初始化项目,由ModelHub XC社区提供模型

Model: laion/exp_tas_timeout_multiplier_8_0_traces
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-19 23:06:55 +08:00
commit 2a077fe060
23 changed files with 163475 additions and 0 deletions

36
.gitattributes vendored Normal file
View File

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

61
README.md Normal file
View File

@@ -0,0 +1,61 @@
---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3-8B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: exp_tas_timeout_multiplier_8_0_traces
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# exp_tas_timeout_multiplier_8_0_traces
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the DCAgent/exp_tas_timeout_multiplier_8.0_traces dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 4e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 7.0
### Training results
### Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu128
- Datasets 4.4.1
- Tokenizers 0.22.2

28
added_tokens.json Normal file
View File

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

16
all_results.json Normal file
View File

@@ -0,0 +1,16 @@
{
"achieved_tflops_per_gpu": 3.9026639361996787,
"achieved_tflops_per_gpu_theoretical": 470.9187342324204,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.35643327236175537,
"mfu_percent": 0.39460707140542756,
"mfu_percent_theoretical": 47.615645524006105,
"total_flos": 1.0328415967578685e+18,
"train_loss": 0.4849937954541771,
"train_runtime": 33081.3008,
"train_samples_per_second": 2.216,
"train_steps_per_second": 0.139,
"valid_targets_mean": 2517.8,
"valid_targets_min": 562
}

89
chat_template.jinja Normal file
View File

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

68
config.json Normal file
View File

@@ -0,0 +1,68 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 36,
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "4.57.3",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

12
generation_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "4.57.3"
}

151388
merges.txt Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:023e95edd44d1ed164693ba45e78539dc23a57823102c008dad3abf04a1ee48b
size 4902257696

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2d1ee2e99f28f83c86f6d3583ec36ddd2c6914db4db770855d1f6326429b722d
size 4915960368

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fa28879d88b8c1054fac88344770d0cc7813450a87ac7b437ea407ecba452f6c
size 4983068496

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ffac46826ba4c9aa3b18141e679b855fdc5a769463d953fd2fe3ef2cb02bf0b6
size 1580230264

View File

@@ -0,0 +1,407 @@
{
"metadata": {
"total_parameters": 308224,
"total_size": 16381470720
},
"weight_map": {
"lm_head.weight": "model-00004-of-00004.safetensors",
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.norm.weight": "model-00004-of-00004.safetensors"
}
}

12
run_summary.json Normal file
View File

@@ -0,0 +1,12 @@
{
"agent_name": "terminus-2",
"training_start": null,
"training_end": null,
"created_by": "DCAgent",
"base_model_name": "Qwen/Qwen3-8B",
"dataset_name": "DCAgent/exp_tas_timeout_multiplier_8.0_traces",
"training_type": "SFT",
"training_parameters": "https://huggingface.co/laion/exp_tas_timeout_multiplier_8_0_traces/blob/main/config.json",
"wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/sft_exp_tas_timeout_multiplier_8-0_traces_Qwen3-8B",
"traces_location_s3": null
}

31
special_tokens_map.json Normal file
View File

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

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

Binary file not shown.

240
tokenizer_config.json Normal file
View File

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

16
train_results.json Normal file
View File

@@ -0,0 +1,16 @@
{
"achieved_tflops_per_gpu": 3.9026639361996787,
"achieved_tflops_per_gpu_theoretical": 470.9187342324204,
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.35643327236175537,
"mfu_percent": 0.39460707140542756,
"mfu_percent_theoretical": 47.615645524006105,
"total_flos": 1.0328415967578685e+18,
"train_loss": 0.4849937954541771,
"train_runtime": 33081.3008,
"train_samples_per_second": 2.216,
"train_steps_per_second": 0.139,
"valid_targets_mean": 2517.8,
"valid_targets_min": 562
}

918
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,918 @@
{"current_steps": 5, "total_steps": 4585, "loss": 0.9853, "lr": 3.4858387799564276e-07, "epoch": 0.007639419404125287, "percentage": 0.11, "elapsed_time": "0:00:44", "remaining_time": "11:24:04"}
{"current_steps": 10, "total_steps": 4585, "loss": 1.0071, "lr": 7.843137254901962e-07, "epoch": 0.015278838808250574, "percentage": 0.22, "elapsed_time": "0:01:22", "remaining_time": "10:27:05"}
{"current_steps": 15, "total_steps": 4585, "loss": 1.0029, "lr": 1.2200435729847495e-06, "epoch": 0.02291825821237586, "percentage": 0.33, "elapsed_time": "0:02:10", "remaining_time": "11:03:19"}
{"current_steps": 20, "total_steps": 4585, "loss": 0.959, "lr": 1.655773420479303e-06, "epoch": 0.030557677616501147, "percentage": 0.44, "elapsed_time": "0:02:49", "remaining_time": "10:45:58"}
{"current_steps": 25, "total_steps": 4585, "loss": 0.9939, "lr": 2.0915032679738565e-06, "epoch": 0.03819709702062643, "percentage": 0.55, "elapsed_time": "0:03:21", "remaining_time": "10:12:30"}
{"current_steps": 30, "total_steps": 4585, "loss": 0.922, "lr": 2.5272331154684097e-06, "epoch": 0.04583651642475172, "percentage": 0.65, "elapsed_time": "0:03:55", "remaining_time": "9:56:46"}
{"current_steps": 35, "total_steps": 4585, "loss": 0.9547, "lr": 2.962962962962963e-06, "epoch": 0.053475935828877004, "percentage": 0.76, "elapsed_time": "0:04:36", "remaining_time": "9:58:29"}
{"current_steps": 40, "total_steps": 4585, "loss": 0.8596, "lr": 3.398692810457517e-06, "epoch": 0.061115355233002294, "percentage": 0.87, "elapsed_time": "0:05:14", "remaining_time": "9:55:41"}
{"current_steps": 45, "total_steps": 4585, "loss": 0.8571, "lr": 3.83442265795207e-06, "epoch": 0.06875477463712758, "percentage": 0.98, "elapsed_time": "0:05:51", "remaining_time": "9:51:25"}
{"current_steps": 50, "total_steps": 4585, "loss": 0.8804, "lr": 4.270152505446624e-06, "epoch": 0.07639419404125286, "percentage": 1.09, "elapsed_time": "0:06:26", "remaining_time": "9:44:55"}
{"current_steps": 55, "total_steps": 4585, "loss": 0.8181, "lr": 4.705882352941177e-06, "epoch": 0.08403361344537816, "percentage": 1.2, "elapsed_time": "0:06:58", "remaining_time": "9:35:06"}
{"current_steps": 60, "total_steps": 4585, "loss": 0.8229, "lr": 5.14161220043573e-06, "epoch": 0.09167303284950344, "percentage": 1.31, "elapsed_time": "0:07:39", "remaining_time": "9:37:14"}
{"current_steps": 65, "total_steps": 4585, "loss": 0.7262, "lr": 5.577342047930284e-06, "epoch": 0.09931245225362872, "percentage": 1.42, "elapsed_time": "0:08:22", "remaining_time": "9:42:00"}
{"current_steps": 70, "total_steps": 4585, "loss": 0.8129, "lr": 6.0130718954248365e-06, "epoch": 0.10695187165775401, "percentage": 1.53, "elapsed_time": "0:09:03", "remaining_time": "9:44:29"}
{"current_steps": 75, "total_steps": 4585, "loss": 0.7625, "lr": 6.4488017429193905e-06, "epoch": 0.11459129106187929, "percentage": 1.64, "elapsed_time": "0:09:46", "remaining_time": "9:47:39"}
{"current_steps": 80, "total_steps": 4585, "loss": 0.7621, "lr": 6.8845315904139445e-06, "epoch": 0.12223071046600459, "percentage": 1.74, "elapsed_time": "0:10:26", "remaining_time": "9:48:15"}
{"current_steps": 85, "total_steps": 4585, "loss": 0.7235, "lr": 7.320261437908497e-06, "epoch": 0.12987012987012986, "percentage": 1.85, "elapsed_time": "0:11:05", "remaining_time": "9:47:21"}
{"current_steps": 90, "total_steps": 4585, "loss": 0.7184, "lr": 7.755991285403051e-06, "epoch": 0.13750954927425516, "percentage": 1.96, "elapsed_time": "0:11:50", "remaining_time": "9:51:44"}
{"current_steps": 95, "total_steps": 4585, "loss": 0.714, "lr": 8.191721132897605e-06, "epoch": 0.14514896867838045, "percentage": 2.07, "elapsed_time": "0:12:32", "remaining_time": "9:52:58"}
{"current_steps": 100, "total_steps": 4585, "loss": 0.7336, "lr": 8.627450980392157e-06, "epoch": 0.15278838808250572, "percentage": 2.18, "elapsed_time": "0:13:04", "remaining_time": "9:46:39"}
{"current_steps": 105, "total_steps": 4585, "loss": 0.6585, "lr": 9.063180827886711e-06, "epoch": 0.16042780748663102, "percentage": 2.29, "elapsed_time": "0:13:30", "remaining_time": "9:36:33"}
{"current_steps": 110, "total_steps": 4585, "loss": 0.7021, "lr": 9.498910675381264e-06, "epoch": 0.16806722689075632, "percentage": 2.4, "elapsed_time": "0:14:03", "remaining_time": "9:31:54"}
{"current_steps": 115, "total_steps": 4585, "loss": 0.6992, "lr": 9.934640522875818e-06, "epoch": 0.17570664629488159, "percentage": 2.51, "elapsed_time": "0:14:34", "remaining_time": "9:26:21"}
{"current_steps": 120, "total_steps": 4585, "loss": 0.7356, "lr": 1.037037037037037e-05, "epoch": 0.18334606569900688, "percentage": 2.62, "elapsed_time": "0:15:08", "remaining_time": "9:23:18"}
{"current_steps": 125, "total_steps": 4585, "loss": 0.6595, "lr": 1.0806100217864926e-05, "epoch": 0.19098548510313215, "percentage": 2.73, "elapsed_time": "0:15:50", "remaining_time": "9:25:04"}
{"current_steps": 130, "total_steps": 4585, "loss": 0.698, "lr": 1.1241830065359478e-05, "epoch": 0.19862490450725745, "percentage": 2.84, "elapsed_time": "0:16:36", "remaining_time": "9:28:58"}
{"current_steps": 135, "total_steps": 4585, "loss": 0.6742, "lr": 1.167755991285403e-05, "epoch": 0.20626432391138275, "percentage": 2.94, "elapsed_time": "0:17:13", "remaining_time": "9:27:37"}
{"current_steps": 140, "total_steps": 4585, "loss": 0.6659, "lr": 1.2113289760348586e-05, "epoch": 0.21390374331550802, "percentage": 3.05, "elapsed_time": "0:17:56", "remaining_time": "9:29:43"}
{"current_steps": 145, "total_steps": 4585, "loss": 0.6921, "lr": 1.2549019607843138e-05, "epoch": 0.2215431627196333, "percentage": 3.16, "elapsed_time": "0:18:38", "remaining_time": "9:30:36"}
{"current_steps": 150, "total_steps": 4585, "loss": 0.6682, "lr": 1.298474945533769e-05, "epoch": 0.22918258212375858, "percentage": 3.27, "elapsed_time": "0:19:12", "remaining_time": "9:27:44"}
{"current_steps": 155, "total_steps": 4585, "loss": 0.6625, "lr": 1.3420479302832245e-05, "epoch": 0.23682200152788388, "percentage": 3.38, "elapsed_time": "0:19:47", "remaining_time": "9:25:32"}
{"current_steps": 160, "total_steps": 4585, "loss": 0.6769, "lr": 1.3856209150326799e-05, "epoch": 0.24446142093200918, "percentage": 3.49, "elapsed_time": "0:20:34", "remaining_time": "9:29:07"}
{"current_steps": 165, "total_steps": 4585, "loss": 0.6664, "lr": 1.4291938997821353e-05, "epoch": 0.25210084033613445, "percentage": 3.6, "elapsed_time": "0:21:14", "remaining_time": "9:29:07"}
{"current_steps": 170, "total_steps": 4585, "loss": 0.635, "lr": 1.4727668845315905e-05, "epoch": 0.2597402597402597, "percentage": 3.71, "elapsed_time": "0:21:54", "remaining_time": "9:28:45"}
{"current_steps": 175, "total_steps": 4585, "loss": 0.6856, "lr": 1.5163398692810458e-05, "epoch": 0.26737967914438504, "percentage": 3.82, "elapsed_time": "0:22:29", "remaining_time": "9:26:35"}
{"current_steps": 180, "total_steps": 4585, "loss": 0.6345, "lr": 1.559912854030501e-05, "epoch": 0.2750190985485103, "percentage": 3.93, "elapsed_time": "0:23:15", "remaining_time": "9:29:22"}
{"current_steps": 185, "total_steps": 4585, "loss": 0.6095, "lr": 1.6034858387799567e-05, "epoch": 0.2826585179526356, "percentage": 4.03, "elapsed_time": "0:23:55", "remaining_time": "9:28:51"}
{"current_steps": 190, "total_steps": 4585, "loss": 0.6729, "lr": 1.647058823529412e-05, "epoch": 0.2902979373567609, "percentage": 4.14, "elapsed_time": "0:24:38", "remaining_time": "9:30:00"}
{"current_steps": 195, "total_steps": 4585, "loss": 0.6387, "lr": 1.6906318082788672e-05, "epoch": 0.2979373567608862, "percentage": 4.25, "elapsed_time": "0:25:12", "remaining_time": "9:27:37"}
{"current_steps": 200, "total_steps": 4585, "loss": 0.631, "lr": 1.7342047930283224e-05, "epoch": 0.30557677616501144, "percentage": 4.36, "elapsed_time": "0:25:54", "remaining_time": "9:27:56"}
{"current_steps": 205, "total_steps": 4585, "loss": 0.6251, "lr": 1.7777777777777777e-05, "epoch": 0.31321619556913677, "percentage": 4.47, "elapsed_time": "0:26:35", "remaining_time": "9:28:01"}
{"current_steps": 210, "total_steps": 4585, "loss": 0.6464, "lr": 1.8213507625272332e-05, "epoch": 0.32085561497326204, "percentage": 4.58, "elapsed_time": "0:27:17", "remaining_time": "9:28:29"}
{"current_steps": 215, "total_steps": 4585, "loss": 0.6271, "lr": 1.8649237472766885e-05, "epoch": 0.3284950343773873, "percentage": 4.69, "elapsed_time": "0:27:53", "remaining_time": "9:26:56"}
{"current_steps": 220, "total_steps": 4585, "loss": 0.6122, "lr": 1.908496732026144e-05, "epoch": 0.33613445378151263, "percentage": 4.8, "elapsed_time": "0:28:24", "remaining_time": "9:23:43"}
{"current_steps": 225, "total_steps": 4585, "loss": 0.6125, "lr": 1.9520697167755993e-05, "epoch": 0.3437738731856379, "percentage": 4.91, "elapsed_time": "0:28:56", "remaining_time": "9:20:54"}
{"current_steps": 230, "total_steps": 4585, "loss": 0.6279, "lr": 1.9956427015250545e-05, "epoch": 0.35141329258976317, "percentage": 5.02, "elapsed_time": "0:29:36", "remaining_time": "9:20:37"}
{"current_steps": 235, "total_steps": 4585, "loss": 0.6654, "lr": 2.0392156862745097e-05, "epoch": 0.35905271199388844, "percentage": 5.13, "elapsed_time": "0:30:13", "remaining_time": "9:19:21"}
{"current_steps": 240, "total_steps": 4585, "loss": 0.6017, "lr": 2.0827886710239653e-05, "epoch": 0.36669213139801377, "percentage": 5.23, "elapsed_time": "0:30:48", "remaining_time": "9:17:52"}
{"current_steps": 245, "total_steps": 4585, "loss": 0.6515, "lr": 2.126361655773421e-05, "epoch": 0.37433155080213903, "percentage": 5.34, "elapsed_time": "0:31:24", "remaining_time": "9:16:23"}
{"current_steps": 250, "total_steps": 4585, "loss": 0.6187, "lr": 2.1699346405228758e-05, "epoch": 0.3819709702062643, "percentage": 5.45, "elapsed_time": "0:32:02", "remaining_time": "9:15:41"}
{"current_steps": 255, "total_steps": 4585, "loss": 0.5786, "lr": 2.2135076252723313e-05, "epoch": 0.38961038961038963, "percentage": 5.56, "elapsed_time": "0:32:45", "remaining_time": "9:16:17"}
{"current_steps": 260, "total_steps": 4585, "loss": 0.6133, "lr": 2.257080610021787e-05, "epoch": 0.3972498090145149, "percentage": 5.67, "elapsed_time": "0:33:21", "remaining_time": "9:14:55"}
{"current_steps": 265, "total_steps": 4585, "loss": 0.6471, "lr": 2.3006535947712418e-05, "epoch": 0.40488922841864017, "percentage": 5.78, "elapsed_time": "0:34:02", "remaining_time": "9:15:03"}
{"current_steps": 270, "total_steps": 4585, "loss": 0.635, "lr": 2.3442265795206974e-05, "epoch": 0.4125286478227655, "percentage": 5.89, "elapsed_time": "0:34:33", "remaining_time": "9:12:19"}
{"current_steps": 275, "total_steps": 4585, "loss": 0.6027, "lr": 2.387799564270153e-05, "epoch": 0.42016806722689076, "percentage": 6.0, "elapsed_time": "0:35:14", "remaining_time": "9:12:17"}
{"current_steps": 280, "total_steps": 4585, "loss": 0.5793, "lr": 2.431372549019608e-05, "epoch": 0.42780748663101603, "percentage": 6.11, "elapsed_time": "0:35:54", "remaining_time": "9:12:05"}
{"current_steps": 285, "total_steps": 4585, "loss": 0.6192, "lr": 2.4749455337690634e-05, "epoch": 0.43544690603514136, "percentage": 6.22, "elapsed_time": "0:36:37", "remaining_time": "9:12:34"}
{"current_steps": 290, "total_steps": 4585, "loss": 0.628, "lr": 2.5185185185185187e-05, "epoch": 0.4430863254392666, "percentage": 6.32, "elapsed_time": "0:37:19", "remaining_time": "9:12:53"}
{"current_steps": 295, "total_steps": 4585, "loss": 0.6153, "lr": 2.562091503267974e-05, "epoch": 0.4507257448433919, "percentage": 6.43, "elapsed_time": "0:37:59", "remaining_time": "9:12:33"}
{"current_steps": 300, "total_steps": 4585, "loss": 0.6203, "lr": 2.6056644880174295e-05, "epoch": 0.45836516424751717, "percentage": 6.54, "elapsed_time": "0:38:30", "remaining_time": "9:09:56"}
{"current_steps": 305, "total_steps": 4585, "loss": 0.6258, "lr": 2.6492374727668847e-05, "epoch": 0.4660045836516425, "percentage": 6.65, "elapsed_time": "0:39:03", "remaining_time": "9:08:02"}
{"current_steps": 310, "total_steps": 4585, "loss": 0.6027, "lr": 2.6928104575163403e-05, "epoch": 0.47364400305576776, "percentage": 6.76, "elapsed_time": "0:39:39", "remaining_time": "9:06:50"}
{"current_steps": 315, "total_steps": 4585, "loss": 0.6064, "lr": 2.736383442265795e-05, "epoch": 0.48128342245989303, "percentage": 6.87, "elapsed_time": "0:40:06", "remaining_time": "9:03:39"}
{"current_steps": 320, "total_steps": 4585, "loss": 0.6047, "lr": 2.7799564270152507e-05, "epoch": 0.48892284186401835, "percentage": 6.98, "elapsed_time": "0:40:44", "remaining_time": "9:02:54"}
{"current_steps": 325, "total_steps": 4585, "loss": 0.6213, "lr": 2.8235294117647063e-05, "epoch": 0.4965622612681436, "percentage": 7.09, "elapsed_time": "0:41:20", "remaining_time": "9:01:50"}
{"current_steps": 330, "total_steps": 4585, "loss": 0.5847, "lr": 2.8671023965141612e-05, "epoch": 0.5042016806722689, "percentage": 7.2, "elapsed_time": "0:41:55", "remaining_time": "9:00:34"}
{"current_steps": 335, "total_steps": 4585, "loss": 0.6142, "lr": 2.9106753812636168e-05, "epoch": 0.5118411000763942, "percentage": 7.31, "elapsed_time": "0:42:33", "remaining_time": "8:59:52"}
{"current_steps": 340, "total_steps": 4585, "loss": 0.6064, "lr": 2.9542483660130724e-05, "epoch": 0.5194805194805194, "percentage": 7.42, "elapsed_time": "0:43:16", "remaining_time": "9:00:18"}
{"current_steps": 345, "total_steps": 4585, "loss": 0.5969, "lr": 2.9978213507625272e-05, "epoch": 0.5271199388846448, "percentage": 7.52, "elapsed_time": "0:44:00", "remaining_time": "9:00:56"}
{"current_steps": 350, "total_steps": 4585, "loss": 0.5802, "lr": 3.0413943355119828e-05, "epoch": 0.5347593582887701, "percentage": 7.63, "elapsed_time": "0:44:36", "remaining_time": "8:59:51"}
{"current_steps": 355, "total_steps": 4585, "loss": 0.6115, "lr": 3.0849673202614384e-05, "epoch": 0.5423987776928954, "percentage": 7.74, "elapsed_time": "0:45:12", "remaining_time": "8:58:46"}
{"current_steps": 360, "total_steps": 4585, "loss": 0.5981, "lr": 3.1285403050108936e-05, "epoch": 0.5500381970970206, "percentage": 7.85, "elapsed_time": "0:45:55", "remaining_time": "8:59:00"}
{"current_steps": 365, "total_steps": 4585, "loss": 0.5909, "lr": 3.172113289760349e-05, "epoch": 0.5576776165011459, "percentage": 7.96, "elapsed_time": "0:46:31", "remaining_time": "8:57:48"}
{"current_steps": 370, "total_steps": 4585, "loss": 0.5739, "lr": 3.215686274509804e-05, "epoch": 0.5653170359052712, "percentage": 8.07, "elapsed_time": "0:47:07", "remaining_time": "8:56:51"}
{"current_steps": 375, "total_steps": 4585, "loss": 0.5903, "lr": 3.259259259259259e-05, "epoch": 0.5729564553093965, "percentage": 8.18, "elapsed_time": "0:47:41", "remaining_time": "8:55:25"}
{"current_steps": 380, "total_steps": 4585, "loss": 0.5981, "lr": 3.3028322440087146e-05, "epoch": 0.5805958747135218, "percentage": 8.29, "elapsed_time": "0:48:10", "remaining_time": "8:53:09"}
{"current_steps": 385, "total_steps": 4585, "loss": 0.574, "lr": 3.3464052287581705e-05, "epoch": 0.5882352941176471, "percentage": 8.4, "elapsed_time": "0:48:48", "remaining_time": "8:52:27"}
{"current_steps": 390, "total_steps": 4585, "loss": 0.5929, "lr": 3.389978213507625e-05, "epoch": 0.5958747135217723, "percentage": 8.51, "elapsed_time": "0:49:28", "remaining_time": "8:52:15"}
{"current_steps": 395, "total_steps": 4585, "loss": 0.6145, "lr": 3.433551198257081e-05, "epoch": 0.6035141329258976, "percentage": 8.62, "elapsed_time": "0:50:02", "remaining_time": "8:50:51"}
{"current_steps": 400, "total_steps": 4585, "loss": 0.5987, "lr": 3.477124183006536e-05, "epoch": 0.6111535523300229, "percentage": 8.72, "elapsed_time": "0:50:33", "remaining_time": "8:49:00"}
{"current_steps": 405, "total_steps": 4585, "loss": 0.572, "lr": 3.5206971677559914e-05, "epoch": 0.6187929717341482, "percentage": 8.83, "elapsed_time": "0:51:12", "remaining_time": "8:48:31"}
{"current_steps": 410, "total_steps": 4585, "loss": 0.5668, "lr": 3.5642701525054466e-05, "epoch": 0.6264323911382735, "percentage": 8.94, "elapsed_time": "0:51:52", "remaining_time": "8:48:11"}
{"current_steps": 415, "total_steps": 4585, "loss": 0.6283, "lr": 3.6078431372549025e-05, "epoch": 0.6340718105423988, "percentage": 9.05, "elapsed_time": "0:52:25", "remaining_time": "8:46:47"}
{"current_steps": 420, "total_steps": 4585, "loss": 0.5964, "lr": 3.651416122004358e-05, "epoch": 0.6417112299465241, "percentage": 9.16, "elapsed_time": "0:52:57", "remaining_time": "8:45:10"}
{"current_steps": 425, "total_steps": 4585, "loss": 0.5885, "lr": 3.694989106753813e-05, "epoch": 0.6493506493506493, "percentage": 9.27, "elapsed_time": "0:53:36", "remaining_time": "8:44:46"}
{"current_steps": 430, "total_steps": 4585, "loss": 0.5811, "lr": 3.738562091503268e-05, "epoch": 0.6569900687547746, "percentage": 9.38, "elapsed_time": "0:54:10", "remaining_time": "8:43:28"}
{"current_steps": 435, "total_steps": 4585, "loss": 0.5774, "lr": 3.7821350762527235e-05, "epoch": 0.6646294881588999, "percentage": 9.49, "elapsed_time": "0:54:46", "remaining_time": "8:42:31"}
{"current_steps": 440, "total_steps": 4585, "loss": 0.5808, "lr": 3.825708061002179e-05, "epoch": 0.6722689075630253, "percentage": 9.6, "elapsed_time": "0:55:18", "remaining_time": "8:41:04"}
{"current_steps": 445, "total_steps": 4585, "loss": 0.5552, "lr": 3.8692810457516346e-05, "epoch": 0.6799083269671505, "percentage": 9.71, "elapsed_time": "0:56:01", "remaining_time": "8:41:11"}
{"current_steps": 450, "total_steps": 4585, "loss": 0.5729, "lr": 3.91285403050109e-05, "epoch": 0.6875477463712758, "percentage": 9.81, "elapsed_time": "0:56:43", "remaining_time": "8:41:14"}
{"current_steps": 455, "total_steps": 4585, "loss": 0.6083, "lr": 3.956427015250545e-05, "epoch": 0.6951871657754011, "percentage": 9.92, "elapsed_time": "0:57:26", "remaining_time": "8:41:20"}
{"current_steps": 460, "total_steps": 4585, "loss": 0.5937, "lr": 4e-05, "epoch": 0.7028265851795263, "percentage": 10.03, "elapsed_time": "0:58:08", "remaining_time": "8:41:20"}
{"current_steps": 465, "total_steps": 4585, "loss": 0.5958, "lr": 3.999985506249457e-05, "epoch": 0.7104660045836516, "percentage": 10.14, "elapsed_time": "0:58:50", "remaining_time": "8:41:24"}
{"current_steps": 470, "total_steps": 4585, "loss": 0.5721, "lr": 3.9999420252078994e-05, "epoch": 0.7181054239877769, "percentage": 10.25, "elapsed_time": "0:59:24", "remaining_time": "8:40:10"}
{"current_steps": 475, "total_steps": 4585, "loss": 0.5944, "lr": 3.9998695575055276e-05, "epoch": 0.7257448433919023, "percentage": 10.36, "elapsed_time": "0:59:59", "remaining_time": "8:39:06"}
{"current_steps": 480, "total_steps": 4585, "loss": 0.5551, "lr": 3.9997681041926714e-05, "epoch": 0.7333842627960275, "percentage": 10.47, "elapsed_time": "1:00:35", "remaining_time": "8:38:13"}
{"current_steps": 485, "total_steps": 4585, "loss": 0.5536, "lr": 3.99963766673977e-05, "epoch": 0.7410236822001528, "percentage": 10.58, "elapsed_time": "1:01:17", "remaining_time": "8:38:10"}
{"current_steps": 490, "total_steps": 4585, "loss": 0.5756, "lr": 3.999478247037352e-05, "epoch": 0.7486631016042781, "percentage": 10.69, "elapsed_time": "1:02:07", "remaining_time": "8:39:13"}
{"current_steps": 495, "total_steps": 4585, "loss": 0.6146, "lr": 3.999289847396006e-05, "epoch": 0.7563025210084033, "percentage": 10.8, "elapsed_time": "1:02:43", "remaining_time": "8:38:19"}
{"current_steps": 500, "total_steps": 4585, "loss": 0.5805, "lr": 3.9990724705463495e-05, "epoch": 0.7639419404125286, "percentage": 10.91, "elapsed_time": "1:03:12", "remaining_time": "8:36:23"}
{"current_steps": 505, "total_steps": 4585, "loss": 0.5759, "lr": 3.998826119638989e-05, "epoch": 0.771581359816654, "percentage": 11.01, "elapsed_time": "1:03:51", "remaining_time": "8:35:53"}
{"current_steps": 510, "total_steps": 4585, "loss": 0.5894, "lr": 3.998550798244472e-05, "epoch": 0.7792207792207793, "percentage": 11.12, "elapsed_time": "1:04:26", "remaining_time": "8:34:55"}
{"current_steps": 515, "total_steps": 4585, "loss": 0.5479, "lr": 3.9982465103532386e-05, "epoch": 0.7868601986249045, "percentage": 11.23, "elapsed_time": "1:04:59", "remaining_time": "8:33:39"}
{"current_steps": 520, "total_steps": 4585, "loss": 0.5928, "lr": 3.997913260375562e-05, "epoch": 0.7944996180290298, "percentage": 11.34, "elapsed_time": "1:05:34", "remaining_time": "8:32:38"}
{"current_steps": 525, "total_steps": 4585, "loss": 0.5838, "lr": 3.9975510531414835e-05, "epoch": 0.8021390374331551, "percentage": 11.45, "elapsed_time": "1:06:11", "remaining_time": "8:31:50"}
{"current_steps": 530, "total_steps": 4585, "loss": 0.5411, "lr": 3.997159893900745e-05, "epoch": 0.8097784568372803, "percentage": 11.56, "elapsed_time": "1:06:51", "remaining_time": "8:31:28"}
{"current_steps": 535, "total_steps": 4585, "loss": 0.5935, "lr": 3.9967397883227104e-05, "epoch": 0.8174178762414056, "percentage": 11.67, "elapsed_time": "1:07:19", "remaining_time": "8:29:40"}
{"current_steps": 540, "total_steps": 4585, "loss": 0.5777, "lr": 3.9962907424962856e-05, "epoch": 0.825057295645531, "percentage": 11.78, "elapsed_time": "1:07:55", "remaining_time": "8:28:51"}
{"current_steps": 545, "total_steps": 4585, "loss": 0.6051, "lr": 3.995812762929829e-05, "epoch": 0.8326967150496563, "percentage": 11.89, "elapsed_time": "1:08:37", "remaining_time": "8:28:45"}
{"current_steps": 550, "total_steps": 4585, "loss": 0.5861, "lr": 3.995305856551057e-05, "epoch": 0.8403361344537815, "percentage": 12.0, "elapsed_time": "1:09:12", "remaining_time": "8:27:41"}
{"current_steps": 555, "total_steps": 4585, "loss": 0.5494, "lr": 3.994770030706944e-05, "epoch": 0.8479755538579068, "percentage": 12.1, "elapsed_time": "1:09:49", "remaining_time": "8:27:02"}
{"current_steps": 560, "total_steps": 4585, "loss": 0.5937, "lr": 3.994205293163616e-05, "epoch": 0.8556149732620321, "percentage": 12.21, "elapsed_time": "1:10:24", "remaining_time": "8:26:00"}
{"current_steps": 565, "total_steps": 4585, "loss": 0.5482, "lr": 3.9936116521062376e-05, "epoch": 0.8632543926661573, "percentage": 12.32, "elapsed_time": "1:11:01", "remaining_time": "8:25:19"}
{"current_steps": 570, "total_steps": 4585, "loss": 0.5766, "lr": 3.992989116138895e-05, "epoch": 0.8708938120702827, "percentage": 12.43, "elapsed_time": "1:11:47", "remaining_time": "8:25:39"}
{"current_steps": 575, "total_steps": 4585, "loss": 0.5918, "lr": 3.99233769428447e-05, "epoch": 0.878533231474408, "percentage": 12.54, "elapsed_time": "1:12:17", "remaining_time": "8:24:12"}
{"current_steps": 580, "total_steps": 4585, "loss": 0.5691, "lr": 3.991657395984507e-05, "epoch": 0.8861726508785333, "percentage": 12.65, "elapsed_time": "1:12:46", "remaining_time": "8:22:30"}
{"current_steps": 585, "total_steps": 4585, "loss": 0.602, "lr": 3.99094823109908e-05, "epoch": 0.8938120702826585, "percentage": 12.76, "elapsed_time": "1:13:17", "remaining_time": "8:21:10"}
{"current_steps": 590, "total_steps": 4585, "loss": 0.5667, "lr": 3.990210209906649e-05, "epoch": 0.9014514896867838, "percentage": 12.87, "elapsed_time": "1:13:56", "remaining_time": "8:20:42"}
{"current_steps": 595, "total_steps": 4585, "loss": 0.5745, "lr": 3.989443343103908e-05, "epoch": 0.9090909090909091, "percentage": 12.98, "elapsed_time": "1:14:38", "remaining_time": "8:20:30"}
{"current_steps": 600, "total_steps": 4585, "loss": 0.5671, "lr": 3.9886476418056336e-05, "epoch": 0.9167303284950343, "percentage": 13.09, "elapsed_time": "1:15:21", "remaining_time": "8:20:30"}
{"current_steps": 605, "total_steps": 4585, "loss": 0.5372, "lr": 3.987823117544522e-05, "epoch": 0.9243697478991597, "percentage": 13.2, "elapsed_time": "1:15:55", "remaining_time": "8:19:25"}
{"current_steps": 610, "total_steps": 4585, "loss": 0.5665, "lr": 3.986969782271022e-05, "epoch": 0.932009167303285, "percentage": 13.3, "elapsed_time": "1:16:30", "remaining_time": "8:18:32"}
{"current_steps": 615, "total_steps": 4585, "loss": 0.6083, "lr": 3.986087648353162e-05, "epoch": 0.9396485867074102, "percentage": 13.41, "elapsed_time": "1:17:02", "remaining_time": "8:17:16"}
{"current_steps": 620, "total_steps": 4585, "loss": 0.5559, "lr": 3.985176728576371e-05, "epoch": 0.9472880061115355, "percentage": 13.52, "elapsed_time": "1:17:50", "remaining_time": "8:17:47"}
{"current_steps": 625, "total_steps": 4585, "loss": 0.5598, "lr": 3.984237036143293e-05, "epoch": 0.9549274255156608, "percentage": 13.63, "elapsed_time": "1:18:22", "remaining_time": "8:16:34"}
{"current_steps": 630, "total_steps": 4585, "loss": 0.5471, "lr": 3.9832685846735965e-05, "epoch": 0.9625668449197861, "percentage": 13.74, "elapsed_time": "1:19:07", "remaining_time": "8:16:44"}
{"current_steps": 635, "total_steps": 4585, "loss": 0.601, "lr": 3.982271388203775e-05, "epoch": 0.9702062643239114, "percentage": 13.85, "elapsed_time": "1:19:40", "remaining_time": "8:15:35"}
{"current_steps": 640, "total_steps": 4585, "loss": 0.5831, "lr": 3.981245461186945e-05, "epoch": 0.9778456837280367, "percentage": 13.96, "elapsed_time": "1:20:12", "remaining_time": "8:14:22"}
{"current_steps": 645, "total_steps": 4585, "loss": 0.563, "lr": 3.980190818492637e-05, "epoch": 0.985485103132162, "percentage": 14.07, "elapsed_time": "1:20:53", "remaining_time": "8:14:06"}
{"current_steps": 650, "total_steps": 4585, "loss": 0.6126, "lr": 3.979107475406579e-05, "epoch": 0.9931245225362872, "percentage": 14.18, "elapsed_time": "1:21:28", "remaining_time": "8:13:13"}
{"current_steps": 655, "total_steps": 4585, "loss": 0.5592, "lr": 3.977995447630475e-05, "epoch": 1.0, "percentage": 14.29, "elapsed_time": "1:21:56", "remaining_time": "8:11:38"}
{"current_steps": 660, "total_steps": 4585, "loss": 0.5855, "lr": 3.9768547512817794e-05, "epoch": 1.0076394194041254, "percentage": 14.39, "elapsed_time": "1:22:33", "remaining_time": "8:10:55"}
{"current_steps": 665, "total_steps": 4585, "loss": 0.5707, "lr": 3.9756854028934604e-05, "epoch": 1.0152788388082505, "percentage": 14.5, "elapsed_time": "1:23:13", "remaining_time": "8:10:35"}
{"current_steps": 670, "total_steps": 4585, "loss": 0.5371, "lr": 3.974487419413761e-05, "epoch": 1.022918258212376, "percentage": 14.61, "elapsed_time": "1:23:50", "remaining_time": "8:09:52"}
{"current_steps": 675, "total_steps": 4585, "loss": 0.5463, "lr": 3.973260818205955e-05, "epoch": 1.030557677616501, "percentage": 14.72, "elapsed_time": "1:24:25", "remaining_time": "8:09:04"}
{"current_steps": 680, "total_steps": 4585, "loss": 0.5226, "lr": 3.972005617048094e-05, "epoch": 1.0381970970206265, "percentage": 14.83, "elapsed_time": "1:25:03", "remaining_time": "8:08:28"}
{"current_steps": 685, "total_steps": 4585, "loss": 0.5186, "lr": 3.970721834132751e-05, "epoch": 1.0458365164247516, "percentage": 14.94, "elapsed_time": "1:25:30", "remaining_time": "8:06:51"}
{"current_steps": 690, "total_steps": 4585, "loss": 0.5645, "lr": 3.969409488066756e-05, "epoch": 1.053475935828877, "percentage": 15.05, "elapsed_time": "1:26:05", "remaining_time": "8:06:01"}
{"current_steps": 695, "total_steps": 4585, "loss": 0.5285, "lr": 3.9680685978709254e-05, "epoch": 1.0611153552330024, "percentage": 15.16, "elapsed_time": "1:26:39", "remaining_time": "8:05:01"}
{"current_steps": 700, "total_steps": 4585, "loss": 0.5529, "lr": 3.966699182979785e-05, "epoch": 1.0687547746371275, "percentage": 15.27, "elapsed_time": "1:27:16", "remaining_time": "8:04:19"}
{"current_steps": 705, "total_steps": 4585, "loss": 0.5641, "lr": 3.965301263241296e-05, "epoch": 1.076394194041253, "percentage": 15.38, "elapsed_time": "1:27:46", "remaining_time": "8:03:03"}
{"current_steps": 710, "total_steps": 4585, "loss": 0.5408, "lr": 3.963874858916556e-05, "epoch": 1.084033613445378, "percentage": 15.49, "elapsed_time": "1:28:17", "remaining_time": "8:01:51"}
{"current_steps": 715, "total_steps": 4585, "loss": 0.5436, "lr": 3.9624199906795136e-05, "epoch": 1.0916730328495035, "percentage": 15.59, "elapsed_time": "1:29:07", "remaining_time": "8:02:24"}
{"current_steps": 720, "total_steps": 4585, "loss": 0.5102, "lr": 3.960936679616667e-05, "epoch": 1.0993124522536286, "percentage": 15.7, "elapsed_time": "1:29:39", "remaining_time": "8:01:19"}
{"current_steps": 725, "total_steps": 4585, "loss": 0.5143, "lr": 3.959424947226756e-05, "epoch": 1.106951871657754, "percentage": 15.81, "elapsed_time": "1:30:15", "remaining_time": "8:00:32"}
{"current_steps": 730, "total_steps": 4585, "loss": 0.5857, "lr": 3.957884815420453e-05, "epoch": 1.1145912910618794, "percentage": 15.92, "elapsed_time": "1:30:41", "remaining_time": "7:58:57"}
{"current_steps": 735, "total_steps": 4585, "loss": 0.5619, "lr": 3.956316306520044e-05, "epoch": 1.1222307104660045, "percentage": 16.03, "elapsed_time": "1:31:25", "remaining_time": "7:58:52"}
{"current_steps": 740, "total_steps": 4585, "loss": 0.5111, "lr": 3.9547194432591066e-05, "epoch": 1.12987012987013, "percentage": 16.14, "elapsed_time": "1:31:57", "remaining_time": "7:57:50"}
{"current_steps": 745, "total_steps": 4585, "loss": 0.5282, "lr": 3.9530942487821785e-05, "epoch": 1.137509549274255, "percentage": 16.25, "elapsed_time": "1:32:39", "remaining_time": "7:57:33"}
{"current_steps": 750, "total_steps": 4585, "loss": 0.5659, "lr": 3.951440746644422e-05, "epoch": 1.1451489686783805, "percentage": 16.36, "elapsed_time": "1:33:11", "remaining_time": "7:56:29"}
{"current_steps": 755, "total_steps": 4585, "loss": 0.5475, "lr": 3.949758960811284e-05, "epoch": 1.1527883880825058, "percentage": 16.47, "elapsed_time": "1:33:43", "remaining_time": "7:55:26"}
{"current_steps": 760, "total_steps": 4585, "loss": 0.521, "lr": 3.9480489156581514e-05, "epoch": 1.160427807486631, "percentage": 16.58, "elapsed_time": "1:34:14", "remaining_time": "7:54:16"}
{"current_steps": 765, "total_steps": 4585, "loss": 0.5316, "lr": 3.94631063596999e-05, "epoch": 1.1680672268907564, "percentage": 16.68, "elapsed_time": "1:34:51", "remaining_time": "7:53:38"}
{"current_steps": 770, "total_steps": 4585, "loss": 0.5058, "lr": 3.9445441469409924e-05, "epoch": 1.1757066462948815, "percentage": 16.79, "elapsed_time": "1:35:22", "remaining_time": "7:52:31"}
{"current_steps": 775, "total_steps": 4585, "loss": 0.5436, "lr": 3.94274947417421e-05, "epoch": 1.183346065699007, "percentage": 16.9, "elapsed_time": "1:36:02", "remaining_time": "7:52:06"}
{"current_steps": 780, "total_steps": 4585, "loss": 0.5254, "lr": 3.9409266436811824e-05, "epoch": 1.190985485103132, "percentage": 17.01, "elapsed_time": "1:36:40", "remaining_time": "7:51:34"}
{"current_steps": 785, "total_steps": 4585, "loss": 0.5343, "lr": 3.9390756818815605e-05, "epoch": 1.1986249045072574, "percentage": 17.12, "elapsed_time": "1:37:17", "remaining_time": "7:50:58"}
{"current_steps": 790, "total_steps": 4585, "loss": 0.5432, "lr": 3.937196615602722e-05, "epoch": 1.2062643239113828, "percentage": 17.23, "elapsed_time": "1:37:55", "remaining_time": "7:50:26"}
{"current_steps": 795, "total_steps": 4585, "loss": 0.5174, "lr": 3.9352894720793844e-05, "epoch": 1.213903743315508, "percentage": 17.34, "elapsed_time": "1:38:41", "remaining_time": "7:50:30"}
{"current_steps": 800, "total_steps": 4585, "loss": 0.5672, "lr": 3.9333542789532116e-05, "epoch": 1.2215431627196334, "percentage": 17.45, "elapsed_time": "1:39:14", "remaining_time": "7:49:32"}
{"current_steps": 805, "total_steps": 4585, "loss": 0.518, "lr": 3.9313910642724084e-05, "epoch": 1.2291825821237585, "percentage": 17.56, "elapsed_time": "1:39:49", "remaining_time": "7:48:44"}
{"current_steps": 810, "total_steps": 4585, "loss": 0.5205, "lr": 3.92939985649132e-05, "epoch": 1.236822001527884, "percentage": 17.67, "elapsed_time": "1:40:31", "remaining_time": "7:48:28"}
{"current_steps": 815, "total_steps": 4585, "loss": 0.5072, "lr": 3.927380684470016e-05, "epoch": 1.244461420932009, "percentage": 17.78, "elapsed_time": "1:41:07", "remaining_time": "7:47:47"}
{"current_steps": 820, "total_steps": 4585, "loss": 0.5256, "lr": 3.9253335774738693e-05, "epoch": 1.2521008403361344, "percentage": 17.88, "elapsed_time": "1:41:39", "remaining_time": "7:46:47"}
{"current_steps": 825, "total_steps": 4585, "loss": 0.5265, "lr": 3.92325856517314e-05, "epoch": 1.2597402597402598, "percentage": 17.99, "elapsed_time": "1:42:19", "remaining_time": "7:46:21"}
{"current_steps": 830, "total_steps": 4585, "loss": 0.5689, "lr": 3.9211556776425374e-05, "epoch": 1.267379679144385, "percentage": 18.1, "elapsed_time": "1:42:52", "remaining_time": "7:45:25"}
{"current_steps": 835, "total_steps": 4585, "loss": 0.5661, "lr": 3.919024945360791e-05, "epoch": 1.2750190985485104, "percentage": 18.21, "elapsed_time": "1:43:22", "remaining_time": "7:44:15"}
{"current_steps": 840, "total_steps": 4585, "loss": 0.5022, "lr": 3.916866399210201e-05, "epoch": 1.2826585179526355, "percentage": 18.32, "elapsed_time": "1:44:05", "remaining_time": "7:44:03"}
{"current_steps": 845, "total_steps": 4585, "loss": 0.5273, "lr": 3.9146800704761976e-05, "epoch": 1.290297937356761, "percentage": 18.43, "elapsed_time": "1:44:38", "remaining_time": "7:43:07"}
{"current_steps": 850, "total_steps": 4585, "loss": 0.539, "lr": 3.912465990846884e-05, "epoch": 1.2979373567608863, "percentage": 18.54, "elapsed_time": "1:45:13", "remaining_time": "7:42:24"}
{"current_steps": 855, "total_steps": 4585, "loss": 0.542, "lr": 3.910224192412578e-05, "epoch": 1.3055767761650114, "percentage": 18.65, "elapsed_time": "1:45:55", "remaining_time": "7:42:05"}
{"current_steps": 860, "total_steps": 4585, "loss": 0.5641, "lr": 3.9079547076653466e-05, "epoch": 1.3132161955691368, "percentage": 18.76, "elapsed_time": "1:46:18", "remaining_time": "7:40:27"}
{"current_steps": 865, "total_steps": 4585, "loss": 0.5432, "lr": 3.9056575694985356e-05, "epoch": 1.320855614973262, "percentage": 18.87, "elapsed_time": "1:46:55", "remaining_time": "7:39:50"}
{"current_steps": 870, "total_steps": 4585, "loss": 0.5787, "lr": 3.903332811206293e-05, "epoch": 1.3284950343773874, "percentage": 18.97, "elapsed_time": "1:47:27", "remaining_time": "7:38:52"}
{"current_steps": 875, "total_steps": 4585, "loss": 0.5364, "lr": 3.900980466483085e-05, "epoch": 1.3361344537815127, "percentage": 19.08, "elapsed_time": "1:48:06", "remaining_time": "7:38:20"}
{"current_steps": 880, "total_steps": 4585, "loss": 0.5189, "lr": 3.89860056942321e-05, "epoch": 1.343773873185638, "percentage": 19.19, "elapsed_time": "1:48:35", "remaining_time": "7:37:13"}
{"current_steps": 885, "total_steps": 4585, "loss": 0.5318, "lr": 3.896193154520302e-05, "epoch": 1.351413292589763, "percentage": 19.3, "elapsed_time": "1:49:09", "remaining_time": "7:36:21"}
{"current_steps": 890, "total_steps": 4585, "loss": 0.515, "lr": 3.8937582566668324e-05, "epoch": 1.3590527119938884, "percentage": 19.41, "elapsed_time": "1:49:39", "remaining_time": "7:35:16"}
{"current_steps": 895, "total_steps": 4585, "loss": 0.5303, "lr": 3.891295911153601e-05, "epoch": 1.3666921313980138, "percentage": 19.52, "elapsed_time": "1:50:12", "remaining_time": "7:34:21"}
{"current_steps": 900, "total_steps": 4585, "loss": 0.5403, "lr": 3.888806153669233e-05, "epoch": 1.374331550802139, "percentage": 19.63, "elapsed_time": "1:50:46", "remaining_time": "7:33:31"}
{"current_steps": 905, "total_steps": 4585, "loss": 0.5463, "lr": 3.88628902029965e-05, "epoch": 1.3819709702062644, "percentage": 19.74, "elapsed_time": "1:51:21", "remaining_time": "7:32:48"}
{"current_steps": 910, "total_steps": 4585, "loss": 0.5348, "lr": 3.883744547527555e-05, "epoch": 1.3896103896103895, "percentage": 19.85, "elapsed_time": "1:52:01", "remaining_time": "7:32:25"}
{"current_steps": 915, "total_steps": 4585, "loss": 0.5418, "lr": 3.881172772231903e-05, "epoch": 1.397249809014515, "percentage": 19.96, "elapsed_time": "1:52:31", "remaining_time": "7:31:19"}
{"current_steps": 920, "total_steps": 4585, "loss": 0.572, "lr": 3.878573731687362e-05, "epoch": 1.4048892284186403, "percentage": 20.07, "elapsed_time": "1:53:11", "remaining_time": "7:30:56"}
{"current_steps": 925, "total_steps": 4585, "loss": 0.529, "lr": 3.8759474635637785e-05, "epoch": 1.4125286478227654, "percentage": 20.17, "elapsed_time": "1:53:41", "remaining_time": "7:29:50"}
{"current_steps": 930, "total_steps": 4585, "loss": 0.5537, "lr": 3.8732940059256276e-05, "epoch": 1.4201680672268908, "percentage": 20.28, "elapsed_time": "1:54:15", "remaining_time": "7:29:04"}
{"current_steps": 935, "total_steps": 4585, "loss": 0.5306, "lr": 3.870613397231462e-05, "epoch": 1.427807486631016, "percentage": 20.39, "elapsed_time": "1:55:01", "remaining_time": "7:29:02"}
{"current_steps": 940, "total_steps": 4585, "loss": 0.5311, "lr": 3.867905676333354e-05, "epoch": 1.4354469060351414, "percentage": 20.5, "elapsed_time": "1:55:31", "remaining_time": "7:27:56"}
{"current_steps": 945, "total_steps": 4585, "loss": 0.5346, "lr": 3.8651708824763384e-05, "epoch": 1.4430863254392667, "percentage": 20.61, "elapsed_time": "1:56:06", "remaining_time": "7:27:14"}
{"current_steps": 950, "total_steps": 4585, "loss": 0.5648, "lr": 3.862409055297831e-05, "epoch": 1.450725744843392, "percentage": 20.72, "elapsed_time": "1:56:46", "remaining_time": "7:26:49"}
{"current_steps": 955, "total_steps": 4585, "loss": 0.525, "lr": 3.8596202348270695e-05, "epoch": 1.458365164247517, "percentage": 20.83, "elapsed_time": "1:57:26", "remaining_time": "7:26:25"}
{"current_steps": 960, "total_steps": 4585, "loss": 0.5238, "lr": 3.85680446148452e-05, "epoch": 1.4660045836516424, "percentage": 20.94, "elapsed_time": "1:58:08", "remaining_time": "7:26:06"}
{"current_steps": 965, "total_steps": 4585, "loss": 0.558, "lr": 3.853961776081299e-05, "epoch": 1.4736440030557678, "percentage": 21.05, "elapsed_time": "1:58:33", "remaining_time": "7:24:45"}
{"current_steps": 970, "total_steps": 4585, "loss": 0.5318, "lr": 3.8510922198185805e-05, "epoch": 1.481283422459893, "percentage": 21.16, "elapsed_time": "1:59:10", "remaining_time": "7:24:07"}
{"current_steps": 975, "total_steps": 4585, "loss": 0.5603, "lr": 3.8481958342869966e-05, "epoch": 1.4889228418640184, "percentage": 21.26, "elapsed_time": "1:59:56", "remaining_time": "7:24:03"}
{"current_steps": 980, "total_steps": 4585, "loss": 0.4938, "lr": 3.8452726614660364e-05, "epoch": 1.4965622612681435, "percentage": 21.37, "elapsed_time": "2:00:36", "remaining_time": "7:23:40"}
{"current_steps": 985, "total_steps": 4585, "loss": 0.5159, "lr": 3.8423227437234385e-05, "epoch": 1.504201680672269, "percentage": 21.48, "elapsed_time": "2:01:13", "remaining_time": "7:23:03"}
{"current_steps": 990, "total_steps": 4585, "loss": 0.5241, "lr": 3.8393461238145737e-05, "epoch": 1.5118411000763943, "percentage": 21.59, "elapsed_time": "2:01:55", "remaining_time": "7:22:46"}
{"current_steps": 995, "total_steps": 4585, "loss": 0.5646, "lr": 3.83634284488183e-05, "epoch": 1.5194805194805194, "percentage": 21.7, "elapsed_time": "2:02:30", "remaining_time": "7:22:01"}
{"current_steps": 1000, "total_steps": 4585, "loss": 0.558, "lr": 3.833312950453981e-05, "epoch": 1.5271199388846448, "percentage": 21.81, "elapsed_time": "2:03:11", "remaining_time": "7:21:37"}
{"current_steps": 1005, "total_steps": 4585, "loss": 0.5231, "lr": 3.830256484445562e-05, "epoch": 1.53475935828877, "percentage": 21.92, "elapsed_time": "2:03:47", "remaining_time": "7:20:57"}
{"current_steps": 1010, "total_steps": 4585, "loss": 0.5597, "lr": 3.827173491156228e-05, "epoch": 1.5423987776928954, "percentage": 22.03, "elapsed_time": "2:04:24", "remaining_time": "7:20:19"}
{"current_steps": 1015, "total_steps": 4585, "loss": 0.5225, "lr": 3.824064015270116e-05, "epoch": 1.5500381970970207, "percentage": 22.14, "elapsed_time": "2:05:02", "remaining_time": "7:19:49"}
{"current_steps": 1020, "total_steps": 4585, "loss": 0.5736, "lr": 3.820928101855193e-05, "epoch": 1.557677616501146, "percentage": 22.25, "elapsed_time": "2:05:27", "remaining_time": "7:18:30"}
{"current_steps": 1025, "total_steps": 4585, "loss": 0.518, "lr": 3.817765796362606e-05, "epoch": 1.565317035905271, "percentage": 22.36, "elapsed_time": "2:06:06", "remaining_time": "7:17:59"}
{"current_steps": 1030, "total_steps": 4585, "loss": 0.5404, "lr": 3.814577144626021e-05, "epoch": 1.5729564553093964, "percentage": 22.46, "elapsed_time": "2:06:39", "remaining_time": "7:17:08"}
{"current_steps": 1035, "total_steps": 4585, "loss": 0.5613, "lr": 3.811362192860962e-05, "epoch": 1.5805958747135218, "percentage": 22.57, "elapsed_time": "2:07:06", "remaining_time": "7:15:56"}
{"current_steps": 1040, "total_steps": 4585, "loss": 0.5421, "lr": 3.808120987664137e-05, "epoch": 1.5882352941176472, "percentage": 22.68, "elapsed_time": "2:07:35", "remaining_time": "7:14:56"}
{"current_steps": 1045, "total_steps": 4585, "loss": 0.5357, "lr": 3.804853576012767e-05, "epoch": 1.5958747135217723, "percentage": 22.79, "elapsed_time": "2:08:07", "remaining_time": "7:14:00"}
{"current_steps": 1050, "total_steps": 4585, "loss": 0.5328, "lr": 3.8015600052638994e-05, "epoch": 1.6035141329258975, "percentage": 22.9, "elapsed_time": "2:08:39", "remaining_time": "7:13:10"}
{"current_steps": 1055, "total_steps": 4585, "loss": 0.5186, "lr": 3.798240323153729e-05, "epoch": 1.6111535523300229, "percentage": 23.01, "elapsed_time": "2:09:16", "remaining_time": "7:12:31"}
{"current_steps": 1060, "total_steps": 4585, "loss": 0.5433, "lr": 3.7948945777968986e-05, "epoch": 1.6187929717341483, "percentage": 23.12, "elapsed_time": "2:09:42", "remaining_time": "7:11:19"}
{"current_steps": 1065, "total_steps": 4585, "loss": 0.5291, "lr": 3.7915228176858076e-05, "epoch": 1.6264323911382736, "percentage": 23.23, "elapsed_time": "2:10:11", "remaining_time": "7:10:19"}
{"current_steps": 1070, "total_steps": 4585, "loss": 0.5656, "lr": 3.788125091689906e-05, "epoch": 1.6340718105423988, "percentage": 23.34, "elapsed_time": "2:10:45", "remaining_time": "7:09:31"}
{"current_steps": 1075, "total_steps": 4585, "loss": 0.5188, "lr": 3.7847014490549865e-05, "epoch": 1.641711229946524, "percentage": 23.45, "elapsed_time": "2:11:18", "remaining_time": "7:08:42"}
{"current_steps": 1080, "total_steps": 4585, "loss": 0.5173, "lr": 3.7812519394024714e-05, "epoch": 1.6493506493506493, "percentage": 23.56, "elapsed_time": "2:11:54", "remaining_time": "7:08:05"}
{"current_steps": 1085, "total_steps": 4585, "loss": 0.5399, "lr": 3.777776612728693e-05, "epoch": 1.6569900687547747, "percentage": 23.66, "elapsed_time": "2:12:36", "remaining_time": "7:07:44"}
{"current_steps": 1090, "total_steps": 4585, "loss": 0.5159, "lr": 3.77427551940417e-05, "epoch": 1.6646294881588999, "percentage": 23.77, "elapsed_time": "2:13:16", "remaining_time": "7:07:19"}
{"current_steps": 1095, "total_steps": 4585, "loss": 0.5214, "lr": 3.770748710172874e-05, "epoch": 1.6722689075630253, "percentage": 23.88, "elapsed_time": "2:13:50", "remaining_time": "7:06:34"}
{"current_steps": 1100, "total_steps": 4585, "loss": 0.5302, "lr": 3.7671962361515e-05, "epoch": 1.6799083269671504, "percentage": 23.99, "elapsed_time": "2:14:33", "remaining_time": "7:06:19"}
{"current_steps": 1105, "total_steps": 4585, "loss": 0.516, "lr": 3.76361814882872e-05, "epoch": 1.6875477463712758, "percentage": 24.1, "elapsed_time": "2:15:08", "remaining_time": "7:05:35"}
{"current_steps": 1110, "total_steps": 4585, "loss": 0.5525, "lr": 3.760014500064437e-05, "epoch": 1.6951871657754012, "percentage": 24.21, "elapsed_time": "2:15:49", "remaining_time": "7:05:13"}
{"current_steps": 1115, "total_steps": 4585, "loss": 0.5417, "lr": 3.75638534208904e-05, "epoch": 1.7028265851795263, "percentage": 24.32, "elapsed_time": "2:16:25", "remaining_time": "7:04:35"}
{"current_steps": 1120, "total_steps": 4585, "loss": 0.4856, "lr": 3.7527307275026375e-05, "epoch": 1.7104660045836515, "percentage": 24.43, "elapsed_time": "2:16:59", "remaining_time": "7:03:48"}
{"current_steps": 1125, "total_steps": 4585, "loss": 0.5104, "lr": 3.749050709274303e-05, "epoch": 1.7181054239877769, "percentage": 24.54, "elapsed_time": "2:17:36", "remaining_time": "7:03:14"}
{"current_steps": 1130, "total_steps": 4585, "loss": 0.5307, "lr": 3.7453453407413017e-05, "epoch": 1.7257448433919023, "percentage": 24.65, "elapsed_time": "2:18:13", "remaining_time": "7:02:37"}
{"current_steps": 1135, "total_steps": 4585, "loss": 0.5621, "lr": 3.7416146756083206e-05, "epoch": 1.7333842627960276, "percentage": 24.75, "elapsed_time": "2:18:48", "remaining_time": "7:01:54"}
{"current_steps": 1140, "total_steps": 4585, "loss": 0.5091, "lr": 3.7378587679466905e-05, "epoch": 1.7410236822001528, "percentage": 24.86, "elapsed_time": "2:19:29", "remaining_time": "7:01:31"}
{"current_steps": 1145, "total_steps": 4585, "loss": 0.5564, "lr": 3.7340776721936e-05, "epoch": 1.748663101604278, "percentage": 24.97, "elapsed_time": "2:20:14", "remaining_time": "7:01:19"}
{"current_steps": 1150, "total_steps": 4585, "loss": 0.5301, "lr": 3.730271443151307e-05, "epoch": 1.7563025210084033, "percentage": 25.08, "elapsed_time": "2:20:45", "remaining_time": "7:00:25"}
{"current_steps": 1155, "total_steps": 4585, "loss": 0.5295, "lr": 3.726440135986346e-05, "epoch": 1.7639419404125287, "percentage": 25.19, "elapsed_time": "2:21:22", "remaining_time": "6:59:49"}
{"current_steps": 1160, "total_steps": 4585, "loss": 0.5332, "lr": 3.722583806228727e-05, "epoch": 1.771581359816654, "percentage": 25.3, "elapsed_time": "2:21:57", "remaining_time": "6:59:09"}
{"current_steps": 1165, "total_steps": 4585, "loss": 0.5465, "lr": 3.7187025097711325e-05, "epoch": 1.7792207792207793, "percentage": 25.41, "elapsed_time": "2:22:38", "remaining_time": "6:58:45"}
{"current_steps": 1170, "total_steps": 4585, "loss": 0.5383, "lr": 3.714796302868105e-05, "epoch": 1.7868601986249044, "percentage": 25.52, "elapsed_time": "2:23:08", "remaining_time": "6:57:48"}
{"current_steps": 1175, "total_steps": 4585, "loss": 0.5371, "lr": 3.710865242135231e-05, "epoch": 1.7944996180290298, "percentage": 25.63, "elapsed_time": "2:23:43", "remaining_time": "6:57:05"}
{"current_steps": 1180, "total_steps": 4585, "loss": 0.5058, "lr": 3.7069093845483265e-05, "epoch": 1.8021390374331552, "percentage": 25.74, "elapsed_time": "2:24:13", "remaining_time": "6:56:09"}
{"current_steps": 1185, "total_steps": 4585, "loss": 0.506, "lr": 3.702928787442603e-05, "epoch": 1.8097784568372803, "percentage": 25.85, "elapsed_time": "2:24:54", "remaining_time": "6:55:45"}
{"current_steps": 1190, "total_steps": 4585, "loss": 0.5523, "lr": 3.698923508511843e-05, "epoch": 1.8174178762414055, "percentage": 25.95, "elapsed_time": "2:25:21", "remaining_time": "6:54:42"}
{"current_steps": 1195, "total_steps": 4585, "loss": 0.509, "lr": 3.69489360580756e-05, "epoch": 1.8250572956455309, "percentage": 26.06, "elapsed_time": "2:25:52", "remaining_time": "6:53:47"}
{"current_steps": 1200, "total_steps": 4585, "loss": 0.4913, "lr": 3.690839137738159e-05, "epoch": 1.8326967150496563, "percentage": 26.17, "elapsed_time": "2:26:44", "remaining_time": "6:53:55"}
{"current_steps": 1205, "total_steps": 4585, "loss": 0.555, "lr": 3.6867601630680866e-05, "epoch": 1.8403361344537816, "percentage": 26.28, "elapsed_time": "2:27:26", "remaining_time": "6:53:33"}
{"current_steps": 1210, "total_steps": 4585, "loss": 0.5505, "lr": 3.682656740916986e-05, "epoch": 1.8479755538579068, "percentage": 26.39, "elapsed_time": "2:27:59", "remaining_time": "6:52:46"}
{"current_steps": 1215, "total_steps": 4585, "loss": 0.5594, "lr": 3.678528930758834e-05, "epoch": 1.855614973262032, "percentage": 26.5, "elapsed_time": "2:28:28", "remaining_time": "6:51:49"}
{"current_steps": 1220, "total_steps": 4585, "loss": 0.5401, "lr": 3.674376792421081e-05, "epoch": 1.8632543926661573, "percentage": 26.61, "elapsed_time": "2:29:00", "remaining_time": "6:50:58"}
{"current_steps": 1225, "total_steps": 4585, "loss": 0.5286, "lr": 3.670200386083784e-05, "epoch": 1.8708938120702827, "percentage": 26.72, "elapsed_time": "2:29:38", "remaining_time": "6:50:26"}
{"current_steps": 1230, "total_steps": 4585, "loss": 0.5662, "lr": 3.665999772278736e-05, "epoch": 1.878533231474408, "percentage": 26.83, "elapsed_time": "2:30:10", "remaining_time": "6:49:38"}
{"current_steps": 1235, "total_steps": 4585, "loss": 0.5345, "lr": 3.661775011888584e-05, "epoch": 1.8861726508785333, "percentage": 26.94, "elapsed_time": "2:30:40", "remaining_time": "6:48:42"}
{"current_steps": 1240, "total_steps": 4585, "loss": 0.4882, "lr": 3.657526166145952e-05, "epoch": 1.8938120702826584, "percentage": 27.04, "elapsed_time": "2:31:20", "remaining_time": "6:48:14"}
{"current_steps": 1245, "total_steps": 4585, "loss": 0.5019, "lr": 3.65325329663255e-05, "epoch": 1.9014514896867838, "percentage": 27.15, "elapsed_time": "2:31:51", "remaining_time": "6:47:23"}
{"current_steps": 1250, "total_steps": 4585, "loss": 0.5196, "lr": 3.648956465278284e-05, "epoch": 1.9090909090909092, "percentage": 27.26, "elapsed_time": "2:32:26", "remaining_time": "6:46:41"}
{"current_steps": 1255, "total_steps": 4585, "loss": 0.5425, "lr": 3.6446357343603536e-05, "epoch": 1.9167303284950343, "percentage": 27.37, "elapsed_time": "2:32:56", "remaining_time": "6:45:48"}
{"current_steps": 1260, "total_steps": 4585, "loss": 0.5057, "lr": 3.6402911665023565e-05, "epoch": 1.9243697478991597, "percentage": 27.48, "elapsed_time": "2:33:33", "remaining_time": "6:45:13"}
{"current_steps": 1265, "total_steps": 4585, "loss": 0.5472, "lr": 3.6359228246733744e-05, "epoch": 1.9320091673032849, "percentage": 27.59, "elapsed_time": "2:34:14", "remaining_time": "6:44:49"}
{"current_steps": 1270, "total_steps": 4585, "loss": 0.5313, "lr": 3.631530772187065e-05, "epoch": 1.9396485867074102, "percentage": 27.7, "elapsed_time": "2:34:41", "remaining_time": "6:43:46"}
{"current_steps": 1275, "total_steps": 4585, "loss": 0.4999, "lr": 3.627115072700741e-05, "epoch": 1.9472880061115356, "percentage": 27.81, "elapsed_time": "2:35:13", "remaining_time": "6:42:59"}
{"current_steps": 1280, "total_steps": 4585, "loss": 0.5491, "lr": 3.6226757902144495e-05, "epoch": 1.9549274255156608, "percentage": 27.92, "elapsed_time": "2:35:50", "remaining_time": "6:42:22"}
{"current_steps": 1285, "total_steps": 4585, "loss": 0.513, "lr": 3.618212989070043e-05, "epoch": 1.962566844919786, "percentage": 28.03, "elapsed_time": "2:36:32", "remaining_time": "6:42:00"}
{"current_steps": 1290, "total_steps": 4585, "loss": 0.5191, "lr": 3.613726733950248e-05, "epoch": 1.9702062643239113, "percentage": 28.14, "elapsed_time": "2:37:08", "remaining_time": "6:41:22"}
{"current_steps": 1295, "total_steps": 4585, "loss": 0.5531, "lr": 3.609217089877728e-05, "epoch": 1.9778456837280367, "percentage": 28.24, "elapsed_time": "2:37:43", "remaining_time": "6:40:43"}
{"current_steps": 1300, "total_steps": 4585, "loss": 0.5478, "lr": 3.604684122214138e-05, "epoch": 1.985485103132162, "percentage": 28.35, "elapsed_time": "2:38:20", "remaining_time": "6:40:06"}
{"current_steps": 1305, "total_steps": 4585, "loss": 0.5442, "lr": 3.600127896659181e-05, "epoch": 1.9931245225362872, "percentage": 28.46, "elapsed_time": "2:38:58", "remaining_time": "6:39:34"}
{"current_steps": 1310, "total_steps": 4585, "loss": 0.4938, "lr": 3.5955484792496536e-05, "epoch": 2.0, "percentage": 28.57, "elapsed_time": "2:39:37", "remaining_time": "6:39:03"}
{"current_steps": 1315, "total_steps": 4585, "loss": 0.4783, "lr": 3.5909459363584895e-05, "epoch": 2.0076394194041254, "percentage": 28.68, "elapsed_time": "2:40:21", "remaining_time": "6:38:44"}
{"current_steps": 1320, "total_steps": 4585, "loss": 0.4646, "lr": 3.5863203346937974e-05, "epoch": 2.0152788388082508, "percentage": 28.79, "elapsed_time": "2:40:56", "remaining_time": "6:38:04"}
{"current_steps": 1325, "total_steps": 4585, "loss": 0.4872, "lr": 3.5816717412978935e-05, "epoch": 2.0229182582123757, "percentage": 28.9, "elapsed_time": "2:41:26", "remaining_time": "6:37:11"}
{"current_steps": 1330, "total_steps": 4585, "loss": 0.4855, "lr": 3.577000223546331e-05, "epoch": 2.030557677616501, "percentage": 29.01, "elapsed_time": "2:41:58", "remaining_time": "6:36:25"}
{"current_steps": 1335, "total_steps": 4585, "loss": 0.4616, "lr": 3.5723058491469226e-05, "epoch": 2.0381970970206265, "percentage": 29.12, "elapsed_time": "2:42:34", "remaining_time": "6:35:47"}
{"current_steps": 1340, "total_steps": 4585, "loss": 0.5099, "lr": 3.56758868613876e-05, "epoch": 2.045836516424752, "percentage": 29.23, "elapsed_time": "2:43:15", "remaining_time": "6:35:20"}
{"current_steps": 1345, "total_steps": 4585, "loss": 0.5191, "lr": 3.5628488028912284e-05, "epoch": 2.053475935828877, "percentage": 29.33, "elapsed_time": "2:43:46", "remaining_time": "6:34:30"}
{"current_steps": 1350, "total_steps": 4585, "loss": 0.4767, "lr": 3.558086268103011e-05, "epoch": 2.061115355233002, "percentage": 29.44, "elapsed_time": "2:44:28", "remaining_time": "6:34:08"}
{"current_steps": 1355, "total_steps": 4585, "loss": 0.4833, "lr": 3.5533011508011e-05, "epoch": 2.0687547746371275, "percentage": 29.55, "elapsed_time": "2:45:05", "remaining_time": "6:33:31"}
{"current_steps": 1360, "total_steps": 4585, "loss": 0.5111, "lr": 3.548493520339792e-05, "epoch": 2.076394194041253, "percentage": 29.66, "elapsed_time": "2:45:35", "remaining_time": "6:32:40"}
{"current_steps": 1365, "total_steps": 4585, "loss": 0.507, "lr": 3.5436634463996834e-05, "epoch": 2.0840336134453783, "percentage": 29.77, "elapsed_time": "2:46:09", "remaining_time": "6:31:57"}
{"current_steps": 1370, "total_steps": 4585, "loss": 0.5495, "lr": 3.538810998986661e-05, "epoch": 2.0916730328495032, "percentage": 29.88, "elapsed_time": "2:46:45", "remaining_time": "6:31:21"}
{"current_steps": 1375, "total_steps": 4585, "loss": 0.5278, "lr": 3.533936248430887e-05, "epoch": 2.0993124522536286, "percentage": 29.99, "elapsed_time": "2:47:24", "remaining_time": "6:30:49"}
{"current_steps": 1380, "total_steps": 4585, "loss": 0.4977, "lr": 3.52903926538578e-05, "epoch": 2.106951871657754, "percentage": 30.1, "elapsed_time": "2:48:00", "remaining_time": "6:30:11"}
{"current_steps": 1385, "total_steps": 4585, "loss": 0.5114, "lr": 3.524120120826991e-05, "epoch": 2.1145912910618794, "percentage": 30.21, "elapsed_time": "2:48:38", "remaining_time": "6:29:38"}
{"current_steps": 1390, "total_steps": 4585, "loss": 0.4868, "lr": 3.519178886051374e-05, "epoch": 2.1222307104660048, "percentage": 30.32, "elapsed_time": "2:49:14", "remaining_time": "6:29:00"}
{"current_steps": 1395, "total_steps": 4585, "loss": 0.4773, "lr": 3.514215632675953e-05, "epoch": 2.1298701298701297, "percentage": 30.43, "elapsed_time": "2:49:53", "remaining_time": "6:28:29"}
{"current_steps": 1400, "total_steps": 4585, "loss": 0.5114, "lr": 3.509230432636884e-05, "epoch": 2.137509549274255, "percentage": 30.53, "elapsed_time": "2:50:26", "remaining_time": "6:27:45"}
{"current_steps": 1405, "total_steps": 4585, "loss": 0.4978, "lr": 3.504223358188414e-05, "epoch": 2.1451489686783805, "percentage": 30.64, "elapsed_time": "2:51:04", "remaining_time": "6:27:12"}
{"current_steps": 1410, "total_steps": 4585, "loss": 0.4943, "lr": 3.4991944819018295e-05, "epoch": 2.152788388082506, "percentage": 30.75, "elapsed_time": "2:51:40", "remaining_time": "6:26:35"}
{"current_steps": 1415, "total_steps": 4585, "loss": 0.4697, "lr": 3.4941438766644094e-05, "epoch": 2.160427807486631, "percentage": 30.86, "elapsed_time": "2:52:18", "remaining_time": "6:26:00"}
{"current_steps": 1420, "total_steps": 4585, "loss": 0.4957, "lr": 3.489071615678366e-05, "epoch": 2.168067226890756, "percentage": 30.97, "elapsed_time": "2:53:01", "remaining_time": "6:25:40"}
{"current_steps": 1425, "total_steps": 4585, "loss": 0.4863, "lr": 3.483977772459786e-05, "epoch": 2.1757066462948815, "percentage": 31.08, "elapsed_time": "2:53:42", "remaining_time": "6:25:12"}
{"current_steps": 1430, "total_steps": 4585, "loss": 0.4905, "lr": 3.478862420837561e-05, "epoch": 2.183346065699007, "percentage": 31.19, "elapsed_time": "2:54:13", "remaining_time": "6:24:24"}
{"current_steps": 1435, "total_steps": 4585, "loss": 0.5062, "lr": 3.473725634952321e-05, "epoch": 2.1909854851031323, "percentage": 31.3, "elapsed_time": "2:54:42", "remaining_time": "6:23:30"}
{"current_steps": 1440, "total_steps": 4585, "loss": 0.4551, "lr": 3.4685674892553604e-05, "epoch": 2.1986249045072572, "percentage": 31.41, "elapsed_time": "2:55:27", "remaining_time": "6:23:13"}
{"current_steps": 1445, "total_steps": 4585, "loss": 0.4455, "lr": 3.463388058507556e-05, "epoch": 2.2062643239113826, "percentage": 31.52, "elapsed_time": "2:56:01", "remaining_time": "6:22:30"}
{"current_steps": 1450, "total_steps": 4585, "loss": 0.4922, "lr": 3.458187417778284e-05, "epoch": 2.213903743315508, "percentage": 31.62, "elapsed_time": "2:56:36", "remaining_time": "6:21:50"}
{"current_steps": 1455, "total_steps": 4585, "loss": 0.4853, "lr": 3.452965642444334e-05, "epoch": 2.2215431627196334, "percentage": 31.73, "elapsed_time": "2:57:11", "remaining_time": "6:21:09"}
{"current_steps": 1460, "total_steps": 4585, "loss": 0.4831, "lr": 3.447722808188816e-05, "epoch": 2.2291825821237587, "percentage": 31.84, "elapsed_time": "2:57:46", "remaining_time": "6:20:29"}
{"current_steps": 1465, "total_steps": 4585, "loss": 0.5236, "lr": 3.442458991000062e-05, "epoch": 2.2368220015278837, "percentage": 31.95, "elapsed_time": "2:58:13", "remaining_time": "6:19:33"}
{"current_steps": 1470, "total_steps": 4585, "loss": 0.5182, "lr": 3.437174267170524e-05, "epoch": 2.244461420932009, "percentage": 32.06, "elapsed_time": "2:58:46", "remaining_time": "6:18:49"}
{"current_steps": 1475, "total_steps": 4585, "loss": 0.4896, "lr": 3.4318687132956714e-05, "epoch": 2.2521008403361344, "percentage": 32.17, "elapsed_time": "2:59:31", "remaining_time": "6:18:31"}
{"current_steps": 1480, "total_steps": 4585, "loss": 0.4805, "lr": 3.426542406272879e-05, "epoch": 2.25974025974026, "percentage": 32.28, "elapsed_time": "3:00:04", "remaining_time": "6:17:47"}
{"current_steps": 1485, "total_steps": 4585, "loss": 0.5131, "lr": 3.4211954233003115e-05, "epoch": 2.267379679144385, "percentage": 32.39, "elapsed_time": "3:00:35", "remaining_time": "6:16:58"}
{"current_steps": 1490, "total_steps": 4585, "loss": 0.4764, "lr": 3.415827841875807e-05, "epoch": 2.27501909854851, "percentage": 32.5, "elapsed_time": "3:01:02", "remaining_time": "6:16:03"}
{"current_steps": 1495, "total_steps": 4585, "loss": 0.5384, "lr": 3.4104397397957495e-05, "epoch": 2.2826585179526355, "percentage": 32.61, "elapsed_time": "3:01:38", "remaining_time": "6:15:26"}
{"current_steps": 1500, "total_steps": 4585, "loss": 0.4798, "lr": 3.405031195153949e-05, "epoch": 2.290297937356761, "percentage": 32.72, "elapsed_time": "3:02:12", "remaining_time": "6:14:44"}
{"current_steps": 1505, "total_steps": 4585, "loss": 0.4687, "lr": 3.399602286340503e-05, "epoch": 2.2979373567608863, "percentage": 32.82, "elapsed_time": "3:03:36", "remaining_time": "6:15:45"}
{"current_steps": 1510, "total_steps": 4585, "loss": 0.5092, "lr": 3.394153092040658e-05, "epoch": 2.3055767761650117, "percentage": 32.93, "elapsed_time": "3:04:15", "remaining_time": "6:15:13"}
{"current_steps": 1515, "total_steps": 4585, "loss": 0.5131, "lr": 3.3886836912336796e-05, "epoch": 2.3132161955691366, "percentage": 33.04, "elapsed_time": "3:04:47", "remaining_time": "6:14:27"}
{"current_steps": 1520, "total_steps": 4585, "loss": 0.475, "lr": 3.383194163191698e-05, "epoch": 2.320855614973262, "percentage": 33.15, "elapsed_time": "3:05:19", "remaining_time": "6:13:41"}
{"current_steps": 1525, "total_steps": 4585, "loss": 0.5013, "lr": 3.3776845874785624e-05, "epoch": 2.3284950343773874, "percentage": 33.26, "elapsed_time": "3:05:51", "remaining_time": "6:12:55"}
{"current_steps": 1530, "total_steps": 4585, "loss": 0.4798, "lr": 3.37215504394869e-05, "epoch": 2.3361344537815127, "percentage": 33.37, "elapsed_time": "3:06:36", "remaining_time": "6:12:36"}
{"current_steps": 1535, "total_steps": 4585, "loss": 0.4925, "lr": 3.366605612745906e-05, "epoch": 2.343773873185638, "percentage": 33.48, "elapsed_time": "3:07:07", "remaining_time": "6:11:49"}
{"current_steps": 1540, "total_steps": 4585, "loss": 0.4864, "lr": 3.3610363743022795e-05, "epoch": 2.351413292589763, "percentage": 33.59, "elapsed_time": "3:07:35", "remaining_time": "6:10:56"}
{"current_steps": 1545, "total_steps": 4585, "loss": 0.5, "lr": 3.3554474093369656e-05, "epoch": 2.3590527119938884, "percentage": 33.7, "elapsed_time": "3:08:15", "remaining_time": "6:10:26"}
{"current_steps": 1550, "total_steps": 4585, "loss": 0.5091, "lr": 3.349838798855027e-05, "epoch": 2.366692131398014, "percentage": 33.81, "elapsed_time": "3:08:53", "remaining_time": "6:09:52"}
{"current_steps": 1555, "total_steps": 4585, "loss": 0.4559, "lr": 3.3442106241462645e-05, "epoch": 2.374331550802139, "percentage": 33.91, "elapsed_time": "3:09:29", "remaining_time": "6:09:14"}
{"current_steps": 1560, "total_steps": 4585, "loss": 0.5004, "lr": 3.338562966784038e-05, "epoch": 2.381970970206264, "percentage": 34.02, "elapsed_time": "3:10:03", "remaining_time": "6:08:31"}
{"current_steps": 1565, "total_steps": 4585, "loss": 0.494, "lr": 3.3328959086240876e-05, "epoch": 2.3896103896103895, "percentage": 34.13, "elapsed_time": "3:10:34", "remaining_time": "6:07:45"}
{"current_steps": 1570, "total_steps": 4585, "loss": 0.519, "lr": 3.3272095318033376e-05, "epoch": 2.397249809014515, "percentage": 34.24, "elapsed_time": "3:11:06", "remaining_time": "6:07:00"}
{"current_steps": 1575, "total_steps": 4585, "loss": 0.4903, "lr": 3.321503918738716e-05, "epoch": 2.4048892284186403, "percentage": 34.35, "elapsed_time": "3:11:39", "remaining_time": "6:06:17"}
{"current_steps": 1580, "total_steps": 4585, "loss": 0.4936, "lr": 3.315779152125955e-05, "epoch": 2.4125286478227657, "percentage": 34.46, "elapsed_time": "3:12:21", "remaining_time": "6:05:51"}
{"current_steps": 1585, "total_steps": 4585, "loss": 0.4993, "lr": 3.310035314938394e-05, "epoch": 2.4201680672268906, "percentage": 34.57, "elapsed_time": "3:12:57", "remaining_time": "6:05:13"}
{"current_steps": 1590, "total_steps": 4585, "loss": 0.4882, "lr": 3.304272490425777e-05, "epoch": 2.427807486631016, "percentage": 34.68, "elapsed_time": "3:13:28", "remaining_time": "6:04:26"}
{"current_steps": 1595, "total_steps": 4585, "loss": 0.5389, "lr": 3.2984907621130435e-05, "epoch": 2.4354469060351414, "percentage": 34.79, "elapsed_time": "3:14:05", "remaining_time": "6:03:50"}
{"current_steps": 1600, "total_steps": 4585, "loss": 0.5318, "lr": 3.292690213799122e-05, "epoch": 2.4430863254392667, "percentage": 34.9, "elapsed_time": "3:14:45", "remaining_time": "6:03:20"}
{"current_steps": 1605, "total_steps": 4585, "loss": 0.5288, "lr": 3.286870929555713e-05, "epoch": 2.4507257448433917, "percentage": 35.01, "elapsed_time": "3:15:21", "remaining_time": "6:02:43"}
{"current_steps": 1610, "total_steps": 4585, "loss": 0.4947, "lr": 3.281032993726071e-05, "epoch": 2.458365164247517, "percentage": 35.11, "elapsed_time": "3:15:56", "remaining_time": "6:02:04"}
{"current_steps": 1615, "total_steps": 4585, "loss": 0.4733, "lr": 3.275176490923781e-05, "epoch": 2.4660045836516424, "percentage": 35.22, "elapsed_time": "3:16:39", "remaining_time": "6:01:38"}
{"current_steps": 1620, "total_steps": 4585, "loss": 0.4731, "lr": 3.269301506031534e-05, "epoch": 2.473644003055768, "percentage": 35.33, "elapsed_time": "3:17:11", "remaining_time": "6:00:55"}
{"current_steps": 1625, "total_steps": 4585, "loss": 0.5177, "lr": 3.2634081241998954e-05, "epoch": 2.481283422459893, "percentage": 35.44, "elapsed_time": "3:17:45", "remaining_time": "6:00:13"}
{"current_steps": 1630, "total_steps": 4585, "loss": 0.525, "lr": 3.257496430846071e-05, "epoch": 2.488922841864018, "percentage": 35.55, "elapsed_time": "3:18:19", "remaining_time": "5:59:33"}
{"current_steps": 1635, "total_steps": 4585, "loss": 0.4685, "lr": 3.251566511652669e-05, "epoch": 2.4965622612681435, "percentage": 35.66, "elapsed_time": "3:18:53", "remaining_time": "5:58:52"}
{"current_steps": 1640, "total_steps": 4585, "loss": 0.4816, "lr": 3.245618452566461e-05, "epoch": 2.504201680672269, "percentage": 35.77, "elapsed_time": "3:19:24", "remaining_time": "5:58:04"}
{"current_steps": 1645, "total_steps": 4585, "loss": 0.5, "lr": 3.23965233979713e-05, "epoch": 2.5118411000763943, "percentage": 35.88, "elapsed_time": "3:19:54", "remaining_time": "5:57:16"}
{"current_steps": 1650, "total_steps": 4585, "loss": 0.5077, "lr": 3.233668259816026e-05, "epoch": 2.5194805194805197, "percentage": 35.99, "elapsed_time": "3:20:39", "remaining_time": "5:56:55"}
{"current_steps": 1655, "total_steps": 4585, "loss": 0.5, "lr": 3.227666299354912e-05, "epoch": 2.5271199388846446, "percentage": 36.1, "elapsed_time": "3:21:12", "remaining_time": "5:56:13"}
{"current_steps": 1660, "total_steps": 4585, "loss": 0.506, "lr": 3.221646545404706e-05, "epoch": 2.53475935828877, "percentage": 36.21, "elapsed_time": "3:21:49", "remaining_time": "5:55:36"}
{"current_steps": 1665, "total_steps": 4585, "loss": 0.4704, "lr": 3.21560908521422e-05, "epoch": 2.5423987776928954, "percentage": 36.31, "elapsed_time": "3:22:28", "remaining_time": "5:55:04"}
{"current_steps": 1670, "total_steps": 4585, "loss": 0.4741, "lr": 3.209554006288895e-05, "epoch": 2.5500381970970207, "percentage": 36.42, "elapsed_time": "3:23:14", "remaining_time": "5:54:46"}
{"current_steps": 1675, "total_steps": 4585, "loss": 0.5118, "lr": 3.203481396389535e-05, "epoch": 2.557677616501146, "percentage": 36.53, "elapsed_time": "3:23:46", "remaining_time": "5:54:02"}
{"current_steps": 1680, "total_steps": 4585, "loss": 0.4825, "lr": 3.1973913435310335e-05, "epoch": 2.565317035905271, "percentage": 36.64, "elapsed_time": "3:24:20", "remaining_time": "5:53:20"}
{"current_steps": 1685, "total_steps": 4585, "loss": 0.5003, "lr": 3.1912839359810974e-05, "epoch": 2.5729564553093964, "percentage": 36.75, "elapsed_time": "3:24:51", "remaining_time": "5:52:35"}
{"current_steps": 1690, "total_steps": 4585, "loss": 0.4805, "lr": 3.185159262258967e-05, "epoch": 2.580595874713522, "percentage": 36.86, "elapsed_time": "3:25:28", "remaining_time": "5:51:58"}
{"current_steps": 1695, "total_steps": 4585, "loss": 0.4918, "lr": 3.179017411134137e-05, "epoch": 2.588235294117647, "percentage": 36.97, "elapsed_time": "3:26:02", "remaining_time": "5:51:17"}
{"current_steps": 1700, "total_steps": 4585, "loss": 0.4995, "lr": 3.172858471625065e-05, "epoch": 2.5958747135217726, "percentage": 37.08, "elapsed_time": "3:26:31", "remaining_time": "5:50:29"}
{"current_steps": 1705, "total_steps": 4585, "loss": 0.4978, "lr": 3.166682532997883e-05, "epoch": 2.6035141329258975, "percentage": 37.19, "elapsed_time": "3:27:08", "remaining_time": "5:49:53"}
{"current_steps": 1710, "total_steps": 4585, "loss": 0.4732, "lr": 3.160489684765105e-05, "epoch": 2.611153552330023, "percentage": 37.3, "elapsed_time": "3:27:41", "remaining_time": "5:49:11"}
{"current_steps": 1715, "total_steps": 4585, "loss": 0.4727, "lr": 3.154280016684329e-05, "epoch": 2.6187929717341483, "percentage": 37.4, "elapsed_time": "3:28:17", "remaining_time": "5:48:34"}
{"current_steps": 1720, "total_steps": 4585, "loss": 0.4939, "lr": 3.148053618756936e-05, "epoch": 2.6264323911382736, "percentage": 37.51, "elapsed_time": "3:28:57", "remaining_time": "5:48:04"}
{"current_steps": 1725, "total_steps": 4585, "loss": 0.4862, "lr": 3.141810581226782e-05, "epoch": 2.634071810542399, "percentage": 37.62, "elapsed_time": "3:29:39", "remaining_time": "5:47:37"}
{"current_steps": 1730, "total_steps": 4585, "loss": 0.4809, "lr": 3.135550994578897e-05, "epoch": 2.641711229946524, "percentage": 37.73, "elapsed_time": "3:30:14", "remaining_time": "5:46:56"}
{"current_steps": 1735, "total_steps": 4585, "loss": 0.5099, "lr": 3.129274949538169e-05, "epoch": 2.6493506493506493, "percentage": 37.84, "elapsed_time": "3:30:48", "remaining_time": "5:46:17"}
{"current_steps": 1740, "total_steps": 4585, "loss": 0.4703, "lr": 3.122982537068028e-05, "epoch": 2.6569900687547747, "percentage": 37.95, "elapsed_time": "3:31:23", "remaining_time": "5:45:38"}
{"current_steps": 1745, "total_steps": 4585, "loss": 0.4571, "lr": 3.1166738483691305e-05, "epoch": 2.6646294881588997, "percentage": 38.06, "elapsed_time": "3:31:53", "remaining_time": "5:44:51"}
{"current_steps": 1750, "total_steps": 4585, "loss": 0.4965, "lr": 3.110348974878038e-05, "epoch": 2.6722689075630255, "percentage": 38.17, "elapsed_time": "3:32:25", "remaining_time": "5:44:08"}
{"current_steps": 1755, "total_steps": 4585, "loss": 0.4863, "lr": 3.104008008265888e-05, "epoch": 2.6799083269671504, "percentage": 38.28, "elapsed_time": "3:33:02", "remaining_time": "5:43:31"}
{"current_steps": 1760, "total_steps": 4585, "loss": 0.4809, "lr": 3.09765104043707e-05, "epoch": 2.687547746371276, "percentage": 38.39, "elapsed_time": "3:33:35", "remaining_time": "5:42:49"}
{"current_steps": 1765, "total_steps": 4585, "loss": 0.4641, "lr": 3.0912781635278886e-05, "epoch": 2.695187165775401, "percentage": 38.5, "elapsed_time": "3:34:13", "remaining_time": "5:42:16"}
{"current_steps": 1770, "total_steps": 4585, "loss": 0.507, "lr": 3.0848894699052326e-05, "epoch": 2.702826585179526, "percentage": 38.6, "elapsed_time": "3:34:56", "remaining_time": "5:41:51"}
{"current_steps": 1775, "total_steps": 4585, "loss": 0.4636, "lr": 3.0784850521652336e-05, "epoch": 2.7104660045836515, "percentage": 38.71, "elapsed_time": "3:35:39", "remaining_time": "5:41:24"}
{"current_steps": 1780, "total_steps": 4585, "loss": 0.4696, "lr": 3.072065003131925e-05, "epoch": 2.718105423987777, "percentage": 38.82, "elapsed_time": "3:36:13", "remaining_time": "5:40:44"}
{"current_steps": 1785, "total_steps": 4585, "loss": 0.5542, "lr": 3.0656294158558954e-05, "epoch": 2.7257448433919023, "percentage": 38.93, "elapsed_time": "3:36:51", "remaining_time": "5:40:09"}
{"current_steps": 1790, "total_steps": 4585, "loss": 0.4799, "lr": 3.059178383612941e-05, "epoch": 2.7333842627960276, "percentage": 39.04, "elapsed_time": "3:37:28", "remaining_time": "5:39:34"}
{"current_steps": 1795, "total_steps": 4585, "loss": 0.477, "lr": 3.052711999902715e-05, "epoch": 2.7410236822001526, "percentage": 39.15, "elapsed_time": "3:38:00", "remaining_time": "5:38:50"}
{"current_steps": 1800, "total_steps": 4585, "loss": 0.5119, "lr": 3.0462303584473692e-05, "epoch": 2.748663101604278, "percentage": 39.26, "elapsed_time": "3:38:37", "remaining_time": "5:38:15"}
{"current_steps": 1805, "total_steps": 4585, "loss": 0.4682, "lr": 3.039733553190198e-05, "epoch": 2.7563025210084033, "percentage": 39.37, "elapsed_time": "3:39:20", "remaining_time": "5:37:49"}
{"current_steps": 1810, "total_steps": 4585, "loss": 0.4915, "lr": 3.0332216782942763e-05, "epoch": 2.7639419404125287, "percentage": 39.48, "elapsed_time": "3:39:51", "remaining_time": "5:37:04"}
{"current_steps": 1815, "total_steps": 4585, "loss": 0.4823, "lr": 3.0266948281410943e-05, "epoch": 2.771581359816654, "percentage": 39.59, "elapsed_time": "3:40:26", "remaining_time": "5:36:25"}
{"current_steps": 1820, "total_steps": 4585, "loss": 0.4715, "lr": 3.020153097329189e-05, "epoch": 2.779220779220779, "percentage": 39.69, "elapsed_time": "3:40:56", "remaining_time": "5:35:40"}
{"current_steps": 1825, "total_steps": 4585, "loss": 0.4841, "lr": 3.013596580672777e-05, "epoch": 2.7868601986249044, "percentage": 39.8, "elapsed_time": "3:41:30", "remaining_time": "5:34:59"}
{"current_steps": 1830, "total_steps": 4585, "loss": 0.5067, "lr": 3.0070253732003736e-05, "epoch": 2.79449961802903, "percentage": 39.91, "elapsed_time": "3:42:00", "remaining_time": "5:34:13"}
{"current_steps": 1835, "total_steps": 4585, "loss": 0.5046, "lr": 3.0004395701534208e-05, "epoch": 2.802139037433155, "percentage": 40.02, "elapsed_time": "3:42:38", "remaining_time": "5:33:39"}
{"current_steps": 1840, "total_steps": 4585, "loss": 0.4447, "lr": 2.9938392669849053e-05, "epoch": 2.8097784568372806, "percentage": 40.13, "elapsed_time": "3:43:14", "remaining_time": "5:33:03"}
{"current_steps": 1845, "total_steps": 4585, "loss": 0.494, "lr": 2.9872245593579752e-05, "epoch": 2.8174178762414055, "percentage": 40.24, "elapsed_time": "3:43:54", "remaining_time": "5:32:30"}
{"current_steps": 1850, "total_steps": 4585, "loss": 0.4549, "lr": 2.9805955431445514e-05, "epoch": 2.825057295645531, "percentage": 40.35, "elapsed_time": "3:44:31", "remaining_time": "5:31:56"}
{"current_steps": 1855, "total_steps": 4585, "loss": 0.4566, "lr": 2.973952314423943e-05, "epoch": 2.8326967150496563, "percentage": 40.46, "elapsed_time": "3:45:10", "remaining_time": "5:31:22"}
{"current_steps": 1860, "total_steps": 4585, "loss": 0.4829, "lr": 2.9672949694814485e-05, "epoch": 2.8403361344537816, "percentage": 40.57, "elapsed_time": "3:45:42", "remaining_time": "5:30:40"}
{"current_steps": 1865, "total_steps": 4585, "loss": 0.5093, "lr": 2.9606236048069655e-05, "epoch": 2.847975553857907, "percentage": 40.68, "elapsed_time": "3:46:07", "remaining_time": "5:29:47"}
{"current_steps": 1870, "total_steps": 4585, "loss": 0.5206, "lr": 2.9539383170935888e-05, "epoch": 2.855614973262032, "percentage": 40.79, "elapsed_time": "3:46:36", "remaining_time": "5:29:00"}
{"current_steps": 1875, "total_steps": 4585, "loss": 0.5005, "lr": 2.9472392032362118e-05, "epoch": 2.8632543926661573, "percentage": 40.89, "elapsed_time": "3:47:10", "remaining_time": "5:28:20"}
{"current_steps": 1880, "total_steps": 4585, "loss": 0.5001, "lr": 2.9405263603301185e-05, "epoch": 2.8708938120702827, "percentage": 41.0, "elapsed_time": "3:47:47", "remaining_time": "5:27:45"}
{"current_steps": 1885, "total_steps": 4585, "loss": 0.4851, "lr": 2.93379988566958e-05, "epoch": 2.878533231474408, "percentage": 41.11, "elapsed_time": "3:48:39", "remaining_time": "5:27:30"}
{"current_steps": 1890, "total_steps": 4585, "loss": 0.4948, "lr": 2.9270598767464422e-05, "epoch": 2.8861726508785335, "percentage": 41.22, "elapsed_time": "3:49:17", "remaining_time": "5:26:56"}
{"current_steps": 1895, "total_steps": 4585, "loss": 0.5069, "lr": 2.920306431248712e-05, "epoch": 2.8938120702826584, "percentage": 41.33, "elapsed_time": "3:49:51", "remaining_time": "5:26:17"}
{"current_steps": 1900, "total_steps": 4585, "loss": 0.4846, "lr": 2.9135396470591456e-05, "epoch": 2.901451489686784, "percentage": 41.44, "elapsed_time": "3:50:25", "remaining_time": "5:25:37"}
{"current_steps": 1905, "total_steps": 4585, "loss": 0.5126, "lr": 2.9067596222538234e-05, "epoch": 2.909090909090909, "percentage": 41.55, "elapsed_time": "3:51:01", "remaining_time": "5:25:00"}
{"current_steps": 1910, "total_steps": 4585, "loss": 0.5072, "lr": 2.8999664551007344e-05, "epoch": 2.916730328495034, "percentage": 41.66, "elapsed_time": "3:51:33", "remaining_time": "5:24:18"}
{"current_steps": 1915, "total_steps": 4585, "loss": 0.505, "lr": 2.8931602440583488e-05, "epoch": 2.92436974789916, "percentage": 41.77, "elapsed_time": "3:52:14", "remaining_time": "5:23:48"}
{"current_steps": 1920, "total_steps": 4585, "loss": 0.5075, "lr": 2.8863410877741906e-05, "epoch": 2.932009167303285, "percentage": 41.88, "elapsed_time": "3:52:47", "remaining_time": "5:23:07"}
{"current_steps": 1925, "total_steps": 4585, "loss": 0.5141, "lr": 2.8795090850834113e-05, "epoch": 2.9396485867074102, "percentage": 41.98, "elapsed_time": "3:53:15", "remaining_time": "5:22:19"}
{"current_steps": 1930, "total_steps": 4585, "loss": 0.4939, "lr": 2.8726643350073528e-05, "epoch": 2.9472880061115356, "percentage": 42.09, "elapsed_time": "3:53:50", "remaining_time": "5:21:41"}
{"current_steps": 1935, "total_steps": 4585, "loss": 0.4925, "lr": 2.865806936752115e-05, "epoch": 2.9549274255156606, "percentage": 42.2, "elapsed_time": "3:54:28", "remaining_time": "5:21:07"}
{"current_steps": 1940, "total_steps": 4585, "loss": 0.4893, "lr": 2.8589369897071174e-05, "epoch": 2.962566844919786, "percentage": 42.31, "elapsed_time": "3:55:10", "remaining_time": "5:20:38"}
{"current_steps": 1945, "total_steps": 4585, "loss": 0.5234, "lr": 2.8520545934436602e-05, "epoch": 2.9702062643239113, "percentage": 42.42, "elapsed_time": "3:55:44", "remaining_time": "5:19:59"}
{"current_steps": 1950, "total_steps": 4585, "loss": 0.4762, "lr": 2.845159847713477e-05, "epoch": 2.9778456837280367, "percentage": 42.53, "elapsed_time": "3:56:15", "remaining_time": "5:19:15"}
{"current_steps": 1955, "total_steps": 4585, "loss": 0.479, "lr": 2.8382528524472916e-05, "epoch": 2.985485103132162, "percentage": 42.64, "elapsed_time": "3:56:56", "remaining_time": "5:18:44"}
{"current_steps": 1960, "total_steps": 4585, "loss": 0.5213, "lr": 2.831333707753372e-05, "epoch": 2.993124522536287, "percentage": 42.75, "elapsed_time": "3:57:27", "remaining_time": "5:18:01"}
{"current_steps": 1965, "total_steps": 4585, "loss": 0.4668, "lr": 2.8244025139160745e-05, "epoch": 3.0, "percentage": 42.86, "elapsed_time": "3:58:00", "remaining_time": "5:17:20"}
{"current_steps": 1970, "total_steps": 4585, "loss": 0.4627, "lr": 2.8174593713943933e-05, "epoch": 3.0076394194041254, "percentage": 42.97, "elapsed_time": "3:58:32", "remaining_time": "5:16:38"}
{"current_steps": 1975, "total_steps": 4585, "loss": 0.4775, "lr": 2.8105043808205042e-05, "epoch": 3.0152788388082508, "percentage": 43.08, "elapsed_time": "3:59:12", "remaining_time": "5:16:07"}
{"current_steps": 1980, "total_steps": 4585, "loss": 0.4444, "lr": 2.803537642998307e-05, "epoch": 3.0229182582123757, "percentage": 43.18, "elapsed_time": "3:59:41", "remaining_time": "5:15:21"}
{"current_steps": 1985, "total_steps": 4585, "loss": 0.462, "lr": 2.79655925890196e-05, "epoch": 3.030557677616501, "percentage": 43.29, "elapsed_time": "4:00:22", "remaining_time": "5:14:51"}
{"current_steps": 1990, "total_steps": 4585, "loss": 0.4743, "lr": 2.789569329674422e-05, "epoch": 3.0381970970206265, "percentage": 43.4, "elapsed_time": "4:00:55", "remaining_time": "5:14:10"}
{"current_steps": 1995, "total_steps": 4585, "loss": 0.4322, "lr": 2.7825679566259834e-05, "epoch": 3.045836516424752, "percentage": 43.51, "elapsed_time": "4:01:33", "remaining_time": "5:13:36"}
{"current_steps": 2000, "total_steps": 4585, "loss": 0.5, "lr": 2.7755552412327996e-05, "epoch": 3.053475935828877, "percentage": 43.62, "elapsed_time": "4:02:03", "remaining_time": "5:12:51"}
{"current_steps": 2005, "total_steps": 4585, "loss": 0.433, "lr": 2.768531285135417e-05, "epoch": 3.061115355233002, "percentage": 43.73, "elapsed_time": "4:02:38", "remaining_time": "5:12:14"}
{"current_steps": 2010, "total_steps": 4585, "loss": 0.446, "lr": 2.7614961901373027e-05, "epoch": 3.0687547746371275, "percentage": 43.84, "elapsed_time": "4:03:22", "remaining_time": "5:11:46"}
{"current_steps": 2015, "total_steps": 4585, "loss": 0.4686, "lr": 2.7544500582033706e-05, "epoch": 3.076394194041253, "percentage": 43.95, "elapsed_time": "4:03:59", "remaining_time": "5:11:12"}
{"current_steps": 2020, "total_steps": 4585, "loss": 0.4463, "lr": 2.7473929914584977e-05, "epoch": 3.0840336134453783, "percentage": 44.06, "elapsed_time": "4:04:33", "remaining_time": "5:10:33"}
{"current_steps": 2025, "total_steps": 4585, "loss": 0.453, "lr": 2.7403250921860497e-05, "epoch": 3.0916730328495032, "percentage": 44.17, "elapsed_time": "4:05:09", "remaining_time": "5:09:56"}
{"current_steps": 2030, "total_steps": 4585, "loss": 0.4718, "lr": 2.7332464628263945e-05, "epoch": 3.0993124522536286, "percentage": 44.27, "elapsed_time": "4:05:40", "remaining_time": "5:09:13"}
{"current_steps": 2035, "total_steps": 4585, "loss": 0.4698, "lr": 2.7261572059754217e-05, "epoch": 3.106951871657754, "percentage": 44.38, "elapsed_time": "4:06:08", "remaining_time": "5:08:25"}
{"current_steps": 2040, "total_steps": 4585, "loss": 0.4708, "lr": 2.7190574243830505e-05, "epoch": 3.1145912910618794, "percentage": 44.49, "elapsed_time": "4:06:49", "remaining_time": "5:07:55"}
{"current_steps": 2045, "total_steps": 4585, "loss": 0.4434, "lr": 2.7119472209517442e-05, "epoch": 3.1222307104660048, "percentage": 44.6, "elapsed_time": "4:07:20", "remaining_time": "5:07:13"}
{"current_steps": 2050, "total_steps": 4585, "loss": 0.4766, "lr": 2.7048266987350183e-05, "epoch": 3.1298701298701297, "percentage": 44.71, "elapsed_time": "4:07:52", "remaining_time": "5:06:30"}
{"current_steps": 2055, "total_steps": 4585, "loss": 0.4393, "lr": 2.6976959609359447e-05, "epoch": 3.137509549274255, "percentage": 44.82, "elapsed_time": "4:08:27", "remaining_time": "5:05:53"}
{"current_steps": 2060, "total_steps": 4585, "loss": 0.4505, "lr": 2.6905551109056598e-05, "epoch": 3.1451489686783805, "percentage": 44.93, "elapsed_time": "4:09:00", "remaining_time": "5:05:12"}
{"current_steps": 2065, "total_steps": 4585, "loss": 0.4618, "lr": 2.6834042521418604e-05, "epoch": 3.152788388082506, "percentage": 45.04, "elapsed_time": "4:09:41", "remaining_time": "5:04:41"}
{"current_steps": 2070, "total_steps": 4585, "loss": 0.4114, "lr": 2.6762434882873116e-05, "epoch": 3.160427807486631, "percentage": 45.15, "elapsed_time": "4:10:19", "remaining_time": "5:04:08"}
{"current_steps": 2075, "total_steps": 4585, "loss": 0.4752, "lr": 2.6690729231283374e-05, "epoch": 3.168067226890756, "percentage": 45.26, "elapsed_time": "4:10:59", "remaining_time": "5:03:36"}
{"current_steps": 2080, "total_steps": 4585, "loss": 0.4793, "lr": 2.66189266059332e-05, "epoch": 3.1757066462948815, "percentage": 45.37, "elapsed_time": "4:11:30", "remaining_time": "5:02:53"}
{"current_steps": 2085, "total_steps": 4585, "loss": 0.4558, "lr": 2.6547028047511943e-05, "epoch": 3.183346065699007, "percentage": 45.47, "elapsed_time": "4:12:02", "remaining_time": "5:02:12"}
{"current_steps": 2090, "total_steps": 4585, "loss": 0.4833, "lr": 2.6475034598099372e-05, "epoch": 3.1909854851031323, "percentage": 45.58, "elapsed_time": "4:12:35", "remaining_time": "5:01:32"}
{"current_steps": 2095, "total_steps": 4585, "loss": 0.4655, "lr": 2.6402947301150583e-05, "epoch": 3.1986249045072572, "percentage": 45.69, "elapsed_time": "4:13:14", "remaining_time": "5:00:59"}
{"current_steps": 2100, "total_steps": 4585, "loss": 0.4547, "lr": 2.6330767201480873e-05, "epoch": 3.2062643239113826, "percentage": 45.8, "elapsed_time": "4:13:52", "remaining_time": "5:00:24"}
{"current_steps": 2105, "total_steps": 4585, "loss": 0.4367, "lr": 2.62584953452506e-05, "epoch": 3.213903743315508, "percentage": 45.91, "elapsed_time": "4:14:24", "remaining_time": "4:59:43"}
{"current_steps": 2110, "total_steps": 4585, "loss": 0.4772, "lr": 2.6186132779950022e-05, "epoch": 3.2215431627196334, "percentage": 46.02, "elapsed_time": "4:14:58", "remaining_time": "4:59:04"}
{"current_steps": 2115, "total_steps": 4585, "loss": 0.4602, "lr": 2.6113680554384107e-05, "epoch": 3.2291825821237587, "percentage": 46.13, "elapsed_time": "4:15:26", "remaining_time": "4:58:18"}
{"current_steps": 2120, "total_steps": 4585, "loss": 0.4383, "lr": 2.604113971865734e-05, "epoch": 3.2368220015278837, "percentage": 46.24, "elapsed_time": "4:16:01", "remaining_time": "4:57:40"}
{"current_steps": 2125, "total_steps": 4585, "loss": 0.463, "lr": 2.59685113241585e-05, "epoch": 3.244461420932009, "percentage": 46.35, "elapsed_time": "4:16:30", "remaining_time": "4:56:56"}
{"current_steps": 2130, "total_steps": 4585, "loss": 0.461, "lr": 2.5895796423545418e-05, "epoch": 3.2521008403361344, "percentage": 46.46, "elapsed_time": "4:17:07", "remaining_time": "4:56:21"}
{"current_steps": 2135, "total_steps": 4585, "loss": 0.4546, "lr": 2.5822996070729723e-05, "epoch": 3.25974025974026, "percentage": 46.56, "elapsed_time": "4:17:32", "remaining_time": "4:55:32"}
{"current_steps": 2140, "total_steps": 4585, "loss": 0.4528, "lr": 2.575011132086157e-05, "epoch": 3.267379679144385, "percentage": 46.67, "elapsed_time": "4:18:12", "remaining_time": "4:55:01"}
{"current_steps": 2145, "total_steps": 4585, "loss": 0.4391, "lr": 2.567714323031434e-05, "epoch": 3.27501909854851, "percentage": 46.78, "elapsed_time": "4:18:48", "remaining_time": "4:54:24"}
{"current_steps": 2150, "total_steps": 4585, "loss": 0.4654, "lr": 2.560409285666933e-05, "epoch": 3.2826585179526355, "percentage": 46.89, "elapsed_time": "4:19:19", "remaining_time": "4:53:42"}
{"current_steps": 2155, "total_steps": 4585, "loss": 0.4053, "lr": 2.5530961258700444e-05, "epoch": 3.290297937356761, "percentage": 47.0, "elapsed_time": "4:19:56", "remaining_time": "4:53:06"}
{"current_steps": 2160, "total_steps": 4585, "loss": 0.4473, "lr": 2.545774949635881e-05, "epoch": 3.2979373567608863, "percentage": 47.11, "elapsed_time": "4:20:32", "remaining_time": "4:52:30"}
{"current_steps": 2165, "total_steps": 4585, "loss": 0.459, "lr": 2.5384458630757456e-05, "epoch": 3.3055767761650117, "percentage": 47.22, "elapsed_time": "4:21:01", "remaining_time": "4:51:46"}
{"current_steps": 2170, "total_steps": 4585, "loss": 0.4592, "lr": 2.5311089724155896e-05, "epoch": 3.3132161955691366, "percentage": 47.33, "elapsed_time": "4:21:37", "remaining_time": "4:51:09"}
{"current_steps": 2175, "total_steps": 4585, "loss": 0.4614, "lr": 2.5237643839944774e-05, "epoch": 3.320855614973262, "percentage": 47.44, "elapsed_time": "4:22:19", "remaining_time": "4:50:40"}
{"current_steps": 2180, "total_steps": 4585, "loss": 0.4579, "lr": 2.5164122042630405e-05, "epoch": 3.3284950343773874, "percentage": 47.55, "elapsed_time": "4:22:54", "remaining_time": "4:50:03"}
{"current_steps": 2185, "total_steps": 4585, "loss": 0.4325, "lr": 2.509052539781937e-05, "epoch": 3.3361344537815127, "percentage": 47.66, "elapsed_time": "4:23:27", "remaining_time": "4:49:22"}
{"current_steps": 2190, "total_steps": 4585, "loss": 0.4945, "lr": 2.5016854972203094e-05, "epoch": 3.343773873185638, "percentage": 47.76, "elapsed_time": "4:24:10", "remaining_time": "4:48:53"}
{"current_steps": 2195, "total_steps": 4585, "loss": 0.4724, "lr": 2.4943111833542333e-05, "epoch": 3.351413292589763, "percentage": 47.87, "elapsed_time": "4:24:43", "remaining_time": "4:48:14"}
{"current_steps": 2200, "total_steps": 4585, "loss": 0.4782, "lr": 2.4869297050651765e-05, "epoch": 3.3590527119938884, "percentage": 47.98, "elapsed_time": "4:25:19", "remaining_time": "4:47:38"}
{"current_steps": 2205, "total_steps": 4585, "loss": 0.474, "lr": 2.479541169338442e-05, "epoch": 3.366692131398014, "percentage": 48.09, "elapsed_time": "4:26:01", "remaining_time": "4:47:08"}
{"current_steps": 2210, "total_steps": 4585, "loss": 0.5287, "lr": 2.4721456832616247e-05, "epoch": 3.374331550802139, "percentage": 48.2, "elapsed_time": "4:26:38", "remaining_time": "4:46:32"}
{"current_steps": 2215, "total_steps": 4585, "loss": 0.4516, "lr": 2.4647433540230547e-05, "epoch": 3.381970970206264, "percentage": 48.31, "elapsed_time": "4:27:25", "remaining_time": "4:46:08"}
{"current_steps": 2220, "total_steps": 4585, "loss": 0.4694, "lr": 2.4573342889102443e-05, "epoch": 3.3896103896103895, "percentage": 48.42, "elapsed_time": "4:28:10", "remaining_time": "4:45:41"}
{"current_steps": 2225, "total_steps": 4585, "loss": 0.4493, "lr": 2.4499185953083363e-05, "epoch": 3.397249809014515, "percentage": 48.53, "elapsed_time": "4:28:47", "remaining_time": "4:45:05"}
{"current_steps": 2230, "total_steps": 4585, "loss": 0.4948, "lr": 2.4424963806985432e-05, "epoch": 3.4048892284186403, "percentage": 48.64, "elapsed_time": "4:29:21", "remaining_time": "4:44:27"}
{"current_steps": 2235, "total_steps": 4585, "loss": 0.4442, "lr": 2.4350677526565934e-05, "epoch": 3.4125286478227657, "percentage": 48.75, "elapsed_time": "4:29:58", "remaining_time": "4:43:51"}
{"current_steps": 2240, "total_steps": 4585, "loss": 0.4853, "lr": 2.427632818851166e-05, "epoch": 3.4201680672268906, "percentage": 48.85, "elapsed_time": "4:30:30", "remaining_time": "4:43:11"}
{"current_steps": 2245, "total_steps": 4585, "loss": 0.4965, "lr": 2.4201916870423393e-05, "epoch": 3.427807486631016, "percentage": 48.96, "elapsed_time": "4:31:01", "remaining_time": "4:42:30"}
{"current_steps": 2250, "total_steps": 4585, "loss": 0.4842, "lr": 2.4127444650800203e-05, "epoch": 3.4354469060351414, "percentage": 49.07, "elapsed_time": "4:31:34", "remaining_time": "4:41:49"}
{"current_steps": 2255, "total_steps": 4585, "loss": 0.4814, "lr": 2.405291260902387e-05, "epoch": 3.4430863254392667, "percentage": 49.18, "elapsed_time": "4:32:06", "remaining_time": "4:41:09"}
{"current_steps": 2260, "total_steps": 4585, "loss": 0.4655, "lr": 2.3978321825343206e-05, "epoch": 3.4507257448433917, "percentage": 49.29, "elapsed_time": "4:32:50", "remaining_time": "4:40:41"}
{"current_steps": 2265, "total_steps": 4585, "loss": 0.4542, "lr": 2.390367338085843e-05, "epoch": 3.458365164247517, "percentage": 49.4, "elapsed_time": "4:33:19", "remaining_time": "4:39:57"}
{"current_steps": 2270, "total_steps": 4585, "loss": 0.4334, "lr": 2.382896835750547e-05, "epoch": 3.4660045836516424, "percentage": 49.51, "elapsed_time": "4:33:58", "remaining_time": "4:39:24"}
{"current_steps": 2275, "total_steps": 4585, "loss": 0.4482, "lr": 2.3754207838040296e-05, "epoch": 3.473644003055768, "percentage": 49.62, "elapsed_time": "4:34:37", "remaining_time": "4:38:50"}
{"current_steps": 2280, "total_steps": 4585, "loss": 0.4817, "lr": 2.367939290602324e-05, "epoch": 3.481283422459893, "percentage": 49.73, "elapsed_time": "4:35:20", "remaining_time": "4:38:21"}
{"current_steps": 2285, "total_steps": 4585, "loss": 0.4778, "lr": 2.360452464580326e-05, "epoch": 3.488922841864018, "percentage": 49.84, "elapsed_time": "4:35:54", "remaining_time": "4:37:43"}
{"current_steps": 2290, "total_steps": 4585, "loss": 0.4631, "lr": 2.352960414250223e-05, "epoch": 3.4965622612681435, "percentage": 49.95, "elapsed_time": "4:36:27", "remaining_time": "4:37:03"}
{"current_steps": 2295, "total_steps": 4585, "loss": 0.4822, "lr": 2.345463248199925e-05, "epoch": 3.504201680672269, "percentage": 50.05, "elapsed_time": "4:37:09", "remaining_time": "4:36:32"}
{"current_steps": 2300, "total_steps": 4585, "loss": 0.4335, "lr": 2.337961075091486e-05, "epoch": 3.5118411000763943, "percentage": 50.16, "elapsed_time": "4:37:53", "remaining_time": "4:36:05"}
{"current_steps": 2305, "total_steps": 4585, "loss": 0.4776, "lr": 2.3304540036595313e-05, "epoch": 3.5194805194805197, "percentage": 50.27, "elapsed_time": "4:38:22", "remaining_time": "4:35:21"}
{"current_steps": 2310, "total_steps": 4585, "loss": 0.4637, "lr": 2.322942142709682e-05, "epoch": 3.5271199388846446, "percentage": 50.38, "elapsed_time": "4:38:58", "remaining_time": "4:34:45"}
{"current_steps": 2315, "total_steps": 4585, "loss": 0.4551, "lr": 2.3154256011169758e-05, "epoch": 3.53475935828877, "percentage": 50.49, "elapsed_time": "4:39:31", "remaining_time": "4:34:05"}
{"current_steps": 2320, "total_steps": 4585, "loss": 0.4654, "lr": 2.3079044878242934e-05, "epoch": 3.5423987776928954, "percentage": 50.6, "elapsed_time": "4:40:09", "remaining_time": "4:33:30"}
{"current_steps": 2325, "total_steps": 4585, "loss": 0.439, "lr": 2.300378911840773e-05, "epoch": 3.5500381970970207, "percentage": 50.71, "elapsed_time": "4:40:40", "remaining_time": "4:32:49"}
{"current_steps": 2330, "total_steps": 4585, "loss": 0.4712, "lr": 2.2928489822402363e-05, "epoch": 3.557677616501146, "percentage": 50.82, "elapsed_time": "4:41:17", "remaining_time": "4:32:14"}
{"current_steps": 2335, "total_steps": 4585, "loss": 0.4488, "lr": 2.285314808159604e-05, "epoch": 3.565317035905271, "percentage": 50.93, "elapsed_time": "4:41:45", "remaining_time": "4:31:30"}
{"current_steps": 2340, "total_steps": 4585, "loss": 0.4621, "lr": 2.2777764987973167e-05, "epoch": 3.5729564553093964, "percentage": 51.04, "elapsed_time": "4:42:24", "remaining_time": "4:30:56"}
{"current_steps": 2345, "total_steps": 4585, "loss": 0.4665, "lr": 2.2702341634117487e-05, "epoch": 3.580595874713522, "percentage": 51.15, "elapsed_time": "4:43:02", "remaining_time": "4:30:21"}
{"current_steps": 2350, "total_steps": 4585, "loss": 0.4541, "lr": 2.262687911319628e-05, "epoch": 3.588235294117647, "percentage": 51.25, "elapsed_time": "4:43:41", "remaining_time": "4:29:48"}
{"current_steps": 2355, "total_steps": 4585, "loss": 0.4519, "lr": 2.2551378518944505e-05, "epoch": 3.5958747135217726, "percentage": 51.36, "elapsed_time": "4:44:13", "remaining_time": "4:29:08"}
{"current_steps": 2360, "total_steps": 4585, "loss": 0.4157, "lr": 2.247584094564894e-05, "epoch": 3.6035141329258975, "percentage": 51.47, "elapsed_time": "4:44:47", "remaining_time": "4:28:30"}
{"current_steps": 2365, "total_steps": 4585, "loss": 0.4754, "lr": 2.240026748813232e-05, "epoch": 3.611153552330023, "percentage": 51.58, "elapsed_time": "4:45:23", "remaining_time": "4:27:53"}
{"current_steps": 2370, "total_steps": 4585, "loss": 0.4702, "lr": 2.2324659241737495e-05, "epoch": 3.6187929717341483, "percentage": 51.69, "elapsed_time": "4:46:02", "remaining_time": "4:27:19"}
{"current_steps": 2375, "total_steps": 4585, "loss": 0.4511, "lr": 2.2249017302311527e-05, "epoch": 3.6264323911382736, "percentage": 51.8, "elapsed_time": "4:46:30", "remaining_time": "4:26:35"}
{"current_steps": 2380, "total_steps": 4585, "loss": 0.4597, "lr": 2.2173342766189803e-05, "epoch": 3.634071810542399, "percentage": 51.91, "elapsed_time": "4:47:06", "remaining_time": "4:25:59"}
{"current_steps": 2385, "total_steps": 4585, "loss": 0.4803, "lr": 2.209763673018019e-05, "epoch": 3.641711229946524, "percentage": 52.02, "elapsed_time": "4:47:40", "remaining_time": "4:25:21"}
{"current_steps": 2390, "total_steps": 4585, "loss": 0.4427, "lr": 2.202190029154708e-05, "epoch": 3.6493506493506493, "percentage": 52.13, "elapsed_time": "4:48:14", "remaining_time": "4:24:43"}
{"current_steps": 2395, "total_steps": 4585, "loss": 0.4577, "lr": 2.1946134547995524e-05, "epoch": 3.6569900687547747, "percentage": 52.24, "elapsed_time": "4:48:53", "remaining_time": "4:24:09"}
{"current_steps": 2400, "total_steps": 4585, "loss": 0.4405, "lr": 2.1870340597655303e-05, "epoch": 3.6646294881588997, "percentage": 52.34, "elapsed_time": "4:49:33", "remaining_time": "4:23:36"}
{"current_steps": 2405, "total_steps": 4585, "loss": 0.449, "lr": 2.1794519539065037e-05, "epoch": 3.6722689075630255, "percentage": 52.45, "elapsed_time": "4:50:06", "remaining_time": "4:22:57"}
{"current_steps": 2410, "total_steps": 4585, "loss": 0.4624, "lr": 2.171867247115622e-05, "epoch": 3.6799083269671504, "percentage": 52.56, "elapsed_time": "4:50:39", "remaining_time": "4:22:18"}
{"current_steps": 2415, "total_steps": 4585, "loss": 0.4353, "lr": 2.1642800493237343e-05, "epoch": 3.687547746371276, "percentage": 52.67, "elapsed_time": "4:51:19", "remaining_time": "4:21:45"}
{"current_steps": 2420, "total_steps": 4585, "loss": 0.4741, "lr": 2.1566904704977925e-05, "epoch": 3.695187165775401, "percentage": 52.78, "elapsed_time": "4:51:52", "remaining_time": "4:21:07"}
{"current_steps": 2425, "total_steps": 4585, "loss": 0.4841, "lr": 2.1490986206392598e-05, "epoch": 3.702826585179526, "percentage": 52.89, "elapsed_time": "4:52:27", "remaining_time": "4:20:29"}
{"current_steps": 2430, "total_steps": 4585, "loss": 0.4792, "lr": 2.1415046097825126e-05, "epoch": 3.7104660045836515, "percentage": 53.0, "elapsed_time": "4:52:57", "remaining_time": "4:19:48"}
{"current_steps": 2435, "total_steps": 4585, "loss": 0.5025, "lr": 2.1339085479932503e-05, "epoch": 3.718105423987777, "percentage": 53.11, "elapsed_time": "4:53:32", "remaining_time": "4:19:11"}
{"current_steps": 2440, "total_steps": 4585, "loss": 0.4922, "lr": 2.1263105453668987e-05, "epoch": 3.7257448433919023, "percentage": 53.22, "elapsed_time": "4:54:07", "remaining_time": "4:18:33"}
{"current_steps": 2445, "total_steps": 4585, "loss": 0.4759, "lr": 2.1187107120270115e-05, "epoch": 3.7333842627960276, "percentage": 53.33, "elapsed_time": "4:54:43", "remaining_time": "4:17:57"}
{"current_steps": 2450, "total_steps": 4585, "loss": 0.453, "lr": 2.1111091581236764e-05, "epoch": 3.7410236822001526, "percentage": 53.44, "elapsed_time": "4:55:06", "remaining_time": "4:17:09"}
{"current_steps": 2455, "total_steps": 4585, "loss": 0.4407, "lr": 2.1035059938319212e-05, "epoch": 3.748663101604278, "percentage": 53.54, "elapsed_time": "4:55:46", "remaining_time": "4:16:36"}
{"current_steps": 2460, "total_steps": 4585, "loss": 0.4533, "lr": 2.0959013293501117e-05, "epoch": 3.7563025210084033, "percentage": 53.65, "elapsed_time": "4:56:21", "remaining_time": "4:15:59"}
{"current_steps": 2465, "total_steps": 4585, "loss": 0.4877, "lr": 2.0882952748983586e-05, "epoch": 3.7639419404125287, "percentage": 53.76, "elapsed_time": "4:56:58", "remaining_time": "4:15:24"}
{"current_steps": 2470, "total_steps": 4585, "loss": 0.445, "lr": 2.080687940716916e-05, "epoch": 3.771581359816654, "percentage": 53.87, "elapsed_time": "4:57:33", "remaining_time": "4:14:47"}
{"current_steps": 2475, "total_steps": 4585, "loss": 0.4462, "lr": 2.0730794370645895e-05, "epoch": 3.779220779220779, "percentage": 53.98, "elapsed_time": "4:58:22", "remaining_time": "4:14:22"}
{"current_steps": 2480, "total_steps": 4585, "loss": 0.4215, "lr": 2.0654698742171324e-05, "epoch": 3.7868601986249044, "percentage": 54.09, "elapsed_time": "4:59:00", "remaining_time": "4:13:48"}
{"current_steps": 2485, "total_steps": 4585, "loss": 0.4614, "lr": 2.05785936246565e-05, "epoch": 3.79449961802903, "percentage": 54.2, "elapsed_time": "4:59:40", "remaining_time": "4:13:15"}
{"current_steps": 2490, "total_steps": 4585, "loss": 0.4291, "lr": 2.050248012115001e-05, "epoch": 3.802139037433155, "percentage": 54.31, "elapsed_time": "5:00:15", "remaining_time": "4:12:37"}
{"current_steps": 2495, "total_steps": 4585, "loss": 0.453, "lr": 2.0426359334822e-05, "epoch": 3.8097784568372806, "percentage": 54.42, "elapsed_time": "5:00:51", "remaining_time": "4:12:01"}
{"current_steps": 2500, "total_steps": 4585, "loss": 0.4673, "lr": 2.035023236894815e-05, "epoch": 3.8174178762414055, "percentage": 54.53, "elapsed_time": "5:01:28", "remaining_time": "4:11:25"}
{"current_steps": 2505, "total_steps": 4585, "loss": 0.4696, "lr": 2.0274100326893707e-05, "epoch": 3.825057295645531, "percentage": 54.63, "elapsed_time": "5:02:08", "remaining_time": "4:10:52"}
{"current_steps": 2510, "total_steps": 4585, "loss": 0.4553, "lr": 2.0197964312097506e-05, "epoch": 3.8326967150496563, "percentage": 54.74, "elapsed_time": "5:02:45", "remaining_time": "4:10:17"}
{"current_steps": 2515, "total_steps": 4585, "loss": 0.4693, "lr": 2.012182542805595e-05, "epoch": 3.8403361344537816, "percentage": 54.85, "elapsed_time": "5:03:27", "remaining_time": "4:09:45"}
{"current_steps": 2520, "total_steps": 4585, "loss": 0.4698, "lr": 2.004568477830703e-05, "epoch": 3.847975553857907, "percentage": 54.96, "elapsed_time": "5:04:03", "remaining_time": "4:09:09"}
{"current_steps": 2525, "total_steps": 4585, "loss": 0.4457, "lr": 1.9969543466414322e-05, "epoch": 3.855614973262032, "percentage": 55.07, "elapsed_time": "5:04:49", "remaining_time": "4:08:41"}
{"current_steps": 2530, "total_steps": 4585, "loss": 0.4726, "lr": 1.989340259595102e-05, "epoch": 3.8632543926661573, "percentage": 55.18, "elapsed_time": "5:05:26", "remaining_time": "4:08:05"}
{"current_steps": 2535, "total_steps": 4585, "loss": 0.4556, "lr": 1.9817263270483905e-05, "epoch": 3.8708938120702827, "percentage": 55.29, "elapsed_time": "5:06:08", "remaining_time": "4:07:34"}
{"current_steps": 2540, "total_steps": 4585, "loss": 0.4348, "lr": 1.9741126593557353e-05, "epoch": 3.878533231474408, "percentage": 55.4, "elapsed_time": "5:06:38", "remaining_time": "4:06:53"}
{"current_steps": 2545, "total_steps": 4585, "loss": 0.4539, "lr": 1.9664993668677387e-05, "epoch": 3.8861726508785335, "percentage": 55.51, "elapsed_time": "5:07:20", "remaining_time": "4:06:21"}
{"current_steps": 2550, "total_steps": 4585, "loss": 0.4467, "lr": 1.958886559929561e-05, "epoch": 3.8938120702826584, "percentage": 55.62, "elapsed_time": "5:08:01", "remaining_time": "4:05:48"}
{"current_steps": 2555, "total_steps": 4585, "loss": 0.4512, "lr": 1.9512743488793272e-05, "epoch": 3.901451489686784, "percentage": 55.73, "elapsed_time": "5:08:34", "remaining_time": "4:05:10"}
{"current_steps": 2560, "total_steps": 4585, "loss": 0.4673, "lr": 1.9436628440465267e-05, "epoch": 3.909090909090909, "percentage": 55.83, "elapsed_time": "5:09:08", "remaining_time": "4:04:31"}
{"current_steps": 2565, "total_steps": 4585, "loss": 0.435, "lr": 1.9360521557504102e-05, "epoch": 3.916730328495034, "percentage": 55.94, "elapsed_time": "5:09:31", "remaining_time": "4:03:45"}
{"current_steps": 2570, "total_steps": 4585, "loss": 0.4702, "lr": 1.928442394298397e-05, "epoch": 3.92436974789916, "percentage": 56.05, "elapsed_time": "5:10:00", "remaining_time": "4:03:03"}
{"current_steps": 2575, "total_steps": 4585, "loss": 0.4621, "lr": 1.9208336699844695e-05, "epoch": 3.932009167303285, "percentage": 56.16, "elapsed_time": "5:10:36", "remaining_time": "4:02:27"}
{"current_steps": 2580, "total_steps": 4585, "loss": 0.5097, "lr": 1.913226093087581e-05, "epoch": 3.9396485867074102, "percentage": 56.27, "elapsed_time": "5:11:17", "remaining_time": "4:01:54"}
{"current_steps": 2585, "total_steps": 4585, "loss": 0.4846, "lr": 1.905619773870052e-05, "epoch": 3.9472880061115356, "percentage": 56.38, "elapsed_time": "5:11:48", "remaining_time": "4:01:14"}
{"current_steps": 2590, "total_steps": 4585, "loss": 0.4482, "lr": 1.898014822575977e-05, "epoch": 3.9549274255156606, "percentage": 56.49, "elapsed_time": "5:12:16", "remaining_time": "4:00:32"}
{"current_steps": 2595, "total_steps": 4585, "loss": 0.4633, "lr": 1.890411349429623e-05, "epoch": 3.962566844919786, "percentage": 56.6, "elapsed_time": "5:12:58", "remaining_time": "4:00:00"}
{"current_steps": 2600, "total_steps": 4585, "loss": 0.4755, "lr": 1.8828094646338323e-05, "epoch": 3.9702062643239113, "percentage": 56.71, "elapsed_time": "5:13:27", "remaining_time": "3:59:18"}
{"current_steps": 2605, "total_steps": 4585, "loss": 0.4247, "lr": 1.875209278368428e-05, "epoch": 3.9778456837280367, "percentage": 56.82, "elapsed_time": "5:14:03", "remaining_time": "3:58:42"}
{"current_steps": 2610, "total_steps": 4585, "loss": 0.4601, "lr": 1.867610900788612e-05, "epoch": 3.985485103132162, "percentage": 56.92, "elapsed_time": "5:14:34", "remaining_time": "3:58:02"}
{"current_steps": 2615, "total_steps": 4585, "loss": 0.4532, "lr": 1.8600144420233752e-05, "epoch": 3.993124522536287, "percentage": 57.03, "elapsed_time": "5:15:01", "remaining_time": "3:57:19"}
{"current_steps": 2620, "total_steps": 4585, "loss": 0.492, "lr": 1.8524200121738948e-05, "epoch": 4.0, "percentage": 57.14, "elapsed_time": "5:15:33", "remaining_time": "3:56:39"}
{"current_steps": 2625, "total_steps": 4585, "loss": 0.4482, "lr": 1.844827721311943e-05, "epoch": 4.007639419404125, "percentage": 57.25, "elapsed_time": "5:16:08", "remaining_time": "3:56:03"}
{"current_steps": 2630, "total_steps": 4585, "loss": 0.4226, "lr": 1.83723767947829e-05, "epoch": 4.015278838808251, "percentage": 57.36, "elapsed_time": "5:16:45", "remaining_time": "3:55:27"}
{"current_steps": 2635, "total_steps": 4585, "loss": 0.4452, "lr": 1.829649996681108e-05, "epoch": 4.022918258212376, "percentage": 57.47, "elapsed_time": "5:17:17", "remaining_time": "3:54:48"}
{"current_steps": 2640, "total_steps": 4585, "loss": 0.419, "lr": 1.8220647828943798e-05, "epoch": 4.0305576776165015, "percentage": 57.58, "elapsed_time": "5:17:46", "remaining_time": "3:54:07"}
{"current_steps": 2645, "total_steps": 4585, "loss": 0.4246, "lr": 1.8144821480563004e-05, "epoch": 4.0381970970206265, "percentage": 57.69, "elapsed_time": "5:18:20", "remaining_time": "3:53:29"}
{"current_steps": 2650, "total_steps": 4585, "loss": 0.4329, "lr": 1.8069022020676883e-05, "epoch": 4.045836516424751, "percentage": 57.8, "elapsed_time": "5:18:51", "remaining_time": "3:52:49"}
{"current_steps": 2655, "total_steps": 4585, "loss": 0.4365, "lr": 1.7993250547903898e-05, "epoch": 4.053475935828877, "percentage": 57.91, "elapsed_time": "5:19:32", "remaining_time": "3:52:16"}
{"current_steps": 2660, "total_steps": 4585, "loss": 0.4409, "lr": 1.791750816045687e-05, "epoch": 4.061115355233002, "percentage": 58.02, "elapsed_time": "5:20:07", "remaining_time": "3:51:40"}
{"current_steps": 2665, "total_steps": 4585, "loss": 0.4164, "lr": 1.7841795956127076e-05, "epoch": 4.068754774637128, "percentage": 58.12, "elapsed_time": "5:20:44", "remaining_time": "3:51:04"}
{"current_steps": 2670, "total_steps": 4585, "loss": 0.4106, "lr": 1.7766115032268313e-05, "epoch": 4.076394194041253, "percentage": 58.23, "elapsed_time": "5:21:16", "remaining_time": "3:50:25"}
{"current_steps": 2675, "total_steps": 4585, "loss": 0.4538, "lr": 1.769046648578102e-05, "epoch": 4.084033613445378, "percentage": 58.34, "elapsed_time": "5:21:54", "remaining_time": "3:49:50"}
{"current_steps": 2680, "total_steps": 4585, "loss": 0.4423, "lr": 1.7614851413096338e-05, "epoch": 4.091673032849504, "percentage": 58.45, "elapsed_time": "5:22:26", "remaining_time": "3:49:11"}
{"current_steps": 2685, "total_steps": 4585, "loss": 0.423, "lr": 1.753927091016029e-05, "epoch": 4.099312452253629, "percentage": 58.56, "elapsed_time": "5:22:55", "remaining_time": "3:48:30"}
{"current_steps": 2690, "total_steps": 4585, "loss": 0.4761, "lr": 1.746372607241782e-05, "epoch": 4.106951871657754, "percentage": 58.67, "elapsed_time": "5:23:30", "remaining_time": "3:47:53"}
{"current_steps": 2695, "total_steps": 4585, "loss": 0.4312, "lr": 1.738821799479696e-05, "epoch": 4.114591291061879, "percentage": 58.78, "elapsed_time": "5:24:04", "remaining_time": "3:47:16"}
{"current_steps": 2700, "total_steps": 4585, "loss": 0.4277, "lr": 1.731274777169296e-05, "epoch": 4.122230710466004, "percentage": 58.89, "elapsed_time": "5:24:31", "remaining_time": "3:46:33"}
{"current_steps": 2705, "total_steps": 4585, "loss": 0.4449, "lr": 1.72373164969524e-05, "epoch": 4.12987012987013, "percentage": 59.0, "elapsed_time": "5:25:03", "remaining_time": "3:45:54"}
{"current_steps": 2710, "total_steps": 4585, "loss": 0.4402, "lr": 1.7161925263857367e-05, "epoch": 4.137509549274255, "percentage": 59.11, "elapsed_time": "5:25:39", "remaining_time": "3:45:18"}
{"current_steps": 2715, "total_steps": 4585, "loss": 0.4603, "lr": 1.7086575165109576e-05, "epoch": 4.145148968678381, "percentage": 59.21, "elapsed_time": "5:26:17", "remaining_time": "3:44:44"}
{"current_steps": 2720, "total_steps": 4585, "loss": 0.416, "lr": 1.7011267292814567e-05, "epoch": 4.152788388082506, "percentage": 59.32, "elapsed_time": "5:26:52", "remaining_time": "3:44:07"}
{"current_steps": 2725, "total_steps": 4585, "loss": 0.4299, "lr": 1.6936002738465852e-05, "epoch": 4.160427807486631, "percentage": 59.43, "elapsed_time": "5:27:30", "remaining_time": "3:43:32"}
{"current_steps": 2730, "total_steps": 4585, "loss": 0.4333, "lr": 1.686078259292911e-05, "epoch": 4.168067226890757, "percentage": 59.54, "elapsed_time": "5:28:00", "remaining_time": "3:42:52"}
{"current_steps": 2735, "total_steps": 4585, "loss": 0.431, "lr": 1.6785607946426365e-05, "epoch": 4.1757066462948815, "percentage": 59.65, "elapsed_time": "5:28:39", "remaining_time": "3:42:18"}
{"current_steps": 2740, "total_steps": 4585, "loss": 0.4323, "lr": 1.671047988852019e-05, "epoch": 4.1833460656990065, "percentage": 59.76, "elapsed_time": "5:29:22", "remaining_time": "3:41:47"}
{"current_steps": 2745, "total_steps": 4585, "loss": 0.4154, "lr": 1.663539950809792e-05, "epoch": 4.190985485103132, "percentage": 59.87, "elapsed_time": "5:30:03", "remaining_time": "3:41:14"}
{"current_steps": 2750, "total_steps": 4585, "loss": 0.4078, "lr": 1.6560367893355852e-05, "epoch": 4.198624904507257, "percentage": 59.98, "elapsed_time": "5:30:35", "remaining_time": "3:40:35"}
{"current_steps": 2755, "total_steps": 4585, "loss": 0.4319, "lr": 1.6485386131783495e-05, "epoch": 4.206264323911383, "percentage": 60.09, "elapsed_time": "5:31:09", "remaining_time": "3:39:58"}
{"current_steps": 2760, "total_steps": 4585, "loss": 0.4536, "lr": 1.6410455310147797e-05, "epoch": 4.213903743315508, "percentage": 60.2, "elapsed_time": "5:31:55", "remaining_time": "3:39:28"}
{"current_steps": 2765, "total_steps": 4585, "loss": 0.4086, "lr": 1.63355765144774e-05, "epoch": 4.221543162719633, "percentage": 60.31, "elapsed_time": "5:32:29", "remaining_time": "3:38:51"}
{"current_steps": 2770, "total_steps": 4585, "loss": 0.4166, "lr": 1.6260750830046876e-05, "epoch": 4.229182582123759, "percentage": 60.41, "elapsed_time": "5:33:13", "remaining_time": "3:38:20"}
{"current_steps": 2775, "total_steps": 4585, "loss": 0.4275, "lr": 1.6185979341361037e-05, "epoch": 4.236822001527884, "percentage": 60.52, "elapsed_time": "5:33:54", "remaining_time": "3:37:47"}
{"current_steps": 2780, "total_steps": 4585, "loss": 0.4173, "lr": 1.6111263132139198e-05, "epoch": 4.2444614209320095, "percentage": 60.63, "elapsed_time": "5:34:31", "remaining_time": "3:37:12"}
{"current_steps": 2785, "total_steps": 4585, "loss": 0.4585, "lr": 1.6036603285299443e-05, "epoch": 4.2521008403361344, "percentage": 60.74, "elapsed_time": "5:35:02", "remaining_time": "3:36:32"}
{"current_steps": 2790, "total_steps": 4585, "loss": 0.4041, "lr": 1.596200088294297e-05, "epoch": 4.259740259740259, "percentage": 60.85, "elapsed_time": "5:35:42", "remaining_time": "3:35:58"}
{"current_steps": 2795, "total_steps": 4585, "loss": 0.4341, "lr": 1.588745700633839e-05, "epoch": 4.267379679144385, "percentage": 60.96, "elapsed_time": "5:36:15", "remaining_time": "3:35:21"}
{"current_steps": 2800, "total_steps": 4585, "loss": 0.4069, "lr": 1.5812972735906066e-05, "epoch": 4.27501909854851, "percentage": 61.07, "elapsed_time": "5:36:59", "remaining_time": "3:34:50"}
{"current_steps": 2805, "total_steps": 4585, "loss": 0.4319, "lr": 1.5738549151202407e-05, "epoch": 4.282658517952636, "percentage": 61.18, "elapsed_time": "5:37:39", "remaining_time": "3:34:16"}
{"current_steps": 2810, "total_steps": 4585, "loss": 0.4446, "lr": 1.5664187330904306e-05, "epoch": 4.290297937356761, "percentage": 61.29, "elapsed_time": "5:38:07", "remaining_time": "3:33:35"}
{"current_steps": 2815, "total_steps": 4585, "loss": 0.4502, "lr": 1.5589888352793436e-05, "epoch": 4.297937356760886, "percentage": 61.4, "elapsed_time": "5:38:47", "remaining_time": "3:33:01"}
{"current_steps": 2820, "total_steps": 4585, "loss": 0.4387, "lr": 1.5515653293740637e-05, "epoch": 4.305576776165012, "percentage": 61.5, "elapsed_time": "5:39:21", "remaining_time": "3:32:23"}
{"current_steps": 2825, "total_steps": 4585, "loss": 0.4278, "lr": 1.544148322969035e-05, "epoch": 4.313216195569137, "percentage": 61.61, "elapsed_time": "5:39:59", "remaining_time": "3:31:49"}
{"current_steps": 2830, "total_steps": 4585, "loss": 0.4179, "lr": 1.5367379235644973e-05, "epoch": 4.320855614973262, "percentage": 61.72, "elapsed_time": "5:40:39", "remaining_time": "3:31:15"}
{"current_steps": 2835, "total_steps": 4585, "loss": 0.4201, "lr": 1.529334238564932e-05, "epoch": 4.328495034377387, "percentage": 61.83, "elapsed_time": "5:41:23", "remaining_time": "3:30:43"}
{"current_steps": 2840, "total_steps": 4585, "loss": 0.4335, "lr": 1.521937375277501e-05, "epoch": 4.336134453781512, "percentage": 61.94, "elapsed_time": "5:42:01", "remaining_time": "3:30:09"}
{"current_steps": 2845, "total_steps": 4585, "loss": 0.4265, "lr": 1.5145474409104962e-05, "epoch": 4.343773873185638, "percentage": 62.05, "elapsed_time": "5:42:41", "remaining_time": "3:29:35"}
{"current_steps": 2850, "total_steps": 4585, "loss": 0.4196, "lr": 1.507164542571784e-05, "epoch": 4.351413292589763, "percentage": 62.16, "elapsed_time": "5:43:23", "remaining_time": "3:29:02"}
{"current_steps": 2855, "total_steps": 4585, "loss": 0.4607, "lr": 1.49978878726725e-05, "epoch": 4.359052711993888, "percentage": 62.27, "elapsed_time": "5:43:58", "remaining_time": "3:28:26"}
{"current_steps": 2860, "total_steps": 4585, "loss": 0.4384, "lr": 1.4924202818992517e-05, "epoch": 4.366692131398014, "percentage": 62.38, "elapsed_time": "5:44:38", "remaining_time": "3:27:52"}
{"current_steps": 2865, "total_steps": 4585, "loss": 0.4178, "lr": 1.4850591332650679e-05, "epoch": 4.374331550802139, "percentage": 62.49, "elapsed_time": "5:45:11", "remaining_time": "3:27:13"}
{"current_steps": 2870, "total_steps": 4585, "loss": 0.4552, "lr": 1.4777054480553514e-05, "epoch": 4.381970970206265, "percentage": 62.6, "elapsed_time": "5:45:42", "remaining_time": "3:26:35"}
{"current_steps": 2875, "total_steps": 4585, "loss": 0.4326, "lr": 1.47035933285258e-05, "epoch": 4.3896103896103895, "percentage": 62.7, "elapsed_time": "5:46:21", "remaining_time": "3:26:00"}
{"current_steps": 2880, "total_steps": 4585, "loss": 0.399, "lr": 1.4630208941295156e-05, "epoch": 4.3972498090145145, "percentage": 62.81, "elapsed_time": "5:46:54", "remaining_time": "3:25:22"}
{"current_steps": 2885, "total_steps": 4585, "loss": 0.4158, "lr": 1.4556902382476579e-05, "epoch": 4.40488922841864, "percentage": 62.92, "elapsed_time": "5:47:37", "remaining_time": "3:24:50"}
{"current_steps": 2890, "total_steps": 4585, "loss": 0.4487, "lr": 1.448367471455705e-05, "epoch": 4.412528647822765, "percentage": 63.03, "elapsed_time": "5:48:13", "remaining_time": "3:24:14"}
{"current_steps": 2895, "total_steps": 4585, "loss": 0.4602, "lr": 1.4410526998880122e-05, "epoch": 4.420168067226891, "percentage": 63.14, "elapsed_time": "5:48:44", "remaining_time": "3:23:35"}
{"current_steps": 2900, "total_steps": 4585, "loss": 0.4528, "lr": 1.4337460295630531e-05, "epoch": 4.427807486631016, "percentage": 63.25, "elapsed_time": "5:49:22", "remaining_time": "3:22:59"}
{"current_steps": 2905, "total_steps": 4585, "loss": 0.4225, "lr": 1.4264475663818864e-05, "epoch": 4.435446906035141, "percentage": 63.36, "elapsed_time": "5:50:01", "remaining_time": "3:22:25"}
{"current_steps": 2910, "total_steps": 4585, "loss": 0.4594, "lr": 1.419157416126615e-05, "epoch": 4.443086325439267, "percentage": 63.47, "elapsed_time": "5:50:39", "remaining_time": "3:21:50"}
{"current_steps": 2915, "total_steps": 4585, "loss": 0.4441, "lr": 1.4118756844588585e-05, "epoch": 4.450725744843392, "percentage": 63.58, "elapsed_time": "5:51:21", "remaining_time": "3:21:17"}
{"current_steps": 2920, "total_steps": 4585, "loss": 0.4148, "lr": 1.4046024769182194e-05, "epoch": 4.4583651642475175, "percentage": 63.69, "elapsed_time": "5:51:58", "remaining_time": "3:20:41"}
{"current_steps": 2925, "total_steps": 4585, "loss": 0.4363, "lr": 1.3973378989207535e-05, "epoch": 4.466004583651642, "percentage": 63.79, "elapsed_time": "5:52:29", "remaining_time": "3:20:02"}
{"current_steps": 2930, "total_steps": 4585, "loss": 0.4472, "lr": 1.3900820557574425e-05, "epoch": 4.473644003055767, "percentage": 63.9, "elapsed_time": "5:53:05", "remaining_time": "3:19:26"}
{"current_steps": 2935, "total_steps": 4585, "loss": 0.4237, "lr": 1.3828350525926663e-05, "epoch": 4.481283422459893, "percentage": 64.01, "elapsed_time": "5:53:42", "remaining_time": "3:18:51"}
{"current_steps": 2940, "total_steps": 4585, "loss": 0.4194, "lr": 1.3755969944626823e-05, "epoch": 4.488922841864018, "percentage": 64.12, "elapsed_time": "5:54:12", "remaining_time": "3:18:11"}
{"current_steps": 2945, "total_steps": 4585, "loss": 0.4394, "lr": 1.368367986274098e-05, "epoch": 4.496562261268144, "percentage": 64.23, "elapsed_time": "5:54:37", "remaining_time": "3:17:28"}
{"current_steps": 2950, "total_steps": 4585, "loss": 0.4564, "lr": 1.3611481328023554e-05, "epoch": 4.504201680672269, "percentage": 64.34, "elapsed_time": "5:55:13", "remaining_time": "3:16:52"}
{"current_steps": 2955, "total_steps": 4585, "loss": 0.4139, "lr": 1.3539375386902092e-05, "epoch": 4.511841100076394, "percentage": 64.45, "elapsed_time": "5:55:46", "remaining_time": "3:16:15"}
{"current_steps": 2960, "total_steps": 4585, "loss": 0.4588, "lr": 1.3467363084462122e-05, "epoch": 4.51948051948052, "percentage": 64.56, "elapsed_time": "5:56:23", "remaining_time": "3:15:39"}
{"current_steps": 2965, "total_steps": 4585, "loss": 0.4403, "lr": 1.3395445464431997e-05, "epoch": 4.527119938884645, "percentage": 64.67, "elapsed_time": "5:57:03", "remaining_time": "3:15:05"}
{"current_steps": 2970, "total_steps": 4585, "loss": 0.4426, "lr": 1.3323623569167748e-05, "epoch": 4.53475935828877, "percentage": 64.78, "elapsed_time": "5:57:40", "remaining_time": "3:14:29"}
{"current_steps": 2975, "total_steps": 4585, "loss": 0.4323, "lr": 1.3251898439638025e-05, "epoch": 4.542398777692895, "percentage": 64.89, "elapsed_time": "5:58:07", "remaining_time": "3:13:48"}
{"current_steps": 2980, "total_steps": 4585, "loss": 0.4606, "lr": 1.3180271115408944e-05, "epoch": 4.55003819709702, "percentage": 64.99, "elapsed_time": "5:58:39", "remaining_time": "3:13:09"}
{"current_steps": 2985, "total_steps": 4585, "loss": 0.409, "lr": 1.310874263462909e-05, "epoch": 4.557677616501146, "percentage": 65.1, "elapsed_time": "5:59:18", "remaining_time": "3:12:35"}
{"current_steps": 2990, "total_steps": 4585, "loss": 0.4415, "lr": 1.303731403401441e-05, "epoch": 4.565317035905271, "percentage": 65.21, "elapsed_time": "5:59:53", "remaining_time": "3:11:58"}
{"current_steps": 2995, "total_steps": 4585, "loss": 0.4487, "lr": 1.2965986348833229e-05, "epoch": 4.572956455309397, "percentage": 65.32, "elapsed_time": "6:00:31", "remaining_time": "3:11:24"}
{"current_steps": 3000, "total_steps": 4585, "loss": 0.4133, "lr": 1.2894760612891219e-05, "epoch": 4.580595874713522, "percentage": 65.43, "elapsed_time": "6:01:09", "remaining_time": "3:10:48"}
{"current_steps": 3005, "total_steps": 4585, "loss": 0.4569, "lr": 1.2823637858516432e-05, "epoch": 4.588235294117647, "percentage": 65.54, "elapsed_time": "6:02:33", "remaining_time": "3:10:37"}
{"current_steps": 3010, "total_steps": 4585, "loss": 0.4303, "lr": 1.2752619116544333e-05, "epoch": 4.595874713521773, "percentage": 65.65, "elapsed_time": "6:03:13", "remaining_time": "3:10:03"}
{"current_steps": 3015, "total_steps": 4585, "loss": 0.4554, "lr": 1.2681705416302839e-05, "epoch": 4.6035141329258975, "percentage": 65.76, "elapsed_time": "6:03:51", "remaining_time": "3:09:28"}
{"current_steps": 3020, "total_steps": 4585, "loss": 0.458, "lr": 1.2610897785597441e-05, "epoch": 4.611153552330023, "percentage": 65.87, "elapsed_time": "6:04:26", "remaining_time": "3:08:51"}
{"current_steps": 3025, "total_steps": 4585, "loss": 0.4231, "lr": 1.2540197250696266e-05, "epoch": 4.618792971734148, "percentage": 65.98, "elapsed_time": "6:05:00", "remaining_time": "3:08:14"}
{"current_steps": 3030, "total_steps": 4585, "loss": 0.4362, "lr": 1.2469604836315237e-05, "epoch": 4.626432391138273, "percentage": 66.09, "elapsed_time": "6:05:38", "remaining_time": "3:07:38"}
{"current_steps": 3035, "total_steps": 4585, "loss": 0.4173, "lr": 1.2399121565603203e-05, "epoch": 4.634071810542399, "percentage": 66.19, "elapsed_time": "6:06:13", "remaining_time": "3:07:02"}
{"current_steps": 3040, "total_steps": 4585, "loss": 0.4372, "lr": 1.2328748460127095e-05, "epoch": 4.641711229946524, "percentage": 66.3, "elapsed_time": "6:06:47", "remaining_time": "3:06:24"}
{"current_steps": 3045, "total_steps": 4585, "loss": 0.4339, "lr": 1.2258486539857163e-05, "epoch": 4.64935064935065, "percentage": 66.41, "elapsed_time": "6:07:25", "remaining_time": "3:05:49"}
{"current_steps": 3050, "total_steps": 4585, "loss": 0.456, "lr": 1.2188336823152137e-05, "epoch": 4.656990068754775, "percentage": 66.52, "elapsed_time": "6:07:56", "remaining_time": "3:05:10"}
{"current_steps": 3055, "total_steps": 4585, "loss": 0.4407, "lr": 1.2118300326744525e-05, "epoch": 4.6646294881589, "percentage": 66.63, "elapsed_time": "6:08:27", "remaining_time": "3:04:31"}
{"current_steps": 3060, "total_steps": 4585, "loss": 0.4282, "lr": 1.2048378065725821e-05, "epoch": 4.6722689075630255, "percentage": 66.74, "elapsed_time": "6:09:05", "remaining_time": "3:03:56"}
{"current_steps": 3065, "total_steps": 4585, "loss": 0.4675, "lr": 1.1978571053531848e-05, "epoch": 4.67990832696715, "percentage": 66.85, "elapsed_time": "6:09:33", "remaining_time": "3:03:16"}
{"current_steps": 3070, "total_steps": 4585, "loss": 0.4489, "lr": 1.1908880301928012e-05, "epoch": 4.687547746371276, "percentage": 66.96, "elapsed_time": "6:10:04", "remaining_time": "3:02:37"}
{"current_steps": 3075, "total_steps": 4585, "loss": 0.4537, "lr": 1.1839306820994692e-05, "epoch": 4.695187165775401, "percentage": 67.07, "elapsed_time": "6:10:34", "remaining_time": "3:01:58"}
{"current_steps": 3080, "total_steps": 4585, "loss": 0.4268, "lr": 1.1769851619112571e-05, "epoch": 4.702826585179526, "percentage": 67.18, "elapsed_time": "6:11:07", "remaining_time": "3:01:20"}
{"current_steps": 3085, "total_steps": 4585, "loss": 0.4363, "lr": 1.1700515702948003e-05, "epoch": 4.710466004583652, "percentage": 67.28, "elapsed_time": "6:11:42", "remaining_time": "3:00:43"}
{"current_steps": 3090, "total_steps": 4585, "loss": 0.4032, "lr": 1.1631300077438474e-05, "epoch": 4.718105423987777, "percentage": 67.39, "elapsed_time": "6:12:17", "remaining_time": "3:00:07"}
{"current_steps": 3095, "total_steps": 4585, "loss": 0.4147, "lr": 1.1562205745777976e-05, "epoch": 4.725744843391903, "percentage": 67.5, "elapsed_time": "6:13:01", "remaining_time": "2:59:34"}
{"current_steps": 3100, "total_steps": 4585, "loss": 0.4374, "lr": 1.149323370940254e-05, "epoch": 4.733384262796028, "percentage": 67.61, "elapsed_time": "6:13:29", "remaining_time": "2:58:54"}
{"current_steps": 3105, "total_steps": 4585, "loss": 0.4386, "lr": 1.1424384967975638e-05, "epoch": 4.741023682200153, "percentage": 67.72, "elapsed_time": "6:14:03", "remaining_time": "2:58:17"}
{"current_steps": 3110, "total_steps": 4585, "loss": 0.4324, "lr": 1.1355660519373757e-05, "epoch": 4.748663101604278, "percentage": 67.83, "elapsed_time": "6:14:41", "remaining_time": "2:57:42"}
{"current_steps": 3115, "total_steps": 4585, "loss": 0.4511, "lr": 1.1287061359671918e-05, "epoch": 4.756302521008403, "percentage": 67.94, "elapsed_time": "6:15:18", "remaining_time": "2:57:06"}
{"current_steps": 3120, "total_steps": 4585, "loss": 0.4428, "lr": 1.1218588483129226e-05, "epoch": 4.763941940412528, "percentage": 68.05, "elapsed_time": "6:15:51", "remaining_time": "2:56:28"}
{"current_steps": 3125, "total_steps": 4585, "loss": 0.4254, "lr": 1.115024288217447e-05, "epoch": 4.771581359816654, "percentage": 68.16, "elapsed_time": "6:16:33", "remaining_time": "2:55:55"}
{"current_steps": 3130, "total_steps": 4585, "loss": 0.4409, "lr": 1.1082025547391742e-05, "epoch": 4.779220779220779, "percentage": 68.27, "elapsed_time": "6:17:11", "remaining_time": "2:55:20"}
{"current_steps": 3135, "total_steps": 4585, "loss": 0.4348, "lr": 1.1013937467506075e-05, "epoch": 4.786860198624905, "percentage": 68.38, "elapsed_time": "6:17:47", "remaining_time": "2:54:44"}
{"current_steps": 3140, "total_steps": 4585, "loss": 0.4284, "lr": 1.0945979629369103e-05, "epoch": 4.79449961802903, "percentage": 68.48, "elapsed_time": "6:18:23", "remaining_time": "2:54:07"}
{"current_steps": 3145, "total_steps": 4585, "loss": 0.4664, "lr": 1.0878153017944801e-05, "epoch": 4.802139037433155, "percentage": 68.59, "elapsed_time": "6:19:06", "remaining_time": "2:53:35"}
{"current_steps": 3150, "total_steps": 4585, "loss": 0.4421, "lr": 1.0810458616295146e-05, "epoch": 4.809778456837281, "percentage": 68.7, "elapsed_time": "6:19:34", "remaining_time": "2:52:55"}
{"current_steps": 3155, "total_steps": 4585, "loss": 0.4394, "lr": 1.0742897405565892e-05, "epoch": 4.8174178762414055, "percentage": 68.81, "elapsed_time": "6:20:08", "remaining_time": "2:52:17"}
{"current_steps": 3160, "total_steps": 4585, "loss": 0.4434, "lr": 1.0675470364972412e-05, "epoch": 4.825057295645531, "percentage": 68.92, "elapsed_time": "6:20:37", "remaining_time": "2:51:38"}
{"current_steps": 3165, "total_steps": 4585, "loss": 0.4605, "lr": 1.0608178471785369e-05, "epoch": 4.832696715049656, "percentage": 69.03, "elapsed_time": "6:21:06", "remaining_time": "2:50:59"}
{"current_steps": 3170, "total_steps": 4585, "loss": 0.415, "lr": 1.0541022701316704e-05, "epoch": 4.840336134453781, "percentage": 69.14, "elapsed_time": "6:21:40", "remaining_time": "2:50:21"}
{"current_steps": 3175, "total_steps": 4585, "loss": 0.4214, "lr": 1.0474004026905393e-05, "epoch": 4.847975553857907, "percentage": 69.25, "elapsed_time": "6:22:18", "remaining_time": "2:49:47"}
{"current_steps": 3180, "total_steps": 4585, "loss": 0.4427, "lr": 1.040712341990338e-05, "epoch": 4.855614973262032, "percentage": 69.36, "elapsed_time": "6:22:53", "remaining_time": "2:49:10"}
{"current_steps": 3185, "total_steps": 4585, "loss": 0.4209, "lr": 1.0340381849661512e-05, "epoch": 4.863254392666157, "percentage": 69.47, "elapsed_time": "6:23:31", "remaining_time": "2:48:34"}
{"current_steps": 3190, "total_steps": 4585, "loss": 0.4843, "lr": 1.027378028351545e-05, "epoch": 4.870893812070283, "percentage": 69.57, "elapsed_time": "6:24:07", "remaining_time": "2:47:58"}
{"current_steps": 3195, "total_steps": 4585, "loss": 0.4559, "lr": 1.020731968677168e-05, "epoch": 4.878533231474408, "percentage": 69.68, "elapsed_time": "6:24:38", "remaining_time": "2:47:20"}
{"current_steps": 3200, "total_steps": 4585, "loss": 0.4392, "lr": 1.0141001022693513e-05, "epoch": 4.8861726508785335, "percentage": 69.79, "elapsed_time": "6:25:25", "remaining_time": "2:46:49"}
{"current_steps": 3205, "total_steps": 4585, "loss": 0.4411, "lr": 1.0074825252487124e-05, "epoch": 4.893812070282658, "percentage": 69.9, "elapsed_time": "6:26:02", "remaining_time": "2:46:13"}
{"current_steps": 3210, "total_steps": 4585, "loss": 0.4115, "lr": 1.0008793335287605e-05, "epoch": 4.901451489686783, "percentage": 70.01, "elapsed_time": "6:26:41", "remaining_time": "2:45:38"}
{"current_steps": 3215, "total_steps": 4585, "loss": 0.4486, "lr": 9.942906228145123e-06, "epoch": 4.909090909090909, "percentage": 70.12, "elapsed_time": "6:27:23", "remaining_time": "2:45:04"}
{"current_steps": 3220, "total_steps": 4585, "loss": 0.4429, "lr": 9.877164886010938e-06, "epoch": 4.916730328495034, "percentage": 70.23, "elapsed_time": "6:27:54", "remaining_time": "2:44:26"}
{"current_steps": 3225, "total_steps": 4585, "loss": 0.4377, "lr": 9.811570261723676e-06, "epoch": 4.92436974789916, "percentage": 70.34, "elapsed_time": "6:28:32", "remaining_time": "2:43:51"}
{"current_steps": 3230, "total_steps": 4585, "loss": 0.4166, "lr": 9.746123305995476e-06, "epoch": 4.932009167303285, "percentage": 70.45, "elapsed_time": "6:29:11", "remaining_time": "2:43:15"}
{"current_steps": 3235, "total_steps": 4585, "loss": 0.4418, "lr": 9.68082496739816e-06, "epoch": 4.93964858670741, "percentage": 70.56, "elapsed_time": "6:29:42", "remaining_time": "2:42:37"}
{"current_steps": 3240, "total_steps": 4585, "loss": 0.4071, "lr": 9.615676192349577e-06, "epoch": 4.947288006111536, "percentage": 70.67, "elapsed_time": "6:30:13", "remaining_time": "2:41:59"}
{"current_steps": 3245, "total_steps": 4585, "loss": 0.4239, "lr": 9.550677925099815e-06, "epoch": 4.954927425515661, "percentage": 70.77, "elapsed_time": "6:30:49", "remaining_time": "2:41:23"}
{"current_steps": 3250, "total_steps": 4585, "loss": 0.4375, "lr": 9.485831107717547e-06, "epoch": 4.962566844919786, "percentage": 70.88, "elapsed_time": "6:31:26", "remaining_time": "2:40:47"}
{"current_steps": 3255, "total_steps": 4585, "loss": 0.4194, "lr": 9.421136680076365e-06, "epoch": 4.970206264323911, "percentage": 70.99, "elapsed_time": "6:32:00", "remaining_time": "2:40:10"}
{"current_steps": 3260, "total_steps": 4585, "loss": 0.4544, "lr": 9.356595579841158e-06, "epoch": 4.977845683728036, "percentage": 71.1, "elapsed_time": "6:32:36", "remaining_time": "2:39:34"}
{"current_steps": 3265, "total_steps": 4585, "loss": 0.4498, "lr": 9.292208742454549e-06, "epoch": 4.985485103132162, "percentage": 71.21, "elapsed_time": "6:33:09", "remaining_time": "2:38:56"}
{"current_steps": 3270, "total_steps": 4585, "loss": 0.4317, "lr": 9.227977101123287e-06, "epoch": 4.993124522536287, "percentage": 71.32, "elapsed_time": "6:33:47", "remaining_time": "2:38:21"}
{"current_steps": 3275, "total_steps": 4585, "loss": 0.4491, "lr": 9.16390158680476e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "6:34:20", "remaining_time": "2:37:44"}
{"current_steps": 3280, "total_steps": 4585, "loss": 0.411, "lr": 9.099983128193481e-06, "epoch": 5.007639419404125, "percentage": 71.54, "elapsed_time": "6:34:56", "remaining_time": "2:37:08"}
{"current_steps": 3285, "total_steps": 4585, "loss": 0.4068, "lr": 9.036222651707666e-06, "epoch": 5.015278838808251, "percentage": 71.65, "elapsed_time": "6:35:22", "remaining_time": "2:36:28"}
{"current_steps": 3290, "total_steps": 4585, "loss": 0.4542, "lr": 8.972621081475727e-06, "epoch": 5.022918258212376, "percentage": 71.76, "elapsed_time": "6:36:00", "remaining_time": "2:35:52"}
{"current_steps": 3295, "total_steps": 4585, "loss": 0.4142, "lr": 8.909179339322971e-06, "epoch": 5.0305576776165015, "percentage": 71.86, "elapsed_time": "6:36:38", "remaining_time": "2:35:17"}
{"current_steps": 3300, "total_steps": 4585, "loss": 0.4163, "lr": 8.845898344758199e-06, "epoch": 5.0381970970206265, "percentage": 71.97, "elapsed_time": "6:37:18", "remaining_time": "2:34:42"}
{"current_steps": 3305, "total_steps": 4585, "loss": 0.4009, "lr": 8.782779014960327e-06, "epoch": 5.045836516424751, "percentage": 72.08, "elapsed_time": "6:37:49", "remaining_time": "2:34:04"}
{"current_steps": 3310, "total_steps": 4585, "loss": 0.418, "lr": 8.719822264765204e-06, "epoch": 5.053475935828877, "percentage": 72.19, "elapsed_time": "6:38:29", "remaining_time": "2:33:30"}
{"current_steps": 3315, "total_steps": 4585, "loss": 0.3937, "lr": 8.657029006652247e-06, "epoch": 5.061115355233002, "percentage": 72.3, "elapsed_time": "6:39:04", "remaining_time": "2:32:53"}
{"current_steps": 3320, "total_steps": 4585, "loss": 0.4165, "lr": 8.594400150731278e-06, "epoch": 5.068754774637128, "percentage": 72.41, "elapsed_time": "6:39:39", "remaining_time": "2:32:16"}
{"current_steps": 3325, "total_steps": 4585, "loss": 0.4048, "lr": 8.531936604729315e-06, "epoch": 5.076394194041253, "percentage": 72.52, "elapsed_time": "6:40:14", "remaining_time": "2:31:40"}
{"current_steps": 3330, "total_steps": 4585, "loss": 0.4092, "lr": 8.469639273977404e-06, "epoch": 5.084033613445378, "percentage": 72.63, "elapsed_time": "6:40:43", "remaining_time": "2:31:01"}
{"current_steps": 3335, "total_steps": 4585, "loss": 0.4242, "lr": 8.407509061397525e-06, "epoch": 5.091673032849504, "percentage": 72.74, "elapsed_time": "6:41:19", "remaining_time": "2:30:25"}
{"current_steps": 3340, "total_steps": 4585, "loss": 0.431, "lr": 8.345546867489478e-06, "epoch": 5.099312452253629, "percentage": 72.85, "elapsed_time": "6:41:51", "remaining_time": "2:29:47"}
{"current_steps": 3345, "total_steps": 4585, "loss": 0.4167, "lr": 8.283753590317844e-06, "epoch": 5.106951871657754, "percentage": 72.96, "elapsed_time": "6:42:31", "remaining_time": "2:29:13"}
{"current_steps": 3350, "total_steps": 4585, "loss": 0.4175, "lr": 8.222130125498959e-06, "epoch": 5.114591291061879, "percentage": 73.06, "elapsed_time": "6:43:16", "remaining_time": "2:28:40"}
{"current_steps": 3355, "total_steps": 4585, "loss": 0.4037, "lr": 8.160677366187973e-06, "epoch": 5.122230710466004, "percentage": 73.17, "elapsed_time": "6:43:53", "remaining_time": "2:28:04"}
{"current_steps": 3360, "total_steps": 4585, "loss": 0.4049, "lr": 8.099396203065818e-06, "epoch": 5.12987012987013, "percentage": 73.28, "elapsed_time": "6:44:29", "remaining_time": "2:27:28"}
{"current_steps": 3365, "total_steps": 4585, "loss": 0.4215, "lr": 8.038287524326412e-06, "epoch": 5.137509549274255, "percentage": 73.39, "elapsed_time": "6:45:03", "remaining_time": "2:26:51"}
{"current_steps": 3370, "total_steps": 4585, "loss": 0.4217, "lr": 7.977352215663687e-06, "epoch": 5.145148968678381, "percentage": 73.5, "elapsed_time": "6:45:43", "remaining_time": "2:26:16"}
{"current_steps": 3375, "total_steps": 4585, "loss": 0.4492, "lr": 7.916591160258801e-06, "epoch": 5.152788388082506, "percentage": 73.61, "elapsed_time": "6:46:10", "remaining_time": "2:25:37"}
{"current_steps": 3380, "total_steps": 4585, "loss": 0.4031, "lr": 7.856005238767352e-06, "epoch": 5.160427807486631, "percentage": 73.72, "elapsed_time": "6:46:44", "remaining_time": "2:25:00"}
{"current_steps": 3385, "total_steps": 4585, "loss": 0.4003, "lr": 7.79559532930656e-06, "epoch": 5.168067226890757, "percentage": 73.83, "elapsed_time": "6:47:12", "remaining_time": "2:24:21"}
{"current_steps": 3390, "total_steps": 4585, "loss": 0.4254, "lr": 7.735362307442587e-06, "epoch": 5.1757066462948815, "percentage": 73.94, "elapsed_time": "6:47:50", "remaining_time": "2:23:45"}
{"current_steps": 3395, "total_steps": 4585, "loss": 0.444, "lr": 7.675307046177824e-06, "epoch": 5.1833460656990065, "percentage": 74.05, "elapsed_time": "6:48:37", "remaining_time": "2:23:13"}
{"current_steps": 3400, "total_steps": 4585, "loss": 0.4146, "lr": 7.615430415938247e-06, "epoch": 5.190985485103132, "percentage": 74.15, "elapsed_time": "6:49:05", "remaining_time": "2:22:34"}
{"current_steps": 3405, "total_steps": 4585, "loss": 0.4166, "lr": 7.555733284560791e-06, "epoch": 5.198624904507257, "percentage": 74.26, "elapsed_time": "6:49:38", "remaining_time": "2:21:57"}
{"current_steps": 3410, "total_steps": 4585, "loss": 0.4104, "lr": 7.496216517280801e-06, "epoch": 5.206264323911383, "percentage": 74.37, "elapsed_time": "6:50:18", "remaining_time": "2:21:23"}
{"current_steps": 3415, "total_steps": 4585, "loss": 0.4272, "lr": 7.436880976719447e-06, "epoch": 5.213903743315508, "percentage": 74.48, "elapsed_time": "6:51:02", "remaining_time": "2:20:49"}
{"current_steps": 3420, "total_steps": 4585, "loss": 0.4128, "lr": 7.377727522871246e-06, "epoch": 5.221543162719633, "percentage": 74.59, "elapsed_time": "6:51:38", "remaining_time": "2:20:13"}
{"current_steps": 3425, "total_steps": 4585, "loss": 0.3837, "lr": 7.318757013091622e-06, "epoch": 5.229182582123759, "percentage": 74.7, "elapsed_time": "6:52:11", "remaining_time": "2:19:36"}
{"current_steps": 3430, "total_steps": 4585, "loss": 0.3728, "lr": 7.259970302084405e-06, "epoch": 5.236822001527884, "percentage": 74.81, "elapsed_time": "6:52:54", "remaining_time": "2:19:02"}
{"current_steps": 3435, "total_steps": 4585, "loss": 0.4363, "lr": 7.2013682418895435e-06, "epoch": 5.2444614209320095, "percentage": 74.92, "elapsed_time": "6:53:31", "remaining_time": "2:18:26"}
{"current_steps": 3440, "total_steps": 4585, "loss": 0.4256, "lr": 7.142951681870669e-06, "epoch": 5.2521008403361344, "percentage": 75.03, "elapsed_time": "6:54:12", "remaining_time": "2:17:52"}
{"current_steps": 3445, "total_steps": 4585, "loss": 0.3894, "lr": 7.084721468702822e-06, "epoch": 5.259740259740259, "percentage": 75.14, "elapsed_time": "6:54:51", "remaining_time": "2:17:16"}
{"current_steps": 3450, "total_steps": 4585, "loss": 0.3987, "lr": 7.026678446360204e-06, "epoch": 5.267379679144385, "percentage": 75.25, "elapsed_time": "6:55:25", "remaining_time": "2:16:40"}
{"current_steps": 3455, "total_steps": 4585, "loss": 0.4252, "lr": 6.9688234561038925e-06, "epoch": 5.27501909854851, "percentage": 75.35, "elapsed_time": "6:56:00", "remaining_time": "2:16:03"}
{"current_steps": 3460, "total_steps": 4585, "loss": 0.4159, "lr": 6.911157336469685e-06, "epoch": 5.282658517952636, "percentage": 75.46, "elapsed_time": "6:56:40", "remaining_time": "2:15:28"}
{"current_steps": 3465, "total_steps": 4585, "loss": 0.4084, "lr": 6.853680923255932e-06, "epoch": 5.290297937356761, "percentage": 75.57, "elapsed_time": "6:57:13", "remaining_time": "2:14:51"}
{"current_steps": 3470, "total_steps": 4585, "loss": 0.4149, "lr": 6.796395049511431e-06, "epoch": 5.297937356760886, "percentage": 75.68, "elapsed_time": "6:57:43", "remaining_time": "2:14:13"}
{"current_steps": 3475, "total_steps": 4585, "loss": 0.4052, "lr": 6.739300545523335e-06, "epoch": 5.305576776165012, "percentage": 75.79, "elapsed_time": "6:58:13", "remaining_time": "2:13:35"}
{"current_steps": 3480, "total_steps": 4585, "loss": 0.4145, "lr": 6.682398238805161e-06, "epoch": 5.313216195569137, "percentage": 75.9, "elapsed_time": "6:58:44", "remaining_time": "2:12:57"}
{"current_steps": 3485, "total_steps": 4585, "loss": 0.3901, "lr": 6.625688954084739e-06, "epoch": 5.320855614973262, "percentage": 76.01, "elapsed_time": "6:59:20", "remaining_time": "2:12:21"}
{"current_steps": 3490, "total_steps": 4585, "loss": 0.4121, "lr": 6.569173513292289e-06, "epoch": 5.328495034377387, "percentage": 76.12, "elapsed_time": "6:59:50", "remaining_time": "2:11:43"}
{"current_steps": 3495, "total_steps": 4585, "loss": 0.4422, "lr": 6.512852735548529e-06, "epoch": 5.336134453781512, "percentage": 76.23, "elapsed_time": "7:00:30", "remaining_time": "2:11:08"}
{"current_steps": 3500, "total_steps": 4585, "loss": 0.4181, "lr": 6.456727437152737e-06, "epoch": 5.343773873185638, "percentage": 76.34, "elapsed_time": "7:01:11", "remaining_time": "2:10:34"}
{"current_steps": 3505, "total_steps": 4585, "loss": 0.4309, "lr": 6.400798431571009e-06, "epoch": 5.351413292589763, "percentage": 76.44, "elapsed_time": "7:01:45", "remaining_time": "2:09:57"}
{"current_steps": 3510, "total_steps": 4585, "loss": 0.4146, "lr": 6.345066529424391e-06, "epoch": 5.359052711993888, "percentage": 76.55, "elapsed_time": "7:02:12", "remaining_time": "2:09:18"}
{"current_steps": 3515, "total_steps": 4585, "loss": 0.4199, "lr": 6.289532538477163e-06, "epoch": 5.366692131398014, "percentage": 76.66, "elapsed_time": "7:02:45", "remaining_time": "2:08:41"}
{"current_steps": 3520, "total_steps": 4585, "loss": 0.4154, "lr": 6.234197263625157e-06, "epoch": 5.374331550802139, "percentage": 76.77, "elapsed_time": "7:03:08", "remaining_time": "2:08:01"}
{"current_steps": 3525, "total_steps": 4585, "loss": 0.4036, "lr": 6.179061506884018e-06, "epoch": 5.381970970206265, "percentage": 76.88, "elapsed_time": "7:03:42", "remaining_time": "2:07:24"}
{"current_steps": 3530, "total_steps": 4585, "loss": 0.4486, "lr": 6.124126067377669e-06, "epoch": 5.3896103896103895, "percentage": 76.99, "elapsed_time": "7:04:13", "remaining_time": "2:06:47"}
{"current_steps": 3535, "total_steps": 4585, "loss": 0.4272, "lr": 6.069391741326658e-06, "epoch": 5.3972498090145145, "percentage": 77.1, "elapsed_time": "7:04:54", "remaining_time": "2:06:12"}
{"current_steps": 3540, "total_steps": 4585, "loss": 0.475, "lr": 6.014859322036655e-06, "epoch": 5.40488922841864, "percentage": 77.21, "elapsed_time": "7:05:31", "remaining_time": "2:05:36"}
{"current_steps": 3545, "total_steps": 4585, "loss": 0.4249, "lr": 5.960529599886933e-06, "epoch": 5.412528647822765, "percentage": 77.32, "elapsed_time": "7:06:12", "remaining_time": "2:05:02"}
{"current_steps": 3550, "total_steps": 4585, "loss": 0.4233, "lr": 5.906403362318953e-06, "epoch": 5.420168067226891, "percentage": 77.43, "elapsed_time": "7:06:47", "remaining_time": "2:04:25"}
{"current_steps": 3555, "total_steps": 4585, "loss": 0.4273, "lr": 5.852481393824876e-06, "epoch": 5.427807486631016, "percentage": 77.54, "elapsed_time": "7:07:23", "remaining_time": "2:03:49"}
{"current_steps": 3560, "total_steps": 4585, "loss": 0.4056, "lr": 5.7987644759362715e-06, "epoch": 5.435446906035141, "percentage": 77.64, "elapsed_time": "7:07:58", "remaining_time": "2:03:13"}
{"current_steps": 3565, "total_steps": 4585, "loss": 0.4148, "lr": 5.745253387212759e-06, "epoch": 5.443086325439267, "percentage": 77.75, "elapsed_time": "7:08:27", "remaining_time": "2:02:35"}
{"current_steps": 3570, "total_steps": 4585, "loss": 0.3924, "lr": 5.691948903230691e-06, "epoch": 5.450725744843392, "percentage": 77.86, "elapsed_time": "7:09:06", "remaining_time": "2:02:00"}
{"current_steps": 3575, "total_steps": 4585, "loss": 0.4349, "lr": 5.638851796571974e-06, "epoch": 5.4583651642475175, "percentage": 77.97, "elapsed_time": "7:09:34", "remaining_time": "2:01:21"}
{"current_steps": 3580, "total_steps": 4585, "loss": 0.4053, "lr": 5.585962836812822e-06, "epoch": 5.466004583651642, "percentage": 78.08, "elapsed_time": "7:10:13", "remaining_time": "2:00:46"}
{"current_steps": 3585, "total_steps": 4585, "loss": 0.3872, "lr": 5.533282790512624e-06, "epoch": 5.473644003055767, "percentage": 78.19, "elapsed_time": "7:10:50", "remaining_time": "2:00:10"}
{"current_steps": 3590, "total_steps": 4585, "loss": 0.4047, "lr": 5.480812421202828e-06, "epoch": 5.481283422459893, "percentage": 78.3, "elapsed_time": "7:11:25", "remaining_time": "1:59:34"}
{"current_steps": 3595, "total_steps": 4585, "loss": 0.4002, "lr": 5.428552489375876e-06, "epoch": 5.488922841864018, "percentage": 78.41, "elapsed_time": "7:12:02", "remaining_time": "1:58:58"}
{"current_steps": 3600, "total_steps": 4585, "loss": 0.3985, "lr": 5.376503752474191e-06, "epoch": 5.496562261268144, "percentage": 78.52, "elapsed_time": "7:12:35", "remaining_time": "1:58:21"}
{"current_steps": 3605, "total_steps": 4585, "loss": 0.417, "lr": 5.32466696487918e-06, "epoch": 5.504201680672269, "percentage": 78.63, "elapsed_time": "7:13:11", "remaining_time": "1:57:45"}
{"current_steps": 3610, "total_steps": 4585, "loss": 0.4103, "lr": 5.273042877900308e-06, "epoch": 5.511841100076394, "percentage": 78.74, "elapsed_time": "7:13:42", "remaining_time": "1:57:08"}
{"current_steps": 3615, "total_steps": 4585, "loss": 0.4082, "lr": 5.221632239764207e-06, "epoch": 5.51948051948052, "percentage": 78.84, "elapsed_time": "7:14:19", "remaining_time": "1:56:32"}
{"current_steps": 3620, "total_steps": 4585, "loss": 0.4218, "lr": 5.170435795603863e-06, "epoch": 5.527119938884645, "percentage": 78.95, "elapsed_time": "7:14:56", "remaining_time": "1:55:56"}
{"current_steps": 3625, "total_steps": 4585, "loss": 0.4508, "lr": 5.119454287447738e-06, "epoch": 5.53475935828877, "percentage": 79.06, "elapsed_time": "7:15:32", "remaining_time": "1:55:20"}
{"current_steps": 3630, "total_steps": 4585, "loss": 0.4187, "lr": 5.068688454209114e-06, "epoch": 5.542398777692895, "percentage": 79.17, "elapsed_time": "7:16:04", "remaining_time": "1:54:43"}
{"current_steps": 3635, "total_steps": 4585, "loss": 0.3994, "lr": 5.018139031675309e-06, "epoch": 5.55003819709702, "percentage": 79.28, "elapsed_time": "7:16:39", "remaining_time": "1:54:07"}
{"current_steps": 3640, "total_steps": 4585, "loss": 0.4128, "lr": 4.967806752497036e-06, "epoch": 5.557677616501146, "percentage": 79.39, "elapsed_time": "7:17:21", "remaining_time": "1:53:32"}
{"current_steps": 3645, "total_steps": 4585, "loss": 0.4224, "lr": 4.917692346177804e-06, "epoch": 5.565317035905271, "percentage": 79.5, "elapsed_time": "7:17:57", "remaining_time": "1:52:56"}
{"current_steps": 3650, "total_steps": 4585, "loss": 0.4094, "lr": 4.8677965390633145e-06, "epoch": 5.572956455309397, "percentage": 79.61, "elapsed_time": "7:18:30", "remaining_time": "1:52:19"}
{"current_steps": 3655, "total_steps": 4585, "loss": 0.4224, "lr": 4.818120054330946e-06, "epoch": 5.580595874713522, "percentage": 79.72, "elapsed_time": "7:19:07", "remaining_time": "1:51:43"}
{"current_steps": 3660, "total_steps": 4585, "loss": 0.4246, "lr": 4.768663611979276e-06, "epoch": 5.588235294117647, "percentage": 79.83, "elapsed_time": "7:19:43", "remaining_time": "1:51:08"}
{"current_steps": 3665, "total_steps": 4585, "loss": 0.3903, "lr": 4.719427928817637e-06, "epoch": 5.595874713521773, "percentage": 79.93, "elapsed_time": "7:20:17", "remaining_time": "1:50:31"}
{"current_steps": 3670, "total_steps": 4585, "loss": 0.4041, "lr": 4.670413718455753e-06, "epoch": 5.6035141329258975, "percentage": 80.04, "elapsed_time": "7:20:41", "remaining_time": "1:49:52"}
{"current_steps": 3675, "total_steps": 4585, "loss": 0.4116, "lr": 4.6216216912933546e-06, "epoch": 5.611153552330023, "percentage": 80.15, "elapsed_time": "7:21:15", "remaining_time": "1:49:15"}
{"current_steps": 3680, "total_steps": 4585, "loss": 0.4107, "lr": 4.5730525545099095e-06, "epoch": 5.618792971734148, "percentage": 80.26, "elapsed_time": "7:21:46", "remaining_time": "1:48:38"}
{"current_steps": 3685, "total_steps": 4585, "loss": 0.4294, "lr": 4.524707012054368e-06, "epoch": 5.626432391138273, "percentage": 80.37, "elapsed_time": "7:22:22", "remaining_time": "1:48:02"}
{"current_steps": 3690, "total_steps": 4585, "loss": 0.4114, "lr": 4.476585764634975e-06, "epoch": 5.634071810542399, "percentage": 80.48, "elapsed_time": "7:23:01", "remaining_time": "1:47:27"}
{"current_steps": 3695, "total_steps": 4585, "loss": 0.4307, "lr": 4.4286895097090695e-06, "epoch": 5.641711229946524, "percentage": 80.59, "elapsed_time": "7:23:35", "remaining_time": "1:46:50"}
{"current_steps": 3700, "total_steps": 4585, "loss": 0.4381, "lr": 4.381018941473037e-06, "epoch": 5.64935064935065, "percentage": 80.7, "elapsed_time": "7:24:17", "remaining_time": "1:46:16"}
{"current_steps": 3705, "total_steps": 4585, "loss": 0.4181, "lr": 4.333574750852194e-06, "epoch": 5.656990068754775, "percentage": 80.81, "elapsed_time": "7:24:55", "remaining_time": "1:45:40"}
{"current_steps": 3710, "total_steps": 4585, "loss": 0.4226, "lr": 4.2863576254908e-06, "epoch": 5.6646294881589, "percentage": 80.92, "elapsed_time": "7:25:32", "remaining_time": "1:45:04"}
{"current_steps": 3715, "total_steps": 4585, "loss": 0.4236, "lr": 4.239368249742102e-06, "epoch": 5.6722689075630255, "percentage": 81.03, "elapsed_time": "7:26:13", "remaining_time": "1:44:30"}
{"current_steps": 3720, "total_steps": 4585, "loss": 0.4125, "lr": 4.192607304658387e-06, "epoch": 5.67990832696715, "percentage": 81.13, "elapsed_time": "7:26:46", "remaining_time": "1:43:53"}
{"current_steps": 3725, "total_steps": 4585, "loss": 0.4663, "lr": 4.146075467981125e-06, "epoch": 5.687547746371276, "percentage": 81.24, "elapsed_time": "7:27:21", "remaining_time": "1:43:17"}
{"current_steps": 3730, "total_steps": 4585, "loss": 0.4271, "lr": 4.09977341413115e-06, "epoch": 5.695187165775401, "percentage": 81.35, "elapsed_time": "7:27:57", "remaining_time": "1:42:41"}
{"current_steps": 3735, "total_steps": 4585, "loss": 0.4025, "lr": 4.053701814198882e-06, "epoch": 5.702826585179526, "percentage": 81.46, "elapsed_time": "7:28:33", "remaining_time": "1:42:04"}
{"current_steps": 3740, "total_steps": 4585, "loss": 0.4187, "lr": 4.0078613359345884e-06, "epoch": 5.710466004583652, "percentage": 81.57, "elapsed_time": "7:29:09", "remaining_time": "1:41:28"}
{"current_steps": 3745, "total_steps": 4585, "loss": 0.4154, "lr": 3.962252643738742e-06, "epoch": 5.718105423987777, "percentage": 81.68, "elapsed_time": "7:29:37", "remaining_time": "1:40:51"}
{"current_steps": 3750, "total_steps": 4585, "loss": 0.4236, "lr": 3.916876398652338e-06, "epoch": 5.725744843391903, "percentage": 81.79, "elapsed_time": "7:30:18", "remaining_time": "1:40:16"}
{"current_steps": 3755, "total_steps": 4585, "loss": 0.4194, "lr": 3.8717332583473545e-06, "epoch": 5.733384262796028, "percentage": 81.9, "elapsed_time": "7:30:48", "remaining_time": "1:39:38"}
{"current_steps": 3760, "total_steps": 4585, "loss": 0.402, "lr": 3.826823877117218e-06, "epoch": 5.741023682200153, "percentage": 82.01, "elapsed_time": "7:31:26", "remaining_time": "1:39:03"}
{"current_steps": 3765, "total_steps": 4585, "loss": 0.3925, "lr": 3.7821489058672754e-06, "epoch": 5.748663101604278, "percentage": 82.12, "elapsed_time": "7:32:05", "remaining_time": "1:38:27"}
{"current_steps": 3770, "total_steps": 4585, "loss": 0.4083, "lr": 3.7377089921054355e-06, "epoch": 5.756302521008403, "percentage": 82.22, "elapsed_time": "7:32:38", "remaining_time": "1:37:51"}
{"current_steps": 3775, "total_steps": 4585, "loss": 0.4336, "lr": 3.6935047799327107e-06, "epoch": 5.763941940412528, "percentage": 82.33, "elapsed_time": "7:33:11", "remaining_time": "1:37:14"}
{"current_steps": 3780, "total_steps": 4585, "loss": 0.4282, "lr": 3.649536910033926e-06, "epoch": 5.771581359816654, "percentage": 82.44, "elapsed_time": "7:33:46", "remaining_time": "1:36:38"}
{"current_steps": 3785, "total_steps": 4585, "loss": 0.4232, "lr": 3.605806019668432e-06, "epoch": 5.779220779220779, "percentage": 82.55, "elapsed_time": "7:34:25", "remaining_time": "1:36:02"}
{"current_steps": 3790, "total_steps": 4585, "loss": 0.4247, "lr": 3.562312742660825e-06, "epoch": 5.786860198624905, "percentage": 82.66, "elapsed_time": "7:34:58", "remaining_time": "1:35:26"}
{"current_steps": 3795, "total_steps": 4585, "loss": 0.4449, "lr": 3.5190577093918266e-06, "epoch": 5.79449961802903, "percentage": 82.77, "elapsed_time": "7:35:31", "remaining_time": "1:34:49"}
{"current_steps": 3800, "total_steps": 4585, "loss": 0.4243, "lr": 3.476041546789095e-06, "epoch": 5.802139037433155, "percentage": 82.88, "elapsed_time": "7:36:10", "remaining_time": "1:34:14"}
{"current_steps": 3805, "total_steps": 4585, "loss": 0.4288, "lr": 3.433264878318159e-06, "epoch": 5.809778456837281, "percentage": 82.99, "elapsed_time": "7:36:48", "remaining_time": "1:33:38"}
{"current_steps": 3810, "total_steps": 4585, "loss": 0.4071, "lr": 3.390728323973376e-06, "epoch": 5.8174178762414055, "percentage": 83.1, "elapsed_time": "7:37:25", "remaining_time": "1:33:02"}
{"current_steps": 3815, "total_steps": 4585, "loss": 0.4448, "lr": 3.3484325002689653e-06, "epoch": 5.825057295645531, "percentage": 83.21, "elapsed_time": "7:38:06", "remaining_time": "1:32:27"}
{"current_steps": 3820, "total_steps": 4585, "loss": 0.4425, "lr": 3.3063780202300365e-06, "epoch": 5.832696715049656, "percentage": 83.32, "elapsed_time": "7:38:45", "remaining_time": "1:31:52"}
{"current_steps": 3825, "total_steps": 4585, "loss": 0.4271, "lr": 3.264565493383729e-06, "epoch": 5.840336134453781, "percentage": 83.42, "elapsed_time": "7:39:18", "remaining_time": "1:31:15"}
{"current_steps": 3830, "total_steps": 4585, "loss": 0.3845, "lr": 3.222995525750392e-06, "epoch": 5.847975553857907, "percentage": 83.53, "elapsed_time": "7:39:58", "remaining_time": "1:30:40"}
{"current_steps": 3835, "total_steps": 4585, "loss": 0.4, "lr": 3.181668719834745e-06, "epoch": 5.855614973262032, "percentage": 83.64, "elapsed_time": "7:40:34", "remaining_time": "1:30:04"}
{"current_steps": 3840, "total_steps": 4585, "loss": 0.415, "lr": 3.14058567461722e-06, "epoch": 5.863254392666157, "percentage": 83.75, "elapsed_time": "7:41:16", "remaining_time": "1:29:29"}
{"current_steps": 3845, "total_steps": 4585, "loss": 0.4349, "lr": 3.0997469855452222e-06, "epoch": 5.870893812070283, "percentage": 83.86, "elapsed_time": "7:41:49", "remaining_time": "1:28:52"}
{"current_steps": 3850, "total_steps": 4585, "loss": 0.4424, "lr": 3.0591532445245155e-06, "epoch": 5.878533231474408, "percentage": 83.97, "elapsed_time": "7:42:16", "remaining_time": "1:28:15"}
{"current_steps": 3855, "total_steps": 4585, "loss": 0.414, "lr": 3.0188050399106726e-06, "epoch": 5.8861726508785335, "percentage": 84.08, "elapsed_time": "7:42:55", "remaining_time": "1:27:39"}
{"current_steps": 3860, "total_steps": 4585, "loss": 0.4129, "lr": 2.9787029565004856e-06, "epoch": 5.893812070282658, "percentage": 84.19, "elapsed_time": "7:43:32", "remaining_time": "1:27:03"}
{"current_steps": 3865, "total_steps": 4585, "loss": 0.3855, "lr": 2.93884757552356e-06, "epoch": 5.901451489686783, "percentage": 84.3, "elapsed_time": "7:44:15", "remaining_time": "1:26:29"}
{"current_steps": 3870, "total_steps": 4585, "loss": 0.4305, "lr": 2.8992394746338457e-06, "epoch": 5.909090909090909, "percentage": 84.41, "elapsed_time": "7:45:00", "remaining_time": "1:25:54"}
{"current_steps": 3875, "total_steps": 4585, "loss": 0.4229, "lr": 2.8598792279012745e-06, "epoch": 5.916730328495034, "percentage": 84.51, "elapsed_time": "7:45:31", "remaining_time": "1:25:17"}
{"current_steps": 3880, "total_steps": 4585, "loss": 0.4367, "lr": 2.8207674058034374e-06, "epoch": 5.92436974789916, "percentage": 84.62, "elapsed_time": "7:46:05", "remaining_time": "1:24:41"}
{"current_steps": 3885, "total_steps": 4585, "loss": 0.3896, "lr": 2.7819045752173425e-06, "epoch": 5.932009167303285, "percentage": 84.73, "elapsed_time": "7:46:51", "remaining_time": "1:24:07"}
{"current_steps": 3890, "total_steps": 4585, "loss": 0.4329, "lr": 2.7432912994111417e-06, "epoch": 5.93964858670741, "percentage": 84.84, "elapsed_time": "7:47:31", "remaining_time": "1:23:31"}
{"current_steps": 3895, "total_steps": 4585, "loss": 0.443, "lr": 2.7049281380360382e-06, "epoch": 5.947288006111536, "percentage": 84.95, "elapsed_time": "7:48:06", "remaining_time": "1:22:55"}
{"current_steps": 3900, "total_steps": 4585, "loss": 0.4348, "lr": 2.666815647118117e-06, "epoch": 5.954927425515661, "percentage": 85.06, "elapsed_time": "7:48:34", "remaining_time": "1:22:18"}
{"current_steps": 3905, "total_steps": 4585, "loss": 0.4034, "lr": 2.6289543790503103e-06, "epoch": 5.962566844919786, "percentage": 85.17, "elapsed_time": "7:49:14", "remaining_time": "1:21:42"}
{"current_steps": 3910, "total_steps": 4585, "loss": 0.4449, "lr": 2.591344882584401e-06, "epoch": 5.970206264323911, "percentage": 85.28, "elapsed_time": "7:49:48", "remaining_time": "1:21:06"}
{"current_steps": 3915, "total_steps": 4585, "loss": 0.4289, "lr": 2.5539877028230442e-06, "epoch": 5.977845683728036, "percentage": 85.39, "elapsed_time": "7:50:29", "remaining_time": "1:20:31"}
{"current_steps": 3920, "total_steps": 4585, "loss": 0.4427, "lr": 2.5168833812118855e-06, "epoch": 5.985485103132162, "percentage": 85.5, "elapsed_time": "7:51:02", "remaining_time": "1:19:54"}
{"current_steps": 3925, "total_steps": 4585, "loss": 0.4061, "lr": 2.480032455531707e-06, "epoch": 5.993124522536287, "percentage": 85.61, "elapsed_time": "7:51:38", "remaining_time": "1:19:18"}
{"current_steps": 3930, "total_steps": 4585, "loss": 0.4544, "lr": 2.443435459890626e-06, "epoch": 6.0, "percentage": 85.71, "elapsed_time": "7:52:08", "remaining_time": "1:18:41"}
{"current_steps": 3935, "total_steps": 4585, "loss": 0.4425, "lr": 2.4070929247163764e-06, "epoch": 6.007639419404125, "percentage": 85.82, "elapsed_time": "7:52:45", "remaining_time": "1:18:05"}
{"current_steps": 3940, "total_steps": 4585, "loss": 0.381, "lr": 2.371005376748596e-06, "epoch": 6.015278838808251, "percentage": 85.93, "elapsed_time": "7:53:19", "remaining_time": "1:17:29"}
{"current_steps": 3945, "total_steps": 4585, "loss": 0.4147, "lr": 2.3351733390312005e-06, "epoch": 6.022918258212376, "percentage": 86.04, "elapsed_time": "7:53:56", "remaining_time": "1:16:53"}
{"current_steps": 3950, "total_steps": 4585, "loss": 0.3916, "lr": 2.2995973309048013e-06, "epoch": 6.0305576776165015, "percentage": 86.15, "elapsed_time": "7:54:34", "remaining_time": "1:16:17"}
{"current_steps": 3955, "total_steps": 4585, "loss": 0.441, "lr": 2.2642778679992007e-06, "epoch": 6.0381970970206265, "percentage": 86.26, "elapsed_time": "7:55:06", "remaining_time": "1:15:40"}
{"current_steps": 3960, "total_steps": 4585, "loss": 0.4039, "lr": 2.2292154622258623e-06, "epoch": 6.045836516424751, "percentage": 86.37, "elapsed_time": "7:55:38", "remaining_time": "1:15:04"}
{"current_steps": 3965, "total_steps": 4585, "loss": 0.395, "lr": 2.194410621770566e-06, "epoch": 6.053475935828877, "percentage": 86.48, "elapsed_time": "7:56:13", "remaining_time": "1:14:27"}
{"current_steps": 3970, "total_steps": 4585, "loss": 0.3969, "lr": 2.1598638510859795e-06, "epoch": 6.061115355233002, "percentage": 86.59, "elapsed_time": "7:56:52", "remaining_time": "1:13:52"}
{"current_steps": 3975, "total_steps": 4585, "loss": 0.4092, "lr": 2.1255756508843774e-06, "epoch": 6.068754774637128, "percentage": 86.7, "elapsed_time": "7:57:32", "remaining_time": "1:13:16"}
{"current_steps": 3980, "total_steps": 4585, "loss": 0.4309, "lr": 2.0915465181303874e-06, "epoch": 6.076394194041253, "percentage": 86.8, "elapsed_time": "7:58:05", "remaining_time": "1:12:40"}
{"current_steps": 3985, "total_steps": 4585, "loss": 0.396, "lr": 2.057776946033765e-06, "epoch": 6.084033613445378, "percentage": 86.91, "elapsed_time": "7:58:42", "remaining_time": "1:12:04"}
{"current_steps": 3990, "total_steps": 4585, "loss": 0.404, "lr": 2.0242674240422655e-06, "epoch": 6.091673032849504, "percentage": 87.02, "elapsed_time": "7:59:14", "remaining_time": "1:11:27"}
{"current_steps": 3995, "total_steps": 4585, "loss": 0.4378, "lr": 1.991018437834542e-06, "epoch": 6.099312452253629, "percentage": 87.13, "elapsed_time": "7:59:52", "remaining_time": "1:10:52"}
{"current_steps": 4000, "total_steps": 4585, "loss": 0.4248, "lr": 1.9580304693131015e-06, "epoch": 6.106951871657754, "percentage": 87.24, "elapsed_time": "8:00:22", "remaining_time": "1:10:15"}
{"current_steps": 4005, "total_steps": 4585, "loss": 0.3909, "lr": 1.925303996597341e-06, "epoch": 6.114591291061879, "percentage": 87.35, "elapsed_time": "8:01:01", "remaining_time": "1:09:39"}
{"current_steps": 4010, "total_steps": 4585, "loss": 0.422, "lr": 1.8928394940165828e-06, "epoch": 6.122230710466004, "percentage": 87.46, "elapsed_time": "8:01:33", "remaining_time": "1:09:03"}
{"current_steps": 4015, "total_steps": 4585, "loss": 0.4067, "lr": 1.860637432103234e-06, "epoch": 6.12987012987013, "percentage": 87.57, "elapsed_time": "8:02:10", "remaining_time": "1:08:27"}
{"current_steps": 4020, "total_steps": 4585, "loss": 0.3906, "lr": 1.8286982775859407e-06, "epoch": 6.137509549274255, "percentage": 87.68, "elapsed_time": "8:02:52", "remaining_time": "1:07:51"}
{"current_steps": 4025, "total_steps": 4585, "loss": 0.4181, "lr": 1.7970224933828539e-06, "epoch": 6.145148968678381, "percentage": 87.79, "elapsed_time": "8:03:32", "remaining_time": "1:07:16"}
{"current_steps": 4030, "total_steps": 4585, "loss": 0.3878, "lr": 1.7656105385948708e-06, "epoch": 6.152788388082506, "percentage": 87.9, "elapsed_time": "8:04:14", "remaining_time": "1:06:41"}
{"current_steps": 4035, "total_steps": 4585, "loss": 0.4066, "lr": 1.7344628684990405e-06, "epoch": 6.160427807486631, "percentage": 88.0, "elapsed_time": "8:04:50", "remaining_time": "1:06:05"}
{"current_steps": 4040, "total_steps": 4585, "loss": 0.4129, "lr": 1.7035799345419212e-06, "epoch": 6.168067226890757, "percentage": 88.11, "elapsed_time": "8:05:20", "remaining_time": "1:05:28"}
{"current_steps": 4045, "total_steps": 4585, "loss": 0.4063, "lr": 1.672962184333049e-06, "epoch": 6.1757066462948815, "percentage": 88.22, "elapsed_time": "8:06:10", "remaining_time": "1:04:54"}
{"current_steps": 4050, "total_steps": 4585, "loss": 0.4065, "lr": 1.6426100616384654e-06, "epoch": 6.1833460656990065, "percentage": 88.33, "elapsed_time": "8:06:52", "remaining_time": "1:04:18"}
{"current_steps": 4055, "total_steps": 4585, "loss": 0.3991, "lr": 1.6125240063742565e-06, "epoch": 6.190985485103132, "percentage": 88.44, "elapsed_time": "8:07:31", "remaining_time": "1:03:43"}
{"current_steps": 4060, "total_steps": 4585, "loss": 0.3961, "lr": 1.582704454600208e-06, "epoch": 6.198624904507257, "percentage": 88.55, "elapsed_time": "8:08:00", "remaining_time": "1:03:06"}
{"current_steps": 4065, "total_steps": 4585, "loss": 0.3997, "lr": 1.5531518385134625e-06, "epoch": 6.206264323911383, "percentage": 88.66, "elapsed_time": "8:08:32", "remaining_time": "1:02:29"}
{"current_steps": 4070, "total_steps": 4585, "loss": 0.4392, "lr": 1.5238665864422665e-06, "epoch": 6.213903743315508, "percentage": 88.77, "elapsed_time": "8:09:12", "remaining_time": "1:01:54"}
{"current_steps": 4075, "total_steps": 4585, "loss": 0.3981, "lr": 1.4948491228397544e-06, "epoch": 6.221543162719633, "percentage": 88.88, "elapsed_time": "8:09:45", "remaining_time": "1:01:17"}
{"current_steps": 4080, "total_steps": 4585, "loss": 0.3941, "lr": 1.4660998682778105e-06, "epoch": 6.229182582123759, "percentage": 88.99, "elapsed_time": "8:10:16", "remaining_time": "1:00:41"}
{"current_steps": 4085, "total_steps": 4585, "loss": 0.3894, "lr": 1.4376192394409571e-06, "epoch": 6.236822001527884, "percentage": 89.09, "elapsed_time": "8:10:45", "remaining_time": "1:00:04"}
{"current_steps": 4090, "total_steps": 4585, "loss": 0.4365, "lr": 1.409407649120318e-06, "epoch": 6.2444614209320095, "percentage": 89.2, "elapsed_time": "8:11:17", "remaining_time": "0:59:27"}
{"current_steps": 4095, "total_steps": 4585, "loss": 0.4201, "lr": 1.38146550620766e-06, "epoch": 6.2521008403361344, "percentage": 89.31, "elapsed_time": "8:11:52", "remaining_time": "0:58:51"}
{"current_steps": 4100, "total_steps": 4585, "loss": 0.4405, "lr": 1.353793215689414e-06, "epoch": 6.259740259740259, "percentage": 89.42, "elapsed_time": "8:12:28", "remaining_time": "0:58:15"}
{"current_steps": 4105, "total_steps": 4585, "loss": 0.4023, "lr": 1.326391178640869e-06, "epoch": 6.267379679144385, "percentage": 89.53, "elapsed_time": "8:13:01", "remaining_time": "0:57:38"}
{"current_steps": 4110, "total_steps": 4585, "loss": 0.4166, "lr": 1.2992597922203087e-06, "epoch": 6.27501909854851, "percentage": 89.64, "elapsed_time": "8:13:31", "remaining_time": "0:57:02"}
{"current_steps": 4115, "total_steps": 4585, "loss": 0.389, "lr": 1.2723994496632775e-06, "epoch": 6.282658517952636, "percentage": 89.75, "elapsed_time": "8:14:08", "remaining_time": "0:56:26"}
{"current_steps": 4120, "total_steps": 4585, "loss": 0.4135, "lr": 1.2458105402768905e-06, "epoch": 6.290297937356761, "percentage": 89.86, "elapsed_time": "8:14:48", "remaining_time": "0:55:50"}
{"current_steps": 4125, "total_steps": 4585, "loss": 0.4354, "lr": 1.2194934494341548e-06, "epoch": 6.297937356760886, "percentage": 89.97, "elapsed_time": "8:15:30", "remaining_time": "0:55:15"}
{"current_steps": 4130, "total_steps": 4585, "loss": 0.4045, "lr": 1.1934485585684286e-06, "epoch": 6.305576776165012, "percentage": 90.08, "elapsed_time": "8:16:05", "remaining_time": "0:54:39"}
{"current_steps": 4135, "total_steps": 4585, "loss": 0.4074, "lr": 1.1676762451678592e-06, "epoch": 6.313216195569137, "percentage": 90.19, "elapsed_time": "8:16:46", "remaining_time": "0:54:03"}
{"current_steps": 4140, "total_steps": 4585, "loss": 0.3883, "lr": 1.1421768827699297e-06, "epoch": 6.320855614973262, "percentage": 90.29, "elapsed_time": "8:17:27", "remaining_time": "0:53:28"}
{"current_steps": 4145, "total_steps": 4585, "loss": 0.3842, "lr": 1.1169508409560326e-06, "epoch": 6.328495034377387, "percentage": 90.4, "elapsed_time": "8:18:01", "remaining_time": "0:52:51"}
{"current_steps": 4150, "total_steps": 4585, "loss": 0.4035, "lr": 1.091998485346133e-06, "epoch": 6.336134453781512, "percentage": 90.51, "elapsed_time": "8:18:31", "remaining_time": "0:52:15"}
{"current_steps": 4155, "total_steps": 4585, "loss": 0.4323, "lr": 1.067320177593445e-06, "epoch": 6.343773873185638, "percentage": 90.62, "elapsed_time": "8:19:06", "remaining_time": "0:51:39"}
{"current_steps": 4160, "total_steps": 4585, "loss": 0.3926, "lr": 1.0429162753792044e-06, "epoch": 6.351413292589763, "percentage": 90.73, "elapsed_time": "8:19:45", "remaining_time": "0:51:03"}
{"current_steps": 4165, "total_steps": 4585, "loss": 0.3856, "lr": 1.0187871324074817e-06, "epoch": 6.359052711993888, "percentage": 90.84, "elapsed_time": "8:20:16", "remaining_time": "0:50:26"}
{"current_steps": 4170, "total_steps": 4585, "loss": 0.4099, "lr": 9.94933098400055e-07, "epoch": 6.366692131398014, "percentage": 90.95, "elapsed_time": "8:20:59", "remaining_time": "0:49:51"}
{"current_steps": 4175, "total_steps": 4585, "loss": 0.4277, "lr": 9.713545190913476e-07, "epoch": 6.374331550802139, "percentage": 91.06, "elapsed_time": "8:21:28", "remaining_time": "0:49:14"}
{"current_steps": 4180, "total_steps": 4585, "loss": 0.3976, "lr": 9.480517362234032e-07, "epoch": 6.381970970206265, "percentage": 91.17, "elapsed_time": "8:21:57", "remaining_time": "0:48:38"}
{"current_steps": 4185, "total_steps": 4585, "loss": 0.393, "lr": 9.250250875409383e-07, "epoch": 6.3896103896103895, "percentage": 91.28, "elapsed_time": "8:22:31", "remaining_time": "0:48:01"}
{"current_steps": 4190, "total_steps": 4585, "loss": 0.3939, "lr": 9.022749067864689e-07, "epoch": 6.3972498090145145, "percentage": 91.38, "elapsed_time": "8:23:05", "remaining_time": "0:47:25"}
{"current_steps": 4195, "total_steps": 4585, "loss": 0.3922, "lr": 8.798015236954227e-07, "epoch": 6.40488922841864, "percentage": 91.49, "elapsed_time": "8:23:40", "remaining_time": "0:46:49"}
{"current_steps": 4200, "total_steps": 4585, "loss": 0.3943, "lr": 8.57605263991419e-07, "epoch": 6.412528647822765, "percentage": 91.6, "elapsed_time": "8:24:25", "remaining_time": "0:46:14"}
{"current_steps": 4205, "total_steps": 4585, "loss": 0.3897, "lr": 8.356864493815075e-07, "epoch": 6.420168067226891, "percentage": 91.71, "elapsed_time": "8:25:00", "remaining_time": "0:45:38"}
{"current_steps": 4210, "total_steps": 4585, "loss": 0.4303, "lr": 8.14045397551515e-07, "epoch": 6.427807486631016, "percentage": 91.82, "elapsed_time": "8:25:29", "remaining_time": "0:45:01"}
{"current_steps": 4215, "total_steps": 4585, "loss": 0.394, "lr": 7.926824221614504e-07, "epoch": 6.435446906035141, "percentage": 91.93, "elapsed_time": "8:26:07", "remaining_time": "0:44:25"}
{"current_steps": 4220, "total_steps": 4585, "loss": 0.438, "lr": 7.715978328409557e-07, "epoch": 6.443086325439267, "percentage": 92.04, "elapsed_time": "8:26:39", "remaining_time": "0:43:49"}
{"current_steps": 4225, "total_steps": 4585, "loss": 0.4103, "lr": 7.507919351847981e-07, "epoch": 6.450725744843392, "percentage": 92.15, "elapsed_time": "8:27:17", "remaining_time": "0:43:13"}
{"current_steps": 4230, "total_steps": 4585, "loss": 0.423, "lr": 7.30265030748476e-07, "epoch": 6.4583651642475175, "percentage": 92.26, "elapsed_time": "8:27:48", "remaining_time": "0:42:37"}
{"current_steps": 4235, "total_steps": 4585, "loss": 0.4379, "lr": 7.100174170438201e-07, "epoch": 6.466004583651642, "percentage": 92.37, "elapsed_time": "8:28:22", "remaining_time": "0:42:00"}
{"current_steps": 4240, "total_steps": 4585, "loss": 0.4064, "lr": 6.900493875346881e-07, "epoch": 6.473644003055767, "percentage": 92.48, "elapsed_time": "8:28:57", "remaining_time": "0:41:24"}
{"current_steps": 4245, "total_steps": 4585, "loss": 0.3957, "lr": 6.703612316327235e-07, "epoch": 6.481283422459893, "percentage": 92.58, "elapsed_time": "8:29:35", "remaining_time": "0:40:48"}
{"current_steps": 4250, "total_steps": 4585, "loss": 0.427, "lr": 6.509532346931458e-07, "epoch": 6.488922841864018, "percentage": 92.69, "elapsed_time": "8:30:07", "remaining_time": "0:40:12"}
{"current_steps": 4255, "total_steps": 4585, "loss": 0.3992, "lr": 6.318256780106202e-07, "epoch": 6.496562261268144, "percentage": 92.8, "elapsed_time": "8:30:44", "remaining_time": "0:39:36"}
{"current_steps": 4260, "total_steps": 4585, "loss": 0.4374, "lr": 6.129788388151837e-07, "epoch": 6.504201680672269, "percentage": 92.91, "elapsed_time": "8:31:05", "remaining_time": "0:38:59"}
{"current_steps": 4265, "total_steps": 4585, "loss": 0.4113, "lr": 5.94412990268216e-07, "epoch": 6.511841100076394, "percentage": 93.02, "elapsed_time": "8:31:42", "remaining_time": "0:38:23"}
{"current_steps": 4270, "total_steps": 4585, "loss": 0.4191, "lr": 5.761284014585044e-07, "epoch": 6.51948051948052, "percentage": 93.13, "elapsed_time": "8:32:21", "remaining_time": "0:37:47"}
{"current_steps": 4275, "total_steps": 4585, "loss": 0.4025, "lr": 5.581253373983097e-07, "epoch": 6.527119938884645, "percentage": 93.24, "elapsed_time": "8:32:48", "remaining_time": "0:37:11"}
{"current_steps": 4280, "total_steps": 4585, "loss": 0.4055, "lr": 5.404040590195548e-07, "epoch": 6.53475935828877, "percentage": 93.35, "elapsed_time": "8:33:23", "remaining_time": "0:36:35"}
{"current_steps": 4285, "total_steps": 4585, "loss": 0.4031, "lr": 5.229648231700246e-07, "epoch": 6.542398777692895, "percentage": 93.46, "elapsed_time": "8:34:00", "remaining_time": "0:35:59"}
{"current_steps": 4290, "total_steps": 4585, "loss": 0.4204, "lr": 5.058078826096613e-07, "epoch": 6.55003819709702, "percentage": 93.57, "elapsed_time": "8:34:39", "remaining_time": "0:35:23"}
{"current_steps": 4295, "total_steps": 4585, "loss": 0.4115, "lr": 4.889334860068706e-07, "epoch": 6.557677616501146, "percentage": 93.68, "elapsed_time": "8:35:13", "remaining_time": "0:34:47"}
{"current_steps": 4300, "total_steps": 4585, "loss": 0.3866, "lr": 4.723418779349542e-07, "epoch": 6.565317035905271, "percentage": 93.78, "elapsed_time": "8:35:51", "remaining_time": "0:34:11"}
{"current_steps": 4305, "total_steps": 4585, "loss": 0.426, "lr": 4.560332988685412e-07, "epoch": 6.572956455309397, "percentage": 93.89, "elapsed_time": "8:36:28", "remaining_time": "0:33:35"}
{"current_steps": 4310, "total_steps": 4585, "loss": 0.3835, "lr": 4.40007985180102e-07, "epoch": 6.580595874713522, "percentage": 94.0, "elapsed_time": "8:36:58", "remaining_time": "0:32:59"}
{"current_steps": 4315, "total_steps": 4585, "loss": 0.4255, "lr": 4.242661691365446e-07, "epoch": 6.588235294117647, "percentage": 94.11, "elapsed_time": "8:37:28", "remaining_time": "0:32:22"}
{"current_steps": 4320, "total_steps": 4585, "loss": 0.3911, "lr": 4.088080788958171e-07, "epoch": 6.595874713521773, "percentage": 94.22, "elapsed_time": "8:37:59", "remaining_time": "0:31:46"}
{"current_steps": 4325, "total_steps": 4585, "loss": 0.41, "lr": 3.936339385036236e-07, "epoch": 6.6035141329258975, "percentage": 94.33, "elapsed_time": "8:38:31", "remaining_time": "0:31:10"}
{"current_steps": 4330, "total_steps": 4585, "loss": 0.395, "lr": 3.787439678901739e-07, "epoch": 6.611153552330023, "percentage": 94.44, "elapsed_time": "8:39:18", "remaining_time": "0:30:34"}
{"current_steps": 4335, "total_steps": 4585, "loss": 0.4145, "lr": 3.641383828669831e-07, "epoch": 6.618792971734148, "percentage": 94.55, "elapsed_time": "8:39:51", "remaining_time": "0:29:58"}
{"current_steps": 4340, "total_steps": 4585, "loss": 0.4177, "lr": 3.498173951237593e-07, "epoch": 6.626432391138273, "percentage": 94.66, "elapsed_time": "8:40:41", "remaining_time": "0:29:23"}
{"current_steps": 4345, "total_steps": 4585, "loss": 0.4204, "lr": 3.3578121222532565e-07, "epoch": 6.634071810542399, "percentage": 94.77, "elapsed_time": "8:41:13", "remaining_time": "0:28:47"}
{"current_steps": 4350, "total_steps": 4585, "loss": 0.4402, "lr": 3.2203003760861827e-07, "epoch": 6.641711229946524, "percentage": 94.87, "elapsed_time": "8:41:53", "remaining_time": "0:28:11"}
{"current_steps": 4355, "total_steps": 4585, "loss": 0.4008, "lr": 3.085640705797266e-07, "epoch": 6.64935064935065, "percentage": 94.98, "elapsed_time": "8:42:29", "remaining_time": "0:27:35"}
{"current_steps": 4360, "total_steps": 4585, "loss": 0.3911, "lr": 2.953835063110222e-07, "epoch": 6.656990068754775, "percentage": 95.09, "elapsed_time": "8:43:08", "remaining_time": "0:26:59"}
{"current_steps": 4365, "total_steps": 4585, "loss": 0.4095, "lr": 2.824885358383123e-07, "epoch": 6.6646294881589, "percentage": 95.2, "elapsed_time": "8:43:38", "remaining_time": "0:26:23"}
{"current_steps": 4370, "total_steps": 4585, "loss": 0.454, "lr": 2.6987934605808617e-07, "epoch": 6.6722689075630255, "percentage": 95.31, "elapsed_time": "8:44:07", "remaining_time": "0:25:47"}
{"current_steps": 4375, "total_steps": 4585, "loss": 0.4354, "lr": 2.575561197247911e-07, "epoch": 6.67990832696715, "percentage": 95.42, "elapsed_time": "8:44:41", "remaining_time": "0:25:11"}
{"current_steps": 4380, "total_steps": 4585, "loss": 0.3982, "lr": 2.4551903544819625e-07, "epoch": 6.687547746371276, "percentage": 95.53, "elapsed_time": "8:45:13", "remaining_time": "0:24:34"}
{"current_steps": 4385, "total_steps": 4585, "loss": 0.3993, "lr": 2.3376826769080153e-07, "epoch": 6.695187165775401, "percentage": 95.64, "elapsed_time": "8:45:46", "remaining_time": "0:23:58"}
{"current_steps": 4390, "total_steps": 4585, "loss": 0.3856, "lr": 2.2230398676529763e-07, "epoch": 6.702826585179526, "percentage": 95.75, "elapsed_time": "8:46:27", "remaining_time": "0:23:23"}
{"current_steps": 4395, "total_steps": 4585, "loss": 0.4006, "lr": 2.1112635883211663e-07, "epoch": 6.710466004583652, "percentage": 95.86, "elapsed_time": "8:47:09", "remaining_time": "0:22:47"}
{"current_steps": 4400, "total_steps": 4585, "loss": 0.4371, "lr": 2.0023554589701177e-07, "epoch": 6.718105423987777, "percentage": 95.97, "elapsed_time": "8:47:44", "remaining_time": "0:22:11"}
{"current_steps": 4405, "total_steps": 4585, "loss": 0.3804, "lr": 1.8963170580870384e-07, "epoch": 6.725744843391903, "percentage": 96.07, "elapsed_time": "8:48:18", "remaining_time": "0:21:35"}
{"current_steps": 4410, "total_steps": 4585, "loss": 0.389, "lr": 1.793149922566051e-07, "epoch": 6.733384262796028, "percentage": 96.18, "elapsed_time": "8:48:58", "remaining_time": "0:20:59"}
{"current_steps": 4415, "total_steps": 4585, "loss": 0.3947, "lr": 1.6928555476859454e-07, "epoch": 6.741023682200153, "percentage": 96.29, "elapsed_time": "8:49:32", "remaining_time": "0:20:23"}
{"current_steps": 4420, "total_steps": 4585, "loss": 0.3938, "lr": 1.5954353870883289e-07, "epoch": 6.748663101604278, "percentage": 96.4, "elapsed_time": "8:50:10", "remaining_time": "0:19:47"}
{"current_steps": 4425, "total_steps": 4585, "loss": 0.424, "lr": 1.500890852756709e-07, "epoch": 6.756302521008403, "percentage": 96.51, "elapsed_time": "8:50:39", "remaining_time": "0:19:11"}
{"current_steps": 4430, "total_steps": 4585, "loss": 0.4071, "lr": 1.409223314996e-07, "epoch": 6.763941940412528, "percentage": 96.62, "elapsed_time": "8:51:10", "remaining_time": "0:18:35"}
{"current_steps": 4435, "total_steps": 4585, "loss": 0.4216, "lr": 1.3204341024125822e-07, "epoch": 6.771581359816654, "percentage": 96.73, "elapsed_time": "8:51:52", "remaining_time": "0:17:59"}
{"current_steps": 4440, "total_steps": 4585, "loss": 0.4104, "lr": 1.234524501895207e-07, "epoch": 6.779220779220779, "percentage": 96.84, "elapsed_time": "8:52:33", "remaining_time": "0:17:23"}
{"current_steps": 4445, "total_steps": 4585, "loss": 0.4265, "lr": 1.1514957585961884e-07, "epoch": 6.786860198624905, "percentage": 96.95, "elapsed_time": "8:53:01", "remaining_time": "0:16:47"}
{"current_steps": 4450, "total_steps": 4585, "loss": 0.4298, "lr": 1.0713490759133749e-07, "epoch": 6.79449961802903, "percentage": 97.06, "elapsed_time": "8:53:31", "remaining_time": "0:16:11"}
{"current_steps": 4455, "total_steps": 4585, "loss": 0.4038, "lr": 9.940856154728285e-08, "epoch": 6.802139037433155, "percentage": 97.16, "elapsed_time": "8:54:09", "remaining_time": "0:15:35"}
{"current_steps": 4460, "total_steps": 4585, "loss": 0.4128, "lr": 9.197064971118608e-08, "epoch": 6.809778456837281, "percentage": 97.27, "elapsed_time": "8:54:45", "remaining_time": "0:14:59"}
{"current_steps": 4465, "total_steps": 4585, "loss": 0.3957, "lr": 8.482127988628686e-08, "epoch": 6.8174178762414055, "percentage": 97.38, "elapsed_time": "8:55:21", "remaining_time": "0:14:23"}
{"current_steps": 4470, "total_steps": 4585, "loss": 0.3905, "lr": 7.79605556937657e-08, "epoch": 6.825057295645531, "percentage": 97.49, "elapsed_time": "8:56:08", "remaining_time": "0:13:47"}
{"current_steps": 4475, "total_steps": 4585, "loss": 0.3832, "lr": 7.138857657125187e-08, "epoch": 6.832696715049656, "percentage": 97.6, "elapsed_time": "8:56:45", "remaining_time": "0:13:11"}
{"current_steps": 4480, "total_steps": 4585, "loss": 0.4065, "lr": 6.510543777136446e-08, "epoch": 6.840336134453781, "percentage": 97.71, "elapsed_time": "8:57:27", "remaining_time": "0:12:35"}
{"current_steps": 4485, "total_steps": 4585, "loss": 0.4075, "lr": 5.9111230360358044e-08, "epoch": 6.847975553857907, "percentage": 97.82, "elapsed_time": "8:57:52", "remaining_time": "0:11:59"}
{"current_steps": 4490, "total_steps": 4585, "loss": 0.4429, "lr": 5.340604121677251e-08, "epoch": 6.855614973262032, "percentage": 97.93, "elapsed_time": "8:58:31", "remaining_time": "0:11:23"}
{"current_steps": 4495, "total_steps": 4585, "loss": 0.4006, "lr": 4.798995303020082e-08, "epoch": 6.863254392666157, "percentage": 98.04, "elapsed_time": "8:59:08", "remaining_time": "0:10:47"}
{"current_steps": 4500, "total_steps": 4585, "loss": 0.4184, "lr": 4.286304430006993e-08, "epoch": 6.870893812070283, "percentage": 98.15, "elapsed_time": "8:59:50", "remaining_time": "0:10:11"}
{"current_steps": 4505, "total_steps": 4585, "loss": 0.3843, "lr": 3.802538933451949e-08, "epoch": 6.878533231474408, "percentage": 98.26, "elapsed_time": "9:01:08", "remaining_time": "0:09:36"}
{"current_steps": 4510, "total_steps": 4585, "loss": 0.3997, "lr": 3.34770582493138e-08, "epoch": 6.8861726508785335, "percentage": 98.36, "elapsed_time": "9:01:44", "remaining_time": "0:09:00"}
{"current_steps": 4515, "total_steps": 4585, "loss": 0.4075, "lr": 2.921811696682708e-08, "epoch": 6.893812070282658, "percentage": 98.47, "elapsed_time": "9:02:18", "remaining_time": "0:08:24"}
{"current_steps": 4520, "total_steps": 4585, "loss": 0.415, "lr": 2.5248627215093135e-08, "epoch": 6.901451489686783, "percentage": 98.58, "elapsed_time": "9:02:51", "remaining_time": "0:07:48"}
{"current_steps": 4525, "total_steps": 4585, "loss": 0.4057, "lr": 2.1568646526906045e-08, "epoch": 6.909090909090909, "percentage": 98.69, "elapsed_time": "9:03:21", "remaining_time": "0:07:12"}
{"current_steps": 4530, "total_steps": 4585, "loss": 0.4415, "lr": 1.8178228238985296e-08, "epoch": 6.916730328495034, "percentage": 98.8, "elapsed_time": "9:04:00", "remaining_time": "0:06:36"}
{"current_steps": 4535, "total_steps": 4585, "loss": 0.438, "lr": 1.507742149121194e-08, "epoch": 6.92436974789916, "percentage": 98.91, "elapsed_time": "9:04:37", "remaining_time": "0:06:00"}
{"current_steps": 4540, "total_steps": 4585, "loss": 0.406, "lr": 1.2266271225902515e-08, "epoch": 6.932009167303285, "percentage": 99.02, "elapsed_time": "9:05:21", "remaining_time": "0:05:24"}
{"current_steps": 4545, "total_steps": 4585, "loss": 0.4244, "lr": 9.744818187169547e-09, "epoch": 6.93964858670741, "percentage": 99.13, "elapsed_time": "9:05:53", "remaining_time": "0:04:48"}
{"current_steps": 4550, "total_steps": 4585, "loss": 0.4061, "lr": 7.513098920324257e-09, "epoch": 6.947288006111536, "percentage": 99.24, "elapsed_time": "9:06:33", "remaining_time": "0:04:12"}
{"current_steps": 4555, "total_steps": 4585, "loss": 0.4024, "lr": 5.571145771345876e-09, "epoch": 6.954927425515661, "percentage": 99.35, "elapsed_time": "9:07:10", "remaining_time": "0:03:36"}
{"current_steps": 4560, "total_steps": 4585, "loss": 0.3819, "lr": 3.918986886424225e-09, "epoch": 6.962566844919786, "percentage": 99.45, "elapsed_time": "9:07:49", "remaining_time": "0:03:00"}
{"current_steps": 4565, "total_steps": 4585, "loss": 0.4236, "lr": 2.5566462115333978e-09, "epoch": 6.970206264323911, "percentage": 99.56, "elapsed_time": "9:08:29", "remaining_time": "0:02:24"}
{"current_steps": 4570, "total_steps": 4585, "loss": 0.3961, "lr": 1.484143492100909e-09, "epoch": 6.977845683728036, "percentage": 99.67, "elapsed_time": "9:09:10", "remaining_time": "0:01:48"}
{"current_steps": 4575, "total_steps": 4585, "loss": 0.4307, "lr": 7.014942727145979e-10, "epoch": 6.985485103132162, "percentage": 99.78, "elapsed_time": "9:09:38", "remaining_time": "0:01:12"}
{"current_steps": 4580, "total_steps": 4585, "loss": 0.408, "lr": 2.0870989689614208e-10, "epoch": 6.993124522536287, "percentage": 99.89, "elapsed_time": "9:10:17", "remaining_time": "0:00:36"}
{"current_steps": 4585, "total_steps": 4585, "loss": 0.3911, "lr": 5.797506938964859e-12, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "9:10:51", "remaining_time": "0:00:00"}
{"current_steps": 4585, "total_steps": 4585, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "9:11:18", "remaining_time": "0:00:00"}

10134
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 sha256:5d6faf1b5569fa0dcddacae4051dbd6eeb5a139c0334eb770f3e78482d44cef4
size 8657

BIN
training_loss.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 45 KiB

1
vocab.json Normal file

File diff suppressed because one or more lines are too long