初始化项目,由ModelHub XC社区提供模型

Model: modrill/qwen3-4b-think-baseline-full-sft
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-26 22:34:10 +08:00
commit 84ba2b4166
11 changed files with 493 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

12
MANIFEST.txt Normal file
View File

@@ -0,0 +1,12 @@
name: think_baseline
base_model: Qwen3-4B-Base
method: full SFT (ZeRO-3)
dataset: think_all
template: qwen3
epochs: 2
seed: 42
cutoff_len: 24576
learning_rate: 2e-5
train_loss: 0.6698
train_steps: 838
finished_at: 2026-06-08 00:22 CST

66
README.md Normal file
View File

@@ -0,0 +1,66 @@
---
license: apache-2.0
base_model: Qwen/Qwen3-4B-Base
tags:
- qwen3
- code
- sft
- full-sft
- think
- llama-factory
language:
- en
- zh
library_name: transformers
pipeline_tag: text-generation
---
# Qwen3-4B Code SFT - Think Baseline (Full SFT)
Full-parameter supervised fine-tuning (not LoRA) of [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) on the think_all dataset with thinking mode enabled.
**This repo contains native full fine-tuned weights** (single `model.safetensors`, ~7.5 GB). For LoRA adapters merged into base weights, see [modrill/qwen3-4b-think-baseline-lora-sft](https://huggingface.co/modrill/qwen3-4b-think-baseline-lora-sft).
## Model Details
- **Base model:** Qwen/Qwen3-4B-Base
- **Fine-tuning:** Full SFT (DeepSpeed ZeRO-3), finetuning_type: full
- **Dataset:** think_all
- **Mode:** Think (`enable_thinking=true`)
- **Training cutoff length:** 24576 tokens
- **Epochs:** 2
- **Learning rate:** 2e-5
- **Train loss:** ~0.67
- **Finished:** 2026-06-08
## Usage
### HuggingFace Transformers
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "modrill/qwen3-4b-think-baseline-full-sft"
tok = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model_id, trust_remote_code=True, torch_dtype="auto", device_map="auto"
)
```
### vLLM
```bash
python -m vllm.entrypoints.openai.api_server \
--model modrill/qwen3-4b-think-baseline-full-sft \
--served-model-name think-baseline-full \
--port 8801
```
## Inference Tips
- Set `enable_thinking=true` in the chat template
- Recommended `max_tokens`: 24576
## License
Apache 2.0, consistent with the Qwen3 base model license.

85
chat_template.jinja Normal file
View File

@@ -0,0 +1,85 @@
{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set content = message.content %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in message.content %}
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
{{- message.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 %}

71
config.json Normal file
View File

@@ -0,0 +1,71 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 9728,
"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": 32768,
"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_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "5.6.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

10
generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"do_sample": false,
"eos_token_id": [
151645,
151643
],
"max_new_tokens": 2048,
"pad_token_id": 151643,
"transformers_version": "5.6.0"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b4620375fca6edb35eef18a8b5afdc9ee6602c3315188a94eab09ebdd9346cd0
size 8044982080

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
size 11422650

31
tokenizer_config.json Normal file
View File

@@ -0,0 +1,31 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_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|>"
],
"is_local": true,
"local_files_only": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 2.0,
"total_flos": 1548137571287040.0,
"train_loss": 0.6697529787664481,
"train_runtime": 98109.4565,
"train_samples_per_second": 0.546,
"train_steps_per_second": 0.009
}

168
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,168 @@
{"current_steps": 5, "total_steps": 838, "loss": 3.781953811645508, "lr": 3.0769230769230774e-06, "epoch": 0.011952786493351263, "percentage": 0.6, "elapsed_time": "0:10:10", "remaining_time": "1 day, 4:15:52"}
{"current_steps": 10, "total_steps": 838, "loss": 3.357831573486328, "lr": 6.923076923076923e-06, "epoch": 0.023905572986702525, "percentage": 1.19, "elapsed_time": "0:20:15", "remaining_time": "1 day, 3:56:51"}
{"current_steps": 15, "total_steps": 838, "loss": 2.7730730056762694, "lr": 1.076923076923077e-05, "epoch": 0.03585835948005379, "percentage": 1.79, "elapsed_time": "0:30:21", "remaining_time": "1 day, 3:45:19"}
{"current_steps": 20, "total_steps": 838, "loss": 2.102706527709961, "lr": 1.4615384615384615e-05, "epoch": 0.04781114597340505, "percentage": 2.39, "elapsed_time": "0:40:28", "remaining_time": "1 day, 3:35:09"}
{"current_steps": 25, "total_steps": 838, "loss": 1.4456439018249512, "lr": 1.8461538461538465e-05, "epoch": 0.05976393246675631, "percentage": 2.98, "elapsed_time": "0:50:37", "remaining_time": "1 day, 3:26:13"}
{"current_steps": 30, "total_steps": 838, "loss": 1.0631353378295898, "lr": 1.9999326410474702e-05, "epoch": 0.07171671896010758, "percentage": 3.58, "elapsed_time": "1:00:44", "remaining_time": "1 day, 3:16:01"}
{"current_steps": 35, "total_steps": 838, "loss": 0.9063571929931641, "lr": 1.9995210358660037e-05, "epoch": 0.08366950545345883, "percentage": 4.18, "elapsed_time": "1:11:00", "remaining_time": "1 day, 3:09:04"}
{"current_steps": 40, "total_steps": 838, "loss": 0.829831600189209, "lr": 1.9987354009829813e-05, "epoch": 0.0956222919468101, "percentage": 4.77, "elapsed_time": "1:21:15", "remaining_time": "1 day, 3:01:07"}
{"current_steps": 45, "total_steps": 838, "loss": 0.7827383041381836, "lr": 1.997576030389995e-05, "epoch": 0.10757507844016136, "percentage": 5.37, "elapsed_time": "1:31:25", "remaining_time": "1 day, 2:51:11"}
{"current_steps": 50, "total_steps": 838, "loss": 0.7520761489868164, "lr": 1.9960433579338792e-05, "epoch": 0.11952786493351263, "percentage": 5.97, "elapsed_time": "1:41:32", "remaining_time": "1 day, 2:40:12"}
{"current_steps": 55, "total_steps": 838, "loss": 0.7288134574890137, "lr": 1.9941379571543597e-05, "epoch": 0.13148065142686388, "percentage": 6.56, "elapsed_time": "1:51:41", "remaining_time": "1 day, 2:29:59"}
{"current_steps": 60, "total_steps": 838, "loss": 0.7251720905303956, "lr": 1.991860541069432e-05, "epoch": 0.14343343792021515, "percentage": 7.16, "elapsed_time": "2:01:52", "remaining_time": "1 day, 2:20:20"}
{"current_steps": 65, "total_steps": 838, "loss": 0.7100698947906494, "lr": 1.989211961908541e-05, "epoch": 0.15538622441356642, "percentage": 7.76, "elapsed_time": "2:11:58", "remaining_time": "1 day, 2:09:26"}
{"current_steps": 70, "total_steps": 838, "loss": 0.6971686840057373, "lr": 1.986193210793673e-05, "epoch": 0.16733901090691766, "percentage": 8.35, "elapsed_time": "2:22:11", "remaining_time": "1 day, 2:00:06"}
{"current_steps": 75, "total_steps": 838, "loss": 0.6870299816131592, "lr": 1.9828054173684646e-05, "epoch": 0.17929179740026893, "percentage": 8.95, "elapsed_time": "2:32:25", "remaining_time": "1 day, 1:50:36"}
{"current_steps": 80, "total_steps": 838, "loss": 0.6773219108581543, "lr": 1.979049849375483e-05, "epoch": 0.1912445838936202, "percentage": 9.55, "elapsed_time": "2:42:40", "remaining_time": "1 day, 1:41:22"}
{"current_steps": 85, "total_steps": 838, "loss": 0.6699982166290284, "lr": 1.9749279121818235e-05, "epoch": 0.20319737038697147, "percentage": 10.14, "elapsed_time": "2:52:47", "remaining_time": "1 day, 1:30:41"}
{"current_steps": 90, "total_steps": 838, "loss": 0.6664721488952636, "lr": 1.9704411482532116e-05, "epoch": 0.2151501568803227, "percentage": 10.74, "elapsed_time": "3:02:53", "remaining_time": "1 day, 1:20:02"}
{"current_steps": 95, "total_steps": 838, "loss": 0.6662642002105713, "lr": 1.965591236576794e-05, "epoch": 0.22710294337367398, "percentage": 11.34, "elapsed_time": "3:12:55", "remaining_time": "1 day, 1:08:54"}
{"current_steps": 100, "total_steps": 838, "loss": 0.6621074199676513, "lr": 1.9603799920328508e-05, "epoch": 0.23905572986702525, "percentage": 11.93, "elapsed_time": "3:22:59", "remaining_time": "1 day, 0:58:03"}
{"current_steps": 105, "total_steps": 838, "loss": 0.6573224067687988, "lr": 1.954809364715648e-05, "epoch": 0.2510085163603765, "percentage": 12.53, "elapsed_time": "3:33:05", "remaining_time": "1 day, 0:47:34"}
{"current_steps": 110, "total_steps": 838, "loss": 0.6587805271148681, "lr": 1.9488814392036976e-05, "epoch": 0.26296130285372776, "percentage": 13.13, "elapsed_time": "3:43:09", "remaining_time": "1 day, 0:36:52"}
{"current_steps": 115, "total_steps": 838, "loss": 0.6495862483978272, "lr": 1.942598433779687e-05, "epoch": 0.27491408934707906, "percentage": 13.72, "elapsed_time": "3:53:10", "remaining_time": "1 day, 0:25:54"}
{"current_steps": 120, "total_steps": 838, "loss": 0.6501082420349121, "lr": 1.93596269960038e-05, "epoch": 0.2868668758404303, "percentage": 14.32, "elapsed_time": "4:03:10", "remaining_time": "1 day, 0:15:02"}
{"current_steps": 125, "total_steps": 838, "loss": 0.6507360935211182, "lr": 1.9289767198167918e-05, "epoch": 0.29881966233378154, "percentage": 14.92, "elapsed_time": "4:13:18", "remaining_time": "1 day, 0:04:51"}
{"current_steps": 130, "total_steps": 838, "loss": 0.6456474304199219, "lr": 1.9216431086449707e-05, "epoch": 0.31077244882713284, "percentage": 15.51, "elapsed_time": "4:23:25", "remaining_time": "23:54:36"}
{"current_steps": 135, "total_steps": 838, "loss": 0.6424931526184082, "lr": 1.9139646103877378e-05, "epoch": 0.3227252353204841, "percentage": 16.11, "elapsed_time": "4:33:29", "remaining_time": "23:44:11"}
{"current_steps": 140, "total_steps": 838, "loss": 0.6433355331420898, "lr": 1.9059440984077425e-05, "epoch": 0.3346780218138353, "percentage": 16.71, "elapsed_time": "4:43:30", "remaining_time": "23:33:27"}
{"current_steps": 145, "total_steps": 838, "loss": 0.6428297996520996, "lr": 1.8975845740522246e-05, "epoch": 0.3466308083071866, "percentage": 17.3, "elapsed_time": "4:53:28", "remaining_time": "23:22:35"}
{"current_steps": 150, "total_steps": 838, "loss": 0.6387664318084717, "lr": 1.888889165529883e-05, "epoch": 0.35858359480053786, "percentage": 17.9, "elapsed_time": "5:03:28", "remaining_time": "23:11:58"}
{"current_steps": 155, "total_steps": 838, "loss": 0.6378631591796875, "lr": 1.8798611267402745e-05, "epoch": 0.37053638129388916, "percentage": 18.5, "elapsed_time": "5:13:31", "remaining_time": "23:01:32"}
{"current_steps": 160, "total_steps": 838, "loss": 0.6357398986816406, "lr": 1.8705038360561724e-05, "epoch": 0.3824891677872404, "percentage": 19.09, "elapsed_time": "5:23:30", "remaining_time": "22:50:53"}
{"current_steps": 165, "total_steps": 838, "loss": 0.6283899307250976, "lr": 1.86082079505935e-05, "epoch": 0.39444195428059164, "percentage": 19.69, "elapsed_time": "5:33:28", "remaining_time": "22:40:11"}
{"current_steps": 170, "total_steps": 838, "loss": 0.6344176292419433, "lr": 1.850815627230259e-05, "epoch": 0.40639474077394294, "percentage": 20.29, "elapsed_time": "5:43:26", "remaining_time": "22:29:31"}
{"current_steps": 175, "total_steps": 838, "loss": 0.6346979141235352, "lr": 1.8404920765920898e-05, "epoch": 0.4183475272672942, "percentage": 20.88, "elapsed_time": "5:53:22", "remaining_time": "22:18:47"}
{"current_steps": 180, "total_steps": 838, "loss": 0.6299883842468261, "lr": 1.8298540063097233e-05, "epoch": 0.4303003137606454, "percentage": 21.48, "elapsed_time": "6:03:18", "remaining_time": "22:08:05"}
{"current_steps": 185, "total_steps": 838, "loss": 0.6316470146179199, "lr": 1.8189053972441027e-05, "epoch": 0.4422531002539967, "percentage": 22.08, "elapsed_time": "6:13:16", "remaining_time": "21:57:35"}
{"current_steps": 190, "total_steps": 838, "loss": 0.6279996871948242, "lr": 1.8076503464625568e-05, "epoch": 0.45420588674734796, "percentage": 22.67, "elapsed_time": "6:23:12", "remaining_time": "21:46:56"}
{"current_steps": 195, "total_steps": 838, "loss": 0.6266597270965576, "lr": 1.796093065705644e-05, "epoch": 0.46615867324069926, "percentage": 23.27, "elapsed_time": "6:33:08", "remaining_time": "21:36:22"}
{"current_steps": 200, "total_steps": 838, "loss": 0.6253810405731202, "lr": 1.784237879811078e-05, "epoch": 0.4781114597340505, "percentage": 23.87, "elapsed_time": "6:43:06", "remaining_time": "21:25:56"}
{"current_steps": 205, "total_steps": 838, "loss": 0.6256628036499023, "lr": 1.7720892250953375e-05, "epoch": 0.49006424622740175, "percentage": 24.46, "elapsed_time": "6:52:59", "remaining_time": "21:15:13"}
{"current_steps": 210, "total_steps": 838, "loss": 0.6216660499572754, "lr": 1.759651647693556e-05, "epoch": 0.502017032720753, "percentage": 25.06, "elapsed_time": "7:02:52", "remaining_time": "21:04:36"}
{"current_steps": 215, "total_steps": 838, "loss": 0.6221325397491455, "lr": 1.746929801858317e-05, "epoch": 0.5139698192141043, "percentage": 25.66, "elapsed_time": "7:12:50", "remaining_time": "20:54:13"}
{"current_steps": 220, "total_steps": 838, "loss": 0.6234128952026368, "lr": 1.733928448217992e-05, "epoch": 0.5259226057074555, "percentage": 26.25, "elapsed_time": "7:22:40", "remaining_time": "20:43:30"}
{"current_steps": 225, "total_steps": 838, "loss": 0.620493221282959, "lr": 1.7206524519952697e-05, "epoch": 0.5378753922008068, "percentage": 26.85, "elapsed_time": "7:32:31", "remaining_time": "20:32:53"}
{"current_steps": 230, "total_steps": 838, "loss": 0.6177290439605713, "lr": 1.7071067811865477e-05, "epoch": 0.5498281786941581, "percentage": 27.45, "elapsed_time": "7:42:28", "remaining_time": "20:22:31"}
{"current_steps": 235, "total_steps": 838, "loss": 0.6173371315002442, "lr": 1.693296504702862e-05, "epoch": 0.5617809651875093, "percentage": 28.04, "elapsed_time": "7:52:16", "remaining_time": "20:11:50"}
{"current_steps": 240, "total_steps": 838, "loss": 0.615760087966919, "lr": 1.6792267904730577e-05, "epoch": 0.5737337516808606, "percentage": 28.64, "elapsed_time": "8:02:09", "remaining_time": "20:01:23"}
{"current_steps": 245, "total_steps": 838, "loss": 0.6138944625854492, "lr": 1.6649029035099e-05, "epoch": 0.5856865381742119, "percentage": 29.24, "elapsed_time": "8:12:01", "remaining_time": "19:50:54"}
{"current_steps": 250, "total_steps": 838, "loss": 0.6182753562927246, "lr": 1.6503302039398647e-05, "epoch": 0.5976393246675631, "percentage": 29.83, "elapsed_time": "8:21:52", "remaining_time": "19:40:25"}
{"current_steps": 255, "total_steps": 838, "loss": 0.6080506801605224, "lr": 1.6355141449973254e-05, "epoch": 0.6095921111609144, "percentage": 30.43, "elapsed_time": "8:31:42", "remaining_time": "19:29:54"}
{"current_steps": 260, "total_steps": 838, "loss": 0.609522533416748, "lr": 1.6204602709839088e-05, "epoch": 0.6215448976542657, "percentage": 31.03, "elapsed_time": "8:41:32", "remaining_time": "19:19:26"}
{"current_steps": 265, "total_steps": 838, "loss": 0.6120513916015625, "lr": 1.6051742151937655e-05, "epoch": 0.6334976841476169, "percentage": 31.62, "elapsed_time": "8:51:21", "remaining_time": "19:08:55"}
{"current_steps": 270, "total_steps": 838, "loss": 0.6115104675292968, "lr": 1.5896616978055402e-05, "epoch": 0.6454504706409682, "percentage": 32.22, "elapsed_time": "9:01:11", "remaining_time": "18:58:30"}
{"current_steps": 275, "total_steps": 838, "loss": 0.6086444854736328, "lr": 1.5739285237418323e-05, "epoch": 0.6574032571343195, "percentage": 32.82, "elapsed_time": "9:11:01", "remaining_time": "18:48:05"}
{"current_steps": 280, "total_steps": 838, "loss": 0.6117893695831299, "lr": 1.5579805804969403e-05, "epoch": 0.6693560436276706, "percentage": 33.41, "elapsed_time": "9:20:49", "remaining_time": "18:37:37"}
{"current_steps": 285, "total_steps": 838, "loss": 0.611101770401001, "lr": 1.5418238359337077e-05, "epoch": 0.681308830121022, "percentage": 34.01, "elapsed_time": "9:30:35", "remaining_time": "18:27:08"}
{"current_steps": 290, "total_steps": 838, "loss": 0.6106156349182129, "lr": 1.5254643360502988e-05, "epoch": 0.6932616166143732, "percentage": 34.61, "elapsed_time": "9:40:20", "remaining_time": "18:16:39"}
{"current_steps": 295, "total_steps": 838, "loss": 0.6108765602111816, "lr": 1.5089082027177291e-05, "epoch": 0.7052144031077245, "percentage": 35.2, "elapsed_time": "9:50:07", "remaining_time": "18:06:13"}
{"current_steps": 300, "total_steps": 838, "loss": 0.6092706680297851, "lr": 1.4921616313890073e-05, "epoch": 0.7171671896010757, "percentage": 35.8, "elapsed_time": "9:59:54", "remaining_time": "17:55:50"}
{"current_steps": 305, "total_steps": 838, "loss": 0.6059467315673828, "lr": 1.4752308887807427e-05, "epoch": 0.729119976094427, "percentage": 36.4, "elapsed_time": "10:09:37", "remaining_time": "17:45:19"}
{"current_steps": 310, "total_steps": 838, "loss": 0.6053099155426025, "lr": 1.458122310528082e-05, "epoch": 0.7410727625877783, "percentage": 36.99, "elapsed_time": "10:19:25", "remaining_time": "17:35:01"}
{"current_steps": 315, "total_steps": 838, "loss": 0.6064858436584473, "lr": 1.4408422988138585e-05, "epoch": 0.7530255490811295, "percentage": 37.59, "elapsed_time": "10:29:11", "remaining_time": "17:24:39"}
{"current_steps": 320, "total_steps": 838, "loss": 0.6048956871032715, "lr": 1.4233973199728394e-05, "epoch": 0.7649783355744808, "percentage": 38.19, "elapsed_time": "10:38:55", "remaining_time": "17:14:15"}
{"current_steps": 325, "total_steps": 838, "loss": 0.601306676864624, "lr": 1.4057939020719642e-05, "epoch": 0.7769311220678321, "percentage": 38.78, "elapsed_time": "10:48:43", "remaining_time": "17:03:59"}
{"current_steps": 330, "total_steps": 838, "loss": 0.605643367767334, "lr": 1.3880386324674842e-05, "epoch": 0.7888839085611833, "percentage": 39.38, "elapsed_time": "10:58:28", "remaining_time": "16:53:38"}
{"current_steps": 335, "total_steps": 838, "loss": 0.6025477409362793, "lr": 1.3701381553399147e-05, "epoch": 0.8008366950545346, "percentage": 39.98, "elapsed_time": "11:08:08", "remaining_time": "16:43:12"}
{"current_steps": 340, "total_steps": 838, "loss": 0.6008072853088379, "lr": 1.352099169207723e-05, "epoch": 0.8127894815478859, "percentage": 40.57, "elapsed_time": "11:17:51", "remaining_time": "16:32:51"}
{"current_steps": 345, "total_steps": 838, "loss": 0.5990739822387695, "lr": 1.3339284244206847e-05, "epoch": 0.8247422680412371, "percentage": 41.17, "elapsed_time": "11:27:34", "remaining_time": "16:22:31"}
{"current_steps": 350, "total_steps": 838, "loss": 0.5999683380126953, "lr": 1.3156327206338404e-05, "epoch": 0.8366950545345884, "percentage": 41.77, "elapsed_time": "11:37:16", "remaining_time": "16:12:12"}
{"current_steps": 355, "total_steps": 838, "loss": 0.600177812576294, "lr": 1.2972189042630044e-05, "epoch": 0.8486478410279397, "percentage": 42.36, "elapsed_time": "11:46:58", "remaining_time": "16:01:53"}
{"current_steps": 360, "total_steps": 838, "loss": 0.6015380859375, "lr": 1.2786938659227759e-05, "epoch": 0.8606006275212909, "percentage": 42.96, "elapsed_time": "11:56:41", "remaining_time": "15:51:36"}
{"current_steps": 365, "total_steps": 838, "loss": 0.5957009792327881, "lr": 1.2600645378480083e-05, "epoch": 0.8725534140146421, "percentage": 43.56, "elapsed_time": "12:06:24", "remaining_time": "15:41:20"}
{"current_steps": 370, "total_steps": 838, "loss": 0.598288631439209, "lr": 1.2413378912997058e-05, "epoch": 0.8845062005079934, "percentage": 44.15, "elapsed_time": "12:16:05", "remaining_time": "15:31:03"}
{"current_steps": 375, "total_steps": 838, "loss": 0.6014204978942871, "lr": 1.2225209339563144e-05, "epoch": 0.8964589870013447, "percentage": 44.75, "elapsed_time": "12:25:45", "remaining_time": "15:20:45"}
{"current_steps": 380, "total_steps": 838, "loss": 0.5959988594055176, "lr": 1.2036207072913873e-05, "epoch": 0.9084117734946959, "percentage": 45.35, "elapsed_time": "12:35:25", "remaining_time": "15:10:28"}
{"current_steps": 385, "total_steps": 838, "loss": 0.600127124786377, "lr": 1.1846442839386004e-05, "epoch": 0.9203645599880472, "percentage": 45.94, "elapsed_time": "12:45:02", "remaining_time": "15:00:10"}
{"current_steps": 390, "total_steps": 838, "loss": 0.5965915203094483, "lr": 1.1655987650451121e-05, "epoch": 0.9323173464813985, "percentage": 46.54, "elapsed_time": "12:54:40", "remaining_time": "14:49:53"}
{"current_steps": 395, "total_steps": 838, "loss": 0.5974255084991456, "lr": 1.1464912776142494e-05, "epoch": 0.9442701329747497, "percentage": 47.14, "elapsed_time": "13:04:18", "remaining_time": "14:39:36"}
{"current_steps": 400, "total_steps": 838, "loss": 0.5984516143798828, "lr": 1.1273289718385188e-05, "epoch": 0.956222919468101, "percentage": 47.73, "elapsed_time": "13:13:56", "remaining_time": "14:29:21"}
{"current_steps": 405, "total_steps": 838, "loss": 0.5971392631530762, "lr": 1.1081190184239418e-05, "epoch": 0.9681757059614523, "percentage": 48.33, "elapsed_time": "13:23:34", "remaining_time": "14:19:07"}
{"current_steps": 410, "total_steps": 838, "loss": 0.6007642269134521, "lr": 1.0888686059067124e-05, "epoch": 0.9801284924548035, "percentage": 48.93, "elapsed_time": "13:33:10", "remaining_time": "14:08:53"}
{"current_steps": 415, "total_steps": 838, "loss": 0.5945420265197754, "lr": 1.0695849379631813e-05, "epoch": 0.9920812789481548, "percentage": 49.52, "elapsed_time": "13:42:48", "remaining_time": "13:58:39"}
{"current_steps": 420, "total_steps": 838, "loss": 0.5932960510253906, "lr": 1.050275230714178e-05, "epoch": 1.0023905572986702, "percentage": 50.12, "elapsed_time": "13:52:31", "remaining_time": "13:48:33"}
{"current_steps": 425, "total_steps": 838, "loss": 0.5823319435119629, "lr": 1.0309467100246713e-05, "epoch": 1.0143433437920215, "percentage": 50.72, "elapsed_time": "14:02:06", "remaining_time": "13:38:20"}
{"current_steps": 430, "total_steps": 838, "loss": 0.5844221591949463, "lr": 1.0116066087997894e-05, "epoch": 1.0262961302853728, "percentage": 51.31, "elapsed_time": "14:11:42", "remaining_time": "13:28:07"}
{"current_steps": 435, "total_steps": 838, "loss": 0.5829752445220947, "lr": 9.92262164278198e-06, "epoch": 1.038248916778724, "percentage": 51.91, "elapsed_time": "14:21:17", "remaining_time": "13:17:55"}
{"current_steps": 440, "total_steps": 838, "loss": 0.5771419525146484, "lr": 9.729206153238658e-06, "epoch": 1.0502017032720754, "percentage": 52.51, "elapsed_time": "14:30:52", "remaining_time": "13:07:45"}
{"current_steps": 445, "total_steps": 838, "loss": 0.5796083927154541, "lr": 9.53589199717212e-06, "epoch": 1.0621544897654265, "percentage": 53.1, "elapsed_time": "14:40:28", "remaining_time": "12:57:35"}
{"current_steps": 450, "total_steps": 838, "loss": 0.57957763671875, "lr": 9.342751514466681e-06, "epoch": 1.0741072762587778, "percentage": 53.7, "elapsed_time": "14:50:03", "remaining_time": "12:47:25"}
{"current_steps": 455, "total_steps": 838, "loss": 0.580908203125, "lr": 9.149856980016529e-06, "epoch": 1.086060062752129, "percentage": 54.3, "elapsed_time": "14:59:39", "remaining_time": "12:37:17"}
{"current_steps": 460, "total_steps": 838, "loss": 0.5784452438354493, "lr": 8.957280576679814e-06, "epoch": 1.0980128492454804, "percentage": 54.89, "elapsed_time": "15:09:15", "remaining_time": "12:27:10"}
{"current_steps": 465, "total_steps": 838, "loss": 0.5803499698638916, "lr": 8.765094368267186e-06, "epoch": 1.1099656357388317, "percentage": 55.49, "elapsed_time": "15:18:51", "remaining_time": "12:17:03"}
{"current_steps": 470, "total_steps": 838, "loss": 0.5817919731140136, "lr": 8.573370272574861e-06, "epoch": 1.121918422232183, "percentage": 56.09, "elapsed_time": "15:28:27", "remaining_time": "12:06:57"}
{"current_steps": 475, "total_steps": 838, "loss": 0.5773644924163819, "lr": 8.382180034472353e-06, "epoch": 1.1338712087255343, "percentage": 56.68, "elapsed_time": "15:38:03", "remaining_time": "11:56:52"}
{"current_steps": 480, "total_steps": 838, "loss": 0.5796680450439453, "lr": 8.191595199054898e-06, "epoch": 1.1458239952188853, "percentage": 57.28, "elapsed_time": "15:47:39", "remaining_time": "11:46:47"}
{"current_steps": 485, "total_steps": 838, "loss": 0.5763995170593261, "lr": 8.00168708487063e-06, "epoch": 1.1577767817122366, "percentage": 57.88, "elapsed_time": "15:57:15", "remaining_time": "11:36:43"}
{"current_steps": 490, "total_steps": 838, "loss": 0.5773411273956299, "lr": 7.812526757232559e-06, "epoch": 1.169729568205588, "percentage": 58.47, "elapsed_time": "16:06:51", "remaining_time": "11:26:40"}
{"current_steps": 495, "total_steps": 838, "loss": 0.5760007858276367, "lr": 7.6241850016252915e-06, "epoch": 1.1816823546989392, "percentage": 59.07, "elapsed_time": "16:16:28", "remaining_time": "11:16:37"}
{"current_steps": 500, "total_steps": 838, "loss": 0.5818538665771484, "lr": 7.436732297216449e-06, "epoch": 1.1936351411922905, "percentage": 59.67, "elapsed_time": "16:26:04", "remaining_time": "11:06:35"}
{"current_steps": 505, "total_steps": 838, "loss": 0.5778368949890137, "lr": 7.250238790482773e-06, "epoch": 1.2055879276856416, "percentage": 60.26, "elapsed_time": "16:35:41", "remaining_time": "10:56:33"}
{"current_steps": 510, "total_steps": 838, "loss": 0.5712313652038574, "lr": 7.064774268960654e-06, "epoch": 1.217540714178993, "percentage": 60.86, "elapsed_time": "16:45:17", "remaining_time": "10:46:32"}
{"current_steps": 515, "total_steps": 838, "loss": 0.5747489929199219, "lr": 6.880408135131022e-06, "epoch": 1.2294935006723442, "percentage": 61.46, "elapsed_time": "16:54:53", "remaining_time": "10:36:31"}
{"current_steps": 520, "total_steps": 838, "loss": 0.5774303913116455, "lr": 6.697209380448333e-06, "epoch": 1.2414462871656955, "percentage": 62.05, "elapsed_time": "17:04:30", "remaining_time": "10:26:31"}
{"current_steps": 525, "total_steps": 838, "loss": 0.5766214847564697, "lr": 6.515246559523311e-06, "epoch": 1.2533990736590468, "percentage": 62.65, "elapsed_time": "17:14:06", "remaining_time": "10:16:31"}
{"current_steps": 530, "total_steps": 838, "loss": 0.5807313919067383, "lr": 6.334587764469252e-06, "epoch": 1.265351860152398, "percentage": 63.25, "elapsed_time": "17:23:43", "remaining_time": "10:06:32"}
{"current_steps": 535, "total_steps": 838, "loss": 0.577438497543335, "lr": 6.155300599421305e-06, "epoch": 1.2773046466457494, "percentage": 63.84, "elapsed_time": "17:33:19", "remaining_time": "9:56:33"}
{"current_steps": 540, "total_steps": 838, "loss": 0.5809723854064941, "lr": 5.977452155238422e-06, "epoch": 1.2892574331391007, "percentage": 64.44, "elapsed_time": "17:42:56", "remaining_time": "9:46:35"}
{"current_steps": 545, "total_steps": 838, "loss": 0.5761542797088623, "lr": 5.801108984397355e-06, "epoch": 1.3012102196324518, "percentage": 65.04, "elapsed_time": "17:52:33", "remaining_time": "9:36:37"}
{"current_steps": 550, "total_steps": 838, "loss": 0.57545166015625, "lr": 5.626337076088118e-06, "epoch": 1.313163006125803, "percentage": 65.63, "elapsed_time": "18:02:10", "remaining_time": "9:26:39"}
{"current_steps": 555, "total_steps": 838, "loss": 0.57459716796875, "lr": 5.453201831520245e-06, "epoch": 1.3251157926191544, "percentage": 66.23, "elapsed_time": "18:11:46", "remaining_time": "9:16:42"}
{"current_steps": 560, "total_steps": 838, "loss": 0.5742292404174805, "lr": 5.281768039449091e-06, "epoch": 1.3370685791125057, "percentage": 66.83, "elapsed_time": "18:21:23", "remaining_time": "9:06:45"}
{"current_steps": 565, "total_steps": 838, "loss": 0.5767020225524903, "lr": 5.112099851931265e-06, "epoch": 1.349021365605857, "percentage": 67.42, "elapsed_time": "18:30:58", "remaining_time": "8:56:48"}
{"current_steps": 570, "total_steps": 838, "loss": 0.5800568580627441, "lr": 4.944260760318398e-06, "epoch": 1.360974152099208, "percentage": 68.02, "elapsed_time": "18:40:35", "remaining_time": "8:46:52"}
{"current_steps": 575, "total_steps": 838, "loss": 0.5764224052429199, "lr": 4.778313571498075e-06, "epoch": 1.3729269385925593, "percentage": 68.62, "elapsed_time": "18:50:10", "remaining_time": "8:36:56"}
{"current_steps": 580, "total_steps": 838, "loss": 0.5748445987701416, "lr": 4.614320384390959e-06, "epoch": 1.3848797250859106, "percentage": 69.21, "elapsed_time": "18:59:46", "remaining_time": "8:27:00"}
{"current_steps": 585, "total_steps": 838, "loss": 0.5741267681121827, "lr": 4.452342566712818e-06, "epoch": 1.396832511579262, "percentage": 69.81, "elapsed_time": "19:09:22", "remaining_time": "8:17:04"}
{"current_steps": 590, "total_steps": 838, "loss": 0.5751005649566651, "lr": 4.292440732010177e-06, "epoch": 1.4087852980726132, "percentage": 70.41, "elapsed_time": "19:18:57", "remaining_time": "8:07:09"}
{"current_steps": 595, "total_steps": 838, "loss": 0.5727577686309815, "lr": 4.1346747169781695e-06, "epoch": 1.4207380845659645, "percentage": 71.0, "elapsed_time": "19:28:33", "remaining_time": "7:57:14"}
{"current_steps": 600, "total_steps": 838, "loss": 0.5734814643859864, "lr": 3.979103559069142e-06, "epoch": 1.4326908710593158, "percentage": 71.6, "elapsed_time": "19:38:10", "remaining_time": "7:47:20"}
{"current_steps": 605, "total_steps": 838, "loss": 0.5790888786315918, "lr": 3.825785474400291e-06, "epoch": 1.444643657552667, "percentage": 72.2, "elapsed_time": "19:47:45", "remaining_time": "7:37:26"}
{"current_steps": 610, "total_steps": 838, "loss": 0.5729323387145996, "lr": 3.6747778359686746e-06, "epoch": 1.4565964440460182, "percentage": 72.79, "elapsed_time": "19:57:21", "remaining_time": "7:27:32"}
{"current_steps": 615, "total_steps": 838, "loss": 0.5743005275726318, "lr": 3.5261371521817247e-06, "epoch": 1.4685492305393695, "percentage": 73.39, "elapsed_time": "20:06:57", "remaining_time": "7:17:38"}
{"current_steps": 620, "total_steps": 838, "loss": 0.5747577667236328, "lr": 3.379919045711304e-06, "epoch": 1.4805020170327208, "percentage": 73.99, "elapsed_time": "20:16:32", "remaining_time": "7:07:45"}
{"current_steps": 625, "total_steps": 838, "loss": 0.5756843566894532, "lr": 3.2361782326792025e-06, "epoch": 1.492454803526072, "percentage": 74.58, "elapsed_time": "20:26:09", "remaining_time": "6:57:52"}
{"current_steps": 630, "total_steps": 838, "loss": 0.5745338439941406, "lr": 3.0949685021818642e-06, "epoch": 1.5044075900194231, "percentage": 75.18, "elapsed_time": "20:35:45", "remaining_time": "6:47:59"}
{"current_steps": 635, "total_steps": 838, "loss": 0.5757760047912598, "lr": 2.956342696162037e-06, "epoch": 1.5163603765127744, "percentage": 75.78, "elapsed_time": "20:45:21", "remaining_time": "6:38:07"}
{"current_steps": 640, "total_steps": 838, "loss": 0.5728174209594726, "lr": 2.82035268963485e-06, "epoch": 1.5283131630061257, "percentage": 76.37, "elapsed_time": "20:54:57", "remaining_time": "6:28:15"}
{"current_steps": 645, "total_steps": 838, "loss": 0.576561450958252, "lr": 2.687049371275705e-06, "epoch": 1.540265949499477, "percentage": 76.97, "elapsed_time": "21:04:33", "remaining_time": "6:18:23"}
{"current_steps": 650, "total_steps": 838, "loss": 0.5675359725952148, "lr": 2.5564826243772965e-06, "epoch": 1.5522187359928283, "percentage": 77.57, "elapsed_time": "21:14:10", "remaining_time": "6:08:31"}
{"current_steps": 655, "total_steps": 838, "loss": 0.5752163887023926, "lr": 2.428701308182826e-06, "epoch": 1.5641715224861796, "percentage": 78.16, "elapsed_time": "21:23:46", "remaining_time": "5:58:40"}
{"current_steps": 660, "total_steps": 838, "loss": 0.5792200565338135, "lr": 2.3037532396024375e-06, "epoch": 1.576124308979531, "percentage": 78.76, "elapsed_time": "21:33:23", "remaining_time": "5:48:49"}
{"current_steps": 665, "total_steps": 838, "loss": 0.5774263858795166, "lr": 2.1816851753197023e-06, "epoch": 1.5880770954728822, "percentage": 79.36, "elapsed_time": "21:42:59", "remaining_time": "5:38:58"}
{"current_steps": 670, "total_steps": 838, "loss": 0.5775305747985839, "lr": 2.0625427942948617e-06, "epoch": 1.6000298819662335, "percentage": 79.95, "elapsed_time": "21:52:36", "remaining_time": "5:29:07"}
{"current_steps": 675, "total_steps": 838, "loss": 0.5713157653808594, "lr": 1.946370680671341e-06, "epoch": 1.6119826684595846, "percentage": 80.55, "elapsed_time": "22:02:13", "remaining_time": "5:19:17"}
{"current_steps": 680, "total_steps": 838, "loss": 0.5721651077270508, "lr": 1.8332123070919593e-06, "epoch": 1.623935454952936, "percentage": 81.15, "elapsed_time": "22:11:50", "remaining_time": "5:09:27"}
{"current_steps": 685, "total_steps": 838, "loss": 0.5746645927429199, "lr": 1.7231100184310955e-06, "epoch": 1.6358882414462872, "percentage": 81.74, "elapsed_time": "22:21:27", "remaining_time": "4:59:37"}
{"current_steps": 690, "total_steps": 838, "loss": 0.5708446025848388, "lr": 1.6161050159488422e-06, "epoch": 1.6478410279396383, "percentage": 82.34, "elapsed_time": "22:31:03", "remaining_time": "4:49:47"}
{"current_steps": 695, "total_steps": 838, "loss": 0.5715685367584229, "lr": 1.5122373418731306e-06, "epoch": 1.6597938144329896, "percentage": 82.94, "elapsed_time": "22:40:40", "remaining_time": "4:39:58"}
{"current_steps": 700, "total_steps": 838, "loss": 0.5733305931091308, "lr": 1.4115458644155799e-06, "epoch": 1.6717466009263409, "percentage": 83.53, "elapsed_time": "22:50:17", "remaining_time": "4:30:08"}
{"current_steps": 705, "total_steps": 838, "loss": 0.5701050758361816, "lr": 1.3140682632266544e-06, "epoch": 1.6836993874196922, "percentage": 84.13, "elapsed_time": "22:59:54", "remaining_time": "4:20:19"}
{"current_steps": 710, "total_steps": 838, "loss": 0.5752843856811524, "lr": 1.219841015295601e-06, "epoch": 1.6956521739130435, "percentage": 84.73, "elapsed_time": "23:09:30", "remaining_time": "4:10:30"}
{"current_steps": 715, "total_steps": 838, "loss": 0.5716147422790527, "lr": 1.1288993813004467e-06, "epoch": 1.7076049604063948, "percentage": 85.32, "elapsed_time": "23:19:06", "remaining_time": "4:00:41"}
{"current_steps": 720, "total_steps": 838, "loss": 0.5669195175170898, "lr": 1.0412773924131202e-06, "epoch": 1.719557746899746, "percentage": 85.92, "elapsed_time": "23:28:43", "remaining_time": "3:50:52"}
{"current_steps": 725, "total_steps": 838, "loss": 0.567324447631836, "lr": 9.570078375647006e-07, "epoch": 1.7315105333930974, "percentage": 86.52, "elapsed_time": "23:38:19", "remaining_time": "3:41:03"}
{"current_steps": 730, "total_steps": 838, "loss": 0.5737391948699951, "lr": 8.761222511754897e-07, "epoch": 1.7434633198864486, "percentage": 87.11, "elapsed_time": "23:47:55", "remaining_time": "3:31:15"}
{"current_steps": 735, "total_steps": 838, "loss": 0.5722625732421875, "lr": 7.986509013545673e-07, "epoch": 1.7554161063798, "percentage": 87.71, "elapsed_time": "23:57:31", "remaining_time": "3:21:26"}
{"current_steps": 740, "total_steps": 838, "loss": 0.571877908706665, "lr": 7.246227785731841e-07, "epoch": 1.767368892873151, "percentage": 88.31, "elapsed_time": "1 day, 0:07:06", "remaining_time": "3:11:38"}
{"current_steps": 745, "total_steps": 838, "loss": 0.5695056438446044, "lr": 6.540655848162602e-07, "epoch": 1.7793216793665023, "percentage": 88.9, "elapsed_time": "1 day, 0:16:42", "remaining_time": "3:01:50"}
{"current_steps": 750, "total_steps": 838, "loss": 0.5675976753234864, "lr": 5.870057232160786e-07, "epoch": 1.7912744658598536, "percentage": 89.5, "elapsed_time": "1 day, 0:26:18", "remaining_time": "2:52:02"}
{"current_steps": 755, "total_steps": 838, "loss": 0.5719050884246826, "lr": 5.234682881719766e-07, "epoch": 1.8032272523532047, "percentage": 90.1, "elapsed_time": "1 day, 0:35:53", "remaining_time": "2:42:15"}
{"current_steps": 760, "total_steps": 838, "loss": 0.5688658714294433, "lr": 4.634770559598023e-07, "epoch": 1.815180038846556, "percentage": 90.69, "elapsed_time": "1 day, 0:45:29", "remaining_time": "2:32:27"}
{"current_steps": 765, "total_steps": 838, "loss": 0.5725912094116211, "lr": 4.070544758346273e-07, "epoch": 1.8271328253399073, "percentage": 91.29, "elapsed_time": "1 day, 0:55:04", "remaining_time": "2:22:40"}
{"current_steps": 770, "total_steps": 838, "loss": 0.5723624229431152, "lr": 3.5422166163002315e-07, "epoch": 1.8390856118332586, "percentage": 91.89, "elapsed_time": "1 day, 1:04:40", "remaining_time": "2:12:52"}
{"current_steps": 775, "total_steps": 838, "loss": 0.5731348037719727, "lr": 3.049983838570858e-07, "epoch": 1.8510383983266099, "percentage": 92.48, "elapsed_time": "1 day, 1:14:15", "remaining_time": "2:03:05"}
{"current_steps": 780, "total_steps": 838, "loss": 0.5693378448486328, "lr": 2.5940306230612946e-07, "epoch": 1.8629911848199612, "percentage": 93.08, "elapsed_time": "1 day, 1:23:50", "remaining_time": "1:53:18"}
{"current_steps": 785, "total_steps": 838, "loss": 0.5738930702209473, "lr": 2.1745275915383668e-07, "epoch": 1.8749439713133125, "percentage": 93.68, "elapsed_time": "1 day, 1:33:25", "remaining_time": "1:43:31"}
{"current_steps": 790, "total_steps": 838, "loss": 0.5733755111694336, "lr": 1.791631725784404e-07, "epoch": 1.8868967578066638, "percentage": 94.27, "elapsed_time": "1 day, 1:43:00", "remaining_time": "1:33:45"}
{"current_steps": 795, "total_steps": 838, "loss": 0.5737156867980957, "lr": 1.4454863088532388e-07, "epoch": 1.898849544300015, "percentage": 94.87, "elapsed_time": "1 day, 1:52:35", "remaining_time": "1:23:58"}
{"current_steps": 800, "total_steps": 838, "loss": 0.5738909244537354, "lr": 1.1362208714524203e-07, "epoch": 1.9108023307933664, "percentage": 95.47, "elapsed_time": "1 day, 2:02:10", "remaining_time": "1:14:12"}
{"current_steps": 805, "total_steps": 838, "loss": 0.5715600490570069, "lr": 8.639511434716863e-08, "epoch": 1.9227551172867174, "percentage": 96.06, "elapsed_time": "1 day, 2:11:44", "remaining_time": "1:04:25"}
{"current_steps": 810, "total_steps": 838, "loss": 0.5690464973449707, "lr": 6.287790106757396e-08, "epoch": 1.9347079037800687, "percentage": 96.66, "elapsed_time": "1 day, 2:21:18", "remaining_time": "0:54:39"}
{"current_steps": 815, "total_steps": 838, "loss": 0.5704758167266846, "lr": 4.307924765777682e-08, "epoch": 1.94666069027342, "percentage": 97.26, "elapsed_time": "1 day, 2:30:52", "remaining_time": "0:44:53"}
{"current_steps": 820, "total_steps": 838, "loss": 0.5708345890045166, "lr": 2.7006562950767644e-08, "epoch": 1.958613476766771, "percentage": 97.85, "elapsed_time": "1 day, 2:40:27", "remaining_time": "0:35:07"}
{"current_steps": 825, "total_steps": 838, "loss": 0.5729907989501953, "lr": 1.4665861488761813e-08, "epoch": 1.9705662632601224, "percentage": 98.45, "elapsed_time": "1 day, 2:50:00", "remaining_time": "0:25:22"}
{"current_steps": 830, "total_steps": 838, "loss": 0.5732277870178223, "lr": 6.0617612724989114e-09, "epoch": 1.9825190497534737, "percentage": 99.05, "elapsed_time": "1 day, 2:59:35", "remaining_time": "0:15:36"}
{"current_steps": 835, "total_steps": 838, "loss": 0.5770379066467285, "lr": 1.1974820331517313e-09, "epoch": 1.994471836246825, "percentage": 99.64, "elapsed_time": "1 day, 3:09:09", "remaining_time": "0:05:51"}
{"current_steps": 838, "total_steps": 838, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "1 day, 3:15:09", "remaining_time": "0:00:00"}