lldois/v14_world_cot_preserve_lr8e6
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/v14_world_cot_preserve_lr8e6
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-13 10:55:17 +08:00
commit f5cf6da4c2
16 changed files with 3295 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: OpenOneRec/OneReason-0.8B-pretrain-competition
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: v14_world_cot_preserve_lr8e6
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. -->
# v14_world_cot_preserve_lr8e6
This model is a fine-tuned version of [OpenOneRec/OneReason-0.8B-pretrain-competition](https://huggingface.co/OpenOneRec/OneReason-0.8B-pretrain-competition) on the exp_world_cot_preserve 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: 8e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 202607114
- 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: linear
- lr_scheduler_warmup_steps: 0.05
- num_epochs: 1
### 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": 1.9165347193492685e+17,
"train_loss": 1.8377702086790462,
"train_runtime": 3207.2413,
"train_samples_per_second": 0.497,
"train_steps_per_second": 0.124
}

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
}

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 sha256:22583c345880598d52974925f09fc0e564acbefcc1c80ceedd634704d29dfaca
size 1602902832

3
runs/Jul07_05-02-58_ubuntu-System-Product-Name/events.out.tfevents.1783371778.ubuntu-System-Product-Name.2870209.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4fe0ae378b11206f199e83b03bb770d9f209816a2a11ac8e3059bd3214bb540d
size 22860

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": false,
"local_files_only": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

2317
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": 1.9165347193492685e+17,
"train_loss": 1.8377702086790462,
"train_runtime": 3207.2413,
"train_samples_per_second": 0.497,
"train_steps_per_second": 0.124
}

80
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,80 @@
{"current_steps": 5, "total_steps": 399, "loss": 3.015527534484863, "lr": 1.6e-06, "epoch": 0.012554927809165096, "percentage": 1.25, "elapsed_time": "0:00:39", "remaining_time": "0:52:16"}
{"current_steps": 10, "total_steps": 399, "loss": 2.9056806564331055, "lr": 3.6e-06, "epoch": 0.025109855618330193, "percentage": 2.51, "elapsed_time": "0:01:20", "remaining_time": "0:52:23"}
{"current_steps": 15, "total_steps": 399, "loss": 2.7296630859375, "lr": 5.6e-06, "epoch": 0.03766478342749529, "percentage": 3.76, "elapsed_time": "0:02:01", "remaining_time": "0:51:58"}
{"current_steps": 20, "total_steps": 399, "loss": 2.554681396484375, "lr": 7.599999999999999e-06, "epoch": 0.050219711236660386, "percentage": 5.01, "elapsed_time": "0:02:43", "remaining_time": "0:51:31"}
{"current_steps": 25, "total_steps": 399, "loss": 2.3827802658081056, "lr": 7.9155672823219e-06, "epoch": 0.06277463904582549, "percentage": 6.27, "elapsed_time": "0:03:23", "remaining_time": "0:50:47"}
{"current_steps": 30, "total_steps": 399, "loss": 2.2648855209350587, "lr": 7.810026385224273e-06, "epoch": 0.07532956685499058, "percentage": 7.52, "elapsed_time": "0:04:03", "remaining_time": "0:49:49"}
{"current_steps": 35, "total_steps": 399, "loss": 2.164264106750488, "lr": 7.704485488126649e-06, "epoch": 0.08788449466415568, "percentage": 8.77, "elapsed_time": "0:04:42", "remaining_time": "0:49:01"}
{"current_steps": 40, "total_steps": 399, "loss": 2.1138830184936523, "lr": 7.5989445910290234e-06, "epoch": 0.10043942247332077, "percentage": 10.03, "elapsed_time": "0:05:23", "remaining_time": "0:48:22"}
{"current_steps": 45, "total_steps": 399, "loss": 2.094548988342285, "lr": 7.493403693931398e-06, "epoch": 0.11299435028248588, "percentage": 11.28, "elapsed_time": "0:06:01", "remaining_time": "0:47:21"}
{"current_steps": 50, "total_steps": 399, "loss": 2.0466962814331056, "lr": 7.387862796833773e-06, "epoch": 0.12554927809165098, "percentage": 12.53, "elapsed_time": "0:06:39", "remaining_time": "0:46:29"}
{"current_steps": 55, "total_steps": 399, "loss": 1.987128448486328, "lr": 7.282321899736147e-06, "epoch": 0.13810420590081607, "percentage": 13.78, "elapsed_time": "0:07:19", "remaining_time": "0:45:46"}
{"current_steps": 60, "total_steps": 399, "loss": 1.9320449829101562, "lr": 7.176781002638522e-06, "epoch": 0.15065913370998116, "percentage": 15.04, "elapsed_time": "0:07:58", "remaining_time": "0:45:06"}
{"current_steps": 65, "total_steps": 399, "loss": 1.8850692749023437, "lr": 7.071240105540897e-06, "epoch": 0.16321406151914628, "percentage": 16.29, "elapsed_time": "0:08:38", "remaining_time": "0:44:26"}
{"current_steps": 70, "total_steps": 399, "loss": 1.824066734313965, "lr": 6.965699208443271e-06, "epoch": 0.17576898932831136, "percentage": 17.54, "elapsed_time": "0:09:20", "remaining_time": "0:43:56"}
{"current_steps": 75, "total_steps": 399, "loss": 1.834686851501465, "lr": 6.860158311345646e-06, "epoch": 0.18832391713747645, "percentage": 18.8, "elapsed_time": "0:10:01", "remaining_time": "0:43:17"}
{"current_steps": 80, "total_steps": 399, "loss": 1.8118074417114258, "lr": 6.754617414248021e-06, "epoch": 0.20087884494664154, "percentage": 20.05, "elapsed_time": "0:10:42", "remaining_time": "0:42:43"}
{"current_steps": 85, "total_steps": 399, "loss": 1.8300344467163085, "lr": 6.649076517150395e-06, "epoch": 0.21343377275580666, "percentage": 21.3, "elapsed_time": "0:11:22", "remaining_time": "0:42:01"}
{"current_steps": 90, "total_steps": 399, "loss": 1.8369518280029298, "lr": 6.54353562005277e-06, "epoch": 0.22598870056497175, "percentage": 22.56, "elapsed_time": "0:12:02", "remaining_time": "0:41:20"}
{"current_steps": 95, "total_steps": 399, "loss": 1.783146286010742, "lr": 6.437994722955145e-06, "epoch": 0.23854362837413684, "percentage": 23.81, "elapsed_time": "0:12:43", "remaining_time": "0:40:42"}
{"current_steps": 100, "total_steps": 399, "loss": 1.8646963119506836, "lr": 6.332453825857519e-06, "epoch": 0.25109855618330196, "percentage": 25.06, "elapsed_time": "0:13:23", "remaining_time": "0:40:01"}
{"current_steps": 105, "total_steps": 399, "loss": 1.777773094177246, "lr": 6.226912928759894e-06, "epoch": 0.263653483992467, "percentage": 26.32, "elapsed_time": "0:14:03", "remaining_time": "0:39:21"}
{"current_steps": 110, "total_steps": 399, "loss": 1.8915065765380858, "lr": 6.121372031662269e-06, "epoch": 0.27620841180163214, "percentage": 27.57, "elapsed_time": "0:14:41", "remaining_time": "0:38:36"}
{"current_steps": 115, "total_steps": 399, "loss": 1.7347688674926758, "lr": 6.015831134564643e-06, "epoch": 0.28876333961079725, "percentage": 28.82, "elapsed_time": "0:15:23", "remaining_time": "0:38:01"}
{"current_steps": 120, "total_steps": 399, "loss": 1.7663537979125976, "lr": 5.910290237467018e-06, "epoch": 0.3013182674199623, "percentage": 30.08, "elapsed_time": "0:16:02", "remaining_time": "0:37:18"}
{"current_steps": 125, "total_steps": 399, "loss": 1.7853734970092774, "lr": 5.804749340369393e-06, "epoch": 0.31387319522912743, "percentage": 31.33, "elapsed_time": "0:16:43", "remaining_time": "0:36:39"}
{"current_steps": 130, "total_steps": 399, "loss": 1.727178192138672, "lr": 5.699208443271768e-06, "epoch": 0.32642812303829255, "percentage": 32.58, "elapsed_time": "0:17:24", "remaining_time": "0:36:00"}
{"current_steps": 135, "total_steps": 399, "loss": 1.759018325805664, "lr": 5.593667546174142e-06, "epoch": 0.3389830508474576, "percentage": 33.83, "elapsed_time": "0:18:04", "remaining_time": "0:35:20"}
{"current_steps": 140, "total_steps": 399, "loss": 1.8040559768676758, "lr": 5.488126649076517e-06, "epoch": 0.35153797865662273, "percentage": 35.09, "elapsed_time": "0:18:42", "remaining_time": "0:34:36"}
{"current_steps": 145, "total_steps": 399, "loss": 1.7908735275268555, "lr": 5.382585751978892e-06, "epoch": 0.36409290646578785, "percentage": 36.34, "elapsed_time": "0:19:21", "remaining_time": "0:33:54"}
{"current_steps": 150, "total_steps": 399, "loss": 1.770136260986328, "lr": 5.277044854881266e-06, "epoch": 0.3766478342749529, "percentage": 37.59, "elapsed_time": "0:20:00", "remaining_time": "0:33:12"}
{"current_steps": 155, "total_steps": 399, "loss": 1.7118070602416993, "lr": 5.171503957783641e-06, "epoch": 0.389202762084118, "percentage": 38.85, "elapsed_time": "0:20:42", "remaining_time": "0:32:36"}
{"current_steps": 160, "total_steps": 399, "loss": 1.7357185363769532, "lr": 5.065963060686016e-06, "epoch": 0.4017576898932831, "percentage": 40.1, "elapsed_time": "0:21:23", "remaining_time": "0:31:56"}
{"current_steps": 165, "total_steps": 399, "loss": 1.7145261764526367, "lr": 4.96042216358839e-06, "epoch": 0.4143126177024482, "percentage": 41.35, "elapsed_time": "0:22:02", "remaining_time": "0:31:16"}
{"current_steps": 170, "total_steps": 399, "loss": 1.7963302612304688, "lr": 4.854881266490765e-06, "epoch": 0.4268675455116133, "percentage": 42.61, "elapsed_time": "0:22:43", "remaining_time": "0:30:36"}
{"current_steps": 175, "total_steps": 399, "loss": 1.750374984741211, "lr": 4.74934036939314e-06, "epoch": 0.4394224733207784, "percentage": 43.86, "elapsed_time": "0:23:23", "remaining_time": "0:29:56"}
{"current_steps": 180, "total_steps": 399, "loss": 1.781978225708008, "lr": 4.643799472295514e-06, "epoch": 0.4519774011299435, "percentage": 45.11, "elapsed_time": "0:24:03", "remaining_time": "0:29:16"}
{"current_steps": 185, "total_steps": 399, "loss": 1.7206108093261718, "lr": 4.538258575197889e-06, "epoch": 0.4645323289391086, "percentage": 46.37, "elapsed_time": "0:24:43", "remaining_time": "0:28:36"}
{"current_steps": 190, "total_steps": 399, "loss": 1.7622594833374023, "lr": 4.432717678100264e-06, "epoch": 0.4770872567482737, "percentage": 47.62, "elapsed_time": "0:25:24", "remaining_time": "0:27:57"}
{"current_steps": 195, "total_steps": 399, "loss": 1.710411834716797, "lr": 4.327176781002638e-06, "epoch": 0.4896421845574388, "percentage": 48.87, "elapsed_time": "0:26:05", "remaining_time": "0:27:18"}
{"current_steps": 200, "total_steps": 399, "loss": 1.7073869705200195, "lr": 4.221635883905013e-06, "epoch": 0.5021971123666039, "percentage": 50.13, "elapsed_time": "0:26:46", "remaining_time": "0:26:38"}
{"current_steps": 205, "total_steps": 399, "loss": 1.8353261947631836, "lr": 4.116094986807388e-06, "epoch": 0.514752040175769, "percentage": 51.38, "elapsed_time": "0:27:25", "remaining_time": "0:25:57"}
{"current_steps": 210, "total_steps": 399, "loss": 1.698282814025879, "lr": 4.010554089709762e-06, "epoch": 0.527306967984934, "percentage": 52.63, "elapsed_time": "0:28:07", "remaining_time": "0:25:18"}
{"current_steps": 215, "total_steps": 399, "loss": 1.7486772537231445, "lr": 3.905013192612137e-06, "epoch": 0.5398618957940992, "percentage": 53.88, "elapsed_time": "0:28:46", "remaining_time": "0:24:37"}
{"current_steps": 220, "total_steps": 399, "loss": 1.6990921020507812, "lr": 3.7994722955145117e-06, "epoch": 0.5524168236032643, "percentage": 55.14, "elapsed_time": "0:29:27", "remaining_time": "0:23:58"}
{"current_steps": 225, "total_steps": 399, "loss": 1.762404441833496, "lr": 3.6939313984168864e-06, "epoch": 0.5649717514124294, "percentage": 56.39, "elapsed_time": "0:30:07", "remaining_time": "0:23:18"}
{"current_steps": 230, "total_steps": 399, "loss": 1.7405305862426759, "lr": 3.588390501319261e-06, "epoch": 0.5775266792215945, "percentage": 57.64, "elapsed_time": "0:30:45", "remaining_time": "0:22:36"}
{"current_steps": 235, "total_steps": 399, "loss": 1.7367145538330078, "lr": 3.4828496042216354e-06, "epoch": 0.5900816070307596, "percentage": 58.9, "elapsed_time": "0:31:26", "remaining_time": "0:21:56"}
{"current_steps": 240, "total_steps": 399, "loss": 1.7370288848876954, "lr": 3.3773087071240105e-06, "epoch": 0.6026365348399246, "percentage": 60.15, "elapsed_time": "0:32:06", "remaining_time": "0:21:16"}
{"current_steps": 245, "total_steps": 399, "loss": 1.7362842559814453, "lr": 3.271767810026385e-06, "epoch": 0.6151914626490897, "percentage": 61.4, "elapsed_time": "0:32:46", "remaining_time": "0:20:36"}
{"current_steps": 250, "total_steps": 399, "loss": 1.7747028350830079, "lr": 3.1662269129287594e-06, "epoch": 0.6277463904582549, "percentage": 62.66, "elapsed_time": "0:33:26", "remaining_time": "0:19:56"}
{"current_steps": 255, "total_steps": 399, "loss": 1.7429088592529296, "lr": 3.0606860158311345e-06, "epoch": 0.64030131826742, "percentage": 63.91, "elapsed_time": "0:34:08", "remaining_time": "0:19:16"}
{"current_steps": 260, "total_steps": 399, "loss": 1.721456527709961, "lr": 2.955145118733509e-06, "epoch": 0.6528562460765851, "percentage": 65.16, "elapsed_time": "0:34:50", "remaining_time": "0:18:37"}
{"current_steps": 265, "total_steps": 399, "loss": 1.7210311889648438, "lr": 2.849604221635884e-06, "epoch": 0.6654111738857501, "percentage": 66.42, "elapsed_time": "0:35:31", "remaining_time": "0:17:57"}
{"current_steps": 270, "total_steps": 399, "loss": 1.7025691986083984, "lr": 2.7440633245382586e-06, "epoch": 0.6779661016949152, "percentage": 67.67, "elapsed_time": "0:36:11", "remaining_time": "0:17:17"}
{"current_steps": 275, "total_steps": 399, "loss": 1.7361589431762696, "lr": 2.638522427440633e-06, "epoch": 0.6905210295040803, "percentage": 68.92, "elapsed_time": "0:36:52", "remaining_time": "0:16:37"}
{"current_steps": 280, "total_steps": 399, "loss": 1.6922121047973633, "lr": 2.532981530343008e-06, "epoch": 0.7030759573132455, "percentage": 70.18, "elapsed_time": "0:37:33", "remaining_time": "0:15:57"}
{"current_steps": 285, "total_steps": 399, "loss": 1.6920455932617187, "lr": 2.4274406332453826e-06, "epoch": 0.7156308851224106, "percentage": 71.43, "elapsed_time": "0:38:14", "remaining_time": "0:15:17"}
{"current_steps": 290, "total_steps": 399, "loss": 1.698456382751465, "lr": 2.321899736147757e-06, "epoch": 0.7281858129315757, "percentage": 72.68, "elapsed_time": "0:38:55", "remaining_time": "0:14:37"}
{"current_steps": 295, "total_steps": 399, "loss": 1.670083999633789, "lr": 2.216358839050132e-06, "epoch": 0.7407407407407407, "percentage": 73.93, "elapsed_time": "0:39:37", "remaining_time": "0:13:58"}
{"current_steps": 300, "total_steps": 399, "loss": 1.6989984512329102, "lr": 2.1108179419525067e-06, "epoch": 0.7532956685499058, "percentage": 75.19, "elapsed_time": "0:40:17", "remaining_time": "0:13:17"}
{"current_steps": 305, "total_steps": 399, "loss": 1.6980472564697267, "lr": 2.005277044854881e-06, "epoch": 0.7658505963590709, "percentage": 76.44, "elapsed_time": "0:40:56", "remaining_time": "0:12:37"}
{"current_steps": 310, "total_steps": 399, "loss": 1.7009418487548829, "lr": 1.8997361477572559e-06, "epoch": 0.778405524168236, "percentage": 77.69, "elapsed_time": "0:41:35", "remaining_time": "0:11:56"}
{"current_steps": 315, "total_steps": 399, "loss": 1.68243350982666, "lr": 1.7941952506596305e-06, "epoch": 0.7909604519774012, "percentage": 78.95, "elapsed_time": "0:42:15", "remaining_time": "0:11:16"}
{"current_steps": 320, "total_steps": 399, "loss": 1.7379121780395508, "lr": 1.6886543535620052e-06, "epoch": 0.8035153797865662, "percentage": 80.2, "elapsed_time": "0:42:57", "remaining_time": "0:10:36"}
{"current_steps": 325, "total_steps": 399, "loss": 1.72882080078125, "lr": 1.5831134564643797e-06, "epoch": 0.8160703075957313, "percentage": 81.45, "elapsed_time": "0:43:37", "remaining_time": "0:09:55"}
{"current_steps": 330, "total_steps": 399, "loss": 1.7303064346313477, "lr": 1.4775725593667546e-06, "epoch": 0.8286252354048964, "percentage": 82.71, "elapsed_time": "0:44:19", "remaining_time": "0:09:16"}
{"current_steps": 335, "total_steps": 399, "loss": 1.7374654769897462, "lr": 1.3720316622691293e-06, "epoch": 0.8411801632140615, "percentage": 83.96, "elapsed_time": "0:45:00", "remaining_time": "0:08:35"}
{"current_steps": 340, "total_steps": 399, "loss": 1.7751611709594726, "lr": 1.266490765171504e-06, "epoch": 0.8537350910232266, "percentage": 85.21, "elapsed_time": "0:45:38", "remaining_time": "0:07:55"}
{"current_steps": 345, "total_steps": 399, "loss": 1.710137939453125, "lr": 1.1609498680738785e-06, "epoch": 0.8662900188323918, "percentage": 86.47, "elapsed_time": "0:46:17", "remaining_time": "0:07:14"}
{"current_steps": 350, "total_steps": 399, "loss": 1.7200075149536134, "lr": 1.0554089709762534e-06, "epoch": 0.8788449466415568, "percentage": 87.72, "elapsed_time": "0:46:56", "remaining_time": "0:06:34"}
{"current_steps": 355, "total_steps": 399, "loss": 1.7364322662353515, "lr": 9.498680738786279e-07, "epoch": 0.8913998744507219, "percentage": 88.97, "elapsed_time": "0:47:37", "remaining_time": "0:05:54"}
{"current_steps": 360, "total_steps": 399, "loss": 1.7424024581909179, "lr": 8.443271767810026e-07, "epoch": 0.903954802259887, "percentage": 90.23, "elapsed_time": "0:48:17", "remaining_time": "0:05:13"}
{"current_steps": 365, "total_steps": 399, "loss": 1.7035579681396484, "lr": 7.387862796833773e-07, "epoch": 0.9165097300690521, "percentage": 91.48, "elapsed_time": "0:48:58", "remaining_time": "0:04:33"}
{"current_steps": 370, "total_steps": 399, "loss": 1.7039636611938476, "lr": 6.33245382585752e-07, "epoch": 0.9290646578782172, "percentage": 92.73, "elapsed_time": "0:49:38", "remaining_time": "0:03:53"}
{"current_steps": 375, "total_steps": 399, "loss": 1.7040679931640625, "lr": 5.277044854881267e-07, "epoch": 0.9416195856873822, "percentage": 93.98, "elapsed_time": "0:50:18", "remaining_time": "0:03:13"}
{"current_steps": 380, "total_steps": 399, "loss": 1.7816453933715821, "lr": 4.221635883905013e-07, "epoch": 0.9541745134965474, "percentage": 95.24, "elapsed_time": "0:50:58", "remaining_time": "0:02:32"}
{"current_steps": 385, "total_steps": 399, "loss": 1.6937868118286132, "lr": 3.16622691292876e-07, "epoch": 0.9667294413057125, "percentage": 96.49, "elapsed_time": "0:51:38", "remaining_time": "0:01:52"}
{"current_steps": 390, "total_steps": 399, "loss": 1.692620849609375, "lr": 2.1108179419525065e-07, "epoch": 0.9792843691148776, "percentage": 97.74, "elapsed_time": "0:52:19", "remaining_time": "0:01:12"}
{"current_steps": 395, "total_steps": 399, "loss": 1.6935569763183593, "lr": 1.0554089709762533e-07, "epoch": 0.9918392969240427, "percentage": 99.0, "elapsed_time": "0:53:00", "remaining_time": "0:00:32"}
{"current_steps": 399, "total_steps": 399, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:53:27", "remaining_time": "0:00:00"}

596
trainer_state.json Normal file
View File

@@ -0,0 +1,596 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 399,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.012554927809165096,
"grad_norm": 52.0,
"learning_rate": 1.6e-06,
"loss": 3.015527534484863,
"step": 5
},
{
"epoch": 0.025109855618330193,
"grad_norm": 27.0,
"learning_rate": 3.6e-06,
"loss": 2.9056806564331055,
"step": 10
},
{
"epoch": 0.03766478342749529,
"grad_norm": 13.3125,
"learning_rate": 5.6e-06,
"loss": 2.7296630859375,
"step": 15
},
{
"epoch": 0.050219711236660386,
"grad_norm": 7.3125,
"learning_rate": 7.599999999999999e-06,
"loss": 2.554681396484375,
"step": 20
},
{
"epoch": 0.06277463904582549,
"grad_norm": 6.90625,
"learning_rate": 7.9155672823219e-06,
"loss": 2.3827802658081056,
"step": 25
},
{
"epoch": 0.07532956685499058,
"grad_norm": 4.6875,
"learning_rate": 7.810026385224273e-06,
"loss": 2.2648855209350587,
"step": 30
},
{
"epoch": 0.08788449466415568,
"grad_norm": 3.734375,
"learning_rate": 7.704485488126649e-06,
"loss": 2.164264106750488,
"step": 35
},
{
"epoch": 0.10043942247332077,
"grad_norm": 6.4375,
"learning_rate": 7.5989445910290234e-06,
"loss": 2.1138830184936523,
"step": 40
},
{
"epoch": 0.11299435028248588,
"grad_norm": 8.1875,
"learning_rate": 7.493403693931398e-06,
"loss": 2.094548988342285,
"step": 45
},
{
"epoch": 0.12554927809165098,
"grad_norm": 2.6875,
"learning_rate": 7.387862796833773e-06,
"loss": 2.0466962814331056,
"step": 50
},
{
"epoch": 0.13810420590081607,
"grad_norm": 2.9375,
"learning_rate": 7.282321899736147e-06,
"loss": 1.987128448486328,
"step": 55
},
{
"epoch": 0.15065913370998116,
"grad_norm": 2.796875,
"learning_rate": 7.176781002638522e-06,
"loss": 1.9320449829101562,
"step": 60
},
{
"epoch": 0.16321406151914628,
"grad_norm": 2.75,
"learning_rate": 7.071240105540897e-06,
"loss": 1.8850692749023437,
"step": 65
},
{
"epoch": 0.17576898932831136,
"grad_norm": 5.84375,
"learning_rate": 6.965699208443271e-06,
"loss": 1.824066734313965,
"step": 70
},
{
"epoch": 0.18832391713747645,
"grad_norm": 2.5625,
"learning_rate": 6.860158311345646e-06,
"loss": 1.834686851501465,
"step": 75
},
{
"epoch": 0.20087884494664154,
"grad_norm": 2.4375,
"learning_rate": 6.754617414248021e-06,
"loss": 1.8118074417114258,
"step": 80
},
{
"epoch": 0.21343377275580666,
"grad_norm": 2.421875,
"learning_rate": 6.649076517150395e-06,
"loss": 1.8300344467163085,
"step": 85
},
{
"epoch": 0.22598870056497175,
"grad_norm": 2.546875,
"learning_rate": 6.54353562005277e-06,
"loss": 1.8369518280029298,
"step": 90
},
{
"epoch": 0.23854362837413684,
"grad_norm": 2.515625,
"learning_rate": 6.437994722955145e-06,
"loss": 1.783146286010742,
"step": 95
},
{
"epoch": 0.25109855618330196,
"grad_norm": 2.65625,
"learning_rate": 6.332453825857519e-06,
"loss": 1.8646963119506836,
"step": 100
},
{
"epoch": 0.263653483992467,
"grad_norm": 2.4375,
"learning_rate": 6.226912928759894e-06,
"loss": 1.777773094177246,
"step": 105
},
{
"epoch": 0.27620841180163214,
"grad_norm": 2.375,
"learning_rate": 6.121372031662269e-06,
"loss": 1.8915065765380858,
"step": 110
},
{
"epoch": 0.28876333961079725,
"grad_norm": 2.171875,
"learning_rate": 6.015831134564643e-06,
"loss": 1.7347688674926758,
"step": 115
},
{
"epoch": 0.3013182674199623,
"grad_norm": 2.296875,
"learning_rate": 5.910290237467018e-06,
"loss": 1.7663537979125976,
"step": 120
},
{
"epoch": 0.31387319522912743,
"grad_norm": 2.09375,
"learning_rate": 5.804749340369393e-06,
"loss": 1.7853734970092774,
"step": 125
},
{
"epoch": 0.32642812303829255,
"grad_norm": 2.3125,
"learning_rate": 5.699208443271768e-06,
"loss": 1.727178192138672,
"step": 130
},
{
"epoch": 0.3389830508474576,
"grad_norm": 2.0625,
"learning_rate": 5.593667546174142e-06,
"loss": 1.759018325805664,
"step": 135
},
{
"epoch": 0.35153797865662273,
"grad_norm": 2.28125,
"learning_rate": 5.488126649076517e-06,
"loss": 1.8040559768676758,
"step": 140
},
{
"epoch": 0.36409290646578785,
"grad_norm": 2.796875,
"learning_rate": 5.382585751978892e-06,
"loss": 1.7908735275268555,
"step": 145
},
{
"epoch": 0.3766478342749529,
"grad_norm": 2.4375,
"learning_rate": 5.277044854881266e-06,
"loss": 1.770136260986328,
"step": 150
},
{
"epoch": 0.389202762084118,
"grad_norm": 2.96875,
"learning_rate": 5.171503957783641e-06,
"loss": 1.7118070602416993,
"step": 155
},
{
"epoch": 0.4017576898932831,
"grad_norm": 2.46875,
"learning_rate": 5.065963060686016e-06,
"loss": 1.7357185363769532,
"step": 160
},
{
"epoch": 0.4143126177024482,
"grad_norm": 2.25,
"learning_rate": 4.96042216358839e-06,
"loss": 1.7145261764526367,
"step": 165
},
{
"epoch": 0.4268675455116133,
"grad_norm": 2.734375,
"learning_rate": 4.854881266490765e-06,
"loss": 1.7963302612304688,
"step": 170
},
{
"epoch": 0.4394224733207784,
"grad_norm": 2.40625,
"learning_rate": 4.74934036939314e-06,
"loss": 1.750374984741211,
"step": 175
},
{
"epoch": 0.4519774011299435,
"grad_norm": 3.984375,
"learning_rate": 4.643799472295514e-06,
"loss": 1.781978225708008,
"step": 180
},
{
"epoch": 0.4645323289391086,
"grad_norm": 2.296875,
"learning_rate": 4.538258575197889e-06,
"loss": 1.7206108093261718,
"step": 185
},
{
"epoch": 0.4770872567482737,
"grad_norm": 2.390625,
"learning_rate": 4.432717678100264e-06,
"loss": 1.7622594833374023,
"step": 190
},
{
"epoch": 0.4896421845574388,
"grad_norm": 2.640625,
"learning_rate": 4.327176781002638e-06,
"loss": 1.710411834716797,
"step": 195
},
{
"epoch": 0.5021971123666039,
"grad_norm": 2.296875,
"learning_rate": 4.221635883905013e-06,
"loss": 1.7073869705200195,
"step": 200
},
{
"epoch": 0.514752040175769,
"grad_norm": 2.859375,
"learning_rate": 4.116094986807388e-06,
"loss": 1.8353261947631836,
"step": 205
},
{
"epoch": 0.527306967984934,
"grad_norm": 3.34375,
"learning_rate": 4.010554089709762e-06,
"loss": 1.698282814025879,
"step": 210
},
{
"epoch": 0.5398618957940992,
"grad_norm": 2.609375,
"learning_rate": 3.905013192612137e-06,
"loss": 1.7486772537231445,
"step": 215
},
{
"epoch": 0.5524168236032643,
"grad_norm": 2.5625,
"learning_rate": 3.7994722955145117e-06,
"loss": 1.6990921020507812,
"step": 220
},
{
"epoch": 0.5649717514124294,
"grad_norm": 2.140625,
"learning_rate": 3.6939313984168864e-06,
"loss": 1.762404441833496,
"step": 225
},
{
"epoch": 0.5775266792215945,
"grad_norm": 2.203125,
"learning_rate": 3.588390501319261e-06,
"loss": 1.7405305862426759,
"step": 230
},
{
"epoch": 0.5900816070307596,
"grad_norm": 2.109375,
"learning_rate": 3.4828496042216354e-06,
"loss": 1.7367145538330078,
"step": 235
},
{
"epoch": 0.6026365348399246,
"grad_norm": 2.34375,
"learning_rate": 3.3773087071240105e-06,
"loss": 1.7370288848876954,
"step": 240
},
{
"epoch": 0.6151914626490897,
"grad_norm": 2.71875,
"learning_rate": 3.271767810026385e-06,
"loss": 1.7362842559814453,
"step": 245
},
{
"epoch": 0.6277463904582549,
"grad_norm": 2.0625,
"learning_rate": 3.1662269129287594e-06,
"loss": 1.7747028350830079,
"step": 250
},
{
"epoch": 0.64030131826742,
"grad_norm": 2.9375,
"learning_rate": 3.0606860158311345e-06,
"loss": 1.7429088592529296,
"step": 255
},
{
"epoch": 0.6528562460765851,
"grad_norm": 2.640625,
"learning_rate": 2.955145118733509e-06,
"loss": 1.721456527709961,
"step": 260
},
{
"epoch": 0.6654111738857501,
"grad_norm": 2.078125,
"learning_rate": 2.849604221635884e-06,
"loss": 1.7210311889648438,
"step": 265
},
{
"epoch": 0.6779661016949152,
"grad_norm": 2.078125,
"learning_rate": 2.7440633245382586e-06,
"loss": 1.7025691986083984,
"step": 270
},
{
"epoch": 0.6905210295040803,
"grad_norm": 4.25,
"learning_rate": 2.638522427440633e-06,
"loss": 1.7361589431762696,
"step": 275
},
{
"epoch": 0.7030759573132455,
"grad_norm": 2.265625,
"learning_rate": 2.532981530343008e-06,
"loss": 1.6922121047973633,
"step": 280
},
{
"epoch": 0.7156308851224106,
"grad_norm": 2.40625,
"learning_rate": 2.4274406332453826e-06,
"loss": 1.6920455932617187,
"step": 285
},
{
"epoch": 0.7281858129315757,
"grad_norm": 2.15625,
"learning_rate": 2.321899736147757e-06,
"loss": 1.698456382751465,
"step": 290
},
{
"epoch": 0.7407407407407407,
"grad_norm": 2.65625,
"learning_rate": 2.216358839050132e-06,
"loss": 1.670083999633789,
"step": 295
},
{
"epoch": 0.7532956685499058,
"grad_norm": 2.0,
"learning_rate": 2.1108179419525067e-06,
"loss": 1.6989984512329102,
"step": 300
},
{
"epoch": 0.7658505963590709,
"grad_norm": 2.1875,
"learning_rate": 2.005277044854881e-06,
"loss": 1.6980472564697267,
"step": 305
},
{
"epoch": 0.778405524168236,
"grad_norm": 2.046875,
"learning_rate": 1.8997361477572559e-06,
"loss": 1.7009418487548829,
"step": 310
},
{
"epoch": 0.7909604519774012,
"grad_norm": 2.359375,
"learning_rate": 1.7941952506596305e-06,
"loss": 1.68243350982666,
"step": 315
},
{
"epoch": 0.8035153797865662,
"grad_norm": 2.359375,
"learning_rate": 1.6886543535620052e-06,
"loss": 1.7379121780395508,
"step": 320
},
{
"epoch": 0.8160703075957313,
"grad_norm": 2.609375,
"learning_rate": 1.5831134564643797e-06,
"loss": 1.72882080078125,
"step": 325
},
{
"epoch": 0.8286252354048964,
"grad_norm": 5.03125,
"learning_rate": 1.4775725593667546e-06,
"loss": 1.7303064346313477,
"step": 330
},
{
"epoch": 0.8411801632140615,
"grad_norm": 2.65625,
"learning_rate": 1.3720316622691293e-06,
"loss": 1.7374654769897462,
"step": 335
},
{
"epoch": 0.8537350910232266,
"grad_norm": 2.125,
"learning_rate": 1.266490765171504e-06,
"loss": 1.7751611709594726,
"step": 340
},
{
"epoch": 0.8662900188323918,
"grad_norm": 2.25,
"learning_rate": 1.1609498680738785e-06,
"loss": 1.710137939453125,
"step": 345
},
{
"epoch": 0.8788449466415568,
"grad_norm": 1.9921875,
"learning_rate": 1.0554089709762534e-06,
"loss": 1.7200075149536134,
"step": 350
},
{
"epoch": 0.8913998744507219,
"grad_norm": 2.953125,
"learning_rate": 9.498680738786279e-07,
"loss": 1.7364322662353515,
"step": 355
},
{
"epoch": 0.903954802259887,
"grad_norm": 2.0,
"learning_rate": 8.443271767810026e-07,
"loss": 1.7424024581909179,
"step": 360
},
{
"epoch": 0.9165097300690521,
"grad_norm": 2.15625,
"learning_rate": 7.387862796833773e-07,
"loss": 1.7035579681396484,
"step": 365
},
{
"epoch": 0.9290646578782172,
"grad_norm": 2.546875,
"learning_rate": 6.33245382585752e-07,
"loss": 1.7039636611938476,
"step": 370
},
{
"epoch": 0.9416195856873822,
"grad_norm": 2.75,
"learning_rate": 5.277044854881267e-07,
"loss": 1.7040679931640625,
"step": 375
},
{
"epoch": 0.9541745134965474,
"grad_norm": 2.96875,
"learning_rate": 4.221635883905013e-07,
"loss": 1.7816453933715821,
"step": 380
},
{
"epoch": 0.9667294413057125,
"grad_norm": 2.609375,
"learning_rate": 3.16622691292876e-07,
"loss": 1.6937868118286132,
"step": 385
},
{
"epoch": 0.9792843691148776,
"grad_norm": 2.625,
"learning_rate": 2.1108179419525065e-07,
"loss": 1.692620849609375,
"step": 390
},
{
"epoch": 0.9918392969240427,
"grad_norm": 2.25,
"learning_rate": 1.0554089709762533e-07,
"loss": 1.6935569763183593,
"step": 395
},
{
"epoch": 1.0,
"step": 399,
"total_flos": 1.9165347193492685e+17,
"train_loss": 1.8377702086790462,
"train_runtime": 3207.2413,
"train_samples_per_second": 0.497,
"train_steps_per_second": 0.124
}
],
"logging_steps": 5,
"max_steps": 399,
"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": 1.9165347193492685e+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:ff6ad16007970c1b5085dd8ed3c24fef3ceaed2c8e81e466c33ae33939e98959
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 41 KiB