lldois/v42_v29_user_evolution_guard_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/v42_v29_user_evolution_guard_lr5e7_ep10
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-19 01:58:10 +08:00
commit df882f613a
17 changed files with 3229 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: v42_v29_user_evolution_guard_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. -->
# v42_v29_user_evolution_guard_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_v42_user_evolution 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: 202607192
- 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": 3.143810179830989e+17,
"train_loss": 1.9069785443783536,
"train_runtime": 5405.3324,
"train_samples_per_second": 0.483,
"train_steps_per_second": 0.121
}

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": "v42_v29_user_evolution_guard_lr5e7_ep10",
"base": "/home/ll/llm4rec/experiments/outputs/v29_v19_user_world_guard_lr8e7_ep018",
"dataset": "v42_user_evolution",
"dataset_manifest": {
"name": "v42_user_evolution",
"path": "/home/ll/llm4rec/experiments/data/v42_user_evolution.jsonl",
"records": 75000,
"bytes": 381438256,
"sha256": "d4dcc5f06f9e32b0d781e29d2b6965ffc8683fc9b63e1d2533322535cfd73fde",
"requested_components": {
"general": 26000,
"r0": 6000,
"r3_think": 12000,
"r3_direct": 12000,
"old_rec": 5000,
"old_user": 9000,
"old_item": 5000
},
"groups": {
"general": 26000,
"r3": 24000,
"old_user": 9000,
"old_item": 5000,
"old_rec": 5000,
"r0": 6000
},
"variants": {
"official_general_cot": 13010,
"profile_video/video_cot": 3756,
"official_general_direct": 12990,
"original_competition": 8591,
"profile_goods_cot": 2593,
"profile_goods_direct": 2680,
"user_array_json_strict": 1530,
"item_no_think_direct_final": 883,
"rec_no_think_direct_final": 2473,
"profile_video/video_direct": 3677,
"sid_to_caption_cot": 1487,
"caption_to_sid_direct": 3020,
"profile_live_cot": 2827,
"user_strict_logic": 1274,
"user_strict_array": 1537,
"sid_to_caption_direct": 1493,
"profile_live_direct": 2850,
"profile_video/ad_direct": 2793,
"profile_video/ad_cot": 2824,
"item_short_think": 865,
"user_logic_json_strict": 1260,
"user_extra_no_think_logic": 587
},
"routes": {
"think": 33240,
"no_think": 41760
},
"target_leakage": 0,
"seed": 202607159
},
"learning_rate": "5.0e-7",
"epochs": 1.0,
"stages": null,
"note": "Protects structured user extraction/evolution formats while adding real-holdout R3 and general 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/v42_v29_user_evolution_guard_lr5e7_ep10.yaml"
],
"reproduce": "/home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/python /home/ll/llm4rec/experiments/run_v34_v43.py --single v42_v29_user_evolution_guard_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:ee2d14b407067abc7bbd66a60019472aaa976bf31bda9ddeb2b8a4fd25bfaeb9
size 1602902832

3
runs/Jul15_05-36-53_ubuntu-System-Product-Name/events.out.tfevents.1784065013.ubuntu-System-Product-Name.1385064.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b9533e5971fd3539d92a32bbaaf774f8752e26ffbc9d2a89507de45d715d5dac
size 19983

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
}

2291
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": 3.143810179830989e+17,
"train_loss": 1.9069785443783536,
"train_runtime": 5405.3324,
"train_samples_per_second": 0.483,
"train_steps_per_second": 0.121
}

66
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,66 @@
{"current_steps": 10, "total_steps": 653, "loss": 1.8881567001342774, "lr": 2.25e-07, "epoch": 0.015319800842589047, "percentage": 1.53, "elapsed_time": "0:01:21", "remaining_time": "1:27:47"}
{"current_steps": 20, "total_steps": 653, "loss": 2.0835521697998045, "lr": 4.7499999999999995e-07, "epoch": 0.030639601685178094, "percentage": 3.06, "elapsed_time": "0:02:42", "remaining_time": "1:25:46"}
{"current_steps": 30, "total_steps": 653, "loss": 1.9390586853027343, "lr": 4.997506466835169e-07, "epoch": 0.04595940252776714, "percentage": 4.59, "elapsed_time": "0:04:02", "remaining_time": "1:24:03"}
{"current_steps": 40, "total_steps": 653, "loss": 1.9236089706420898, "lr": 4.988893231902699e-07, "epoch": 0.06127920337035619, "percentage": 6.13, "elapsed_time": "0:05:24", "remaining_time": "1:22:55"}
{"current_steps": 50, "total_steps": 653, "loss": 1.716681671142578, "lr": 4.974150717193653e-07, "epoch": 0.07659900421294523, "percentage": 7.66, "elapsed_time": "0:06:49", "remaining_time": "1:22:20"}
{"current_steps": 60, "total_steps": 653, "loss": 1.9944971084594727, "lr": 4.953315228402511e-07, "epoch": 0.09191880505553428, "percentage": 9.19, "elapsed_time": "0:08:09", "remaining_time": "1:20:33"}
{"current_steps": 70, "total_steps": 653, "loss": 1.9377096176147461, "lr": 4.926438076103162e-07, "epoch": 0.10723860589812333, "percentage": 10.72, "elapsed_time": "0:09:31", "remaining_time": "1:19:20"}
{"current_steps": 80, "total_steps": 653, "loss": 2.0413049697875976, "lr": 4.893585449388785e-07, "epoch": 0.12255840674071238, "percentage": 12.25, "elapsed_time": "0:10:52", "remaining_time": "1:17:56"}
{"current_steps": 90, "total_steps": 653, "loss": 1.8533470153808593, "lr": 4.854838252871096e-07, "epoch": 0.1378782075833014, "percentage": 13.78, "elapsed_time": "0:12:14", "remaining_time": "1:16:36"}
{"current_steps": 100, "total_steps": 653, "loss": 1.641725730895996, "lr": 4.810291907440381e-07, "epoch": 0.15319800842589046, "percentage": 15.31, "elapsed_time": "0:13:40", "remaining_time": "1:15:37"}
{"current_steps": 110, "total_steps": 653, "loss": 1.8656742095947265, "lr": 4.7600561152769787e-07, "epoch": 0.1685178092684795, "percentage": 16.85, "elapsed_time": "0:15:03", "remaining_time": "1:14:21"}
{"current_steps": 120, "total_steps": 653, "loss": 1.9227891921997071, "lr": 4.704254589692902e-07, "epoch": 0.18383761011106856, "percentage": 18.38, "elapsed_time": "0:16:26", "remaining_time": "1:13:02"}
{"current_steps": 130, "total_steps": 653, "loss": 1.9448070526123047, "lr": 4.6430247504689124e-07, "epoch": 0.1991574109536576, "percentage": 19.91, "elapsed_time": "0:17:44", "remaining_time": "1:11:21"}
{"current_steps": 140, "total_steps": 653, "loss": 1.8896455764770508, "lr": 4.576517385437314e-07, "epoch": 0.21447721179624665, "percentage": 21.44, "elapsed_time": "0:19:06", "remaining_time": "1:10:02"}
{"current_steps": 150, "total_steps": 653, "loss": 1.874186897277832, "lr": 4.504896279143888e-07, "epoch": 0.2297970126388357, "percentage": 22.97, "elapsed_time": "0:20:31", "remaining_time": "1:08:48"}
{"current_steps": 160, "total_steps": 653, "loss": 1.7868270874023438, "lr": 4.4283378095034244e-07, "epoch": 0.24511681348142475, "percentage": 24.5, "elapsed_time": "0:21:56", "remaining_time": "1:07:34"}
{"current_steps": 170, "total_steps": 653, "loss": 2.1282052993774414, "lr": 4.347030513442168e-07, "epoch": 0.26043661432401377, "percentage": 26.03, "elapsed_time": "0:23:21", "remaining_time": "1:06:20"}
{"current_steps": 180, "total_steps": 653, "loss": 1.8293880462646483, "lr": 4.261174622596835e-07, "epoch": 0.2757564151666028, "percentage": 27.57, "elapsed_time": "0:24:45", "remaining_time": "1:05:03"}
{"current_steps": 190, "total_steps": 653, "loss": 2.0162126541137697, "lr": 4.170981570213621e-07, "epoch": 0.29107621600919187, "percentage": 29.1, "elapsed_time": "0:26:08", "remaining_time": "1:03:41"}
{"current_steps": 200, "total_steps": 653, "loss": 1.958943748474121, "lr": 4.076673470461537e-07, "epoch": 0.3063960168517809, "percentage": 30.63, "elapsed_time": "0:27:31", "remaining_time": "1:02:19"}
{"current_steps": 210, "total_steps": 653, "loss": 1.844751739501953, "lr": 3.978482571442339e-07, "epoch": 0.32171581769436997, "percentage": 32.16, "elapsed_time": "0:28:55", "remaining_time": "1:01:00"}
{"current_steps": 220, "total_steps": 653, "loss": 1.926915740966797, "lr": 3.876650683244093e-07, "epoch": 0.337035618536959, "percentage": 33.69, "elapsed_time": "0:30:20", "remaining_time": "0:59:42"}
{"current_steps": 230, "total_steps": 653, "loss": 1.620564079284668, "lr": 3.771428582446907e-07, "epoch": 0.35235541937954806, "percentage": 35.22, "elapsed_time": "0:31:44", "remaining_time": "0:58:22"}
{"current_steps": 240, "total_steps": 653, "loss": 1.9423002243041991, "lr": 3.663075394547285e-07, "epoch": 0.3676752202221371, "percentage": 36.75, "elapsed_time": "0:33:05", "remaining_time": "0:56:57"}
{"current_steps": 250, "total_steps": 653, "loss": 1.8801351547241212, "lr": 3.551857955822014e-07, "epoch": 0.38299502106472616, "percentage": 38.28, "elapsed_time": "0:34:29", "remaining_time": "0:55:36"}
{"current_steps": 260, "total_steps": 653, "loss": 1.84176025390625, "lr": 3.43805015620307e-07, "epoch": 0.3983148219073152, "percentage": 39.82, "elapsed_time": "0:35:52", "remaining_time": "0:54:14"}
{"current_steps": 270, "total_steps": 653, "loss": 1.9039052963256835, "lr": 3.3219322647818214e-07, "epoch": 0.41363462274990426, "percentage": 41.35, "elapsed_time": "0:37:13", "remaining_time": "0:52:47"}
{"current_steps": 280, "total_steps": 653, "loss": 2.1408451080322264, "lr": 3.2037902396035824e-07, "epoch": 0.4289544235924933, "percentage": 42.88, "elapsed_time": "0:38:34", "remaining_time": "0:51:22"}
{"current_steps": 290, "total_steps": 653, "loss": 1.8292259216308593, "lr": 3.0839150234522397e-07, "epoch": 0.44427422443508235, "percentage": 44.41, "elapsed_time": "0:39:57", "remaining_time": "0:50:01"}
{"current_steps": 300, "total_steps": 653, "loss": 1.767644500732422, "lr": 2.9626018273592076e-07, "epoch": 0.4595940252776714, "percentage": 45.94, "elapsed_time": "0:41:20", "remaining_time": "0:48:39"}
{"current_steps": 310, "total_steps": 653, "loss": 2.0017181396484376, "lr": 2.840149403601165e-07, "epoch": 0.47491382612026045, "percentage": 47.47, "elapsed_time": "0:42:45", "remaining_time": "0:47:18"}
{"current_steps": 320, "total_steps": 653, "loss": 1.9466903686523438, "lr": 2.716859309976941e-07, "epoch": 0.4902336269628495, "percentage": 49.0, "elapsed_time": "0:44:08", "remaining_time": "0:45:56"}
{"current_steps": 330, "total_steps": 653, "loss": 1.7483896255493163, "lr": 2.59303516717537e-07, "epoch": 0.5055534278054385, "percentage": 50.54, "elapsed_time": "0:45:32", "remaining_time": "0:44:34"}
{"current_steps": 340, "total_steps": 653, "loss": 1.6642837524414062, "lr": 2.4689819110629636e-07, "epoch": 0.5208732286480275, "percentage": 52.07, "elapsed_time": "0:46:57", "remaining_time": "0:43:14"}
{"current_steps": 350, "total_steps": 653, "loss": 1.879330825805664, "lr": 2.3450050417327588e-07, "epoch": 0.5361930294906166, "percentage": 53.6, "elapsed_time": "0:48:19", "remaining_time": "0:41:49"}
{"current_steps": 360, "total_steps": 653, "loss": 1.950868797302246, "lr": 2.2214098711636751e-07, "epoch": 0.5515128303332056, "percentage": 55.13, "elapsed_time": "0:49:40", "remaining_time": "0:40:25"}
{"current_steps": 370, "total_steps": 653, "loss": 1.9813783645629883, "lr": 2.0985007713431238e-07, "epoch": 0.5668326311757947, "percentage": 56.66, "elapsed_time": "0:51:04", "remaining_time": "0:39:03"}
{"current_steps": 380, "total_steps": 653, "loss": 1.7870925903320312, "lr": 1.9765804247044975e-07, "epoch": 0.5821524320183837, "percentage": 58.19, "elapsed_time": "0:52:30", "remaining_time": "0:37:43"}
{"current_steps": 390, "total_steps": 653, "loss": 1.9392311096191406, "lr": 1.855949078725442e-07, "epoch": 0.5974722328609728, "percentage": 59.72, "elapsed_time": "0:53:53", "remaining_time": "0:36:20"}
{"current_steps": 400, "total_steps": 653, "loss": 1.9289718627929688, "lr": 1.7369038065225742e-07, "epoch": 0.6127920337035618, "percentage": 61.26, "elapsed_time": "0:55:17", "remaining_time": "0:34:58"}
{"current_steps": 410, "total_steps": 653, "loss": 1.8457157135009765, "lr": 1.619737775263556e-07, "epoch": 0.6281118345461509, "percentage": 62.79, "elapsed_time": "0:56:38", "remaining_time": "0:33:34"}
{"current_steps": 420, "total_steps": 653, "loss": 1.831606674194336, "lr": 1.5047395241981604e-07, "epoch": 0.6434316353887399, "percentage": 64.32, "elapsed_time": "0:58:00", "remaining_time": "0:32:10"}
{"current_steps": 430, "total_steps": 653, "loss": 1.941716194152832, "lr": 1.3921922540862904e-07, "epoch": 0.658751436231329, "percentage": 65.85, "elapsed_time": "0:59:22", "remaining_time": "0:30:47"}
{"current_steps": 440, "total_steps": 653, "loss": 1.8431577682495117, "lr": 1.2823731297728534e-07, "epoch": 0.674071237073918, "percentage": 67.38, "elapsed_time": "1:00:47", "remaining_time": "0:29:25"}
{"current_steps": 450, "total_steps": 653, "loss": 2.0610845565795897, "lr": 1.175552597626985e-07, "epoch": 0.6893910379165071, "percentage": 68.91, "elapsed_time": "1:02:07", "remaining_time": "0:28:01"}
{"current_steps": 460, "total_steps": 653, "loss": 1.9088102340698243, "lr": 1.0719937195265555e-07, "epoch": 0.7047108387590961, "percentage": 70.44, "elapsed_time": "1:03:31", "remaining_time": "0:26:39"}
{"current_steps": 470, "total_steps": 653, "loss": 1.9430780410766602, "lr": 9.719515250281121e-08, "epoch": 0.7200306396016852, "percentage": 71.98, "elapsed_time": "1:04:55", "remaining_time": "0:25:16"}
{"current_steps": 480, "total_steps": 653, "loss": 1.8786405563354491, "lr": 8.756723833176374e-08, "epoch": 0.7353504404442742, "percentage": 73.51, "elapsed_time": "1:06:21", "remaining_time": "0:23:54"}
{"current_steps": 490, "total_steps": 653, "loss": 1.9569564819335938, "lr": 7.833933964887984e-08, "epoch": 0.7506702412868632, "percentage": 75.04, "elapsed_time": "1:07:44", "remaining_time": "0:22:31"}
{"current_steps": 500, "total_steps": 653, "loss": 2.0343820571899416, "lr": 6.95341815642815e-08, "epoch": 0.7659900421294523, "percentage": 76.57, "elapsed_time": "1:09:07", "remaining_time": "0:21:09"}
{"current_steps": 510, "total_steps": 653, "loss": 2.027488136291504, "lr": 6.117344812479152e-08, "epoch": 0.7813098429720413, "percentage": 78.1, "elapsed_time": "1:10:31", "remaining_time": "0:19:46"}
{"current_steps": 520, "total_steps": 653, "loss": 1.718618392944336, "lr": 5.3277728913655644e-08, "epoch": 0.7966296438146304, "percentage": 79.63, "elapsed_time": "1:11:54", "remaining_time": "0:18:23"}
{"current_steps": 530, "total_steps": 653, "loss": 1.826439666748047, "lr": 4.586646834554864e-08, "epoch": 0.8119494446572194, "percentage": 81.16, "elapsed_time": "1:13:17", "remaining_time": "0:17:00"}
{"current_steps": 540, "total_steps": 653, "loss": 1.8948688507080078, "lr": 3.895791778173288e-08, "epoch": 0.8272692454998085, "percentage": 82.7, "elapsed_time": "1:14:39", "remaining_time": "0:15:37"}
{"current_steps": 550, "total_steps": 653, "loss": 1.9602611541748047, "lr": 3.256909058329335e-08, "epoch": 0.8425890463423975, "percentage": 84.23, "elapsed_time": "1:15:59", "remaining_time": "0:14:13"}
{"current_steps": 560, "total_steps": 653, "loss": 1.9529207229614258, "lr": 2.671572021313695e-08, "epoch": 0.8579088471849866, "percentage": 85.76, "elapsed_time": "1:17:25", "remaining_time": "0:12:51"}
{"current_steps": 570, "total_steps": 653, "loss": 1.9812084197998048, "lr": 2.1412221489936795e-08, "epoch": 0.8732286480275756, "percentage": 87.29, "elapsed_time": "1:18:47", "remaining_time": "0:11:28"}
{"current_steps": 580, "total_steps": 653, "loss": 2.084661865234375, "lr": 1.6671655089439186e-08, "epoch": 0.8885484488701647, "percentage": 88.82, "elapsed_time": "1:20:05", "remaining_time": "0:10:04"}
{"current_steps": 590, "total_steps": 653, "loss": 1.9481664657592774, "lr": 1.250569538055471e-08, "epoch": 0.9038682497127537, "percentage": 90.35, "elapsed_time": "1:21:27", "remaining_time": "0:08:41"}
{"current_steps": 600, "total_steps": 653, "loss": 1.9511104583740235, "lr": 8.924601675441207e-09, "epoch": 0.9191880505553428, "percentage": 91.88, "elapsed_time": "1:22:49", "remaining_time": "0:07:18"}
{"current_steps": 610, "total_steps": 653, "loss": 2.0635440826416014, "lr": 5.937192964380555e-09, "epoch": 0.9345078513979318, "percentage": 93.42, "elapsed_time": "1:24:11", "remaining_time": "0:05:56"}
{"current_steps": 620, "total_steps": 653, "loss": 1.669927978515625, "lr": 3.550826197667889e-09, "epoch": 0.9498276522405209, "percentage": 94.95, "elapsed_time": "1:25:35", "remaining_time": "0:04:33"}
{"current_steps": 630, "total_steps": 653, "loss": 1.881399917602539, "lr": 1.7713781679977447e-09, "epoch": 0.9651474530831099, "percentage": 96.48, "elapsed_time": "1:27:00", "remaining_time": "0:03:10"}
{"current_steps": 640, "total_steps": 653, "loss": 1.9342432022094727, "lr": 6.032310379642803e-10, "epoch": 0.980467253925699, "percentage": 98.01, "elapsed_time": "1:28:22", "remaining_time": "0:01:47"}
{"current_steps": 650, "total_steps": 653, "loss": 1.9714859008789063, "lr": 4.926154831655371e-11, "epoch": 0.995787054768288, "percentage": 99.54, "elapsed_time": "1:29:44", "remaining_time": "0:00:24"}
{"current_steps": 653, "total_steps": 653, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:30:05", "remaining_time": "0:00:00"}

498
trainer_state.json Normal file
View File

@@ -0,0 +1,498 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 653,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.015319800842589047,
"grad_norm": 4.5,
"learning_rate": 2.25e-07,
"loss": 1.8881567001342774,
"step": 10
},
{
"epoch": 0.030639601685178094,
"grad_norm": 12.9375,
"learning_rate": 4.7499999999999995e-07,
"loss": 2.0835521697998045,
"step": 20
},
{
"epoch": 0.04595940252776714,
"grad_norm": 10.0,
"learning_rate": 4.997506466835169e-07,
"loss": 1.9390586853027343,
"step": 30
},
{
"epoch": 0.06127920337035619,
"grad_norm": 11.6875,
"learning_rate": 4.988893231902699e-07,
"loss": 1.9236089706420898,
"step": 40
},
{
"epoch": 0.07659900421294523,
"grad_norm": 13.375,
"learning_rate": 4.974150717193653e-07,
"loss": 1.716681671142578,
"step": 50
},
{
"epoch": 0.09191880505553428,
"grad_norm": 7.65625,
"learning_rate": 4.953315228402511e-07,
"loss": 1.9944971084594727,
"step": 60
},
{
"epoch": 0.10723860589812333,
"grad_norm": 9.25,
"learning_rate": 4.926438076103162e-07,
"loss": 1.9377096176147461,
"step": 70
},
{
"epoch": 0.12255840674071238,
"grad_norm": 12.0625,
"learning_rate": 4.893585449388785e-07,
"loss": 2.0413049697875976,
"step": 80
},
{
"epoch": 0.1378782075833014,
"grad_norm": 6.03125,
"learning_rate": 4.854838252871096e-07,
"loss": 1.8533470153808593,
"step": 90
},
{
"epoch": 0.15319800842589046,
"grad_norm": 4.5625,
"learning_rate": 4.810291907440381e-07,
"loss": 1.641725730895996,
"step": 100
},
{
"epoch": 0.1685178092684795,
"grad_norm": 5.84375,
"learning_rate": 4.7600561152769787e-07,
"loss": 1.8656742095947265,
"step": 110
},
{
"epoch": 0.18383761011106856,
"grad_norm": 11.0,
"learning_rate": 4.704254589692902e-07,
"loss": 1.9227891921997071,
"step": 120
},
{
"epoch": 0.1991574109536576,
"grad_norm": 7.03125,
"learning_rate": 4.6430247504689124e-07,
"loss": 1.9448070526123047,
"step": 130
},
{
"epoch": 0.21447721179624665,
"grad_norm": 10.9375,
"learning_rate": 4.576517385437314e-07,
"loss": 1.8896455764770508,
"step": 140
},
{
"epoch": 0.2297970126388357,
"grad_norm": 9.9375,
"learning_rate": 4.504896279143888e-07,
"loss": 1.874186897277832,
"step": 150
},
{
"epoch": 0.24511681348142475,
"grad_norm": 6.09375,
"learning_rate": 4.4283378095034244e-07,
"loss": 1.7868270874023438,
"step": 160
},
{
"epoch": 0.26043661432401377,
"grad_norm": 5.125,
"learning_rate": 4.347030513442168e-07,
"loss": 2.1282052993774414,
"step": 170
},
{
"epoch": 0.2757564151666028,
"grad_norm": 5.9375,
"learning_rate": 4.261174622596835e-07,
"loss": 1.8293880462646483,
"step": 180
},
{
"epoch": 0.29107621600919187,
"grad_norm": 12.3125,
"learning_rate": 4.170981570213621e-07,
"loss": 2.0162126541137697,
"step": 190
},
{
"epoch": 0.3063960168517809,
"grad_norm": 17.25,
"learning_rate": 4.076673470461537e-07,
"loss": 1.958943748474121,
"step": 200
},
{
"epoch": 0.32171581769436997,
"grad_norm": 12.9375,
"learning_rate": 3.978482571442339e-07,
"loss": 1.844751739501953,
"step": 210
},
{
"epoch": 0.337035618536959,
"grad_norm": 5.9375,
"learning_rate": 3.876650683244093e-07,
"loss": 1.926915740966797,
"step": 220
},
{
"epoch": 0.35235541937954806,
"grad_norm": 6.0,
"learning_rate": 3.771428582446907e-07,
"loss": 1.620564079284668,
"step": 230
},
{
"epoch": 0.3676752202221371,
"grad_norm": 4.78125,
"learning_rate": 3.663075394547285e-07,
"loss": 1.9423002243041991,
"step": 240
},
{
"epoch": 0.38299502106472616,
"grad_norm": 6.1875,
"learning_rate": 3.551857955822014e-07,
"loss": 1.8801351547241212,
"step": 250
},
{
"epoch": 0.3983148219073152,
"grad_norm": 5.75,
"learning_rate": 3.43805015620307e-07,
"loss": 1.84176025390625,
"step": 260
},
{
"epoch": 0.41363462274990426,
"grad_norm": 9.9375,
"learning_rate": 3.3219322647818214e-07,
"loss": 1.9039052963256835,
"step": 270
},
{
"epoch": 0.4289544235924933,
"grad_norm": 7.71875,
"learning_rate": 3.2037902396035824e-07,
"loss": 2.1408451080322264,
"step": 280
},
{
"epoch": 0.44427422443508235,
"grad_norm": 14.3125,
"learning_rate": 3.0839150234522397e-07,
"loss": 1.8292259216308593,
"step": 290
},
{
"epoch": 0.4595940252776714,
"grad_norm": 13.75,
"learning_rate": 2.9626018273592076e-07,
"loss": 1.767644500732422,
"step": 300
},
{
"epoch": 0.47491382612026045,
"grad_norm": 8.5625,
"learning_rate": 2.840149403601165e-07,
"loss": 2.0017181396484376,
"step": 310
},
{
"epoch": 0.4902336269628495,
"grad_norm": 5.5625,
"learning_rate": 2.716859309976941e-07,
"loss": 1.9466903686523438,
"step": 320
},
{
"epoch": 0.5055534278054385,
"grad_norm": 12.375,
"learning_rate": 2.59303516717537e-07,
"loss": 1.7483896255493163,
"step": 330
},
{
"epoch": 0.5208732286480275,
"grad_norm": 5.6875,
"learning_rate": 2.4689819110629636e-07,
"loss": 1.6642837524414062,
"step": 340
},
{
"epoch": 0.5361930294906166,
"grad_norm": 7.53125,
"learning_rate": 2.3450050417327588e-07,
"loss": 1.879330825805664,
"step": 350
},
{
"epoch": 0.5515128303332056,
"grad_norm": 11.125,
"learning_rate": 2.2214098711636751e-07,
"loss": 1.950868797302246,
"step": 360
},
{
"epoch": 0.5668326311757947,
"grad_norm": 9.375,
"learning_rate": 2.0985007713431238e-07,
"loss": 1.9813783645629883,
"step": 370
},
{
"epoch": 0.5821524320183837,
"grad_norm": 6.96875,
"learning_rate": 1.9765804247044975e-07,
"loss": 1.7870925903320312,
"step": 380
},
{
"epoch": 0.5974722328609728,
"grad_norm": 17.5,
"learning_rate": 1.855949078725442e-07,
"loss": 1.9392311096191406,
"step": 390
},
{
"epoch": 0.6127920337035618,
"grad_norm": 13.375,
"learning_rate": 1.7369038065225742e-07,
"loss": 1.9289718627929688,
"step": 400
},
{
"epoch": 0.6281118345461509,
"grad_norm": 8.4375,
"learning_rate": 1.619737775263556e-07,
"loss": 1.8457157135009765,
"step": 410
},
{
"epoch": 0.6434316353887399,
"grad_norm": 5.96875,
"learning_rate": 1.5047395241981604e-07,
"loss": 1.831606674194336,
"step": 420
},
{
"epoch": 0.658751436231329,
"grad_norm": 8.375,
"learning_rate": 1.3921922540862904e-07,
"loss": 1.941716194152832,
"step": 430
},
{
"epoch": 0.674071237073918,
"grad_norm": 5.1875,
"learning_rate": 1.2823731297728534e-07,
"loss": 1.8431577682495117,
"step": 440
},
{
"epoch": 0.6893910379165071,
"grad_norm": 7.90625,
"learning_rate": 1.175552597626985e-07,
"loss": 2.0610845565795897,
"step": 450
},
{
"epoch": 0.7047108387590961,
"grad_norm": 4.375,
"learning_rate": 1.0719937195265555e-07,
"loss": 1.9088102340698243,
"step": 460
},
{
"epoch": 0.7200306396016852,
"grad_norm": 8.8125,
"learning_rate": 9.719515250281121e-08,
"loss": 1.9430780410766602,
"step": 470
},
{
"epoch": 0.7353504404442742,
"grad_norm": 4.6875,
"learning_rate": 8.756723833176374e-08,
"loss": 1.8786405563354491,
"step": 480
},
{
"epoch": 0.7506702412868632,
"grad_norm": 12.0625,
"learning_rate": 7.833933964887984e-08,
"loss": 1.9569564819335938,
"step": 490
},
{
"epoch": 0.7659900421294523,
"grad_norm": 23.375,
"learning_rate": 6.95341815642815e-08,
"loss": 2.0343820571899416,
"step": 500
},
{
"epoch": 0.7813098429720413,
"grad_norm": 7.84375,
"learning_rate": 6.117344812479152e-08,
"loss": 2.027488136291504,
"step": 510
},
{
"epoch": 0.7966296438146304,
"grad_norm": 10.9375,
"learning_rate": 5.3277728913655644e-08,
"loss": 1.718618392944336,
"step": 520
},
{
"epoch": 0.8119494446572194,
"grad_norm": 7.28125,
"learning_rate": 4.586646834554864e-08,
"loss": 1.826439666748047,
"step": 530
},
{
"epoch": 0.8272692454998085,
"grad_norm": 16.125,
"learning_rate": 3.895791778173288e-08,
"loss": 1.8948688507080078,
"step": 540
},
{
"epoch": 0.8425890463423975,
"grad_norm": 6.4375,
"learning_rate": 3.256909058329335e-08,
"loss": 1.9602611541748047,
"step": 550
},
{
"epoch": 0.8579088471849866,
"grad_norm": 8.1875,
"learning_rate": 2.671572021313695e-08,
"loss": 1.9529207229614258,
"step": 560
},
{
"epoch": 0.8732286480275756,
"grad_norm": 6.78125,
"learning_rate": 2.1412221489936795e-08,
"loss": 1.9812084197998048,
"step": 570
},
{
"epoch": 0.8885484488701647,
"grad_norm": 9.5625,
"learning_rate": 1.6671655089439186e-08,
"loss": 2.084661865234375,
"step": 580
},
{
"epoch": 0.9038682497127537,
"grad_norm": 4.9375,
"learning_rate": 1.250569538055471e-08,
"loss": 1.9481664657592774,
"step": 590
},
{
"epoch": 0.9191880505553428,
"grad_norm": 4.53125,
"learning_rate": 8.924601675441207e-09,
"loss": 1.9511104583740235,
"step": 600
},
{
"epoch": 0.9345078513979318,
"grad_norm": 17.0,
"learning_rate": 5.937192964380555e-09,
"loss": 2.0635440826416014,
"step": 610
},
{
"epoch": 0.9498276522405209,
"grad_norm": 17.625,
"learning_rate": 3.550826197667889e-09,
"loss": 1.669927978515625,
"step": 620
},
{
"epoch": 0.9651474530831099,
"grad_norm": 4.09375,
"learning_rate": 1.7713781679977447e-09,
"loss": 1.881399917602539,
"step": 630
},
{
"epoch": 0.980467253925699,
"grad_norm": 5.03125,
"learning_rate": 6.032310379642803e-10,
"loss": 1.9342432022094727,
"step": 640
},
{
"epoch": 0.995787054768288,
"grad_norm": 6.15625,
"learning_rate": 4.926154831655371e-11,
"loss": 1.9714859008789063,
"step": 650
},
{
"epoch": 1.0,
"step": 653,
"total_flos": 3.143810179830989e+17,
"train_loss": 1.9069785443783536,
"train_runtime": 5405.3324,
"train_samples_per_second": 0.483,
"train_steps_per_second": 0.121
}
],
"logging_steps": 10,
"max_steps": 653,
"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": 3.143810179830989e+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 sha256:1d2e340f313a1b4b9bbf912191aafdc85797546cce596e62465b095876ef07dd
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 56 KiB