lldois/v35_v29_cot_r3_balanced_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/v35_v29_cot_r3_balanced_lr6e7_ep10
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-19 03:31:10 +08:00
commit cb41ce5fb7
17 changed files with 3110 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: v35_v29_cot_r3_balanced_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. -->
# v35_v29_cot_r3_balanced_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_v35_cot_r3_balanced 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: 202607185
- 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": 2.3199594469350605e+17,
"train_loss": 2.076033425085323,
"train_runtime": 3739.4992,
"train_samples_per_second": 0.518,
"train_steps_per_second": 0.13
}

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": "v35_v29_cot_r3_balanced_lr6e7_ep10",
"base": "/home/ll/llm4rec/experiments/outputs/v29_v19_user_world_guard_lr8e7_ep018",
"dataset": "v35_cot_r3_balanced",
"dataset_manifest": {
"name": "v35_cot_r3_balanced",
"path": "/home/ll/llm4rec/experiments/data/v35_cot_r3_balanced.jsonl",
"records": 80000,
"bytes": 310914202,
"sha256": "4207a66e3c1e6fe035067e219a3a45243c46a9167f1b912eca13d62ec1cdf192",
"requested_components": {
"general": 24000,
"r0": 12000,
"r3_think": 18000,
"r3_direct": 14000,
"old_rec": 5000,
"old_user": 3500,
"old_item": 3500
},
"groups": {
"r3": 32000,
"old_user": 3500,
"general": 24000,
"old_rec": 5000,
"r0": 12000,
"old_item": 3500
},
"variants": {
"profile_goods_direct": 3190,
"original_competition": 5884,
"official_general_cot": 11903,
"user_array_json_strict": 607,
"official_general_direct": 12097,
"rec_no_think_direct_final": 2500,
"profile_live_direct": 3236,
"caption_to_sid_direct": 5975,
"sid_to_caption_direct": 3085,
"sid_to_caption_cot": 2940,
"profile_video/ad_direct": 3187,
"profile_video/video_direct": 4387,
"profile_live_cot": 4191,
"profile_goods_cot": 4133,
"profile_video/video_cot": 5547,
"profile_video/ad_cot": 4129,
"user_strict_array": 606,
"user_strict_logic": 511,
"item_short_think": 629,
"item_no_think_direct_final": 577,
"user_logic_json_strict": 462,
"user_extra_no_think_logic": 224
},
"routes": {
"no_think": 42146,
"think": 37854
},
"target_leakage": 0,
"seed": 202607152
},
"learning_rate": "6.0e-7",
"epochs": 1.0,
"stages": null,
"note": "Higher R3 CoT ratio with compact Persona-Expansion-Transition traces and direct-route balance.",
"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/v35_v29_cot_r3_balanced_lr6e7_ep10.yaml"
],
"reproduce": "/home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/python /home/ll/llm4rec/experiments/run_v34_v43.py --single v35_v29_cot_r3_balanced_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 sha256:615f1fab6fbcdcd53029b386e3c06accdbe9156f75d9aecd45810deabe05d9c1
size 1602902832

3
runs/Jul15_00-59-52_ubuntu-System-Product-Name/events.out.tfevents.1784048392.ubuntu-System-Product-Name.1380389.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:029901109eb7a33373ab77dc3d28c6b733fb9c5c72506bd33ea54be4b878cda5
size 16386

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
}

2308
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": 2.3199594469350605e+17,
"train_loss": 2.076033425085323,
"train_runtime": 3739.4992,
"train_samples_per_second": 0.518,
"train_steps_per_second": 0.13
}

49
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,49 @@
{"current_steps": 10, "total_steps": 485, "loss": 2.075181579589844, "lr": 3.6e-07, "epoch": 0.020650490449148167, "percentage": 2.06, "elapsed_time": "0:01:17", "remaining_time": "1:01:21"}
{"current_steps": 20, "total_steps": 485, "loss": 2.085246467590332, "lr": 5.998927766432351e-07, "epoch": 0.041300980898296334, "percentage": 4.12, "elapsed_time": "0:02:34", "remaining_time": "1:00:00"}
{"current_steps": 30, "total_steps": 485, "loss": 2.2069232940673826, "lr": 5.986873939340487e-07, "epoch": 0.061951471347444505, "percentage": 6.19, "elapsed_time": "0:03:52", "remaining_time": "0:58:51"}
{"current_steps": 40, "total_steps": 485, "loss": 2.1064844131469727, "lr": 5.961480008160849e-07, "epoch": 0.08260196179659267, "percentage": 8.25, "elapsed_time": "0:05:06", "remaining_time": "0:56:52"}
{"current_steps": 50, "total_steps": 485, "loss": 2.148875617980957, "lr": 5.922859388354552e-07, "epoch": 0.10325245224574084, "percentage": 10.31, "elapsed_time": "0:06:25", "remaining_time": "0:55:52"}
{"current_steps": 60, "total_steps": 485, "loss": 2.2333826065063476, "lr": 5.871184568984952e-07, "epoch": 0.12390294269488901, "percentage": 12.37, "elapsed_time": "0:07:42", "remaining_time": "0:54:37"}
{"current_steps": 70, "total_steps": 485, "loss": 2.1595861434936525, "lr": 5.806686342339606e-07, "epoch": 0.14455343314403718, "percentage": 14.43, "elapsed_time": "0:08:57", "remaining_time": "0:53:06"}
{"current_steps": 80, "total_steps": 485, "loss": 2.0489675521850588, "lr": 5.729652773155893e-07, "epoch": 0.16520392359318534, "percentage": 16.49, "elapsed_time": "0:10:16", "remaining_time": "0:51:58"}
{"current_steps": 90, "total_steps": 485, "loss": 2.1140844345092775, "lr": 5.640427912053975e-07, "epoch": 0.1858544140423335, "percentage": 18.56, "elapsed_time": "0:11:33", "remaining_time": "0:50:42"}
{"current_steps": 100, "total_steps": 485, "loss": 2.1626249313354493, "lr": 5.539410258923193e-07, "epoch": 0.20650490449148168, "percentage": 20.62, "elapsed_time": "0:12:47", "remaining_time": "0:49:15"}
{"current_steps": 110, "total_steps": 485, "loss": 1.9297166824340821, "lr": 5.427050983124842e-07, "epoch": 0.22715539494062983, "percentage": 22.68, "elapsed_time": "0:14:06", "remaining_time": "0:48:06"}
{"current_steps": 120, "total_steps": 485, "loss": 2.105946350097656, "lr": 5.303851908460263e-07, "epoch": 0.24780588538977802, "percentage": 24.74, "elapsed_time": "0:15:24", "remaining_time": "0:46:51"}
{"current_steps": 130, "total_steps": 485, "loss": 2.3158504486083986, "lr": 5.170363271903941e-07, "epoch": 0.2684563758389262, "percentage": 26.8, "elapsed_time": "0:16:38", "remaining_time": "0:45:27"}
{"current_steps": 140, "total_steps": 485, "loss": 2.025718116760254, "lr": 5.027181266111595e-07, "epoch": 0.28910686628807436, "percentage": 28.87, "elapsed_time": "0:17:56", "remaining_time": "0:44:11"}
{"current_steps": 150, "total_steps": 485, "loss": 2.0087594985961914, "lr": 4.874945376679055e-07, "epoch": 0.3097573567372225, "percentage": 30.93, "elapsed_time": "0:19:13", "remaining_time": "0:42:55"}
{"current_steps": 160, "total_steps": 485, "loss": 1.9722934722900392, "lr": 4.71433552604435e-07, "epoch": 0.3304078471863707, "percentage": 32.99, "elapsed_time": "0:20:29", "remaining_time": "0:41:37"}
{"current_steps": 170, "total_steps": 485, "loss": 2.084832954406738, "lr": 4.5460690367890496e-07, "epoch": 0.35105833763551886, "percentage": 35.05, "elapsed_time": "0:21:47", "remaining_time": "0:40:23"}
{"current_steps": 180, "total_steps": 485, "loss": 1.9973403930664062, "lr": 4.37089742790148e-07, "epoch": 0.371708828084667, "percentage": 37.11, "elapsed_time": "0:23:03", "remaining_time": "0:39:04"}
{"current_steps": 190, "total_steps": 485, "loss": 1.9446184158325195, "lr": 4.1896030583104884e-07, "epoch": 0.39235931853381517, "percentage": 39.18, "elapsed_time": "0:24:19", "remaining_time": "0:37:46"}
{"current_steps": 200, "total_steps": 485, "loss": 2.216297721862793, "lr": 4.0029956326805454e-07, "epoch": 0.41300980898296336, "percentage": 41.24, "elapsed_time": "0:25:37", "remaining_time": "0:36:30"}
{"current_steps": 210, "total_steps": 485, "loss": 1.9691858291625977, "lr": 3.8119085850741565e-07, "epoch": 0.43366029943211154, "percentage": 43.3, "elapsed_time": "0:26:55", "remaining_time": "0:35:15"}
{"current_steps": 220, "total_steps": 485, "loss": 2.18753604888916, "lr": 3.617195356633018e-07, "epoch": 0.45431078988125967, "percentage": 45.36, "elapsed_time": "0:28:12", "remaining_time": "0:33:58"}
{"current_steps": 230, "total_steps": 485, "loss": 2.077012825012207, "lr": 3.419725583902706e-07, "epoch": 0.47496128033040785, "percentage": 47.42, "elapsed_time": "0:29:30", "remaining_time": "0:32:43"}
{"current_steps": 240, "total_steps": 485, "loss": 2.1807201385498045, "lr": 3.2203812148247463e-07, "epoch": 0.49561177077955604, "percentage": 49.48, "elapsed_time": "0:30:49", "remaining_time": "0:31:27"}
{"current_steps": 250, "total_steps": 485, "loss": 2.1047475814819334, "lr": 3.020052569743027e-07, "epoch": 0.5162622612287042, "percentage": 51.55, "elapsed_time": "0:32:08", "remaining_time": "0:30:12"}
{"current_steps": 260, "total_steps": 485, "loss": 1.9689088821411134, "lr": 2.819634365016999e-07, "epoch": 0.5369127516778524, "percentage": 53.61, "elapsed_time": "0:33:25", "remaining_time": "0:28:55"}
{"current_steps": 270, "total_steps": 485, "loss": 2.0879981994628904, "lr": 2.6200217170012295e-07, "epoch": 0.5575632421270005, "percentage": 55.67, "elapsed_time": "0:34:40", "remaining_time": "0:27:36"}
{"current_steps": 280, "total_steps": 485, "loss": 2.080374336242676, "lr": 2.422106144238464e-07, "epoch": 0.5782137325761487, "percentage": 57.73, "elapsed_time": "0:35:58", "remaining_time": "0:26:20"}
{"current_steps": 290, "total_steps": 485, "loss": 2.179820251464844, "lr": 2.2267715857213983e-07, "epoch": 0.5988642230252968, "percentage": 59.79, "elapsed_time": "0:37:13", "remaining_time": "0:25:01"}
{"current_steps": 300, "total_steps": 485, "loss": 1.9253725051879882, "lr": 2.0348904530065538e-07, "epoch": 0.619514713474445, "percentage": 61.86, "elapsed_time": "0:38:29", "remaining_time": "0:23:44"}
{"current_steps": 310, "total_steps": 485, "loss": 1.8352821350097657, "lr": 1.8473197338124887e-07, "epoch": 0.6401652039235932, "percentage": 63.92, "elapsed_time": "0:39:47", "remaining_time": "0:22:27"}
{"current_steps": 320, "total_steps": 485, "loss": 2.013896369934082, "lr": 1.66489716450461e-07, "epoch": 0.6608156943727413, "percentage": 65.98, "elapsed_time": "0:41:03", "remaining_time": "0:21:10"}
{"current_steps": 330, "total_steps": 485, "loss": 2.13570613861084, "lr": 1.4884374885611996e-07, "epoch": 0.6814661848218895, "percentage": 68.04, "elapsed_time": "0:42:19", "remaining_time": "0:19:52"}
{"current_steps": 340, "total_steps": 485, "loss": 2.071014404296875, "lr": 1.3187288177312556e-07, "epoch": 0.7021166752710377, "percentage": 70.1, "elapsed_time": "0:43:37", "remaining_time": "0:18:36"}
{"current_steps": 350, "total_steps": 485, "loss": 2.260077476501465, "lr": 1.1565291121361143e-07, "epoch": 0.7227671657201858, "percentage": 72.16, "elapsed_time": "0:44:52", "remaining_time": "0:17:18"}
{"current_steps": 360, "total_steps": 485, "loss": 2.126547431945801, "lr": 1.0025627950355415e-07, "epoch": 0.743417656169334, "percentage": 74.23, "elapsed_time": "0:46:08", "remaining_time": "0:16:01"}
{"current_steps": 370, "total_steps": 485, "loss": 2.061558151245117, "lr": 8.575175173775983e-08, "epoch": 0.7640681466184822, "percentage": 76.29, "elapsed_time": "0:47:25", "remaining_time": "0:14:44"}
{"current_steps": 380, "total_steps": 485, "loss": 2.0802581787109373, "lr": 7.220410865825828e-08, "epoch": 0.7847186370676303, "percentage": 78.35, "elapsed_time": "0:48:42", "remaining_time": "0:13:27"}
{"current_steps": 390, "total_steps": 485, "loss": 1.9892038345336913, "lr": 5.967385732778304e-08, "epoch": 0.8053691275167785, "percentage": 80.41, "elapsed_time": "0:50:03", "remaining_time": "0:12:11"}
{"current_steps": 400, "total_steps": 485, "loss": 2.121898651123047, "lr": 4.821696089054069e-08, "epoch": 0.8260196179659267, "percentage": 82.47, "elapsed_time": "0:51:21", "remaining_time": "0:10:54"}
{"current_steps": 410, "total_steps": 485, "loss": 1.8785961151123047, "lr": 3.7884588627223946e-08, "epoch": 0.8466701084150748, "percentage": 84.54, "elapsed_time": "0:52:38", "remaining_time": "0:09:37"}
{"current_steps": 420, "total_steps": 485, "loss": 2.034098815917969, "lr": 2.8722887420582297e-08, "epoch": 0.8673205988642231, "percentage": 86.6, "elapsed_time": "0:53:56", "remaining_time": "0:08:20"}
{"current_steps": 430, "total_steps": 485, "loss": 2.088451385498047, "lr": 2.077277565224146e-08, "epoch": 0.8879710893133712, "percentage": 88.66, "elapsed_time": "0:55:14", "remaining_time": "0:07:03"}
{"current_steps": 440, "total_steps": 485, "loss": 2.0510417938232424, "lr": 1.4069760451277756e-08, "epoch": 0.9086215797625193, "percentage": 90.72, "elapsed_time": "0:56:34", "remaining_time": "0:05:47"}
{"current_steps": 450, "total_steps": 485, "loss": 2.012544631958008, "lr": 8.64377911076044e-09, "epoch": 0.9292720702116676, "percentage": 92.78, "elapsed_time": "0:57:53", "remaining_time": "0:04:30"}
{"current_steps": 460, "total_steps": 485, "loss": 2.140595817565918, "lr": 4.519065380533282e-09, "epoch": 0.9499225606608157, "percentage": 94.85, "elapsed_time": "0:59:11", "remaining_time": "0:03:13"}
{"current_steps": 470, "total_steps": 485, "loss": 1.9902917861938476, "lr": 1.7140412334049615e-09, "epoch": 0.9705730511099638, "percentage": 96.91, "elapsed_time": "1:00:29", "remaining_time": "0:01:55"}
{"current_steps": 480, "total_steps": 485, "loss": 2.080463409423828, "lr": 2.4123458814648835e-10, "epoch": 0.9912235415591121, "percentage": 98.97, "elapsed_time": "1:01:47", "remaining_time": "0:00:38"}
{"current_steps": 485, "total_steps": 485, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:02:19", "remaining_time": "0:00:00"}

379
trainer_state.json Normal file
View File

@@ -0,0 +1,379 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 485,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.020650490449148167,
"grad_norm": 4.40625,
"learning_rate": 3.6e-07,
"loss": 2.075181579589844,
"step": 10
},
{
"epoch": 0.041300980898296334,
"grad_norm": 16.0,
"learning_rate": 5.998927766432351e-07,
"loss": 2.085246467590332,
"step": 20
},
{
"epoch": 0.061951471347444505,
"grad_norm": 30.0,
"learning_rate": 5.986873939340487e-07,
"loss": 2.2069232940673826,
"step": 30
},
{
"epoch": 0.08260196179659267,
"grad_norm": 5.53125,
"learning_rate": 5.961480008160849e-07,
"loss": 2.1064844131469727,
"step": 40
},
{
"epoch": 0.10325245224574084,
"grad_norm": 7.53125,
"learning_rate": 5.922859388354552e-07,
"loss": 2.148875617980957,
"step": 50
},
{
"epoch": 0.12390294269488901,
"grad_norm": 22.25,
"learning_rate": 5.871184568984952e-07,
"loss": 2.2333826065063476,
"step": 60
},
{
"epoch": 0.14455343314403718,
"grad_norm": 25.0,
"learning_rate": 5.806686342339606e-07,
"loss": 2.1595861434936525,
"step": 70
},
{
"epoch": 0.16520392359318534,
"grad_norm": 10.8125,
"learning_rate": 5.729652773155893e-07,
"loss": 2.0489675521850588,
"step": 80
},
{
"epoch": 0.1858544140423335,
"grad_norm": 6.375,
"learning_rate": 5.640427912053975e-07,
"loss": 2.1140844345092775,
"step": 90
},
{
"epoch": 0.20650490449148168,
"grad_norm": 14.6875,
"learning_rate": 5.539410258923193e-07,
"loss": 2.1626249313354493,
"step": 100
},
{
"epoch": 0.22715539494062983,
"grad_norm": 6.59375,
"learning_rate": 5.427050983124842e-07,
"loss": 1.9297166824340821,
"step": 110
},
{
"epoch": 0.24780588538977802,
"grad_norm": 23.875,
"learning_rate": 5.303851908460263e-07,
"loss": 2.105946350097656,
"step": 120
},
{
"epoch": 0.2684563758389262,
"grad_norm": 16.375,
"learning_rate": 5.170363271903941e-07,
"loss": 2.3158504486083986,
"step": 130
},
{
"epoch": 0.28910686628807436,
"grad_norm": 9.8125,
"learning_rate": 5.027181266111595e-07,
"loss": 2.025718116760254,
"step": 140
},
{
"epoch": 0.3097573567372225,
"grad_norm": 12.3125,
"learning_rate": 4.874945376679055e-07,
"loss": 2.0087594985961914,
"step": 150
},
{
"epoch": 0.3304078471863707,
"grad_norm": 8.8125,
"learning_rate": 4.71433552604435e-07,
"loss": 1.9722934722900392,
"step": 160
},
{
"epoch": 0.35105833763551886,
"grad_norm": 19.875,
"learning_rate": 4.5460690367890496e-07,
"loss": 2.084832954406738,
"step": 170
},
{
"epoch": 0.371708828084667,
"grad_norm": 16.75,
"learning_rate": 4.37089742790148e-07,
"loss": 1.9973403930664062,
"step": 180
},
{
"epoch": 0.39235931853381517,
"grad_norm": 8.125,
"learning_rate": 4.1896030583104884e-07,
"loss": 1.9446184158325195,
"step": 190
},
{
"epoch": 0.41300980898296336,
"grad_norm": 20.625,
"learning_rate": 4.0029956326805454e-07,
"loss": 2.216297721862793,
"step": 200
},
{
"epoch": 0.43366029943211154,
"grad_norm": 8.0625,
"learning_rate": 3.8119085850741565e-07,
"loss": 1.9691858291625977,
"step": 210
},
{
"epoch": 0.45431078988125967,
"grad_norm": 5.78125,
"learning_rate": 3.617195356633018e-07,
"loss": 2.18753604888916,
"step": 220
},
{
"epoch": 0.47496128033040785,
"grad_norm": 4.96875,
"learning_rate": 3.419725583902706e-07,
"loss": 2.077012825012207,
"step": 230
},
{
"epoch": 0.49561177077955604,
"grad_norm": 12.6875,
"learning_rate": 3.2203812148247463e-07,
"loss": 2.1807201385498045,
"step": 240
},
{
"epoch": 0.5162622612287042,
"grad_norm": 14.25,
"learning_rate": 3.020052569743027e-07,
"loss": 2.1047475814819334,
"step": 250
},
{
"epoch": 0.5369127516778524,
"grad_norm": 10.4375,
"learning_rate": 2.819634365016999e-07,
"loss": 1.9689088821411134,
"step": 260
},
{
"epoch": 0.5575632421270005,
"grad_norm": 5.125,
"learning_rate": 2.6200217170012295e-07,
"loss": 2.0879981994628904,
"step": 270
},
{
"epoch": 0.5782137325761487,
"grad_norm": 11.75,
"learning_rate": 2.422106144238464e-07,
"loss": 2.080374336242676,
"step": 280
},
{
"epoch": 0.5988642230252968,
"grad_norm": 6.4375,
"learning_rate": 2.2267715857213983e-07,
"loss": 2.179820251464844,
"step": 290
},
{
"epoch": 0.619514713474445,
"grad_norm": 8.0,
"learning_rate": 2.0348904530065538e-07,
"loss": 1.9253725051879882,
"step": 300
},
{
"epoch": 0.6401652039235932,
"grad_norm": 6.625,
"learning_rate": 1.8473197338124887e-07,
"loss": 1.8352821350097657,
"step": 310
},
{
"epoch": 0.6608156943727413,
"grad_norm": 6.0625,
"learning_rate": 1.66489716450461e-07,
"loss": 2.013896369934082,
"step": 320
},
{
"epoch": 0.6814661848218895,
"grad_norm": 5.4375,
"learning_rate": 1.4884374885611996e-07,
"loss": 2.13570613861084,
"step": 330
},
{
"epoch": 0.7021166752710377,
"grad_norm": 9.125,
"learning_rate": 1.3187288177312556e-07,
"loss": 2.071014404296875,
"step": 340
},
{
"epoch": 0.7227671657201858,
"grad_norm": 13.375,
"learning_rate": 1.1565291121361143e-07,
"loss": 2.260077476501465,
"step": 350
},
{
"epoch": 0.743417656169334,
"grad_norm": 13.5,
"learning_rate": 1.0025627950355415e-07,
"loss": 2.126547431945801,
"step": 360
},
{
"epoch": 0.7640681466184822,
"grad_norm": 12.4375,
"learning_rate": 8.575175173775983e-08,
"loss": 2.061558151245117,
"step": 370
},
{
"epoch": 0.7847186370676303,
"grad_norm": 9.625,
"learning_rate": 7.220410865825828e-08,
"loss": 2.0802581787109373,
"step": 380
},
{
"epoch": 0.8053691275167785,
"grad_norm": 10.6875,
"learning_rate": 5.967385732778304e-08,
"loss": 1.9892038345336913,
"step": 390
},
{
"epoch": 0.8260196179659267,
"grad_norm": 8.75,
"learning_rate": 4.821696089054069e-08,
"loss": 2.121898651123047,
"step": 400
},
{
"epoch": 0.8466701084150748,
"grad_norm": 4.53125,
"learning_rate": 3.7884588627223946e-08,
"loss": 1.8785961151123047,
"step": 410
},
{
"epoch": 0.8673205988642231,
"grad_norm": 6.28125,
"learning_rate": 2.8722887420582297e-08,
"loss": 2.034098815917969,
"step": 420
},
{
"epoch": 0.8879710893133712,
"grad_norm": 17.0,
"learning_rate": 2.077277565224146e-08,
"loss": 2.088451385498047,
"step": 430
},
{
"epoch": 0.9086215797625193,
"grad_norm": 17.5,
"learning_rate": 1.4069760451277756e-08,
"loss": 2.0510417938232424,
"step": 440
},
{
"epoch": 0.9292720702116676,
"grad_norm": 18.25,
"learning_rate": 8.64377911076044e-09,
"loss": 2.012544631958008,
"step": 450
},
{
"epoch": 0.9499225606608157,
"grad_norm": 10.0,
"learning_rate": 4.519065380533282e-09,
"loss": 2.140595817565918,
"step": 460
},
{
"epoch": 0.9705730511099638,
"grad_norm": 11.625,
"learning_rate": 1.7140412334049615e-09,
"loss": 1.9902917861938476,
"step": 470
},
{
"epoch": 0.9912235415591121,
"grad_norm": 10.625,
"learning_rate": 2.4123458814648835e-10,
"loss": 2.080463409423828,
"step": 480
},
{
"epoch": 1.0,
"step": 485,
"total_flos": 2.3199594469350605e+17,
"train_loss": 2.076033425085323,
"train_runtime": 3739.4992,
"train_samples_per_second": 0.518,
"train_steps_per_second": 0.13
}
],
"logging_steps": 10,
"max_steps": 485,
"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": 2.3199594469350605e+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 sha256:07bb47d0a04d9f74bba78b9db2609738fc781ea4ec39a46463322547139e5ab8
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 52 KiB