lldois/v08_rec_focus_lr2e5
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: lldois/v08_rec_focus_lr2e5
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-16 18:03:17 +08:00
commit 554c7f1188
16 changed files with 1764 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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: v08_rec_focus_lr2e5
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. -->
# v08_rec_focus_lr2e5
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_rec_focus 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: 2e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 202607068
- 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: 1
### 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": 1.0,
"total_flos": 1.335043548266926e+17,
"train_loss": 1.5747115251829298,
"train_runtime": 2170.5286,
"train_samples_per_second": 0.512,
"train_steps_per_second": 0.128
}

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:acd27da718075ff3ab7a5664c97044c138a235072a04b68af3f71336d5d140b8
size 1602902832

3
runs/Jul06_04-17-30_ubuntu-System-Product-Name/events.out.tfevents.1783282650.ubuntu-System-Product-Name.1677645.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a7e744e61372cf82f02b676403e82dec5883f3bd1d38fada3c64d7390c68a44d
size 17819

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
}

978
train.log Normal file
View 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": 1.0,
"total_flos": 1.335043548266926e+17,
"train_loss": 1.5747115251829298,
"train_runtime": 2170.5286,
"train_samples_per_second": 0.512,
"train_steps_per_second": 0.128
}

56
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,56 @@
{"current_steps": 5, "total_steps": 278, "loss": 2.950368309020996, "lr": 8.888888888888888e-06, "epoch": 0.017985611510791366, "percentage": 1.8, "elapsed_time": "0:00:39", "remaining_time": "0:36:12"}
{"current_steps": 10, "total_steps": 278, "loss": 2.4953432083129883, "lr": 2e-05, "epoch": 0.03597122302158273, "percentage": 3.6, "elapsed_time": "0:01:17", "remaining_time": "0:34:50"}
{"current_steps": 15, "total_steps": 278, "loss": 2.1284584045410155, "lr": 1.9982955597229275e-05, "epoch": 0.0539568345323741, "percentage": 5.4, "elapsed_time": "0:01:56", "remaining_time": "0:34:08"}
{"current_steps": 20, "total_steps": 278, "loss": 1.9327747344970703, "lr": 1.9931880491250263e-05, "epoch": 0.07194244604316546, "percentage": 7.19, "elapsed_time": "0:02:36", "remaining_time": "0:33:35"}
{"current_steps": 25, "total_steps": 278, "loss": 1.813704490661621, "lr": 1.9846948790998532e-05, "epoch": 0.08992805755395683, "percentage": 8.99, "elapsed_time": "0:03:15", "remaining_time": "0:32:58"}
{"current_steps": 30, "total_steps": 278, "loss": 1.739830207824707, "lr": 1.9728450018495506e-05, "epoch": 0.1079136690647482, "percentage": 10.79, "elapsed_time": "0:03:54", "remaining_time": "0:32:22"}
{"current_steps": 35, "total_steps": 278, "loss": 1.7107593536376953, "lr": 1.9576788121902457e-05, "epoch": 0.12589928057553956, "percentage": 12.59, "elapsed_time": "0:04:34", "remaining_time": "0:31:46"}
{"current_steps": 40, "total_steps": 278, "loss": 1.6636060714721679, "lr": 1.9392480098509488e-05, "epoch": 0.14388489208633093, "percentage": 14.39, "elapsed_time": "0:05:13", "remaining_time": "0:31:04"}
{"current_steps": 45, "total_steps": 278, "loss": 1.6550146102905274, "lr": 1.9176154232353513e-05, "epoch": 0.1618705035971223, "percentage": 16.19, "elapsed_time": "0:05:50", "remaining_time": "0:30:16"}
{"current_steps": 50, "total_steps": 278, "loss": 1.620616340637207, "lr": 1.8928547952473037e-05, "epoch": 0.17985611510791366, "percentage": 17.99, "elapsed_time": "0:06:30", "remaining_time": "0:29:40"}
{"current_steps": 55, "total_steps": 278, "loss": 1.5874693870544434, "lr": 1.865050531910062e-05, "epoch": 0.19784172661870503, "percentage": 19.78, "elapsed_time": "0:07:10", "remaining_time": "0:29:04"}
{"current_steps": 60, "total_steps": 278, "loss": 1.5906153678894044, "lr": 1.8342974146362397e-05, "epoch": 0.2158273381294964, "percentage": 21.58, "elapsed_time": "0:07:48", "remaining_time": "0:28:21"}
{"current_steps": 65, "total_steps": 278, "loss": 1.5618690490722655, "lr": 1.80070027712929e-05, "epoch": 0.23381294964028776, "percentage": 23.38, "elapsed_time": "0:08:27", "remaining_time": "0:27:43"}
{"current_steps": 70, "total_steps": 278, "loss": 1.560389232635498, "lr": 1.7643736480179353e-05, "epoch": 0.2517985611510791, "percentage": 25.18, "elapsed_time": "0:09:07", "remaining_time": "0:27:06"}
{"current_steps": 75, "total_steps": 278, "loss": 1.5437555313110352, "lr": 1.725441360441752e-05, "epoch": 0.2697841726618705, "percentage": 26.98, "elapsed_time": "0:09:46", "remaining_time": "0:26:27"}
{"current_steps": 80, "total_steps": 278, "loss": 1.523001766204834, "lr": 1.684036129918786e-05, "epoch": 0.28776978417266186, "percentage": 28.78, "elapsed_time": "0:10:25", "remaining_time": "0:25:47"}
{"current_steps": 85, "total_steps": 278, "loss": 1.5343033790588378, "lr": 1.6402991019342073e-05, "epoch": 0.3057553956834532, "percentage": 30.58, "elapsed_time": "0:11:04", "remaining_time": "0:25:08"}
{"current_steps": 90, "total_steps": 278, "loss": 1.5191097259521484, "lr": 1.5943793707922086e-05, "epoch": 0.3237410071942446, "percentage": 32.37, "elapsed_time": "0:11:43", "remaining_time": "0:24:30"}
{"current_steps": 95, "total_steps": 278, "loss": 1.5029571533203125, "lr": 1.5464334713713312e-05, "epoch": 0.34172661870503596, "percentage": 34.17, "elapsed_time": "0:12:21", "remaining_time": "0:23:48"}
{"current_steps": 100, "total_steps": 278, "loss": 1.5281996726989746, "lr": 1.4966248455157622e-05, "epoch": 0.3597122302158273, "percentage": 35.97, "elapsed_time": "0:13:00", "remaining_time": "0:23:09"}
{"current_steps": 105, "total_steps": 278, "loss": 1.5251441955566407, "lr": 1.445123284881609e-05, "epoch": 0.3776978417266187, "percentage": 37.77, "elapsed_time": "0:13:38", "remaining_time": "0:22:28"}
{"current_steps": 110, "total_steps": 278, "loss": 1.5085590362548829, "lr": 1.392104352137426e-05, "epoch": 0.39568345323741005, "percentage": 39.57, "elapsed_time": "0:14:17", "remaining_time": "0:21:49"}
{"current_steps": 115, "total_steps": 278, "loss": 1.500697422027588, "lr": 1.3377487824920459e-05, "epoch": 0.4136690647482014, "percentage": 41.37, "elapsed_time": "0:14:57", "remaining_time": "0:21:11"}
{"current_steps": 120, "total_steps": 278, "loss": 1.4779583930969238, "lr": 1.2822418675898428e-05, "epoch": 0.4316546762589928, "percentage": 43.17, "elapsed_time": "0:15:36", "remaining_time": "0:20:33"}
{"current_steps": 125, "total_steps": 278, "loss": 1.4670068740844726, "lr": 1.2257728238736468e-05, "epoch": 0.44964028776978415, "percentage": 44.96, "elapsed_time": "0:16:16", "remaining_time": "0:19:54"}
{"current_steps": 130, "total_steps": 278, "loss": 1.489361572265625, "lr": 1.1685341475684935e-05, "epoch": 0.4676258992805755, "percentage": 46.76, "elapsed_time": "0:16:54", "remaining_time": "0:19:15"}
{"current_steps": 135, "total_steps": 278, "loss": 1.4737789154052734, "lr": 1.1107209584849845e-05, "epoch": 0.4856115107913669, "percentage": 48.56, "elapsed_time": "0:17:33", "remaining_time": "0:18:36"}
{"current_steps": 140, "total_steps": 278, "loss": 1.4690287590026856, "lr": 1.0525303348791599e-05, "epoch": 0.5035971223021583, "percentage": 50.36, "elapsed_time": "0:18:13", "remaining_time": "0:17:57"}
{"current_steps": 145, "total_steps": 278, "loss": 1.49021577835083, "lr": 9.94160641636263e-06, "epoch": 0.5215827338129496, "percentage": 52.16, "elapsed_time": "0:18:53", "remaining_time": "0:17:19"}
{"current_steps": 150, "total_steps": 278, "loss": 1.4638582229614259, "lr": 9.358108540685406e-06, "epoch": 0.539568345323741, "percentage": 53.96, "elapsed_time": "0:19:32", "remaining_time": "0:16:40"}
{"current_steps": 155, "total_steps": 278, "loss": 1.4586694717407227, "lr": 8.776798796321715e-06, "epoch": 0.5575539568345323, "percentage": 55.76, "elapsed_time": "0:20:10", "remaining_time": "0:16:00"}
{"current_steps": 160, "total_steps": 278, "loss": 1.479645347595215, "lr": 8.199658798755048e-06, "epoch": 0.5755395683453237, "percentage": 57.55, "elapsed_time": "0:20:49", "remaining_time": "0:15:21"}
{"current_steps": 165, "total_steps": 278, "loss": 1.455679225921631, "lr": 7.628655949300133e-06, "epoch": 0.5935251798561151, "percentage": 59.35, "elapsed_time": "0:21:28", "remaining_time": "0:14:42"}
{"current_steps": 170, "total_steps": 278, "loss": 1.4653221130371095, "lr": 7.065736728466832e-06, "epoch": 0.6115107913669064, "percentage": 61.15, "elapsed_time": "0:22:05", "remaining_time": "0:14:02"}
{"current_steps": 175, "total_steps": 278, "loss": 1.4618860244750977, "lr": 6.512820060640608e-06, "epoch": 0.6294964028776978, "percentage": 62.95, "elapsed_time": "0:22:44", "remaining_time": "0:13:23"}
{"current_steps": 180, "total_steps": 278, "loss": 1.449009895324707, "lr": 5.971790772698467e-06, "epoch": 0.6474820143884892, "percentage": 64.75, "elapsed_time": "0:23:24", "remaining_time": "0:12:44"}
{"current_steps": 185, "total_steps": 278, "loss": 1.449843692779541, "lr": 5.444493168859304e-06, "epoch": 0.6654676258992805, "percentage": 66.55, "elapsed_time": "0:24:02", "remaining_time": "0:12:05"}
{"current_steps": 190, "total_steps": 278, "loss": 1.459362506866455, "lr": 4.932724743671089e-06, "epoch": 0.6834532374100719, "percentage": 68.35, "elapsed_time": "0:24:41", "remaining_time": "0:11:26"}
{"current_steps": 195, "total_steps": 278, "loss": 1.470369243621826, "lr": 4.438230054566678e-06, "epoch": 0.7014388489208633, "percentage": 70.14, "elapsed_time": "0:25:21", "remaining_time": "0:10:47"}
{"current_steps": 200, "total_steps": 278, "loss": 1.4958831787109375, "lr": 3.96269477487588e-06, "epoch": 0.7194244604316546, "percentage": 71.94, "elapsed_time": "0:26:00", "remaining_time": "0:10:08"}
{"current_steps": 205, "total_steps": 278, "loss": 1.4567132949829102, "lr": 3.5077399475664474e-06, "epoch": 0.737410071942446, "percentage": 73.74, "elapsed_time": "0:26:38", "remaining_time": "0:09:29"}
{"current_steps": 210, "total_steps": 278, "loss": 1.4700736045837401, "lr": 3.074916459302211e-06, "epoch": 0.7553956834532374, "percentage": 75.54, "elapsed_time": "0:27:17", "remaining_time": "0:08:50"}
{"current_steps": 215, "total_steps": 278, "loss": 1.442730712890625, "lr": 2.665699753655684e-06, "epoch": 0.7733812949640287, "percentage": 77.34, "elapsed_time": "0:27:57", "remaining_time": "0:08:11"}
{"current_steps": 220, "total_steps": 278, "loss": 1.464546012878418, "lr": 2.281484801497186e-06, "epoch": 0.7913669064748201, "percentage": 79.14, "elapsed_time": "0:28:34", "remaining_time": "0:07:31"}
{"current_steps": 225, "total_steps": 278, "loss": 1.4540756225585938, "lr": 1.923581345705736e-06, "epoch": 0.8093525179856115, "percentage": 80.94, "elapsed_time": "0:29:13", "remaining_time": "0:06:53"}
{"current_steps": 230, "total_steps": 278, "loss": 1.4824945449829101, "lr": 1.5932094364120453e-06, "epoch": 0.8273381294964028, "percentage": 82.73, "elapsed_time": "0:29:53", "remaining_time": "0:06:14"}
{"current_steps": 235, "total_steps": 278, "loss": 1.4647997856140136, "lr": 1.291495271993337e-06, "epoch": 0.8453237410071942, "percentage": 84.53, "elapsed_time": "0:30:33", "remaining_time": "0:05:35"}
{"current_steps": 240, "total_steps": 278, "loss": 1.4619410514831543, "lr": 1.0194673599976134e-06, "epoch": 0.8633093525179856, "percentage": 86.33, "elapsed_time": "0:31:12", "remaining_time": "0:04:56"}
{"current_steps": 245, "total_steps": 278, "loss": 1.4849969863891601, "lr": 7.780530110842566e-07, "epoch": 0.8812949640287769, "percentage": 88.13, "elapsed_time": "0:31:51", "remaining_time": "0:04:17"}
{"current_steps": 250, "total_steps": 278, "loss": 1.4814369201660156, "lr": 5.680751779327742e-07, "epoch": 0.8992805755395683, "percentage": 89.93, "elapsed_time": "0:32:30", "remaining_time": "0:03:38"}
{"current_steps": 255, "total_steps": 278, "loss": 1.4613136291503905, "lr": 3.9024964989539227e-07, "epoch": 0.9172661870503597, "percentage": 91.73, "elapsed_time": "0:33:08", "remaining_time": "0:02:59"}
{"current_steps": 260, "total_steps": 278, "loss": 1.4574945449829102, "lr": 2.4518261295667255e-07, "epoch": 0.935251798561151, "percentage": 93.53, "elapsed_time": "0:33:47", "remaining_time": "0:02:20"}
{"current_steps": 265, "total_steps": 278, "loss": 1.468781089782715, "lr": 1.3336858331787993e-07, "epoch": 0.9532374100719424, "percentage": 95.32, "elapsed_time": "0:34:26", "remaining_time": "0:01:41"}
{"current_steps": 270, "total_steps": 278, "loss": 1.470302200317383, "lr": 5.518872165033329e-08, "epoch": 0.9712230215827338, "percentage": 97.12, "elapsed_time": "0:35:05", "remaining_time": "0:01:02"}
{"current_steps": 275, "total_steps": 278, "loss": 1.4709739685058594, "lr": 1.0909533764194013e-08, "epoch": 0.9892086330935251, "percentage": 98.92, "elapsed_time": "0:35:44", "remaining_time": "0:00:23"}
{"current_steps": 278, "total_steps": 278, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:36:10", "remaining_time": "0:00:00"}

428
trainer_state.json Normal file
View File

@@ -0,0 +1,428 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 278,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.017985611510791366,
"grad_norm": 24.75,
"learning_rate": 8.888888888888888e-06,
"loss": 2.950368309020996,
"step": 5
},
{
"epoch": 0.03597122302158273,
"grad_norm": 8.4375,
"learning_rate": 2e-05,
"loss": 2.4953432083129883,
"step": 10
},
{
"epoch": 0.0539568345323741,
"grad_norm": 3.875,
"learning_rate": 1.9982955597229275e-05,
"loss": 2.1284584045410155,
"step": 15
},
{
"epoch": 0.07194244604316546,
"grad_norm": 2.875,
"learning_rate": 1.9931880491250263e-05,
"loss": 1.9327747344970703,
"step": 20
},
{
"epoch": 0.08992805755395683,
"grad_norm": 2.28125,
"learning_rate": 1.9846948790998532e-05,
"loss": 1.813704490661621,
"step": 25
},
{
"epoch": 0.1079136690647482,
"grad_norm": 2.484375,
"learning_rate": 1.9728450018495506e-05,
"loss": 1.739830207824707,
"step": 30
},
{
"epoch": 0.12589928057553956,
"grad_norm": 2.1875,
"learning_rate": 1.9576788121902457e-05,
"loss": 1.7107593536376953,
"step": 35
},
{
"epoch": 0.14388489208633093,
"grad_norm": 2.109375,
"learning_rate": 1.9392480098509488e-05,
"loss": 1.6636060714721679,
"step": 40
},
{
"epoch": 0.1618705035971223,
"grad_norm": 1.9765625,
"learning_rate": 1.9176154232353513e-05,
"loss": 1.6550146102905274,
"step": 45
},
{
"epoch": 0.17985611510791366,
"grad_norm": 2.15625,
"learning_rate": 1.8928547952473037e-05,
"loss": 1.620616340637207,
"step": 50
},
{
"epoch": 0.19784172661870503,
"grad_norm": 2.109375,
"learning_rate": 1.865050531910062e-05,
"loss": 1.5874693870544434,
"step": 55
},
{
"epoch": 0.2158273381294964,
"grad_norm": 1.828125,
"learning_rate": 1.8342974146362397e-05,
"loss": 1.5906153678894044,
"step": 60
},
{
"epoch": 0.23381294964028776,
"grad_norm": 1.9921875,
"learning_rate": 1.80070027712929e-05,
"loss": 1.5618690490722655,
"step": 65
},
{
"epoch": 0.2517985611510791,
"grad_norm": 2.046875,
"learning_rate": 1.7643736480179353e-05,
"loss": 1.560389232635498,
"step": 70
},
{
"epoch": 0.2697841726618705,
"grad_norm": 2.015625,
"learning_rate": 1.725441360441752e-05,
"loss": 1.5437555313110352,
"step": 75
},
{
"epoch": 0.28776978417266186,
"grad_norm": 2.1875,
"learning_rate": 1.684036129918786e-05,
"loss": 1.523001766204834,
"step": 80
},
{
"epoch": 0.3057553956834532,
"grad_norm": 2.203125,
"learning_rate": 1.6402991019342073e-05,
"loss": 1.5343033790588378,
"step": 85
},
{
"epoch": 0.3237410071942446,
"grad_norm": 2.203125,
"learning_rate": 1.5943793707922086e-05,
"loss": 1.5191097259521484,
"step": 90
},
{
"epoch": 0.34172661870503596,
"grad_norm": 2.0625,
"learning_rate": 1.5464334713713312e-05,
"loss": 1.5029571533203125,
"step": 95
},
{
"epoch": 0.3597122302158273,
"grad_norm": 1.9140625,
"learning_rate": 1.4966248455157622e-05,
"loss": 1.5281996726989746,
"step": 100
},
{
"epoch": 0.3776978417266187,
"grad_norm": 1.9140625,
"learning_rate": 1.445123284881609e-05,
"loss": 1.5251441955566407,
"step": 105
},
{
"epoch": 0.39568345323741005,
"grad_norm": 2.03125,
"learning_rate": 1.392104352137426e-05,
"loss": 1.5085590362548829,
"step": 110
},
{
"epoch": 0.4136690647482014,
"grad_norm": 2.1875,
"learning_rate": 1.3377487824920459e-05,
"loss": 1.500697422027588,
"step": 115
},
{
"epoch": 0.4316546762589928,
"grad_norm": 2.015625,
"learning_rate": 1.2822418675898428e-05,
"loss": 1.4779583930969238,
"step": 120
},
{
"epoch": 0.44964028776978415,
"grad_norm": 2.125,
"learning_rate": 1.2257728238736468e-05,
"loss": 1.4670068740844726,
"step": 125
},
{
"epoch": 0.4676258992805755,
"grad_norm": 1.9609375,
"learning_rate": 1.1685341475684935e-05,
"loss": 1.489361572265625,
"step": 130
},
{
"epoch": 0.4856115107913669,
"grad_norm": 2.015625,
"learning_rate": 1.1107209584849845e-05,
"loss": 1.4737789154052734,
"step": 135
},
{
"epoch": 0.5035971223021583,
"grad_norm": 2.015625,
"learning_rate": 1.0525303348791599e-05,
"loss": 1.4690287590026856,
"step": 140
},
{
"epoch": 0.5215827338129496,
"grad_norm": 2.25,
"learning_rate": 9.94160641636263e-06,
"loss": 1.49021577835083,
"step": 145
},
{
"epoch": 0.539568345323741,
"grad_norm": 2.109375,
"learning_rate": 9.358108540685406e-06,
"loss": 1.4638582229614259,
"step": 150
},
{
"epoch": 0.5575539568345323,
"grad_norm": 2.046875,
"learning_rate": 8.776798796321715e-06,
"loss": 1.4586694717407227,
"step": 155
},
{
"epoch": 0.5755395683453237,
"grad_norm": 1.9921875,
"learning_rate": 8.199658798755048e-06,
"loss": 1.479645347595215,
"step": 160
},
{
"epoch": 0.5935251798561151,
"grad_norm": 1.96875,
"learning_rate": 7.628655949300133e-06,
"loss": 1.455679225921631,
"step": 165
},
{
"epoch": 0.6115107913669064,
"grad_norm": 1.9921875,
"learning_rate": 7.065736728466832e-06,
"loss": 1.4653221130371095,
"step": 170
},
{
"epoch": 0.6294964028776978,
"grad_norm": 2.0,
"learning_rate": 6.512820060640608e-06,
"loss": 1.4618860244750977,
"step": 175
},
{
"epoch": 0.6474820143884892,
"grad_norm": 1.8671875,
"learning_rate": 5.971790772698467e-06,
"loss": 1.449009895324707,
"step": 180
},
{
"epoch": 0.6654676258992805,
"grad_norm": 1.9609375,
"learning_rate": 5.444493168859304e-06,
"loss": 1.449843692779541,
"step": 185
},
{
"epoch": 0.6834532374100719,
"grad_norm": 2.015625,
"learning_rate": 4.932724743671089e-06,
"loss": 1.459362506866455,
"step": 190
},
{
"epoch": 0.7014388489208633,
"grad_norm": 1.96875,
"learning_rate": 4.438230054566678e-06,
"loss": 1.470369243621826,
"step": 195
},
{
"epoch": 0.7194244604316546,
"grad_norm": 1.9140625,
"learning_rate": 3.96269477487588e-06,
"loss": 1.4958831787109375,
"step": 200
},
{
"epoch": 0.737410071942446,
"grad_norm": 1.984375,
"learning_rate": 3.5077399475664474e-06,
"loss": 1.4567132949829102,
"step": 205
},
{
"epoch": 0.7553956834532374,
"grad_norm": 1.953125,
"learning_rate": 3.074916459302211e-06,
"loss": 1.4700736045837401,
"step": 210
},
{
"epoch": 0.7733812949640287,
"grad_norm": 2.21875,
"learning_rate": 2.665699753655684e-06,
"loss": 1.442730712890625,
"step": 215
},
{
"epoch": 0.7913669064748201,
"grad_norm": 1.9609375,
"learning_rate": 2.281484801497186e-06,
"loss": 1.464546012878418,
"step": 220
},
{
"epoch": 0.8093525179856115,
"grad_norm": 2.0,
"learning_rate": 1.923581345705736e-06,
"loss": 1.4540756225585938,
"step": 225
},
{
"epoch": 0.8273381294964028,
"grad_norm": 2.1875,
"learning_rate": 1.5932094364120453e-06,
"loss": 1.4824945449829101,
"step": 230
},
{
"epoch": 0.8453237410071942,
"grad_norm": 1.765625,
"learning_rate": 1.291495271993337e-06,
"loss": 1.4647997856140136,
"step": 235
},
{
"epoch": 0.8633093525179856,
"grad_norm": 1.8046875,
"learning_rate": 1.0194673599976134e-06,
"loss": 1.4619410514831543,
"step": 240
},
{
"epoch": 0.8812949640287769,
"grad_norm": 1.8984375,
"learning_rate": 7.780530110842566e-07,
"loss": 1.4849969863891601,
"step": 245
},
{
"epoch": 0.8992805755395683,
"grad_norm": 1.953125,
"learning_rate": 5.680751779327742e-07,
"loss": 1.4814369201660156,
"step": 250
},
{
"epoch": 0.9172661870503597,
"grad_norm": 2.046875,
"learning_rate": 3.9024964989539227e-07,
"loss": 1.4613136291503905,
"step": 255
},
{
"epoch": 0.935251798561151,
"grad_norm": 2.046875,
"learning_rate": 2.4518261295667255e-07,
"loss": 1.4574945449829102,
"step": 260
},
{
"epoch": 0.9532374100719424,
"grad_norm": 1.96875,
"learning_rate": 1.3336858331787993e-07,
"loss": 1.468781089782715,
"step": 265
},
{
"epoch": 0.9712230215827338,
"grad_norm": 2.34375,
"learning_rate": 5.518872165033329e-08,
"loss": 1.470302200317383,
"step": 270
},
{
"epoch": 0.9892086330935251,
"grad_norm": 1.8671875,
"learning_rate": 1.0909533764194013e-08,
"loss": 1.4709739685058594,
"step": 275
},
{
"epoch": 1.0,
"step": 278,
"total_flos": 1.335043548266926e+17,
"train_loss": 1.5747115251829298,
"train_runtime": 2170.5286,
"train_samples_per_second": 0.512,
"train_steps_per_second": 0.128
}
],
"logging_steps": 5,
"max_steps": 278,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.335043548266926e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4639fb3231fba64da5bd48c2c419deb1f2d9d4feaeeed9e621d3ae5ffc77f7e7
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 36 KiB