lldois/v37_v29_r0_perception_lr6e7_ep10
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/v37_v29_r0_perception_lr6e7_ep10
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-19 04:14:10 +08:00
commit 382dfc9021
17 changed files with 2995 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: lldois/v29_v19_user_world_guard_lr8e7_ep018
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: v37_v29_r0_perception_lr6e7_ep10
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. -->
# v37_v29_r0_perception_lr6e7_ep10
This model is a fine-tuned version of [lldois/v29_v19_user_world_guard_lr8e7_ep018](https://huggingface.co/lldois/v29_v19_user_world_guard_lr8e7_ep018) on the exp_v37_r0_perception 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: 6e-07
- train_batch_size: 1
- eval_batch_size: 8
- seed: 202607187
- 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: 1.0
### 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": 2.1268932852271104e+17,
"train_loss": 1.9281885245235708,
"train_runtime": 3538.1073,
"train_samples_per_second": 0.505,
"train_steps_per_second": 0.126
}

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": "v37_v29_r0_perception_lr6e7_ep10",
"base": "/home/ll/llm4rec/experiments/outputs/v29_v19_user_world_guard_lr8e7_ep018",
"dataset": "v37_r0_perception",
"dataset_manifest": {
"name": "v37_r0_perception",
"path": "/home/ll/llm4rec/experiments/data/v37_r0_perception.jsonl",
"records": 80000,
"bytes": 267058830,
"sha256": "71579dd6021ab3045524e80275a793d3adcb1b552884209837e77c149d880266",
"requested_components": {
"general": 24000,
"r0": 28000,
"r3_think": 8000,
"r3_direct": 8000,
"old_rec": 4000,
"old_user": 4000,
"old_item": 4000
},
"groups": {
"r3": 16000,
"general": 24000,
"r0": 28000,
"old_item": 4000,
"old_rec": 4000,
"old_user": 4000
},
"variants": {
"profile_video/ad_direct": 1832,
"official_general_direct": 12089,
"sid_to_caption_direct": 6995,
"official_general_cot": 11911,
"sid_to_caption_cot": 6897,
"original_competition": 5843,
"caption_to_sid_direct": 14108,
"profile_live_cot": 1864,
"profile_video/video_direct": 2451,
"rec_no_think_direct_final": 2009,
"user_strict_logic": 556,
"profile_goods_direct": 1859,
"profile_video/ad_cot": 1818,
"user_logic_json_strict": 573,
"profile_video/video_cot": 2471,
"item_no_think_direct_final": 721,
"item_short_think": 712,
"user_strict_array": 660,
"profile_goods_cot": 1847,
"profile_live_direct": 1858,
"user_array_json_strict": 653,
"user_extra_no_think_logic": 273
},
"routes": {
"no_think": 48386,
"think": 31614
},
"target_leakage": 0,
"seed": 202607154
},
"learning_rate": "6.0e-7",
"epochs": 1.0,
"stages": null,
"note": "R0-heavy bidirectional caption/SID grounding to improve item perception and downstream recommendation semantics.",
"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/v37_v29_r0_perception_lr6e7_ep10.yaml"
],
"reproduce": "/home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/python /home/ll/llm4rec/experiments/run_v34_v43.py --single v37_v29_r0_perception_lr6e7_ep10 --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 sha256:5d57eacf720283361a9370f87b775077118b51c3ee0c454087508855abbcd62b
size 1602902832

3
runs/Jul15_02-03-01_ubuntu-System-Product-Name/events.out.tfevents.1784052181.ubuntu-System-Product-Name.1381877.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1aa8f0e8404d4245df9acfb651b6274466f519fcd0c6daf76b177b00d3fc83b5
size 15538

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": true,
"local_files_only": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

2225
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": 2.1268932852271104e+17,
"train_loss": 1.9281885245235708,
"train_runtime": 3538.1073,
"train_samples_per_second": 0.505,
"train_steps_per_second": 0.126
}

45
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,45 @@
{"current_steps": 10, "total_steps": 447, "loss": 1.9765892028808594, "lr": 3.8571428571428574e-07, "epoch": 0.022396416573348264, "percentage": 2.24, "elapsed_time": "0:01:15", "remaining_time": "0:54:38"}
{"current_steps": 20, "total_steps": 447, "loss": 1.9137596130371093, "lr": 5.998026179790181e-07, "epoch": 0.04479283314669653, "percentage": 4.47, "elapsed_time": "0:02:32", "remaining_time": "0:54:22"}
{"current_steps": 30, "total_steps": 447, "loss": 2.0828577041625977, "lr": 5.982251198558757e-07, "epoch": 0.0671892497200448, "percentage": 6.71, "elapsed_time": "0:03:52", "remaining_time": "0:53:56"}
{"current_steps": 40, "total_steps": 447, "loss": 1.7728485107421874, "lr": 5.950784240718929e-07, "epoch": 0.08958566629339305, "percentage": 8.95, "elapsed_time": "0:05:09", "remaining_time": "0:52:25"}
{"current_steps": 50, "total_steps": 447, "loss": 1.9481042861938476, "lr": 5.903790878763917e-07, "epoch": 0.11198208286674133, "percentage": 11.19, "elapsed_time": "0:06:29", "remaining_time": "0:51:31"}
{"current_steps": 60, "total_steps": 447, "loss": 1.72081298828125, "lr": 5.841518381849623e-07, "epoch": 0.1343784994400896, "percentage": 13.42, "elapsed_time": "0:07:53", "remaining_time": "0:50:54"}
{"current_steps": 70, "total_steps": 447, "loss": 2.0641489028930664, "lr": 5.764294414716493e-07, "epoch": 0.15677491601343785, "percentage": 15.66, "elapsed_time": "0:09:09", "remaining_time": "0:49:20"}
{"current_steps": 80, "total_steps": 447, "loss": 1.887424850463867, "lr": 5.672525313586791e-07, "epoch": 0.1791713325867861, "percentage": 17.9, "elapsed_time": "0:10:29", "remaining_time": "0:48:05"}
{"current_steps": 90, "total_steps": 447, "loss": 1.74453125, "lr": 5.566693948109122e-07, "epoch": 0.20156774916013437, "percentage": 20.13, "elapsed_time": "0:11:52", "remaining_time": "0:47:06"}
{"current_steps": 100, "total_steps": 447, "loss": 2.011259078979492, "lr": 5.447357180600218e-07, "epoch": 0.22396416573348266, "percentage": 22.37, "elapsed_time": "0:13:10", "remaining_time": "0:45:44"}
{"current_steps": 110, "total_steps": 447, "loss": 1.8667875289916993, "lr": 5.315142935952922e-07, "epoch": 0.24636058230683092, "percentage": 24.61, "elapsed_time": "0:14:29", "remaining_time": "0:44:24"}
{"current_steps": 120, "total_steps": 447, "loss": 1.884227180480957, "lr": 5.170746897627867e-07, "epoch": 0.2687569988801792, "percentage": 26.85, "elapsed_time": "0:15:50", "remaining_time": "0:43:09"}
{"current_steps": 130, "total_steps": 447, "loss": 1.7954404830932618, "lr": 5.014928847113897e-07, "epoch": 0.2911534154535274, "percentage": 29.08, "elapsed_time": "0:17:12", "remaining_time": "0:41:56"}
{"current_steps": 140, "total_steps": 447, "loss": 1.8177595138549805, "lr": 4.848508666118165e-07, "epoch": 0.3135498320268757, "percentage": 31.32, "elapsed_time": "0:18:34", "remaining_time": "0:40:43"}
{"current_steps": 150, "total_steps": 447, "loss": 2.0977893829345704, "lr": 4.6723620225215703e-07, "epoch": 0.335946248600224, "percentage": 33.56, "elapsed_time": "0:19:50", "remaining_time": "0:39:17"}
{"current_steps": 160, "total_steps": 447, "loss": 1.7599393844604492, "lr": 4.4874157627991176e-07, "epoch": 0.3583426651735722, "percentage": 35.79, "elapsed_time": "0:21:12", "remaining_time": "0:38:02"}
{"current_steps": 170, "total_steps": 447, "loss": 2.047610855102539, "lr": 4.294643035149318e-07, "epoch": 0.3807390817469205, "percentage": 38.03, "elapsed_time": "0:22:33", "remaining_time": "0:36:44"}
{"current_steps": 180, "total_steps": 447, "loss": 1.9894037246704102, "lr": 4.0950581689936744e-07, "epoch": 0.40313549832026874, "percentage": 40.27, "elapsed_time": "0:23:54", "remaining_time": "0:35:27"}
{"current_steps": 190, "total_steps": 447, "loss": 1.8606115341186524, "lr": 3.8897113377892806e-07, "epoch": 0.425531914893617, "percentage": 42.51, "elapsed_time": "0:25:12", "remaining_time": "0:34:05"}
{"current_steps": 200, "total_steps": 447, "loss": 1.9338333129882812, "lr": 3.679683033237648e-07, "epoch": 0.4479283314669653, "percentage": 44.74, "elapsed_time": "0:26:32", "remaining_time": "0:32:46"}
{"current_steps": 210, "total_steps": 447, "loss": 2.0058767318725588, "lr": 3.4660783799653415e-07, "epoch": 0.47032474804031354, "percentage": 46.98, "elapsed_time": "0:27:49", "remaining_time": "0:31:23"}
{"current_steps": 220, "total_steps": 447, "loss": 2.109703254699707, "lr": 3.250021320591351e-07, "epoch": 0.49272116461366183, "percentage": 49.22, "elapsed_time": "0:29:08", "remaining_time": "0:30:03"}
{"current_steps": 230, "total_steps": 447, "loss": 1.9790294647216797, "lr": 3.0326487017781626e-07, "epoch": 0.5151175811870101, "percentage": 51.45, "elapsed_time": "0:30:30", "remaining_time": "0:28:46"}
{"current_steps": 240, "total_steps": 447, "loss": 1.7579475402832032, "lr": 2.815104292384474e-07, "epoch": 0.5375139977603584, "percentage": 53.69, "elapsed_time": "0:31:50", "remaining_time": "0:27:28"}
{"current_steps": 250, "total_steps": 447, "loss": 2.0079017639160157, "lr": 2.5985327651947727e-07, "epoch": 0.5599104143337066, "percentage": 55.93, "elapsed_time": "0:33:06", "remaining_time": "0:26:05"}
{"current_steps": 260, "total_steps": 447, "loss": 1.9991819381713867, "lr": 2.3840736738926488e-07, "epoch": 0.5823068309070548, "percentage": 58.17, "elapsed_time": "0:34:23", "remaining_time": "0:24:43"}
{"current_steps": 270, "total_steps": 447, "loss": 2.0415130615234376, "lr": 2.172855456969734e-07, "epoch": 0.6047032474804032, "percentage": 60.4, "elapsed_time": "0:35:42", "remaining_time": "0:23:24"}
{"current_steps": 280, "total_steps": 447, "loss": 1.8622777938842774, "lr": 1.9659895001204434e-07, "epoch": 0.6270996640537514, "percentage": 62.64, "elapsed_time": "0:37:00", "remaining_time": "0:22:04"}
{"current_steps": 290, "total_steps": 447, "loss": 2.0226877212524412, "lr": 1.7645642883649244e-07, "epoch": 0.6494960806270996, "percentage": 64.88, "elapsed_time": "0:38:18", "remaining_time": "0:20:44"}
{"current_steps": 300, "total_steps": 447, "loss": 1.9547592163085938, "lr": 1.5696396786705375e-07, "epoch": 0.671892497200448, "percentage": 67.11, "elapsed_time": "0:39:38", "remaining_time": "0:19:25"}
{"current_steps": 310, "total_steps": 447, "loss": 1.98193302154541, "lr": 1.3822413232081009e-07, "epoch": 0.6942889137737962, "percentage": 69.35, "elapsed_time": "0:40:57", "remaining_time": "0:18:06"}
{"current_steps": 320, "total_steps": 447, "loss": 1.8750802993774414, "lr": 1.2033552725865636e-07, "epoch": 0.7166853303471444, "percentage": 71.59, "elapsed_time": "0:42:19", "remaining_time": "0:16:48"}
{"current_steps": 330, "total_steps": 447, "loss": 1.8019701004028321, "lr": 1.0339227874627297e-07, "epoch": 0.7390817469204927, "percentage": 73.83, "elapsed_time": "0:43:38", "remaining_time": "0:15:28"}
{"current_steps": 340, "total_steps": 447, "loss": 1.6816850662231446, "lr": 8.748353858262847e-08, "epoch": 0.761478163493841, "percentage": 76.06, "elapsed_time": "0:44:59", "remaining_time": "0:14:09"}
{"current_steps": 350, "total_steps": 447, "loss": 1.991793441772461, "lr": 7.269301520202152e-08, "epoch": 0.7838745800671892, "percentage": 78.3, "elapsed_time": "0:46:18", "remaining_time": "0:12:49"}
{"current_steps": 360, "total_steps": 447, "loss": 1.8806726455688476, "lr": 5.909853321796119e-08, "epoch": 0.8062709966405375, "percentage": 80.54, "elapsed_time": "0:47:33", "remaining_time": "0:11:29"}
{"current_steps": 370, "total_steps": 447, "loss": 2.013884925842285, "lr": 4.677162392646981e-08, "epoch": 0.8286674132138858, "percentage": 82.77, "elapsed_time": "0:48:54", "remaining_time": "0:10:10"}
{"current_steps": 380, "total_steps": 447, "loss": 2.0343597412109373, "lr": 3.577714892349537e-08, "epoch": 0.851063829787234, "percentage": 85.01, "elapsed_time": "0:50:09", "remaining_time": "0:08:50"}
{"current_steps": 390, "total_steps": 447, "loss": 1.941878318786621, "lr": 2.6172958816877822e-08, "epoch": 0.8734602463605823, "percentage": 87.25, "elapsed_time": "0:51:28", "remaining_time": "0:07:31"}
{"current_steps": 400, "total_steps": 447, "loss": 1.8717647552490235, "lr": 1.800958882865644e-08, "epoch": 0.8958566629339306, "percentage": 89.49, "elapsed_time": "0:52:48", "remaining_time": "0:06:12"}
{"current_steps": 410, "total_steps": 447, "loss": 1.965050506591797, "lr": 1.1329992889392948e-08, "epoch": 0.9182530795072789, "percentage": 91.72, "elapsed_time": "0:54:08", "remaining_time": "0:04:53"}
{"current_steps": 420, "total_steps": 447, "loss": 1.9910579681396485, "lr": 6.169317623651893e-09, "epoch": 0.9406494960806271, "percentage": 93.96, "elapsed_time": "0:55:29", "remaining_time": "0:03:34"}
{"current_steps": 430, "total_steps": 447, "loss": 1.9617082595825195, "lr": 2.5547174158769502e-09, "epoch": 0.9630459126539753, "percentage": 96.2, "elapsed_time": "0:56:50", "remaining_time": "0:02:14"}
{"current_steps": 440, "total_steps": 447, "loss": 1.8637035369873047, "lr": 5.052115297494275e-10, "epoch": 0.9854423292273237, "percentage": 98.43, "elapsed_time": "0:58:08", "remaining_time": "0:00:55"}
{"current_steps": 447, "total_steps": 447, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:58:58", "remaining_time": "0:00:00"}

351
trainer_state.json Normal file
View File

@@ -0,0 +1,351 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 447,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.022396416573348264,
"grad_norm": 6.21875,
"learning_rate": 3.8571428571428574e-07,
"loss": 1.9765892028808594,
"step": 10
},
{
"epoch": 0.04479283314669653,
"grad_norm": 7.59375,
"learning_rate": 5.998026179790181e-07,
"loss": 1.9137596130371093,
"step": 20
},
{
"epoch": 0.0671892497200448,
"grad_norm": 15.8125,
"learning_rate": 5.982251198558757e-07,
"loss": 2.0828577041625977,
"step": 30
},
{
"epoch": 0.08958566629339305,
"grad_norm": 24.125,
"learning_rate": 5.950784240718929e-07,
"loss": 1.7728485107421874,
"step": 40
},
{
"epoch": 0.11198208286674133,
"grad_norm": 14.3125,
"learning_rate": 5.903790878763917e-07,
"loss": 1.9481042861938476,
"step": 50
},
{
"epoch": 0.1343784994400896,
"grad_norm": 11.9375,
"learning_rate": 5.841518381849623e-07,
"loss": 1.72081298828125,
"step": 60
},
{
"epoch": 0.15677491601343785,
"grad_norm": 6.3125,
"learning_rate": 5.764294414716493e-07,
"loss": 2.0641489028930664,
"step": 70
},
{
"epoch": 0.1791713325867861,
"grad_norm": 6.71875,
"learning_rate": 5.672525313586791e-07,
"loss": 1.887424850463867,
"step": 80
},
{
"epoch": 0.20156774916013437,
"grad_norm": 9.0625,
"learning_rate": 5.566693948109122e-07,
"loss": 1.74453125,
"step": 90
},
{
"epoch": 0.22396416573348266,
"grad_norm": 11.9375,
"learning_rate": 5.447357180600218e-07,
"loss": 2.011259078979492,
"step": 100
},
{
"epoch": 0.24636058230683092,
"grad_norm": 6.96875,
"learning_rate": 5.315142935952922e-07,
"loss": 1.8667875289916993,
"step": 110
},
{
"epoch": 0.2687569988801792,
"grad_norm": 4.90625,
"learning_rate": 5.170746897627867e-07,
"loss": 1.884227180480957,
"step": 120
},
{
"epoch": 0.2911534154535274,
"grad_norm": 8.625,
"learning_rate": 5.014928847113897e-07,
"loss": 1.7954404830932618,
"step": 130
},
{
"epoch": 0.3135498320268757,
"grad_norm": 20.875,
"learning_rate": 4.848508666118165e-07,
"loss": 1.8177595138549805,
"step": 140
},
{
"epoch": 0.335946248600224,
"grad_norm": 6.21875,
"learning_rate": 4.6723620225215703e-07,
"loss": 2.0977893829345704,
"step": 150
},
{
"epoch": 0.3583426651735722,
"grad_norm": 7.59375,
"learning_rate": 4.4874157627991176e-07,
"loss": 1.7599393844604492,
"step": 160
},
{
"epoch": 0.3807390817469205,
"grad_norm": 13.6875,
"learning_rate": 4.294643035149318e-07,
"loss": 2.047610855102539,
"step": 170
},
{
"epoch": 0.40313549832026874,
"grad_norm": 4.40625,
"learning_rate": 4.0950581689936744e-07,
"loss": 1.9894037246704102,
"step": 180
},
{
"epoch": 0.425531914893617,
"grad_norm": 6.09375,
"learning_rate": 3.8897113377892806e-07,
"loss": 1.8606115341186524,
"step": 190
},
{
"epoch": 0.4479283314669653,
"grad_norm": 4.0625,
"learning_rate": 3.679683033237648e-07,
"loss": 1.9338333129882812,
"step": 200
},
{
"epoch": 0.47032474804031354,
"grad_norm": 24.125,
"learning_rate": 3.4660783799653415e-07,
"loss": 2.0058767318725588,
"step": 210
},
{
"epoch": 0.49272116461366183,
"grad_norm": 14.75,
"learning_rate": 3.250021320591351e-07,
"loss": 2.109703254699707,
"step": 220
},
{
"epoch": 0.5151175811870101,
"grad_norm": 11.4375,
"learning_rate": 3.0326487017781626e-07,
"loss": 1.9790294647216797,
"step": 230
},
{
"epoch": 0.5375139977603584,
"grad_norm": 6.90625,
"learning_rate": 2.815104292384474e-07,
"loss": 1.7579475402832032,
"step": 240
},
{
"epoch": 0.5599104143337066,
"grad_norm": 6.0625,
"learning_rate": 2.5985327651947727e-07,
"loss": 2.0079017639160157,
"step": 250
},
{
"epoch": 0.5823068309070548,
"grad_norm": 8.3125,
"learning_rate": 2.3840736738926488e-07,
"loss": 1.9991819381713867,
"step": 260
},
{
"epoch": 0.6047032474804032,
"grad_norm": 4.40625,
"learning_rate": 2.172855456969734e-07,
"loss": 2.0415130615234376,
"step": 270
},
{
"epoch": 0.6270996640537514,
"grad_norm": 8.3125,
"learning_rate": 1.9659895001204434e-07,
"loss": 1.8622777938842774,
"step": 280
},
{
"epoch": 0.6494960806270996,
"grad_norm": 5.8125,
"learning_rate": 1.7645642883649244e-07,
"loss": 2.0226877212524412,
"step": 290
},
{
"epoch": 0.671892497200448,
"grad_norm": 4.21875,
"learning_rate": 1.5696396786705375e-07,
"loss": 1.9547592163085938,
"step": 300
},
{
"epoch": 0.6942889137737962,
"grad_norm": 13.1875,
"learning_rate": 1.3822413232081009e-07,
"loss": 1.98193302154541,
"step": 310
},
{
"epoch": 0.7166853303471444,
"grad_norm": 13.75,
"learning_rate": 1.2033552725865636e-07,
"loss": 1.8750802993774414,
"step": 320
},
{
"epoch": 0.7390817469204927,
"grad_norm": 13.0,
"learning_rate": 1.0339227874627297e-07,
"loss": 1.8019701004028321,
"step": 330
},
{
"epoch": 0.761478163493841,
"grad_norm": 17.375,
"learning_rate": 8.748353858262847e-08,
"loss": 1.6816850662231446,
"step": 340
},
{
"epoch": 0.7838745800671892,
"grad_norm": 13.9375,
"learning_rate": 7.269301520202152e-08,
"loss": 1.991793441772461,
"step": 350
},
{
"epoch": 0.8062709966405375,
"grad_norm": 4.5,
"learning_rate": 5.909853321796119e-08,
"loss": 1.8806726455688476,
"step": 360
},
{
"epoch": 0.8286674132138858,
"grad_norm": 9.5,
"learning_rate": 4.677162392646981e-08,
"loss": 2.013884925842285,
"step": 370
},
{
"epoch": 0.851063829787234,
"grad_norm": 8.6875,
"learning_rate": 3.577714892349537e-08,
"loss": 2.0343597412109373,
"step": 380
},
{
"epoch": 0.8734602463605823,
"grad_norm": 4.4375,
"learning_rate": 2.6172958816877822e-08,
"loss": 1.941878318786621,
"step": 390
},
{
"epoch": 0.8958566629339306,
"grad_norm": 8.6875,
"learning_rate": 1.800958882865644e-08,
"loss": 1.8717647552490235,
"step": 400
},
{
"epoch": 0.9182530795072789,
"grad_norm": 7.25,
"learning_rate": 1.1329992889392948e-08,
"loss": 1.965050506591797,
"step": 410
},
{
"epoch": 0.9406494960806271,
"grad_norm": 7.15625,
"learning_rate": 6.169317623651893e-09,
"loss": 1.9910579681396485,
"step": 420
},
{
"epoch": 0.9630459126539753,
"grad_norm": 5.375,
"learning_rate": 2.5547174158769502e-09,
"loss": 1.9617082595825195,
"step": 430
},
{
"epoch": 0.9854423292273237,
"grad_norm": 7.40625,
"learning_rate": 5.052115297494275e-10,
"loss": 1.8637035369873047,
"step": 440
},
{
"epoch": 1.0,
"step": 447,
"total_flos": 2.1268932852271104e+17,
"train_loss": 1.9281885245235708,
"train_runtime": 3538.1073,
"train_samples_per_second": 0.505,
"train_steps_per_second": 0.126
}
],
"logging_steps": 10,
"max_steps": 447,
"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": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.1268932852271104e+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:d4d5c293f826f3a5d7bbc0ebfd662b511b6795846b9f17c6d72336631bfce5ff
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 56 KiB