lldois/v39_v29_curriculum_r0_to_r3_lr6e7_ep08x2
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/v39_v29_curriculum_r0_to_r3_lr6e7_ep08x2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-19 04:21:09 +08:00
commit a403fa0226
17 changed files with 5317 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: v39_v29_curriculum_r0_to_r3_lr6e7_ep08x2
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. -->
# v39_v29_curriculum_r0_to_r3_lr6e7_ep08x2
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_v39_curriculum_r3 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: 202607191
- 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: 0.8
### 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": 0.802937576499388,
"total_flos": 1.5578264772983194e+17,
"train_loss": 2.1087728360804117,
"train_runtime": 2487.2809,
"train_samples_per_second": 0.526,
"train_steps_per_second": 0.132
}

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
}

84
experiment_recipe.json Normal file
View File

@@ -0,0 +1,84 @@
{
"created_at": "2026-07-15 00:59:15",
"name": "v39_v29_curriculum_r0_to_r3_lr6e7_ep08x2",
"base": "/home/ll/llm4rec/experiments/outputs/v29_v19_user_world_guard_lr8e7_ep018",
"dataset": "v39_curriculum_r3",
"dataset_manifest": {
"name": "v39_curriculum_r3",
"path": "/home/ll/llm4rec/experiments/data/v39_curriculum_r3.jsonl",
"records": 70000,
"bytes": 263483139,
"sha256": "fb38ffd99b1ed61bbca834a85af32e3bb557aeba6a8b05f134ab5b99c16a22da",
"requested_components": {
"general": 22000,
"r0": 6000,
"r3_think": 16000,
"r3_direct": 18000,
"old_rec": 3000,
"old_user": 2500,
"old_item": 2500
},
"groups": {
"general": 22000,
"r3": 34000,
"old_rec": 3000,
"old_user": 2500,
"r0": 6000,
"old_item": 2500
},
"variants": {
"official_general_direct": 10947,
"profile_live_direct": 4236,
"profile_video/ad_cot": 3722,
"profile_live_cot": 3715,
"original_competition": 3943,
"user_strict_logic": 357,
"profile_video/video_direct": 5603,
"caption_to_sid_direct": 2978,
"profile_video/video_cot": 4939,
"profile_goods_cot": 3624,
"official_general_cot": 11053,
"profile_video/ad_direct": 4171,
"profile_goods_direct": 3990,
"rec_no_think_direct_final": 1484,
"sid_to_caption_cot": 1530,
"sid_to_caption_direct": 1492,
"item_no_think_direct_final": 429,
"user_array_json_strict": 402,
"item_short_think": 417,
"user_logic_json_strict": 364,
"user_strict_array": 429,
"user_extra_no_think_logic": 175
},
"routes": {
"no_think": 38178,
"think": 31822
},
"target_leakage": 0,
"seed": 202607157
},
"learning_rate": "5.0e-7",
"epochs": 0.8,
"stages": [
{
"dataset": "v39_curriculum_r0",
"lr": "6.0e-7",
"epochs": 0.8
},
{
"dataset": "v39_curriculum_r3",
"lr": "5.0e-7",
"epochs": 0.8
}
],
"note": "Two-stage curriculum: 0.8 epoch R0/general alignment followed by 0.8 epoch R3/general cognition.",
"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/v39_v29_curriculum_r0_to_r3_lr6e7_ep08x2_stage1.yaml",
"/home/ll/llm4rec/experiments/configs/v39_v29_curriculum_r0_to_r3_lr6e7_ep08x2_stage2.yaml"
],
"reproduce": "/home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/python /home/ll/llm4rec/experiments/run_v34_v43.py --single v39_v29_curriculum_r0_to_r3_lr6e7_ep08x2 --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 sha256:0687b6847e3ba3f043b60de783a366d09423f9bf19cdc15815f6dd818e0268cf
size 1602902832

3
runs/Jul15_04-08-48_ubuntu-System-Product-Name/events.out.tfevents.1784059728.ubuntu-System-Product-Name.1383912.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6026fe48374d3b721987f3c83ac4c6688338814b5937192b4d0805033d527b20
size 13022

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
}

4631
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": 0.802937576499388,
"total_flos": 1.5578264772983194e+17,
"train_loss": 2.1087728360804117,
"train_runtime": 2487.2809,
"train_samples_per_second": 0.526,
"train_steps_per_second": 0.132
}

33
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,33 @@
{"current_steps": 10, "total_steps": 328, "loss": 2.0334224700927734, "lr": 4.5e-07, "epoch": 0.02447980416156671, "percentage": 3.05, "elapsed_time": "0:01:17", "remaining_time": "0:41:14"}
{"current_steps": 20, "total_steps": 328, "loss": 2.123665428161621, "lr": 4.990124606538042e-07, "epoch": 0.04895960832313342, "percentage": 6.1, "elapsed_time": "0:02:34", "remaining_time": "0:39:44"}
{"current_steps": 30, "total_steps": 328, "loss": 2.0373281478881835, "lr": 4.956087596148824e-07, "epoch": 0.07343941248470012, "percentage": 9.15, "elapsed_time": "0:03:51", "remaining_time": "0:38:17"}
{"current_steps": 40, "total_steps": 328, "loss": 2.0780839920043945, "lr": 4.898098898861766e-07, "epoch": 0.09791921664626684, "percentage": 12.2, "elapsed_time": "0:05:08", "remaining_time": "0:37:02"}
{"current_steps": 50, "total_steps": 328, "loss": 2.168250846862793, "lr": 4.816724018579583e-07, "epoch": 0.12239902080783353, "percentage": 15.24, "elapsed_time": "0:06:25", "remaining_time": "0:35:45"}
{"current_steps": 60, "total_steps": 328, "loss": 2.0774251937866213, "lr": 4.7127565205061093e-07, "epoch": 0.14687882496940025, "percentage": 18.29, "elapsed_time": "0:07:37", "remaining_time": "0:34:03"}
{"current_steps": 70, "total_steps": 328, "loss": 2.2656288146972656, "lr": 4.587210292324061e-07, "epoch": 0.17135862913096694, "percentage": 21.34, "elapsed_time": "0:08:50", "remaining_time": "0:32:34"}
{"current_steps": 80, "total_steps": 328, "loss": 1.990157699584961, "lr": 4.441309656795106e-07, "epoch": 0.19583843329253367, "percentage": 24.39, "elapsed_time": "0:10:05", "remaining_time": "0:31:17"}
{"current_steps": 90, "total_steps": 328, "loss": 2.2658514022827148, "lr": 4.2764774322038486e-07, "epoch": 0.22031823745410037, "percentage": 27.44, "elapsed_time": "0:11:20", "remaining_time": "0:29:58"}
{"current_steps": 100, "total_steps": 328, "loss": 2.0881725311279298, "lr": 4.094321057079873e-07, "epoch": 0.24479804161566707, "percentage": 30.49, "elapsed_time": "0:12:35", "remaining_time": "0:28:42"}
{"current_steps": 110, "total_steps": 328, "loss": 2.186654281616211, "lr": 3.896616914509131e-07, "epoch": 0.2692778457772338, "percentage": 33.54, "elapsed_time": "0:13:50", "remaining_time": "0:27:26"}
{"current_steps": 120, "total_steps": 328, "loss": 2.238821601867676, "lr": 3.6852930089034707e-07, "epoch": 0.2937576499388005, "percentage": 36.59, "elapsed_time": "0:15:08", "remaining_time": "0:26:13"}
{"current_steps": 130, "total_steps": 328, "loss": 2.05932559967041, "lr": 3.4624101641638926e-07, "epoch": 0.3182374541003672, "percentage": 39.63, "elapsed_time": "0:16:24", "remaining_time": "0:25:00"}
{"current_steps": 140, "total_steps": 328, "loss": 2.070750617980957, "lr": 3.2301419265924393e-07, "epoch": 0.3427172582619339, "percentage": 42.68, "elapsed_time": "0:17:41", "remaining_time": "0:23:46"}
{"current_steps": 150, "total_steps": 328, "loss": 2.12088565826416, "lr": 2.9907533685388716e-07, "epoch": 0.3671970624235006, "percentage": 45.73, "elapsed_time": "0:18:56", "remaining_time": "0:22:28"}
{"current_steps": 160, "total_steps": 328, "loss": 1.9712303161621094, "lr": 2.7465789994882794e-07, "epoch": 0.39167686658506734, "percentage": 48.78, "elapsed_time": "0:20:13", "remaining_time": "0:21:14"}
{"current_steps": 170, "total_steps": 328, "loss": 2.1383413314819335, "lr": 2.5e-07, "epoch": 0.41615667074663404, "percentage": 51.83, "elapsed_time": "0:21:29", "remaining_time": "0:19:58"}
{"current_steps": 180, "total_steps": 328, "loss": 2.009996032714844, "lr": 2.2534210005117207e-07, "epoch": 0.44063647490820074, "percentage": 54.88, "elapsed_time": "0:22:46", "remaining_time": "0:18:43"}
{"current_steps": 190, "total_steps": 328, "loss": 2.076437759399414, "lr": 2.0092466314611287e-07, "epoch": 0.46511627906976744, "percentage": 57.93, "elapsed_time": "0:24:04", "remaining_time": "0:17:29"}
{"current_steps": 200, "total_steps": 328, "loss": 2.1122467041015627, "lr": 1.7698580734075607e-07, "epoch": 0.48959608323133413, "percentage": 60.98, "elapsed_time": "0:25:20", "remaining_time": "0:16:13"}
{"current_steps": 210, "total_steps": 328, "loss": 1.956191062927246, "lr": 1.5375898358361077e-07, "epoch": 0.5140758873929009, "percentage": 64.02, "elapsed_time": "0:26:33", "remaining_time": "0:14:55"}
{"current_steps": 220, "total_steps": 328, "loss": 1.944639015197754, "lr": 1.3147069910965296e-07, "epoch": 0.5385556915544676, "percentage": 67.07, "elapsed_time": "0:27:48", "remaining_time": "0:13:38"}
{"current_steps": 230, "total_steps": 328, "loss": 2.2447561264038085, "lr": 1.1033830854908691e-07, "epoch": 0.5630354957160343, "percentage": 70.12, "elapsed_time": "0:29:01", "remaining_time": "0:12:21"}
{"current_steps": 240, "total_steps": 328, "loss": 2.1660913467407226, "lr": 9.05678942920127e-08, "epoch": 0.587515299877601, "percentage": 73.17, "elapsed_time": "0:30:16", "remaining_time": "0:11:06"}
{"current_steps": 250, "total_steps": 328, "loss": 2.3716936111450195, "lr": 7.235225677961512e-08, "epoch": 0.6119951040391677, "percentage": 76.22, "elapsed_time": "0:31:31", "remaining_time": "0:09:50"}
{"current_steps": 260, "total_steps": 328, "loss": 2.1261455535888674, "lr": 5.586903432048942e-08, "epoch": 0.6364749082007344, "percentage": 79.27, "elapsed_time": "0:32:48", "remaining_time": "0:08:34"}
{"current_steps": 270, "total_steps": 328, "loss": 2.064971923828125, "lr": 4.127897076759399e-08, "epoch": 0.6609547123623011, "percentage": 82.32, "elapsed_time": "0:34:06", "remaining_time": "0:07:19"}
{"current_steps": 280, "total_steps": 328, "loss": 2.085330009460449, "lr": 2.8724347949389048e-08, "epoch": 0.6854345165238678, "percentage": 85.37, "elapsed_time": "0:35:23", "remaining_time": "0:06:04"}
{"current_steps": 290, "total_steps": 328, "loss": 2.1130571365356445, "lr": 1.8327598142041656e-08, "epoch": 0.7099143206854345, "percentage": 88.41, "elapsed_time": "0:36:40", "remaining_time": "0:04:48"}
{"current_steps": 300, "total_steps": 328, "loss": 2.056776428222656, "lr": 1.0190110113823425e-08, "epoch": 0.7343941248470012, "percentage": 91.46, "elapsed_time": "0:37:56", "remaining_time": "0:03:32"}
{"current_steps": 310, "total_steps": 328, "loss": 2.13861141204834, "lr": 4.391240385117623e-09, "epoch": 0.758873929008568, "percentage": 94.51, "elapsed_time": "0:39:11", "remaining_time": "0:02:16"}
{"current_steps": 320, "total_steps": 328, "loss": 2.129196357727051, "lr": 9.87539346195776e-10, "epoch": 0.7833537331701347, "percentage": 97.56, "elapsed_time": "0:40:27", "remaining_time": "0:01:00"}
{"current_steps": 328, "total_steps": 328, "epoch": 0.802937576499388, "percentage": 100.0, "elapsed_time": "0:41:27", "remaining_time": "0:00:00"}

267
trainer_state.json Normal file
View File

@@ -0,0 +1,267 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.802937576499388,
"eval_steps": 500,
"global_step": 328,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02447980416156671,
"grad_norm": 6.0,
"learning_rate": 4.5e-07,
"loss": 2.0334224700927734,
"step": 10
},
{
"epoch": 0.04895960832313342,
"grad_norm": 4.9375,
"learning_rate": 4.990124606538042e-07,
"loss": 2.123665428161621,
"step": 20
},
{
"epoch": 0.07343941248470012,
"grad_norm": 13.875,
"learning_rate": 4.956087596148824e-07,
"loss": 2.0373281478881835,
"step": 30
},
{
"epoch": 0.09791921664626684,
"grad_norm": 12.3125,
"learning_rate": 4.898098898861766e-07,
"loss": 2.0780839920043945,
"step": 40
},
{
"epoch": 0.12239902080783353,
"grad_norm": 11.6875,
"learning_rate": 4.816724018579583e-07,
"loss": 2.168250846862793,
"step": 50
},
{
"epoch": 0.14687882496940025,
"grad_norm": 27.5,
"learning_rate": 4.7127565205061093e-07,
"loss": 2.0774251937866213,
"step": 60
},
{
"epoch": 0.17135862913096694,
"grad_norm": 14.6875,
"learning_rate": 4.587210292324061e-07,
"loss": 2.2656288146972656,
"step": 70
},
{
"epoch": 0.19583843329253367,
"grad_norm": 13.3125,
"learning_rate": 4.441309656795106e-07,
"loss": 1.990157699584961,
"step": 80
},
{
"epoch": 0.22031823745410037,
"grad_norm": 5.3125,
"learning_rate": 4.2764774322038486e-07,
"loss": 2.2658514022827148,
"step": 90
},
{
"epoch": 0.24479804161566707,
"grad_norm": 24.375,
"learning_rate": 4.094321057079873e-07,
"loss": 2.0881725311279298,
"step": 100
},
{
"epoch": 0.2692778457772338,
"grad_norm": 5.5625,
"learning_rate": 3.896616914509131e-07,
"loss": 2.186654281616211,
"step": 110
},
{
"epoch": 0.2937576499388005,
"grad_norm": 15.5,
"learning_rate": 3.6852930089034707e-07,
"loss": 2.238821601867676,
"step": 120
},
{
"epoch": 0.3182374541003672,
"grad_norm": 14.1875,
"learning_rate": 3.4624101641638926e-07,
"loss": 2.05932559967041,
"step": 130
},
{
"epoch": 0.3427172582619339,
"grad_norm": 10.875,
"learning_rate": 3.2301419265924393e-07,
"loss": 2.070750617980957,
"step": 140
},
{
"epoch": 0.3671970624235006,
"grad_norm": 10.75,
"learning_rate": 2.9907533685388716e-07,
"loss": 2.12088565826416,
"step": 150
},
{
"epoch": 0.39167686658506734,
"grad_norm": 5.15625,
"learning_rate": 2.7465789994882794e-07,
"loss": 1.9712303161621094,
"step": 160
},
{
"epoch": 0.41615667074663404,
"grad_norm": 9.625,
"learning_rate": 2.5e-07,
"loss": 2.1383413314819335,
"step": 170
},
{
"epoch": 0.44063647490820074,
"grad_norm": 7.34375,
"learning_rate": 2.2534210005117207e-07,
"loss": 2.009996032714844,
"step": 180
},
{
"epoch": 0.46511627906976744,
"grad_norm": 10.0,
"learning_rate": 2.0092466314611287e-07,
"loss": 2.076437759399414,
"step": 190
},
{
"epoch": 0.48959608323133413,
"grad_norm": 9.6875,
"learning_rate": 1.7698580734075607e-07,
"loss": 2.1122467041015627,
"step": 200
},
{
"epoch": 0.5140758873929009,
"grad_norm": 7.53125,
"learning_rate": 1.5375898358361077e-07,
"loss": 1.956191062927246,
"step": 210
},
{
"epoch": 0.5385556915544676,
"grad_norm": 10.3125,
"learning_rate": 1.3147069910965296e-07,
"loss": 1.944639015197754,
"step": 220
},
{
"epoch": 0.5630354957160343,
"grad_norm": 13.3125,
"learning_rate": 1.1033830854908691e-07,
"loss": 2.2447561264038085,
"step": 230
},
{
"epoch": 0.587515299877601,
"grad_norm": 11.1875,
"learning_rate": 9.05678942920127e-08,
"loss": 2.1660913467407226,
"step": 240
},
{
"epoch": 0.6119951040391677,
"grad_norm": 18.5,
"learning_rate": 7.235225677961512e-08,
"loss": 2.3716936111450195,
"step": 250
},
{
"epoch": 0.6364749082007344,
"grad_norm": 8.3125,
"learning_rate": 5.586903432048942e-08,
"loss": 2.1261455535888674,
"step": 260
},
{
"epoch": 0.6609547123623011,
"grad_norm": 8.8125,
"learning_rate": 4.127897076759399e-08,
"loss": 2.064971923828125,
"step": 270
},
{
"epoch": 0.6854345165238678,
"grad_norm": 14.5625,
"learning_rate": 2.8724347949389048e-08,
"loss": 2.085330009460449,
"step": 280
},
{
"epoch": 0.7099143206854345,
"grad_norm": 17.25,
"learning_rate": 1.8327598142041656e-08,
"loss": 2.1130571365356445,
"step": 290
},
{
"epoch": 0.7343941248470012,
"grad_norm": 10.625,
"learning_rate": 1.0190110113823425e-08,
"loss": 2.056776428222656,
"step": 300
},
{
"epoch": 0.758873929008568,
"grad_norm": 13.75,
"learning_rate": 4.391240385117623e-09,
"loss": 2.13861141204834,
"step": 310
},
{
"epoch": 0.7833537331701347,
"grad_norm": 14.8125,
"learning_rate": 9.87539346195776e-10,
"loss": 2.129196357727051,
"step": 320
},
{
"epoch": 0.802937576499388,
"step": 328,
"total_flos": 1.5578264772983194e+17,
"train_loss": 2.1087728360804117,
"train_runtime": 2487.2809,
"train_samples_per_second": 0.526,
"train_steps_per_second": 0.132
}
],
"logging_steps": 10,
"max_steps": 328,
"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": 1.5578264772983194e+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 sha256:0d157f0534fd2599e3d7295487e4330fdc7950247c986ff8da3fdf1b2b72a0cc
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 50 KiB