lldois/v34_v29_paper_mix_lr5e7_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/v34_v29_paper_mix_lr5e7_ep10
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-19 03:59:11 +08:00
commit 0d1bc395ab
17 changed files with 3098 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: v34_v29_paper_mix_lr5e7_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. -->
# v34_v29_paper_mix_lr5e7_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_v34_paper_mix dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-07
- train_batch_size: 1
- eval_batch_size: 8
- seed: 202607184
- 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": 2.27705175303125e+17,
"train_loss": 1.8975331122133912,
"train_runtime": 3756.1832,
"train_samples_per_second": 0.507,
"train_steps_per_second": 0.127
}

89
chat_template.jinja Normal file
View File

@@ -0,0 +1,89 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if message.content is string %}
{%- set content = message.content %}
{%- else %}
{%- set content = '' %}
{%- endif %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in content %}
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and reasoning_content) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- endif %}
{%- endif %}

63
config.json Normal file
View File

@@ -0,0 +1,63 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "5.6.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 176253
}

72
experiment_recipe.json Normal file
View File

@@ -0,0 +1,72 @@
{
"created_at": "2026-07-15 00:59:15",
"name": "v34_v29_paper_mix_lr5e7_ep10",
"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": "5.0e-7",
"epochs": 1.0,
"stages": null,
"note": "Anchor run using a scaled OneReason-like R0/R3/general mixture plus old-task replay.",
"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/v34_v29_paper_mix_lr5e7_ep10.yaml"
],
"reproduce": "/home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/python /home/ll/llm4rec/experiments/run_v34_v43.py --single v34_v29_paper_mix_lr5e7_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 sha256:3ada26e67cafc409cf6c815d35e0f769f3e37e320ae3637666601c65ab73433d
size 1602902832

3
runs/Jul15_00-59-52_ubuntu-System-Product-Name/events.out.tfevents.1784048392.ubuntu-System-Product-Name.1380388.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8ea0965da2ce4988748d0ebadca49e606be0b9655ac51ffadd812cfbe4441e52
size 16163

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
}

2304
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": 2.27705175303125e+17,
"train_loss": 1.8975331122133912,
"train_runtime": 3756.1832,
"train_samples_per_second": 0.507,
"train_steps_per_second": 0.127
}

48
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,48 @@
{"current_steps": 10, "total_steps": 476, "loss": 1.8080066680908202, "lr": 3e-07, "epoch": 0.021019442984760904, "percentage": 2.1, "elapsed_time": "0:01:18", "remaining_time": "1:00:49"}
{"current_steps": 20, "total_steps": 476, "loss": 1.9573022842407226, "lr": 4.99907124535624e-07, "epoch": 0.04203888596952181, "percentage": 4.2, "elapsed_time": "0:02:36", "remaining_time": "0:59:35"}
{"current_steps": 30, "total_steps": 476, "loss": 1.93359317779541, "lr": 4.988630678996146e-07, "epoch": 0.0630583289542827, "percentage": 6.3, "elapsed_time": "0:03:56", "remaining_time": "0:58:35"}
{"current_steps": 40, "total_steps": 476, "loss": 1.8890295028686523, "lr": 4.966637232576035e-07, "epoch": 0.08407777193904362, "percentage": 8.4, "elapsed_time": "0:05:16", "remaining_time": "0:57:32"}
{"current_steps": 50, "total_steps": 476, "loss": 1.8508934020996093, "lr": 4.933193005475595e-07, "epoch": 0.10509721492380451, "percentage": 10.5, "elapsed_time": "0:06:35", "remaining_time": "0:56:13"}
{"current_steps": 60, "total_steps": 476, "loss": 1.8927783966064453, "lr": 4.888453254618907e-07, "epoch": 0.1261166579085654, "percentage": 12.61, "elapsed_time": "0:07:51", "remaining_time": "0:54:31"}
{"current_steps": 70, "total_steps": 476, "loss": 1.8637098312377929, "lr": 4.832625673730847e-07, "epoch": 0.14713610089332632, "percentage": 14.71, "elapsed_time": "0:09:10", "remaining_time": "0:53:11"}
{"current_steps": 80, "total_steps": 476, "loss": 1.983097457885742, "lr": 4.765969429168031e-07, "epoch": 0.16815554387808723, "percentage": 16.81, "elapsed_time": "0:10:29", "remaining_time": "0:51:55"}
{"current_steps": 90, "total_steps": 476, "loss": 1.919074821472168, "lr": 4.6887939568002264e-07, "epoch": 0.18917498686284814, "percentage": 18.91, "elapsed_time": "0:11:47", "remaining_time": "0:50:33"}
{"current_steps": 100, "total_steps": 476, "loss": 1.8743148803710938, "lr": 4.6014575255274225e-07, "epoch": 0.21019442984760903, "percentage": 21.01, "elapsed_time": "0:13:07", "remaining_time": "0:49:19"}
{"current_steps": 110, "total_steps": 476, "loss": 1.9480220794677734, "lr": 4.504365574101089e-07, "epoch": 0.23121387283236994, "percentage": 23.11, "elapsed_time": "0:14:27", "remaining_time": "0:48:07"}
{"current_steps": 120, "total_steps": 476, "loss": 1.8002925872802735, "lr": 4.3979688289705503e-07, "epoch": 0.2522333158171308, "percentage": 25.21, "elapsed_time": "0:15:49", "remaining_time": "0:46:57"}
{"current_steps": 130, "total_steps": 476, "loss": 1.915324592590332, "lr": 4.282761211891912e-07, "epoch": 0.27325275880189176, "percentage": 27.31, "elapsed_time": "0:17:09", "remaining_time": "0:45:40"}
{"current_steps": 140, "total_steps": 476, "loss": 1.985239601135254, "lr": 4.1592775470129854e-07, "epoch": 0.29427220178665264, "percentage": 29.41, "elapsed_time": "0:18:29", "remaining_time": "0:44:23"}
{"current_steps": 150, "total_steps": 476, "loss": 1.8037527084350586, "lr": 4.028091078078516e-07, "epoch": 0.3152916447714136, "percentage": 31.51, "elapsed_time": "0:19:49", "remaining_time": "0:43:05"}
{"current_steps": 160, "total_steps": 476, "loss": 1.8475725173950195, "lr": 3.8898108072815116e-07, "epoch": 0.33631108775617446, "percentage": 33.61, "elapsed_time": "0:21:11", "remaining_time": "0:41:51"}
{"current_steps": 170, "total_steps": 476, "loss": 1.8196781158447266, "lr": 3.7450786681144234e-07, "epoch": 0.35733053074093535, "percentage": 35.71, "elapsed_time": "0:22:31", "remaining_time": "0:40:33"}
{"current_steps": 180, "total_steps": 476, "loss": 1.813003921508789, "lr": 3.5945665453445397e-07, "epoch": 0.3783499737256963, "percentage": 37.82, "elapsed_time": "0:23:51", "remaining_time": "0:39:13"}
{"current_steps": 190, "total_steps": 476, "loss": 1.8163671493530273, "lr": 3.4389731559476716e-07, "epoch": 0.39936941671045717, "percentage": 39.92, "elapsed_time": "0:25:11", "remaining_time": "0:37:55"}
{"current_steps": 200, "total_steps": 476, "loss": 1.853123092651367, "lr": 3.279020805479643e-07, "epoch": 0.42038885969521805, "percentage": 42.02, "elapsed_time": "0:26:29", "remaining_time": "0:36:33"}
{"current_steps": 210, "total_steps": 476, "loss": 1.8787429809570313, "lr": 3.1154520349433735e-07, "epoch": 0.441408302679979, "percentage": 44.12, "elapsed_time": "0:27:46", "remaining_time": "0:35:11"}
{"current_steps": 220, "total_steps": 476, "loss": 1.9475088119506836, "lr": 2.9490261737176715e-07, "epoch": 0.4624277456647399, "percentage": 46.22, "elapsed_time": "0:29:03", "remaining_time": "0:33:49"}
{"current_steps": 230, "total_steps": 476, "loss": 1.9444992065429687, "lr": 2.780515814549969e-07, "epoch": 0.4834471886495008, "percentage": 48.32, "elapsed_time": "0:30:22", "remaining_time": "0:32:29"}
{"current_steps": 240, "total_steps": 476, "loss": 1.7953880310058594, "lr": 2.6107032269769897e-07, "epoch": 0.5044666316342616, "percentage": 50.42, "elapsed_time": "0:31:43", "remaining_time": "0:31:12"}
{"current_steps": 250, "total_steps": 476, "loss": 1.9037723541259766, "lr": 2.440376725823213e-07, "epoch": 0.5254860746190226, "percentage": 52.52, "elapsed_time": "0:33:02", "remaining_time": "0:29:51"}
{"current_steps": 260, "total_steps": 476, "loss": 1.9526327133178711, "lr": 2.2703270116355234e-07, "epoch": 0.5465055176037835, "percentage": 54.62, "elapsed_time": "0:34:16", "remaining_time": "0:28:28"}
{"current_steps": 270, "total_steps": 476, "loss": 1.9550243377685548, "lr": 2.101343500042697e-07, "epoch": 0.5675249605885444, "percentage": 56.72, "elapsed_time": "0:35:37", "remaining_time": "0:27:11"}
{"current_steps": 280, "total_steps": 476, "loss": 1.896200180053711, "lr": 1.934210657079821e-07, "epoch": 0.5885444035733053, "percentage": 58.82, "elapsed_time": "0:36:56", "remaining_time": "0:25:51"}
{"current_steps": 290, "total_steps": 476, "loss": 1.9687370300292968, "lr": 1.7697043574900388e-07, "epoch": 0.6095638465580662, "percentage": 60.92, "elapsed_time": "0:38:15", "remaining_time": "0:24:32"}
{"current_steps": 300, "total_steps": 476, "loss": 1.7474214553833007, "lr": 1.608588282909325e-07, "epoch": 0.6305832895428272, "percentage": 63.03, "elapsed_time": "0:39:35", "remaining_time": "0:23:13"}
{"current_steps": 310, "total_steps": 476, "loss": 1.952895164489746, "lr": 1.4516103766548969e-07, "epoch": 0.651602732527588, "percentage": 65.13, "elapsed_time": "0:40:55", "remaining_time": "0:21:54"}
{"current_steps": 320, "total_steps": 476, "loss": 2.002369689941406, "lr": 1.2994993715750356e-07, "epoch": 0.6726221755123489, "percentage": 67.23, "elapsed_time": "0:42:14", "remaining_time": "0:20:35"}
{"current_steps": 330, "total_steps": 476, "loss": 1.9351655960083007, "lr": 1.1529614070789883e-07, "epoch": 0.6936416184971098, "percentage": 69.33, "elapsed_time": "0:43:32", "remaining_time": "0:19:15"}
{"current_steps": 340, "total_steps": 476, "loss": 1.9994436264038087, "lr": 1.0126767510515585e-07, "epoch": 0.7146610614818707, "percentage": 71.43, "elapsed_time": "0:44:52", "remaining_time": "0:17:56"}
{"current_steps": 350, "total_steps": 476, "loss": 2.0275642395019533, "lr": 8.792966418701511e-08, "epoch": 0.7356805044666316, "percentage": 73.53, "elapsed_time": "0:46:11", "remaining_time": "0:16:37"}
{"current_steps": 360, "total_steps": 476, "loss": 1.9153682708740234, "lr": 7.534402651844351e-08, "epoch": 0.7566999474513926, "percentage": 75.63, "elapsed_time": "0:47:29", "remaining_time": "0:15:18"}
{"current_steps": 370, "total_steps": 476, "loss": 1.9506032943725586, "lr": 6.356918794932362e-08, "epoch": 0.7777193904361535, "percentage": 77.73, "elapsed_time": "0:48:51", "remaining_time": "0:13:59"}
{"current_steps": 380, "total_steps": 476, "loss": 1.9164735794067382, "lr": 5.265981038624656e-08, "epoch": 0.7987388334209143, "percentage": 79.83, "elapsed_time": "0:50:06", "remaining_time": "0:12:39"}
{"current_steps": 390, "total_steps": 476, "loss": 1.793134880065918, "lr": 4.266653803752299e-08, "epoch": 0.8197582764056752, "percentage": 81.93, "elapsed_time": "0:51:23", "remaining_time": "0:11:20"}
{"current_steps": 400, "total_steps": 476, "loss": 1.9492578506469727, "lr": 3.363576230940962e-08, "epoch": 0.8407777193904361, "percentage": 84.03, "elapsed_time": "0:52:40", "remaining_time": "0:10:00"}
{"current_steps": 410, "total_steps": 476, "loss": 1.8826881408691407, "lr": 2.560940644496379e-08, "epoch": 0.8617971623751971, "percentage": 86.13, "elapsed_time": "0:53:58", "remaining_time": "0:08:41"}
{"current_steps": 420, "total_steps": 476, "loss": 1.80709228515625, "lr": 1.8624730905291208e-08, "epoch": 0.882816605359958, "percentage": 88.24, "elapsed_time": "0:55:20", "remaining_time": "0:07:22"}
{"current_steps": 430, "total_steps": 476, "loss": 1.8871631622314453, "lr": 1.271416039665657e-08, "epoch": 0.9038360483447189, "percentage": 90.34, "elapsed_time": "0:56:35", "remaining_time": "0:06:03"}
{"current_steps": 440, "total_steps": 476, "loss": 1.9046966552734375, "lr": 7.905133346444464e-09, "epoch": 0.9248554913294798, "percentage": 92.44, "elapsed_time": "0:57:55", "remaining_time": "0:04:44"}
{"current_steps": 450, "total_steps": 476, "loss": 1.8698127746582032, "lr": 4.219974526741527e-09, "epoch": 0.9458749343142406, "percentage": 94.54, "elapsed_time": "0:59:13", "remaining_time": "0:03:25"}
{"current_steps": 460, "total_steps": 476, "loss": 1.9108594894409179, "lr": 1.6757914168557264e-09, "epoch": 0.9668943772990016, "percentage": 96.64, "elapsed_time": "1:00:32", "remaining_time": "0:02:06"}
{"current_steps": 470, "total_steps": 476, "loss": 1.9814664840698242, "lr": 2.843947858848228e-10, "epoch": 0.9879138202837625, "percentage": 98.74, "elapsed_time": "1:01:48", "remaining_time": "0:00:47"}
{"current_steps": 476, "total_steps": 476, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:02:36", "remaining_time": "0:00:00"}

372
trainer_state.json Normal file
View File

@@ -0,0 +1,372 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 476,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.021019442984760904,
"grad_norm": 5.53125,
"learning_rate": 3e-07,
"loss": 1.8080066680908202,
"step": 10
},
{
"epoch": 0.04203888596952181,
"grad_norm": 5.15625,
"learning_rate": 4.99907124535624e-07,
"loss": 1.9573022842407226,
"step": 20
},
{
"epoch": 0.0630583289542827,
"grad_norm": 8.125,
"learning_rate": 4.988630678996146e-07,
"loss": 1.93359317779541,
"step": 30
},
{
"epoch": 0.08407777193904362,
"grad_norm": 8.75,
"learning_rate": 4.966637232576035e-07,
"loss": 1.8890295028686523,
"step": 40
},
{
"epoch": 0.10509721492380451,
"grad_norm": 7.375,
"learning_rate": 4.933193005475595e-07,
"loss": 1.8508934020996093,
"step": 50
},
{
"epoch": 0.1261166579085654,
"grad_norm": 5.21875,
"learning_rate": 4.888453254618907e-07,
"loss": 1.8927783966064453,
"step": 60
},
{
"epoch": 0.14713610089332632,
"grad_norm": 5.125,
"learning_rate": 4.832625673730847e-07,
"loss": 1.8637098312377929,
"step": 70
},
{
"epoch": 0.16815554387808723,
"grad_norm": 11.0625,
"learning_rate": 4.765969429168031e-07,
"loss": 1.983097457885742,
"step": 80
},
{
"epoch": 0.18917498686284814,
"grad_norm": 5.21875,
"learning_rate": 4.6887939568002264e-07,
"loss": 1.919074821472168,
"step": 90
},
{
"epoch": 0.21019442984760903,
"grad_norm": 5.9375,
"learning_rate": 4.6014575255274225e-07,
"loss": 1.8743148803710938,
"step": 100
},
{
"epoch": 0.23121387283236994,
"grad_norm": 9.4375,
"learning_rate": 4.504365574101089e-07,
"loss": 1.9480220794677734,
"step": 110
},
{
"epoch": 0.2522333158171308,
"grad_norm": 6.1875,
"learning_rate": 4.3979688289705503e-07,
"loss": 1.8002925872802735,
"step": 120
},
{
"epoch": 0.27325275880189176,
"grad_norm": 7.125,
"learning_rate": 4.282761211891912e-07,
"loss": 1.915324592590332,
"step": 130
},
{
"epoch": 0.29427220178665264,
"grad_norm": 12.625,
"learning_rate": 4.1592775470129854e-07,
"loss": 1.985239601135254,
"step": 140
},
{
"epoch": 0.3152916447714136,
"grad_norm": 7.28125,
"learning_rate": 4.028091078078516e-07,
"loss": 1.8037527084350586,
"step": 150
},
{
"epoch": 0.33631108775617446,
"grad_norm": 6.46875,
"learning_rate": 3.8898108072815116e-07,
"loss": 1.8475725173950195,
"step": 160
},
{
"epoch": 0.35733053074093535,
"grad_norm": 9.375,
"learning_rate": 3.7450786681144234e-07,
"loss": 1.8196781158447266,
"step": 170
},
{
"epoch": 0.3783499737256963,
"grad_norm": 6.90625,
"learning_rate": 3.5945665453445397e-07,
"loss": 1.813003921508789,
"step": 180
},
{
"epoch": 0.39936941671045717,
"grad_norm": 5.8125,
"learning_rate": 3.4389731559476716e-07,
"loss": 1.8163671493530273,
"step": 190
},
{
"epoch": 0.42038885969521805,
"grad_norm": 9.5,
"learning_rate": 3.279020805479643e-07,
"loss": 1.853123092651367,
"step": 200
},
{
"epoch": 0.441408302679979,
"grad_norm": 6.59375,
"learning_rate": 3.1154520349433735e-07,
"loss": 1.8787429809570313,
"step": 210
},
{
"epoch": 0.4624277456647399,
"grad_norm": 5.875,
"learning_rate": 2.9490261737176715e-07,
"loss": 1.9475088119506836,
"step": 220
},
{
"epoch": 0.4834471886495008,
"grad_norm": 12.75,
"learning_rate": 2.780515814549969e-07,
"loss": 1.9444992065429687,
"step": 230
},
{
"epoch": 0.5044666316342616,
"grad_norm": 4.96875,
"learning_rate": 2.6107032269769897e-07,
"loss": 1.7953880310058594,
"step": 240
},
{
"epoch": 0.5254860746190226,
"grad_norm": 7.53125,
"learning_rate": 2.440376725823213e-07,
"loss": 1.9037723541259766,
"step": 250
},
{
"epoch": 0.5465055176037835,
"grad_norm": 9.5625,
"learning_rate": 2.2703270116355234e-07,
"loss": 1.9526327133178711,
"step": 260
},
{
"epoch": 0.5675249605885444,
"grad_norm": 8.875,
"learning_rate": 2.101343500042697e-07,
"loss": 1.9550243377685548,
"step": 270
},
{
"epoch": 0.5885444035733053,
"grad_norm": 11.75,
"learning_rate": 1.934210657079821e-07,
"loss": 1.896200180053711,
"step": 280
},
{
"epoch": 0.6095638465580662,
"grad_norm": 4.53125,
"learning_rate": 1.7697043574900388e-07,
"loss": 1.9687370300292968,
"step": 290
},
{
"epoch": 0.6305832895428272,
"grad_norm": 4.90625,
"learning_rate": 1.608588282909325e-07,
"loss": 1.7474214553833007,
"step": 300
},
{
"epoch": 0.651602732527588,
"grad_norm": 12.1875,
"learning_rate": 1.4516103766548969e-07,
"loss": 1.952895164489746,
"step": 310
},
{
"epoch": 0.6726221755123489,
"grad_norm": 7.875,
"learning_rate": 1.2994993715750356e-07,
"loss": 2.002369689941406,
"step": 320
},
{
"epoch": 0.6936416184971098,
"grad_norm": 4.75,
"learning_rate": 1.1529614070789883e-07,
"loss": 1.9351655960083007,
"step": 330
},
{
"epoch": 0.7146610614818707,
"grad_norm": 5.9375,
"learning_rate": 1.0126767510515585e-07,
"loss": 1.9994436264038087,
"step": 340
},
{
"epoch": 0.7356805044666316,
"grad_norm": 6.875,
"learning_rate": 8.792966418701511e-08,
"loss": 2.0275642395019533,
"step": 350
},
{
"epoch": 0.7566999474513926,
"grad_norm": 5.28125,
"learning_rate": 7.534402651844351e-08,
"loss": 1.9153682708740234,
"step": 360
},
{
"epoch": 0.7777193904361535,
"grad_norm": 4.71875,
"learning_rate": 6.356918794932362e-08,
"loss": 1.9506032943725586,
"step": 370
},
{
"epoch": 0.7987388334209143,
"grad_norm": 22.125,
"learning_rate": 5.265981038624656e-08,
"loss": 1.9164735794067382,
"step": 380
},
{
"epoch": 0.8197582764056752,
"grad_norm": 10.0625,
"learning_rate": 4.266653803752299e-08,
"loss": 1.793134880065918,
"step": 390
},
{
"epoch": 0.8407777193904361,
"grad_norm": 5.6875,
"learning_rate": 3.363576230940962e-08,
"loss": 1.9492578506469727,
"step": 400
},
{
"epoch": 0.8617971623751971,
"grad_norm": 4.96875,
"learning_rate": 2.560940644496379e-08,
"loss": 1.8826881408691407,
"step": 410
},
{
"epoch": 0.882816605359958,
"grad_norm": 18.875,
"learning_rate": 1.8624730905291208e-08,
"loss": 1.80709228515625,
"step": 420
},
{
"epoch": 0.9038360483447189,
"grad_norm": 10.875,
"learning_rate": 1.271416039665657e-08,
"loss": 1.8871631622314453,
"step": 430
},
{
"epoch": 0.9248554913294798,
"grad_norm": 12.25,
"learning_rate": 7.905133346444464e-09,
"loss": 1.9046966552734375,
"step": 440
},
{
"epoch": 0.9458749343142406,
"grad_norm": 9.0,
"learning_rate": 4.219974526741527e-09,
"loss": 1.8698127746582032,
"step": 450
},
{
"epoch": 0.9668943772990016,
"grad_norm": 10.3125,
"learning_rate": 1.6757914168557264e-09,
"loss": 1.9108594894409179,
"step": 460
},
{
"epoch": 0.9879138202837625,
"grad_norm": 11.1875,
"learning_rate": 2.843947858848228e-10,
"loss": 1.9814664840698242,
"step": 470
},
{
"epoch": 1.0,
"step": 476,
"total_flos": 2.27705175303125e+17,
"train_loss": 1.8975331122133912,
"train_runtime": 3756.1832,
"train_samples_per_second": 0.507,
"train_steps_per_second": 0.127
}
],
"logging_steps": 10,
"max_steps": 476,
"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": 2.27705175303125e+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 sha256:5e252b984848dc9bfcf318b05fe4f092a70a863026183fb517ac0a8f42bf7a45
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 55 KiB