lldois/onereason_0.8b_sft
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/onereason_0.8b_sft
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-07 11:33:17 +08:00
commit e5a0d25204
16 changed files with 3341 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: onereason_0.8b_sft
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. -->
# onereason_0.8b_sft
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 data_final 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: 2e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 20260701
- 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
### 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": 1.5697158980369568,
"train_runtime": 3253.1715,
"train_samples_per_second": 0.491,
"train_steps_per_second": 0.123
}

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 sha256:0d3bb000bd65ffd468cbd154366027bb20fee3326c34556c34d5b636dcf17110
size 1602902832

3
runs/Jul05_17-58-46_ubuntu-System-Product-Name/events.out.tfevents.1783245526.ubuntu-System-Product-Name.1097917.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ddd3d03946ddea2482f422f0db9a6076e3695cdb570095200eea12595849ba37
size 23003

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
}

2355
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": 1.5697158980369568,
"train_runtime": 3253.1715,
"train_samples_per_second": 0.491,
"train_steps_per_second": 0.123
}

81
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,81 @@
{"current_steps": 5, "total_steps": 400, "loss": 3.0092775344848635, "lr": 6.666666666666667e-06, "epoch": 0.012523481527864746, "percentage": 1.25, "elapsed_time": "0:00:41", "remaining_time": "0:54:28"}
{"current_steps": 10, "total_steps": 400, "loss": 2.547764778137207, "lr": 1.5000000000000002e-05, "epoch": 0.025046963055729492, "percentage": 2.5, "elapsed_time": "0:01:21", "remaining_time": "0:52:42"}
{"current_steps": 15, "total_steps": 400, "loss": 2.233675956726074, "lr": 1.9998688836656322e-05, "epoch": 0.03757044458359424, "percentage": 3.75, "elapsed_time": "0:02:02", "remaining_time": "0:52:24"}
{"current_steps": 20, "total_steps": 400, "loss": 2.057873344421387, "lr": 1.9983942197426272e-05, "epoch": 0.050093926111458985, "percentage": 5.0, "elapsed_time": "0:02:42", "remaining_time": "0:51:29"}
{"current_steps": 25, "total_steps": 400, "loss": 1.851465606689453, "lr": 1.995283421166614e-05, "epoch": 0.06261740763932373, "percentage": 6.25, "elapsed_time": "0:03:24", "remaining_time": "0:51:14"}
{"current_steps": 30, "total_steps": 400, "loss": 1.855565071105957, "lr": 1.9905415858090036e-05, "epoch": 0.07514088916718847, "percentage": 7.5, "elapsed_time": "0:04:04", "remaining_time": "0:50:10"}
{"current_steps": 35, "total_steps": 400, "loss": 1.752499771118164, "lr": 1.9841764844290744e-05, "epoch": 0.08766437069505323, "percentage": 8.75, "elapsed_time": "0:04:45", "remaining_time": "0:49:38"}
{"current_steps": 40, "total_steps": 400, "loss": 1.8114988327026367, "lr": 1.976198547939518e-05, "epoch": 0.10018785222291797, "percentage": 10.0, "elapsed_time": "0:05:24", "remaining_time": "0:48:44"}
{"current_steps": 45, "total_steps": 400, "loss": 1.6981731414794923, "lr": 1.9666208503126115e-05, "epoch": 0.11271133375078271, "percentage": 11.25, "elapsed_time": "0:06:05", "remaining_time": "0:48:06"}
{"current_steps": 50, "total_steps": 400, "loss": 1.6682065963745116, "lr": 1.955459087155033e-05, "epoch": 0.12523481527864747, "percentage": 12.5, "elapsed_time": "0:06:45", "remaining_time": "0:47:21"}
{"current_steps": 55, "total_steps": 400, "loss": 1.654319953918457, "lr": 1.9427315499864345e-05, "epoch": 0.13775829680651222, "percentage": 13.75, "elapsed_time": "0:07:25", "remaining_time": "0:46:34"}
{"current_steps": 60, "total_steps": 400, "loss": 1.628897476196289, "lr": 1.928459096263918e-05, "epoch": 0.15028177833437695, "percentage": 15.0, "elapsed_time": "0:08:04", "remaining_time": "0:45:43"}
{"current_steps": 65, "total_steps": 400, "loss": 1.588959312438965, "lr": 1.9126651152015404e-05, "epoch": 0.1628052598622417, "percentage": 16.25, "elapsed_time": "0:08:45", "remaining_time": "0:45:10"}
{"current_steps": 70, "total_steps": 400, "loss": 1.643252182006836, "lr": 1.8953754894408617e-05, "epoch": 0.17532874139010646, "percentage": 17.5, "elapsed_time": "0:09:26", "remaining_time": "0:44:30"}
{"current_steps": 75, "total_steps": 400, "loss": 1.575343132019043, "lr": 1.876618552635348e-05, "epoch": 0.18785222291797118, "percentage": 18.75, "elapsed_time": "0:10:08", "remaining_time": "0:43:56"}
{"current_steps": 80, "total_steps": 400, "loss": 1.6070398330688476, "lr": 1.8564250430181387e-05, "epoch": 0.20037570444583594, "percentage": 20.0, "elapsed_time": "0:10:48", "remaining_time": "0:43:13"}
{"current_steps": 85, "total_steps": 400, "loss": 1.6005193710327148, "lr": 1.8348280530292712e-05, "epoch": 0.2128991859737007, "percentage": 21.25, "elapsed_time": "0:11:28", "remaining_time": "0:42:31"}
{"current_steps": 90, "total_steps": 400, "loss": 1.5561012268066405, "lr": 1.8118629750849106e-05, "epoch": 0.22542266750156542, "percentage": 22.5, "elapsed_time": "0:12:09", "remaining_time": "0:41:51"}
{"current_steps": 95, "total_steps": 400, "loss": 1.5994838714599608, "lr": 1.7875674435774546e-05, "epoch": 0.23794614902943018, "percentage": 23.75, "elapsed_time": "0:12:49", "remaining_time": "0:41:10"}
{"current_steps": 100, "total_steps": 400, "loss": 1.5856236457824706, "lr": 1.7619812732015664e-05, "epoch": 0.25046963055729493, "percentage": 25.0, "elapsed_time": "0:13:29", "remaining_time": "0:40:27"}
{"current_steps": 105, "total_steps": 400, "loss": 1.5562751770019532, "lr": 1.7351463937072008e-05, "epoch": 0.2629931120851597, "percentage": 26.25, "elapsed_time": "0:14:10", "remaining_time": "0:39:49"}
{"current_steps": 110, "total_steps": 400, "loss": 1.5253159523010253, "lr": 1.7071067811865477e-05, "epoch": 0.27551659361302444, "percentage": 27.5, "elapsed_time": "0:14:50", "remaining_time": "0:39:07"}
{"current_steps": 115, "total_steps": 400, "loss": 1.5002705574035644, "lr": 1.6779083860075032e-05, "epoch": 0.28804007514088914, "percentage": 28.75, "elapsed_time": "0:15:32", "remaining_time": "0:38:32"}
{"current_steps": 120, "total_steps": 400, "loss": 1.5255040168762206, "lr": 1.6475990575117603e-05, "epoch": 0.3005635566687539, "percentage": 30.0, "elapsed_time": "0:16:11", "remaining_time": "0:37:46"}
{"current_steps": 125, "total_steps": 400, "loss": 1.489553737640381, "lr": 1.6162284656009276e-05, "epoch": 0.31308703819661865, "percentage": 31.25, "elapsed_time": "0:16:54", "remaining_time": "0:37:10"}
{"current_steps": 130, "total_steps": 400, "loss": 1.4954115867614746, "lr": 1.5838480193391753e-05, "epoch": 0.3256105197244834, "percentage": 32.5, "elapsed_time": "0:17:34", "remaining_time": "0:36:29"}
{"current_steps": 135, "total_steps": 400, "loss": 1.504003143310547, "lr": 1.5505107827058038e-05, "epoch": 0.33813400125234816, "percentage": 33.75, "elapsed_time": "0:18:15", "remaining_time": "0:35:50"}
{"current_steps": 140, "total_steps": 400, "loss": 1.5397921562194825, "lr": 1.516271387635786e-05, "epoch": 0.3506574827802129, "percentage": 35.0, "elapsed_time": "0:18:54", "remaining_time": "0:35:07"}
{"current_steps": 145, "total_steps": 400, "loss": 1.5844552040100097, "lr": 1.4811859444908053e-05, "epoch": 0.36318096430807767, "percentage": 36.25, "elapsed_time": "0:19:36", "remaining_time": "0:34:28"}
{"current_steps": 150, "total_steps": 400, "loss": 1.4908522605895995, "lr": 1.4453119501074924e-05, "epoch": 0.37570444583594237, "percentage": 37.5, "elapsed_time": "0:20:17", "remaining_time": "0:33:49"}
{"current_steps": 155, "total_steps": 400, "loss": 1.4880791664123536, "lr": 1.4087081935735565e-05, "epoch": 0.3882279273638071, "percentage": 38.75, "elapsed_time": "0:20:58", "remaining_time": "0:33:09"}
{"current_steps": 160, "total_steps": 400, "loss": 1.4971721649169922, "lr": 1.3714346598862168e-05, "epoch": 0.4007514088916719, "percentage": 40.0, "elapsed_time": "0:21:39", "remaining_time": "0:32:29"}
{"current_steps": 165, "total_steps": 400, "loss": 1.4654574394226074, "lr": 1.3335524316508208e-05, "epoch": 0.41327489041953663, "percentage": 41.25, "elapsed_time": "0:22:20", "remaining_time": "0:31:49"}
{"current_steps": 170, "total_steps": 400, "loss": 1.450455379486084, "lr": 1.2951235889807386e-05, "epoch": 0.4257983719474014, "percentage": 42.5, "elapsed_time": "0:23:00", "remaining_time": "0:31:07"}
{"current_steps": 175, "total_steps": 400, "loss": 1.570608425140381, "lr": 1.2562111077625723e-05, "epoch": 0.43832185347526614, "percentage": 43.75, "elapsed_time": "0:23:41", "remaining_time": "0:30:27"}
{"current_steps": 180, "total_steps": 400, "loss": 1.4704577445983886, "lr": 1.2168787564534078e-05, "epoch": 0.45084533500313084, "percentage": 45.0, "elapsed_time": "0:24:22", "remaining_time": "0:29:47"}
{"current_steps": 185, "total_steps": 400, "loss": 1.5063845634460449, "lr": 1.177190991579223e-05, "epoch": 0.4633688165309956, "percentage": 46.25, "elapsed_time": "0:25:01", "remaining_time": "0:29:04"}
{"current_steps": 190, "total_steps": 400, "loss": 1.4744919776916503, "lr": 1.1372128521057155e-05, "epoch": 0.47589229805886035, "percentage": 47.5, "elapsed_time": "0:25:44", "remaining_time": "0:28:26"}
{"current_steps": 195, "total_steps": 400, "loss": 1.511544895172119, "lr": 1.0970098528546482e-05, "epoch": 0.4884157795867251, "percentage": 48.75, "elapsed_time": "0:26:23", "remaining_time": "0:27:44"}
{"current_steps": 200, "total_steps": 400, "loss": 1.4689907073974608, "lr": 1.0566478771403763e-05, "epoch": 0.5009392611145899, "percentage": 50.0, "elapsed_time": "0:27:04", "remaining_time": "0:27:04"}
{"current_steps": 205, "total_steps": 400, "loss": 1.4732332229614258, "lr": 1.0161930688025018e-05, "epoch": 0.5134627426424546, "percentage": 51.25, "elapsed_time": "0:27:45", "remaining_time": "0:26:24"}
{"current_steps": 210, "total_steps": 400, "loss": 1.4493576049804688, "lr": 9.757117238115871e-06, "epoch": 0.5259862241703194, "percentage": 52.5, "elapsed_time": "0:28:26", "remaining_time": "0:25:44"}
{"current_steps": 215, "total_steps": 400, "loss": 1.4741571426391602, "lr": 9.352701816255643e-06, "epoch": 0.5385097056981841, "percentage": 53.75, "elapsed_time": "0:29:07", "remaining_time": "0:25:03"}
{"current_steps": 220, "total_steps": 400, "loss": 1.4440049171447753, "lr": 8.949347164748761e-06, "epoch": 0.5510331872260489, "percentage": 55.0, "elapsed_time": "0:29:49", "remaining_time": "0:24:24"}
{"current_steps": 225, "total_steps": 400, "loss": 1.5042129516601563, "lr": 8.5477142875451e-06, "epoch": 0.5635566687539136, "percentage": 56.25, "elapsed_time": "0:30:30", "remaining_time": "0:23:43"}
{"current_steps": 230, "total_steps": 400, "loss": 1.479151153564453, "lr": 8.148461367009081e-06, "epoch": 0.5760801502817783, "percentage": 57.5, "elapsed_time": "0:31:10", "remaining_time": "0:23:02"}
{"current_steps": 235, "total_steps": 400, "loss": 1.5147887229919434, "lr": 7.752242685312709e-06, "epoch": 0.588603631809643, "percentage": 58.75, "elapsed_time": "0:31:50", "remaining_time": "0:22:21"}
{"current_steps": 240, "total_steps": 400, "loss": 1.4407625198364258, "lr": 7.35970755222007e-06, "epoch": 0.6011271133375078, "percentage": 60.0, "elapsed_time": "0:32:32", "remaining_time": "0:21:41"}
{"current_steps": 245, "total_steps": 400, "loss": 1.4036590576171875, "lr": 6.971499241020495e-06, "epoch": 0.6136505948653725, "percentage": 61.25, "elapsed_time": "0:33:14", "remaining_time": "0:21:02"}
{"current_steps": 250, "total_steps": 400, "loss": 1.4591806411743165, "lr": 6.588253934354039e-06, "epoch": 0.6261740763932373, "percentage": 62.5, "elapsed_time": "0:33:54", "remaining_time": "0:20:20"}
{"current_steps": 255, "total_steps": 400, "loss": 1.5027113914489747, "lr": 6.210599681656933e-06, "epoch": 0.638697557921102, "percentage": 63.75, "elapsed_time": "0:34:36", "remaining_time": "0:19:40"}
{"current_steps": 260, "total_steps": 400, "loss": 1.4685559272766113, "lr": 5.839155369935407e-06, "epoch": 0.6512210394489668, "percentage": 65.0, "elapsed_time": "0:35:17", "remaining_time": "0:19:00"}
{"current_steps": 265, "total_steps": 400, "loss": 1.5166523933410645, "lr": 5.4745297095546125e-06, "epoch": 0.6637445209768316, "percentage": 66.25, "elapsed_time": "0:35:58", "remaining_time": "0:18:19"}
{"current_steps": 270, "total_steps": 400, "loss": 1.4691507339477539, "lr": 5.117320236704697e-06, "epoch": 0.6762680025046963, "percentage": 67.5, "elapsed_time": "0:36:40", "remaining_time": "0:17:39"}
{"current_steps": 275, "total_steps": 400, "loss": 1.53342924118042, "lr": 4.7681123341787e-06, "epoch": 0.6887914840325611, "percentage": 68.75, "elapsed_time": "0:37:18", "remaining_time": "0:16:57"}
{"current_steps": 280, "total_steps": 400, "loss": 1.514073371887207, "lr": 4.427478272067066e-06, "epoch": 0.7013149655604258, "percentage": 70.0, "elapsed_time": "0:37:59", "remaining_time": "0:16:16"}
{"current_steps": 285, "total_steps": 400, "loss": 1.4454584121704102, "lr": 4.095976269940777e-06, "epoch": 0.7138384470882906, "percentage": 71.25, "elapsed_time": "0:38:39", "remaining_time": "0:15:35"}
{"current_steps": 290, "total_steps": 400, "loss": 1.4844335556030273, "lr": 3.7741495820600128e-06, "epoch": 0.7263619286161553, "percentage": 72.5, "elapsed_time": "0:39:20", "remaining_time": "0:14:55"}
{"current_steps": 295, "total_steps": 400, "loss": 1.4866701126098634, "lr": 3.4625256071074776e-06, "epoch": 0.73888541014402, "percentage": 73.75, "elapsed_time": "0:39:58", "remaining_time": "0:14:13"}
{"current_steps": 300, "total_steps": 400, "loss": 1.4392054557800293, "lr": 3.1616150239052647e-06, "epoch": 0.7514088916718847, "percentage": 75.0, "elapsed_time": "0:40:42", "remaining_time": "0:13:34"}
{"current_steps": 305, "total_steps": 400, "loss": 1.4637357711791992, "lr": 2.8719109545317102e-06, "epoch": 0.7639323731997495, "percentage": 76.25, "elapsed_time": "0:41:21", "remaining_time": "0:12:52"}
{"current_steps": 310, "total_steps": 400, "loss": 1.4387860298156738, "lr": 2.593888156209603e-06, "epoch": 0.7764558547276142, "percentage": 77.5, "elapsed_time": "0:42:04", "remaining_time": "0:12:13"}
{"current_steps": 315, "total_steps": 400, "loss": 1.4650882720947265, "lr": 2.328002243290138e-06, "epoch": 0.788979336255479, "percentage": 78.75, "elapsed_time": "0:42:46", "remaining_time": "0:11:32"}
{"current_steps": 320, "total_steps": 400, "loss": 1.5315435409545899, "lr": 2.074688940607529e-06, "epoch": 0.8015028177833438, "percentage": 80.0, "elapsed_time": "0:43:26", "remaining_time": "0:10:51"}
{"current_steps": 325, "total_steps": 400, "loss": 1.5125369071960448, "lr": 1.8343633694278895e-06, "epoch": 0.8140262993112085, "percentage": 81.25, "elapsed_time": "0:44:07", "remaining_time": "0:10:10"}
{"current_steps": 330, "total_steps": 400, "loss": 1.4377523422241212, "lr": 1.607419367162577e-06, "epoch": 0.8265497808390733, "percentage": 82.5, "elapsed_time": "0:44:48", "remaining_time": "0:09:30"}
{"current_steps": 335, "total_steps": 400, "loss": 1.4360872268676759, "lr": 1.3942288419607476e-06, "epoch": 0.839073262366938, "percentage": 83.75, "elapsed_time": "0:45:29", "remaining_time": "0:08:49"}
{"current_steps": 340, "total_steps": 400, "loss": 1.4957749366760253, "lr": 1.195141163238892e-06, "epoch": 0.8515967438948028, "percentage": 85.0, "elapsed_time": "0:46:10", "remaining_time": "0:08:08"}
{"current_steps": 345, "total_steps": 400, "loss": 1.4363853454589843, "lr": 1.010482589146048e-06, "epoch": 0.8641202254226675, "percentage": 86.25, "elapsed_time": "0:46:50", "remaining_time": "0:07:28"}
{"current_steps": 350, "total_steps": 400, "loss": 1.5025806427001953, "lr": 8.405557319029911e-07, "epoch": 0.8766437069505323, "percentage": 87.5, "elapsed_time": "0:47:31", "remaining_time": "0:06:47"}
{"current_steps": 355, "total_steps": 400, "loss": 1.4651078224182128, "lr": 6.856390618915775e-07, "epoch": 0.889167188478397, "percentage": 88.75, "elapsed_time": "0:48:12", "remaining_time": "0:06:06"}
{"current_steps": 360, "total_steps": 400, "loss": 1.464914894104004, "lr": 5.459864513068991e-07, "epoch": 0.9016906700062617, "percentage": 90.0, "elapsed_time": "0:48:52", "remaining_time": "0:05:25"}
{"current_steps": 365, "total_steps": 400, "loss": 1.44300537109375, "lr": 4.218267581201296e-07, "epoch": 0.9142141515341264, "percentage": 91.25, "elapsed_time": "0:49:32", "remaining_time": "0:04:45"}
{"current_steps": 370, "total_steps": 400, "loss": 1.4994802474975586, "lr": 3.133634510338235e-07, "epoch": 0.9267376330619912, "percentage": 92.5, "elapsed_time": "0:50:10", "remaining_time": "0:04:04"}
{"current_steps": 375, "total_steps": 400, "loss": 1.4373616218566894, "lr": 2.2077427604429435e-07, "epoch": 0.939261114589856, "percentage": 93.75, "elapsed_time": "0:50:52", "remaining_time": "0:03:23"}
{"current_steps": 380, "total_steps": 400, "loss": 1.4988561630249024, "lr": 1.4421096515749855e-07, "epoch": 0.9517845961177207, "percentage": 95.0, "elapsed_time": "0:51:33", "remaining_time": "0:02:42"}
{"current_steps": 385, "total_steps": 400, "loss": 1.5371465682983398, "lr": 8.379898773574924e-08, "epoch": 0.9643080776455855, "percentage": 96.25, "elapsed_time": "0:52:14", "remaining_time": "0:02:02"}
{"current_steps": 390, "total_steps": 400, "loss": 1.4375405311584473, "lr": 3.963734488278248e-08, "epoch": 0.9768315591734502, "percentage": 97.5, "elapsed_time": "0:52:54", "remaining_time": "0:01:21"}
{"current_steps": 395, "total_steps": 400, "loss": 1.4510549545288085, "lr": 1.179840720409331e-08, "epoch": 0.989355040701315, "percentage": 98.75, "elapsed_time": "0:53:35", "remaining_time": "0:00:40"}
{"current_steps": 400, "total_steps": 400, "loss": 1.4790672302246093, "lr": 3.277962084369257e-10, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:54:10", "remaining_time": "0:00:00"}
{"current_steps": 400, "total_steps": 400, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:54:13", "remaining_time": "0:00:00"}

603
trainer_state.json Normal file
View File

@@ -0,0 +1,603 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.012523481527864746,
"grad_norm": 29.625,
"learning_rate": 6.666666666666667e-06,
"loss": 3.0092775344848635,
"step": 5
},
{
"epoch": 0.025046963055729492,
"grad_norm": 8.8125,
"learning_rate": 1.5000000000000002e-05,
"loss": 2.547764778137207,
"step": 10
},
{
"epoch": 0.03757044458359424,
"grad_norm": 4.9375,
"learning_rate": 1.9998688836656322e-05,
"loss": 2.233675956726074,
"step": 15
},
{
"epoch": 0.050093926111458985,
"grad_norm": 3.015625,
"learning_rate": 1.9983942197426272e-05,
"loss": 2.057873344421387,
"step": 20
},
{
"epoch": 0.06261740763932373,
"grad_norm": 3.09375,
"learning_rate": 1.995283421166614e-05,
"loss": 1.851465606689453,
"step": 25
},
{
"epoch": 0.07514088916718847,
"grad_norm": 3.265625,
"learning_rate": 1.9905415858090036e-05,
"loss": 1.855565071105957,
"step": 30
},
{
"epoch": 0.08766437069505323,
"grad_norm": 2.359375,
"learning_rate": 1.9841764844290744e-05,
"loss": 1.752499771118164,
"step": 35
},
{
"epoch": 0.10018785222291797,
"grad_norm": 2.921875,
"learning_rate": 1.976198547939518e-05,
"loss": 1.8114988327026367,
"step": 40
},
{
"epoch": 0.11271133375078271,
"grad_norm": 2.59375,
"learning_rate": 1.9666208503126115e-05,
"loss": 1.6981731414794923,
"step": 45
},
{
"epoch": 0.12523481527864747,
"grad_norm": 2.34375,
"learning_rate": 1.955459087155033e-05,
"loss": 1.6682065963745116,
"step": 50
},
{
"epoch": 0.13775829680651222,
"grad_norm": 2.21875,
"learning_rate": 1.9427315499864345e-05,
"loss": 1.654319953918457,
"step": 55
},
{
"epoch": 0.15028177833437695,
"grad_norm": 2.109375,
"learning_rate": 1.928459096263918e-05,
"loss": 1.628897476196289,
"step": 60
},
{
"epoch": 0.1628052598622417,
"grad_norm": 2.140625,
"learning_rate": 1.9126651152015404e-05,
"loss": 1.588959312438965,
"step": 65
},
{
"epoch": 0.17532874139010646,
"grad_norm": 2.390625,
"learning_rate": 1.8953754894408617e-05,
"loss": 1.643252182006836,
"step": 70
},
{
"epoch": 0.18785222291797118,
"grad_norm": 2.59375,
"learning_rate": 1.876618552635348e-05,
"loss": 1.575343132019043,
"step": 75
},
{
"epoch": 0.20037570444583594,
"grad_norm": 2.3125,
"learning_rate": 1.8564250430181387e-05,
"loss": 1.6070398330688476,
"step": 80
},
{
"epoch": 0.2128991859737007,
"grad_norm": 2.09375,
"learning_rate": 1.8348280530292712e-05,
"loss": 1.6005193710327148,
"step": 85
},
{
"epoch": 0.22542266750156542,
"grad_norm": 2.296875,
"learning_rate": 1.8118629750849106e-05,
"loss": 1.5561012268066405,
"step": 90
},
{
"epoch": 0.23794614902943018,
"grad_norm": 1.9140625,
"learning_rate": 1.7875674435774546e-05,
"loss": 1.5994838714599608,
"step": 95
},
{
"epoch": 0.25046963055729493,
"grad_norm": 2.046875,
"learning_rate": 1.7619812732015664e-05,
"loss": 1.5856236457824706,
"step": 100
},
{
"epoch": 0.2629931120851597,
"grad_norm": 2.703125,
"learning_rate": 1.7351463937072008e-05,
"loss": 1.5562751770019532,
"step": 105
},
{
"epoch": 0.27551659361302444,
"grad_norm": 2.234375,
"learning_rate": 1.7071067811865477e-05,
"loss": 1.5253159523010253,
"step": 110
},
{
"epoch": 0.28804007514088914,
"grad_norm": 2.875,
"learning_rate": 1.6779083860075032e-05,
"loss": 1.5002705574035644,
"step": 115
},
{
"epoch": 0.3005635566687539,
"grad_norm": 2.296875,
"learning_rate": 1.6475990575117603e-05,
"loss": 1.5255040168762206,
"step": 120
},
{
"epoch": 0.31308703819661865,
"grad_norm": 3.53125,
"learning_rate": 1.6162284656009276e-05,
"loss": 1.489553737640381,
"step": 125
},
{
"epoch": 0.3256105197244834,
"grad_norm": 2.390625,
"learning_rate": 1.5838480193391753e-05,
"loss": 1.4954115867614746,
"step": 130
},
{
"epoch": 0.33813400125234816,
"grad_norm": 1.921875,
"learning_rate": 1.5505107827058038e-05,
"loss": 1.504003143310547,
"step": 135
},
{
"epoch": 0.3506574827802129,
"grad_norm": 2.078125,
"learning_rate": 1.516271387635786e-05,
"loss": 1.5397921562194825,
"step": 140
},
{
"epoch": 0.36318096430807767,
"grad_norm": 2.6875,
"learning_rate": 1.4811859444908053e-05,
"loss": 1.5844552040100097,
"step": 145
},
{
"epoch": 0.37570444583594237,
"grad_norm": 2.328125,
"learning_rate": 1.4453119501074924e-05,
"loss": 1.4908522605895995,
"step": 150
},
{
"epoch": 0.3882279273638071,
"grad_norm": 2.5625,
"learning_rate": 1.4087081935735565e-05,
"loss": 1.4880791664123536,
"step": 155
},
{
"epoch": 0.4007514088916719,
"grad_norm": 2.234375,
"learning_rate": 1.3714346598862168e-05,
"loss": 1.4971721649169922,
"step": 160
},
{
"epoch": 0.41327489041953663,
"grad_norm": 3.03125,
"learning_rate": 1.3335524316508208e-05,
"loss": 1.4654574394226074,
"step": 165
},
{
"epoch": 0.4257983719474014,
"grad_norm": 1.9296875,
"learning_rate": 1.2951235889807386e-05,
"loss": 1.450455379486084,
"step": 170
},
{
"epoch": 0.43832185347526614,
"grad_norm": 2.21875,
"learning_rate": 1.2562111077625723e-05,
"loss": 1.570608425140381,
"step": 175
},
{
"epoch": 0.45084533500313084,
"grad_norm": 2.46875,
"learning_rate": 1.2168787564534078e-05,
"loss": 1.4704577445983886,
"step": 180
},
{
"epoch": 0.4633688165309956,
"grad_norm": 2.140625,
"learning_rate": 1.177190991579223e-05,
"loss": 1.5063845634460449,
"step": 185
},
{
"epoch": 0.47589229805886035,
"grad_norm": 2.3125,
"learning_rate": 1.1372128521057155e-05,
"loss": 1.4744919776916503,
"step": 190
},
{
"epoch": 0.4884157795867251,
"grad_norm": 2.390625,
"learning_rate": 1.0970098528546482e-05,
"loss": 1.511544895172119,
"step": 195
},
{
"epoch": 0.5009392611145899,
"grad_norm": 1.7578125,
"learning_rate": 1.0566478771403763e-05,
"loss": 1.4689907073974608,
"step": 200
},
{
"epoch": 0.5134627426424546,
"grad_norm": 2.4375,
"learning_rate": 1.0161930688025018e-05,
"loss": 1.4732332229614258,
"step": 205
},
{
"epoch": 0.5259862241703194,
"grad_norm": 2.359375,
"learning_rate": 9.757117238115871e-06,
"loss": 1.4493576049804688,
"step": 210
},
{
"epoch": 0.5385097056981841,
"grad_norm": 1.9296875,
"learning_rate": 9.352701816255643e-06,
"loss": 1.4741571426391602,
"step": 215
},
{
"epoch": 0.5510331872260489,
"grad_norm": 2.484375,
"learning_rate": 8.949347164748761e-06,
"loss": 1.4440049171447753,
"step": 220
},
{
"epoch": 0.5635566687539136,
"grad_norm": 2.3125,
"learning_rate": 8.5477142875451e-06,
"loss": 1.5042129516601563,
"step": 225
},
{
"epoch": 0.5760801502817783,
"grad_norm": 1.9921875,
"learning_rate": 8.148461367009081e-06,
"loss": 1.479151153564453,
"step": 230
},
{
"epoch": 0.588603631809643,
"grad_norm": 1.984375,
"learning_rate": 7.752242685312709e-06,
"loss": 1.5147887229919434,
"step": 235
},
{
"epoch": 0.6011271133375078,
"grad_norm": 3.046875,
"learning_rate": 7.35970755222007e-06,
"loss": 1.4407625198364258,
"step": 240
},
{
"epoch": 0.6136505948653725,
"grad_norm": 3.15625,
"learning_rate": 6.971499241020495e-06,
"loss": 1.4036590576171875,
"step": 245
},
{
"epoch": 0.6261740763932373,
"grad_norm": 2.53125,
"learning_rate": 6.588253934354039e-06,
"loss": 1.4591806411743165,
"step": 250
},
{
"epoch": 0.638697557921102,
"grad_norm": 2.0625,
"learning_rate": 6.210599681656933e-06,
"loss": 1.5027113914489747,
"step": 255
},
{
"epoch": 0.6512210394489668,
"grad_norm": 1.953125,
"learning_rate": 5.839155369935407e-06,
"loss": 1.4685559272766113,
"step": 260
},
{
"epoch": 0.6637445209768316,
"grad_norm": 2.375,
"learning_rate": 5.4745297095546125e-06,
"loss": 1.5166523933410645,
"step": 265
},
{
"epoch": 0.6762680025046963,
"grad_norm": 2.625,
"learning_rate": 5.117320236704697e-06,
"loss": 1.4691507339477539,
"step": 270
},
{
"epoch": 0.6887914840325611,
"grad_norm": 2.078125,
"learning_rate": 4.7681123341787e-06,
"loss": 1.53342924118042,
"step": 275
},
{
"epoch": 0.7013149655604258,
"grad_norm": 2.453125,
"learning_rate": 4.427478272067066e-06,
"loss": 1.514073371887207,
"step": 280
},
{
"epoch": 0.7138384470882906,
"grad_norm": 2.234375,
"learning_rate": 4.095976269940777e-06,
"loss": 1.4454584121704102,
"step": 285
},
{
"epoch": 0.7263619286161553,
"grad_norm": 1.828125,
"learning_rate": 3.7741495820600128e-06,
"loss": 1.4844335556030273,
"step": 290
},
{
"epoch": 0.73888541014402,
"grad_norm": 2.015625,
"learning_rate": 3.4625256071074776e-06,
"loss": 1.4866701126098634,
"step": 295
},
{
"epoch": 0.7514088916718847,
"grad_norm": 2.53125,
"learning_rate": 3.1616150239052647e-06,
"loss": 1.4392054557800293,
"step": 300
},
{
"epoch": 0.7639323731997495,
"grad_norm": 2.5625,
"learning_rate": 2.8719109545317102e-06,
"loss": 1.4637357711791992,
"step": 305
},
{
"epoch": 0.7764558547276142,
"grad_norm": 2.390625,
"learning_rate": 2.593888156209603e-06,
"loss": 1.4387860298156738,
"step": 310
},
{
"epoch": 0.788979336255479,
"grad_norm": 2.265625,
"learning_rate": 2.328002243290138e-06,
"loss": 1.4650882720947265,
"step": 315
},
{
"epoch": 0.8015028177833438,
"grad_norm": 1.984375,
"learning_rate": 2.074688940607529e-06,
"loss": 1.5315435409545899,
"step": 320
},
{
"epoch": 0.8140262993112085,
"grad_norm": 2.515625,
"learning_rate": 1.8343633694278895e-06,
"loss": 1.5125369071960448,
"step": 325
},
{
"epoch": 0.8265497808390733,
"grad_norm": 2.203125,
"learning_rate": 1.607419367162577e-06,
"loss": 1.4377523422241212,
"step": 330
},
{
"epoch": 0.839073262366938,
"grad_norm": 2.4375,
"learning_rate": 1.3942288419607476e-06,
"loss": 1.4360872268676759,
"step": 335
},
{
"epoch": 0.8515967438948028,
"grad_norm": 1.9609375,
"learning_rate": 1.195141163238892e-06,
"loss": 1.4957749366760253,
"step": 340
},
{
"epoch": 0.8641202254226675,
"grad_norm": 1.7578125,
"learning_rate": 1.010482589146048e-06,
"loss": 1.4363853454589843,
"step": 345
},
{
"epoch": 0.8766437069505323,
"grad_norm": 2.0625,
"learning_rate": 8.405557319029911e-07,
"loss": 1.5025806427001953,
"step": 350
},
{
"epoch": 0.889167188478397,
"grad_norm": 1.9453125,
"learning_rate": 6.856390618915775e-07,
"loss": 1.4651078224182128,
"step": 355
},
{
"epoch": 0.9016906700062617,
"grad_norm": 2.140625,
"learning_rate": 5.459864513068991e-07,
"loss": 1.464914894104004,
"step": 360
},
{
"epoch": 0.9142141515341264,
"grad_norm": 1.890625,
"learning_rate": 4.218267581201296e-07,
"loss": 1.44300537109375,
"step": 365
},
{
"epoch": 0.9267376330619912,
"grad_norm": 2.359375,
"learning_rate": 3.133634510338235e-07,
"loss": 1.4994802474975586,
"step": 370
},
{
"epoch": 0.939261114589856,
"grad_norm": 2.25,
"learning_rate": 2.2077427604429435e-07,
"loss": 1.4373616218566894,
"step": 375
},
{
"epoch": 0.9517845961177207,
"grad_norm": 2.359375,
"learning_rate": 1.4421096515749855e-07,
"loss": 1.4988561630249024,
"step": 380
},
{
"epoch": 0.9643080776455855,
"grad_norm": 2.25,
"learning_rate": 8.379898773574924e-08,
"loss": 1.5371465682983398,
"step": 385
},
{
"epoch": 0.9768315591734502,
"grad_norm": 2.59375,
"learning_rate": 3.963734488278248e-08,
"loss": 1.4375405311584473,
"step": 390
},
{
"epoch": 0.989355040701315,
"grad_norm": 2.546875,
"learning_rate": 1.179840720409331e-08,
"loss": 1.4510549545288085,
"step": 395
},
{
"epoch": 1.0,
"grad_norm": 3.5625,
"learning_rate": 3.277962084369257e-10,
"loss": 1.4790672302246093,
"step": 400
},
{
"epoch": 1.0,
"step": 400,
"total_flos": 1.9165347193492685e+17,
"train_loss": 1.5697158980369568,
"train_runtime": 3253.1715,
"train_samples_per_second": 0.491,
"train_steps_per_second": 0.123
}
],
"logging_steps": 5,
"max_steps": 400,
"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": true,
"should_training_stop": true
},
"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 sha256:273f769e444be04697b84c34148346e60c10e764e55272bdfc1a679083132aae
size 5969

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 39 KiB