lldois/v43_v29_paper_mix_low_lr25e7_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/v43_v29_paper_mix_low_lr25e7_ep15
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-19 02:01:10 +08:00
commit 12bf328a3f
17 changed files with 3310 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: v43_v29_paper_mix_low_lr25e7_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. -->
# v43_v29_paper_mix_low_lr25e7_ep15
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_v43_paper_mix_low 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: 2.5e-07
- train_batch_size: 1
- eval_batch_size: 8
- seed: 202607193
- 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": 3.414600284463329e+17,
"train_loss": 1.907181319736299,
"train_runtime": 5553.447,
"train_samples_per_second": 0.514,
"train_steps_per_second": 0.129
}

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": "v43_v29_paper_mix_low_lr25e7_ep15",
"base": "/home/ll/llm4rec/experiments/outputs/v29_v19_user_world_guard_lr8e7_ep018",
"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": "2.5e-7",
"epochs": 1.5,
"stages": null,
"note": "Controlled long, low-LR exposure on exactly the same data as v34.",
"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/v43_v29_paper_mix_low_lr25e7_ep15.yaml"
],
"reproduce": "/home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/python /home/ll/llm4rec/experiments/run_v34_v43.py --single v43_v29_paper_mix_low_lr25e7_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 sha256:5315105b7f0339eef45a7ef8bf071004513786a2bcdee4b2a8e5d0747ddb8666
size 1602902832

3
runs/Jul15_06-33-43_ubuntu-System-Product-Name/events.out.tfevents.1784068423.ubuntu-System-Product-Name.1387087.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:befb23d331977f468131ec2acfcdfbe6f353e0187df25ae12402f0b585319271
size 21239

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
}

2324
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": 3.414600284463329e+17,
"train_loss": 1.907181319736299,
"train_runtime": 5553.447,
"train_samples_per_second": 0.514,
"train_steps_per_second": 0.129
}

72
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,72 @@
{"current_steps": 10, "total_steps": 714, "loss": 1.8086944580078126, "lr": 1.0227272727272728e-07, "epoch": 0.021019442984760904, "percentage": 1.4, "elapsed_time": "0:01:18", "remaining_time": "1:32:11"}
{"current_steps": 20, "total_steps": 714, "loss": 1.9563072204589844, "lr": 2.159090909090909e-07, "epoch": 0.04203888596952181, "percentage": 2.8, "elapsed_time": "0:02:38", "remaining_time": "1:31:32"}
{"current_steps": 30, "total_steps": 714, "loss": 1.9191463470458985, "lr": 2.4993688579681983e-07, "epoch": 0.0630583289542827, "percentage": 4.2, "elapsed_time": "0:03:54", "remaining_time": "1:29:12"}
{"current_steps": 40, "total_steps": 714, "loss": 1.8105619430541993, "lr": 2.496279084257832e-07, "epoch": 0.08407777193904362, "percentage": 5.6, "elapsed_time": "0:05:12", "remaining_time": "1:27:45"}
{"current_steps": 50, "total_steps": 714, "loss": 1.9305204391479491, "lr": 2.490621113927919e-07, "epoch": 0.10509721492380451, "percentage": 7.0, "elapsed_time": "0:06:30", "remaining_time": "1:26:22"}
{"current_steps": 60, "total_steps": 714, "loss": 1.9595895767211915, "lr": 2.4824066063093887e-07, "epoch": 0.1261166579085654, "percentage": 8.4, "elapsed_time": "0:07:45", "remaining_time": "1:24:30"}
{"current_steps": 70, "total_steps": 714, "loss": 1.9885068893432618, "lr": 2.4716524889676334e-07, "epoch": 0.14713610089332632, "percentage": 9.8, "elapsed_time": "0:09:05", "remaining_time": "1:23:42"}
{"current_steps": 80, "total_steps": 714, "loss": 1.9129520416259767, "lr": 2.458380922820022e-07, "epoch": 0.16815554387808723, "percentage": 11.2, "elapsed_time": "0:10:22", "remaining_time": "1:22:11"}
{"current_steps": 90, "total_steps": 714, "loss": 1.9894475936889648, "lr": 2.442619256469084e-07, "epoch": 0.18917498686284814, "percentage": 12.61, "elapsed_time": "0:11:38", "remaining_time": "1:20:41"}
{"current_steps": 100, "total_steps": 714, "loss": 1.8159450531005858, "lr": 2.42439996984548e-07, "epoch": 0.21019442984760903, "percentage": 14.01, "elapsed_time": "0:12:59", "remaining_time": "1:19:43"}
{"current_steps": 110, "total_steps": 714, "loss": 1.9744218826293944, "lr": 2.403760607276888e-07, "epoch": 0.23121387283236994, "percentage": 15.41, "elapsed_time": "0:14:14", "remaining_time": "1:18:14"}
{"current_steps": 120, "total_steps": 714, "loss": 1.8607925415039062, "lr": 2.3807437001207282e-07, "epoch": 0.2522333158171308, "percentage": 16.81, "elapsed_time": "0:15:31", "remaining_time": "1:16:49"}
{"current_steps": 130, "total_steps": 714, "loss": 1.9678337097167968, "lr": 2.3553966791201608e-07, "epoch": 0.27325275880189176, "percentage": 18.21, "elapsed_time": "0:16:48", "remaining_time": "1:15:30"}
{"current_steps": 140, "total_steps": 714, "loss": 1.905088233947754, "lr": 2.3277717766639592e-07, "epoch": 0.29427220178665264, "percentage": 19.61, "elapsed_time": "0:18:06", "remaining_time": "1:14:14"}
{"current_steps": 150, "total_steps": 714, "loss": 1.8011585235595704, "lr": 2.297925919151675e-07, "epoch": 0.3152916447714136, "percentage": 21.01, "elapsed_time": "0:19:25", "remaining_time": "1:13:02"}
{"current_steps": 160, "total_steps": 714, "loss": 1.847894287109375, "lr": 2.265920609685895e-07, "epoch": 0.33631108775617446, "percentage": 22.41, "elapsed_time": "0:20:48", "remaining_time": "1:12:02"}
{"current_steps": 170, "total_steps": 714, "loss": 1.8336673736572267, "lr": 2.2318218013333245e-07, "epoch": 0.35733053074093535, "percentage": 23.81, "elapsed_time": "0:22:05", "remaining_time": "1:10:42"}
{"current_steps": 180, "total_steps": 714, "loss": 1.9188970565795898, "lr": 2.1956997612158683e-07, "epoch": 0.3783499737256963, "percentage": 25.21, "elapsed_time": "0:23:21", "remaining_time": "1:09:18"}
{"current_steps": 190, "total_steps": 714, "loss": 1.9967548370361328, "lr": 2.157628925711777e-07, "epoch": 0.39936941671045717, "percentage": 26.61, "elapsed_time": "0:24:40", "remaining_time": "1:08:02"}
{"current_steps": 200, "total_steps": 714, "loss": 1.9001514434814453, "lr": 2.117687747065239e-07, "epoch": 0.42038885969521805, "percentage": 28.01, "elapsed_time": "0:25:56", "remaining_time": "1:06:40"}
{"current_steps": 210, "total_steps": 714, "loss": 1.939328956604004, "lr": 2.0759585317205137e-07, "epoch": 0.441408302679979, "percentage": 29.41, "elapsed_time": "0:27:15", "remaining_time": "1:05:24"}
{"current_steps": 220, "total_steps": 714, "loss": 1.9735946655273438, "lr": 2.0325272707137493e-07, "epoch": 0.4624277456647399, "percentage": 30.81, "elapsed_time": "0:28:34", "remaining_time": "1:04:10"}
{"current_steps": 230, "total_steps": 714, "loss": 1.8626848220825196, "lr": 1.9874834624719906e-07, "epoch": 0.4834471886495008, "percentage": 32.21, "elapsed_time": "0:29:52", "remaining_time": "1:02:52"}
{"current_steps": 240, "total_steps": 714, "loss": 1.746560287475586, "lr": 1.9409199283845392e-07, "epoch": 0.5044666316342616, "percentage": 33.61, "elapsed_time": "0:31:12", "remaining_time": "1:01:37"}
{"current_steps": 250, "total_steps": 714, "loss": 1.920944595336914, "lr": 1.892932621526712e-07, "epoch": 0.5254860746190226, "percentage": 35.01, "elapsed_time": "0:32:29", "remaining_time": "1:00:18"}
{"current_steps": 260, "total_steps": 714, "loss": 1.9723596572875977, "lr": 1.8436204289301616e-07, "epoch": 0.5465055176037835, "percentage": 36.41, "elapsed_time": "0:33:45", "remaining_time": "0:58:56"}
{"current_steps": 270, "total_steps": 714, "loss": 1.8008295059204102, "lr": 1.79308496780722e-07, "epoch": 0.5675249605885444, "percentage": 37.82, "elapsed_time": "0:35:03", "remaining_time": "0:57:39"}
{"current_steps": 280, "total_steps": 714, "loss": 1.8942089080810547, "lr": 1.7414303761491778e-07, "epoch": 0.5885444035733053, "percentage": 39.22, "elapsed_time": "0:36:23", "remaining_time": "0:56:24"}
{"current_steps": 290, "total_steps": 714, "loss": 1.9562250137329102, "lr": 1.6887630981300217e-07, "epoch": 0.6095638465580662, "percentage": 40.62, "elapsed_time": "0:37:44", "remaining_time": "0:55:10"}
{"current_steps": 300, "total_steps": 714, "loss": 1.8874702453613281, "lr": 1.6351916647578366e-07, "epoch": 0.6305832895428272, "percentage": 42.02, "elapsed_time": "0:39:01", "remaining_time": "0:53:51"}
{"current_steps": 310, "total_steps": 714, "loss": 1.82128849029541, "lr": 1.5808264702258885e-07, "epoch": 0.651602732527588, "percentage": 43.42, "elapsed_time": "0:40:19", "remaining_time": "0:52:32"}
{"current_steps": 320, "total_steps": 714, "loss": 1.9460525512695312, "lr": 1.5257795444242566e-07, "epoch": 0.6726221755123489, "percentage": 44.82, "elapsed_time": "0:41:33", "remaining_time": "0:51:09"}
{"current_steps": 330, "total_steps": 714, "loss": 1.9333660125732421, "lr": 1.4701643220808016e-07, "epoch": 0.6936416184971098, "percentage": 46.22, "elapsed_time": "0:42:48", "remaining_time": "0:49:48"}
{"current_steps": 340, "total_steps": 714, "loss": 1.8776426315307617, "lr": 1.414095409007192e-07, "epoch": 0.7146610614818707, "percentage": 47.62, "elapsed_time": "0:44:07", "remaining_time": "0:48:32"}
{"current_steps": 350, "total_steps": 714, "loss": 1.8990169525146485, "lr": 1.3576883459316937e-07, "epoch": 0.7356805044666316, "percentage": 49.02, "elapsed_time": "0:45:25", "remaining_time": "0:47:14"}
{"current_steps": 360, "total_steps": 714, "loss": 1.9327930450439452, "lr": 1.3010593704053815e-07, "epoch": 0.7566999474513926, "percentage": 50.42, "elapsed_time": "0:46:43", "remaining_time": "0:45:57"}
{"current_steps": 370, "total_steps": 714, "loss": 1.9645748138427734, "lr": 1.2443251772724124e-07, "epoch": 0.7777193904361535, "percentage": 51.82, "elapsed_time": "0:48:01", "remaining_time": "0:44:39"}
{"current_steps": 380, "total_steps": 714, "loss": 1.9750782012939454, "lr": 1.1876026781979653e-07, "epoch": 0.7987388334209143, "percentage": 53.22, "elapsed_time": "0:49:21", "remaining_time": "0:43:22"}
{"current_steps": 390, "total_steps": 714, "loss": 1.9279960632324218, "lr": 1.1310087607493711e-07, "epoch": 0.8197582764056752, "percentage": 54.62, "elapsed_time": "0:50:39", "remaining_time": "0:42:05"}
{"current_steps": 400, "total_steps": 714, "loss": 1.9484302520751953, "lr": 1.0746600475269085e-07, "epoch": 0.8407777193904361, "percentage": 56.02, "elapsed_time": "0:51:59", "remaining_time": "0:40:48"}
{"current_steps": 410, "total_steps": 714, "loss": 1.9229631423950195, "lr": 1.0186726558406097e-07, "epoch": 0.8617971623751971, "percentage": 57.42, "elapsed_time": "0:53:19", "remaining_time": "0:39:32"}
{"current_steps": 420, "total_steps": 714, "loss": 1.9820945739746094, "lr": 9.631619584283176e-08, "epoch": 0.882816605359958, "percentage": 58.82, "elapsed_time": "0:54:35", "remaining_time": "0:38:12"}
{"current_steps": 430, "total_steps": 714, "loss": 2.0028038024902344, "lr": 9.08242345708071e-08, "epoch": 0.9038360483447189, "percentage": 60.22, "elapsed_time": "0:55:52", "remaining_time": "0:36:53"}
{"current_steps": 440, "total_steps": 714, "loss": 1.9427295684814454, "lr": 8.540269900547556e-08, "epoch": 0.9248554913294798, "percentage": 61.62, "elapsed_time": "0:57:11", "remaining_time": "0:35:37"}
{"current_steps": 450, "total_steps": 714, "loss": 1.8801141738891602, "lr": 8.00627612586759e-08, "epoch": 0.9458749343142406, "percentage": 63.03, "elapsed_time": "0:58:28", "remaining_time": "0:34:18"}
{"current_steps": 460, "total_steps": 714, "loss": 1.7729660034179688, "lr": 7.48154252943221e-08, "epoch": 0.9668943772990016, "percentage": 64.43, "elapsed_time": "0:59:48", "remaining_time": "0:33:01"}
{"current_steps": 470, "total_steps": 714, "loss": 2.0267822265625, "lr": 6.967150425262934e-08, "epoch": 0.9879138202837625, "percentage": 65.83, "elapsed_time": "1:01:03", "remaining_time": "0:31:42"}
{"current_steps": 480, "total_steps": 714, "loss": 1.847897720336914, "lr": 6.464159816756865e-08, "epoch": 1.0084077771939044, "percentage": 67.23, "elapsed_time": "1:02:19", "remaining_time": "0:30:23"}
{"current_steps": 490, "total_steps": 714, "loss": 1.7879396438598634, "lr": 5.973607212346771e-08, "epoch": 1.0294272201786652, "percentage": 68.63, "elapsed_time": "1:03:36", "remaining_time": "0:29:04"}
{"current_steps": 500, "total_steps": 714, "loss": 2.006256675720215, "lr": 5.496503489577081e-08, "epoch": 1.0504466631634262, "percentage": 70.03, "elapsed_time": "1:04:51", "remaining_time": "0:27:45"}
{"current_steps": 510, "total_steps": 714, "loss": 1.9164451599121093, "lr": 5.033831811997166e-08, "epoch": 1.0714661061481872, "percentage": 71.43, "elapsed_time": "1:06:07", "remaining_time": "0:26:27"}
{"current_steps": 520, "total_steps": 714, "loss": 1.7832933425903321, "lr": 4.5865456031646654e-08, "epoch": 1.092485549132948, "percentage": 72.83, "elapsed_time": "1:07:23", "remaining_time": "0:25:08"}
{"current_steps": 530, "total_steps": 714, "loss": 1.8139366149902343, "lr": 4.1555665819337293e-08, "epoch": 1.113504992117709, "percentage": 74.23, "elapsed_time": "1:08:41", "remaining_time": "0:23:50"}
{"current_steps": 540, "total_steps": 714, "loss": 1.869268798828125, "lr": 3.7417828630768835e-08, "epoch": 1.1345244351024697, "percentage": 75.63, "elapsed_time": "1:09:59", "remaining_time": "0:22:33"}
{"current_steps": 550, "total_steps": 714, "loss": 1.878763771057129, "lr": 3.346047127154539e-08, "epoch": 1.1555438780872307, "percentage": 77.03, "elapsed_time": "1:11:14", "remaining_time": "0:21:14"}
{"current_steps": 560, "total_steps": 714, "loss": 1.8553329467773438, "lr": 2.9691748634034702e-08, "epoch": 1.1765633210719917, "percentage": 78.43, "elapsed_time": "1:12:31", "remaining_time": "0:19:56"}
{"current_steps": 570, "total_steps": 714, "loss": 1.8416221618652344, "lr": 2.6119426892651426e-08, "epoch": 1.1975827640567525, "percentage": 79.83, "elapsed_time": "1:13:50", "remaining_time": "0:18:39"}
{"current_steps": 580, "total_steps": 714, "loss": 1.9319948196411132, "lr": 2.275086750016812e-08, "epoch": 1.2186022070415135, "percentage": 81.23, "elapsed_time": "1:15:09", "remaining_time": "0:17:21"}
{"current_steps": 590, "total_steps": 714, "loss": 1.7423213958740233, "lr": 1.959301201803254e-08, "epoch": 1.2396216500262742, "percentage": 82.63, "elapsed_time": "1:16:29", "remaining_time": "0:16:04"}
{"current_steps": 600, "total_steps": 714, "loss": 1.9869190216064454, "lr": 1.6652367811951715e-08, "epoch": 1.2606410930110352, "percentage": 84.03, "elapsed_time": "1:17:44", "remaining_time": "0:14:46"}
{"current_steps": 610, "total_steps": 714, "loss": 1.8976511001586913, "lr": 1.3934994642219104e-08, "epoch": 1.2816605359957962, "percentage": 85.43, "elapsed_time": "1:19:01", "remaining_time": "0:13:28"}
{"current_steps": 620, "total_steps": 714, "loss": 1.9856376647949219, "lr": 1.1446492176418563e-08, "epoch": 1.302679978980557, "percentage": 86.83, "elapsed_time": "1:20:22", "remaining_time": "0:12:11"}
{"current_steps": 630, "total_steps": 714, "loss": 2.0055776596069337, "lr": 9.191988450237387e-09, "epoch": 1.323699421965318, "percentage": 88.24, "elapsed_time": "1:21:40", "remaining_time": "0:10:53"}
{"current_steps": 640, "total_steps": 714, "loss": 1.9813310623168945, "lr": 7.1761293001671855e-09, "epoch": 1.3447188649500788, "percentage": 89.64, "elapsed_time": "1:22:57", "remaining_time": "0:09:35"}
{"current_steps": 650, "total_steps": 714, "loss": 1.9645788192749023, "lr": 5.403068789868334e-09, "epoch": 1.3657383079348397, "percentage": 91.04, "elapsed_time": "1:24:18", "remaining_time": "0:08:18"}
{"current_steps": 660, "total_steps": 714, "loss": 1.9697418212890625, "lr": 3.8764606499268606e-09, "epoch": 1.3867577509196005, "percentage": 92.44, "elapsed_time": "1:25:35", "remaining_time": "0:07:00"}
{"current_steps": 670, "total_steps": 714, "loss": 1.8822681427001953, "lr": 2.599450748642956e-09, "epoch": 1.4077771939043615, "percentage": 93.84, "elapsed_time": "1:26:53", "remaining_time": "0:05:42"}
{"current_steps": 680, "total_steps": 714, "loss": 1.9432037353515625, "lr": 1.5746706093672235e-09, "epoch": 1.4287966368891225, "percentage": 95.24, "elapsed_time": "1:28:12", "remaining_time": "0:04:24"}
{"current_steps": 690, "total_steps": 714, "loss": 1.8227525711059571, "lr": 8.042319877430981e-10, "epoch": 1.4498160798738833, "percentage": 96.64, "elapsed_time": "1:29:31", "remaining_time": "0:03:06"}
{"current_steps": 700, "total_steps": 714, "loss": 1.9617921829223632, "lr": 2.897225200300807e-10, "epoch": 1.4708355228586443, "percentage": 98.04, "elapsed_time": "1:30:44", "remaining_time": "0:01:48"}
{"current_steps": 710, "total_steps": 714, "loss": 1.9124065399169923, "lr": 3.220245147531053e-11, "epoch": 1.4918549658434053, "percentage": 99.44, "elapsed_time": "1:32:02", "remaining_time": "0:00:31"}
{"current_steps": 714, "total_steps": 714, "epoch": 1.5002627430373097, "percentage": 100.0, "elapsed_time": "1:32:33", "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": 9.625,
"learning_rate": 1.0227272727272728e-07,
"loss": 1.8086944580078126,
"step": 10
},
{
"epoch": 0.04203888596952181,
"grad_norm": 10.5625,
"learning_rate": 2.159090909090909e-07,
"loss": 1.9563072204589844,
"step": 20
},
{
"epoch": 0.0630583289542827,
"grad_norm": 8.375,
"learning_rate": 2.4993688579681983e-07,
"loss": 1.9191463470458985,
"step": 30
},
{
"epoch": 0.08407777193904362,
"grad_norm": 5.21875,
"learning_rate": 2.496279084257832e-07,
"loss": 1.8105619430541993,
"step": 40
},
{
"epoch": 0.10509721492380451,
"grad_norm": 7.15625,
"learning_rate": 2.490621113927919e-07,
"loss": 1.9305204391479491,
"step": 50
},
{
"epoch": 0.1261166579085654,
"grad_norm": 5.21875,
"learning_rate": 2.4824066063093887e-07,
"loss": 1.9595895767211915,
"step": 60
},
{
"epoch": 0.14713610089332632,
"grad_norm": 15.875,
"learning_rate": 2.4716524889676334e-07,
"loss": 1.9885068893432618,
"step": 70
},
{
"epoch": 0.16815554387808723,
"grad_norm": 11.6875,
"learning_rate": 2.458380922820022e-07,
"loss": 1.9129520416259767,
"step": 80
},
{
"epoch": 0.18917498686284814,
"grad_norm": 7.375,
"learning_rate": 2.442619256469084e-07,
"loss": 1.9894475936889648,
"step": 90
},
{
"epoch": 0.21019442984760903,
"grad_norm": 9.25,
"learning_rate": 2.42439996984548e-07,
"loss": 1.8159450531005858,
"step": 100
},
{
"epoch": 0.23121387283236994,
"grad_norm": 5.4375,
"learning_rate": 2.403760607276888e-07,
"loss": 1.9744218826293944,
"step": 110
},
{
"epoch": 0.2522333158171308,
"grad_norm": 8.375,
"learning_rate": 2.3807437001207282e-07,
"loss": 1.8607925415039062,
"step": 120
},
{
"epoch": 0.27325275880189176,
"grad_norm": 6.40625,
"learning_rate": 2.3553966791201608e-07,
"loss": 1.9678337097167968,
"step": 130
},
{
"epoch": 0.29427220178665264,
"grad_norm": 7.84375,
"learning_rate": 2.3277717766639592e-07,
"loss": 1.905088233947754,
"step": 140
},
{
"epoch": 0.3152916447714136,
"grad_norm": 8.1875,
"learning_rate": 2.297925919151675e-07,
"loss": 1.8011585235595704,
"step": 150
},
{
"epoch": 0.33631108775617446,
"grad_norm": 5.6875,
"learning_rate": 2.265920609685895e-07,
"loss": 1.847894287109375,
"step": 160
},
{
"epoch": 0.35733053074093535,
"grad_norm": 4.625,
"learning_rate": 2.2318218013333245e-07,
"loss": 1.8336673736572267,
"step": 170
},
{
"epoch": 0.3783499737256963,
"grad_norm": 15.375,
"learning_rate": 2.1956997612158683e-07,
"loss": 1.9188970565795898,
"step": 180
},
{
"epoch": 0.39936941671045717,
"grad_norm": 5.1875,
"learning_rate": 2.157628925711777e-07,
"loss": 1.9967548370361328,
"step": 190
},
{
"epoch": 0.42038885969521805,
"grad_norm": 6.84375,
"learning_rate": 2.117687747065239e-07,
"loss": 1.9001514434814453,
"step": 200
},
{
"epoch": 0.441408302679979,
"grad_norm": 5.84375,
"learning_rate": 2.0759585317205137e-07,
"loss": 1.939328956604004,
"step": 210
},
{
"epoch": 0.4624277456647399,
"grad_norm": 12.3125,
"learning_rate": 2.0325272707137493e-07,
"loss": 1.9735946655273438,
"step": 220
},
{
"epoch": 0.4834471886495008,
"grad_norm": 5.34375,
"learning_rate": 1.9874834624719906e-07,
"loss": 1.8626848220825196,
"step": 230
},
{
"epoch": 0.5044666316342616,
"grad_norm": 6.4375,
"learning_rate": 1.9409199283845392e-07,
"loss": 1.746560287475586,
"step": 240
},
{
"epoch": 0.5254860746190226,
"grad_norm": 6.4375,
"learning_rate": 1.892932621526712e-07,
"loss": 1.920944595336914,
"step": 250
},
{
"epoch": 0.5465055176037835,
"grad_norm": 8.125,
"learning_rate": 1.8436204289301616e-07,
"loss": 1.9723596572875977,
"step": 260
},
{
"epoch": 0.5675249605885444,
"grad_norm": 5.8125,
"learning_rate": 1.79308496780722e-07,
"loss": 1.8008295059204102,
"step": 270
},
{
"epoch": 0.5885444035733053,
"grad_norm": 6.5,
"learning_rate": 1.7414303761491778e-07,
"loss": 1.8942089080810547,
"step": 280
},
{
"epoch": 0.6095638465580662,
"grad_norm": 7.25,
"learning_rate": 1.6887630981300217e-07,
"loss": 1.9562250137329102,
"step": 290
},
{
"epoch": 0.6305832895428272,
"grad_norm": 4.5,
"learning_rate": 1.6351916647578366e-07,
"loss": 1.8874702453613281,
"step": 300
},
{
"epoch": 0.651602732527588,
"grad_norm": 20.5,
"learning_rate": 1.5808264702258885e-07,
"loss": 1.82128849029541,
"step": 310
},
{
"epoch": 0.6726221755123489,
"grad_norm": 4.59375,
"learning_rate": 1.5257795444242566e-07,
"loss": 1.9460525512695312,
"step": 320
},
{
"epoch": 0.6936416184971098,
"grad_norm": 12.875,
"learning_rate": 1.4701643220808016e-07,
"loss": 1.9333660125732421,
"step": 330
},
{
"epoch": 0.7146610614818707,
"grad_norm": 9.625,
"learning_rate": 1.414095409007192e-07,
"loss": 1.8776426315307617,
"step": 340
},
{
"epoch": 0.7356805044666316,
"grad_norm": 9.875,
"learning_rate": 1.3576883459316937e-07,
"loss": 1.8990169525146485,
"step": 350
},
{
"epoch": 0.7566999474513926,
"grad_norm": 6.15625,
"learning_rate": 1.3010593704053815e-07,
"loss": 1.9327930450439452,
"step": 360
},
{
"epoch": 0.7777193904361535,
"grad_norm": 5.65625,
"learning_rate": 1.2443251772724124e-07,
"loss": 1.9645748138427734,
"step": 370
},
{
"epoch": 0.7987388334209143,
"grad_norm": 15.25,
"learning_rate": 1.1876026781979653e-07,
"loss": 1.9750782012939454,
"step": 380
},
{
"epoch": 0.8197582764056752,
"grad_norm": 9.3125,
"learning_rate": 1.1310087607493711e-07,
"loss": 1.9279960632324218,
"step": 390
},
{
"epoch": 0.8407777193904361,
"grad_norm": 9.1875,
"learning_rate": 1.0746600475269085e-07,
"loss": 1.9484302520751953,
"step": 400
},
{
"epoch": 0.8617971623751971,
"grad_norm": 4.53125,
"learning_rate": 1.0186726558406097e-07,
"loss": 1.9229631423950195,
"step": 410
},
{
"epoch": 0.882816605359958,
"grad_norm": 7.96875,
"learning_rate": 9.631619584283176e-08,
"loss": 1.9820945739746094,
"step": 420
},
{
"epoch": 0.9038360483447189,
"grad_norm": 6.1875,
"learning_rate": 9.08242345708071e-08,
"loss": 2.0028038024902344,
"step": 430
},
{
"epoch": 0.9248554913294798,
"grad_norm": 6.28125,
"learning_rate": 8.540269900547556e-08,
"loss": 1.9427295684814454,
"step": 440
},
{
"epoch": 0.9458749343142406,
"grad_norm": 5.03125,
"learning_rate": 8.00627612586759e-08,
"loss": 1.8801141738891602,
"step": 450
},
{
"epoch": 0.9668943772990016,
"grad_norm": 12.5,
"learning_rate": 7.48154252943221e-08,
"loss": 1.7729660034179688,
"step": 460
},
{
"epoch": 0.9879138202837625,
"grad_norm": 6.3125,
"learning_rate": 6.967150425262934e-08,
"loss": 2.0267822265625,
"step": 470
},
{
"epoch": 1.0084077771939044,
"grad_norm": 7.25,
"learning_rate": 6.464159816756865e-08,
"loss": 1.847897720336914,
"step": 480
},
{
"epoch": 1.0294272201786652,
"grad_norm": 6.46875,
"learning_rate": 5.973607212346771e-08,
"loss": 1.7879396438598634,
"step": 490
},
{
"epoch": 1.0504466631634262,
"grad_norm": 10.0625,
"learning_rate": 5.496503489577081e-08,
"loss": 2.006256675720215,
"step": 500
},
{
"epoch": 1.0714661061481872,
"grad_norm": 19.125,
"learning_rate": 5.033831811997166e-08,
"loss": 1.9164451599121093,
"step": 510
},
{
"epoch": 1.092485549132948,
"grad_norm": 5.34375,
"learning_rate": 4.5865456031646654e-08,
"loss": 1.7832933425903321,
"step": 520
},
{
"epoch": 1.113504992117709,
"grad_norm": 5.75,
"learning_rate": 4.1555665819337293e-08,
"loss": 1.8139366149902343,
"step": 530
},
{
"epoch": 1.1345244351024697,
"grad_norm": 5.84375,
"learning_rate": 3.7417828630768835e-08,
"loss": 1.869268798828125,
"step": 540
},
{
"epoch": 1.1555438780872307,
"grad_norm": 6.46875,
"learning_rate": 3.346047127154539e-08,
"loss": 1.878763771057129,
"step": 550
},
{
"epoch": 1.1765633210719917,
"grad_norm": 10.0625,
"learning_rate": 2.9691748634034702e-08,
"loss": 1.8553329467773438,
"step": 560
},
{
"epoch": 1.1975827640567525,
"grad_norm": 13.3125,
"learning_rate": 2.6119426892651426e-08,
"loss": 1.8416221618652344,
"step": 570
},
{
"epoch": 1.2186022070415135,
"grad_norm": 7.03125,
"learning_rate": 2.275086750016812e-08,
"loss": 1.9319948196411132,
"step": 580
},
{
"epoch": 1.2396216500262742,
"grad_norm": 5.53125,
"learning_rate": 1.959301201803254e-08,
"loss": 1.7423213958740233,
"step": 590
},
{
"epoch": 1.2606410930110352,
"grad_norm": 6.28125,
"learning_rate": 1.6652367811951715e-08,
"loss": 1.9869190216064454,
"step": 600
},
{
"epoch": 1.2816605359957962,
"grad_norm": 14.75,
"learning_rate": 1.3934994642219104e-08,
"loss": 1.8976511001586913,
"step": 610
},
{
"epoch": 1.302679978980557,
"grad_norm": 9.375,
"learning_rate": 1.1446492176418563e-08,
"loss": 1.9856376647949219,
"step": 620
},
{
"epoch": 1.323699421965318,
"grad_norm": 5.125,
"learning_rate": 9.191988450237387e-09,
"loss": 2.0055776596069337,
"step": 630
},
{
"epoch": 1.3447188649500788,
"grad_norm": 9.25,
"learning_rate": 7.1761293001671855e-09,
"loss": 1.9813310623168945,
"step": 640
},
{
"epoch": 1.3657383079348397,
"grad_norm": 7.1875,
"learning_rate": 5.403068789868334e-09,
"loss": 1.9645788192749023,
"step": 650
},
{
"epoch": 1.3867577509196005,
"grad_norm": 4.21875,
"learning_rate": 3.8764606499268606e-09,
"loss": 1.9697418212890625,
"step": 660
},
{
"epoch": 1.4077771939043615,
"grad_norm": 5.15625,
"learning_rate": 2.599450748642956e-09,
"loss": 1.8822681427001953,
"step": 670
},
{
"epoch": 1.4287966368891225,
"grad_norm": 6.9375,
"learning_rate": 1.5746706093672235e-09,
"loss": 1.9432037353515625,
"step": 680
},
{
"epoch": 1.4498160798738833,
"grad_norm": 7.09375,
"learning_rate": 8.042319877430981e-10,
"loss": 1.8227525711059571,
"step": 690
},
{
"epoch": 1.4708355228586443,
"grad_norm": 6.875,
"learning_rate": 2.897225200300807e-10,
"loss": 1.9617921829223632,
"step": 700
},
{
"epoch": 1.4918549658434053,
"grad_norm": 11.1875,
"learning_rate": 3.220245147531053e-11,
"loss": 1.9124065399169923,
"step": 710
},
{
"epoch": 1.5002627430373097,
"step": 714,
"total_flos": 3.414600284463329e+17,
"train_loss": 1.907181319736299,
"train_runtime": 5553.447,
"train_samples_per_second": 0.514,
"train_steps_per_second": 0.129
}
],
"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": 3.414600284463329e+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:efcf2e364c383000757b44f29d4bba7b7a813c601108680de099731ae3d5baec
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 64 KiB