lldois/v38_v29_r3_aggressive_lr7e7_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/v38_v29_r3_aggressive_lr7e7_ep10
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-19 04:13:09 +08:00
commit a5812e8837
17 changed files with 3225 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: v38_v29_r3_aggressive_lr7e7_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. -->
# v38_v29_r3_aggressive_lr7e7_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_v38_r3_aggressive 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: 7e-07
- train_batch_size: 1
- eval_batch_size: 8
- seed: 202607188
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 1.0
### Training results
### Framework versions
- Transformers 5.6.0
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2

8
all_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 1.0,
"total_flos": 2.197680639479255e+17,
"train_loss": 2.143569690286467,
"train_runtime": 3558.7051,
"train_samples_per_second": 0.518,
"train_steps_per_second": 0.13
}

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": "v38_v29_r3_aggressive_lr7e7_ep10",
"base": "/home/ll/llm4rec/experiments/outputs/v29_v19_user_world_guard_lr8e7_ep018",
"dataset": "v38_r3_aggressive",
"dataset_manifest": {
"name": "v38_r3_aggressive",
"path": "/home/ll/llm4rec/experiments/data/v38_r3_aggressive.jsonl",
"records": 80000,
"bytes": 305394286,
"sha256": "1b53237ca7e35d4c0019b89966b7eec83e6945b643ddc0fe86ed057d90f7b81c",
"requested_components": {
"general": 20000,
"r0": 8000,
"r3_think": 20000,
"r3_direct": 22000,
"old_rec": 4000,
"old_user": 3000,
"old_item": 3000
},
"groups": {
"r3": 42000,
"general": 20000,
"old_item": 3000,
"old_user": 3000,
"old_rec": 4000,
"r0": 8000
},
"variants": {
"profile_goods_direct": 5026,
"profile_goods_cot": 4597,
"official_general_cot": 10049,
"profile_video/video_cot": 6131,
"profile_video/video_direct": 6741,
"original_competition": 4883,
"profile_live_direct": 5061,
"user_logic_json_strict": 411,
"official_general_direct": 9951,
"user_strict_array": 503,
"caption_to_sid_direct": 3936,
"profile_live_cot": 4541,
"profile_video/ad_direct": 5172,
"rec_no_think_direct_final": 2005,
"profile_video/ad_cot": 4731,
"sid_to_caption_cot": 2069,
"user_extra_no_think_logic": 204,
"item_short_think": 516,
"item_no_think_direct_final": 555,
"sid_to_caption_direct": 1995,
"user_array_json_strict": 514,
"user_strict_logic": 409
},
"routes": {
"no_think": 43837,
"think": 36163
},
"target_leakage": 0,
"seed": 202607155
},
"learning_rate": "7.0e-7",
"epochs": 1.0,
"stages": null,
"note": "Highest R3 share, trained on real temporal holdouts from official user profiles with target leakage blocked.",
"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/v38_v29_r3_aggressive_lr7e7_ep10.yaml"
],
"reproduce": "/home/ll/llm4rec/demo/LLaMA-Factory/.venv/bin/python /home/ll/llm4rec/experiments/run_v34_v43.py --single v38_v29_r3_aggressive_lr7e7_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 sha256:0304112cb98f02c71547e168b4f355cb192930d83890e8c1d85cf62605c0b894
size 1602902832

3
runs/Jul15_03-02-30_ubuntu-System-Product-Name/events.out.tfevents.1784055750.ubuntu-System-Product-Name.1382577.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5509c00f555f2dc5cce1d125c200662963b799533e37944910794506e462d142
size 15960

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
}

2439
train.log Normal file
View File

File diff suppressed because one or more lines are too long

8
train_results.json Normal file
View File

@@ -0,0 +1,8 @@
{
"epoch": 1.0,
"total_flos": 2.197680639479255e+17,
"train_loss": 2.143569690286467,
"train_runtime": 3558.7051,
"train_samples_per_second": 0.518,
"train_steps_per_second": 0.13
}

47
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,47 @@
{"current_steps": 10, "total_steps": 461, "loss": 2.309475326538086, "lr": 4.5000000000000003e-07, "epoch": 0.021715526601520086, "percentage": 2.17, "elapsed_time": "0:01:17", "remaining_time": "0:58:09"}
{"current_steps": 20, "total_steps": 461, "loss": 2.2500890731811523, "lr": 6.997839182620514e-07, "epoch": 0.04343105320304017, "percentage": 4.34, "elapsed_time": "0:02:36", "remaining_time": "0:57:21"}
{"current_steps": 30, "total_steps": 461, "loss": 2.348200798034668, "lr": 6.980568648741917e-07, "epoch": 0.06514657980456026, "percentage": 6.51, "elapsed_time": "0:03:52", "remaining_time": "0:55:35"}
{"current_steps": 40, "total_steps": 461, "loss": 1.9902046203613282, "lr": 6.946112854013265e-07, "epoch": 0.08686210640608034, "percentage": 8.68, "elapsed_time": "0:05:10", "remaining_time": "0:54:23"}
{"current_steps": 50, "total_steps": 461, "loss": 2.356439399719238, "lr": 6.894641923457209e-07, "epoch": 0.10857763300760044, "percentage": 10.85, "elapsed_time": "0:06:25", "remaining_time": "0:52:48"}
{"current_steps": 60, "total_steps": 461, "loss": 2.275517463684082, "lr": 6.826409994100501e-07, "epoch": 0.13029315960912052, "percentage": 13.02, "elapsed_time": "0:07:41", "remaining_time": "0:51:26"}
{"current_steps": 70, "total_steps": 461, "loss": 1.863471221923828, "lr": 6.74175396017585e-07, "epoch": 0.15200868621064062, "percentage": 15.18, "elapsed_time": "0:09:01", "remaining_time": "0:50:24"}
{"current_steps": 80, "total_steps": 461, "loss": 2.199751091003418, "lr": 6.641091809711172e-07, "epoch": 0.1737242128121607, "percentage": 17.35, "elapsed_time": "0:10:21", "remaining_time": "0:49:21"}
{"current_steps": 90, "total_steps": 461, "loss": 2.2227617263793946, "lr": 6.52492056071934e-07, "epoch": 0.19543973941368079, "percentage": 19.52, "elapsed_time": "0:11:39", "remaining_time": "0:48:04"}
{"current_steps": 100, "total_steps": 461, "loss": 2.2083740234375, "lr": 6.393813807178434e-07, "epoch": 0.21715526601520088, "percentage": 21.69, "elapsed_time": "0:12:54", "remaining_time": "0:46:34"}
{"current_steps": 110, "total_steps": 461, "loss": 2.2678974151611326, "lr": 6.248418886919186e-07, "epoch": 0.23887079261672095, "percentage": 23.86, "elapsed_time": "0:14:10", "remaining_time": "0:45:14"}
{"current_steps": 120, "total_steps": 461, "loss": 2.0732358932495116, "lr": 6.089453685403166e-07, "epoch": 0.26058631921824105, "percentage": 26.03, "elapsed_time": "0:15:29", "remaining_time": "0:44:01"}
{"current_steps": 130, "total_steps": 461, "loss": 2.0399072647094725, "lr": 5.917703091172979e-07, "epoch": 0.28230184581976114, "percentage": 28.2, "elapsed_time": "0:16:45", "remaining_time": "0:42:39"}
{"current_steps": 140, "total_steps": 461, "loss": 2.0727848052978515, "lr": 5.73401512047564e-07, "epoch": 0.30401737242128124, "percentage": 30.37, "elapsed_time": "0:18:03", "remaining_time": "0:41:23"}
{"current_steps": 150, "total_steps": 461, "loss": 2.0733610153198243, "lr": 5.539296730193784e-07, "epoch": 0.3257328990228013, "percentage": 32.54, "elapsed_time": "0:19:20", "remaining_time": "0:40:06"}
{"current_steps": 160, "total_steps": 461, "loss": 2.1352399826049804, "lr": 5.334509339758256e-07, "epoch": 0.3474484256243214, "percentage": 34.71, "elapsed_time": "0:20:37", "remaining_time": "0:38:48"}
{"current_steps": 170, "total_steps": 461, "loss": 2.003406524658203, "lr": 5.120664084152621e-07, "epoch": 0.3691639522258415, "percentage": 36.88, "elapsed_time": "0:21:54", "remaining_time": "0:37:30"}
{"current_steps": 180, "total_steps": 461, "loss": 2.21402530670166, "lr": 4.898816821447787e-07, "epoch": 0.39087947882736157, "percentage": 39.05, "elapsed_time": "0:23:13", "remaining_time": "0:36:15"}
{"current_steps": 190, "total_steps": 461, "loss": 2.0832319259643555, "lr": 4.6700629195170006e-07, "epoch": 0.41259500542888167, "percentage": 41.21, "elapsed_time": "0:24:32", "remaining_time": "0:35:00"}
{"current_steps": 200, "total_steps": 461, "loss": 2.305379295349121, "lr": 4.43553184767171e-07, "epoch": 0.43431053203040176, "percentage": 43.38, "elapsed_time": "0:25:50", "remaining_time": "0:33:42"}
{"current_steps": 210, "total_steps": 461, "loss": 2.1995058059692383, "lr": 4.1963815999220493e-07, "epoch": 0.4560260586319218, "percentage": 45.55, "elapsed_time": "0:27:06", "remaining_time": "0:32:24"}
{"current_steps": 220, "total_steps": 461, "loss": 2.07507266998291, "lr": 3.953792977397001e-07, "epoch": 0.4777415852334419, "percentage": 47.72, "elapsed_time": "0:28:22", "remaining_time": "0:31:04"}
{"current_steps": 230, "total_steps": 461, "loss": 1.987565040588379, "lr": 3.708963758154715e-07, "epoch": 0.499457111834962, "percentage": 49.89, "elapsed_time": "0:29:40", "remaining_time": "0:29:48"}
{"current_steps": 240, "total_steps": 461, "loss": 1.974489974975586, "lr": 3.463102783169471e-07, "epoch": 0.5211726384364821, "percentage": 52.06, "elapsed_time": "0:31:00", "remaining_time": "0:28:33"}
{"current_steps": 250, "total_steps": 461, "loss": 2.0915807723999023, "lr": 3.217423987695643e-07, "epoch": 0.5428881650380022, "percentage": 54.23, "elapsed_time": "0:32:14", "remaining_time": "0:27:12"}
{"current_steps": 260, "total_steps": 461, "loss": 2.112474060058594, "lr": 2.9731404074787175e-07, "epoch": 0.5646036916395223, "percentage": 56.4, "elapsed_time": "0:33:31", "remaining_time": "0:25:54"}
{"current_steps": 270, "total_steps": 461, "loss": 2.2007789611816406, "lr": 2.73145818940763e-07, "epoch": 0.5863192182410424, "percentage": 58.57, "elapsed_time": "0:34:48", "remaining_time": "0:24:37"}
{"current_steps": 280, "total_steps": 461, "loss": 2.275239181518555, "lr": 2.4935706361807427e-07, "epoch": 0.6080347448425625, "percentage": 60.74, "elapsed_time": "0:36:02", "remaining_time": "0:23:18"}
{"current_steps": 290, "total_steps": 461, "loss": 2.0178400039672852, "lr": 2.2606523143898274e-07, "epoch": 0.6297502714440825, "percentage": 62.91, "elapsed_time": "0:37:17", "remaining_time": "0:21:59"}
{"current_steps": 300, "total_steps": 461, "loss": 2.1944948196411134, "lr": 2.033853255113336e-07, "epoch": 0.6514657980456026, "percentage": 65.08, "elapsed_time": "0:38:35", "remaining_time": "0:20:42"}
{"current_steps": 310, "total_steps": 461, "loss": 2.111407661437988, "lr": 1.8142932756534272e-07, "epoch": 0.6731813246471227, "percentage": 67.25, "elapsed_time": "0:39:52", "remaining_time": "0:19:25"}
{"current_steps": 320, "total_steps": 461, "loss": 2.0520841598510744, "lr": 1.603056450453112e-07, "epoch": 0.6948968512486428, "percentage": 69.41, "elapsed_time": "0:41:08", "remaining_time": "0:18:07"}
{"current_steps": 330, "total_steps": 461, "loss": 1.9921758651733399, "lr": 1.401185758493289e-07, "epoch": 0.7166123778501629, "percentage": 71.58, "elapsed_time": "0:42:26", "remaining_time": "0:16:50"}
{"current_steps": 340, "total_steps": 461, "loss": 2.2591268539428713, "lr": 1.2096779335980598e-07, "epoch": 0.738327904451683, "percentage": 73.75, "elapsed_time": "0:43:44", "remaining_time": "0:15:33"}
{"current_steps": 350, "total_steps": 461, "loss": 2.3327383041381835, "lr": 1.0294785430748916e-07, "epoch": 0.760043431053203, "percentage": 75.92, "elapsed_time": "0:44:59", "remaining_time": "0:14:16"}
{"current_steps": 360, "total_steps": 461, "loss": 2.176487350463867, "lr": 8.6147731898877e-08, "epoch": 0.7817589576547231, "percentage": 78.09, "elapsed_time": "0:46:17", "remaining_time": "0:12:59"}
{"current_steps": 370, "total_steps": 461, "loss": 2.1322710037231447, "lr": 7.065037651220986e-08, "epoch": 0.8034744842562432, "percentage": 80.26, "elapsed_time": "0:47:32", "remaining_time": "0:11:41"}
{"current_steps": 380, "total_steps": 461, "loss": 2.1231149673461913, "lr": 5.653230613109414e-08, "epoch": 0.8251900108577633, "percentage": 82.43, "elapsed_time": "0:48:50", "remaining_time": "0:10:24"}
{"current_steps": 390, "total_steps": 461, "loss": 2.1640350341796877, "lr": 4.38632285379887e-08, "epoch": 0.8469055374592834, "percentage": 84.6, "elapsed_time": "0:50:10", "remaining_time": "0:09:08"}
{"current_steps": 400, "total_steps": 461, "loss": 2.0533117294311523, "lr": 3.27056971329667e-08, "epoch": 0.8686210640608035, "percentage": 86.77, "elapsed_time": "0:51:28", "remaining_time": "0:07:50"}
{"current_steps": 410, "total_steps": 461, "loss": 2.199868011474609, "lr": 2.3114802077145063e-08, "epoch": 0.8903365906623235, "percentage": 88.94, "elapsed_time": "0:52:44", "remaining_time": "0:06:33"}
{"current_steps": 420, "total_steps": 461, "loss": 2.2271245956420898, "lr": 1.5137898285755707e-08, "epoch": 0.9120521172638436, "percentage": 91.11, "elapsed_time": "0:54:03", "remaining_time": "0:05:16"}
{"current_steps": 430, "total_steps": 461, "loss": 2.0086801528930662, "lr": 8.814371613888839e-09, "epoch": 0.9337676438653637, "percentage": 93.28, "elapsed_time": "0:55:24", "remaining_time": "0:03:59"}
{"current_steps": 440, "total_steps": 461, "loss": 1.9937088012695312, "lr": 4.175444389363636e-09, "epoch": 0.9554831704668838, "percentage": 95.44, "elapsed_time": "0:56:44", "remaining_time": "0:02:42"}
{"current_steps": 450, "total_steps": 461, "loss": 2.1526458740234373, "lr": 1.2440212529050531e-09, "epoch": 0.9771986970684039, "percentage": 97.61, "elapsed_time": "0:57:59", "remaining_time": "0:01:25"}
{"current_steps": 460, "total_steps": 461, "loss": 2.2378005981445312, "lr": 3.4576066788472026e-11, "epoch": 0.998914223669924, "percentage": 99.78, "elapsed_time": "0:59:14", "remaining_time": "0:00:07"}
{"current_steps": 461, "total_steps": 461, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:59:18", "remaining_time": "0:00:00"}

365
trainer_state.json Normal file
View File

@@ -0,0 +1,365 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 461,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.021715526601520086,
"grad_norm": 5.0625,
"learning_rate": 4.5000000000000003e-07,
"loss": 2.309475326538086,
"step": 10
},
{
"epoch": 0.04343105320304017,
"grad_norm": 9.6875,
"learning_rate": 6.997839182620514e-07,
"loss": 2.2500890731811523,
"step": 20
},
{
"epoch": 0.06514657980456026,
"grad_norm": 7.90625,
"learning_rate": 6.980568648741917e-07,
"loss": 2.348200798034668,
"step": 30
},
{
"epoch": 0.08686210640608034,
"grad_norm": 5.34375,
"learning_rate": 6.946112854013265e-07,
"loss": 1.9902046203613282,
"step": 40
},
{
"epoch": 0.10857763300760044,
"grad_norm": 14.75,
"learning_rate": 6.894641923457209e-07,
"loss": 2.356439399719238,
"step": 50
},
{
"epoch": 0.13029315960912052,
"grad_norm": 7.25,
"learning_rate": 6.826409994100501e-07,
"loss": 2.275517463684082,
"step": 60
},
{
"epoch": 0.15200868621064062,
"grad_norm": 7.9375,
"learning_rate": 6.74175396017585e-07,
"loss": 1.863471221923828,
"step": 70
},
{
"epoch": 0.1737242128121607,
"grad_norm": 13.125,
"learning_rate": 6.641091809711172e-07,
"loss": 2.199751091003418,
"step": 80
},
{
"epoch": 0.19543973941368079,
"grad_norm": 13.75,
"learning_rate": 6.52492056071934e-07,
"loss": 2.2227617263793946,
"step": 90
},
{
"epoch": 0.21715526601520088,
"grad_norm": 7.875,
"learning_rate": 6.393813807178434e-07,
"loss": 2.2083740234375,
"step": 100
},
{
"epoch": 0.23887079261672095,
"grad_norm": 16.625,
"learning_rate": 6.248418886919186e-07,
"loss": 2.2678974151611326,
"step": 110
},
{
"epoch": 0.26058631921824105,
"grad_norm": 11.6875,
"learning_rate": 6.089453685403166e-07,
"loss": 2.0732358932495116,
"step": 120
},
{
"epoch": 0.28230184581976114,
"grad_norm": 12.9375,
"learning_rate": 5.917703091172979e-07,
"loss": 2.0399072647094725,
"step": 130
},
{
"epoch": 0.30401737242128124,
"grad_norm": 9.3125,
"learning_rate": 5.73401512047564e-07,
"loss": 2.0727848052978515,
"step": 140
},
{
"epoch": 0.3257328990228013,
"grad_norm": 24.25,
"learning_rate": 5.539296730193784e-07,
"loss": 2.0733610153198243,
"step": 150
},
{
"epoch": 0.3474484256243214,
"grad_norm": 5.0625,
"learning_rate": 5.334509339758256e-07,
"loss": 2.1352399826049804,
"step": 160
},
{
"epoch": 0.3691639522258415,
"grad_norm": 7.5,
"learning_rate": 5.120664084152621e-07,
"loss": 2.003406524658203,
"step": 170
},
{
"epoch": 0.39087947882736157,
"grad_norm": 5.875,
"learning_rate": 4.898816821447787e-07,
"loss": 2.21402530670166,
"step": 180
},
{
"epoch": 0.41259500542888167,
"grad_norm": 12.1875,
"learning_rate": 4.6700629195170006e-07,
"loss": 2.0832319259643555,
"step": 190
},
{
"epoch": 0.43431053203040176,
"grad_norm": 11.4375,
"learning_rate": 4.43553184767171e-07,
"loss": 2.305379295349121,
"step": 200
},
{
"epoch": 0.4560260586319218,
"grad_norm": 7.71875,
"learning_rate": 4.1963815999220493e-07,
"loss": 2.1995058059692383,
"step": 210
},
{
"epoch": 0.4777415852334419,
"grad_norm": 9.8125,
"learning_rate": 3.953792977397001e-07,
"loss": 2.07507266998291,
"step": 220
},
{
"epoch": 0.499457111834962,
"grad_norm": 8.625,
"learning_rate": 3.708963758154715e-07,
"loss": 1.987565040588379,
"step": 230
},
{
"epoch": 0.5211726384364821,
"grad_norm": 17.125,
"learning_rate": 3.463102783169471e-07,
"loss": 1.974489974975586,
"step": 240
},
{
"epoch": 0.5428881650380022,
"grad_norm": 5.90625,
"learning_rate": 3.217423987695643e-07,
"loss": 2.0915807723999023,
"step": 250
},
{
"epoch": 0.5646036916395223,
"grad_norm": 7.78125,
"learning_rate": 2.9731404074787175e-07,
"loss": 2.112474060058594,
"step": 260
},
{
"epoch": 0.5863192182410424,
"grad_norm": 21.625,
"learning_rate": 2.73145818940763e-07,
"loss": 2.2007789611816406,
"step": 270
},
{
"epoch": 0.6080347448425625,
"grad_norm": 13.8125,
"learning_rate": 2.4935706361807427e-07,
"loss": 2.275239181518555,
"step": 280
},
{
"epoch": 0.6297502714440825,
"grad_norm": 8.6875,
"learning_rate": 2.2606523143898274e-07,
"loss": 2.0178400039672852,
"step": 290
},
{
"epoch": 0.6514657980456026,
"grad_norm": 6.21875,
"learning_rate": 2.033853255113336e-07,
"loss": 2.1944948196411134,
"step": 300
},
{
"epoch": 0.6731813246471227,
"grad_norm": 18.75,
"learning_rate": 1.8142932756534272e-07,
"loss": 2.111407661437988,
"step": 310
},
{
"epoch": 0.6948968512486428,
"grad_norm": 14.875,
"learning_rate": 1.603056450453112e-07,
"loss": 2.0520841598510744,
"step": 320
},
{
"epoch": 0.7166123778501629,
"grad_norm": 4.0,
"learning_rate": 1.401185758493289e-07,
"loss": 1.9921758651733399,
"step": 330
},
{
"epoch": 0.738327904451683,
"grad_norm": 10.125,
"learning_rate": 1.2096779335980598e-07,
"loss": 2.2591268539428713,
"step": 340
},
{
"epoch": 0.760043431053203,
"grad_norm": 18.375,
"learning_rate": 1.0294785430748916e-07,
"loss": 2.3327383041381835,
"step": 350
},
{
"epoch": 0.7817589576547231,
"grad_norm": 6.65625,
"learning_rate": 8.6147731898877e-08,
"loss": 2.176487350463867,
"step": 360
},
{
"epoch": 0.8034744842562432,
"grad_norm": 7.03125,
"learning_rate": 7.065037651220986e-08,
"loss": 2.1322710037231447,
"step": 370
},
{
"epoch": 0.8251900108577633,
"grad_norm": 10.0625,
"learning_rate": 5.653230613109414e-08,
"loss": 2.1231149673461913,
"step": 380
},
{
"epoch": 0.8469055374592834,
"grad_norm": 4.96875,
"learning_rate": 4.38632285379887e-08,
"loss": 2.1640350341796877,
"step": 390
},
{
"epoch": 0.8686210640608035,
"grad_norm": 7.3125,
"learning_rate": 3.27056971329667e-08,
"loss": 2.0533117294311523,
"step": 400
},
{
"epoch": 0.8903365906623235,
"grad_norm": 8.5625,
"learning_rate": 2.3114802077145063e-08,
"loss": 2.199868011474609,
"step": 410
},
{
"epoch": 0.9120521172638436,
"grad_norm": 7.5625,
"learning_rate": 1.5137898285755707e-08,
"loss": 2.2271245956420898,
"step": 420
},
{
"epoch": 0.9337676438653637,
"grad_norm": 5.71875,
"learning_rate": 8.814371613888839e-09,
"loss": 2.0086801528930662,
"step": 430
},
{
"epoch": 0.9554831704668838,
"grad_norm": 5.21875,
"learning_rate": 4.175444389363636e-09,
"loss": 1.9937088012695312,
"step": 440
},
{
"epoch": 0.9771986970684039,
"grad_norm": 12.0625,
"learning_rate": 1.2440212529050531e-09,
"loss": 2.1526458740234373,
"step": 450
},
{
"epoch": 0.998914223669924,
"grad_norm": 8.75,
"learning_rate": 3.4576066788472026e-11,
"loss": 2.2378005981445312,
"step": 460
},
{
"epoch": 1.0,
"step": 461,
"total_flos": 2.197680639479255e+17,
"train_loss": 2.143569690286467,
"train_runtime": 3558.7051,
"train_samples_per_second": 0.518,
"train_steps_per_second": 0.13
}
],
"logging_steps": 10,
"max_steps": 461,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.197680639479255e+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 sha256:8f49e2d2efc6cb169731684579c9ba9fe378b56bbc943f20a164e4e8a8739062
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 53 KiB