lldois/v01_all_lr1e5
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/v01_all_lr1e5
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-31 12:52:20 +08:00
commit a7379e388d
16 changed files with 3222 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: v01_all_lr1e5
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. -->
# v01_all_lr1e5
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 overnight_all 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: 1e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 202607061
- 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": 1.7490570976506525,
"train_runtime": 3250.6471,
"train_samples_per_second": 0.49,
"train_steps_per_second": 0.122
}

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 sha256:1e4add656e8d0ef1c1eea4122ff7da4958b8067611d6196d9a8b7f23972044f9
size 1602902832

3
runs/Jul06_00-06-24_ubuntu-System-Product-Name/events.out.tfevents.1783267584.ubuntu-System-Product-Name.1406827.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cca022f5e874ad6c1d2a7be1a11bd203535990f92f1daaabc869b8dc0bf70ee2
size 22871

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
}

2244
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": 1.7490570976506525,
"train_runtime": 3250.6471,
"train_samples_per_second": 0.49,
"train_steps_per_second": 0.122
}

80
trainer_log.jsonl Normal file
View File

@@ -0,0 +1,80 @@
{"current_steps": 5, "total_steps": 398, "loss": 2.9656538009643554, "lr": 3.3333333333333333e-06, "epoch": 0.01256281407035176, "percentage": 1.26, "elapsed_time": "0:00:39", "remaining_time": "0:51:17"}
{"current_steps": 10, "total_steps": 398, "loss": 2.7247514724731445, "lr": 7.500000000000001e-06, "epoch": 0.02512562814070352, "percentage": 2.51, "elapsed_time": "0:01:20", "remaining_time": "0:51:55"}
{"current_steps": 15, "total_steps": 398, "loss": 2.5403032302856445, "lr": 9.99933760728612e-06, "epoch": 0.03768844221105527, "percentage": 3.77, "elapsed_time": "0:02:00", "remaining_time": "0:51:26"}
{"current_steps": 20, "total_steps": 398, "loss": 2.3779970169067384, "lr": 9.991887704680723e-06, "epoch": 0.05025125628140704, "percentage": 5.03, "elapsed_time": "0:02:41", "remaining_time": "0:50:56"}
{"current_steps": 25, "total_steps": 398, "loss": 2.1928905487060546, "lr": 9.976172285185315e-06, "epoch": 0.06281407035175879, "percentage": 6.28, "elapsed_time": "0:03:23", "remaining_time": "0:50:30"}
{"current_steps": 30, "total_steps": 398, "loss": 2.082417106628418, "lr": 9.952217370231655e-06, "epoch": 0.07537688442211055, "percentage": 7.54, "elapsed_time": "0:04:04", "remaining_time": "0:49:54"}
{"current_steps": 35, "total_steps": 398, "loss": 1.9925090789794921, "lr": 9.920062624124282e-06, "epoch": 0.08793969849246232, "percentage": 8.79, "elapsed_time": "0:04:44", "remaining_time": "0:49:11"}
{"current_steps": 40, "total_steps": 398, "loss": 2.0241403579711914, "lr": 9.879761288364767e-06, "epoch": 0.10050251256281408, "percentage": 10.05, "elapsed_time": "0:05:25", "remaining_time": "0:48:29"}
{"current_steps": 45, "total_steps": 398, "loss": 1.8994447708129882, "lr": 9.831380093494957e-06, "epoch": 0.11306532663316583, "percentage": 11.31, "elapsed_time": "0:06:04", "remaining_time": "0:47:39"}
{"current_steps": 50, "total_steps": 398, "loss": 1.8455327987670898, "lr": 9.77499914860525e-06, "epoch": 0.12562814070351758, "percentage": 12.56, "elapsed_time": "0:06:45", "remaining_time": "0:47:03"}
{"current_steps": 55, "total_steps": 398, "loss": 1.8259857177734375, "lr": 9.710711808690754e-06, "epoch": 0.13819095477386933, "percentage": 13.82, "elapsed_time": "0:07:25", "remaining_time": "0:46:16"}
{"current_steps": 60, "total_steps": 398, "loss": 1.8774749755859375, "lr": 9.638624520075047e-06, "epoch": 0.1507537688442211, "percentage": 15.08, "elapsed_time": "0:08:04", "remaining_time": "0:45:30"}
{"current_steps": 65, "total_steps": 398, "loss": 1.8711318969726562, "lr": 9.558856644157432e-06, "epoch": 0.16331658291457288, "percentage": 16.33, "elapsed_time": "0:08:45", "remaining_time": "0:44:53"}
{"current_steps": 70, "total_steps": 398, "loss": 1.804541778564453, "lr": 9.471540259775554e-06, "epoch": 0.17587939698492464, "percentage": 17.59, "elapsed_time": "0:09:27", "remaining_time": "0:44:20"}
{"current_steps": 75, "total_steps": 398, "loss": 1.7933189392089843, "lr": 9.376819944510598e-06, "epoch": 0.1884422110552764, "percentage": 18.84, "elapsed_time": "0:10:07", "remaining_time": "0:43:34"}
{"current_steps": 80, "total_steps": 398, "loss": 1.7203624725341797, "lr": 9.274852535297198e-06, "epoch": 0.20100502512562815, "percentage": 20.1, "elapsed_time": "0:10:48", "remaining_time": "0:42:58"}
{"current_steps": 85, "total_steps": 398, "loss": 1.7706247329711915, "lr": 9.165806868734444e-06, "epoch": 0.2135678391959799, "percentage": 21.36, "elapsed_time": "0:11:28", "remaining_time": "0:42:14"}
{"current_steps": 90, "total_steps": 398, "loss": 1.7302061080932618, "lr": 9.049863501527947e-06, "epoch": 0.22613065326633167, "percentage": 22.61, "elapsed_time": "0:12:08", "remaining_time": "0:41:31"}
{"current_steps": 95, "total_steps": 398, "loss": 1.7422285079956055, "lr": 8.927214411525895e-06, "epoch": 0.23869346733668342, "percentage": 23.87, "elapsed_time": "0:12:48", "remaining_time": "0:40:52"}
{"current_steps": 100, "total_steps": 398, "loss": 1.7749662399291992, "lr": 8.798062679844077e-06, "epoch": 0.25125628140703515, "percentage": 25.13, "elapsed_time": "0:13:28", "remaining_time": "0:40:10"}
{"current_steps": 105, "total_steps": 398, "loss": 1.6960893630981446, "lr": 8.662622154606238e-06, "epoch": 0.2638190954773869, "percentage": 26.38, "elapsed_time": "0:14:10", "remaining_time": "0:39:33"}
{"current_steps": 110, "total_steps": 398, "loss": 1.663231086730957, "lr": 8.521117096856529e-06, "epoch": 0.27638190954773867, "percentage": 27.64, "elapsed_time": "0:14:52", "remaining_time": "0:38:55"}
{"current_steps": 115, "total_steps": 398, "loss": 1.6814579010009765, "lr": 8.373781809230355e-06, "epoch": 0.2889447236180904, "percentage": 28.89, "elapsed_time": "0:15:32", "remaining_time": "0:38:14"}
{"current_steps": 120, "total_steps": 398, "loss": 1.6490394592285156, "lr": 8.220860247998455e-06, "epoch": 0.3015075376884422, "percentage": 30.15, "elapsed_time": "0:16:15", "remaining_time": "0:37:38"}
{"current_steps": 125, "total_steps": 398, "loss": 1.6724288940429688, "lr": 8.062605619126585e-06, "epoch": 0.314070351758794, "percentage": 31.41, "elapsed_time": "0:16:55", "remaining_time": "0:36:58"}
{"current_steps": 130, "total_steps": 398, "loss": 1.7372112274169922, "lr": 7.899279959019654e-06, "epoch": 0.32663316582914576, "percentage": 32.66, "elapsed_time": "0:17:36", "remaining_time": "0:36:18"}
{"current_steps": 135, "total_steps": 398, "loss": 1.6612102508544921, "lr": 7.73115370064452e-06, "epoch": 0.3391959798994975, "percentage": 33.92, "elapsed_time": "0:18:16", "remaining_time": "0:35:35"}
{"current_steps": 140, "total_steps": 398, "loss": 1.6610906600952149, "lr": 7.558505225749827e-06, "epoch": 0.35175879396984927, "percentage": 35.18, "elapsed_time": "0:18:57", "remaining_time": "0:34:55"}
{"current_steps": 145, "total_steps": 398, "loss": 1.6504524230957032, "lr": 7.381620403924333e-06, "epoch": 0.36432160804020103, "percentage": 36.43, "elapsed_time": "0:19:38", "remaining_time": "0:34:16"}
{"current_steps": 150, "total_steps": 398, "loss": 1.6796260833740235, "lr": 7.200792119256961e-06, "epoch": 0.3768844221105528, "percentage": 37.69, "elapsed_time": "0:20:18", "remaining_time": "0:33:35"}
{"current_steps": 155, "total_steps": 398, "loss": 1.6536401748657226, "lr": 7.0163197853822975e-06, "epoch": 0.38944723618090454, "percentage": 38.94, "elapsed_time": "0:21:01", "remaining_time": "0:32:57"}
{"current_steps": 160, "total_steps": 398, "loss": 1.6703350067138671, "lr": 6.828508849714546e-06, "epoch": 0.4020100502512563, "percentage": 40.2, "elapsed_time": "0:21:42", "remaining_time": "0:32:16"}
{"current_steps": 165, "total_steps": 398, "loss": 1.658207321166992, "lr": 6.6376702876908e-06, "epoch": 0.41457286432160806, "percentage": 41.46, "elapsed_time": "0:22:23", "remaining_time": "0:31:36"}
{"current_steps": 170, "total_steps": 398, "loss": 1.6739206314086914, "lr": 6.444120087861081e-06, "epoch": 0.4271356783919598, "percentage": 42.71, "elapsed_time": "0:23:04", "remaining_time": "0:30:57"}
{"current_steps": 175, "total_steps": 398, "loss": 1.679785919189453, "lr": 6.2481787286777116e-06, "epoch": 0.4396984924623116, "percentage": 43.97, "elapsed_time": "0:23:46", "remaining_time": "0:30:17"}
{"current_steps": 180, "total_steps": 398, "loss": 1.652729606628418, "lr": 6.050170647850351e-06, "epoch": 0.45226130653266333, "percentage": 45.23, "elapsed_time": "0:24:28", "remaining_time": "0:29:38"}
{"current_steps": 185, "total_steps": 398, "loss": 1.6558731079101563, "lr": 5.850423705145334e-06, "epoch": 0.4648241206030151, "percentage": 46.48, "elapsed_time": "0:25:10", "remaining_time": "0:28:58"}
{"current_steps": 190, "total_steps": 398, "loss": 1.6815605163574219, "lr": 5.64926863951881e-06, "epoch": 0.47738693467336685, "percentage": 47.74, "elapsed_time": "0:25:51", "remaining_time": "0:28:18"}
{"current_steps": 195, "total_steps": 398, "loss": 1.7241903305053712, "lr": 5.447038521482542e-06, "epoch": 0.4899497487437186, "percentage": 48.99, "elapsed_time": "0:26:30", "remaining_time": "0:27:35"}
{"current_steps": 200, "total_steps": 398, "loss": 1.6395009994506835, "lr": 5.244068201609132e-06, "epoch": 0.5025125628140703, "percentage": 50.25, "elapsed_time": "0:27:09", "remaining_time": "0:26:53"}
{"current_steps": 205, "total_steps": 398, "loss": 1.6607843399047852, "lr": 5.040693756089865e-06, "epoch": 0.5150753768844221, "percentage": 51.51, "elapsed_time": "0:27:50", "remaining_time": "0:26:12"}
{"current_steps": 210, "total_steps": 398, "loss": 1.670051383972168, "lr": 4.837251930263149e-06, "epoch": 0.5276381909547738, "percentage": 52.76, "elapsed_time": "0:28:30", "remaining_time": "0:25:31"}
{"current_steps": 215, "total_steps": 398, "loss": 1.6406648635864258, "lr": 4.634079581035029e-06, "epoch": 0.5402010050251256, "percentage": 54.02, "elapsed_time": "0:29:11", "remaining_time": "0:24:50"}
{"current_steps": 220, "total_steps": 398, "loss": 1.7157506942749023, "lr": 4.431513119114934e-06, "epoch": 0.5527638190954773, "percentage": 55.28, "elapsed_time": "0:29:50", "remaining_time": "0:24:08"}
{"current_steps": 225, "total_steps": 398, "loss": 1.631689453125, "lr": 4.229887951990255e-06, "epoch": 0.5653266331658291, "percentage": 56.53, "elapsed_time": "0:30:32", "remaining_time": "0:23:28"}
{"current_steps": 230, "total_steps": 398, "loss": 1.6348350524902344, "lr": 4.029537928562028e-06, "epoch": 0.5778894472361809, "percentage": 57.79, "elapsed_time": "0:31:12", "remaining_time": "0:22:47"}
{"current_steps": 235, "total_steps": 398, "loss": 1.6371662139892578, "lr": 3.83079478636133e-06, "epoch": 0.5904522613065326, "percentage": 59.05, "elapsed_time": "0:31:53", "remaining_time": "0:22:07"}
{"current_steps": 240, "total_steps": 398, "loss": 1.6417142868041992, "lr": 3.633987602261647e-06, "epoch": 0.6030150753768844, "percentage": 60.3, "elapsed_time": "0:32:35", "remaining_time": "0:21:27"}
{"current_steps": 245, "total_steps": 398, "loss": 1.651812744140625, "lr": 3.439442247596724e-06, "epoch": 0.6155778894472361, "percentage": 61.56, "elapsed_time": "0:33:15", "remaining_time": "0:20:46"}
{"current_steps": 250, "total_steps": 398, "loss": 1.6704858779907226, "lr": 3.24748084858614e-06, "epoch": 0.628140703517588, "percentage": 62.81, "elapsed_time": "0:33:57", "remaining_time": "0:20:05"}
{"current_steps": 255, "total_steps": 398, "loss": 1.6126070022583008, "lr": 3.0584212529619777e-06, "epoch": 0.6407035175879398, "percentage": 64.07, "elapsed_time": "0:34:38", "remaining_time": "0:19:25"}
{"current_steps": 260, "total_steps": 398, "loss": 1.650954246520996, "lr": 2.872576503679789e-06, "epoch": 0.6532663316582915, "percentage": 65.33, "elapsed_time": "0:35:18", "remaining_time": "0:18:44"}
{"current_steps": 265, "total_steps": 398, "loss": 1.6697248458862304, "lr": 2.6902543205852496e-06, "epoch": 0.6658291457286433, "percentage": 66.58, "elapsed_time": "0:36:00", "remaining_time": "0:18:04"}
{"current_steps": 270, "total_steps": 398, "loss": 1.66760311126709, "lr": 2.511756590894765e-06, "epoch": 0.678391959798995, "percentage": 67.84, "elapsed_time": "0:36:42", "remaining_time": "0:17:23"}
{"current_steps": 275, "total_steps": 398, "loss": 1.669024658203125, "lr": 2.3373788693337024e-06, "epoch": 0.6909547738693468, "percentage": 69.1, "elapsed_time": "0:37:21", "remaining_time": "0:16:42"}
{"current_steps": 280, "total_steps": 398, "loss": 1.6077774047851563, "lr": 2.167409888759856e-06, "epoch": 0.7035175879396985, "percentage": 70.35, "elapsed_time": "0:38:04", "remaining_time": "0:16:02"}
{"current_steps": 285, "total_steps": 398, "loss": 1.5952661514282227, "lr": 2.002131082082549e-06, "epoch": 0.7160804020100503, "percentage": 71.61, "elapsed_time": "0:38:46", "remaining_time": "0:15:22"}
{"current_steps": 290, "total_steps": 398, "loss": 1.6444393157958985, "lr": 1.8418161162688613e-06, "epoch": 0.7286432160804021, "percentage": 72.86, "elapsed_time": "0:39:25", "remaining_time": "0:14:41"}
{"current_steps": 295, "total_steps": 398, "loss": 1.661176872253418, "lr": 1.6867304392086575e-06, "epoch": 0.7412060301507538, "percentage": 74.12, "elapsed_time": "0:40:08", "remaining_time": "0:14:00"}
{"current_steps": 300, "total_steps": 398, "loss": 1.6453720092773438, "lr": 1.5371308401886759e-06, "epoch": 0.7537688442211056, "percentage": 75.38, "elapsed_time": "0:40:49", "remaining_time": "0:13:20"}
{"current_steps": 305, "total_steps": 398, "loss": 1.627047348022461, "lr": 1.393265024703422e-06, "epoch": 0.7663316582914573, "percentage": 76.63, "elapsed_time": "0:41:31", "remaining_time": "0:12:39"}
{"current_steps": 310, "total_steps": 398, "loss": 1.6264894485473633, "lr": 1.255371204306956e-06, "epoch": 0.7788944723618091, "percentage": 77.89, "elapsed_time": "0:42:12", "remaining_time": "0:11:58"}
{"current_steps": 315, "total_steps": 398, "loss": 1.6122165679931642, "lr": 1.1236777021845957e-06, "epoch": 0.7914572864321608, "percentage": 79.15, "elapsed_time": "0:42:54", "remaining_time": "0:11:18"}
{"current_steps": 320, "total_steps": 398, "loss": 1.6706012725830077, "lr": 9.984025750977338e-07, "epoch": 0.8040201005025126, "percentage": 80.4, "elapsed_time": "0:43:32", "remaining_time": "0:10:36"}
{"current_steps": 325, "total_steps": 398, "loss": 1.6766525268554688, "lr": 8.797532523276542e-07, "epoch": 0.8165829145728644, "percentage": 81.66, "elapsed_time": "0:44:13", "remaining_time": "0:09:55"}
{"current_steps": 330, "total_steps": 398, "loss": 1.6081558227539063, "lr": 7.679261922162417e-07, "epoch": 0.8291457286432161, "percentage": 82.91, "elapsed_time": "0:44:53", "remaining_time": "0:09:14"}
{"current_steps": 335, "total_steps": 398, "loss": 1.661915397644043, "lr": 6.631065568722633e-07, "epoch": 0.8417085427135679, "percentage": 84.17, "elapsed_time": "0:45:34", "remaining_time": "0:08:34"}
{"current_steps": 340, "total_steps": 398, "loss": 1.6015464782714843, "lr": 5.654679055818202e-07, "epoch": 0.8542713567839196, "percentage": 85.43, "elapsed_time": "0:46:17", "remaining_time": "0:07:53"}
{"current_steps": 345, "total_steps": 398, "loss": 1.6529460906982423, "lr": 4.751719074306604e-07, "epoch": 0.8668341708542714, "percentage": 86.68, "elapsed_time": "0:46:56", "remaining_time": "0:07:12"}
{"current_steps": 350, "total_steps": 398, "loss": 1.6363981246948243, "lr": 3.923680736141411e-07, "epoch": 0.8793969849246231, "percentage": 87.94, "elapsed_time": "0:47:36", "remaining_time": "0:06:31"}
{"current_steps": 355, "total_steps": 398, "loss": 1.6596275329589845, "lr": 3.1719350987811537e-07, "epoch": 0.8919597989949749, "percentage": 89.2, "elapsed_time": "0:48:17", "remaining_time": "0:05:50"}
{"current_steps": 360, "total_steps": 398, "loss": 1.6642751693725586, "lr": 2.497726895006353e-07, "epoch": 0.9045226130653267, "percentage": 90.45, "elapsed_time": "0:48:58", "remaining_time": "0:05:10"}
{"current_steps": 365, "total_steps": 398, "loss": 1.66651611328125, "lr": 1.902172471903563e-07, "epoch": 0.9170854271356784, "percentage": 91.71, "elapsed_time": "0:49:39", "remaining_time": "0:04:29"}
{"current_steps": 370, "total_steps": 398, "loss": 1.6170860290527345, "lr": 1.3862579424293366e-07, "epoch": 0.9296482412060302, "percentage": 92.96, "elapsed_time": "0:50:19", "remaining_time": "0:03:48"}
{"current_steps": 375, "total_steps": 398, "loss": 1.6495546340942382, "lr": 9.508375526142976e-08, "epoch": 0.9422110552763819, "percentage": 94.22, "elapsed_time": "0:51:00", "remaining_time": "0:03:07"}
{"current_steps": 380, "total_steps": 398, "loss": 1.6687738418579101, "lr": 5.966322671113523e-08, "epoch": 0.9547738693467337, "percentage": 95.48, "elapsed_time": "0:51:39", "remaining_time": "0:02:26"}
{"current_steps": 385, "total_steps": 398, "loss": 1.6350765228271484, "lr": 3.242285754296859e-08, "epoch": 0.9673366834170855, "percentage": 96.73, "elapsed_time": "0:52:20", "remaining_time": "0:01:46"}
{"current_steps": 390, "total_steps": 398, "loss": 1.6399044036865233, "lr": 1.3407752083142155e-08, "epoch": 0.9798994974874372, "percentage": 97.99, "elapsed_time": "0:53:02", "remaining_time": "0:01:05"}
{"current_steps": 395, "total_steps": 398, "loss": 1.7104473114013672, "lr": 2.6493953498790692e-09, "epoch": 0.992462311557789, "percentage": 99.25, "elapsed_time": "0:53:43", "remaining_time": "0:00:24"}
{"current_steps": 398, "total_steps": 398, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:54:10", "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": 398,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01256281407035176,
"grad_norm": 45.75,
"learning_rate": 3.3333333333333333e-06,
"loss": 2.9656538009643554,
"step": 5
},
{
"epoch": 0.02512562814070352,
"grad_norm": 14.625,
"learning_rate": 7.500000000000001e-06,
"loss": 2.7247514724731445,
"step": 10
},
{
"epoch": 0.03768844221105527,
"grad_norm": 8.375,
"learning_rate": 9.99933760728612e-06,
"loss": 2.5403032302856445,
"step": 15
},
{
"epoch": 0.05025125628140704,
"grad_norm": 5.40625,
"learning_rate": 9.991887704680723e-06,
"loss": 2.3779970169067384,
"step": 20
},
{
"epoch": 0.06281407035175879,
"grad_norm": 4.0625,
"learning_rate": 9.976172285185315e-06,
"loss": 2.1928905487060546,
"step": 25
},
{
"epoch": 0.07537688442211055,
"grad_norm": 3.765625,
"learning_rate": 9.952217370231655e-06,
"loss": 2.082417106628418,
"step": 30
},
{
"epoch": 0.08793969849246232,
"grad_norm": 2.6875,
"learning_rate": 9.920062624124282e-06,
"loss": 1.9925090789794921,
"step": 35
},
{
"epoch": 0.10050251256281408,
"grad_norm": 5.25,
"learning_rate": 9.879761288364767e-06,
"loss": 2.0241403579711914,
"step": 40
},
{
"epoch": 0.11306532663316583,
"grad_norm": 3.234375,
"learning_rate": 9.831380093494957e-06,
"loss": 1.8994447708129882,
"step": 45
},
{
"epoch": 0.12562814070351758,
"grad_norm": 2.53125,
"learning_rate": 9.77499914860525e-06,
"loss": 1.8455327987670898,
"step": 50
},
{
"epoch": 0.13819095477386933,
"grad_norm": 2.34375,
"learning_rate": 9.710711808690754e-06,
"loss": 1.8259857177734375,
"step": 55
},
{
"epoch": 0.1507537688442211,
"grad_norm": 2.796875,
"learning_rate": 9.638624520075047e-06,
"loss": 1.8774749755859375,
"step": 60
},
{
"epoch": 0.16331658291457288,
"grad_norm": 2.625,
"learning_rate": 9.558856644157432e-06,
"loss": 1.8711318969726562,
"step": 65
},
{
"epoch": 0.17587939698492464,
"grad_norm": 2.875,
"learning_rate": 9.471540259775554e-06,
"loss": 1.804541778564453,
"step": 70
},
{
"epoch": 0.1884422110552764,
"grad_norm": 2.265625,
"learning_rate": 9.376819944510598e-06,
"loss": 1.7933189392089843,
"step": 75
},
{
"epoch": 0.20100502512562815,
"grad_norm": 2.21875,
"learning_rate": 9.274852535297198e-06,
"loss": 1.7203624725341797,
"step": 80
},
{
"epoch": 0.2135678391959799,
"grad_norm": 2.4375,
"learning_rate": 9.165806868734444e-06,
"loss": 1.7706247329711915,
"step": 85
},
{
"epoch": 0.22613065326633167,
"grad_norm": 2.671875,
"learning_rate": 9.049863501527947e-06,
"loss": 1.7302061080932618,
"step": 90
},
{
"epoch": 0.23869346733668342,
"grad_norm": 2.265625,
"learning_rate": 8.927214411525895e-06,
"loss": 1.7422285079956055,
"step": 95
},
{
"epoch": 0.25125628140703515,
"grad_norm": 2.640625,
"learning_rate": 8.798062679844077e-06,
"loss": 1.7749662399291992,
"step": 100
},
{
"epoch": 0.2638190954773869,
"grad_norm": 2.375,
"learning_rate": 8.662622154606238e-06,
"loss": 1.6960893630981446,
"step": 105
},
{
"epoch": 0.27638190954773867,
"grad_norm": 2.265625,
"learning_rate": 8.521117096856529e-06,
"loss": 1.663231086730957,
"step": 110
},
{
"epoch": 0.2889447236180904,
"grad_norm": 1.9765625,
"learning_rate": 8.373781809230355e-06,
"loss": 1.6814579010009765,
"step": 115
},
{
"epoch": 0.3015075376884422,
"grad_norm": 2.4375,
"learning_rate": 8.220860247998455e-06,
"loss": 1.6490394592285156,
"step": 120
},
{
"epoch": 0.314070351758794,
"grad_norm": 2.5,
"learning_rate": 8.062605619126585e-06,
"loss": 1.6724288940429688,
"step": 125
},
{
"epoch": 0.32663316582914576,
"grad_norm": 2.109375,
"learning_rate": 7.899279959019654e-06,
"loss": 1.7372112274169922,
"step": 130
},
{
"epoch": 0.3391959798994975,
"grad_norm": 1.96875,
"learning_rate": 7.73115370064452e-06,
"loss": 1.6612102508544921,
"step": 135
},
{
"epoch": 0.35175879396984927,
"grad_norm": 2.4375,
"learning_rate": 7.558505225749827e-06,
"loss": 1.6610906600952149,
"step": 140
},
{
"epoch": 0.36432160804020103,
"grad_norm": 2.25,
"learning_rate": 7.381620403924333e-06,
"loss": 1.6504524230957032,
"step": 145
},
{
"epoch": 0.3768844221105528,
"grad_norm": 2.1875,
"learning_rate": 7.200792119256961e-06,
"loss": 1.6796260833740235,
"step": 150
},
{
"epoch": 0.38944723618090454,
"grad_norm": 2.390625,
"learning_rate": 7.0163197853822975e-06,
"loss": 1.6536401748657226,
"step": 155
},
{
"epoch": 0.4020100502512563,
"grad_norm": 2.03125,
"learning_rate": 6.828508849714546e-06,
"loss": 1.6703350067138671,
"step": 160
},
{
"epoch": 0.41457286432160806,
"grad_norm": 2.6875,
"learning_rate": 6.6376702876908e-06,
"loss": 1.658207321166992,
"step": 165
},
{
"epoch": 0.4271356783919598,
"grad_norm": 2.359375,
"learning_rate": 6.444120087861081e-06,
"loss": 1.6739206314086914,
"step": 170
},
{
"epoch": 0.4396984924623116,
"grad_norm": 3.03125,
"learning_rate": 6.2481787286777116e-06,
"loss": 1.679785919189453,
"step": 175
},
{
"epoch": 0.45226130653266333,
"grad_norm": 2.71875,
"learning_rate": 6.050170647850351e-06,
"loss": 1.652729606628418,
"step": 180
},
{
"epoch": 0.4648241206030151,
"grad_norm": 2.484375,
"learning_rate": 5.850423705145334e-06,
"loss": 1.6558731079101563,
"step": 185
},
{
"epoch": 0.47738693467336685,
"grad_norm": 2.4375,
"learning_rate": 5.64926863951881e-06,
"loss": 1.6815605163574219,
"step": 190
},
{
"epoch": 0.4899497487437186,
"grad_norm": 2.265625,
"learning_rate": 5.447038521482542e-06,
"loss": 1.7241903305053712,
"step": 195
},
{
"epoch": 0.5025125628140703,
"grad_norm": 2.046875,
"learning_rate": 5.244068201609132e-06,
"loss": 1.6395009994506835,
"step": 200
},
{
"epoch": 0.5150753768844221,
"grad_norm": 2.03125,
"learning_rate": 5.040693756089865e-06,
"loss": 1.6607843399047852,
"step": 205
},
{
"epoch": 0.5276381909547738,
"grad_norm": 2.359375,
"learning_rate": 4.837251930263149e-06,
"loss": 1.670051383972168,
"step": 210
},
{
"epoch": 0.5402010050251256,
"grad_norm": 2.453125,
"learning_rate": 4.634079581035029e-06,
"loss": 1.6406648635864258,
"step": 215
},
{
"epoch": 0.5527638190954773,
"grad_norm": 2.3125,
"learning_rate": 4.431513119114934e-06,
"loss": 1.7157506942749023,
"step": 220
},
{
"epoch": 0.5653266331658291,
"grad_norm": 2.484375,
"learning_rate": 4.229887951990255e-06,
"loss": 1.631689453125,
"step": 225
},
{
"epoch": 0.5778894472361809,
"grad_norm": 2.125,
"learning_rate": 4.029537928562028e-06,
"loss": 1.6348350524902344,
"step": 230
},
{
"epoch": 0.5904522613065326,
"grad_norm": 2.03125,
"learning_rate": 3.83079478636133e-06,
"loss": 1.6371662139892578,
"step": 235
},
{
"epoch": 0.6030150753768844,
"grad_norm": 2.15625,
"learning_rate": 3.633987602261647e-06,
"loss": 1.6417142868041992,
"step": 240
},
{
"epoch": 0.6155778894472361,
"grad_norm": 2.296875,
"learning_rate": 3.439442247596724e-06,
"loss": 1.651812744140625,
"step": 245
},
{
"epoch": 0.628140703517588,
"grad_norm": 3.046875,
"learning_rate": 3.24748084858614e-06,
"loss": 1.6704858779907226,
"step": 250
},
{
"epoch": 0.6407035175879398,
"grad_norm": 2.21875,
"learning_rate": 3.0584212529619777e-06,
"loss": 1.6126070022583008,
"step": 255
},
{
"epoch": 0.6532663316582915,
"grad_norm": 2.03125,
"learning_rate": 2.872576503679789e-06,
"loss": 1.650954246520996,
"step": 260
},
{
"epoch": 0.6658291457286433,
"grad_norm": 3.015625,
"learning_rate": 2.6902543205852496e-06,
"loss": 1.6697248458862304,
"step": 265
},
{
"epoch": 0.678391959798995,
"grad_norm": 3.078125,
"learning_rate": 2.511756590894765e-06,
"loss": 1.66760311126709,
"step": 270
},
{
"epoch": 0.6909547738693468,
"grad_norm": 2.578125,
"learning_rate": 2.3373788693337024e-06,
"loss": 1.669024658203125,
"step": 275
},
{
"epoch": 0.7035175879396985,
"grad_norm": 3.078125,
"learning_rate": 2.167409888759856e-06,
"loss": 1.6077774047851563,
"step": 280
},
{
"epoch": 0.7160804020100503,
"grad_norm": 2.84375,
"learning_rate": 2.002131082082549e-06,
"loss": 1.5952661514282227,
"step": 285
},
{
"epoch": 0.7286432160804021,
"grad_norm": 2.09375,
"learning_rate": 1.8418161162688613e-06,
"loss": 1.6444393157958985,
"step": 290
},
{
"epoch": 0.7412060301507538,
"grad_norm": 2.515625,
"learning_rate": 1.6867304392086575e-06,
"loss": 1.661176872253418,
"step": 295
},
{
"epoch": 0.7537688442211056,
"grad_norm": 2.890625,
"learning_rate": 1.5371308401886759e-06,
"loss": 1.6453720092773438,
"step": 300
},
{
"epoch": 0.7663316582914573,
"grad_norm": 2.4375,
"learning_rate": 1.393265024703422e-06,
"loss": 1.627047348022461,
"step": 305
},
{
"epoch": 0.7788944723618091,
"grad_norm": 3.125,
"learning_rate": 1.255371204306956e-06,
"loss": 1.6264894485473633,
"step": 310
},
{
"epoch": 0.7914572864321608,
"grad_norm": 2.4375,
"learning_rate": 1.1236777021845957e-06,
"loss": 1.6122165679931642,
"step": 315
},
{
"epoch": 0.8040201005025126,
"grad_norm": 2.03125,
"learning_rate": 9.984025750977338e-07,
"loss": 1.6706012725830077,
"step": 320
},
{
"epoch": 0.8165829145728644,
"grad_norm": 2.703125,
"learning_rate": 8.797532523276542e-07,
"loss": 1.6766525268554688,
"step": 325
},
{
"epoch": 0.8291457286432161,
"grad_norm": 2.1875,
"learning_rate": 7.679261922162417e-07,
"loss": 1.6081558227539063,
"step": 330
},
{
"epoch": 0.8417085427135679,
"grad_norm": 2.078125,
"learning_rate": 6.631065568722633e-07,
"loss": 1.661915397644043,
"step": 335
},
{
"epoch": 0.8542713567839196,
"grad_norm": 2.75,
"learning_rate": 5.654679055818202e-07,
"loss": 1.6015464782714843,
"step": 340
},
{
"epoch": 0.8668341708542714,
"grad_norm": 2.15625,
"learning_rate": 4.751719074306604e-07,
"loss": 1.6529460906982423,
"step": 345
},
{
"epoch": 0.8793969849246231,
"grad_norm": 2.828125,
"learning_rate": 3.923680736141411e-07,
"loss": 1.6363981246948243,
"step": 350
},
{
"epoch": 0.8919597989949749,
"grad_norm": 2.140625,
"learning_rate": 3.1719350987811537e-07,
"loss": 1.6596275329589845,
"step": 355
},
{
"epoch": 0.9045226130653267,
"grad_norm": 2.578125,
"learning_rate": 2.497726895006353e-07,
"loss": 1.6642751693725586,
"step": 360
},
{
"epoch": 0.9170854271356784,
"grad_norm": 2.53125,
"learning_rate": 1.902172471903563e-07,
"loss": 1.66651611328125,
"step": 365
},
{
"epoch": 0.9296482412060302,
"grad_norm": 1.90625,
"learning_rate": 1.3862579424293366e-07,
"loss": 1.6170860290527345,
"step": 370
},
{
"epoch": 0.9422110552763819,
"grad_norm": 2.359375,
"learning_rate": 9.508375526142976e-08,
"loss": 1.6495546340942382,
"step": 375
},
{
"epoch": 0.9547738693467337,
"grad_norm": 2.15625,
"learning_rate": 5.966322671113523e-08,
"loss": 1.6687738418579101,
"step": 380
},
{
"epoch": 0.9673366834170855,
"grad_norm": 1.8828125,
"learning_rate": 3.242285754296859e-08,
"loss": 1.6350765228271484,
"step": 385
},
{
"epoch": 0.9798994974874372,
"grad_norm": 2.265625,
"learning_rate": 1.3407752083142155e-08,
"loss": 1.6399044036865233,
"step": 390
},
{
"epoch": 0.992462311557789,
"grad_norm": 2.6875,
"learning_rate": 2.6493953498790692e-09,
"loss": 1.7104473114013672,
"step": 395
},
{
"epoch": 1.0,
"step": 398,
"total_flos": 1.9165347193492685e+17,
"train_loss": 1.7490570976506525,
"train_runtime": 3250.6471,
"train_samples_per_second": 0.49,
"train_steps_per_second": 0.122
}
],
"logging_steps": 5,
"max_steps": 398,
"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 sha256:0d935ac5a98fe645c64daf11523ffc761621c8f42affa3db243f1f683ac3ce2a
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 42 KiB