lldois/v36_v29_general_guard_lr4e7_ep12
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/v36_v29_general_guard_lr4e7_ep12
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-19 04:10:09 +08:00
commit c48b1a9c13
17 changed files with 3187 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: v36_v29_general_guard_lr4e7_ep12
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. -->
# v36_v29_general_guard_lr4e7_ep12
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_v36_general_guard 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: 4e-07
- train_batch_size: 1
- eval_batch_size: 8
- seed: 202607186
- 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: 1.2
### 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": 1.2000926354793886,
"total_flos": 3.10173216276566e+17,
"train_loss": 1.8869445338661288,
"train_runtime": 5074.5206,
"train_samples_per_second": 0.511,
"train_steps_per_second": 0.128
}

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": "v36_v29_general_guard_lr4e7_ep12",
"base": "/home/ll/llm4rec/experiments/outputs/v29_v19_user_world_guard_lr8e7_ep018",
"dataset": "v36_general_guard",
"dataset_manifest": {
"name": "v36_general_guard",
"path": "/home/ll/llm4rec/experiments/data/v36_general_guard.jsonl",
"records": 80000,
"bytes": 322603609,
"sha256": "8aa50ef29b36de4764d1255110a3d1eba6c62e3eaa22636cd92f351cb59d72c2",
"requested_components": {
"general": 36000,
"r0": 12000,
"r3_think": 7000,
"r3_direct": 10000,
"old_rec": 6000,
"old_user": 4500,
"old_item": 4500
},
"groups": {
"general": 36000,
"r0": 12000,
"r3": 17000,
"old_item": 4500,
"old_user": 4500,
"old_rec": 6000
},
"variants": {
"official_general_cot": 17998,
"caption_to_sid_direct": 5982,
"profile_video/ad_cot": 1620,
"profile_video/video_cot": 2159,
"original_competition": 7355,
"profile_goods_direct": 2199,
"official_general_direct": 18002,
"profile_live_direct": 2330,
"profile_video/ad_direct": 2329,
"user_strict_logic": 645,
"sid_to_caption_cot": 2964,
"rec_no_think_direct_final": 2970,
"profile_video/video_direct": 3142,
"profile_live_cot": 1623,
"user_strict_array": 775,
"user_array_json_strict": 710,
"item_short_think": 779,
"sid_to_caption_direct": 3054,
"profile_goods_cot": 1598,
"user_extra_no_think_logic": 294,
"item_no_think_direct_final": 819,
"user_logic_json_strict": 653
},
"routes": {
"think": 34086,
"no_think": 45914
},
"target_leakage": 0,
"seed": 202607153
},
"learning_rate": "4.0e-7",
"epochs": 1.2,
"stages": null,
"note": "General-heavy replay explicitly targeting the world-score forgetting seen in v31-v33.",
"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/v36_v29_general_guard_lr4e7_ep12.yaml"
],
"reproduce": "/home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/python /home/ll/llm4rec/experiments/run_v34_v43.py --single v36_v29_general_guard_lr4e7_ep12 --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 sha256:9bb0c47a381d89c19f0b9c266db9edac5df3bca3295f22da541b841e4382cafd
size 1602902832

3
runs/Jul15_02-02-45_ubuntu-System-Product-Name/events.out.tfevents.1784052165.ubuntu-System-Product-Name.1381619.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:35213f676413ac8aaee1d1e8fcce0cc81b49c6cf87d9543501316ac5165eaf29
size 19758

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
}

2257
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": 1.2000926354793886,
"total_flos": 3.10173216276566e+17,
"train_loss": 1.8869445338661288,
"train_runtime": 5074.5206,
"train_samples_per_second": 0.511,
"train_steps_per_second": 0.128
}

65
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,65 @@
{"current_steps": 10, "total_steps": 648, "loss": 1.9585561752319336, "lr": 1.8e-07, "epoch": 0.018527095877721167, "percentage": 1.54, "elapsed_time": "0:01:17", "remaining_time": "1:22:05"}
{"current_steps": 20, "total_steps": 648, "loss": 1.8574798583984375, "lr": 3.7999999999999996e-07, "epoch": 0.037054191755442334, "percentage": 3.09, "elapsed_time": "0:02:32", "remaining_time": "1:19:59"}
{"current_steps": 30, "total_steps": 648, "loss": 1.789466094970703, "lr": 3.997973287649674e-07, "epoch": 0.0555812876331635, "percentage": 4.63, "elapsed_time": "0:03:51", "remaining_time": "1:19:22"}
{"current_steps": 40, "total_steps": 648, "loss": 1.6971963882446288, "lr": 3.9909726417418306e-07, "epoch": 0.07410838351088467, "percentage": 6.17, "elapsed_time": "0:05:11", "remaining_time": "1:18:50"}
{"current_steps": 50, "total_steps": 648, "loss": 1.9821432113647461, "lr": 3.978990552681652e-07, "epoch": 0.09263547938860583, "percentage": 7.72, "elapsed_time": "0:06:26", "remaining_time": "1:17:04"}
{"current_steps": 60, "total_steps": 648, "loss": 1.8834493637084961, "lr": 3.962056999834122e-07, "epoch": 0.111162575266327, "percentage": 9.26, "elapsed_time": "0:07:45", "remaining_time": "1:15:58"}
{"current_steps": 70, "total_steps": 648, "loss": 1.901871681213379, "lr": 3.9402143512002393e-07, "epoch": 0.12968967114404817, "percentage": 10.8, "elapsed_time": "0:09:04", "remaining_time": "1:14:53"}
{"current_steps": 80, "total_steps": 648, "loss": 1.947560691833496, "lr": 3.913517257411654e-07, "epoch": 0.14821676702176934, "percentage": 12.35, "elapsed_time": "0:10:20", "remaining_time": "1:13:25"}
{"current_steps": 90, "total_steps": 648, "loss": 1.8572700500488282, "lr": 3.8820325149939695e-07, "epoch": 0.1667438628994905, "percentage": 13.89, "elapsed_time": "0:11:39", "remaining_time": "1:12:15"}
{"current_steps": 100, "total_steps": 648, "loss": 1.9525575637817383, "lr": 3.8458388992408446e-07, "epoch": 0.18527095877721167, "percentage": 15.43, "elapsed_time": "0:12:59", "remaining_time": "1:11:10"}
{"current_steps": 110, "total_steps": 648, "loss": 1.9637582778930665, "lr": 3.805026967117037e-07, "epoch": 0.20379805465493284, "percentage": 16.98, "elapsed_time": "0:14:15", "remaining_time": "1:09:45"}
{"current_steps": 120, "total_steps": 648, "loss": 1.8187477111816406, "lr": 3.7596988306835307e-07, "epoch": 0.222325150532654, "percentage": 18.52, "elapsed_time": "0:15:36", "remaining_time": "1:08:42"}
{"current_steps": 130, "total_steps": 648, "loss": 1.8701536178588867, "lr": 3.709967901611643e-07, "epoch": 0.24085224641037517, "percentage": 20.06, "elapsed_time": "0:16:56", "remaining_time": "1:07:29"}
{"current_steps": 140, "total_steps": 648, "loss": 1.9594388961791993, "lr": 3.6559586074253323e-07, "epoch": 0.25937934228809634, "percentage": 21.6, "elapsed_time": "0:18:13", "remaining_time": "1:06:07"}
{"current_steps": 150, "total_steps": 648, "loss": 2.0100639343261717, "lr": 3.597806080181688e-07, "epoch": 0.2779064381658175, "percentage": 23.15, "elapsed_time": "0:19:29", "remaining_time": "1:04:43"}
{"current_steps": 160, "total_steps": 648, "loss": 1.7690265655517579, "lr": 3.535655818368514e-07, "epoch": 0.29643353404353867, "percentage": 24.69, "elapsed_time": "0:20:50", "remaining_time": "1:03:35"}
{"current_steps": 170, "total_steps": 648, "loss": 1.901205825805664, "lr": 3.469663322864944e-07, "epoch": 0.31496062992125984, "percentage": 26.23, "elapsed_time": "0:22:10", "remaining_time": "1:02:21"}
{"current_steps": 180, "total_steps": 648, "loss": 1.8674629211425782, "lr": 3.399993707875936e-07, "epoch": 0.333487725798981, "percentage": 27.78, "elapsed_time": "0:23:26", "remaining_time": "1:00:56"}
{"current_steps": 190, "total_steps": 648, "loss": 1.9903881072998046, "lr": 3.326821287814071e-07, "epoch": 0.35201482167670217, "percentage": 29.32, "elapsed_time": "0:24:45", "remaining_time": "0:59:41"}
{"current_steps": 200, "total_steps": 648, "loss": 1.8886430740356446, "lr": 3.250329141162305e-07, "epoch": 0.37054191755442334, "percentage": 30.86, "elapsed_time": "0:26:05", "remaining_time": "0:58:27"}
{"current_steps": 210, "total_steps": 648, "loss": 1.9833818435668946, "lr": 3.1707086524088837e-07, "epoch": 0.3890690134321445, "percentage": 32.41, "elapsed_time": "0:27:23", "remaining_time": "0:57:08"}
{"current_steps": 220, "total_steps": 648, "loss": 1.9257682800292968, "lr": 3.088159033200498e-07, "epoch": 0.4075961093098657, "percentage": 33.95, "elapsed_time": "0:28:42", "remaining_time": "0:55:50"}
{"current_steps": 230, "total_steps": 648, "loss": 1.705978012084961, "lr": 3.002886823911797e-07, "epoch": 0.42612320518758684, "percentage": 35.49, "elapsed_time": "0:30:02", "remaining_time": "0:54:35"}
{"current_steps": 240, "total_steps": 648, "loss": 1.9222623825073242, "lr": 2.9151053768782854e-07, "epoch": 0.444650301065308, "percentage": 37.04, "elapsed_time": "0:31:17", "remaining_time": "0:53:11"}
{"current_steps": 250, "total_steps": 648, "loss": 1.9167638778686524, "lr": 2.8250343225856163e-07, "epoch": 0.4631773969430292, "percentage": 38.58, "elapsed_time": "0:32:33", "remaining_time": "0:51:50"}
{"current_steps": 260, "total_steps": 648, "loss": 1.908761978149414, "lr": 2.7328990201508475e-07, "epoch": 0.48170449282075034, "percentage": 40.12, "elapsed_time": "0:33:53", "remaining_time": "0:50:34"}
{"current_steps": 270, "total_steps": 648, "loss": 1.913759994506836, "lr": 2.6389299934705824e-07, "epoch": 0.5002315886984715, "percentage": 41.67, "elapsed_time": "0:35:14", "remaining_time": "0:49:19"}
{"current_steps": 280, "total_steps": 648, "loss": 1.9161806106567383, "lr": 2.5433623544467476e-07, "epoch": 0.5187586845761927, "percentage": 43.21, "elapsed_time": "0:36:31", "remaining_time": "0:48:00"}
{"current_steps": 290, "total_steps": 648, "loss": 1.785818099975586, "lr": 2.446435214733126e-07, "epoch": 0.5372857804539138, "percentage": 44.75, "elapsed_time": "0:37:50", "remaining_time": "0:46:42"}
{"current_steps": 300, "total_steps": 648, "loss": 1.9147356033325196, "lr": 2.3483910874744376e-07, "epoch": 0.555812876331635, "percentage": 46.3, "elapsed_time": "0:39:07", "remaining_time": "0:45:23"}
{"current_steps": 310, "total_steps": 648, "loss": 1.8954235076904298, "lr": 2.2494752805348493e-07, "epoch": 0.5743399722093562, "percentage": 47.84, "elapsed_time": "0:40:25", "remaining_time": "0:44:04"}
{"current_steps": 320, "total_steps": 648, "loss": 1.862330436706543, "lr": 2.14993528273405e-07, "epoch": 0.5928670680870773, "percentage": 49.38, "elapsed_time": "0:41:44", "remaining_time": "0:42:47"}
{"current_steps": 330, "total_steps": 648, "loss": 1.8166675567626953, "lr": 2.0500201446265426e-07, "epoch": 0.6113941639647985, "percentage": 50.93, "elapsed_time": "0:43:03", "remaining_time": "0:41:29"}
{"current_steps": 340, "total_steps": 648, "loss": 1.86541748046875, "lr": 1.949979855373457e-07, "epoch": 0.6299212598425197, "percentage": 52.47, "elapsed_time": "0:44:21", "remaining_time": "0:40:10"}
{"current_steps": 350, "total_steps": 648, "loss": 1.9255918502807616, "lr": 1.8500647172659497e-07, "epoch": 0.6484483557202408, "percentage": 54.01, "elapsed_time": "0:45:36", "remaining_time": "0:38:49"}
{"current_steps": 360, "total_steps": 648, "loss": 1.8364168167114259, "lr": 1.7505247194651502e-07, "epoch": 0.666975451597962, "percentage": 55.56, "elapsed_time": "0:46:51", "remaining_time": "0:37:29"}
{"current_steps": 370, "total_steps": 648, "loss": 1.9211824417114258, "lr": 1.651608912525562e-07, "epoch": 0.6855025474756832, "percentage": 57.1, "elapsed_time": "0:48:07", "remaining_time": "0:36:09"}
{"current_steps": 380, "total_steps": 648, "loss": 1.8987268447875976, "lr": 1.553564785266874e-07, "epoch": 0.7040296433534043, "percentage": 58.64, "elapsed_time": "0:49:27", "remaining_time": "0:34:53"}
{"current_steps": 390, "total_steps": 648, "loss": 1.8674749374389648, "lr": 1.4566376455532522e-07, "epoch": 0.7225567392311255, "percentage": 60.19, "elapsed_time": "0:50:45", "remaining_time": "0:33:34"}
{"current_steps": 400, "total_steps": 648, "loss": 1.8906829833984375, "lr": 1.361070006529418e-07, "epoch": 0.7410838351088467, "percentage": 61.73, "elapsed_time": "0:52:04", "remaining_time": "0:32:17"}
{"current_steps": 410, "total_steps": 648, "loss": 1.8476547241210937, "lr": 1.267100979849152e-07, "epoch": 0.7596109309865678, "percentage": 63.27, "elapsed_time": "0:53:23", "remaining_time": "0:30:59"}
{"current_steps": 420, "total_steps": 648, "loss": 1.9425527572631835, "lr": 1.1749656774143837e-07, "epoch": 0.778138026864289, "percentage": 64.81, "elapsed_time": "0:54:40", "remaining_time": "0:29:40"}
{"current_steps": 430, "total_steps": 648, "loss": 1.7886039733886718, "lr": 1.0848946231217149e-07, "epoch": 0.7966651227420102, "percentage": 66.36, "elapsed_time": "0:55:54", "remaining_time": "0:28:20"}
{"current_steps": 440, "total_steps": 648, "loss": 1.9002357482910157, "lr": 9.971131760882032e-08, "epoch": 0.8151922186197313, "percentage": 67.9, "elapsed_time": "0:57:14", "remaining_time": "0:27:03"}
{"current_steps": 450, "total_steps": 648, "loss": 2.0303293228149415, "lr": 9.118409667995014e-08, "epoch": 0.8337193144974525, "percentage": 69.44, "elapsed_time": "0:58:34", "remaining_time": "0:25:46"}
{"current_steps": 460, "total_steps": 648, "loss": 1.8214141845703125, "lr": 8.292913475911168e-08, "epoch": 0.8522464103751737, "percentage": 70.99, "elapsed_time": "0:59:53", "remaining_time": "0:24:28"}
{"current_steps": 470, "total_steps": 648, "loss": 1.7804437637329102, "lr": 7.496708588376946e-08, "epoch": 0.8707735062528948, "percentage": 72.53, "elapsed_time": "1:01:14", "remaining_time": "0:23:11"}
{"current_steps": 480, "total_steps": 648, "loss": 1.807050895690918, "lr": 6.731787121859294e-08, "epoch": 0.889300602130616, "percentage": 74.07, "elapsed_time": "1:02:35", "remaining_time": "0:21:54"}
{"current_steps": 490, "total_steps": 648, "loss": 1.8698265075683593, "lr": 6.00006292124064e-08, "epoch": 0.9078276980083372, "percentage": 75.62, "elapsed_time": "1:03:53", "remaining_time": "0:20:36"}
{"current_steps": 500, "total_steps": 648, "loss": 1.8879680633544922, "lr": 5.303366771350557e-08, "epoch": 0.9263547938860583, "percentage": 77.16, "elapsed_time": "1:05:12", "remaining_time": "0:19:17"}
{"current_steps": 510, "total_steps": 648, "loss": 1.8387239456176758, "lr": 4.6434418163148616e-08, "epoch": 0.9448818897637795, "percentage": 78.7, "elapsed_time": "1:06:30", "remaining_time": "0:17:59"}
{"current_steps": 520, "total_steps": 648, "loss": 1.7679691314697266, "lr": 4.021939198183113e-08, "epoch": 0.9634089856415007, "percentage": 80.25, "elapsed_time": "1:07:50", "remaining_time": "0:16:41"}
{"current_steps": 530, "total_steps": 648, "loss": 1.9303434371948243, "lr": 3.440413925746679e-08, "epoch": 0.9819360815192218, "percentage": 81.79, "elapsed_time": "1:09:08", "remaining_time": "0:15:23"}
{"current_steps": 540, "total_steps": 648, "loss": 2.0060049057006837, "lr": 2.900320983883575e-08, "epoch": 1.0, "percentage": 83.33, "elapsed_time": "1:10:24", "remaining_time": "0:14:04"}
{"current_steps": 550, "total_steps": 648, "loss": 1.8175098419189453, "lr": 2.4030116931646914e-08, "epoch": 1.018527095877721, "percentage": 84.88, "elapsed_time": "1:11:46", "remaining_time": "0:12:47"}
{"current_steps": 560, "total_steps": 648, "loss": 1.8821565628051757, "lr": 1.9497303288296263e-08, "epoch": 1.0370541917554423, "percentage": 86.42, "elapsed_time": "1:13:04", "remaining_time": "0:11:29"}
{"current_steps": 570, "total_steps": 648, "loss": 1.9253089904785157, "lr": 1.54161100759155e-08, "epoch": 1.0555812876331636, "percentage": 87.96, "elapsed_time": "1:14:23", "remaining_time": "0:10:10"}
{"current_steps": 580, "total_steps": 648, "loss": 1.918222999572754, "lr": 1.1796748500603015e-08, "epoch": 1.0741083835108847, "percentage": 89.51, "elapsed_time": "1:15:43", "remaining_time": "0:08:52"}
{"current_steps": 590, "total_steps": 648, "loss": 1.950904655456543, "lr": 8.648274258834565e-09, "epoch": 1.0926354793886057, "percentage": 91.05, "elapsed_time": "1:17:03", "remaining_time": "0:07:34"}
{"current_steps": 600, "total_steps": 648, "loss": 1.9175649642944337, "lr": 5.978564879976078e-09, "epoch": 1.111162575266327, "percentage": 92.59, "elapsed_time": "1:18:21", "remaining_time": "0:06:16"}
{"current_steps": 610, "total_steps": 648, "loss": 1.9034099578857422, "lr": 3.79430001658787e-09, "epoch": 1.1296896711440483, "percentage": 94.14, "elapsed_time": "1:19:38", "remaining_time": "0:04:57"}
{"current_steps": 620, "total_steps": 648, "loss": 1.9379833221435547, "lr": 2.100944731834797e-09, "epoch": 1.1482167670217693, "percentage": 95.68, "elapsed_time": "1:20:55", "remaining_time": "0:03:39"}
{"current_steps": 630, "total_steps": 648, "loss": 1.955449676513672, "lr": 9.027358258169026e-10, "epoch": 1.1667438628994904, "percentage": 97.22, "elapsed_time": "1:22:12", "remaining_time": "0:02:20"}
{"current_steps": 640, "total_steps": 648, "loss": 1.7997220993041991, "lr": 2.0267123503259208e-10, "epoch": 1.1852709587772117, "percentage": 98.77, "elapsed_time": "1:23:31", "remaining_time": "0:01:02"}
{"current_steps": 648, "total_steps": 648, "epoch": 1.2000926354793886, "percentage": 100.0, "elapsed_time": "1:24:34", "remaining_time": "0:00:00"}

491
trainer_state.json Normal file
View File

@@ -0,0 +1,491 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.2000926354793886,
"eval_steps": 500,
"global_step": 648,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.018527095877721167,
"grad_norm": 9.9375,
"learning_rate": 1.8e-07,
"loss": 1.9585561752319336,
"step": 10
},
{
"epoch": 0.037054191755442334,
"grad_norm": 6.625,
"learning_rate": 3.7999999999999996e-07,
"loss": 1.8574798583984375,
"step": 20
},
{
"epoch": 0.0555812876331635,
"grad_norm": 6.09375,
"learning_rate": 3.997973287649674e-07,
"loss": 1.789466094970703,
"step": 30
},
{
"epoch": 0.07410838351088467,
"grad_norm": 10.9375,
"learning_rate": 3.9909726417418306e-07,
"loss": 1.6971963882446288,
"step": 40
},
{
"epoch": 0.09263547938860583,
"grad_norm": 5.375,
"learning_rate": 3.978990552681652e-07,
"loss": 1.9821432113647461,
"step": 50
},
{
"epoch": 0.111162575266327,
"grad_norm": 4.28125,
"learning_rate": 3.962056999834122e-07,
"loss": 1.8834493637084961,
"step": 60
},
{
"epoch": 0.12968967114404817,
"grad_norm": 6.3125,
"learning_rate": 3.9402143512002393e-07,
"loss": 1.901871681213379,
"step": 70
},
{
"epoch": 0.14821676702176934,
"grad_norm": 4.6875,
"learning_rate": 3.913517257411654e-07,
"loss": 1.947560691833496,
"step": 80
},
{
"epoch": 0.1667438628994905,
"grad_norm": 7.6875,
"learning_rate": 3.8820325149939695e-07,
"loss": 1.8572700500488282,
"step": 90
},
{
"epoch": 0.18527095877721167,
"grad_norm": 7.625,
"learning_rate": 3.8458388992408446e-07,
"loss": 1.9525575637817383,
"step": 100
},
{
"epoch": 0.20379805465493284,
"grad_norm": 7.5,
"learning_rate": 3.805026967117037e-07,
"loss": 1.9637582778930665,
"step": 110
},
{
"epoch": 0.222325150532654,
"grad_norm": 4.78125,
"learning_rate": 3.7596988306835307e-07,
"loss": 1.8187477111816406,
"step": 120
},
{
"epoch": 0.24085224641037517,
"grad_norm": 7.09375,
"learning_rate": 3.709967901611643e-07,
"loss": 1.8701536178588867,
"step": 130
},
{
"epoch": 0.25937934228809634,
"grad_norm": 5.0,
"learning_rate": 3.6559586074253323e-07,
"loss": 1.9594388961791993,
"step": 140
},
{
"epoch": 0.2779064381658175,
"grad_norm": 11.0,
"learning_rate": 3.597806080181688e-07,
"loss": 2.0100639343261717,
"step": 150
},
{
"epoch": 0.29643353404353867,
"grad_norm": 9.0,
"learning_rate": 3.535655818368514e-07,
"loss": 1.7690265655517579,
"step": 160
},
{
"epoch": 0.31496062992125984,
"grad_norm": 7.0,
"learning_rate": 3.469663322864944e-07,
"loss": 1.901205825805664,
"step": 170
},
{
"epoch": 0.333487725798981,
"grad_norm": 7.3125,
"learning_rate": 3.399993707875936e-07,
"loss": 1.8674629211425782,
"step": 180
},
{
"epoch": 0.35201482167670217,
"grad_norm": 9.375,
"learning_rate": 3.326821287814071e-07,
"loss": 1.9903881072998046,
"step": 190
},
{
"epoch": 0.37054191755442334,
"grad_norm": 13.3125,
"learning_rate": 3.250329141162305e-07,
"loss": 1.8886430740356446,
"step": 200
},
{
"epoch": 0.3890690134321445,
"grad_norm": 6.4375,
"learning_rate": 3.1707086524088837e-07,
"loss": 1.9833818435668946,
"step": 210
},
{
"epoch": 0.4075961093098657,
"grad_norm": 8.25,
"learning_rate": 3.088159033200498e-07,
"loss": 1.9257682800292968,
"step": 220
},
{
"epoch": 0.42612320518758684,
"grad_norm": 7.65625,
"learning_rate": 3.002886823911797e-07,
"loss": 1.705978012084961,
"step": 230
},
{
"epoch": 0.444650301065308,
"grad_norm": 9.75,
"learning_rate": 2.9151053768782854e-07,
"loss": 1.9222623825073242,
"step": 240
},
{
"epoch": 0.4631773969430292,
"grad_norm": 5.25,
"learning_rate": 2.8250343225856163e-07,
"loss": 1.9167638778686524,
"step": 250
},
{
"epoch": 0.48170449282075034,
"grad_norm": 14.25,
"learning_rate": 2.7328990201508475e-07,
"loss": 1.908761978149414,
"step": 260
},
{
"epoch": 0.5002315886984715,
"grad_norm": 4.71875,
"learning_rate": 2.6389299934705824e-07,
"loss": 1.913759994506836,
"step": 270
},
{
"epoch": 0.5187586845761927,
"grad_norm": 5.875,
"learning_rate": 2.5433623544467476e-07,
"loss": 1.9161806106567383,
"step": 280
},
{
"epoch": 0.5372857804539138,
"grad_norm": 4.28125,
"learning_rate": 2.446435214733126e-07,
"loss": 1.785818099975586,
"step": 290
},
{
"epoch": 0.555812876331635,
"grad_norm": 4.9375,
"learning_rate": 2.3483910874744376e-07,
"loss": 1.9147356033325196,
"step": 300
},
{
"epoch": 0.5743399722093562,
"grad_norm": 5.125,
"learning_rate": 2.2494752805348493e-07,
"loss": 1.8954235076904298,
"step": 310
},
{
"epoch": 0.5928670680870773,
"grad_norm": 8.4375,
"learning_rate": 2.14993528273405e-07,
"loss": 1.862330436706543,
"step": 320
},
{
"epoch": 0.6113941639647985,
"grad_norm": 7.15625,
"learning_rate": 2.0500201446265426e-07,
"loss": 1.8166675567626953,
"step": 330
},
{
"epoch": 0.6299212598425197,
"grad_norm": 5.78125,
"learning_rate": 1.949979855373457e-07,
"loss": 1.86541748046875,
"step": 340
},
{
"epoch": 0.6484483557202408,
"grad_norm": 5.625,
"learning_rate": 1.8500647172659497e-07,
"loss": 1.9255918502807616,
"step": 350
},
{
"epoch": 0.666975451597962,
"grad_norm": 5.71875,
"learning_rate": 1.7505247194651502e-07,
"loss": 1.8364168167114259,
"step": 360
},
{
"epoch": 0.6855025474756832,
"grad_norm": 5.53125,
"learning_rate": 1.651608912525562e-07,
"loss": 1.9211824417114258,
"step": 370
},
{
"epoch": 0.7040296433534043,
"grad_norm": 7.25,
"learning_rate": 1.553564785266874e-07,
"loss": 1.8987268447875976,
"step": 380
},
{
"epoch": 0.7225567392311255,
"grad_norm": 20.125,
"learning_rate": 1.4566376455532522e-07,
"loss": 1.8674749374389648,
"step": 390
},
{
"epoch": 0.7410838351088467,
"grad_norm": 6.25,
"learning_rate": 1.361070006529418e-07,
"loss": 1.8906829833984375,
"step": 400
},
{
"epoch": 0.7596109309865678,
"grad_norm": 11.3125,
"learning_rate": 1.267100979849152e-07,
"loss": 1.8476547241210937,
"step": 410
},
{
"epoch": 0.778138026864289,
"grad_norm": 4.6875,
"learning_rate": 1.1749656774143837e-07,
"loss": 1.9425527572631835,
"step": 420
},
{
"epoch": 0.7966651227420102,
"grad_norm": 5.15625,
"learning_rate": 1.0848946231217149e-07,
"loss": 1.7886039733886718,
"step": 430
},
{
"epoch": 0.8151922186197313,
"grad_norm": 4.65625,
"learning_rate": 9.971131760882032e-08,
"loss": 1.9002357482910157,
"step": 440
},
{
"epoch": 0.8337193144974525,
"grad_norm": 7.8125,
"learning_rate": 9.118409667995014e-08,
"loss": 2.0303293228149415,
"step": 450
},
{
"epoch": 0.8522464103751737,
"grad_norm": 6.34375,
"learning_rate": 8.292913475911168e-08,
"loss": 1.8214141845703125,
"step": 460
},
{
"epoch": 0.8707735062528948,
"grad_norm": 4.0625,
"learning_rate": 7.496708588376946e-08,
"loss": 1.7804437637329102,
"step": 470
},
{
"epoch": 0.889300602130616,
"grad_norm": 4.65625,
"learning_rate": 6.731787121859294e-08,
"loss": 1.807050895690918,
"step": 480
},
{
"epoch": 0.9078276980083372,
"grad_norm": 6.875,
"learning_rate": 6.00006292124064e-08,
"loss": 1.8698265075683593,
"step": 490
},
{
"epoch": 0.9263547938860583,
"grad_norm": 12.9375,
"learning_rate": 5.303366771350557e-08,
"loss": 1.8879680633544922,
"step": 500
},
{
"epoch": 0.9448818897637795,
"grad_norm": 7.03125,
"learning_rate": 4.6434418163148616e-08,
"loss": 1.8387239456176758,
"step": 510
},
{
"epoch": 0.9634089856415007,
"grad_norm": 4.90625,
"learning_rate": 4.021939198183113e-08,
"loss": 1.7679691314697266,
"step": 520
},
{
"epoch": 0.9819360815192218,
"grad_norm": 10.25,
"learning_rate": 3.440413925746679e-08,
"loss": 1.9303434371948243,
"step": 530
},
{
"epoch": 1.0,
"grad_norm": 10.1875,
"learning_rate": 2.900320983883575e-08,
"loss": 2.0060049057006837,
"step": 540
},
{
"epoch": 1.018527095877721,
"grad_norm": 6.3125,
"learning_rate": 2.4030116931646914e-08,
"loss": 1.8175098419189453,
"step": 550
},
{
"epoch": 1.0370541917554423,
"grad_norm": 5.53125,
"learning_rate": 1.9497303288296263e-08,
"loss": 1.8821565628051757,
"step": 560
},
{
"epoch": 1.0555812876331636,
"grad_norm": 7.5,
"learning_rate": 1.54161100759155e-08,
"loss": 1.9253089904785157,
"step": 570
},
{
"epoch": 1.0741083835108847,
"grad_norm": 6.9375,
"learning_rate": 1.1796748500603015e-08,
"loss": 1.918222999572754,
"step": 580
},
{
"epoch": 1.0926354793886057,
"grad_norm": 5.71875,
"learning_rate": 8.648274258834565e-09,
"loss": 1.950904655456543,
"step": 590
},
{
"epoch": 1.111162575266327,
"grad_norm": 11.25,
"learning_rate": 5.978564879976078e-09,
"loss": 1.9175649642944337,
"step": 600
},
{
"epoch": 1.1296896711440483,
"grad_norm": 12.6875,
"learning_rate": 3.79430001658787e-09,
"loss": 1.9034099578857422,
"step": 610
},
{
"epoch": 1.1482167670217693,
"grad_norm": 5.0625,
"learning_rate": 2.100944731834797e-09,
"loss": 1.9379833221435547,
"step": 620
},
{
"epoch": 1.1667438628994904,
"grad_norm": 5.8125,
"learning_rate": 9.027358258169026e-10,
"loss": 1.955449676513672,
"step": 630
},
{
"epoch": 1.1852709587772117,
"grad_norm": 4.78125,
"learning_rate": 2.0267123503259208e-10,
"loss": 1.7997220993041991,
"step": 640
},
{
"epoch": 1.2000926354793886,
"step": 648,
"total_flos": 3.10173216276566e+17,
"train_loss": 1.8869445338661288,
"train_runtime": 5074.5206,
"train_samples_per_second": 0.511,
"train_steps_per_second": 0.128
}
],
"logging_steps": 10,
"max_steps": 648,
"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": 3.10173216276566e+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 sha256:6d58bd38694093ec97f676de69d5765b34ecb91d93d6435738200246738d1bb1
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 59 KiB