "lr": 7.085836057270521e-06, "epoch": 1.7151109759805412, "percentage": 42.84, "elapsed_time": "18:44:42", "remaining_time": "1 day, 1:00:40"}
{"current_steps": 354, "total_steps": 824, "loss": 0.5838, "lr": 7.066551694906651e-06, "epoch": 1.7199756764974157, "percentage": 42.96, "elapsed_time": "18:47:44", "remaining_time": "1 day, 0:57:17"}
{"current_steps": 355, "total_steps": 824, "loss": 0.5988, "lr": 7.047230186808085e-06, "epoch": 1.72484037701429, "percentage": 43.08, "elapsed_time": "18:50:50", "remaining_time": "1 day, 0:53:58"}
{"current_steps": 356, "total_steps": 824, "loss": 0.5878, "lr": 7.027871880273959e-06, "epoch": 1.7297050775311646, "percentage": 43.2, "elapsed_time": "18:53:39", "remaining_time": "1 day, 0:50:19"}
{"current_steps": 357, "total_steps": 824, "loss": 0.59, "lr": 7.008477123264849e-06, "epoch": 1.734569778048039, "percentage": 43.33, "elapsed_time": "18:57:13", "remaining_time": "1 day, 0:47:37"}
{"current_steps": 358, "total_steps": 824, "loss": 0.5888, "lr": 6.989046264396516e-06, "epoch": 1.7394344785649134, "percentage": 43.45, "elapsed_time": "19:00:28", "remaining_time": "1 day, 0:44:31"}
{"current_steps": 359, "total_steps": 824, "loss": 0.588, "lr": 6.96957965293365e-06, "epoch": 1.7442991790817879, "percentage": 43.57, "elapsed_time": "19:03:31", "remaining_time": "1 day, 0:41:09"}
{"current_steps": 360, "total_steps": 824, "loss": 0.5589, "lr": 6.9500776387835785e-06, "epoch": 1.7491638795986622, "percentage": 43.69, "elapsed_time": "19:06:49", "remaining_time": "1 day, 0:38:08"}
{"current_steps": 361, "total_steps": 824, "loss": 0.5954, "lr": 6.9305405724899876e-06, "epoch": 1.7540285801155366, "percentage": 43.81, "elapsed_time": "19:09:57", "remaining_time": "1 day, 0:34:52"}
{"current_steps": 362, "total_steps": 824, "loss": 0.6186, "lr": 6.91096880522661e-06, "epoch": 1.7588932806324111, "percentage": 43.93, "elapsed_time": "19:13:06", "remaining_time": "1 day, 0:31:38"}
{"current_steps": 363, "total_steps": 824, "loss": 0.5976, "lr": 6.891362688790925e-06, "epoch": 1.7637579811492854, "percentage": 44.05, "elapsed_time": "19:16:24", "remaining_time": "1 day, 0:28:36"}
{"current_steps": 364, "total_steps": 824, "loss": 0.568, "lr": 6.871722575597829e-06, "epoch": 1.7686226816661599, "percentage": 44.17, "elapsed_time": "19:19:44", "remaining_time": "1 day, 0:25:35"}
{"current_steps": 365, "total_steps": 824, "loss": 0.573, "lr": 6.8520488186733e-06, "epoch": 1.7734873821830344, "percentage": 44.3, "elapsed_time": "19:23:08", "remaining_time": "1 day, 0:22:40"}
{"current_steps": 366, "total_steps": 824, "loss": 0.6199, "lr": 6.832341771648057e-06, "epoch": 1.7783520826999086, "percentage": 44.42, "elapsed_time": "19:25:59", "remaining_time": "1 day, 0:19:05"}
{"current_steps": 367, "total_steps": 824, "loss": 0.5921, "lr": 6.812601788751192e-06, "epoch": 1.7832167832167833, "percentage": 44.54, "elapsed_time": "19:29:18", "remaining_time": "1 day, 0:16:03"}
{"current_steps": 368, "total_steps": 824, "loss": 0.5853, "lr": 6.792829224803816e-06, "epoch": 1.7880814837336576, "percentage": 44.66, "elapsed_time": "19:33:10", "remaining_time": "1 day, 0:13:42"}
{"current_steps": 369, "total_steps": 824, "loss": 0.5921, "lr": 6.773024435212678e-06, "epoch": 1.792946184250532, "percentage": 44.78, "elapsed_time": "19:36:12", "remaining_time": "1 day, 0:10:19"}
{"current_steps": 370, "total_steps": 824, "loss": 0.609, "lr": 6.753187775963773e-06, "epoch": 1.7978108847674066, "percentage": 44.9, "elapsed_time": "19:39:12", "remaining_time": "1 day, 0:06:55"}
{"current_steps": 371, "total_steps": 824, "loss": 0.5656, "lr": 6.733319603615941e-06, "epoch": 1.8026755852842808, "percentage": 45.02, "elapsed_time": "19:42:21", "remaining_time": "1 day, 0:03:41"}
{"current_steps": 372, "total_steps": 824, "loss": 0.6155, "lr": 6.713420275294467e-06, "epoch": 1.8075402858011553, "percentage": 45.15, "elapsed_time": "19:46:11", "remaining_time": "1 day, 0:01:17"}
{"current_steps": 373, "total_steps": 824, "loss": 0.5779, "lr": 6.693490148684654e-06, "epoch": 1.8124049863180298, "percentage": 45.27, "elapsed_time": "19:48:45", "remaining_time": "23:57:20"}
{"current_steps": 374, "total_steps": 824, "loss": 0.5761, "lr": 6.673529582025398e-06, "epoch": 1.817269686834904, "percentage": 45.39, "elapsed_time": "19:51:40", "remaining_time": "23:53:49"}
{"current_steps": 375, "total_steps": 824, "loss": 0.621, "lr": 6.653538934102743e-06, "epoch": 1.8221343873517788, "percentage": 45.51, "elapsed_time": "19:55:02", "remaining_time": "23:50:51"}
{"current_steps": 376, "total_steps": 824, "loss": 0.6025, "lr": 6.633518564243442e-06, "epoch": 1.826999087868653, "percentage": 45.63, "elapsed_time": "19:58:27", "remaining_time": "23:47:57"}
{"current_steps": 377, "total_steps": 824, "loss": 0.5947, "lr": 6.6134688323084884e-06, "epoch": 1.8318637883855275, "percentage": 45.75, "elapsed_time": "20:01:41", "remaining_time": "23:44:49"}
{"current_steps": 378, "total_steps": 824, "loss": 0.6175, "lr": 6.593390098686653e-06, "epoch": 1.836728488902402, "percentage": 45.87, "elapsed_time": "20:04:36", "remaining_time": "23:41:18"}
{"current_steps": 379, "total_steps": 824, "loss": 0.603, "lr": 6.573282724288001e-06, "epoch": 1.8415931894192763, "percentage": 46.0, "elapsed_time": "20:07:13", "remaining_time": "23:37:27"}
{"current_steps": 380, "total_steps": 824, "loss": 0.6132, "lr": 6.553147070537413e-06, "epoch": 1.8464578899361508, "percentage": 46.12, "elapsed_time": "20:10:30", "remaining_time": "23:34:23"}
{"current_steps": 381, "total_steps": 824, "loss": 0.5886, "lr": 6.532983499368078e-06, "epoch": 1.8513225904530253, "percentage": 46.24, "elapsed_time": "20:13:28", "remaining_time": "23:30:56"}
{"current_steps": 382, "total_steps": 824, "loss": 0.5769, "lr": 6.512792373215e-06, "epoch": 1.8561872909698995, "percentage": 46.36, "elapsed_time": "20:16:23", "remaining_time": "23:27:27"}
{"current_steps": 383, "total_steps": 824, "loss": 0.5856, "lr": 6.492574055008474e-06, "epoch": 1.8610519914867742, "percentage": 46.48, "elapsed_time": "20:20:13", "remaining_time": "23:25:00"}
{"current_steps": 384, "total_steps": 824, "loss": 0.5994, "lr": 6.472328908167562e-06, "epoch": 1.8659166920036485, "percentage": 46.6, "elapsed_time": "20:23:53", "remaining_time": "23:22:23"}
{"current_steps": 385, "total_steps": 824, "loss": 0.5939, "lr": 6.452057296593568e-06, "epoch": 1.870781392520523, "percentage": 46.72, "elapsed_time": "20:27:20", "remaining_time": "23:19:29"}
{"current_steps": 386, "total_steps": 824, "loss": 0.5901, "lr": 6.431759584663492e-06, "epoch": 1.8756460930373975, "percentage": 46.84, "elapsed_time": "20:30:30", "remaining_time": "23:16:16"}
{"current_steps": 387, "total_steps": 824, "loss": 0.5561, "lr": 6.411436137223479e-06, "epoch": 1.8805107935542718, "percentage": 46.97, "elapsed_time": "20:33:58", "remaining_time": "23:13:24"}
{"current_steps": 388, "total_steps": 824, "loss": 0.5734, "lr": 6.391087319582264e-06, "epoch": 1.8853754940711462, "percentage": 47.09, "elapsed_time": "20:36:50", "remaining_time": "23:09:51"}
{"current_steps": 389, "total_steps": 824, "loss": 0.5863, "lr": 6.370713497504607e-06, "epoch": 1.8902401945880207, "percentage": 47.21, "elapsed_time": "20:39:57", "remaining_time": "23:06:35"}
{"current_steps": 390, "total_steps": 824, "loss": 0.5863, "lr": 6.350315037204714e-06, "epoch": 1.895104895104895, "percentage": 47.33, "elapsed_time": "20:42:50", "remaining_time": "23:03:03"}
{"current_steps": 391, "total_steps": 824, "loss": 0.5922, "lr": 6.329892305339659e-06, "epoch": 1.8999695956217695, "percentage": 47.45, "elapsed_time": "20:45:41", "remaining_time": "22:59:29"}
{"current_steps": 392, "total_steps": 824, "loss": 0.5764, "lr": 6.309445669002787e-06, "epoch": 1.904834296138644, "percentage": 47.57, "elapsed_time": "20:48:47", "remaining_time": "22:56:13"}
{"current_steps": 393, "total_steps": 824, "loss": 0.5918, "lr": 6.288975495717124e-06, "epoch": 1.9096989966555182, "percentage": 47.69, "elapsed_time": "20:51:59", "remaining_time": "22:53:02"}
{"current_steps": 394, "total_steps": 824, "loss": 0.5982, "lr": 6.268482153428763e-06, "epoch": 1.914563697172393, "percentage": 47.82, "elapsed_time": "20:55:42", "remaining_time": "22:50:26"}
{"current_steps": 395, "total_steps": 824, "loss": 0.6103, "lr": 6.247966010500258e-06, "epoch": 1.9194283976892672, "percentage": 47.94, "elapsed_time": "20:58:31", "remaining_time": "22:46:51"}
{"current_steps": 396, "total_steps": 824, "loss": 0.601, "lr": 6.227427435703997e-06, "epoch": 1.9242930982061417, "percentage": 48.06, "elapsed_time": "21:01:33", "remaining_time": "22:43:30"}
{"current_steps": 397, "total_steps": 824, "loss": 0.587, "lr": 6.206866798215571e-06, "epoch": 1.9291577987230162, "percentage": 48.18, "elapsed_time": "21:04:40", "remaining_time": "22:40:14"}
{"current_steps": 398, "total_steps": 824, "loss": 0.6045, "lr": 6.186284467607149e-06, "epoch": 1.9340224992398904, "percentage": 48.3, "elapsed_time": "21:07:39", "remaining_time": "22:36:50"}
{"current_steps": 399, "total_steps": 824, "loss": 0.5864, "lr": 6.165680813840822e-06, "epoch": 1.938887199756765, "percentage": 48.42, "elapsed_time": "21:10:39", "remaining_time": "22:33:27"}
{"current_steps": 400, "total_steps": 824, "loss": 0.6067, "lr": 6.1450562072619635e-06, "epoch": 1.9437519002736394, "percentage": 48.54, "elapsed_time": "21:13:13", "remaining_time": "22:29:36"}
{"current_steps": 401, "total_steps": 824, "loss": 0.5984, "lr": 6.124411018592568e-06, "epoch": 1.9486166007905137, "percentage": 48.67, "elapsed_time": "21:16:39", "remaining_time": "22:26:41"}
{"current_steps": 402, "total_steps": 824, "loss": 0.5812, "lr": 6.103745618924587e-06, "epoch": 1.9534813013073884, "percentage": 48.79, "elapsed_time": "21:19:46", "remaining_time": "22:23:26"}
{"current_steps": 403, "total_steps": 824, "loss": 0.592, "lr": 6.0830603797132574e-06, "epoch": 1.9583460018242627, "percentage": 48.91, "elapsed_time": "21:23:10", "remaining_time": "22:20:28"}
{"current_steps": 404, "total_steps": 824, "loss": 0.5956, "lr": 6.0623556727704306e-06, "epoch": 1.9632107023411371, "percentage": 49.03, "elapsed_time": "21:26:22", "remaining_time": "22:17:19"}
{"current_steps": 405, "total_steps": 824, "loss": 0.5988, "lr": 6.041631870257882e-06, "epoch": 1.9680754028580116, "percentage": 49.15, "elapsed_time": "21:29:17", "remaining_time": "22:13:51"}
{"current_steps": 406, "total_steps": 824, "loss": 0.595, "lr": 6.020889344680627e-06, "epoch": 1.972940103374886, "percentage": 49.27, "elapsed_time": "21:33:04", "remaining_time": "22:11:17"}
{"current_steps": 407, "total_steps": 824, "loss": 0.606, "lr": 6.000128468880223e-06, "epoch": 1.9778048038917604, "percentage": 49.39, "elapsed_time": "21:36:10", "remaining_time": "22:08:01"}
{"current_steps": 408, "total_steps": 824, "loss": 0.5884, "lr": 5.979349616028067e-06, "epoch": 1.9826695044086349, "percentage": 49.51, "elapsed_time": "21:39:21", "remaining_time": "22:04:50"}
{"current_steps": 409, "total_steps": 824, "loss": 0.5991, "lr": 5.958553159618693e-06, "epoch": 1.9875342049255091, "percentage": 49.64, "elapsed_time": "21:42:31", "remaining_time": "22:01:38"}
{"current_steps": 410, "total_steps": 824, "loss": 0.6118, "lr": 5.937739473463047e-06, "epoch": 1.9923989054423838, "percentage": 49.76, "elapsed_time": "21:46:01", "remaining_time": "21:58:46"}
{"current_steps": 411, "total_steps": 824, "loss": 0.5832, "lr": 5.916908931681781e-06, "epoch": 1.9972636059592581, "percentage": 49.88, "elapsed_time": "21:49:43", "remaining_time": "21:56:06"}
{"current_steps": 412, "total_steps": 824, "loss": 0.5858, "lr": 5.896061908698521e-06, "epoch": 2.0, "percentage": 50.0, "elapsed_time": "21:51:25", "remaining_time": "21:51:25"}
{"current_steps": 413, "total_steps": 824, "loss": 0.5532, "lr": 5.8751987792331365e-06, "epoch": 2.0048647005168743, "percentage": 50.12, "elapsed_time": "21:54:29", "remaining_time": "21:48:07"}
{"current_steps": 414, "total_steps": 824, "loss": 0.563, "lr": 5.854319918295012e-06, "epoch": 2.009729401033749, "percentage": 50.24, "elapsed_time": "21:57:53", "remaining_time": "21:45:09"}
{"current_steps": 415, "total_steps": 824, "loss": 0.5803, "lr": 5.833425701176294e-06, "epoch": 2.0145941015506232, "percentage": 50.36, "elapsed_time": "22:00:45", "remaining_time": "21:41:39"}
{"current_steps": 416, "total_steps": 824, "loss": 0.5798, "lr": 5.812516503445158e-06, "epoch": 2.0194588020674975, "percentage": 50.49, "elapsed_time": "22:03:06", "remaining_time": "21:37:39"}
{"current_steps": 417, "total_steps": 824, "loss": 0.5839, "lr": 5.79159270093905e-06, "epoch": 2.024323502584372, "percentage": 50.61, "elapsed_time": "22:06:57", "remaining_time": "21:35:08"}
{"current_steps": 418, "total_steps": 824, "loss": 0.5578, "lr": 5.770654669757935e-06, "epoch": 2.0291882031012465, "percentage": 50.73, "elapsed_time": "22:10:21", "remaining_time": "21:32:10"}
{"current_steps": 419, "total_steps": 824, "loss": 0.5412, "lr": 5.749702786257529e-06, "epoch": 2.034052903618121, "percentage": 50.85, "elapsed_time": "22:13:42", "remaining_time": "21:29:09"}
{"current_steps": 420, "total_steps": 824, "loss": 0.5418, "lr": 5.7287374270425475e-06, "epoch": 2.0389176041349955, "percentage": 50.97, "elapsed_time": "22:16:56", "remaining_time": "21:26:00"}
{"current_steps": 421, "total_steps": 824, "loss": 0.5512, "lr": 5.707758968959923e-06, "epoch": 2.0437823046518697, "percentage": 51.09, "elapsed_time": "22:20:43", "remaining_time": "21:23:24"}
{"current_steps": 422, "total_steps": 824, "loss": 0.5621, "lr": 5.686767789092041e-06, "epoch": 2.0486470051687444, "percentage": 51.21, "elapsed_time": "22:24:08", "remaining_time": "21:20:26"}
{"current_steps": 423, "total_steps": 824, "loss": 0.5835, "lr": 5.6657642647499545e-06, "epoch": 2.0535117056856187, "percentage": 51.33, "elapsed_time": "22:27:45", "remaining_time": "21:17:39"}
{"current_steps": 424, "total_steps": 824, "loss": 0.5352, "lr": 5.644748773466606e-06, "epoch": 2.058376406202493, "percentage": 51.46, "elapsed_time": "22:31:21", "remaining_time": "21:14:52"}
{"current_steps": 425, "total_steps": 824, "loss": 0.5605, "lr": 5.62372169299004e-06, "epoch": 2.0632411067193677, "percentage": 51.58, "elapsed_time": "22:35:02", "remaining_time": "21:12:08"}
{"current_steps": 426, "total_steps": 824, "loss": 0.5511, "lr": 5.6026834012766155e-06, "epoch": 2.068105807236242, "percentage": 51.7, "elapsed_time": "22:37:56", "remaining_time": "21:08:41"}
{"current_steps": 427, "total_steps": 824, "loss": 0.5729, "lr": 5.581634276484211e-06, "epoch": 2.0729705077531166, "percentage": 51.82, "elapsed_time": "22:41:11", "remaining_time": "21:05:33"}
{"current_steps": 428, "total_steps": 824, "loss": 0.5872, "lr": 5.560574696965425e-06, "epoch": 2.077835208269991, "percentage": 51.94, "elapsed_time": "22:43:44", "remaining_time": "21:01:47"}
{"current_steps": 429, "total_steps": 824, "loss": 0.551, "lr": 5.539505041260779e-06, "epoch": 2.082699908786865, "percentage": 52.06, "elapsed_time": "22:46:40", "remaining_time": "20:58:21"}
{"current_steps": 430, "total_steps": 824, "loss": 0.5675, "lr": 5.518425688091906e-06, "epoch": 2.08756460930374, "percentage": 52.18, "elapsed_time": "22:49:20", "remaining_time": "20:54:41"}
{"current_steps": 431, "total_steps": 824, "loss": 0.569, "lr": 5.497337016354757e-06, "epoch": 2.092429309820614, "percentage": 52.31, "elapsed_time": "22:52:26", "remaining_time": "20:51:26"}
{"current_steps": 432, "total_steps": 824, "loss": 0.5516, "lr": 5.476239405112775e-06, "epoch": 2.0972940103374884, "percentage": 52.43, "elapsed_time": "22:55:20", "remaining_time": "20:47:59"}
{"current_steps": 433, "total_steps": 824, "loss": 0.5602, "lr": 5.45513323359009e-06, "epoch": 2.102158710854363, "percentage": 52.55, "elapsed_time": "22:58:40", "remaining_time": "20:44:56"}
{"current_steps": 434, "total_steps": 824, "loss": 0.5505, "lr": 5.434018881164702e-06, "epoch": 2.1070234113712374, "percentage": 52.67, "elapsed_time": "23:02:02", "remaining_time": "20:41:56"}
{"current_steps": 435, "total_steps": 824, "loss": 0.5352, "lr": 5.412896727361663e-06, "epoch": 2.111888111888112, "percentage": 52.79, "elapsed_time": "23:04:38", "remaining_time": "20:38:13"}
{"current_steps": 436, "total_steps": 824, "loss": 0.5254, "lr": 5.391767151846247e-06, "epoch": 2.1167528124049864, "percentage": 52.91, "elapsed_time": "23:08:01", "remaining_time": "20:35:12"}
{"current_steps": 437, "total_steps": 824, "loss": 0.5519, "lr": 5.370630534417133e-06, "epoch": 2.1216175129218606, "percentage": 53.03, "elapsed_time": "23:11:41", "remaining_time": "20:32:27"}
{"current_steps": 438, "total_steps": 824, "loss": 0.572, "lr": 5.349487254999579e-06, "epoch": 2.1264822134387353, "percentage": 53.16, "elapsed_time": "23:15:43", "remaining_time": "20:30:01"}
{"current_steps": 439, "total_steps": 824, "loss": 0.5561, "lr": 5.328337693638591e-06, "epoch": 2.1313469139556096, "percentage": 53.28, "elapsed_time": "23:18:06", "remaining_time": "20:26:07"}
{"current_steps": 440, "total_steps": 824, "loss": 0.5736, "lr": 5.307182230492089e-06, "epoch": 2.136211614472484, "percentage": 53.4, "elapsed_time": "23:20:44", "remaining_time": "20:22:27"}
{"current_steps": 441, "total_steps": 824, "loss": 0.5558, "lr": 5.286021245824075e-06, "epoch": 2.1410763149893586, "percentage": 53.52, "elapsed_time": "23:24:09", "remaining_time": "20:19:29"}
{"current_steps": 442, "total_steps": 824, "loss": 0.5625, "lr": 5.264855119997803e-06, "epoch": 2.145941015506233, "percentage": 53.64, "elapsed_time": "23:27:09", "remaining_time": "20:16:08"}
{"current_steps": 443, "total_steps": 824, "loss": 0.5593, "lr": 5.243684233468933e-06, "epoch": 2.1508057160231075, "percentage": 53.76, "elapsed_time": "23:30:43", "remaining_time": "20:13:17"}
{"current_steps": 444, "total_steps": 824, "loss": 0.5709, "lr": 5.222508966778702e-06, "epoch": 2.155670416539982, "percentage": 53.88, "elapsed_time": "23:33:38", "remaining_time": "20:09:52"}
{"current_steps": 445, "total_steps": 824, "loss": 0.5681, "lr": 5.201329700547077e-06, "epoch": 2.160535117056856, "percentage": 54.0, "elapsed_time": "23:36:29", "remaining_time": "20:06:24"}
{"current_steps": 446, "total_steps": 824, "loss": 0.5547, "lr": 5.180146815465915e-06, "epoch": 2.165399817573731, "percentage": 54.13, "elapsed_time": "23:40:15", "remaining_time": "20:03:43"}
{"current_steps": 447, "total_steps": 824, "loss": 0.5553, "lr": 5.158960692292122e-06, "epoch": 2.170264518090605, "percentage": 54.25, "elapsed_time": "23:43:47", "remaining_time": "20:00:49"}
{"current_steps": 448, "total_steps": 824, "loss": 0.5603, "lr": 5.137771711840811e-06, "epoch": 2.1751292186074793, "percentage": 54.37, "elapsed_time": "23:47:02", "remaining_time": "19:57:41"}
{"current_steps": 449, "total_steps": 824, "loss": 0.5541, "lr": 5.116580254978447e-06, "epoch": 2.179993919124354, "percentage": 54.49, "elapsed_time": "23:49:46", "remaining_time": "19:54:07"}
{"current_steps": 450, "total_steps": 824, "loss": 0.5653, "lr": 5.095386702616012e-06, "epoch": 2.1848586196412283, "percentage": 54.61, "elapsed_time": "23:52:59", "remaining_time": "19:50:58"}
{"current_steps": 451, "total_steps": 824, "loss": 0.562, "lr": 5.074191435702155e-06, "epoch": 2.1897233201581026, "percentage": 54.73, "elapsed_time": "23:56:19", "remaining_time": "19:47:55"}
{"current_steps": 452, "total_steps": 824, "loss": 0.5757, "lr": 5.05299483521634e-06, "epoch": 2.1945880206749773, "percentage": 54.85, "elapsed_time": "23:59:30", "remaining_time": "19:44:43"}
{"current_steps": 453, "total_steps": 824, "loss": 0.5678, "lr": 5.031797282162007e-06, "epoch": 2.1994527211918515, "percentage": 54.98, "elapsed_time": "1 day, 0:02:32", "remaining_time": "19:41:24"}
{"current_steps": 454, "total_steps": 824, "loss": 0.5492, "lr": 5.010599157559713e-06, "epoch": 2.2043174217087262, "percentage": 55.1, "elapsed_time": "1 day, 0:06:01", "remaining_time": "19:38:29"}
{"current_steps": 455, "total_steps": 824, "loss": 0.5588, "lr": 4.98940084244029e-06, "epoch": 2.2091821222256005, "percentage": 55.22, "elapsed_time": "1 day, 0:09:15", "remaining_time": "19:35:20"}
{"current_steps": 456, "total_steps": 824, "loss": 0.551, "lr": 4.968202717837996e-06, "epoch": 2.2140468227424748, "percentage": 55.34, "elapsed_time": "1 day, 0:12:25", "remaining_time": "19:32:07"}
{"current_steps": 457, "total_steps": 824, "loss": 0.5414, "lr": 4.947005164783661e-06, "epoch": 2.2189115232593495, "percentage": 55.46, "elapsed_time": "1 day, 0:15:04", "remaining_time": "19:28:30"}
{"current_steps": 458, "total_steps": 824, "loss": 0.5584, "lr": 4.925808564297847e-06, "epoch": 2.2237762237762237, "percentage": 55.58, "elapsed_time": "1 day, 0:17:45", "remaining_time": "19:24:55"}
{"current_steps": 459, "total_steps": 824, "loss": 0.5558, "lr": 4.9046132973839895e-06, "epoch": 2.228640924293098, "percentage": 55.7, "elapsed_time": "1 day, 0:20:44", "remaining_time": "19:21:35"}
{"current_steps": 460, "total_steps": 824, "loss": 0.5568, "lr": 4.883419745021554e-06, "epoch": 2.2335056248099727, "percentage": 55.83, "elapsed_time": "1 day, 0:23:22", "remaining_time": "19:17:58"}
{"current_steps": 461, "total_steps": 824, "loss": 0.5493, "lr": 4.862228288159191e-06, "epoch": 2.238370325326847, "percentage": 55.95, "elapsed_time": "1 day, 0:26:53", "remaining_time": "19:15:03"}
{"current_steps": 462, "total_steps": 824, "loss": 0.5555, "lr": 4.841039307707878e-06, "epoch": 2.2432350258437217, "percentage": 56.07, "elapsed_time": "1 day, 0:30:32", "remaining_time": "19:12:14"}
{"current_steps": 463, "total_steps": 824, "loss": 0.5489, "lr": 4.819853184534085e-06, "epoch": 2.248099726360596, "percentage": 56.19, "elapsed_time": "1 day, 0:33:22", "remaining_time": "19:08:47"}
{"current_steps": 464, "total_steps": 824, "loss": 0.5367, "lr": 4.798670299452926e-06, "epoch": 2.2529644268774702, "percentage": 56.31, "elapsed_time": "1 day, 0:36:22", "remaining_time": "19:05:27"}
{"current_steps": 465, "total_steps": 824, "loss": 0.5389, "lr": 4.7774910332213005e-06, "epoch": 2.257829127394345, "percentage": 56.43, "elapsed_time": "1 day, 0:39:45", "remaining_time": "19:02:26"}
{"current_steps": 466, "total_steps": 824, "loss": 0.6028, "lr": 4.756315766531069e-06, "epoch": 2.262693827911219, "percentage": 56.55, "elapsed_time": "1 day, 0:43:03", "remaining_time": "18:59:20"}
{"current_steps": 467, "total_steps": 824, "loss": 0.5531, "lr": 4.735144880002199e-06, "epoch": 2.2675585284280935, "percentage": 56.67, "elapsed_time": "1 day, 0:45:50", "remaining_time": "18:55:51"}
{"current_steps": 468, "total_steps": 824, "loss": 0.5356, "lr": 4.713978754175926e-06, "epoch": 2.272423228944968, "percentage": 56.8, "elapsed_time": "1 day, 0:49:18", "remaining_time": "18:52:53"}
{"current_steps": 469, "total_steps": 824, "loss": 0.5722, "lr": 4.692817769507912e-06, "epoch": 2.2772879294618424, "percentage": 56.92, "elapsed_time": "1 day, 0:53:09", "remaining_time": "18:50:12"}
{"current_steps": 470, "total_steps": 824, "loss": 0.5686, "lr": 4.671662306361409e-06, "epoch": 2.282152629978717, "percentage": 57.04, "elapsed_time": "1 day, 0:56:43", "remaining_time": "18:47:19"}
{"current_steps": 471, "total_steps": 824, "loss": 0.5776, "lr": 4.6505127450004216e-06, "epoch": 2.2870173304955914, "percentage": 57.16, "elapsed_time": "1 day, 0:59:44", "remaining_time": "18:44:00"}
{"current_steps": 472, "total_steps": 824, "loss": 0.5533, "lr": 4.62936946558287e-06, "epoch": 2.2918820310124657, "percentage": 57.28, "elapsed_time": "1 day, 1:02:56", "remaining_time": "18:40:50"}
{"current_steps": 473, "total_steps": 824, "loss": 0.5747, "lr": 4.608232848153757e-06, "epoch": 2.2967467315293404, "percentage": 57.4, "elapsed_time": "1 day, 1:06:17", "remaining_time": "18:37:46"}
{"current_steps": 474, "total_steps": 824, "loss": 0.5548, "lr": 4.587103272638339e-06, "epoch": 2.3016114320462147, "percentage": 57.52, "elapsed_time": "1 day, 1:09:07", "remaining_time": "18:34:19"}
{"current_steps": 475, "total_steps": 824, "loss": 0.5839, "lr": 4.565981118835299e-06, "epoch": 2.306476132563089, "percentage": 57.65, "elapsed_time": "1 day, 1:12:31", "remaining_time": "18:31:18"}
{"current_steps": 476, "total_steps": 824, "loss": 0.5564, "lr": 4.5448667664099125e-06, "epoch": 2.3113408330799636, "percentage": 57.77, "elapsed_time": "1 day, 1:16:36", "remaining_time": "18:28:47"}
{"current_steps": 477, "total_steps": 824, "loss": 0.5758, "lr": 4.523760594887228e-06, "epoch": 2.316205533596838, "percentage": 57.89, "elapsed_time": "1 day, 1:19:33", "remaining_time": "18:25:25"}
{"current_steps": 478, "total_steps": 824, "loss": 0.5615, "lr": 4.5026629836452445e-06, "epoch": 2.321070234113712, "percentage": 58.01, "elapsed_time": "1 day, 1:22:33", "remaining_time": "18:22:06"}
{"current_steps": 479, "total_steps": 824, "loss": 0.5479, "lr": 4.481574311908096e-06, "epoch": 2.325934934630587, "percentage": 58.13, "elapsed_time": "1 day, 1:25:37", "remaining_time": "18:18:49"}
{"current_steps": 480, "total_steps": 824, "loss": 0.5519, "lr": 4.460494958739223e-06, "epoch": 2.330799635147461, "percentage": 58.25, "elapsed_time": "1 day, 1:29:26", "remaining_time": "18:16:05"}
{"current_steps": 481, "total_steps": 824, "loss": 0.5591, "lr": 4.439425303034576e-06, "epoch": 2.335664335664336, "percentage": 58.37, "elapsed_time": "1 day, 1:32:39", "remaining_time": "18:12:56"}
{"current_steps": 482, "total_steps": 824, "loss": 0.5709, "lr": 4.418365723515791e-06, "epoch": 2.34052903618121, "percentage": 58.5, "elapsed_time": "1 day, 1:35:35", "remaining_time": "18:09:34"}
{"current_steps": 483, "total_steps": 824, "loss": 0.5755, "lr": 4.397316598723385e-06, "epoch": 2.3453937366980844, "percentage": 58.62, "elapsed_time": "1 day, 1:39:39", "remaining_time": "18:06:59"}
{"current_steps": 484, "total_steps": 824, "loss": 0.5783, "lr": 4.376278307009962e-06, "epoch": 2.350258437214959, "percentage": 58.74, "elapsed_time": "1 day, 1:42:24", "remaining_time": "18:03:30"}
{"current_steps": 485, "total_steps": 824, "loss": 0.5682, "lr": 4.355251226533396e-06, "epoch": 2.3551231377318333, "percentage": 58.86, "elapsed_time": "1 day, 1:45:10", "remaining_time": "18:00:01"}
{"current_steps": 486, "total_steps": 824, "loss": 0.549, "lr": 4.334235735250047e-06, "epoch": 2.359987838248708, "percentage": 58.98, "elapsed_time": "1 day, 1:48:30", "remaining_time": "17:56:56"}
{"current_steps": 487, "total_steps": 824, "loss": 0.555, "lr": 4.313232210907959e-06, "epoch": 2.3648525387655823, "percentage": 59.1, "elapsed_time": "1 day, 1:51:18", "remaining_time": "17:53:29"}
{"current_steps": 488, "total_steps": 824, "loss": 0.5504, "lr": 4.292241031040077e-06, "epoch": 2.3697172392824566, "percentage": 59.22, "elapsed_time": "1 day, 1:53:56", "remaining_time": "17:49:55"}
{"current_steps": 489, "total_steps": 824, "loss": 0.5518, "lr": 4.271262572957453e-06, "epoch": 2.374581939799331, "percentage": 59.34, "elapsed_time": "1 day, 1:56:47", "remaining_time": "17:46:31"}
{"current_steps": 490, "total_steps": 824, "loss": 0.5608, "lr": 4.250297213742473e-06, "epoch": 2.3794466403162056, "percentage": 59.47, "elapsed_time": "1 day, 2:00:32", "remaining_time": "17:43:43"}
{"current_steps": 491, "total_steps": 824, "loss": 0.5504, "lr": 4.229345330242067e-06, "epoch": 2.38431134083308, "percentage": 59.59, "elapsed_time": "1 day, 2:05:05", "remaining_time": "17:41:27"}
{"current_steps": 492, "total_steps": 824, "loss": 0.5874, "lr": 4.2084072990609505e-06, "epoch": 2.3891760413499545, "percentage": 59.71, "elapsed_time": "1 day, 2:08:27", "remaining_time": "17:38:23"}
{"current_steps": 493, "total_steps": 824, "loss": 0.557, "lr": 4.187483496554844e-06, "epoch": 2.394040741866829, "percentage": 59.83, "elapsed_time": "1 day, 2:11:46", "remaining_time": "17:35:17"}
{"current_steps": 494, "total_steps": 824, "loss": 0.5661, "lr": 4.166574298823707e-06, "epoch": 2.398905442383703, "percentage": 59.95, "elapsed_time": "1 day, 2:15:18", "remaining_time": "17:32:20"}
{"current_steps": 495, "total_steps": 824, "loss": 0.5794, "lr": 4.145680081704989e-06, "epoch": 2.4037701429005778, "percentage": 60.07, "elapsed_time": "1 day, 2:18:24", "remaining_time": "17:29:04"}
{"current_steps": 496, "total_steps": 824, "loss": 0.5696, "lr": 4.1248012207668635e-06, "epoch": 2.408634843417452, "percentage": 60.19, "elapsed_time": "1 day, 2:22:03", "remaining_time": "17:26:11"}
{"current_steps": 497, "total_steps": 824, "loss": 0.5458, "lr": 4.103938091301479e-06, "epoch": 2.4134995439343268, "percentage": 60.32, "elapsed_time": "1 day, 2:24:58", "remaining_time": "17:22:49"}
{"current_steps": 498, "total_steps": 824, "loss": 0.5755, "lr": 4.08309106831822e-06, "epoch": 2.418364244451201, "percentage": 60.44, "elapsed_time": "1 day, 2:28:01", "remaining_time": "17:19:33"}
{"current_steps": 499, "total_steps": 824, "loss": 0.5558, "lr": 4.062260526536955e-06, "epoch": 2.4232289449680753, "percentage": 60.56, "elapsed_time": "1 day, 2:30:58", "remaining_time": "17:16:12"}
{"current_steps": 500, "total_steps": 824, "loss": 0.5664, "lr": 4.041446840381309e-06, "epoch": 2.42809364548495, "percentage": 60.68, "elapsed_time": "1 day, 2:34:02", "remaining_time": "17:12:56"}
{"current_steps": 501, "total_steps": 824, "loss": 0.532, "lr": 4.0206503839719335e-06, "epoch": 2.4329583460018243, "percentage": 60.8, "elapsed_time": "1 day, 2:37:19", "remaining_time": "17:09:48"}
{"current_steps": 502, "total_steps": 824, "loss": 0.5732, "lr": 3.999871531119779e-06, "epoch": 2.4378230465186985, "percentage": 60.92, "elapsed_time": "1 day, 2:40:40", "remaining_time": "17:06:43"}
{"current_steps": 503, "total_steps": 824, "loss": 0.541, "lr": 3.9791106553193746e-06, "epoch": 2.4426877470355732, "percentage": 61.04, "elapsed_time": "1 day, 2:43:08", "remaining_time": "17:03:04"}
{"current_steps": 504, "total_steps": 824, "loss": 0.5831, "lr": 3.9583681297421194e-06, "epoch": 2.4475524475524475, "percentage": 61.17, "elapsed_time": "1 day, 2:45:42", "remaining_time": "16:59:29"}
{"current_steps": 505, "total_steps": 824, "loss": 0.5491, "lr": 3.937644327229572e-06, "epoch": 2.4524171480693218, "percentage": 61.29, "elapsed_time": "1 day, 2:47:57", "remaining_time": "16:55:43"}
{"current_steps": 506, "total_steps": 824, "loss": 0.5842, "lr": 3.916939620286743e-06, "epoch": 2.4572818485861965, "percentage": 61.41, "elapsed_time": "1 day, 2:51:17", "remaining_time": "16:52:37"}
{"current_steps": 507, "total_steps": 824, "loss": 0.5729, "lr": 3.896254381075416e-06, "epoch": 2.4621465491030707, "percentage": 61.53, "elapsed_time": "1 day, 2:54:01", "remaining_time": "16:49:09"}
{"current_steps": 508, "total_steps": 824, "loss": 0.5431, "lr": 3.875588981407433e-06, "epoch": 2.4670112496199454, "percentage": 61.65, "elapsed_time": "1 day, 2:56:53", "remaining_time": "16:45:46"}
{"current_steps": 509, "total_steps": 824, "loss": 0.5558, "lr": 3.854943792738037e-06, "epoch": 2.4718759501368197, "percentage": 61.77, "elapsed_time": "1 day, 3:00:50", "remaining_time": "16:43:04"}
{"current_steps": 510, "total_steps": 824, "loss": 0.5703, "lr": 3.834319186159179e-06, "epoch": 2.476740650653694, "percentage": 61.89, "elapsed_time": "1 day, 3:03:38", "remaining_time": "16:39:39"}
{"current_steps": 511, "total_steps": 824, "loss": 0.5682, "lr": 3.8137155323928526e-06, "epoch": 2.4816053511705687, "percentage": 62.01, "elapsed_time": "1 day, 3:06:19", "remaining_time": "16:36:09"}
{"current_steps": 512, "total_steps": 824, "loss": 0.5735, "lr": 3.7931332017844302e-06, "epoch": 2.486470051687443, "percentage": 62.14, "elapsed_time": "1 day, 3:09:05", "remaining_time": "16:32:43"}
{"current_steps": 513, "total_steps": 824, "loss": 0.5609, "lr": 3.7725725642960047e-06, "epoch": 2.4913347522043177, "percentage": 62.26, "elapsed_time": "1 day, 3:12:16", "remaining_time": "16:29:32"}
{"current_steps": 514, "total_steps": 824, "loss": 0.5521, "lr": 3.752033989499742e-06, "epoch": 2.496199452721192, "percentage": 62.38, "elapsed_time": "1 day, 3:15:37", "remaining_time": "16:26:28"}
{"current_steps": 515, "total_steps": 824, "loss": 0.5538, "lr": 3.7315178465712364e-06, "epoch": 2.501064153238066, "percentage": 62.5, "elapsed_time": "1 day, 3:18:48", "remaining_time": "16:23:17"}
{"current_steps": 516, "total_steps": 824, "loss": 0.5747, "lr": 3.7110245042828786e-06, "epoch": 2.5059288537549405, "percentage": 62.62, "elapsed_time": "1 day, 3:21:40", "remaining_time": "16:19:54"}
{"current_steps": 517, "total_steps": 824, "loss": 0.5523, "lr": 3.690554330997215e-06, "epoch": 2.510793554271815, "percentage": 62.74, "elapsed_time": "1 day, 3:24:06", "remaining_time": "16:16:17"}
{"current_steps": 518, "total_steps": 824, "loss": 0.5654, "lr": 3.670107694660343e-06, "epoch": 2.5156582547886894, "percentage": 62.86, "elapsed_time": "1 day, 3:27:26", "remaining_time": "16:13:12"}
{"current_steps": 519, "total_steps": 824, "loss": 0.5535, "lr": 3.6496849627952875e-06, "epoch": 2.520522955305564, "percentage": 62.99, "elapsed_time": "1 day, 3:30:55", "remaining_time": "16:10:12"}
{"current_steps": 520, "total_steps": 824, "loss": 0.5906, "lr": 3.6292865024953945e-06, "epoch": 2.5253876558224384, "percentage": 63.11, "elapsed_time": "1 day, 3:34:21", "remaining_time": "16:07:09"}
{"current_steps": 521, "total_steps": 824, "loss": 0.5596, "lr": 3.6089126804177373e-06, "epoch": 2.5302523563393127, "percentage": 63.23, "elapsed_time": "1 day, 3:37:25", "remaining_time": "16:03:54"}
{"current_steps": 522, "total_steps": 824, "loss": 0.5659, "lr": 3.5885638627765228e-06, "epoch": 2.5351170568561874, "percentage": 63.35, "elapsed_time": "1 day, 3:41:16", "remaining_time": "16:01:07"}
{"current_steps": 523, "total_steps": 824, "loss": 0.5594, "lr": 3.568240415336509e-06, "epoch": 2.5399817573730616, "percentage": 63.47, "elapsed_time": "1 day, 3:44:38", "remaining_time": "15:58:02"}
{"current_steps": 524, "total_steps": 824, "loss": 0.5617, "lr": 3.547942703406433e-06, "epoch": 2.5448464578899364, "percentage": 63.59, "elapsed_time": "1 day, 3:47:45", "remaining_time": "15:54:49"}
{"current_steps": 525, "total_steps": 824, "loss": 0.5333, "lr": 3.52767109183244e-06, "epoch": 2.5497111584068106, "percentage": 63.71, "elapsed_time": "1 day, 3:51:34", "remaining_time": "15:51:59"}
{"current_steps": 526, "total_steps": 824, "loss": 0.5545, "lr": 3.507425944991529e-06, "epoch": 2.554575858923685, "percentage": 63.83, "elapsed_time": "1 day, 3:54:24", "remaining_time": "15:48:36"}
{"current_steps": 527, "total_steps": 824, "loss": 0.5315, "lr": 3.4872076267850015e-06, "epoch": 2.5594405594405596, "percentage": 63.96, "elapsed_time": "1 day, 3:57:30", "remaining_time": "15:45:23"}
{"current_steps": 528, "total_steps": 824, "loss": 0.5512, "lr": 3.4670165006319236e-06, "epoch": 2.564305259957434, "percentage": 64.08, "elapsed_time": "1 day, 4:00:30", "remaining_time": "15:42:06"}
{"current_steps": 529, "total_steps": 824, "loss": 0.5575, "lr": 3.4468529294625895e-06, "epoch": 2.5691699604743086, "percentage": 64.2, "elapsed_time": "1 day, 4:03:31", "remaining_time": "15:38:49"}
{"current_steps": 530, "total_steps": 824, "loss": 0.5745, "lr": 3.4267172757120005e-06, "epoch": 2.574034660991183, "percentage": 64.32, "elapsed_time": "1 day, 4:07:19", "remaining_time": "15:35:59"}
{"current_steps": 531, "total_steps": 824, "loss": 0.5611, "lr": 3.406609901313349e-06, "epoch": 2.578899361508057, "percentage": 64.44, "elapsed_time": "1 day, 4:11:05", "remaining_time": "15:33:07"}
{"current_steps": 532, "total_steps": 824, "loss": 0.5619, "lr": 3.386531167691512e-06, "epoch": 2.5837640620249314, "percentage": 64.56, "elapsed_time": "1 day, 4:14:02", "remaining_time": "15:29:48"}
{"current_steps": 533, "total_steps": 824, "loss": 0.5613, "lr": 3.36648143575656e-06, "epoch": 2.588628762541806, "percentage": 64.68, "elapsed_time": "1 day, 4:16:52", "remaining_time": "15:26:26"}
{"current_steps": 534, "total_steps": 824, "loss": 0.5555, "lr": 3.3464610658972584e-06, "epoch": 2.5934934630586803, "percentage": 64.81, "elapsed_time": "1 day, 4:19:46", "remaining_time": "15:23:06"}
{"current_steps": 535, "total_steps": 824, "loss": 0.5465, "lr": 3.326470417974604e-06, "epoch": 2.598358163575555, "percentage": 64.93, "elapsed_time": "1 day, 4:23:16", "remaining_time": "15:20:05"}
{"current_steps": 536, "total_steps": 824, "loss": 0.5297, "lr": 3.3065098513153473e-06, "epoch": 2.6032228640924293, "percentage": 65.05, "elapsed_time": "1 day, 4:26:37", "remaining_time": "15:16:59"}
{"current_steps": 537, "total_steps": 824, "loss": 0.5835, "lr": 3.2865797247055354e-06, "epoch": 2.6080875646093036, "percentage": 65.17, "elapsed_time": "1 day, 4:29:27", "remaining_time": "15:13:37"}
{"current_steps": 538, "total_steps": 824, "loss": 0.5511, "lr": 3.266680396384061e-06, "epoch": 2.6129522651261783, "percentage": 65.29, "elapsed_time": "1 day, 4:32:00", "remaining_time": "15:10:05"}
{"current_steps": 539, "total_steps": 824, "loss": 0.568, "lr": 3.2468122240362287e-06, "epoch": 2.6178169656430526, "percentage": 65.41, "elapsed_time": "1 day, 4:35:41", "remaining_time": "15:07:10"}
{"current_steps": 540, "total_steps": 824, "loss": 0.5626, "lr": 3.226975564787322e-06, "epoch": 2.6226816661599273, "percentage": 65.53, "elapsed_time": "1 day, 4:39:03", "remaining_time": "15:04:05"}
{"current_steps": 541, "total_steps": 824, "loss": 0.5599, "lr": 3.2071707751961838e-06, "epoch": 2.6275463666768015, "percentage": 65.66, "elapsed_time": "1 day, 4:42:00", "remaining_time": "15:00:47"}
{"current_steps": 542, "total_steps": 824, "loss": 0.5537, "lr": 3.187398211248811e-06, "epoch": 2.632411067193676, "percentage": 65.78, "elapsed_time": "1 day, 4:45:42", "remaining_time": "14:57:52"}
{"current_steps": 543, "total_steps": 824, "loss": 0.5544, "lr": 3.1676582283519454e-06, "epoch": 2.63727576771055, "percentage": 65.9, "elapsed_time": "1 day, 4:49:17", "remaining_time": "14:54:53"}
{"current_steps": 544, "total_steps": 824, "loss": 0.5518, "lr": 3.1479511813267006e-06, "epoch": 2.6421404682274248, "percentage": 66.02, "elapsed_time": "1 day, 4:52:30", "remaining_time": "14:51:43"}
{"current_steps": 545, "total_steps": 824, "loss": 0.5401, "lr": 3.1282774244021717e-06, "epoch": 2.647005168744299, "percentage": 66.14, "elapsed_time": "1 day, 4:55:15", "remaining_time": "14:48:19"}
{"current_steps": 546, "total_steps": 824, "loss": 0.5746, "lr": 3.1086373112090762e-06, "epoch": 2.6518698692611737, "percentage": 66.26, "elapsed_time": "1 day, 4:58:54", "remaining_time": "14:45:22"}
{"current_steps": 547, "total_steps": 824, "loss": 0.571, "lr": 3.089031194773392e-06, "epoch": 2.656734569778048, "percentage": 66.38, "elapsed_time": "1 day, 5:02:51", "remaining_time": "14:42:34"}
{"current_steps": 548, "total_steps": 824, "loss": 0.5723, "lr": 3.069459427510014e-06, "epoch": 2.6615992702949223, "percentage": 66.5, "elapsed_time": "1 day, 5:06:36", "remaining_time": "14:39:40"}
{"current_steps": 549, "total_steps": 824, "loss": 0.5581, "lr": 3.049922361216422e-06, "epoch": 2.666463970811797, "percentage": 66.63, "elapsed_time": "1 day, 5:09:52", "remaining_time": "14:36:31"}
{"current_steps": 550, "total_steps": 824, "loss": 0.5519, "lr": 3.0304203470663507e-06, "epoch": 2.6713286713286712, "percentage": 66.75, "elapsed_time": "1 day, 5:12:28", "remaining_time": "14:33:03"}
{"current_steps": 551, "total_steps": 824, "loss": 0.5557, "lr": 3.0109537356034856e-06, "epoch": 2.676193371845546, "percentage": 66.87, "elapsed_time": "1 day, 5:15:24", "remaining_time": "14:29:44"}
{"current_steps": 552, "total_steps": 824, "loss": 0.5454, "lr": 2.991522876735154e-06, "epoch": 2.68105807236242, "percentage": 66.99, "elapsed_time": "1 day, 5:18:39", "remaining_time": "14:26:35"}
{"current_steps": 553, "total_steps": 824, "loss": 0.5729, "lr": 2.9721281197260427e-06, "epoch": 2.6859227728792945, "percentage": 67.11, "elapsed_time": "1 day, 5:21:51", "remaining_time": "14:23:24"}
{"current_steps": 554, "total_steps": 824, "loss": 0.5698, "lr": 2.9527698131919156e-06, "epoch": 2.690787473396169, "percentage": 67.23, "elapsed_time": "1 day, 5:24:12", "remaining_time": "14:19:48"}
{"current_steps": 555, "total_steps": 824, "loss": 0.5509, "lr": 2.9334483050933506e-06, "epoch": 2.6956521739130435, "percentage": 67.35, "elapsed_time": "1 day, 5:26:57", "remaining_time": "14:16:25"}
{"current_steps": 556, "total_steps": 824, "loss": 0.5638, "lr": 2.91416394272948e-06, "epoch": 2.700516874429918, "percentage": 67.48, "elapsed_time": "1 day, 5:29:36", "remaining_time": "14:12:58"}
{"current_steps": 557, "total_steps": 824, "loss": 0.5502, "lr": 2.894917072731753e-06, "epoch": 2.7053815749467924, "percentage": 67.6, "elapsed_time": "1 day, 5:32:28", "remaining_time": "14:09:38"}
{"current_steps": 558, "total_steps": 824, "loss": 0.5758, "lr": 2.8757080410577042e-06, "epoch": 2.7102462754636667, "percentage": 67.72, "elapsed_time": "1 day, 5:35:45", "remaining_time": "14:06:30"}
{"current_steps": 559, "total_steps": 824, "loss": 0.5355, "lr": 2.8565371929847286e-06, "epoch": 2.715110975980541, "percentage": 67.84, "elapsed_time": "1 day, 5:38:59", "remaining_time": "14:03:20"}
{"current_steps": 560, "total_steps": 824, "loss": 0.5461, "lr": 2.83740487310389e-06, "epoch": 2.7199756764974157, "percentage": 67.96, "elapsed_time": "1 day, 5:41:19", "remaining_time": "13:59:46"}
{"current_steps": 561, "total_steps": 824, "loss": 0.5533, "lr": 2.81831142531371e-06, "epoch": 2.72484037701429, "percentage": 68.08, "elapsed_time": "1 day, 5:44:25", "remaining_time": "13:56:33"}
{"current_steps": 562, "total_steps": 824, "loss": 0.5843, "lr": 2.7992571928139984e-06, "epoch": 2.7297050775311646, "percentage": 68.2, "elapsed_time": "1 day, 5:47:38", "remaining_time": "13:53:22"}
{"current_steps": 563, "total_steps": 824, "loss": 0.5806, "lr": 2.780242518099675e-06, "epoch": 2.734569778048039, "percentage": 68.33, "elapsed_time": "1 day, 5:50:38", "remaining_time": "13:50:07"}
{"current_steps": 564, "total_steps": 824, "loss": 0.5482, "lr": 2.761267742954629e-06, "epoch": 2.739434478564913, "percentage": 68.45, "elapsed_time": "1 day, 5:53:26", "remaining_time": "13:46:45"}
{"current_steps": 565, "total_steps": 824, "loss": 0.5705, "lr": 2.7423332084455543e-06, "epoch": 2.744299179081788, "percentage": 68.57, "elapsed_time": "1 day, 5:56:46", "remaining_time": "13:43:39"}
{"current_steps": 566, "total_steps": 824, "loss": 0.5781, "lr": 2.723439254915834e-06, "epoch": 2.749163879598662, "percentage": 68.69, "elapsed_time": "1 day, 5:59:59", "remaining_time": "13:40:29"}
{"current_steps": 567, "total_steps": 824, "loss": 0.5762, "lr": 2.704586221979422e-06, "epoch": 2.754028580115537, "percentage": 68.81, "elapsed_time": "1 day, 6:02:38", "remaining_time": "13:37:04"}
{"current_steps": 568, "total_steps": 824, "loss": 0.5433, "lr": 2.6857744485147286e-06, "epoch": 2.758893280632411, "percentage": 68.93, "elapsed_time": "1 day, 6:05:49", "remaining_time": "13:33:53"}
{"current_steps": 569, "total_steps": 824, "loss": 0.5507, "lr": 2.667004272658541e-06, "epoch": 2.7637579811492854, "percentage": 69.05, "elapsed_time": "1 day, 6:09:06", "remaining_time": "13:30:45"}
{"current_steps": 570, "total_steps": 824, "loss": 0.5736, "lr": 2.6482760317999338e-06, "epoch": 2.7686226816661597, "percentage": 69.17, "elapsed_time": "1 day, 6:11:52", "remaining_time": "13:27:23"}
{"current_steps": 571, "total_steps": 824, "loss": 0.5679, "lr": 2.629590062574221e-06, "epoch": 2.7734873821830344, "percentage": 69.3, "elapsed_time": "1 day, 6:14:59", "remaining_time": "13:24:11"}
{"current_steps": 572, "total_steps": 824, "loss": 0.5735, "lr": 2.610946700856885e-06, "epoch": 2.7783520826999086, "percentage": 69.42, "elapsed_time": "1 day, 6:18:24", "remaining_time": "13:21:07"}
{"current_steps": 573, "total_steps": 824, "loss": 0.5689, "lr": 2.592346281757552e-06, "epoch": 2.7832167832167833, "percentage": 69.54, "elapsed_time": "1 day, 6:22:26", "remaining_time": "13:18:18"}
{"current_steps": 574, "total_steps": 824, "loss": 0.5469, "lr": 2.5737891396139713e-06, "epoch": 2.7880814837336576, "percentage": 69.66, "elapsed_time": "1 day, 6:25:52", "remaining_time": "13:15:14"}
{"current_steps": 575, "total_steps": 824, "loss": 0.5526, "lr": 2.5552756079859904e-06, "epoch": 2.792946184250532, "percentage": 69.78, "elapsed_time": "1 day, 6:28:47", "remaining_time": "13:11:56"}
{"current_steps": 576, "total_steps": 824, "loss": 0.5429, "lr": 2.5368060196495785e-06, "epoch": 2.7978108847674066, "percentage": 69.9, "elapsed_time": "1 day, 6:32:03", "remaining_time": "13:08:48"}
{"current_steps": 577, "total_steps": 824, "loss": 0.5678, "lr": 2.5183807065908296e-06, "epoch": 2.802675585284281, "percentage": 70.02, "elapsed_time": "1 day, 6:34:57", "remaining_time": "13:05:30"}
{"current_steps": 578, "total_steps": 824, "loss": 0.553, "lr": 2.5000000000000015e-06, "epoch": 2.8075402858011556, "percentage": 70.15, "elapsed_time": "1 day, 6:37:55", "remaining_time": "13:02:13"}
{"current_steps": 579, "total_steps": 824, "loss": 0.5387, "lr": 2.4816642302655634e-06, "epoch": 2.81240498631803, "percentage": 70.27, "elapsed_time": "1 day, 6:40:49", "remaining_time": "12:58:56"}
{"current_steps": 580, "total_steps": 824, "loss": 0.5761, "lr": 2.4633737269682546e-06, "epoch": 2.817269686834904, "percentage": 70.39, "elapsed_time": "1 day, 6:43:47", "remaining_time": "12:55:39"}
{"current_steps": 581, "total_steps": 824, "loss": 0.5608, "lr": 2.445128818875166e-06, "epoch": 2.822134387351779, "percentage": 70.51, "elapsed_time": "1 day, 6:47:41", "remaining_time": "12:52:47"}
{"current_steps": 582, "total_steps": 824, "loss": 0.5634, "lr": 2.4269298339338205e-06, "epoch": 2.826999087868653, "percentage": 70.63, "elapsed_time": "1 day, 6:50:30", "remaining_time": "12:49:27"}
{"current_steps": 583, "total_steps": 824, "loss": 0.5453, "lr": 2.408777099266291e-06, "epoch": 2.8318637883855278, "percentage": 70.75, "elapsed_time": "1 day, 6:53:55", "remaining_time": "12:46:22"}
{"current_steps": 584, "total_steps": 824, "loss": 0.5556, "lr": 2.3906709411633073e-06, "epoch": 2.836728488902402, "percentage": 70.87, "elapsed_time": "1 day, 6:56:26", "remaining_time": "12:42:55"}
{"current_steps": 585, "total_steps": 824, "loss": 0.5429, "lr": 2.3726116850783987e-06, "epoch": 2.8415931894192763, "percentage": 71.0, "elapsed_time": "1 day, 6:59:38", "remaining_time": "12:39:45"}
{"current_steps": 586, "total_steps": 824, "loss": 0.578, "lr": 2.354599655622049e-06, "epoch": 2.8464578899361506, "percentage": 71.12, "elapsed_time": "1 day, 7:03:02", "remaining_time": "12:36:39"}
{"current_steps": 587, "total_steps": 824, "loss": 0.5467, "lr": 2.3366351765558437e-06, "epoch": 2.8513225904530253, "percentage": 71.24, "elapsed_time": "1 day, 7:06:33", "remaining_time": "12:33:37"}
{"current_steps": 588, "total_steps": 824, "loss": 0.5328, "lr": 2.318718570786675e-06, "epoch": 2.8561872909698995, "percentage": 71.36, "elapsed_time": "1 day, 7:10:22", "remaining_time": "12:30:41"}
{"current_steps": 589, "total_steps": 824, "loss": 0.5502, "lr": 2.3008501603609147e-06, "epoch": 2.8610519914867742, "percentage": 71.48, "elapsed_time": "1 day, 7:13:58", "remaining_time": "12:27:41"}
{"current_steps": 590, "total_steps": 824, "loss": 0.5141, "lr": 2.283030266458644e-06, "epoch": 2.8659166920036485, "percentage": 71.6, "elapsed_time": "1 day, 7:17:05", "remaining_time": "12:24:28"}
{"current_steps": 591, "total_steps": 824, "loss": 0.5685, "lr": 2.265259209387867e-06, "epoch": 2.870781392520523, "percentage": 71.72, "elapsed_time": "1 day, 7:20:17", "remaining_time": "12:21:17"}
{"current_steps": 592, "total_steps": 824, "loss": 0.5532, "lr": 2.2475373085787568e-06, "epoch": 2.8756460930373975, "percentage": 71.84, "elapsed_time": "1 day, 7:23:47", "remaining_time": "12:18:14"}
{"current_steps": 593, "total_steps": 824, "loss": 0.5756, "lr": 2.229864882577921e-06, "epoch": 2.8805107935542718, "percentage": 71.97, "elapsed_time": "1 day, 7:26:36", "remaining_time": "12:14:54"}
{"current_steps": 594, "total_steps": 824, "loss": 0.5544, "lr": 2.2122422490426676e-06, "epoch": 2.8853754940711465, "percentage": 72.09, "elapsed_time": "1 day, 7:30:05", "remaining_time": "12:11:51"}
{"current_steps": 595, "total_steps": 824, "loss": 0.5608, "lr": 2.194669724735296e-06, "epoch": 2.8902401945880207, "percentage": 72.21, "elapsed_time": "1 day, 7:33:32", "remaining_time": "12:08:46"}
{"current_steps": 596, "total_steps": 824, "loss": 0.5445, "lr": 2.1771476255174056e-06, "epoch": 2.895104895104895, "percentage": 72.33, "elapsed_time": "1 day, 7:36:53", "remaining_time": "12:05:39"}
{"current_steps": 597, "total_steps": 824, "loss": 0.5429, "lr": 2.159676266344222e-06, "epoch": 2.8999695956217693, "percentage": 72.45, "elapsed_time": "1 day, 7:39:53", "remaining_time": "12:02:24"}
{"current_steps": 598, "total_steps": 824, "loss": 0.5599, "lr": 2.1422559612589266e-06, "epoch": 2.904834296138644, "percentage": 72.57, "elapsed_time": "1 day, 7:42:36", "remaining_time": "11:59:02"}
{"current_steps": 599, "total_steps": 824, "loss": 0.571, "lr": 2.124887023387017e-06, "epoch": 2.9096989966555182, "percentage": 72.69, "elapsed_time": "1 day, 7:45:44", "remaining_time": "11:55:50"}
{"current_steps": 600, "total_steps": 824, "loss": 0.5515, "lr": 2.1075697649306838e-06, "epoch": 2.914563697172393, "percentage": 72.82, "elapsed_time": "1 day, 7:48:28", "remaining_time": "11:52:29"}
{"current_steps": 601, "total_steps": 824, "loss": 0.5651, "lr": 2.0903044971631854e-06, "epoch": 2.919428397689267, "percentage": 72.94, "elapsed_time": "1 day, 7:51:03", "remaining_time": "11:49:05"}
{"current_steps": 602, "total_steps": 824, "loss": 0.5526, "lr": 2.0730915304232692e-06, "epoch": 2.9242930982061415, "percentage": 73.06, "elapsed_time": "1 day, 7:53:37", "remaining_time": "11:45:41"}
{"current_steps": 603, "total_steps": 824, "loss": 0.5354, "lr": 2.055931174109579e-06, "epoch": 2.929157798723016, "percentage": 73.18, "elapsed_time": "1 day, 7:56:57", "remaining_time": "11:42:33"}
{"current_steps": 604, "total_steps": 824, "loss": 0.5461, "lr": 2.0388237366751005e-06, "epoch": 2.9340224992398904, "percentage": 73.3, "elapsed_time": "1 day, 7:59:30", "remaining_time": "11:39:09"}
{"current_steps": 605, "total_steps": 824, "loss": 0.5461, "lr": 2.02176952562162e-06, "epoch": 2.938887199756765, "percentage": 73.42, "elapsed_time": "1 day, 8:01:57", "remaining_time": "11:35:42"}
{"current_steps": 606, "total_steps": 824, "loss": 0.553, "lr": 2.004768847494186e-06, "epoch": 2.9437519002736394, "percentage": 73.54, "elapsed_time": "1 day, 8:04:46", "remaining_time": "11:32:24"}
{"current_steps": 607, "total_steps": 824, "loss": 0.5698, "lr": 1.987822007875617e-06, "epoch": 2.9486166007905137, "percentage": 73.67, "elapsed_time": "1 day, 8:08:04", "remaining_time": "11:29:16"}
{"current_steps": 608, "total_steps": 824, "loss": 0.5698, "lr": 1.9709293113809876e-06, "epoch": 2.9534813013073884, "percentage": 73.79, "elapsed_time": "1 day, 8:10:47", "remaining_time": "11:25:56"}
{"current_steps": 609, "total_steps": 824, "loss": 0.5707, "lr": 1.954091061652172e-06, "epoch": 2.9583460018242627, "percentage": 73.91, "elapsed_time": "1 day, 8:14:24", "remaining_time": "11:22:55"}
{"current_steps": 610, "total_steps": 824, "loss": 0.567, "lr": 1.9373075613523728e-06, "epoch": 2.9632107023411374, "percentage": 74.03, "elapsed_time": "1 day, 8:17:28", "remaining_time": "11:19:42"}
{"current_steps": 611, "total_steps": 824, "loss": 0.5602, "lr": 1.920579112160685e-06, "epoch": 2.9680754028580116, "percentage": 74.15, "elapsed_time": "1 day, 8:20:06", "remaining_time": "11:16:20"}
{"current_steps": 612, "total_steps": 824, "loss": 0.5562, "lr": 1.903906014766681e-06, "epoch": 2.972940103374886, "percentage": 74.27, "elapsed_time": "1 day, 8:23:35", "remaining_time": "11:13:16"}
{"current_steps": 613, "total_steps": 824, "loss": 0.5471, "lr": 1.8872885688649879e-06, "epoch": 2.97780480389176, "percentage": 74.39, "elapsed_time": "1 day, 8:26:30", "remaining_time": "11:10:00"}
{"current_steps": 614, "total_steps": 824, "loss": 0.5574, "lr": 1.8707270731499223e-06, "epoch": 2.982669504408635, "percentage": 74.51, "elapsed_time": "1 day, 8:29:25", "remaining_time": "11:06:44"}
{"current_steps": 615, "total_steps": 824, "loss": 0.559, "lr": 1.854221825310103e-06, "epoch": 2.987534204925509, "percentage": 74.64, "elapsed_time": "1 day, 8:32:58", "remaining_time": "11:03:41"}
{"current_steps": 616, "total_steps": 824, "loss": 0.559, "lr": 1.8377731220231144e-06, "epoch": 2.992398905442384, "percentage": 74.76, "elapsed_time": "1 day, 8:36:20", "remaining_time": "11:00:34"}
{"current_steps": 617, "total_steps": 824, "loss": 0.5663, "lr": 1.8213812589501611e-06, "epoch": 2.997263605959258, "percentage": 74.88, "elapsed_time": "1 day, 8:39:33", "remaining_time": "10:57:25"}
{"current_steps": 618, "total_steps": 824, "loss": 0.5628, "lr": 1.8050465307307602e-06, "epoch": 3.0, "percentage": 75.0, "elapsed_time": "1 day, 8:40:44", "remaining_time": "10:53:34"}
{"current_steps": 619, "total_steps": 824, "loss": 0.5318, "lr": 1.78876923097745e-06, "epoch": 3.0048647005168743, "percentage": 75.12, "elapsed_time": "1 day, 8:43:07", "remaining_time": "10:50:08"}
{"current_steps": 620, "total_steps": 824, "loss": 0.5526, "lr": 1.7725496522704998e-06, "epoch": 3.009729401033749, "percentage": 75.24, "elapsed_time": "1 day, 8:45:48", "remaining_time": "10:46:48"}
{"current_steps": 621, "total_steps": 824, "loss": 0.5404, "lr": 1.7563880861526656e-06, "epoch": 3.0145941015506232, "percentage": 75.36, "elapsed_time": "1 day, 8:48:15", "remaining_time": "10:43:24"}
{"current_steps": 622, "total_steps": 824, "loss": 0.5547, "lr": 1.7402848231239317e-06, "epoch": 3.0194588020674975, "percentage": 75.49, "elapsed_time": "1 day, 8:50:32", "remaining_time": "10:39:57"}
{"current_steps": 623, "total_steps": 824, "loss": 0.5477, "lr": 1.7242401526363095e-06, "epoch": 3.024323502584372, "percentage": 75.61, "elapsed_time": "1 day, 8:53:07", "remaining_time": "10:36:35"}
{"current_steps": 624, "total_steps": 824, "loss": 0.5448, "lr": 1.70825436308862e-06, "epoch": 3.0291882031012465, "percentage": 75.73, "elapsed_time": "1 day, 8:56:21", "remaining_time": "10:33:26"}
{"current_steps": 625, "total_steps": 824, "loss": 0.5372, "lr": 1.692327741821312e-06, "epoch": 3.034052903618121, "percentage": 75.85, "elapsed_time": "1 day, 8:59:43", "remaining_time": "10:30:20"}
{"current_steps": 626, "total_steps": 824, "loss": 0.5366, "lr": 1.676460575111306e-06, "epoch": 3.0389176041349955, "percentage": 75.97, "elapsed_time": "1 day, 9:02:34", "remaining_time": "10:27:04"}
{"current_steps": 627, "total_steps": 824, "loss": 0.5487, "lr": 1.6606531481668364e-06, "epoch": 3.0437823046518697, "percentage": 76.09, "elapsed_time": "1 day, 9:06:11", "remaining_time": "10:24:03"}
{"current_steps": 628, "total_steps": 824, "loss": 0.5234, "lr": 1.6449057451223354e-06, "epoch": 3.0486470051687444, "percentage": 76.21, "elapsed_time": "1 day, 9:09:13", "remaining_time": "10:20:50"}
{"current_steps": 629, "total_steps": 824, "loss": 0.5376, "lr": 1.6292186490333172e-06, "epoch": 3.0535117056856187, "percentage": 76.33, "elapsed_time": "1 day, 9:12:15", "remaining_time": "10:17:37"}
{"current_steps": 630, "total_steps": 824, "loss": 0.5507, "lr": 1.6135921418712959e-06, "epoch": 3.058376406202493, "percentage": 76.46, "elapsed_time": "1 day, 9:15:45", "remaining_time": "10:14:34"}
{"current_steps": 631, "total_steps": 824, "loss": 0.5456, "lr": 1.5980265045187139e-06, "epoch": 3.0632411067193677, "percentage": 76.58, "elapsed_time": "1 day, 9:18:28", "remaining_time": "10:11:15"}
{"current_steps": 632, "total_steps": 824, "loss": 0.5276, "lr": 1.5825220167638945e-06, "epoch": 3.068105807236242, "percentage": 76.7, "elapsed_time": "1 day, 9:22:26", "remaining_time": "10:08:20"}
{"current_steps": 633, "total_steps": 824, "loss": 0.5571, "lr": 1.567078957296016e-06, "epoch": 3.0729705077531166, "percentage": 76.82, "elapsed_time": "1 day, 9:25:23", "remaining_time": "10:05:06"}
{"current_steps": 634, "total_steps": 824, "loss": 0.5228, "lr": 1.5516976037000941e-06, "epoch": 3.077835208269991, "percentage": 76.94, "elapsed_time": "1 day, 9:29:38", "remaining_time": "10:02:15"}
{"current_steps": 635, "total_steps": 824, "loss": 0.5262, "lr": 1.5363782324520033e-06, "epoch": 3.082699908786865, "percentage": 77.06, "elapsed_time": "1 day, 9:32:57", "remaining_time": "9:59:07"}
{"current_steps": 636, "total_steps": 824, "loss": 0.5108, "lr": 1.5211211189134955e-06, "epoch": 3.08756460930374, "percentage": 77.18, "elapsed_time": "1 day, 9:36:21", "remaining_time": "9:56:01"}
{"current_steps": 637, "total_steps": 824, "loss": 0.5164, "lr": 1.5059265373272574e-06, "epoch": 3.092429309820614, "percentage": 77.31, "elapsed_time": "1 day, 9:39:37", "remaining_time": "9:52:53"}
{"current_steps": 638, "total_steps": 824, "loss": 0.5598, "lr": 1.4907947608119866e-06, "epoch": 3.0972940103374884, "percentage": 77.43, "elapsed_time": "1 day, 9:43:06", "remaining_time": "9:49:48"}
{"current_steps": 639, "total_steps": 824, "loss": 0.5513, "lr": 1.475726061357463e-06, "epoch": 3.102158710854363, "percentage": 77.55, "elapsed_time": "1 day, 9:46:06", "remaining_time": "9:46:35"}
{"current_steps": 640, "total_steps": 824, "loss": 0.5259, "lr": 1.4607207098196851e-06, "epoch": 3.1070234113712374, "percentage": 77.67, "elapsed_time": "1 day, 9:50:03", "remaining_time": "9:43:38"}
{"current_steps": 641, "total_steps": 824, "loss": 0.5375, "lr": 1.4457789759159813e-06, "epoch": 3.111888111888112, "percentage": 77.79, "elapsed_time": "1 day, 9:53:04", "remaining_time": "9:40:25"}
{"current_steps": 642, "total_steps": 824, "loss": 0.5163, "lr": 1.430901128220174e-06, "epoch": 3.1167528124049864, "percentage": 77.91, "elapsed_time": "1 day, 9:56:01", "remaining_time": "9:37:11"}
{"current_steps": 643, "total_steps": 824, "loss": 0.5438, "lr": 1.4160874341577447e-06, "epoch": 3.1216175129218606, "percentage": 78.03, "elapsed_time": "1 day, 9:58:37", "remaining_time": "9:33:51"}
{"current_steps": 644, "total_steps": 824, "loss": 0.5381, "lr": 1.4013381600010278e-06, "epoch": 3.1264822134387353, "percentage": 78.16, "elapsed_time": "1 day, 10:01:09", "remaining_time": "9:30:30"}
{"current_steps": 645, "total_steps": 824, "loss": 0.529, "lr": 1.3866535708644335e-06, "epoch": 3.1313469139556096, "percentage": 78.28, "elapsed_time": "1 day, 10:04:00", "remaining_time": "9:27:15"}
{"current_steps": 646, "total_steps": 824, "loss": 0.5437, "lr": 1.3720339306996666e-06, "epoch": 3.136211614472484, "percentage": 78.4, "elapsed_time": "1 day, 10:07:39", "remaining_time": "9:24:13"}
{"current_steps": 647, "total_steps": 824, "loss": 0.5428, "lr": 1.3574795022910014e-06, "epoch": 3.1410763149893586, "percentage": 78.52, "elapsed_time": "1 day, 10:10:27", "remaining_time": "9:20:56"}
{"current_steps": 648, "total_steps": 824, "loss": 0.5397, "lr": 1.3429905472505344e-06, "epoch": 3.145941015506233, "percentage": 78.64, "elapsed_time": "1 day, 10:14:03", "remaining_time": "9:17:53"}
{"current_steps": 649, "total_steps": 824, "loss": 0.5283, "lr": 1.3285673260135073e-06, "epoch": 3.1508057160231075, "percentage": 78.76, "elapsed_time": "1 day, 10:17:27", "remaining_time": "9:14:46"}
{"current_steps": 650, "total_steps": 824, "loss": 0.5153, "lr": 1.314210097833607e-06, "epoch": 3.155670416539982, "percentage": 78.88, "elapsed_time": "1 day, 10:20:24", "remaining_time": "9:11:33"}
{"current_steps": 651, "total_steps": 824, "loss": 0.5513, "lr": 1.2999191207783129e-06, "epoch": 3.160535117056856, "percentage": 79.0, "elapsed_time": "1 day, 10:23:22", "remaining_time": "9:08:20"}
{"current_steps": 652, "total_steps": 824, "loss": 0.5477, "lr": 1.2856946517242608e-06, "epoch": 3.165399817573731, "percentage": 79.13, "elapsed_time": "1 day, 10:26:53", "remaining_time": "9:05:15"}
{"current_steps": 653, "total_steps": 824, "loss": 0.5427, "lr": 1.2715369463526173e-06, "epoch": 3.170264518090605, "percentage": 79.25, "elapsed_time": "1 day, 10:29:56", "remaining_time": "9:02:03"}
{"current_steps": 654, "total_steps": 824, "loss": 0.5226, "lr": 1.257446259144494e-06, "epoch": 3.1751292186074793, "percentage": 79.37, "elapsed_time": "1 day, 10:33:02", "remaining_time": "8:58:51"}
{"current_steps": 655, "total_steps": 824, "loss": 0.5343, "lr": 1.2434228433763657e-06, "epoch": 3.179993919124354, "percentage": 79.49, "elapsed_time": "1 day, 10:36:25", "remaining_time": "8:55:45"}
{"current_steps": 656, "total_steps": 824, "loss": 0.5654, "lr": 1.2294669511155193e-06, "epoch": 3.1848586196412283, "percentage": 79.61, "elapsed_time": "1 day, 10:39:36", "remaining_time": "8:52:34"}
{"current_steps": 657, "total_steps": 824, "loss": 0.5409, "lr": 1.215578833215526e-06, "epoch": 3.1897233201581026, "percentage": 79.73, "elapsed_time": "1 day, 10:42:39", "remaining_time": "8:49:23"}
{"current_steps": 658, "total_steps": 824, "loss": 0.5345, "lr": 1.201758739311728e-06, "epoch": 3.1945880206749773, "percentage": 79.85, "elapsed_time": "1 day, 10:45:51", "remaining_time": "8:46:13"}
{"current_steps": 659, "total_steps": 824, "loss": 0.5307, "lr": 1.1880069178167586e-06, "epoch": 3.1994527211918515, "percentage": 79.98, "elapsed_time": "1 day, 10:48:37", "remaining_time": "8:42:56"}
{"current_steps": 660, "total_steps": 824, "loss": 0.5344, "lr": 1.1743236159160654e-06, "epoch": 3.2043174217087262, "percentage": 80.1, "elapsed_time": "1 day, 10:52:09", "remaining_time": "8:39:52"}
{"current_steps": 661, "total_steps": 824, "loss": 0.5592, "lr": 1.1607090795634802e-06, "epoch": 3.2091821222256005, "percentage": 80.22, "elapsed_time": "1 day, 10:55:33", "remaining_time": "8:36:45"}
{"current_steps": 662, "total_steps": 824, "loss": 0.5472, "lr": 1.1471635534767877e-06, "epoch": 3.2140468227424748, "percentage": 80.34, "elapsed_time": "1 day, 10:59:00", "remaining_time": "8:33:39"}
{"current_steps": 663, "total_steps": 824, "loss": 0.5328, "lr": 1.133687281133331e-06, "epoch": 3.2189115232593495, "percentage": 80.46, "elapsed_time": "1 day, 11:02:14", "remaining_time": "8:30:29"}
{"current_steps": 664, "total_steps": 824, "loss": 0.5414, "lr": 1.1202805047656406e-06, "epoch": 3.2237762237762237, "percentage": 80.58, "elapsed_time": "1 day, 11:05:40", "remaining_time": "8:27:23"}
{"current_steps": 665, "total_steps": 824, "loss": 0.5229, "lr": 1.1069434653570633e-06, "epoch": 3.228640924293098, "percentage": 80.7, "elapsed_time": "1 day, 11:08:55", "remaining_time": "8:24:14"}
{"current_steps": 666, "total_steps": 824, "loss": 0.5461, "lr": 1.0936764026374547e-06, "epoch": 3.2335056248099727, "percentage": 80.83, "elapsed_time": "1 day, 11:12:41", "remaining_time": "8:21:12"}
{"current_steps": 667, "total_steps": 824, "loss": 0.5335, "lr": 1.0804795550788473e-06, "epoch": 3.238370325326847, "percentage": 80.95, "elapsed_time": "1 day, 11:16:07", "remaining_time": "8:18:05"}
{"current_steps": 668, "total_steps": 824, "loss": 0.5301, "lr": 1.0673531598911824e-06, "epoch": 3.2432350258437217, "percentage": 81.07, "elapsed_time": "1 day, 11:19:06", "remaining_time": "8:14:52"}
{"current_steps": 669, "total_steps": 824, "loss": 0.5506, "lr": 1.0542974530180327e-06, "epoch": 3.248099726360596, "percentage": 81.19, "elapsed_time": "1 day, 11:22:45", "remaining_time": "8:11:49"}
{"current_steps": 670, "total_steps": 824, "loss": 0.5403, "lr": 1.0413126691323667e-06, "epoch": 3.2529644268774702, "percentage": 81.31, "elapsed_time": "1 day, 11:25:38", "remaining_time": "8:08:34"}
{"current_steps": 671, "total_steps": 824, "loss": 0.5357, "lr": 1.0283990416323336e-06, "epoch": 3.257829127394345, "percentage": 81.43, "elapsed_time": "1 day, 11:27:58", "remaining_time": "8:05:13"}
{"current_steps": 672, "total_steps": 824, "loss": 0.5514, "lr": 1.0155568026370637e-06, "epoch": 3.262693827911219, "percentage": 81.55, "elapsed_time": "1 day, 11:31:07", "remaining_time": "8:02:02"}
{"current_steps": 673, "total_steps": 824, "loss": 0.5521, "lr": 1.0027861829824953e-06, "epoch": 3.2675585284280935, "percentage": 81.67, "elapsed_time": "1 day, 11:34:23", "remaining_time": "7:58:53"}
{"current_steps": 674, "total_steps": 824, "loss": 0.528, "lr": 9.900874122172294e-07, "epoch": 3.272423228944968, "percentage": 81.8, "elapsed_time": "1 day, 11:37:47", "remaining_time": "7:55:46"}
{"current_steps": 675, "total_steps": 824, "loss": 0.5364, "lr": 9.774607185984004e-07, "epoch": 3.2772879294618424, "percentage": 81.92, "elapsed_time": "1 day, 11:40:25", "remaining_time": "7:52:28"}
{"current_steps": 676, "total_steps": 824, "loss": 0.5598, "lr": 9.649063290875771e-07, "epoch": 3.282152629978717, "percentage": 82.04, "elapsed_time": "1 day, 11:43:05", "remaining_time": "7:49:11"}
{"current_steps": 677, "total_steps": 824, "loss": 0.5429, "lr": 9.524244693466773e-07, "epoch": 3.2870173304955914, "percentage": 82.16, "elapsed_time": "1 day, 11:45:53", "remaining_time": "7:45:56"}
{"current_steps": 678, "total_steps": 824, "loss": 0.5413, "lr": 9.400153637339182e-07, "epoch": 3.2918820310124657, "percentage": 82.28, "elapsed_time": "1 day, 11:49:19", "remaining_time": "7:42:50"}
{"current_steps": 679, "total_steps": 824, "loss": 0.5725, "lr": 9.276792352997782e-07, "epoch": 3.2967467315293404, "percentage": 82.4, "elapsed_time": "1 day, 11:51:53", "remaining_time": "7:39:32"}
{"current_steps": 680, "total_steps": 824, "loss": 0.5181, "lr": 9.154163057829879e-07, "epoch": 3.3016114320462147, "percentage": 82.52, "elapsed_time": "1 day, 11:55:21", "remaining_time": "7:36:25"}
{"current_steps": 681, "total_steps": 824, "loss": 0.5594, "lr": 9.032267956065516e-07, "epoch": 3.306476132563089, "percentage": 82.65, "elapsed_time": "1 day, 11:58:22", "remaining_time": "7:33:13"}
{"current_steps": 682, "total_steps": 824, "loss": 0.5152, "lr": 8.911109238737748e-07, "epoch": 3.3113408330799636, "percentage": 82.77, "elapsed_time": "1 day, 12:01:18", "remaining_time": "7:30:00"}
{"current_steps": 683, "total_steps": 824, "loss": 0.5708, "lr": 8.790689083643328e-07, "epoch": 3.316205533596838, "percentage": 82.89, "elapsed_time": "1 day, 12:04:33", "remaining_time": "7:26:51"}
{"current_steps": 684, "total_steps": 824, "loss": 0.5575, "lr": 8.671009655303531e-07, "epoch": 3.321070234113712, "percentage": 83.01, "elapsed_time": "1 day, 12:07:57", "remaining_time": "7:23:44"}
{"current_steps": 685, "total_steps": 824, "loss": 0.5267, "lr": 8.552073104925296e-07, "epoch": 3.325934934630587, "percentage": 83.13, "elapsed_time": "1 day, 12:11:53", "remaining_time": "7:20:43"}
{"current_steps": 686, "total_steps": 824, "loss": 0.5299, "lr": 8.433881570362484e-07, "epoch": 3.330799635147461, "percentage": 83.25, "elapsed_time": "1 day, 12:15:39", "remaining_time": "7:17:40"}
{"current_steps": 687, "total_steps": 824, "loss": 0.5492, "lr": 8.316437176077491e-07, "epoch": 3.335664335664336, "percentage": 83.37, "elapsed_time": "1 day, 12:18:49", "remaining_time": "7:14:29"}
{"current_steps": 688, "total_steps": 824, "loss": 0.5315, "lr": 8.199742033103091e-07, "epoch": 3.34052903618121, "percentage": 83.5, "elapsed_time": "1 day, 12:21:52", "remaining_time": "7:11:18"}
{"current_steps": 689, "total_steps": 824, "loss": 0.5458, "lr": 8.083798239004408e-07, "epoch": 3.3453937366980844, "percentage": 83.62, "elapsed_time": "1 day, 12:25:29", "remaining_time": "7:08:13"}
{"current_steps": 690, "total_steps": 824, "loss": 0.5574, "lr": 7.968607877841333e-07, "epoch": 3.350258437214959, "percentage": 83.74, "elapsed_time": "1 day, 12:29:03", "remaining_time": "7:05:07"}
{"current_steps": 691, "total_steps": 824, "loss": 0.5384, "lr": 7.854173020130906e-07, "epoch": 3.3551231377318333, "percentage": 83.86, "elapsed_time": "1 day, 12:33:04", "remaining_time": "7:02:06"}
{"current_steps": 692, "total_steps": 824, "loss": 0.534, "lr": 7.740495722810271e-07, "epoch": 3.359987838248708, "percentage": 83.98, "elapsed_time": "1 day, 12:36:15", "remaining_time": "6:58:56"}
{"current_steps": 693, "total_steps": 824, "loss": 0.5574, "lr": 7.627578029199562e-07, "epoch": 3.3648525387655823, "percentage": 84.1, "elapsed_time": "1 day, 12:39:18", "remaining_time": "6:55:44"}
{"current_steps": 694, "total_steps": 824, "loss": 0.5413, "lr": 7.515421968965242e-07, "epoch": 3.3697172392824566, "percentage": 84.22, "elapsed_time": "1 day, 12:42:33", "remaining_time": "6:52:34"}
{"current_steps": 695, "total_steps": 824, "loss": 0.5301, "lr": 7.404029558083653e-07, "epoch": 3.374581939799331, "percentage": 84.34, "elapsed_time": "1 day, 12:45:29", "remaining_time": "6:49:21"}
{"current_steps": 696, "total_steps": 824, "loss": 0.5434, "lr": 7.293402798804667e-07, "epoch": 3.3794466403162056, "percentage": 84.47, "elapsed_time": "1 day, 12:48:46", "remaining_time": "6:46:12"}
{"current_steps": 697, "total_steps": 824, "loss": 0.5442, "lr": 7.183543679615834e-07, "epoch": 3.38431134083308, "percentage": 84.59, "elapsed_time": "1 day, 12:51:39", "remaining_time": "6:42:59"}
{"current_steps": 698, "total_steps": 824, "loss": 0.5621, "lr": 7.074454175206524e-07, "epoch": 3.3891760413499545, "percentage": 84.71, "elapsed_time": "1 day, 12:54:52", "remaining_time": "6:39:49"}
{"current_steps": 699, "total_steps": 824, "loss": 0.5279, "lr": 6.966136246432492e-07, "epoch": 3.394040741866829, "percentage": 84.83, "elapsed_time": "1 day, 12:57:45", "remaining_time": "6:36:35"}
{"current_steps": 700, "total_steps": 824, "loss": 0.5316, "lr": 6.858591840280627e-07, "epoch": 3.398905442383703, "percentage": 84.95, "elapsed_time": "1 day, 13:01:23", "remaining_time": "6:33:30"}
{"current_steps": 701, "total_steps": 824, "loss": 0.5503, "lr": 6.751822889833926e-07, "epoch": 3.4037701429005778, "percentage": 85.07, "elapsed_time": "1 day, 13:04:15", "remaining_time": "6:30:16"}
{"current_steps": 702, "total_steps": 824, "loss": 0.5364, "lr": 6.645831314236817e-07, "epoch": 3.408634843417452, "percentage": 85.19, "elapsed_time": "1 day, 13:07:10", "remaining_time": "6:27:03"}
{"current_steps": 703, "total_steps": 824, "loss": 0.5329, "lr": 6.540619018660555e-07, "epoch": 3.4134995439343268, "percentage": 85.32, "elapsed_time": "1 day, 13:10:27", "remaining_time": "6:23:54"}
{"current_steps": 704, "total_steps": 824, "loss": 0.5477, "lr": 6.436187894269086e-07, "epoch": 3.418364244451201, "percentage": 85.44, "elapsed_time": "1 day, 13:12:41", "remaining_time": "6:20:34"}
{"current_steps": 705, "total_steps": 824, "loss": 0.5273, "lr": 6.332539818184985e-07, "epoch": 3.4232289449680753, "percentage": 85.56, "elapsed_time": "1 day, 13:17:05", "remaining_time": "6:17:36"}
{"current_steps": 706, "total_steps": 824, "loss": 0.5409, "lr": 6.229676653455719e-07, "epoch": 3.42809364548495, "percentage": 85.68, "elapsed_time": "1 day, 13:21:05", "remaining_time": "6:14:34"}
{"current_steps": 707, "total_steps": 824, "loss": 0.5452, "lr": 6.127600249020216e-07, "epoch": 3.4329583460018243, "percentage": 85.8, "elapsed_time": "1 day, 13:24:18", "remaining_time": "6:11:24"}
{"current_steps": 708, "total_steps": 824, "loss": 0.5338, "lr": 6.026312439675553e-07, "epoch": 3.4378230465186985, "percentage": 85.92, "elapsed_time": "1 day, 13:26:59", "remaining_time": "6:08:09"}
{"current_steps": 709, "total_steps": 824, "loss": 0.5375, "lr": 5.925815046044026e-07, "epoch": 3.4426877470355732, "percentage": 86.04, "elapsed_time": "1 day, 13:29:55", "remaining_time": "6:04:56"}
{"current_steps": 710, "total_steps": 824, "loss": 0.5399, "lr": 5.826109874540409e-07, "epoch": 3.4475524475524475, "percentage": 86.17, "elapsed_time": "1 day, 13:33:57", "remaining_time": "6:01:54"}
{"current_steps": 711, "total_steps": 824, "loss": 0.5683, "lr": 5.727198717339511e-07, "epoch": 3.4524171480693218, "percentage": 86.29, "elapsed_time": "1 day, 13:37:01", "remaining_time": "5:58:42"}
{"current_steps": 712, "total_steps": 824, "loss": 0.5453, "lr": 5.6290833523439e-07, "epoch": 3.4572818485861965, "percentage": 86.41, "elapsed_time": "1 day, 13:39:36", "remaining_time": "5:55:26"}
{"current_steps": 713, "total_steps": 824, "loss": 0.547, "lr": 5.531765543152002e-07, "epoch": 3.4621465491030707, "percentage": 86.53, "elapsed_time": "1 day, 13:43:01", "remaining_time": "5:52:18"}
{"current_steps": 714, "total_steps": 824, "loss": 0.5246, "lr": 5.435247039026398e-07, "epoch": 3.4670112496199454, "percentage": 86.65, "elapsed_time": "1 day, 13:46:12", "remaining_time": "5:49:08"}
{"current_steps": 715, "total_steps": 824, "loss": 0.5371, "lr": 5.33952957486234e-07, "epoch": 3.4718759501368197, "percentage": 86.77, "elapsed_time": "1 day, 13:49:33", "remaining_time": "5:45:59"}
{"current_steps": 716, "total_steps": 824, "loss": 0.5532, "lr": 5.244614871156612e-07, "epoch": 3.476740650653694, "percentage": 86.89, "elapsed_time": "1 day, 13:52:28", "remaining_time": "5:42:46"}
{"current_steps": 717, "total_steps": 824, "loss": 0.5288, "lr": 5.150504633976572e-07, "epoch": 3.4816053511705687, "percentage": 87.01, "elapsed_time": "1 day, 13:55:47", "remaining_time": "5:39:37"}
{"current_steps": 718, "total_steps": 824, "loss": 0.559, "lr": 5.057200554929509e-07, "epoch": 3.486470051687443, "percentage": 87.14, "elapsed_time": "1 day, 13:59:06", "remaining_time": "5:36:28"}
{"current_steps": 719, "total_steps": 824, "loss": 0.5327, "lr": 4.964704311132224e-07, "epoch": 3.4913347522043177, "percentage": 87.26, "elapsed_time": "1 day, 14:02:23", "remaining_time": "5:33:18"}
{"current_steps": 720, "total_steps": 824, "loss": 0.5315, "lr": 4.873017565180871e-07, "epoch": 3.496199452721192, "percentage": 87.38, "elapsed_time": "1 day, 14:05:14", "remaining_time": "5:30:05"}
{"current_steps": 721, "total_steps": 824, "loss": 0.5452, "lr": 4.782141965121129e-07, "epoch": 3.501064153238066, "percentage": 87.5, "elapsed_time": "1 day, 14:08:12", "remaining_time": "5:26:53"}
{"current_steps": 722, "total_steps": 824, "loss": 0.5366, "lr": 4.6920791444184934e-07, "epoch": 3.5059288537549405, "percentage": 87.62, "elapsed_time": "1 day, 14:11:26", "remaining_time": "5:23:43"}
{"current_steps": 723, "total_steps": 824, "loss": 0.532, "lr": 4.602830721928997e-07, "epoch": 3.510793554271815, "percentage": 87.74, "elapsed_time": "1 day, 14:14:58", "remaining_time": "5:20:35"}
{"current_steps": 724, "total_steps": 824, "loss": 0.5493, "lr": 4.5143983018700485e-07, "epoch": 3.5156582547886894, "percentage": 87.86, "elapsed_time": "1 day, 14:18:20", "remaining_time": "5:17:26"}
{"current_steps": 725, "total_steps": 824, "loss": 0.556, "lr": 4.4267834737916295e-07, "epoch": 3.520522955305564, "percentage": 87.99, "elapsed_time": "1 day, 14:20:44", "remaining_time": "5:14:10"}
{"current_steps": 726, "total_steps": 824, "loss": 0.5613, "lr": 4.33998781254773e-07, "epoch": 3.5253876558224384, "percentage": 88.11, "elapsed_time": "1 day, 14:23:36", "remaining_time": "5:10:57"}
{"current_steps": 727, "total_steps": 824, "loss": 0.5343, "lr": 4.2540128782679934e-07, "epoch": 3.5302523563393127, "percentage": 88.23, "elapsed_time": "1 day, 14:26:54", "remaining_time": "5:07:47"}
{"current_steps": 728, "total_steps": 824, "loss": 0.5394, "lr": 4.1688602163297564e-07, "epoch": 3.5351170568561874, "percentage": 88.35, "elapsed_time": "1 day, 14:30:04", "remaining_time": "5:04:37"}
{"current_steps": 729, "total_steps": 824, "loss": 0.5561, "lr": 4.0845313573301736e-07, "epoch": 3.5399817573730616, "percentage": 88.47, "elapsed_time": "1 day, 14:33:21", "remaining_time": "5:01:27"}
{"current_steps": 730, "total_steps": 824, "loss": 0.5315, "lr": 4.001027817058789e-07, "epoch": 3.5448464578899364, "percentage": 88.59, "elapsed_time": "1 day, 14:36:56", "remaining_time": "4:58:20"}
{"current_steps": 731, "total_steps": 824, "loss": 0.535, "lr": 3.9183510964702463e-07, "epoch": 3.5497111584068106, "percentage": 88.71, "elapsed_time": "1 day, 14:40:40", "remaining_time": "4:55:14"}
{"current_steps": 732, "total_steps": 824, "loss": 0.5376, "lr": 3.836502681657289e-07, "epoch": 3.554575858923685, "percentage": 88.83, "elapsed_time": "1 day, 14:43:08", "remaining_time": "4:51:58"}
{"current_steps": 733, "total_steps": 824, "loss": 0.5556, "lr": 3.755484043824131e-07, "epoch": 3.5594405594405596, "percentage": 88.96, "elapsed_time": "1 day, 14:45:38", "remaining_time": "4:48:43"}
{"current_steps": 734, "total_steps": 824, "loss": 0.5512, "lr": 3.675296639259912e-07, "epoch": 3.564305259957434, "percentage": 89.08, "elapsed_time": "1 day, 14:48:34", "remaining_time": "4:45:31"}
{"current_steps": 735, "total_steps": 824, "loss": 0.5246, "lr": 3.595941909312595e-07, "epoch": 3.5691699604743086, "percentage": 89.2, "elapsed_time": "1 day, 14:51:25", "remaining_time": "4:42:18"}
{"current_steps": 736, "total_steps": 824, "loss": 0.5449, "lr": 3.517421280363004e-07, "epoch": 3.574034660991183, "percentage": 89.32, "elapsed_time": "1 day, 14:55:15", "remaining_time": "4:39:12"}
{"current_steps": 737, "total_steps": 824, "loss": 0.5235, "lr": 3.439736163799251e-07, "epoch": 3.578899361508057, "percentage": 89.44, "elapsed_time": "1 day, 14:59:04", "remaining_time": "4:36:07"}
{"current_steps": 738, "total_steps": 824, "loss": 0.521, "lr": 3.362887955991301e-07, "epoch": 3.5837640620249314, "percentage": 89.56, "elapsed_time": "1 day, 15:02:13", "remaining_time": "4:32:56"}
{"current_steps": 739, "total_steps": 824, "loss": 0.5264, "lr": 3.2868780382658895e-07, "epoch": 3.588628762541806, "percentage": 89.68, "elapsed_time": "1 day, 15:05:38", "remaining_time": "4:29:47"}
{"current_steps": 740, "total_steps": 824, "loss": 0.5621, "lr": 3.2117077768817395e-07, "epoch": 3.5934934630586803, "percentage": 89.81, "elapsed_time": "1 day, 15:09:07", "remaining_time": "4:26:39"}
{"current_steps": 741, "total_steps": 824, "loss": 0.5524, "lr": 3.1373785230049356e-07, "epoch": 3.598358163575555, "percentage": 89.93, "elapsed_time": "1 day, 15:12:59", "remaining_time": "4:23:33"}
{"current_steps": 742, "total_steps": 824, "loss": 0.5525, "lr": 3.0638916126846885e-07, "epoch": 3.6032228640924293, "percentage": 90.05, "elapsed_time": "1 day, 15:15:41", "remaining_time": "4:20:19"}
{"current_steps": 743, "total_steps": 824, "loss": 0.5495, "lr": 2.991248366829291e-07, "epoch": 3.6080875646093036, "percentage": 90.17, "elapsed_time": "1 day, 15:18:55", "remaining_time": "4:17:09"}
{"current_steps": 744, "total_steps": 824, "loss": 0.541, "lr": 2.91945009118238e-07, "epoch": 3.6129522651261783, "percentage": 90.29, "elapsed_time": "1 day, 15:22:32", "remaining_time": "4:14:02"}
{"current_steps": 745, "total_steps": 824, "loss": 0.5432, "lr": 2.848498076299483e-07, "epoch": 3.6178169656430526, "percentage": 90.41, "elapsed_time": "1 day, 15:25:36", "remaining_time": "4:10:50"}
{"current_steps": 746, "total_steps": 824, "loss": 0.5294, "lr": 2.7783935975247867e-07, "epoch": 3.6226816661599273, "percentage": 90.53, "elapsed_time": "1 day, 15:28:16", "remaining_time": "4:07:37"}
{"current_steps": 747, "total_steps": 824, "loss": 0.527, "lr": 2.7091379149682683e-07, "epoch": 3.6275463666768015, "percentage": 90.66, "elapsed_time": "1 day, 15:31:15", "remaining_time": "4:04:25"}
{"current_steps": 748, "total_steps": 824, "loss": 0.5337, "lr": 2.6407322734829763e-07, "epoch": 3.632411067193676, "percentage": 90.78, "elapsed_time": "1 day, 15:34:46", "remaining_time": "4:01:17"}
{"current_steps": 749, "total_steps": 824, "loss": 0.5336, "lr": 2.573177902642726e-07, "epoch": 3.63727576771055, "percentage": 90.9, "elapsed_time": "1 day, 15:38:00", "remaining_time": "3:58:07"}
{"current_steps": 750, "total_steps": 824, "loss": 0.5278, "lr": 2.506476016719922e-07, "epoch": 3.6421404682274248, "percentage": 91.02, "elapsed_time": "1 day, 15:41:13", "remaining_time": "3:54:56"}
{"current_steps": 751, "total_steps": 824, "loss": 0.5458, "lr": 2.440627814663804e-07, "epoch": 3.647005168744299, "percentage": 91.14, "elapsed_time": "1 day, 15:44:16", "remaining_time": "3:51:45"}
{"current_steps": 752, "total_steps": 824, "loss": 0.5404, "lr": 2.3756344800788421e-07, "epoch": 3.6518698692611737, "percentage": 91.26, "elapsed_time": "1 day, 15:47:17", "remaining_time": "3:48:34"}
{"current_steps": 753, "total_steps": 824, "loss": 0.5481, "lr": 2.3114971812034981e-07, "epoch": 3.656734569778048, "percentage": 91.38, "elapsed_time": "1 day, 15:50:10", "remaining_time": "3:45:22"}
{"current_steps": 754, "total_steps": 824, "loss": 0.5665, "lr": 2.2482170708892083e-07, "epoch": 3.6615992702949223, "percentage": 91.5, "elapsed_time": "1 day, 15:52:48", "remaining_time": "3:42:08"}
{"current_steps": 755, "total_steps": 824, "loss": 0.5635, "lr": 2.1857952865796616e-07, "epoch": 3.666463970811797, "percentage": 91.63, "elapsed_time": "1 day, 15:56:19", "remaining_time": "3:39:00"}
{"current_steps": 756, "total_steps": 824, "loss": 0.5453, "lr": 2.124232950290367e-07, "epoch": 3.6713286713286712, "percentage": 91.75, "elapsed_time": "1 day, 15:59:12", "remaining_time": "3:35:48"}
{"current_steps": 757, "total_steps": 824, "loss": 0.5274, "lr": 2.0635311685884675e-07, "epoch": 3.676193371845546, "percentage": 91.87, "elapsed_time": "1 day, 16:02:29", "remaining_time": "3:32:38"}
{"current_steps": 758, "total_steps": 824, "loss": 0.5332, "lr": 2.0036910325728521e-07, "epoch": 3.68105807236242, "percentage": 91.99, "elapsed_time": "1 day, 16:06:08", "remaining_time": "3:29:30"}
{"current_steps": 759, "total_steps": 824, "loss": 0.5676, "lr": 1.9447136178545766e-07, "epoch": 3.6859227728792945, "percentage": 92.11, "elapsed_time": "1 day, 16:08:14", "remaining_time": "3:26:14"}
{"current_steps": 760, "total_steps": 824, "loss": 0.5401, "lr": 1.8865999845374794e-07, "epoch": 3.690787473396169, "percentage": 92.23, "elapsed_time": "1 day, 16:11:30", "remaining_time": "3:23:04"}
{"current_steps": 761, "total_steps": 824, "loss": 0.5571, "lr": 1.8293511771991624e-07, "epoch": 3.6956521739130435, "percentage": 92.35, "elapsed_time": "1 day, 16:14:48", "remaining_time": "3:19:54"}
{"current_steps": 762, "total_steps": 824, "loss": 0.5219, "lr": 1.7729682248721848e-07, "epoch": 3.700516874429918, "percentage": 92.48, "elapsed_time": "1 day, 16:17:45", "remaining_time": "3:16:43"}
{"current_steps": 763, "total_steps": 824, "loss": 0.5326, "lr": 1.7174521410256162e-07, "epoch": 3.7053815749467924, "percentage": 92.6, "elapsed_time": "1 day, 16:21:23", "remaining_time": "3:13:35"}
{"current_steps": 764, "total_steps": 824, "loss": 0.5286, "lr": 1.6628039235467686e-07, "epoch": 3.7102462754636667, "percentage": 92.72, "elapsed_time": "1 day, 16:23:45", "remaining_time": "3:10:20"}
{"current_steps": 765, "total_steps": 824, "loss": 0.5412, "lr": 1.6090245547232707e-07, "epoch": 3.715110975980541, "percentage": 92.84, "elapsed_time": "1 day, 16:27:01", "remaining_time": "3:07:10"}
{"current_steps": 766, "total_steps": 824, "loss": 0.5473, "lr": 1.5561150012254446e-07, "epoch": 3.7199756764974157, "percentage": 92.96, "elapsed_time": "1 day, 16:29:51", "remaining_time": "3:03:59"}
{"current_steps": 767, "total_steps": 824, "loss": 0.5286, "lr": 1.5040762140888843e-07, "epoch": 3.72484037701429, "percentage": 93.08, "elapsed_time": "1 day, 16:32:29", "remaining_time": "3:00:46"}
{"current_steps": 768, "total_steps": 824, "loss": 0.5407, "lr": 1.4529091286973994e-07, "epoch": 3.7297050775311646, "percentage": 93.2, "elapsed_time": "1 day, 16:35:41", "remaining_time": "2:57:36"}
{"current_steps": 769, "total_steps": 824, "loss": 0.5739, "lr": 1.402614664766172e-07, "epoch": 3.734569778048039, "percentage": 93.33, "elapsed_time": "1 day, 16:38:34", "remaining_time": "2:54:24"}
{"current_steps": 770, "total_steps": 824, "loss": 0.5561, "lr": 1.353193726325247e-07, "epoch": 3.739434478564913, "percentage": 93.45, "elapsed_time": "1 day, 16:41:44", "remaining_time": "2:51:14"}
{"current_steps": 771, "total_steps": 824, "loss": 0.5494, "lr": 1.3046472017032685e-07, "epoch": 3.744299179081788, "percentage": 93.57, "elapsed_time": "1 day, 16:44:33", "remaining_time": "2:48:02"}
{"current_steps": 772, "total_steps": 824, "loss": 0.5632, "lr": 1.2569759635115086e-07, "epoch": 3.749163879598662, "percentage": 93.69, "elapsed_time": "1 day, 16:47:27", "remaining_time": "2:44:51"}
{"current_steps": 773, "total_steps": 824, "loss": 0.5346, "lr": 1.210180868628219e-07, "epoch": 3.754028580115537, "percentage": 93.81, "elapsed_time": "1 day, 16:50:18", "remaining_time": "2:41:39"}
{"current_steps": 774, "total_steps": 824, "loss": 0.5269, "lr": 1.1642627581831767e-07, "epoch": 3.758893280632411, "percentage": 93.93, "elapsed_time": "1 day, 16:53:34", "remaining_time": "2:38:30"}
{"current_steps": 775, "total_steps": 824, "loss": 0.553, "lr": 1.1192224575425848e-07, "epoch": 3.7637579811492854, "percentage": 94.05, "elapsed_time": "1 day, 16:57:06", "remaining_time": "2:35:21"}
{"current_steps": 776, "total_steps": 824, "loss": 0.5443, "lr": 1.0750607762942622e-07, "epoch": 3.7686226816661597, "percentage": 94.17, "elapsed_time": "1 day, 17:01:11", "remaining_time": "2:32:14"}
{"current_steps": 777, "total_steps": 824, "loss": 0.542, "lr": 1.0317785082330555e-07, "epoch": 3.7734873821830344, "percentage": 94.3, "elapsed_time": "1 day, 17:04:46", "remaining_time": "2:29:05"}
{"current_steps": 778, "total_steps": 824, "loss": 0.565, "lr": 9.89376431346606e-08, "epoch": 3.7783520826999086, "percentage": 94.42, "elapsed_time": "1 day, 17:07:38", "remaining_time": "2:25:54"}
{"current_steps": 779, "total_steps": 824, "loss": 0.5341, "lr": 9.478553078013042e-08, "epoch": 3.7832167832167833, "percentage": 94.54, "elapsed_time": "1 day, 17:10:51", "remaining_time": "2:22:43"}
{"current_steps": 780, "total_steps": 824, "loss": 0.54, "lr": 9.072158839286748e-08, "epoch": 3.7880814837336576, "percentage": 94.66, "elapsed_time": "1 day, 17:13:58", "remaining_time": "2:19:33"}
{"current_steps": 781, "total_steps": 824, "loss": 0.5236, "lr": 8.674588902118919e-08, "epoch": 3.792946184250532, "percentage": 94.78, "elapsed_time": "1 day, 17:17:07", "remaining_time": "2:16:23"}
{"current_steps": 782, "total_steps": 824, "loss": 0.5335, "lr": 8.285850412726837e-08, "epoch": 3.7978108847674066, "percentage": 94.9, "elapsed_time": "1 day, 17:20:10", "remaining_time": "2:13:12"}
{"current_steps": 783, "total_steps": 824, "loss": 0.5584, "lr": 7.905950358584768e-08, "epoch": 3.802675585284281, "percentage": 95.02, "elapsed_time": "1 day, 17:22:54", "remaining_time": "2:10:00"}
{"current_steps": 784, "total_steps": 824, "loss": 0.5477, "lr": 7.534895568298395e-08, "epoch": 3.8075402858011556, "percentage": 95.15, "elapsed_time": "1 day, 17:25:27", "remaining_time": "2:06:48"}
{"current_steps": 785, "total_steps": 824, "loss": 0.5608, "lr": 7.172692711482022e-08, "epoch": 3.81240498631803, "percentage": 95.27, "elapsed_time": "1 day, 17:28:50", "remaining_time": "2:03:38"}
{"current_steps": 786, "total_steps": 824, "loss": 0.5624, "lr": 6.819348298638839e-08, "epoch": 3.817269686834904, "percentage": 95.39, "elapsed_time": "1 day, 17:31:12", "remaining_time": "2:00:26"}
{"current_steps": 787, "total_steps": 824, "loss": 0.5313, "lr": 6.474868681043578e-08, "epoch": 3.822134387351779, "percentage": 95.51, "elapsed_time": "1 day, 17:34:36", "remaining_time": "1:57:16"}
{"current_steps": 788, "total_steps": 824, "loss": 0.5241, "lr": 6.13926005062876e-08, "epoch": 3.826999087868653, "percentage": 95.63, "elapsed_time": "1 day, 17:37:39", "remaining_time": "1:54:06"}
{"current_steps": 789, "total_steps": 824, "loss": 0.5238, "lr": 5.8125284398730666e-08, "epoch": 3.8318637883855278, "percentage": 95.75, "elapsed_time": "1 day, 17:40:42", "remaining_time": "1:50:55"}
{"current_steps": 790, "total_steps": 824, "loss": 0.5493, "lr": 5.4946797216931524e-08, "epoch": 3.836728488902402, "percentage": 95.87, "elapsed_time": "1 day, 17:43:37", "remaining_time": "1:47:45"}
{"current_steps": 791, "total_steps": 824, "loss": 0.525, "lr": 5.185719609337836e-08, "epoch": 3.8415931894192763, "percentage": 96.0, "elapsed_time": "1 day, 17:47:08", "remaining_time": "1:44:35"}
{"current_steps": 792, "total_steps": 824, "loss": 0.5322, "lr": 4.885653656285627e-08, "epoch": 3.8464578899361506, "percentage": 96.12, "elapsed_time": "1 day, 17:49:43", "remaining_time": "1:41:24"}
{"current_steps": 793, "total_steps": 824, "loss": 0.5648, "lr": 4.5944872561448084e-08, "epoch": 3.8513225904530253, "percentage": 96.24, "elapsed_time": "1 day, 17:52:36", "remaining_time": "1:38:13"}
{"current_steps": 794, "total_steps": 824, "loss": 0.543, "lr": 4.3122256425563444e-08, "epoch": 3.8561872909698995, "percentage": 96.36, "elapsed_time": "1 day, 17:55:50", "remaining_time": "1:35:03"}
{"current_steps": 795, "total_steps": 824, "loss": 0.5556, "lr": 4.038873889100237e-08, "epoch": 3.8610519914867742, "percentage": 96.48, "elapsed_time": "1 day, 17:58:55", "remaining_time": "1:31:53"}
{"current_steps": 796, "total_steps": 824, "loss": 0.5717, "lr": 3.77443690920376e-08, "epoch": 3.8659166920036485, "percentage": 96.6, "elapsed_time": "1 day, 18:01:46", "remaining_time": "1:28:42"}
{"current_steps": 797, "total_steps": 824, "loss": 0.5387, "lr": 3.518919456053649e-08, "epoch": 3.870781392520523, "percentage": 96.72, "elapsed_time": "1 day, 18:05:14", "remaining_time": "1:25:32"}
{"current_steps": 798, "total_steps": 824, "loss": 0.5498, "lr": 3.2723261225102164e-08, "epoch": 3.8756460930373975, "percentage": 96.84, "elapsed_time": "1 day, 18:08:07", "remaining_time": "1:22:22"}
{"current_steps": 799, "total_steps": 824, "loss": 0.5393, "lr": 3.034661341025258e-08, "epoch": 3.8805107935542718, "percentage": 96.97, "elapsed_time": "1 day, 18:11:07", "remaining_time": "1:19:11"}
{"current_steps": 800, "total_steps": 824, "loss": 0.5367, "lr": 2.8059293835620006e-08, "epoch": 3.8853754940711465, "percentage": 97.09, "elapsed_time": "1 day, 18:14:17", "remaining_time": "1:16:01"}
{"current_steps": 801, "total_steps": 824, "loss": 0.5483, "lr": 2.5861343615184997e-08, "epoch": 3.8902401945880207, "percentage": 97.21, "elapsed_time": "1 day, 18:17:10", "remaining_time": "1:12:51"}
{"current_steps": 802, "total_steps": 824, "loss": 0.5509, "lr": 2.3752802256536423e-08, "epoch": 3.895104895104895, "percentage": 97.33, "elapsed_time": "1 day, 18:20:35", "remaining_time": "1:09:41"}
{"current_steps": 803, "total_steps": 824, "loss": 0.5244, "lr": 2.173370766016314e-08, "epoch": 3.8999695956217693, "percentage": 97.45, "elapsed_time": "1 day, 18:23:22", "remaining_time": "1:06:30"}
{"current_steps": 804, "total_steps": 824, "loss": 0.5252, "lr": 1.98040961187701e-08, "epoch": 3.904834296138644, "percentage": 97.57, "elapsed_time": "1 day, 18:26:57", "remaining_time": "1:03:21"}
{"current_steps": 805, "total_steps": 824, "loss": 0.5454, "lr": 1.7964002316628316e-08, "epoch": 3.9096989966555182, "percentage": 97.69, "elapsed_time": "1 day, 18:29:56", "remaining_time": "1:00:11"}
{"current_steps": 806, "total_steps": 824, "loss": 0.565, "lr": 1.6213459328950355e-08, "epoch": 3.914563697172393, "percentage": 97.82, "elapsed_time": "1 day, 18:33:07", "remaining_time": "0:57:01"}
{"current_steps": 807, "total_steps": 824, "loss": 0.5233, "lr": 1.4552498621295264e-08, "epoch": 3.919428397689267, "percentage": 97.94, "elapsed_time": "1 day, 18:36:44", "remaining_time": "0:53:51"}
{"current_steps": 808, "total_steps": 824, "loss": 0.5337, "lr": 1.2981150049004021e-08, "epoch": 3.9242930982061415, "percentage": 98.06, "elapsed_time": "1 day, 18:40:40", "remaining_time": "0:50:42"}
{"current_steps": 809, "total_steps": 824, "loss": 0.5578, "lr": 1.1499441856663296e-08, "epoch": 3.929157798723016, "percentage": 98.18, "elapsed_time": "1 day, 18:44:29", "remaining_time": "0:47:32"}
{"current_steps": 810, "total_steps": 824, "loss": 0.5639, "lr": 1.0107400677596413e-08, "epoch": 3.9340224992398904, "percentage": 98.3, "elapsed_time": "1 day, 18:47:27", "remaining_time": "0:44:22"}
{"current_steps": 811, "total_steps": 824, "loss": 0.5397, "lr": 8.805051533384846e-09, "epoch": 3.938887199756765, "percentage": 98.42, "elapsed_time": "1 day, 18:51:27", "remaining_time": "0:41:13"}
{"current_steps": 812, "total_steps": 824, "loss": 0.5365, "lr": 7.59241783341913e-09, "epoch": 3.9437519002736394, "percentage": 98.54, "elapsed_time": "1 day, 18:54:40", "remaining_time": "0:38:02"}
{"current_steps": 813, "total_steps": 824, "loss": 0.5353, "lr": 6.469521374477539e-09, "epoch": 3.9486166007905137, "percentage": 98.67, "elapsed_time": "1 day, 18:57:41", "remaining_time": "0:34:52"}
{"current_steps": 814, "total_steps": 824, "loss": 0.5441, "lr": 5.436382340335833e-09, "epoch": 3.9534813013073884, "percentage": 98.79, "elapsed_time": "1 day, 19:00:35", "remaining_time": "0:31:42"}
{"current_steps": 815, "total_steps": 824, "loss": 0.5262, "lr": 4.493019301401447e-09, "epoch": 3.9583460018242627, "percentage": 98.91, "elapsed_time": "1 day, 19:04:21", "remaining_time": "0:28:32"}
{"current_steps": 816, "total_steps": 824, "loss": 0.5425, "lr": 3.6394492143820847e-09, "epoch": 3.9632107023411374, "percentage": 99.03, "elapsed_time": "1 day, 19:07:27", "remaining_time": "0:25:22"}
{"current_steps": 817, "total_steps": 824, "loss": 0.5457, "lr": 2.875687421980966e-09, "epoch": 3.9680754028580116, "percentage": 99.15, "elapsed_time": "1 day, 19:10:56", "remaining_time": "0:22:11"}
{"current_steps": 818, "total_steps": 824, "loss": 0.5411, "lr": 2.201747652618713e-09, "epoch": 3.972940103374886, "percentage": 99.27, "elapsed_time": "1 day, 19:13:49", "remaining_time": "0:19:01"}
{"current_steps": 819, "total_steps": 824, "loss": 0.5469, "lr": 1.6176420201902132e-09, "epoch": 3.97780480389176, "percentage": 99.39, "elapsed_time": "1 day, 19:16:10", "remaining_time": "0:15:50"}
{"current_steps": 820, "total_steps": 824, "loss": 0.5498, "lr": 1.1233810238425735e-09, "epoch": 3.982669504408635, "percentage": 99.51, "elapsed_time": "1 day, 19:18:54", "remaining_time": "0:12:40"}
{"current_steps": 821, "total_steps": 824, "loss": 0.5326, "lr": 7.189735477913795e-10, "epoch": 3.987534204925509, "percentage": 99.64, "elapsed_time": "1 day, 19:22:43", "remaining_time": "0:09:30"}
{"current_steps": 822, "total_steps": 824, "loss": 0.5297, "lr": 4.0442686115582665e-10, "epoch": 3.992398905442384, "percentage": 99.76, "elapsed_time": "1 day, 19:25:52", "remaining_time": "0:06:20"}
{"current_steps": 823, "total_steps": 824, "loss": 0.5398, "lr": 1.797466178327101e-10, "epoch": 3.997263605959258, "percentage": 99.88, "elapsed_time": "1 day, 19:29:07", "remaining_time": "0:03:10"}
{"current_steps": 824, "total_steps": 824, "loss": 0.5195, "lr": 4.4936856390398465e-11, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "1 day, 19:31:01", "remaining_time": "0:00:00"}
{"current_steps": 824, "total_steps": 824, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "1 day, 19:31:56", "remaining_time": "0:00:00"}

5811
trainer_state.json Normal file

File diff suppressed because it is too large Load Diff

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2cda2f3920139b01bc3cb68c8e7369a53b87e75e32105354012dc3c65a92a697
size 7672

BIN
training_loss.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 42 KiB

1
vocab.json Normal file

File diff suppressed because one or more lines are too long