初始化项目,由ModelHub XC社区提供模型

Model: lldois/v03_all_lr1e5_ep2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-16 09:29:17 +08:00
commit ef51420781
16 changed files with 3949 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

58
README.md Normal file
View File

@@ -0,0 +1,58 @@
---
library_name: transformers
license: other
base_model: OpenOneRec/OneReason-0.8B-pretrain-competition
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: v03_all_lr1e5_ep2
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. -->
# v03_all_lr1e5_ep2
This model is a fine-tuned version of [OpenOneRec/OneReason-0.8B-pretrain-competition](https://huggingface.co/OpenOneRec/OneReason-0.8B-pretrain-competition) on the overnight_all dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 202607063
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 2
### Training results
### Framework versions
- Transformers 5.6.0
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 2.0,
"total_flos": 3.833069438698537e+17,
"train_loss": 1.6445721892555754,
"train_runtime": 6416.9422,
"train_samples_per_second": 0.496,
"train_steps_per_second": 0.124
}

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 %}

63
config.json Normal file
View File

@@ -0,0 +1,63 @@
{
"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": 1024,
"initializer_range": 0.02,
"intermediate_size": 3072,
"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"
],
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"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": false,
"transformers_version": "5.6.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 176253
}

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": "5.6.0"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ada9cf8995f4b12758f1f0d22decbaef429fc7d241ca54d1ab32bad642addce7
size 1602902832

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fea5f3e7c7a4da1819d4b2a543c453fa967010f58d762e5917e1c471b9b9f2a0
size 39759

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cd4d15f596979aecbc11ba12668cb21c9fb8452ce1235cd9d7878cc950170421
size 16016554

16
tokenizer_config.json Normal file
View File

@@ -0,0 +1,16 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"is_local": false,
"local_files_only": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

2331
train.log Normal file

File diff suppressed because one or more lines are too long

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 2.0,
"total_flos": 3.833069438698537e+17,
"train_loss": 1.6445721892555754,
"train_runtime": 6416.9422,
"train_samples_per_second": 0.496,
"train_steps_per_second": 0.124
}

160
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,160 @@
{"current_steps": 5, "total_steps": 796, "loss": 2.998407745361328, "lr": 1.6666666666666667e-06, "epoch": 0.01256281407035176, "percentage": 0.63, "elapsed_time": "0:00:38", "remaining_time": "1:42:41"}
{"current_steps": 10, "total_steps": 796, "loss": 2.837660789489746, "lr": 3.7500000000000005e-06, "epoch": 0.02512562814070352, "percentage": 1.26, "elapsed_time": "0:01:20", "remaining_time": "1:45:00"}
{"current_steps": 15, "total_steps": 796, "loss": 2.7715581893920898, "lr": 5.833333333333334e-06, "epoch": 0.03768844221105527, "percentage": 1.88, "elapsed_time": "0:02:00", "remaining_time": "1:44:35"}
{"current_steps": 20, "total_steps": 796, "loss": 2.556188201904297, "lr": 7.916666666666667e-06, "epoch": 0.05025125628140704, "percentage": 2.51, "elapsed_time": "0:02:39", "remaining_time": "1:43:25"}
{"current_steps": 25, "total_steps": 796, "loss": 2.4427762985229493, "lr": 1e-05, "epoch": 0.06281407035175879, "percentage": 3.14, "elapsed_time": "0:03:20", "remaining_time": "1:43:04"}
{"current_steps": 30, "total_steps": 796, "loss": 2.2074916839599608, "lr": 9.998965024239257e-06, "epoch": 0.07537688442211055, "percentage": 3.77, "elapsed_time": "0:04:01", "remaining_time": "1:42:43"}
{"current_steps": 35, "total_steps": 796, "loss": 2.110469627380371, "lr": 9.995860525426954e-06, "epoch": 0.08793969849246232, "percentage": 4.4, "elapsed_time": "0:04:41", "remaining_time": "1:41:52"}
{"current_steps": 40, "total_steps": 796, "loss": 2.0038677215576173, "lr": 9.9906877887955e-06, "epoch": 0.10050251256281408, "percentage": 5.03, "elapsed_time": "0:05:22", "remaining_time": "1:41:42"}
{"current_steps": 45, "total_steps": 796, "loss": 1.951383399963379, "lr": 9.983448955807708e-06, "epoch": 0.11306532663316583, "percentage": 5.65, "elapsed_time": "0:06:02", "remaining_time": "1:40:43"}
{"current_steps": 50, "total_steps": 796, "loss": 1.893879508972168, "lr": 9.974147023270248e-06, "epoch": 0.12562814070351758, "percentage": 6.28, "elapsed_time": "0:06:42", "remaining_time": "1:40:10"}
{"current_steps": 55, "total_steps": 796, "loss": 1.8473941802978515, "lr": 9.962785842093003e-06, "epoch": 0.13819095477386933, "percentage": 6.91, "elapsed_time": "0:07:21", "remaining_time": "1:39:10"}
{"current_steps": 60, "total_steps": 796, "loss": 1.8276456832885741, "lr": 9.949370115694827e-06, "epoch": 0.1507537688442211, "percentage": 7.54, "elapsed_time": "0:08:02", "remaining_time": "1:38:40"}
{"current_steps": 65, "total_steps": 796, "loss": 1.8131959915161133, "lr": 9.933905398056371e-06, "epoch": 0.16331658291457288, "percentage": 8.17, "elapsed_time": "0:08:41", "remaining_time": "1:37:42"}
{"current_steps": 70, "total_steps": 796, "loss": 1.7640661239624023, "lr": 9.916398091420798e-06, "epoch": 0.17587939698492464, "percentage": 8.79, "elapsed_time": "0:09:21", "remaining_time": "1:37:02"}
{"current_steps": 75, "total_steps": 796, "loss": 1.7705204010009765, "lr": 9.896855443643307e-06, "epoch": 0.1884422110552764, "percentage": 9.42, "elapsed_time": "0:10:00", "remaining_time": "1:36:11"}
{"current_steps": 80, "total_steps": 796, "loss": 1.7359968185424806, "lr": 9.875285545190602e-06, "epoch": 0.20100502512562815, "percentage": 10.05, "elapsed_time": "0:10:40", "remaining_time": "1:35:34"}
{"current_steps": 85, "total_steps": 796, "loss": 1.7584953308105469, "lr": 9.851697325791505e-06, "epoch": 0.2135678391959799, "percentage": 10.68, "elapsed_time": "0:11:21", "remaining_time": "1:35:00"}
{"current_steps": 90, "total_steps": 796, "loss": 1.7408344268798828, "lr": 9.826100550740144e-06, "epoch": 0.22613065326633167, "percentage": 11.31, "elapsed_time": "0:12:00", "remaining_time": "1:34:11"}
{"current_steps": 95, "total_steps": 796, "loss": 1.7312856674194337, "lr": 9.798505816853207e-06, "epoch": 0.23869346733668342, "percentage": 11.93, "elapsed_time": "0:12:40", "remaining_time": "1:33:30"}
{"current_steps": 100, "total_steps": 796, "loss": 1.6844066619873046, "lr": 9.768924548082978e-06, "epoch": 0.25125628140703515, "percentage": 12.56, "elapsed_time": "0:13:21", "remaining_time": "1:32:55"}
{"current_steps": 105, "total_steps": 796, "loss": 1.6968770980834962, "lr": 9.737368990787917e-06, "epoch": 0.2638190954773869, "percentage": 13.19, "elapsed_time": "0:14:02", "remaining_time": "1:32:21"}
{"current_steps": 110, "total_steps": 796, "loss": 1.7310028076171875, "lr": 9.703852208662788e-06, "epoch": 0.27638190954773867, "percentage": 13.82, "elapsed_time": "0:14:42", "remaining_time": "1:31:42"}
{"current_steps": 115, "total_steps": 796, "loss": 1.7414098739624024, "lr": 9.668388077330421e-06, "epoch": 0.2889447236180904, "percentage": 14.45, "elapsed_time": "0:15:22", "remaining_time": "1:31:01"}
{"current_steps": 120, "total_steps": 796, "loss": 1.6551843643188477, "lr": 9.630991278597344e-06, "epoch": 0.3015075376884422, "percentage": 15.08, "elapsed_time": "0:16:03", "remaining_time": "1:30:24"}
{"current_steps": 125, "total_steps": 796, "loss": 1.6384830474853516, "lr": 9.591677294375637e-06, "epoch": 0.314070351758794, "percentage": 15.7, "elapsed_time": "0:16:42", "remaining_time": "1:29:42"}
{"current_steps": 130, "total_steps": 796, "loss": 1.6961067199707032, "lr": 9.550462400273595e-06, "epoch": 0.32663316582914576, "percentage": 16.33, "elapsed_time": "0:17:23", "remaining_time": "1:29:03"}
{"current_steps": 135, "total_steps": 796, "loss": 1.7122671127319335, "lr": 9.507363658857768e-06, "epoch": 0.3391959798994975, "percentage": 16.96, "elapsed_time": "0:18:05", "remaining_time": "1:28:33"}
{"current_steps": 140, "total_steps": 796, "loss": 1.6428680419921875, "lr": 9.462398912589232e-06, "epoch": 0.35175879396984927, "percentage": 17.59, "elapsed_time": "0:18:45", "remaining_time": "1:27:51"}
{"current_steps": 145, "total_steps": 796, "loss": 1.6411958694458009, "lr": 9.415586776436973e-06, "epoch": 0.36432160804020103, "percentage": 18.22, "elapsed_time": "0:19:25", "remaining_time": "1:27:13"}
{"current_steps": 150, "total_steps": 796, "loss": 1.645296859741211, "lr": 9.366946630171485e-06, "epoch": 0.3768844221105528, "percentage": 18.84, "elapsed_time": "0:20:05", "remaining_time": "1:26:33"}
{"current_steps": 155, "total_steps": 796, "loss": 1.6568294525146485, "lr": 9.31649861034172e-06, "epoch": 0.38944723618090454, "percentage": 19.47, "elapsed_time": "0:20:45", "remaining_time": "1:25:50"}
{"current_steps": 160, "total_steps": 796, "loss": 1.7317806243896485, "lr": 9.264263601938759e-06, "epoch": 0.4020100502512563, "percentage": 20.1, "elapsed_time": "0:21:26", "remaining_time": "1:25:12"}
{"current_steps": 165, "total_steps": 796, "loss": 1.6810962677001953, "lr": 9.210263229749626e-06, "epoch": 0.41457286432160806, "percentage": 20.73, "elapsed_time": "0:22:06", "remaining_time": "1:24:34"}
{"current_steps": 170, "total_steps": 796, "loss": 1.6197080612182617, "lr": 9.154519849404833e-06, "epoch": 0.4271356783919598, "percentage": 21.36, "elapsed_time": "0:22:48", "remaining_time": "1:23:59"}
{"current_steps": 175, "total_steps": 796, "loss": 1.6504512786865235, "lr": 9.097056538123376e-06, "epoch": 0.4396984924623116, "percentage": 21.98, "elapsed_time": "0:23:26", "remaining_time": "1:23:11"}
{"current_steps": 180, "total_steps": 796, "loss": 1.6403568267822266, "lr": 9.037897085158977e-06, "epoch": 0.45226130653266333, "percentage": 22.61, "elapsed_time": "0:24:06", "remaining_time": "1:22:29"}
{"current_steps": 185, "total_steps": 796, "loss": 1.6068395614624023, "lr": 8.977065981951567e-06, "epoch": 0.4648241206030151, "percentage": 23.24, "elapsed_time": "0:24:47", "remaining_time": "1:21:54"}
{"current_steps": 190, "total_steps": 796, "loss": 1.6754827499389648, "lr": 8.914588411988079e-06, "epoch": 0.47738693467336685, "percentage": 23.87, "elapsed_time": "0:25:29", "remaining_time": "1:21:16"}
{"current_steps": 195, "total_steps": 796, "loss": 1.6853302001953125, "lr": 8.85049024037671e-06, "epoch": 0.4899497487437186, "percentage": 24.5, "elapsed_time": "0:26:09", "remaining_time": "1:20:36"}
{"current_steps": 200, "total_steps": 796, "loss": 1.603452491760254, "lr": 8.784798003139035e-06, "epoch": 0.5025125628140703, "percentage": 25.13, "elapsed_time": "0:26:49", "remaining_time": "1:19:57"}
{"current_steps": 205, "total_steps": 796, "loss": 1.5766297340393067, "lr": 8.717538896224333e-06, "epoch": 0.5150753768844221, "percentage": 25.75, "elapsed_time": "0:27:31", "remaining_time": "1:19:20"}
{"current_steps": 210, "total_steps": 796, "loss": 1.716385269165039, "lr": 8.648740764250745e-06, "epoch": 0.5276381909547738, "percentage": 26.38, "elapsed_time": "0:28:10", "remaining_time": "1:18:38"}
{"current_steps": 215, "total_steps": 796, "loss": 1.592827320098877, "lr": 8.57843208897786e-06, "epoch": 0.5402010050251256, "percentage": 27.01, "elapsed_time": "0:28:50", "remaining_time": "1:17:56"}
{"current_steps": 220, "total_steps": 796, "loss": 1.615340232849121, "lr": 8.50664197751555e-06, "epoch": 0.5527638190954773, "percentage": 27.64, "elapsed_time": "0:29:30", "remaining_time": "1:17:16"}
{"current_steps": 225, "total_steps": 796, "loss": 1.5731450080871583, "lr": 8.433400150273907e-06, "epoch": 0.5653266331658291, "percentage": 28.27, "elapsed_time": "0:30:12", "remaining_time": "1:16:38"}
{"current_steps": 230, "total_steps": 796, "loss": 1.7298618316650392, "lr": 8.358736928659275e-06, "epoch": 0.5778894472361809, "percentage": 28.89, "elapsed_time": "0:30:51", "remaining_time": "1:15:57"}
{"current_steps": 235, "total_steps": 796, "loss": 1.6517925262451172, "lr": 8.282683222521491e-06, "epoch": 0.5904522613065326, "percentage": 29.52, "elapsed_time": "0:31:31", "remaining_time": "1:15:15"}
{"current_steps": 240, "total_steps": 796, "loss": 1.6013933181762696, "lr": 8.205270517357503e-06, "epoch": 0.6030150753768844, "percentage": 30.15, "elapsed_time": "0:32:11", "remaining_time": "1:14:35"}
{"current_steps": 245, "total_steps": 796, "loss": 1.584385585784912, "lr": 8.126530861276677e-06, "epoch": 0.6155778894472361, "percentage": 30.78, "elapsed_time": "0:32:51", "remaining_time": "1:13:54"}
{"current_steps": 250, "total_steps": 796, "loss": 1.5994317054748535, "lr": 8.046496851733195e-06, "epoch": 0.628140703517588, "percentage": 31.41, "elapsed_time": "0:33:32", "remaining_time": "1:13:14"}
{"current_steps": 255, "total_steps": 796, "loss": 1.590476131439209, "lr": 7.96520162203102e-06, "epoch": 0.6407035175879398, "percentage": 32.04, "elapsed_time": "0:34:15", "remaining_time": "1:12:39"}
{"current_steps": 260, "total_steps": 796, "loss": 1.6111858367919922, "lr": 7.88267882760704e-06, "epoch": 0.6532663316582915, "percentage": 32.66, "elapsed_time": "0:34:56", "remaining_time": "1:12:01"}
{"current_steps": 265, "total_steps": 796, "loss": 1.6274175643920898, "lr": 7.798962632098024e-06, "epoch": 0.6658291457286433, "percentage": 33.29, "elapsed_time": "0:35:34", "remaining_time": "1:11:17"}
{"current_steps": 270, "total_steps": 796, "loss": 1.6058385848999024, "lr": 7.714087693197228e-06, "epoch": 0.678391959798995, "percentage": 33.92, "elapsed_time": "0:36:15", "remaining_time": "1:10:38"}
{"current_steps": 275, "total_steps": 796, "loss": 1.5899338722229004, "lr": 7.628089148306434e-06, "epoch": 0.6909547738693468, "percentage": 34.55, "elapsed_time": "0:36:55", "remaining_time": "1:09:57"}
{"current_steps": 280, "total_steps": 796, "loss": 1.5922243118286132, "lr": 7.541002599989411e-06, "epoch": 0.7035175879396985, "percentage": 35.18, "elapsed_time": "0:37:37", "remaining_time": "1:09:19"}
{"current_steps": 285, "total_steps": 796, "loss": 1.5848384857177735, "lr": 7.452864101232798e-06, "epoch": 0.7160804020100503, "percentage": 35.8, "elapsed_time": "0:38:17", "remaining_time": "1:08:39"}
{"current_steps": 290, "total_steps": 796, "loss": 1.60340576171875, "lr": 7.363710140520515e-06, "epoch": 0.7286432160804021, "percentage": 36.43, "elapsed_time": "0:38:57", "remaining_time": "1:07:59"}
{"current_steps": 295, "total_steps": 796, "loss": 1.6018304824829102, "lr": 7.273577626727884e-06, "epoch": 0.7412060301507538, "percentage": 37.06, "elapsed_time": "0:39:37", "remaining_time": "1:07:17"}
{"current_steps": 300, "total_steps": 796, "loss": 1.5592435836791991, "lr": 7.182503873841722e-06, "epoch": 0.7537688442211056, "percentage": 37.69, "elapsed_time": "0:40:18", "remaining_time": "1:06:38"}
{"current_steps": 305, "total_steps": 796, "loss": 1.6086605072021485, "lr": 7.090526585512696e-06, "epoch": 0.7663316582914573, "percentage": 38.32, "elapsed_time": "0:40:58", "remaining_time": "1:05:57"}
{"current_steps": 310, "total_steps": 796, "loss": 1.6314334869384766, "lr": 6.997683839446392e-06, "epoch": 0.7788944723618091, "percentage": 38.94, "elapsed_time": "0:41:38", "remaining_time": "1:05:16"}
{"current_steps": 315, "total_steps": 796, "loss": 1.5340024948120117, "lr": 6.904014071639503e-06, "epoch": 0.7914572864321608, "percentage": 39.57, "elapsed_time": "0:42:19", "remaining_time": "1:04:38"}
{"current_steps": 320, "total_steps": 796, "loss": 1.5246624946594238, "lr": 6.80955606046771e-06, "epoch": 0.8040201005025126, "percentage": 40.2, "elapsed_time": "0:43:00", "remaining_time": "1:03:58"}
{"current_steps": 325, "total_steps": 796, "loss": 1.5667107582092286, "lr": 6.7143489106318e-06, "epoch": 0.8165829145728644, "percentage": 40.83, "elapsed_time": "0:43:41", "remaining_time": "1:03:18"}
{"current_steps": 330, "total_steps": 796, "loss": 1.555766487121582, "lr": 6.618432036968705e-06, "epoch": 0.8291457286432161, "percentage": 41.46, "elapsed_time": "0:44:21", "remaining_time": "1:02:38"}
{"current_steps": 335, "total_steps": 796, "loss": 1.5755093574523926, "lr": 6.52184514813414e-06, "epoch": 0.8417085427135679, "percentage": 42.09, "elapsed_time": "0:45:02", "remaining_time": "1:01:58"}
{"current_steps": 340, "total_steps": 796, "loss": 1.6115888595581054, "lr": 6.424628230163606e-06, "epoch": 0.8542713567839196, "percentage": 42.71, "elapsed_time": "0:45:42", "remaining_time": "1:01:17"}
{"current_steps": 345, "total_steps": 796, "loss": 1.582913589477539, "lr": 6.3268215299185545e-06, "epoch": 0.8668341708542714, "percentage": 43.34, "elapsed_time": "0:46:23", "remaining_time": "1:00:38"}
{"current_steps": 350, "total_steps": 796, "loss": 1.5411038398742676, "lr": 6.228465538424583e-06, "epoch": 0.8793969849246231, "percentage": 43.97, "elapsed_time": "0:47:03", "remaining_time": "0:59:57"}
{"current_steps": 355, "total_steps": 796, "loss": 1.5892680168151856, "lr": 6.129600974108538e-06, "epoch": 0.8919597989949749, "percentage": 44.6, "elapsed_time": "0:47:44", "remaining_time": "0:59:17"}
{"current_steps": 360, "total_steps": 796, "loss": 1.5735843658447266, "lr": 6.0302687659414904e-06, "epoch": 0.9045226130653267, "percentage": 45.23, "elapsed_time": "0:48:24", "remaining_time": "0:58:37"}
{"current_steps": 365, "total_steps": 796, "loss": 1.5499893188476563, "lr": 5.93051003649452e-06, "epoch": 0.9170854271356784, "percentage": 45.85, "elapsed_time": "0:49:06", "remaining_time": "0:57:59"}
{"current_steps": 370, "total_steps": 796, "loss": 1.6115238189697265, "lr": 5.83036608491439e-06, "epoch": 0.9296482412060302, "percentage": 46.48, "elapsed_time": "0:49:48", "remaining_time": "0:57:20"}
{"current_steps": 375, "total_steps": 796, "loss": 1.5861882209777831, "lr": 5.729878369826087e-06, "epoch": 0.9422110552763819, "percentage": 47.11, "elapsed_time": "0:50:27", "remaining_time": "0:56:38"}
{"current_steps": 380, "total_steps": 796, "loss": 1.5845415115356445, "lr": 5.62908849216936e-06, "epoch": 0.9547738693467337, "percentage": 47.74, "elapsed_time": "0:51:06", "remaining_time": "0:55:56"}
{"current_steps": 385, "total_steps": 796, "loss": 1.5787755012512208, "lr": 5.52803817797633e-06, "epoch": 0.9673366834170855, "percentage": 48.37, "elapsed_time": "0:51:45", "remaining_time": "0:55:14"}
{"current_steps": 390, "total_steps": 796, "loss": 1.5202445983886719, "lr": 5.426769261097318e-06, "epoch": 0.9798994974874372, "percentage": 48.99, "elapsed_time": "0:52:25", "remaining_time": "0:54:34"}
{"current_steps": 395, "total_steps": 796, "loss": 1.5645788192749024, "lr": 5.325323665882039e-06, "epoch": 0.992462311557789, "percentage": 49.62, "elapsed_time": "0:53:04", "remaining_time": "0:53:52"}
{"current_steps": 400, "total_steps": 796, "loss": 1.5927098274230957, "lr": 5.223743389823327e-06, "epoch": 1.0050251256281406, "percentage": 50.25, "elapsed_time": "0:53:43", "remaining_time": "0:53:11"}
{"current_steps": 405, "total_steps": 796, "loss": 1.6001703262329101, "lr": 5.1220704861705775e-06, "epoch": 1.0175879396984924, "percentage": 50.88, "elapsed_time": "0:54:25", "remaining_time": "0:52:32"}
{"current_steps": 410, "total_steps": 796, "loss": 1.5346534729003907, "lr": 5.020347046520112e-06, "epoch": 1.0301507537688441, "percentage": 51.51, "elapsed_time": "0:55:07", "remaining_time": "0:51:53"}
{"current_steps": 415, "total_steps": 796, "loss": 1.5630980491638184, "lr": 4.918615183389666e-06, "epoch": 1.0427135678391959, "percentage": 52.14, "elapsed_time": "0:55:48", "remaining_time": "0:51:14"}
{"current_steps": 420, "total_steps": 796, "loss": 1.523043441772461, "lr": 4.8169170127842135e-06, "epoch": 1.0552763819095476, "percentage": 52.76, "elapsed_time": "0:56:28", "remaining_time": "0:50:33"}
{"current_steps": 425, "total_steps": 796, "loss": 1.5776254653930664, "lr": 4.715294636760352e-06, "epoch": 1.0678391959798994, "percentage": 53.39, "elapsed_time": "0:57:09", "remaining_time": "0:49:53"}
{"current_steps": 430, "total_steps": 796, "loss": 1.5493414878845215, "lr": 4.6137901259964515e-06, "epoch": 1.0804020100502512, "percentage": 54.02, "elapsed_time": "0:57:49", "remaining_time": "0:49:12"}
{"current_steps": 435, "total_steps": 796, "loss": 1.5309125900268554, "lr": 4.512445502375813e-06, "epoch": 1.092964824120603, "percentage": 54.65, "elapsed_time": "0:58:30", "remaining_time": "0:48:33"}
{"current_steps": 440, "total_steps": 796, "loss": 1.54165620803833, "lr": 4.411302721590006e-06, "epoch": 1.1055276381909547, "percentage": 55.28, "elapsed_time": "0:59:10", "remaining_time": "0:47:52"}
{"current_steps": 445, "total_steps": 796, "loss": 1.5176856994628907, "lr": 4.310403655769629e-06, "epoch": 1.1180904522613064, "percentage": 55.9, "elapsed_time": "0:59:49", "remaining_time": "0:47:11"}
{"current_steps": 450, "total_steps": 796, "loss": 1.5529046058654785, "lr": 4.209790076149644e-06, "epoch": 1.1306532663316582, "percentage": 56.53, "elapsed_time": "1:00:29", "remaining_time": "0:46:31"}
{"current_steps": 455, "total_steps": 796, "loss": 1.565816593170166, "lr": 4.109503635776492e-06, "epoch": 1.1432160804020102, "percentage": 57.16, "elapsed_time": "1:01:10", "remaining_time": "0:45:50"}
{"current_steps": 460, "total_steps": 796, "loss": 1.5432037353515624, "lr": 4.009585852264139e-06, "epoch": 1.1557788944723617, "percentage": 57.79, "elapsed_time": "1:01:50", "remaining_time": "0:45:10"}
{"current_steps": 465, "total_steps": 796, "loss": 1.6062923431396485, "lr": 3.91007809060619e-06, "epoch": 1.1683417085427137, "percentage": 58.42, "elapsed_time": "1:02:32", "remaining_time": "0:44:30"}
{"current_steps": 470, "total_steps": 796, "loss": 1.5221455574035645, "lr": 3.8110215460511697e-06, "epoch": 1.1809045226130652, "percentage": 59.05, "elapsed_time": "1:03:12", "remaining_time": "0:43:50"}
{"current_steps": 475, "total_steps": 796, "loss": 1.6717411041259767, "lr": 3.7124572270481055e-06, "epoch": 1.1934673366834172, "percentage": 59.67, "elapsed_time": "1:03:53", "remaining_time": "0:43:10"}
{"current_steps": 480, "total_steps": 796, "loss": 1.5347406387329101, "lr": 3.6144259382694115e-06, "epoch": 1.2060301507537687, "percentage": 60.3, "elapsed_time": "1:04:34", "remaining_time": "0:42:30"}
{"current_steps": 485, "total_steps": 796, "loss": 1.6209028244018555, "lr": 3.516968263718159e-06, "epoch": 1.2185929648241207, "percentage": 60.93, "elapsed_time": "1:05:14", "remaining_time": "0:41:50"}
{"current_steps": 490, "total_steps": 796, "loss": 1.5777502059936523, "lr": 3.420124549926693e-06, "epoch": 1.2311557788944723, "percentage": 61.56, "elapsed_time": "1:05:55", "remaining_time": "0:41:10"}
{"current_steps": 495, "total_steps": 796, "loss": 1.6334873199462892, "lr": 3.3239348892535562e-06, "epoch": 1.2437185929648242, "percentage": 62.19, "elapsed_time": "1:06:35", "remaining_time": "0:40:29"}
{"current_steps": 500, "total_steps": 796, "loss": 1.5432828903198241, "lr": 3.228439103285641e-06, "epoch": 1.2562814070351758, "percentage": 62.81, "elapsed_time": "1:07:16", "remaining_time": "0:39:49"}
{"current_steps": 505, "total_steps": 796, "loss": 1.5457247734069823, "lr": 3.133676726352438e-06, "epoch": 1.2688442211055277, "percentage": 63.44, "elapsed_time": "1:07:59", "remaining_time": "0:39:10"}
{"current_steps": 510, "total_steps": 796, "loss": 1.6380638122558593, "lr": 3.0396869891592096e-06, "epoch": 1.2814070351758793, "percentage": 64.07, "elapsed_time": "1:08:38", "remaining_time": "0:38:29"}
{"current_steps": 515, "total_steps": 796, "loss": 1.562052059173584, "lr": 2.946508802545859e-06, "epoch": 1.2939698492462313, "percentage": 64.7, "elapsed_time": "1:09:19", "remaining_time": "0:37:49"}
{"current_steps": 520, "total_steps": 796, "loss": 1.5281488418579101, "lr": 2.8541807413782142e-06, "epoch": 1.3065326633165828, "percentage": 65.33, "elapsed_time": "1:09:59", "remaining_time": "0:37:09"}
{"current_steps": 525, "total_steps": 796, "loss": 1.586146926879883, "lr": 2.7627410285784164e-06, "epoch": 1.3190954773869348, "percentage": 65.95, "elapsed_time": "1:10:40", "remaining_time": "0:36:28"}
{"current_steps": 530, "total_steps": 796, "loss": 1.5366415977478027, "lr": 2.6722275193009872e-06, "epoch": 1.3316582914572863, "percentage": 66.58, "elapsed_time": "1:11:23", "remaining_time": "0:35:49"}
{"current_steps": 535, "total_steps": 796, "loss": 1.5299442291259766, "lr": 2.582677685261179e-06, "epoch": 1.3442211055276383, "percentage": 67.21, "elapsed_time": "1:12:03", "remaining_time": "0:35:09"}
{"current_steps": 540, "total_steps": 796, "loss": 1.5406274795532227, "lr": 2.4941285992220353e-06, "epoch": 1.3567839195979898, "percentage": 67.84, "elapsed_time": "1:12:43", "remaining_time": "0:34:28"}
{"current_steps": 545, "total_steps": 796, "loss": 1.538019561767578, "lr": 2.4066169196466326e-06, "epoch": 1.3693467336683418, "percentage": 68.47, "elapsed_time": "1:13:23", "remaining_time": "0:33:48"}
{"current_steps": 550, "total_steps": 796, "loss": 1.5008614540100098, "lr": 2.3201788755218265e-06, "epoch": 1.3819095477386933, "percentage": 69.1, "elapsed_time": "1:14:05", "remaining_time": "0:33:08"}
{"current_steps": 555, "total_steps": 796, "loss": 1.6197319030761719, "lr": 2.2348502513598035e-06, "epoch": 1.3944723618090453, "percentage": 69.72, "elapsed_time": "1:14:44", "remaining_time": "0:32:27"}
{"current_steps": 560, "total_steps": 796, "loss": 1.6248485565185546, "lr": 2.15066637238365e-06, "epoch": 1.4070351758793969, "percentage": 70.35, "elapsed_time": "1:15:24", "remaining_time": "0:31:46"}
{"current_steps": 565, "total_steps": 796, "loss": 1.5241939544677734, "lr": 2.0676620899030393e-06, "epoch": 1.4195979899497488, "percentage": 70.98, "elapsed_time": "1:16:05", "remaining_time": "0:31:06"}
{"current_steps": 570, "total_steps": 796, "loss": 1.532661533355713, "lr": 1.985871766886136e-06, "epoch": 1.4321608040201004, "percentage": 71.61, "elapsed_time": "1:16:45", "remaining_time": "0:30:25"}
{"current_steps": 575, "total_steps": 796, "loss": 1.5913199424743651, "lr": 1.905329263733649e-06, "epoch": 1.4447236180904524, "percentage": 72.24, "elapsed_time": "1:17:23", "remaining_time": "0:29:44"}
{"current_steps": 580, "total_steps": 796, "loss": 1.534491729736328, "lr": 1.8260679242609703e-06, "epoch": 1.457286432160804, "percentage": 72.86, "elapsed_time": "1:18:02", "remaining_time": "0:29:03"}
{"current_steps": 585, "total_steps": 796, "loss": 1.5714677810668944, "lr": 1.7481205618941472e-06, "epoch": 1.4698492462311559, "percentage": 73.49, "elapsed_time": "1:18:41", "remaining_time": "0:28:23"}
{"current_steps": 590, "total_steps": 796, "loss": 1.5404623031616211, "lr": 1.6715194460854466e-06, "epoch": 1.4824120603015074, "percentage": 74.12, "elapsed_time": "1:19:21", "remaining_time": "0:27:42"}
{"current_steps": 595, "total_steps": 796, "loss": 1.5692951202392578, "lr": 1.5962962889541106e-06, "epoch": 1.4949748743718594, "percentage": 74.75, "elapsed_time": "1:20:00", "remaining_time": "0:27:01"}
{"current_steps": 600, "total_steps": 796, "loss": 1.5303547859191895, "lr": 1.5224822321578481e-06, "epoch": 1.507537688442211, "percentage": 75.38, "elapsed_time": "1:20:41", "remaining_time": "0:26:21"}
{"current_steps": 605, "total_steps": 796, "loss": 1.5067039489746095, "lr": 1.4501078340004954e-06, "epoch": 1.520100502512563, "percentage": 76.01, "elapsed_time": "1:21:22", "remaining_time": "0:25:41"}
{"current_steps": 610, "total_steps": 796, "loss": 1.5673861503601074, "lr": 1.3792030567811687e-06, "epoch": 1.5326633165829144, "percentage": 76.63, "elapsed_time": "1:22:03", "remaining_time": "0:25:01"}
{"current_steps": 615, "total_steps": 796, "loss": 1.5892368316650392, "lr": 1.3097972543901672e-06, "epoch": 1.5452261306532664, "percentage": 77.26, "elapsed_time": "1:22:43", "remaining_time": "0:24:20"}
{"current_steps": 620, "total_steps": 796, "loss": 1.5634510040283203, "lr": 1.2419191601567409e-06, "epoch": 1.557788944723618, "percentage": 77.89, "elapsed_time": "1:23:24", "remaining_time": "0:23:40"}
{"current_steps": 625, "total_steps": 796, "loss": 1.5212089538574218, "lr": 1.1755968749537755e-06, "epoch": 1.57035175879397, "percentage": 78.52, "elapsed_time": "1:24:05", "remaining_time": "0:23:00"}
{"current_steps": 630, "total_steps": 796, "loss": 1.5546403884887696, "lr": 1.1108578555643058e-06, "epoch": 1.5829145728643215, "percentage": 79.15, "elapsed_time": "1:24:45", "remaining_time": "0:22:20"}
{"current_steps": 635, "total_steps": 796, "loss": 1.5283503532409668, "lr": 1.0477289033146675e-06, "epoch": 1.5954773869346734, "percentage": 79.77, "elapsed_time": "1:25:26", "remaining_time": "0:21:39"}
{"current_steps": 640, "total_steps": 796, "loss": 1.5374995231628419, "lr": 9.86236152979015e-07, "epoch": 1.608040201005025, "percentage": 80.4, "elapsed_time": "1:26:06", "remaining_time": "0:20:59"}
{"current_steps": 645, "total_steps": 796, "loss": 1.5790555000305175, "lr": 9.264050619597697e-07, "epoch": 1.620603015075377, "percentage": 81.03, "elapsed_time": "1:26:44", "remaining_time": "0:20:18"}
{"current_steps": 650, "total_steps": 796, "loss": 1.5679688453674316, "lr": 8.682603997485078e-07, "epoch": 1.6331658291457285, "percentage": 81.66, "elapsed_time": "1:27:25", "remaining_time": "0:19:38"}
{"current_steps": 655, "total_steps": 796, "loss": 1.529183292388916, "lr": 8.11826237671634e-07, "epoch": 1.6457286432160805, "percentage": 82.29, "elapsed_time": "1:28:05", "remaining_time": "0:18:57"}
{"current_steps": 660, "total_steps": 796, "loss": 1.5451692581176757, "lr": 7.571259389250779e-07, "epoch": 1.658291457286432, "percentage": 82.91, "elapsed_time": "1:28:44", "remaining_time": "0:18:17"}
{"current_steps": 665, "total_steps": 796, "loss": 1.5198535919189453, "lr": 7.041821489021639e-07, "epoch": 1.670854271356784, "percentage": 83.54, "elapsed_time": "1:29:25", "remaining_time": "0:17:36"}
{"current_steps": 670, "total_steps": 796, "loss": 1.5573585510253907, "lr": 6.530167858186343e-07, "epoch": 1.6834170854271355, "percentage": 84.17, "elapsed_time": "1:30:05", "remaining_time": "0:16:56"}
{"current_steps": 675, "total_steps": 796, "loss": 1.5550883293151856, "lr": 6.036510316387196e-07, "epoch": 1.6959798994974875, "percentage": 84.8, "elapsed_time": "1:30:45", "remaining_time": "0:16:16"}
{"current_steps": 680, "total_steps": 796, "loss": 1.5345685958862305, "lr": 5.561053233060154e-07, "epoch": 1.708542713567839, "percentage": 85.43, "elapsed_time": "1:31:26", "remaining_time": "0:15:35"}
{"current_steps": 685, "total_steps": 796, "loss": 1.5294795989990235, "lr": 5.103993442827832e-07, "epoch": 1.721105527638191, "percentage": 86.06, "elapsed_time": "1:32:06", "remaining_time": "0:14:55"}
{"current_steps": 690, "total_steps": 796, "loss": 1.6449104309082032, "lr": 4.6655201640118775e-07, "epoch": 1.7336683417085426, "percentage": 86.68, "elapsed_time": "1:32:44", "remaining_time": "0:14:14"}
{"current_steps": 695, "total_steps": 796, "loss": 1.5543377876281739, "lr": 4.2458149202984025e-07, "epoch": 1.7462311557788945, "percentage": 87.31, "elapsed_time": "1:33:23", "remaining_time": "0:13:34"}
{"current_steps": 700, "total_steps": 796, "loss": 1.5942207336425782, "lr": 3.845051465588961e-07, "epoch": 1.758793969849246, "percentage": 87.94, "elapsed_time": "1:34:03", "remaining_time": "0:12:53"}
{"current_steps": 705, "total_steps": 796, "loss": 1.5990875244140625, "lr": 3.4633957120681294e-07, "epoch": 1.771356783919598, "percentage": 88.57, "elapsed_time": "1:34:43", "remaining_time": "0:12:13"}
{"current_steps": 710, "total_steps": 796, "loss": 1.5136988639831543, "lr": 3.1010056615174367e-07, "epoch": 1.7839195979899496, "percentage": 89.2, "elapsed_time": "1:35:24", "remaining_time": "0:11:33"}
{"current_steps": 715, "total_steps": 796, "loss": 1.6442916870117188, "lr": 2.75803133990421e-07, "epoch": 1.7964824120603016, "percentage": 89.82, "elapsed_time": "1:36:05", "remaining_time": "0:10:53"}
{"current_steps": 720, "total_steps": 796, "loss": 1.524810791015625, "lr": 2.434614735272184e-07, "epoch": 1.809045226130653, "percentage": 90.45, "elapsed_time": "1:36:47", "remaining_time": "0:10:12"}
{"current_steps": 725, "total_steps": 796, "loss": 1.6057912826538085, "lr": 2.130889738959946e-07, "epoch": 1.821608040201005, "percentage": 91.08, "elapsed_time": "1:37:25", "remaining_time": "0:09:32"}
{"current_steps": 730, "total_steps": 796, "loss": 1.5753741264343262, "lr": 1.8469820901711345e-07, "epoch": 1.8341708542713566, "percentage": 91.71, "elapsed_time": "1:38:04", "remaining_time": "0:08:52"}
{"current_steps": 735, "total_steps": 796, "loss": 1.5886516571044922, "lr": 1.5830093239196765e-07, "epoch": 1.8467336683417086, "percentage": 92.34, "elapsed_time": "1:38:44", "remaining_time": "0:08:11"}
{"current_steps": 740, "total_steps": 796, "loss": 1.5261211395263672, "lr": 1.3390807223713887e-07, "epoch": 1.8592964824120601, "percentage": 92.96, "elapsed_time": "1:39:22", "remaining_time": "0:07:31"}
{"current_steps": 745, "total_steps": 796, "loss": 1.5142106056213378, "lr": 1.1152972696022447e-07, "epoch": 1.8718592964824121, "percentage": 93.59, "elapsed_time": "1:40:02", "remaining_time": "0:06:50"}
{"current_steps": 750, "total_steps": 796, "loss": 1.555587387084961, "lr": 9.117516097919721e-08, "epoch": 1.8844221105527639, "percentage": 94.22, "elapsed_time": "1:40:42", "remaining_time": "0:06:10"}
{"current_steps": 755, "total_steps": 796, "loss": 1.5386908531188965, "lr": 7.285280088701996e-08, "epoch": 1.8969849246231156, "percentage": 94.85, "elapsed_time": "1:41:22", "remaining_time": "0:05:30"}
{"current_steps": 760, "total_steps": 796, "loss": 1.5089382171630858, "lr": 5.657023196312394e-08, "epoch": 1.9095477386934674, "percentage": 95.48, "elapsed_time": "1:42:03", "remaining_time": "0:04:50"}
{"current_steps": 765, "total_steps": 796, "loss": 1.5173494338989257, "lr": 4.233419503317182e-08, "epoch": 1.9221105527638191, "percentage": 96.11, "elapsed_time": "1:42:44", "remaining_time": "0:04:09"}
{"current_steps": 770, "total_steps": 796, "loss": 1.5515380859375, "lr": 3.0150583678423825e-08, "epoch": 1.934673366834171, "percentage": 96.73, "elapsed_time": "1:43:25", "remaining_time": "0:03:29"}
{"current_steps": 775, "total_steps": 796, "loss": 1.529140090942383, "lr": 2.002444179585339e-08, "epoch": 1.9472361809045227, "percentage": 97.36, "elapsed_time": "1:44:05", "remaining_time": "0:02:49"}
{"current_steps": 780, "total_steps": 796, "loss": 1.5413886070251466, "lr": 1.1959961510018547e-08, "epoch": 1.9597989949748744, "percentage": 97.99, "elapsed_time": "1:44:45", "remaining_time": "0:02:08"}
{"current_steps": 785, "total_steps": 796, "loss": 1.5065739631652832, "lr": 5.9604814375685546e-09, "epoch": 1.9723618090452262, "percentage": 98.62, "elapsed_time": "1:45:25", "remaining_time": "0:01:28"}
{"current_steps": 790, "total_steps": 796, "loss": 1.575080680847168, "lr": 2.028485305082817e-09, "epoch": 1.984924623115578, "percentage": 99.25, "elapsed_time": "1:46:05", "remaining_time": "0:00:48"}
{"current_steps": 795, "total_steps": 796, "loss": 1.5597107887268067, "lr": 1.6560092083672818e-10, "epoch": 1.9974874371859297, "percentage": 99.87, "elapsed_time": "1:46:45", "remaining_time": "0:00:08"}
{"current_steps": 796, "total_steps": 796, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "1:46:56", "remaining_time": "0:00:00"}

1156
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 sha256:0b38f843359b674af66519e06c22a008f5ba20cc1427673092aaf3fb81fc3bff
size 6033

BIN
training_loss.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 45 KiB