lldois/v40_scratch_source_paper_mix_lr3e6_ep15
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/v40_scratch_source_paper_mix_lr3e6_ep15
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-19 04:38:10 +08:00
commit bf796b3d1c
17 changed files with 3313 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: v40_scratch_source_paper_mix_lr3e6_ep15
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. -->
# v40_scratch_source_paper_mix_lr3e6_ep15
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 exp_v34_paper_mix 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: 3e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 202607190
- 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: 1.5
### 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": 1.5002627430373097,
"total_flos": 3.4104097625680896e+17,
"train_loss": 1.8137206637224896,
"train_runtime": 5627.9871,
"train_samples_per_second": 0.507,
"train_steps_per_second": 0.127
}

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
}

72
experiment_recipe.json Normal file
View File

@@ -0,0 +1,72 @@
{
"created_at": "2026-07-15 00:59:15",
"name": "v40_scratch_source_paper_mix_lr3e6_ep15",
"base": "OpenOneRec/OneReason-0.8B-pretrain-competition",
"dataset": "v34_paper_mix",
"dataset_manifest": {
"name": "v34_paper_mix",
"path": "/home/ll/llm4rec/experiments/data/v34_paper_mix.jsonl",
"records": 80000,
"bytes": 287964112,
"sha256": "114013600aa0113ef0ef441bc1ecbd16a8c01f1a77cf76b9d0de16040656da8f",
"requested_components": {
"general": 30400,
"r0": 19000,
"r3_think": 6000,
"r3_direct": 12000,
"old_rec": 5000,
"old_user": 3800,
"old_item": 3800
},
"groups": {
"general": 30400,
"old_rec": 5000,
"r3": 18000,
"r0": 19000,
"old_item": 3800,
"old_user": 3800
},
"variants": {
"official_general_cot": 15121,
"rec_no_think_direct_final": 2520,
"profile_goods_direct": 2647,
"caption_to_sid_direct": 9502,
"profile_live_cot": 1414,
"official_general_direct": 15279,
"profile_video/video_cot": 1876,
"sid_to_caption_cot": 4746,
"item_short_think": 699,
"profile_video/video_direct": 3676,
"original_competition": 6105,
"profile_goods_cot": 1350,
"profile_live_direct": 2834,
"profile_video/ad_direct": 2843,
"sid_to_caption_direct": 4752,
"user_strict_array": 666,
"item_no_think_direct_final": 670,
"profile_video/ad_cot": 1360,
"user_strict_logic": 542,
"user_extra_no_think_logic": 228,
"user_logic_json_strict": 529,
"user_array_json_strict": 641
},
"routes": {
"think": 31005,
"no_think": 48995
},
"target_leakage": 0,
"seed": 202607151
},
"learning_rate": "3.0e-6",
"epochs": 1.5,
"stages": null,
"note": "High-risk restart from the official pretrained checkpoint using the new source-data mixture.",
"cot_policy": "Preserve meaningful CoT for /think and pure final outputs for /no_think.",
"checkpoint_policy": "save_strategy=no; only the final model is retained.",
"script": "/home/ll/llm4rec/experiments/run_v34_v43.py",
"script_sha256": "fbf01773c61579cf6159f64442fc0c8902714c84ed23b488bc9a6236a154f402",
"configs": [
"/home/ll/llm4rec/experiments/configs/v40_scratch_source_paper_mix_lr3e6_ep15.yaml"
],
"reproduce": "/home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/python /home/ll/llm4rec/experiments/run_v34_v43.py --single v40_scratch_source_paper_mix_lr3e6_ep15 --gpu <gpu>"
}

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 sha256:6da4f5f4b16cd9f46a637880ef25393d9769158f797d2b0f55dc4d8554194190
size 1602902832

3
runs/Jul15_04-02-30_ubuntu-System-Product-Name/events.out.tfevents.1784059350.ubuntu-System-Product-Name.1383638.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7b46e595aadaf2b89814add655300115fa062ccef5751b5eee1deb1396d1fc76
size 21249

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
}

2327
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": 1.5002627430373097,
"total_flos": 3.4104097625680896e+17,
"train_loss": 1.8137206637224896,
"train_runtime": 5627.9871,
"train_samples_per_second": 0.507,
"train_steps_per_second": 0.127
}

72
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,72 @@
{"current_steps": 10, "total_steps": 714, "loss": 2.139740753173828, "lr": 1.2272727272727274e-06, "epoch": 0.021019442984760904, "percentage": 1.4, "elapsed_time": "0:01:21", "remaining_time": "1:35:40"}
{"current_steps": 20, "total_steps": 714, "loss": 2.2081624984741213, "lr": 2.590909090909091e-06, "epoch": 0.04203888596952181, "percentage": 2.8, "elapsed_time": "0:02:44", "remaining_time": "1:35:03"}
{"current_steps": 30, "total_steps": 714, "loss": 2.0339645385742187, "lr": 2.999242629561838e-06, "epoch": 0.0630583289542827, "percentage": 4.2, "elapsed_time": "0:04:03", "remaining_time": "1:32:40"}
{"current_steps": 40, "total_steps": 714, "loss": 2.0348079681396483, "lr": 2.995534901109399e-06, "epoch": 0.08407777193904362, "percentage": 5.6, "elapsed_time": "0:05:20", "remaining_time": "1:30:03"}
{"current_steps": 50, "total_steps": 714, "loss": 1.950754165649414, "lr": 2.9887453367135033e-06, "epoch": 0.10509721492380451, "percentage": 7.0, "elapsed_time": "0:06:42", "remaining_time": "1:29:05"}
{"current_steps": 60, "total_steps": 714, "loss": 1.9394699096679688, "lr": 2.9788879275712665e-06, "epoch": 0.1261166579085654, "percentage": 8.4, "elapsed_time": "0:08:01", "remaining_time": "1:27:27"}
{"current_steps": 70, "total_steps": 714, "loss": 1.880813980102539, "lr": 2.9659829867611603e-06, "epoch": 0.14713610089332632, "percentage": 9.8, "elapsed_time": "0:09:21", "remaining_time": "1:26:08"}
{"current_steps": 80, "total_steps": 714, "loss": 1.8970605850219726, "lr": 2.9500571073840264e-06, "epoch": 0.16815554387808723, "percentage": 11.2, "elapsed_time": "0:10:40", "remaining_time": "1:24:35"}
{"current_steps": 90, "total_steps": 714, "loss": 1.8591070175170898, "lr": 2.931143107762901e-06, "epoch": 0.18917498686284814, "percentage": 12.61, "elapsed_time": "0:12:01", "remaining_time": "1:23:23"}
{"current_steps": 100, "total_steps": 714, "loss": 1.892710304260254, "lr": 2.909279963814576e-06, "epoch": 0.21019442984760903, "percentage": 14.01, "elapsed_time": "0:13:18", "remaining_time": "1:21:44"}
{"current_steps": 110, "total_steps": 714, "loss": 1.8118453979492188, "lr": 2.8845127287322656e-06, "epoch": 0.23121387283236994, "percentage": 15.41, "elapsed_time": "0:14:35", "remaining_time": "1:20:04"}
{"current_steps": 120, "total_steps": 714, "loss": 1.8849889755249023, "lr": 2.8568924401448738e-06, "epoch": 0.2522333158171308, "percentage": 16.81, "elapsed_time": "0:15:54", "remaining_time": "1:18:45"}
{"current_steps": 130, "total_steps": 714, "loss": 1.8813108444213866, "lr": 2.826476014944193e-06, "epoch": 0.27325275880189176, "percentage": 18.21, "elapsed_time": "0:17:12", "remaining_time": "1:17:19"}
{"current_steps": 140, "total_steps": 714, "loss": 1.9071147918701172, "lr": 2.7933261319967516e-06, "epoch": 0.29427220178665264, "percentage": 19.61, "elapsed_time": "0:18:29", "remaining_time": "1:15:48"}
{"current_steps": 150, "total_steps": 714, "loss": 1.8963701248168945, "lr": 2.7575111029820103e-06, "epoch": 0.3152916447714136, "percentage": 21.01, "elapsed_time": "0:19:48", "remaining_time": "1:14:27"}
{"current_steps": 160, "total_steps": 714, "loss": 1.9282533645629882, "lr": 2.7191047316230743e-06, "epoch": 0.33631108775617446, "percentage": 22.41, "elapsed_time": "0:21:07", "remaining_time": "1:13:09"}
{"current_steps": 170, "total_steps": 714, "loss": 1.7661924362182617, "lr": 2.6781861615999896e-06, "epoch": 0.35733053074093535, "percentage": 23.81, "elapsed_time": "0:22:27", "remaining_time": "1:11:52"}
{"current_steps": 180, "total_steps": 714, "loss": 1.784163475036621, "lr": 2.6348397134590424e-06, "epoch": 0.3783499737256963, "percentage": 25.21, "elapsed_time": "0:23:45", "remaining_time": "1:10:27"}
{"current_steps": 190, "total_steps": 714, "loss": 1.8109502792358398, "lr": 2.5891547108541323e-06, "epoch": 0.39936941671045717, "percentage": 26.61, "elapsed_time": "0:25:05", "remaining_time": "1:09:10"}
{"current_steps": 200, "total_steps": 714, "loss": 1.821950912475586, "lr": 2.5412252964782867e-06, "epoch": 0.42038885969521805, "percentage": 28.01, "elapsed_time": "0:26:22", "remaining_time": "1:07:48"}
{"current_steps": 210, "total_steps": 714, "loss": 1.9059152603149414, "lr": 2.4911502380646164e-06, "epoch": 0.441408302679979, "percentage": 29.41, "elapsed_time": "0:27:41", "remaining_time": "1:06:26"}
{"current_steps": 220, "total_steps": 714, "loss": 1.8420991897583008, "lr": 2.4390327248564994e-06, "epoch": 0.4624277456647399, "percentage": 30.81, "elapsed_time": "0:28:58", "remaining_time": "1:05:03"}
{"current_steps": 230, "total_steps": 714, "loss": 1.890372085571289, "lr": 2.3849801549663886e-06, "epoch": 0.4834471886495008, "percentage": 32.21, "elapsed_time": "0:30:17", "remaining_time": "1:03:44"}
{"current_steps": 240, "total_steps": 714, "loss": 1.8288061141967773, "lr": 2.3291039140614475e-06, "epoch": 0.5044666316342616, "percentage": 33.61, "elapsed_time": "0:31:36", "remaining_time": "1:02:25"}
{"current_steps": 250, "total_steps": 714, "loss": 1.8653709411621093, "lr": 2.2715191458320545e-06, "epoch": 0.5254860746190226, "percentage": 35.01, "elapsed_time": "0:32:57", "remaining_time": "1:01:09"}
{"current_steps": 260, "total_steps": 714, "loss": 1.771567153930664, "lr": 2.212344514716194e-06, "epoch": 0.5465055176037835, "percentage": 36.41, "elapsed_time": "0:34:15", "remaining_time": "0:59:49"}
{"current_steps": 270, "total_steps": 714, "loss": 1.7724361419677734, "lr": 2.151701961368664e-06, "epoch": 0.5675249605885444, "percentage": 37.82, "elapsed_time": "0:35:37", "remaining_time": "0:58:34"}
{"current_steps": 280, "total_steps": 714, "loss": 1.7283151626586915, "lr": 2.0897164513790135e-06, "epoch": 0.5885444035733053, "percentage": 39.22, "elapsed_time": "0:36:57", "remaining_time": "0:57:17"}
{"current_steps": 290, "total_steps": 714, "loss": 1.7711864471435548, "lr": 2.026515717756026e-06, "epoch": 0.6095638465580662, "percentage": 40.62, "elapsed_time": "0:38:17", "remaining_time": "0:55:58"}
{"current_steps": 300, "total_steps": 714, "loss": 1.7970991134643555, "lr": 1.9622299977094044e-06, "epoch": 0.6305832895428272, "percentage": 42.02, "elapsed_time": "0:39:33", "remaining_time": "0:54:35"}
{"current_steps": 310, "total_steps": 714, "loss": 1.8020233154296874, "lr": 1.8969917642710664e-06, "epoch": 0.651602732527588, "percentage": 43.42, "elapsed_time": "0:40:50", "remaining_time": "0:53:13"}
{"current_steps": 320, "total_steps": 714, "loss": 1.8001415252685546, "lr": 1.830935453309108e-06, "epoch": 0.6726221755123489, "percentage": 44.82, "elapsed_time": "0:42:09", "remaining_time": "0:51:53"}
{"current_steps": 330, "total_steps": 714, "loss": 1.75347843170166, "lr": 1.764197186496962e-06, "epoch": 0.6936416184971098, "percentage": 46.22, "elapsed_time": "0:43:28", "remaining_time": "0:50:34"}
{"current_steps": 340, "total_steps": 714, "loss": 1.809716033935547, "lr": 1.6969144908086306e-06, "epoch": 0.7146610614818707, "percentage": 47.62, "elapsed_time": "0:44:49", "remaining_time": "0:49:18"}
{"current_steps": 350, "total_steps": 714, "loss": 1.7866138458251952, "lr": 1.6292260151180326e-06, "epoch": 0.7356805044666316, "percentage": 49.02, "elapsed_time": "0:46:09", "remaining_time": "0:48:00"}
{"current_steps": 360, "total_steps": 714, "loss": 1.8378917694091796, "lr": 1.5612712444864579e-06, "epoch": 0.7566999474513926, "percentage": 50.42, "elapsed_time": "0:47:28", "remaining_time": "0:46:40"}
{"current_steps": 370, "total_steps": 714, "loss": 1.7029869079589843, "lr": 1.4931902127268951e-06, "epoch": 0.7777193904361535, "percentage": 51.82, "elapsed_time": "0:48:45", "remaining_time": "0:45:19"}
{"current_steps": 380, "total_steps": 714, "loss": 1.7460771560668946, "lr": 1.4251232138375584e-06, "epoch": 0.7987388334209143, "percentage": 53.22, "elapsed_time": "0:50:02", "remaining_time": "0:43:59"}
{"current_steps": 390, "total_steps": 714, "loss": 1.7742759704589843, "lr": 1.3572105128992455e-06, "epoch": 0.8197582764056752, "percentage": 54.62, "elapsed_time": "0:51:20", "remaining_time": "0:42:38"}
{"current_steps": 400, "total_steps": 714, "loss": 1.8007017135620118, "lr": 1.2895920570322904e-06, "epoch": 0.8407777193904361, "percentage": 56.02, "elapsed_time": "0:52:39", "remaining_time": "0:41:20"}
{"current_steps": 410, "total_steps": 714, "loss": 1.7528308868408202, "lr": 1.2224071870087317e-06, "epoch": 0.8617971623751971, "percentage": 57.42, "elapsed_time": "0:53:58", "remaining_time": "0:40:01"}
{"current_steps": 420, "total_steps": 714, "loss": 1.8043436050415038, "lr": 1.1557943501139813e-06, "epoch": 0.882816605359958, "percentage": 58.82, "elapsed_time": "0:55:18", "remaining_time": "0:38:43"}
{"current_steps": 430, "total_steps": 714, "loss": 1.7981443405151367, "lr": 1.0898908148496853e-06, "epoch": 0.9038360483447189, "percentage": 60.22, "elapsed_time": "0:56:37", "remaining_time": "0:37:23"}
{"current_steps": 440, "total_steps": 714, "loss": 1.7500328063964843, "lr": 1.0248323880657068e-06, "epoch": 0.9248554913294798, "percentage": 61.62, "elapsed_time": "0:57:54", "remaining_time": "0:36:03"}
{"current_steps": 450, "total_steps": 714, "loss": 1.7884363174438476, "lr": 9.607531351041108e-07, "epoch": 0.9458749343142406, "percentage": 63.03, "elapsed_time": "0:59:13", "remaining_time": "0:34:44"}
{"current_steps": 460, "total_steps": 714, "loss": 1.714197540283203, "lr": 8.977851035318654e-07, "epoch": 0.9668943772990016, "percentage": 64.43, "elapsed_time": "1:00:31", "remaining_time": "0:33:24"}
{"current_steps": 470, "total_steps": 714, "loss": 1.7554092407226562, "lr": 8.360580510315521e-07, "epoch": 0.9879138202837625, "percentage": 65.83, "elapsed_time": "1:01:51", "remaining_time": "0:32:06"}
{"current_steps": 480, "total_steps": 714, "loss": 1.7379329681396485, "lr": 7.756991780108238e-07, "epoch": 1.0084077771939044, "percentage": 67.23, "elapsed_time": "1:03:08", "remaining_time": "0:30:47"}
{"current_steps": 490, "total_steps": 714, "loss": 1.692732810974121, "lr": 7.168328654816127e-07, "epoch": 1.0294272201786652, "percentage": 68.63, "elapsed_time": "1:04:30", "remaining_time": "0:29:29"}
{"current_steps": 500, "total_steps": 714, "loss": 1.8081771850585937, "lr": 6.595804187492498e-07, "epoch": 1.0504466631634262, "percentage": 70.03, "elapsed_time": "1:05:48", "remaining_time": "0:28:09"}
{"current_steps": 510, "total_steps": 714, "loss": 1.7980724334716798, "lr": 6.0405981743966e-07, "epoch": 1.0714661061481872, "percentage": 71.43, "elapsed_time": "1:07:06", "remaining_time": "0:26:50"}
{"current_steps": 520, "total_steps": 714, "loss": 1.764889907836914, "lr": 5.503854723797599e-07, "epoch": 1.092485549132948, "percentage": 72.83, "elapsed_time": "1:08:24", "remaining_time": "0:25:31"}
{"current_steps": 530, "total_steps": 714, "loss": 1.7189857482910156, "lr": 4.986679898320476e-07, "epoch": 1.113504992117709, "percentage": 74.23, "elapsed_time": "1:09:42", "remaining_time": "0:24:12"}
{"current_steps": 540, "total_steps": 714, "loss": 1.7537565231323242, "lr": 4.490139435692261e-07, "epoch": 1.1345244351024697, "percentage": 75.63, "elapsed_time": "1:11:01", "remaining_time": "0:22:53"}
{"current_steps": 550, "total_steps": 714, "loss": 1.6921497344970704, "lr": 4.0152565525854467e-07, "epoch": 1.1555438780872307, "percentage": 77.03, "elapsed_time": "1:12:20", "remaining_time": "0:21:34"}
{"current_steps": 560, "total_steps": 714, "loss": 1.7711572647094727, "lr": 3.5630098360841646e-07, "epoch": 1.1765633210719917, "percentage": 78.43, "elapsed_time": "1:13:38", "remaining_time": "0:20:15"}
{"current_steps": 570, "total_steps": 714, "loss": 1.6838041305541993, "lr": 3.134331227118171e-07, "epoch": 1.1975827640567525, "percentage": 79.83, "elapsed_time": "1:14:55", "remaining_time": "0:18:55"}
{"current_steps": 580, "total_steps": 714, "loss": 1.73205509185791, "lr": 2.7301041000201746e-07, "epoch": 1.2186022070415135, "percentage": 81.23, "elapsed_time": "1:16:15", "remaining_time": "0:17:37"}
{"current_steps": 590, "total_steps": 714, "loss": 1.7526542663574218, "lr": 2.351161442163905e-07, "epoch": 1.2396216500262742, "percentage": 82.63, "elapsed_time": "1:17:33", "remaining_time": "0:16:18"}
{"current_steps": 600, "total_steps": 714, "loss": 1.7869752883911132, "lr": 1.998284137434206e-07, "epoch": 1.2606410930110352, "percentage": 84.03, "elapsed_time": "1:18:50", "remaining_time": "0:14:58"}
{"current_steps": 610, "total_steps": 714, "loss": 1.828580093383789, "lr": 1.6721993570662926e-07, "epoch": 1.2816605359957962, "percentage": 85.43, "elapsed_time": "1:20:08", "remaining_time": "0:13:39"}
{"current_steps": 620, "total_steps": 714, "loss": 1.7601003646850586, "lr": 1.3735790611702274e-07, "epoch": 1.302679978980557, "percentage": 86.83, "elapsed_time": "1:21:25", "remaining_time": "0:12:20"}
{"current_steps": 630, "total_steps": 714, "loss": 1.7960094451904296, "lr": 1.1030386140284865e-07, "epoch": 1.323699421965318, "percentage": 88.24, "elapsed_time": "1:22:44", "remaining_time": "0:11:01"}
{"current_steps": 640, "total_steps": 714, "loss": 1.7016435623168946, "lr": 8.611355160200623e-08, "epoch": 1.3447188649500788, "percentage": 89.64, "elapsed_time": "1:24:04", "remaining_time": "0:09:43"}
{"current_steps": 650, "total_steps": 714, "loss": 1.7239088058471679, "lr": 6.483682547842001e-08, "epoch": 1.3657383079348397, "percentage": 91.04, "elapsed_time": "1:25:24", "remaining_time": "0:08:24"}
{"current_steps": 660, "total_steps": 714, "loss": 1.7699031829833984, "lr": 4.651752779912233e-08, "epoch": 1.3867577509196005, "percentage": 92.44, "elapsed_time": "1:26:43", "remaining_time": "0:07:05"}
{"current_steps": 670, "total_steps": 714, "loss": 1.8059171676635741, "lr": 3.1193408983715475e-08, "epoch": 1.4077771939043615, "percentage": 93.84, "elapsed_time": "1:28:03", "remaining_time": "0:05:46"}
{"current_steps": 680, "total_steps": 714, "loss": 1.7002668380737305, "lr": 1.8896047312406683e-08, "epoch": 1.4287966368891225, "percentage": 95.24, "elapsed_time": "1:29:20", "remaining_time": "0:04:28"}
{"current_steps": 690, "total_steps": 714, "loss": 1.7966609954833985, "lr": 9.650783852917178e-09, "epoch": 1.4498160798738833, "percentage": 96.64, "elapsed_time": "1:30:40", "remaining_time": "0:03:09"}
{"current_steps": 700, "total_steps": 714, "loss": 1.7154333114624023, "lr": 3.4766702403609684e-09, "epoch": 1.4708355228586443, "percentage": 98.04, "elapsed_time": "1:32:01", "remaining_time": "0:01:50"}
{"current_steps": 710, "total_steps": 714, "loss": 1.7977441787719726, "lr": 3.8642941770372644e-10, "epoch": 1.4918549658434053, "percentage": 99.44, "elapsed_time": "1:33:17", "remaining_time": "0:00:31"}
{"current_steps": 714, "total_steps": 714, "epoch": 1.5002627430373097, "percentage": 100.0, "elapsed_time": "1:33:47", "remaining_time": "0:00:00"}

540
trainer_state.json Normal file
View File

@@ -0,0 +1,540 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.5002627430373097,
"eval_steps": 500,
"global_step": 714,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.021019442984760904,
"grad_norm": 7.8125,
"learning_rate": 1.2272727272727274e-06,
"loss": 2.139740753173828,
"step": 10
},
{
"epoch": 0.04203888596952181,
"grad_norm": 5.96875,
"learning_rate": 2.590909090909091e-06,
"loss": 2.2081624984741213,
"step": 20
},
{
"epoch": 0.0630583289542827,
"grad_norm": 14.125,
"learning_rate": 2.999242629561838e-06,
"loss": 2.0339645385742187,
"step": 30
},
{
"epoch": 0.08407777193904362,
"grad_norm": 5.90625,
"learning_rate": 2.995534901109399e-06,
"loss": 2.0348079681396483,
"step": 40
},
{
"epoch": 0.10509721492380451,
"grad_norm": 4.8125,
"learning_rate": 2.9887453367135033e-06,
"loss": 1.950754165649414,
"step": 50
},
{
"epoch": 0.1261166579085654,
"grad_norm": 6.09375,
"learning_rate": 2.9788879275712665e-06,
"loss": 1.9394699096679688,
"step": 60
},
{
"epoch": 0.14713610089332632,
"grad_norm": 2.921875,
"learning_rate": 2.9659829867611603e-06,
"loss": 1.880813980102539,
"step": 70
},
{
"epoch": 0.16815554387808723,
"grad_norm": 3.96875,
"learning_rate": 2.9500571073840264e-06,
"loss": 1.8970605850219726,
"step": 80
},
{
"epoch": 0.18917498686284814,
"grad_norm": 4.1875,
"learning_rate": 2.931143107762901e-06,
"loss": 1.8591070175170898,
"step": 90
},
{
"epoch": 0.21019442984760903,
"grad_norm": 2.359375,
"learning_rate": 2.909279963814576e-06,
"loss": 1.892710304260254,
"step": 100
},
{
"epoch": 0.23121387283236994,
"grad_norm": 3.125,
"learning_rate": 2.8845127287322656e-06,
"loss": 1.8118453979492188,
"step": 110
},
{
"epoch": 0.2522333158171308,
"grad_norm": 2.71875,
"learning_rate": 2.8568924401448738e-06,
"loss": 1.8849889755249023,
"step": 120
},
{
"epoch": 0.27325275880189176,
"grad_norm": 1.8203125,
"learning_rate": 2.826476014944193e-06,
"loss": 1.8813108444213866,
"step": 130
},
{
"epoch": 0.29427220178665264,
"grad_norm": 2.265625,
"learning_rate": 2.7933261319967516e-06,
"loss": 1.9071147918701172,
"step": 140
},
{
"epoch": 0.3152916447714136,
"grad_norm": 2.828125,
"learning_rate": 2.7575111029820103e-06,
"loss": 1.8963701248168945,
"step": 150
},
{
"epoch": 0.33631108775617446,
"grad_norm": 2.953125,
"learning_rate": 2.7191047316230743e-06,
"loss": 1.9282533645629882,
"step": 160
},
{
"epoch": 0.35733053074093535,
"grad_norm": 1.65625,
"learning_rate": 2.6781861615999896e-06,
"loss": 1.7661924362182617,
"step": 170
},
{
"epoch": 0.3783499737256963,
"grad_norm": 2.078125,
"learning_rate": 2.6348397134590424e-06,
"loss": 1.784163475036621,
"step": 180
},
{
"epoch": 0.39936941671045717,
"grad_norm": 1.765625,
"learning_rate": 2.5891547108541323e-06,
"loss": 1.8109502792358398,
"step": 190
},
{
"epoch": 0.42038885969521805,
"grad_norm": 3.0625,
"learning_rate": 2.5412252964782867e-06,
"loss": 1.821950912475586,
"step": 200
},
{
"epoch": 0.441408302679979,
"grad_norm": 2.453125,
"learning_rate": 2.4911502380646164e-06,
"loss": 1.9059152603149414,
"step": 210
},
{
"epoch": 0.4624277456647399,
"grad_norm": 2.875,
"learning_rate": 2.4390327248564994e-06,
"loss": 1.8420991897583008,
"step": 220
},
{
"epoch": 0.4834471886495008,
"grad_norm": 2.5,
"learning_rate": 2.3849801549663886e-06,
"loss": 1.890372085571289,
"step": 230
},
{
"epoch": 0.5044666316342616,
"grad_norm": 2.484375,
"learning_rate": 2.3291039140614475e-06,
"loss": 1.8288061141967773,
"step": 240
},
{
"epoch": 0.5254860746190226,
"grad_norm": 3.109375,
"learning_rate": 2.2715191458320545e-06,
"loss": 1.8653709411621093,
"step": 250
},
{
"epoch": 0.5465055176037835,
"grad_norm": 2.109375,
"learning_rate": 2.212344514716194e-06,
"loss": 1.771567153930664,
"step": 260
},
{
"epoch": 0.5675249605885444,
"grad_norm": 1.953125,
"learning_rate": 2.151701961368664e-06,
"loss": 1.7724361419677734,
"step": 270
},
{
"epoch": 0.5885444035733053,
"grad_norm": 4.6875,
"learning_rate": 2.0897164513790135e-06,
"loss": 1.7283151626586915,
"step": 280
},
{
"epoch": 0.6095638465580662,
"grad_norm": 2.8125,
"learning_rate": 2.026515717756026e-06,
"loss": 1.7711864471435548,
"step": 290
},
{
"epoch": 0.6305832895428272,
"grad_norm": 5.0,
"learning_rate": 1.9622299977094044e-06,
"loss": 1.7970991134643555,
"step": 300
},
{
"epoch": 0.651602732527588,
"grad_norm": 1.890625,
"learning_rate": 1.8969917642710664e-06,
"loss": 1.8020233154296874,
"step": 310
},
{
"epoch": 0.6726221755123489,
"grad_norm": 1.65625,
"learning_rate": 1.830935453309108e-06,
"loss": 1.8001415252685546,
"step": 320
},
{
"epoch": 0.6936416184971098,
"grad_norm": 2.3125,
"learning_rate": 1.764197186496962e-06,
"loss": 1.75347843170166,
"step": 330
},
{
"epoch": 0.7146610614818707,
"grad_norm": 6.4375,
"learning_rate": 1.6969144908086306e-06,
"loss": 1.809716033935547,
"step": 340
},
{
"epoch": 0.7356805044666316,
"grad_norm": 1.9921875,
"learning_rate": 1.6292260151180326e-06,
"loss": 1.7866138458251952,
"step": 350
},
{
"epoch": 0.7566999474513926,
"grad_norm": 3.6875,
"learning_rate": 1.5612712444864579e-06,
"loss": 1.8378917694091796,
"step": 360
},
{
"epoch": 0.7777193904361535,
"grad_norm": 2.078125,
"learning_rate": 1.4931902127268951e-06,
"loss": 1.7029869079589843,
"step": 370
},
{
"epoch": 0.7987388334209143,
"grad_norm": 1.9453125,
"learning_rate": 1.4251232138375584e-06,
"loss": 1.7460771560668946,
"step": 380
},
{
"epoch": 0.8197582764056752,
"grad_norm": 2.359375,
"learning_rate": 1.3572105128992455e-06,
"loss": 1.7742759704589843,
"step": 390
},
{
"epoch": 0.8407777193904361,
"grad_norm": 3.78125,
"learning_rate": 1.2895920570322904e-06,
"loss": 1.8007017135620118,
"step": 400
},
{
"epoch": 0.8617971623751971,
"grad_norm": 2.484375,
"learning_rate": 1.2224071870087317e-06,
"loss": 1.7528308868408202,
"step": 410
},
{
"epoch": 0.882816605359958,
"grad_norm": 2.375,
"learning_rate": 1.1557943501139813e-06,
"loss": 1.8043436050415038,
"step": 420
},
{
"epoch": 0.9038360483447189,
"grad_norm": 1.625,
"learning_rate": 1.0898908148496853e-06,
"loss": 1.7981443405151367,
"step": 430
},
{
"epoch": 0.9248554913294798,
"grad_norm": 3.390625,
"learning_rate": 1.0248323880657068e-06,
"loss": 1.7500328063964843,
"step": 440
},
{
"epoch": 0.9458749343142406,
"grad_norm": 3.0,
"learning_rate": 9.607531351041108e-07,
"loss": 1.7884363174438476,
"step": 450
},
{
"epoch": 0.9668943772990016,
"grad_norm": 2.859375,
"learning_rate": 8.977851035318654e-07,
"loss": 1.714197540283203,
"step": 460
},
{
"epoch": 0.9879138202837625,
"grad_norm": 2.125,
"learning_rate": 8.360580510315521e-07,
"loss": 1.7554092407226562,
"step": 470
},
{
"epoch": 1.0084077771939044,
"grad_norm": 2.421875,
"learning_rate": 7.756991780108238e-07,
"loss": 1.7379329681396485,
"step": 480
},
{
"epoch": 1.0294272201786652,
"grad_norm": 2.453125,
"learning_rate": 7.168328654816127e-07,
"loss": 1.692732810974121,
"step": 490
},
{
"epoch": 1.0504466631634262,
"grad_norm": 2.40625,
"learning_rate": 6.595804187492498e-07,
"loss": 1.8081771850585937,
"step": 500
},
{
"epoch": 1.0714661061481872,
"grad_norm": 2.71875,
"learning_rate": 6.0405981743966e-07,
"loss": 1.7980724334716798,
"step": 510
},
{
"epoch": 1.092485549132948,
"grad_norm": 4.34375,
"learning_rate": 5.503854723797599e-07,
"loss": 1.764889907836914,
"step": 520
},
{
"epoch": 1.113504992117709,
"grad_norm": 4.53125,
"learning_rate": 4.986679898320476e-07,
"loss": 1.7189857482910156,
"step": 530
},
{
"epoch": 1.1345244351024697,
"grad_norm": 3.296875,
"learning_rate": 4.490139435692261e-07,
"loss": 1.7537565231323242,
"step": 540
},
{
"epoch": 1.1555438780872307,
"grad_norm": 3.234375,
"learning_rate": 4.0152565525854467e-07,
"loss": 1.6921497344970704,
"step": 550
},
{
"epoch": 1.1765633210719917,
"grad_norm": 3.15625,
"learning_rate": 3.5630098360841646e-07,
"loss": 1.7711572647094727,
"step": 560
},
{
"epoch": 1.1975827640567525,
"grad_norm": 1.8671875,
"learning_rate": 3.134331227118171e-07,
"loss": 1.6838041305541993,
"step": 570
},
{
"epoch": 1.2186022070415135,
"grad_norm": 2.09375,
"learning_rate": 2.7301041000201746e-07,
"loss": 1.73205509185791,
"step": 580
},
{
"epoch": 1.2396216500262742,
"grad_norm": 2.234375,
"learning_rate": 2.351161442163905e-07,
"loss": 1.7526542663574218,
"step": 590
},
{
"epoch": 1.2606410930110352,
"grad_norm": 1.5859375,
"learning_rate": 1.998284137434206e-07,
"loss": 1.7869752883911132,
"step": 600
},
{
"epoch": 1.2816605359957962,
"grad_norm": 2.375,
"learning_rate": 1.6721993570662926e-07,
"loss": 1.828580093383789,
"step": 610
},
{
"epoch": 1.302679978980557,
"grad_norm": 2.609375,
"learning_rate": 1.3735790611702274e-07,
"loss": 1.7601003646850586,
"step": 620
},
{
"epoch": 1.323699421965318,
"grad_norm": 3.59375,
"learning_rate": 1.1030386140284865e-07,
"loss": 1.7960094451904296,
"step": 630
},
{
"epoch": 1.3447188649500788,
"grad_norm": 3.046875,
"learning_rate": 8.611355160200623e-08,
"loss": 1.7016435623168946,
"step": 640
},
{
"epoch": 1.3657383079348397,
"grad_norm": 1.7890625,
"learning_rate": 6.483682547842001e-08,
"loss": 1.7239088058471679,
"step": 650
},
{
"epoch": 1.3867577509196005,
"grad_norm": 1.6796875,
"learning_rate": 4.651752779912233e-08,
"loss": 1.7699031829833984,
"step": 660
},
{
"epoch": 1.4077771939043615,
"grad_norm": 1.9140625,
"learning_rate": 3.1193408983715475e-08,
"loss": 1.8059171676635741,
"step": 670
},
{
"epoch": 1.4287966368891225,
"grad_norm": 3.25,
"learning_rate": 1.8896047312406683e-08,
"loss": 1.7002668380737305,
"step": 680
},
{
"epoch": 1.4498160798738833,
"grad_norm": 2.015625,
"learning_rate": 9.650783852917178e-09,
"loss": 1.7966609954833985,
"step": 690
},
{
"epoch": 1.4708355228586443,
"grad_norm": 2.328125,
"learning_rate": 3.4766702403609684e-09,
"loss": 1.7154333114624023,
"step": 700
},
{
"epoch": 1.4918549658434053,
"grad_norm": 1.6875,
"learning_rate": 3.8642941770372644e-10,
"loss": 1.7977441787719726,
"step": 710
},
{
"epoch": 1.5002627430373097,
"step": 714,
"total_flos": 3.4104097625680896e+17,
"train_loss": 1.8137206637224896,
"train_runtime": 5627.9871,
"train_samples_per_second": 0.507,
"train_steps_per_second": 0.127
}
],
"logging_steps": 10,
"max_steps": 714,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 3.4104097625680896e+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:ffc96fcd8bb0a0ba8ddf3fcb143cb11d0d0b51d3dd5a1f139ff393aec6bc8bbd
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 46 KiB