lldois/v09_all_linear_lr2e5
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/v09_all_linear_lr2e5
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-17 16:37:20 +08:00
commit f33ff205af
16 changed files with 3220 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: v09_all_linear_lr2e5
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. -->
# v09_all_linear_lr2e5
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 202607069
- 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": 1.5956898921698182,
"train_runtime": 3205.1567,
"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 sha256:858d7041031f4f5864ccadeccd16de4c19b7971cd4525460c18f3f392c3c64e4
size 1602902832

3
runs/Jul06_04-22-59_ubuntu-System-Product-Name/events.out.tfevents.1783282979.ubuntu-System-Product-Name.1682374.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5f55b3a7af1036cb305ec3ae8293077f6e5f69cbc62cc35b465e7536f0654c0d
size 22885

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
}

2242
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": 1.5956898921698182,
"train_runtime": 3205.1567,
"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": 398, "loss": 2.908399200439453, "lr": 4.000000000000001e-06, "epoch": 0.01256281407035176, "percentage": 1.26, "elapsed_time": "0:00:41", "remaining_time": "0:54:56"}
{"current_steps": 10, "total_steps": 398, "loss": 2.7105648040771486, "lr": 9e-06, "epoch": 0.02512562814070352, "percentage": 2.51, "elapsed_time": "0:01:21", "remaining_time": "0:52:49"}
{"current_steps": 15, "total_steps": 398, "loss": 2.501449775695801, "lr": 1.4e-05, "epoch": 0.03768844221105527, "percentage": 3.77, "elapsed_time": "0:02:01", "remaining_time": "0:51:30"}
{"current_steps": 20, "total_steps": 398, "loss": 2.185238838195801, "lr": 1.9e-05, "epoch": 0.05025125628140704, "percentage": 5.03, "elapsed_time": "0:02:42", "remaining_time": "0:51:06"}
{"current_steps": 25, "total_steps": 398, "loss": 1.959276008605957, "lr": 1.978835978835979e-05, "epoch": 0.06281407035175879, "percentage": 6.28, "elapsed_time": "0:03:23", "remaining_time": "0:50:43"}
{"current_steps": 30, "total_steps": 398, "loss": 1.8451156616210938, "lr": 1.9523809523809524e-05, "epoch": 0.07537688442211055, "percentage": 7.54, "elapsed_time": "0:04:05", "remaining_time": "0:50:17"}
{"current_steps": 35, "total_steps": 398, "loss": 1.7816888809204101, "lr": 1.925925925925926e-05, "epoch": 0.08793969849246232, "percentage": 8.79, "elapsed_time": "0:04:46", "remaining_time": "0:49:28"}
{"current_steps": 40, "total_steps": 398, "loss": 1.721405601501465, "lr": 1.8994708994708996e-05, "epoch": 0.10050251256281408, "percentage": 10.05, "elapsed_time": "0:05:28", "remaining_time": "0:48:59"}
{"current_steps": 45, "total_steps": 398, "loss": 1.7366134643554687, "lr": 1.8730158730158732e-05, "epoch": 0.11306532663316583, "percentage": 11.31, "elapsed_time": "0:06:08", "remaining_time": "0:48:11"}
{"current_steps": 50, "total_steps": 398, "loss": 1.678215217590332, "lr": 1.8465608465608468e-05, "epoch": 0.12562814070351758, "percentage": 12.56, "elapsed_time": "0:06:48", "remaining_time": "0:47:22"}
{"current_steps": 55, "total_steps": 398, "loss": 1.6803802490234374, "lr": 1.82010582010582e-05, "epoch": 0.13819095477386933, "percentage": 13.82, "elapsed_time": "0:07:29", "remaining_time": "0:46:41"}
{"current_steps": 60, "total_steps": 398, "loss": 1.6128549575805664, "lr": 1.7936507936507937e-05, "epoch": 0.1507537688442211, "percentage": 15.08, "elapsed_time": "0:08:10", "remaining_time": "0:46:02"}
{"current_steps": 65, "total_steps": 398, "loss": 1.6951425552368165, "lr": 1.7671957671957673e-05, "epoch": 0.16331658291457288, "percentage": 16.33, "elapsed_time": "0:08:49", "remaining_time": "0:45:14"}
{"current_steps": 70, "total_steps": 398, "loss": 1.662872886657715, "lr": 1.740740740740741e-05, "epoch": 0.17587939698492464, "percentage": 17.59, "elapsed_time": "0:09:28", "remaining_time": "0:44:25"}
{"current_steps": 75, "total_steps": 398, "loss": 1.6751840591430665, "lr": 1.7142857142857142e-05, "epoch": 0.1884422110552764, "percentage": 18.84, "elapsed_time": "0:10:08", "remaining_time": "0:43:39"}
{"current_steps": 80, "total_steps": 398, "loss": 1.7192909240722656, "lr": 1.687830687830688e-05, "epoch": 0.20100502512562815, "percentage": 20.1, "elapsed_time": "0:10:48", "remaining_time": "0:42:58"}
{"current_steps": 85, "total_steps": 398, "loss": 1.5769388198852539, "lr": 1.6613756613756614e-05, "epoch": 0.2135678391959799, "percentage": 21.36, "elapsed_time": "0:11:30", "remaining_time": "0:42:22"}
{"current_steps": 90, "total_steps": 398, "loss": 1.5676084518432618, "lr": 1.634920634920635e-05, "epoch": 0.22613065326633167, "percentage": 22.61, "elapsed_time": "0:12:12", "remaining_time": "0:41:47"}
{"current_steps": 95, "total_steps": 398, "loss": 1.6453401565551757, "lr": 1.6084656084656086e-05, "epoch": 0.23869346733668342, "percentage": 23.87, "elapsed_time": "0:12:52", "remaining_time": "0:41:05"}
{"current_steps": 100, "total_steps": 398, "loss": 1.5511817932128906, "lr": 1.5820105820105822e-05, "epoch": 0.25125628140703515, "percentage": 25.13, "elapsed_time": "0:13:31", "remaining_time": "0:40:19"}
{"current_steps": 105, "total_steps": 398, "loss": 1.5268743515014649, "lr": 1.555555555555556e-05, "epoch": 0.2638190954773869, "percentage": 26.38, "elapsed_time": "0:14:12", "remaining_time": "0:39:38"}
{"current_steps": 110, "total_steps": 398, "loss": 1.530481719970703, "lr": 1.529100529100529e-05, "epoch": 0.27638190954773867, "percentage": 27.64, "elapsed_time": "0:14:54", "remaining_time": "0:39:02"}
{"current_steps": 115, "total_steps": 398, "loss": 1.5688664436340332, "lr": 1.5026455026455027e-05, "epoch": 0.2889447236180904, "percentage": 28.89, "elapsed_time": "0:15:34", "remaining_time": "0:38:18"}
{"current_steps": 120, "total_steps": 398, "loss": 1.5435178756713868, "lr": 1.4761904761904763e-05, "epoch": 0.3015075376884422, "percentage": 30.15, "elapsed_time": "0:16:12", "remaining_time": "0:37:32"}
{"current_steps": 125, "total_steps": 398, "loss": 1.622827911376953, "lr": 1.44973544973545e-05, "epoch": 0.314070351758794, "percentage": 31.41, "elapsed_time": "0:16:53", "remaining_time": "0:36:52"}
{"current_steps": 130, "total_steps": 398, "loss": 1.534958839416504, "lr": 1.4232804232804234e-05, "epoch": 0.32663316582914576, "percentage": 32.66, "elapsed_time": "0:17:33", "remaining_time": "0:36:10"}
{"current_steps": 135, "total_steps": 398, "loss": 1.5641840934753417, "lr": 1.3968253968253968e-05, "epoch": 0.3391959798994975, "percentage": 33.92, "elapsed_time": "0:18:12", "remaining_time": "0:35:27"}
{"current_steps": 140, "total_steps": 398, "loss": 1.6128816604614258, "lr": 1.3703703703703706e-05, "epoch": 0.35175879396984927, "percentage": 35.18, "elapsed_time": "0:18:51", "remaining_time": "0:34:44"}
{"current_steps": 145, "total_steps": 398, "loss": 1.5031535148620605, "lr": 1.343915343915344e-05, "epoch": 0.36432160804020103, "percentage": 36.43, "elapsed_time": "0:19:30", "remaining_time": "0:34:02"}
{"current_steps": 150, "total_steps": 398, "loss": 1.5201923370361328, "lr": 1.3174603174603176e-05, "epoch": 0.3768844221105528, "percentage": 37.69, "elapsed_time": "0:20:09", "remaining_time": "0:33:19"}
{"current_steps": 155, "total_steps": 398, "loss": 1.5293109893798829, "lr": 1.291005291005291e-05, "epoch": 0.38944723618090454, "percentage": 38.94, "elapsed_time": "0:20:49", "remaining_time": "0:32:38"}
{"current_steps": 160, "total_steps": 398, "loss": 1.532673454284668, "lr": 1.2645502645502647e-05, "epoch": 0.4020100502512563, "percentage": 40.2, "elapsed_time": "0:21:29", "remaining_time": "0:31:57"}
{"current_steps": 165, "total_steps": 398, "loss": 1.5430846214294434, "lr": 1.2380952380952383e-05, "epoch": 0.41457286432160806, "percentage": 41.46, "elapsed_time": "0:22:10", "remaining_time": "0:31:18"}
{"current_steps": 170, "total_steps": 398, "loss": 1.5211373329162599, "lr": 1.2116402116402117e-05, "epoch": 0.4271356783919598, "percentage": 42.71, "elapsed_time": "0:22:48", "remaining_time": "0:30:35"}
{"current_steps": 175, "total_steps": 398, "loss": 1.5185907363891602, "lr": 1.1851851851851852e-05, "epoch": 0.4396984924623116, "percentage": 43.97, "elapsed_time": "0:23:27", "remaining_time": "0:29:53"}
{"current_steps": 180, "total_steps": 398, "loss": 1.4886056900024414, "lr": 1.158730158730159e-05, "epoch": 0.45226130653266333, "percentage": 45.23, "elapsed_time": "0:24:07", "remaining_time": "0:29:13"}
{"current_steps": 185, "total_steps": 398, "loss": 1.4682801246643067, "lr": 1.1322751322751324e-05, "epoch": 0.4648241206030151, "percentage": 46.48, "elapsed_time": "0:24:46", "remaining_time": "0:28:31"}
{"current_steps": 190, "total_steps": 398, "loss": 1.5117271423339844, "lr": 1.105820105820106e-05, "epoch": 0.47738693467336685, "percentage": 47.74, "elapsed_time": "0:25:27", "remaining_time": "0:27:52"}
{"current_steps": 195, "total_steps": 398, "loss": 1.544318389892578, "lr": 1.0793650793650794e-05, "epoch": 0.4899497487437186, "percentage": 48.99, "elapsed_time": "0:26:07", "remaining_time": "0:27:11"}
{"current_steps": 200, "total_steps": 398, "loss": 1.5679922103881836, "lr": 1.052910052910053e-05, "epoch": 0.5025125628140703, "percentage": 50.25, "elapsed_time": "0:26:47", "remaining_time": "0:26:31"}
{"current_steps": 205, "total_steps": 398, "loss": 1.5708157539367675, "lr": 1.0264550264550266e-05, "epoch": 0.5150753768844221, "percentage": 51.51, "elapsed_time": "0:27:27", "remaining_time": "0:25:51"}
{"current_steps": 210, "total_steps": 398, "loss": 1.449632453918457, "lr": 1e-05, "epoch": 0.5276381909547738, "percentage": 52.76, "elapsed_time": "0:28:08", "remaining_time": "0:25:11"}
{"current_steps": 215, "total_steps": 398, "loss": 1.4999945640563965, "lr": 9.735449735449735e-06, "epoch": 0.5402010050251256, "percentage": 54.02, "elapsed_time": "0:28:48", "remaining_time": "0:24:31"}
{"current_steps": 220, "total_steps": 398, "loss": 1.5098167419433595, "lr": 9.470899470899471e-06, "epoch": 0.5527638190954773, "percentage": 55.28, "elapsed_time": "0:29:28", "remaining_time": "0:23:50"}
{"current_steps": 225, "total_steps": 398, "loss": 1.4984207153320312, "lr": 9.206349206349207e-06, "epoch": 0.5653266331658291, "percentage": 56.53, "elapsed_time": "0:30:06", "remaining_time": "0:23:09"}
{"current_steps": 230, "total_steps": 398, "loss": 1.4724366188049316, "lr": 8.941798941798942e-06, "epoch": 0.5778894472361809, "percentage": 57.79, "elapsed_time": "0:30:48", "remaining_time": "0:22:30"}
{"current_steps": 235, "total_steps": 398, "loss": 1.486234474182129, "lr": 8.677248677248678e-06, "epoch": 0.5904522613065326, "percentage": 59.05, "elapsed_time": "0:31:30", "remaining_time": "0:21:50"}
{"current_steps": 240, "total_steps": 398, "loss": 1.5106399536132813, "lr": 8.412698412698414e-06, "epoch": 0.6030150753768844, "percentage": 60.3, "elapsed_time": "0:32:10", "remaining_time": "0:21:10"}
{"current_steps": 245, "total_steps": 398, "loss": 1.5564719200134278, "lr": 8.148148148148148e-06, "epoch": 0.6155778894472361, "percentage": 61.56, "elapsed_time": "0:32:50", "remaining_time": "0:20:30"}
{"current_steps": 250, "total_steps": 398, "loss": 1.480449390411377, "lr": 7.883597883597884e-06, "epoch": 0.628140703517588, "percentage": 62.81, "elapsed_time": "0:33:30", "remaining_time": "0:19:50"}
{"current_steps": 255, "total_steps": 398, "loss": 1.4469252586364747, "lr": 7.61904761904762e-06, "epoch": 0.6407035175879398, "percentage": 64.07, "elapsed_time": "0:34:11", "remaining_time": "0:19:10"}
{"current_steps": 260, "total_steps": 398, "loss": 1.4990968704223633, "lr": 7.354497354497355e-06, "epoch": 0.6532663316582915, "percentage": 65.33, "elapsed_time": "0:34:50", "remaining_time": "0:18:29"}
{"current_steps": 265, "total_steps": 398, "loss": 1.448952579498291, "lr": 7.08994708994709e-06, "epoch": 0.6658291457286433, "percentage": 66.58, "elapsed_time": "0:35:32", "remaining_time": "0:17:50"}
{"current_steps": 270, "total_steps": 398, "loss": 1.4773205757141112, "lr": 6.825396825396826e-06, "epoch": 0.678391959798995, "percentage": 67.84, "elapsed_time": "0:36:13", "remaining_time": "0:17:10"}
{"current_steps": 275, "total_steps": 398, "loss": 1.485036277770996, "lr": 6.560846560846561e-06, "epoch": 0.6909547738693468, "percentage": 69.1, "elapsed_time": "0:36:53", "remaining_time": "0:16:30"}
{"current_steps": 280, "total_steps": 398, "loss": 1.4918421745300292, "lr": 6.296296296296297e-06, "epoch": 0.7035175879396985, "percentage": 70.35, "elapsed_time": "0:37:33", "remaining_time": "0:15:49"}
{"current_steps": 285, "total_steps": 398, "loss": 1.4894933700561523, "lr": 6.031746031746032e-06, "epoch": 0.7160804020100503, "percentage": 71.61, "elapsed_time": "0:38:14", "remaining_time": "0:15:09"}
{"current_steps": 290, "total_steps": 398, "loss": 1.4480770111083985, "lr": 5.767195767195768e-06, "epoch": 0.7286432160804021, "percentage": 72.86, "elapsed_time": "0:38:54", "remaining_time": "0:14:29"}
{"current_steps": 295, "total_steps": 398, "loss": 1.4752997398376464, "lr": 5.502645502645503e-06, "epoch": 0.7412060301507538, "percentage": 74.12, "elapsed_time": "0:39:35", "remaining_time": "0:13:49"}
{"current_steps": 300, "total_steps": 398, "loss": 1.4711036682128906, "lr": 5.2380952380952384e-06, "epoch": 0.7537688442211056, "percentage": 75.38, "elapsed_time": "0:40:16", "remaining_time": "0:13:09"}
{"current_steps": 305, "total_steps": 398, "loss": 1.4894997596740722, "lr": 4.973544973544974e-06, "epoch": 0.7663316582914573, "percentage": 76.63, "elapsed_time": "0:40:57", "remaining_time": "0:12:29"}
{"current_steps": 310, "total_steps": 398, "loss": 1.4980501174926757, "lr": 4.708994708994709e-06, "epoch": 0.7788944723618091, "percentage": 77.89, "elapsed_time": "0:41:36", "remaining_time": "0:11:48"}
{"current_steps": 315, "total_steps": 398, "loss": 1.4688381195068358, "lr": 4.444444444444444e-06, "epoch": 0.7914572864321608, "percentage": 79.15, "elapsed_time": "0:42:16", "remaining_time": "0:11:08"}
{"current_steps": 320, "total_steps": 398, "loss": 1.4227490425109863, "lr": 4.17989417989418e-06, "epoch": 0.8040201005025126, "percentage": 80.4, "elapsed_time": "0:42:56", "remaining_time": "0:10:28"}
{"current_steps": 325, "total_steps": 398, "loss": 1.5430548667907715, "lr": 3.9153439153439155e-06, "epoch": 0.8165829145728644, "percentage": 81.66, "elapsed_time": "0:43:37", "remaining_time": "0:09:47"}
{"current_steps": 330, "total_steps": 398, "loss": 1.4949950218200683, "lr": 3.6507936507936507e-06, "epoch": 0.8291457286432161, "percentage": 82.91, "elapsed_time": "0:44:17", "remaining_time": "0:09:07"}
{"current_steps": 335, "total_steps": 398, "loss": 1.508356475830078, "lr": 3.3862433862433864e-06, "epoch": 0.8417085427135679, "percentage": 84.17, "elapsed_time": "0:44:56", "remaining_time": "0:08:27"}
{"current_steps": 340, "total_steps": 398, "loss": 1.4609917640686034, "lr": 3.1216931216931216e-06, "epoch": 0.8542713567839196, "percentage": 85.43, "elapsed_time": "0:45:37", "remaining_time": "0:07:46"}
{"current_steps": 345, "total_steps": 398, "loss": 1.4494487762451171, "lr": 2.8571428571428573e-06, "epoch": 0.8668341708542714, "percentage": 86.68, "elapsed_time": "0:46:17", "remaining_time": "0:07:06"}
{"current_steps": 350, "total_steps": 398, "loss": 1.5313102722167968, "lr": 2.5925925925925925e-06, "epoch": 0.8793969849246231, "percentage": 87.94, "elapsed_time": "0:46:56", "remaining_time": "0:06:26"}
{"current_steps": 355, "total_steps": 398, "loss": 1.4682437896728515, "lr": 2.328042328042328e-06, "epoch": 0.8919597989949749, "percentage": 89.2, "elapsed_time": "0:47:35", "remaining_time": "0:05:45"}
{"current_steps": 360, "total_steps": 398, "loss": 1.5278240203857423, "lr": 2.0634920634920634e-06, "epoch": 0.9045226130653267, "percentage": 90.45, "elapsed_time": "0:48:14", "remaining_time": "0:05:05"}
{"current_steps": 365, "total_steps": 398, "loss": 1.4803818702697753, "lr": 1.798941798941799e-06, "epoch": 0.9170854271356784, "percentage": 91.71, "elapsed_time": "0:48:55", "remaining_time": "0:04:25"}
{"current_steps": 370, "total_steps": 398, "loss": 1.4913017272949218, "lr": 1.5343915343915345e-06, "epoch": 0.9296482412060302, "percentage": 92.96, "elapsed_time": "0:49:33", "remaining_time": "0:03:45"}
{"current_steps": 375, "total_steps": 398, "loss": 1.4437126159667968, "lr": 1.26984126984127e-06, "epoch": 0.9422110552763819, "percentage": 94.22, "elapsed_time": "0:50:13", "remaining_time": "0:03:04"}
{"current_steps": 380, "total_steps": 398, "loss": 1.4650879859924317, "lr": 1.0052910052910054e-06, "epoch": 0.9547738693467337, "percentage": 95.48, "elapsed_time": "0:50:54", "remaining_time": "0:02:24"}
{"current_steps": 385, "total_steps": 398, "loss": 1.54934663772583, "lr": 7.407407407407407e-07, "epoch": 0.9673366834170855, "percentage": 96.73, "elapsed_time": "0:51:36", "remaining_time": "0:01:44"}
{"current_steps": 390, "total_steps": 398, "loss": 1.4588896751403808, "lr": 4.7619047619047623e-07, "epoch": 0.9798994974874372, "percentage": 97.99, "elapsed_time": "0:52:17", "remaining_time": "0:01:04"}
{"current_steps": 395, "total_steps": 398, "loss": 1.4410962104797362, "lr": 2.1164021164021165e-07, "epoch": 0.992462311557789, "percentage": 99.25, "elapsed_time": "0:52:58", "remaining_time": "0:00:24"}
{"current_steps": 398, "total_steps": 398, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:53:25", "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": 41.0,
"learning_rate": 4.000000000000001e-06,
"loss": 2.908399200439453,
"step": 5
},
{
"epoch": 0.02512562814070352,
"grad_norm": 10.25,
"learning_rate": 9e-06,
"loss": 2.7105648040771486,
"step": 10
},
{
"epoch": 0.03768844221105527,
"grad_norm": 7.5625,
"learning_rate": 1.4e-05,
"loss": 2.501449775695801,
"step": 15
},
{
"epoch": 0.05025125628140704,
"grad_norm": 3.875,
"learning_rate": 1.9e-05,
"loss": 2.185238838195801,
"step": 20
},
{
"epoch": 0.06281407035175879,
"grad_norm": 3.578125,
"learning_rate": 1.978835978835979e-05,
"loss": 1.959276008605957,
"step": 25
},
{
"epoch": 0.07537688442211055,
"grad_norm": 2.5625,
"learning_rate": 1.9523809523809524e-05,
"loss": 1.8451156616210938,
"step": 30
},
{
"epoch": 0.08793969849246232,
"grad_norm": 2.34375,
"learning_rate": 1.925925925925926e-05,
"loss": 1.7816888809204101,
"step": 35
},
{
"epoch": 0.10050251256281408,
"grad_norm": 3.046875,
"learning_rate": 1.8994708994708996e-05,
"loss": 1.721405601501465,
"step": 40
},
{
"epoch": 0.11306532663316583,
"grad_norm": 2.5,
"learning_rate": 1.8730158730158732e-05,
"loss": 1.7366134643554687,
"step": 45
},
{
"epoch": 0.12562814070351758,
"grad_norm": 2.109375,
"learning_rate": 1.8465608465608468e-05,
"loss": 1.678215217590332,
"step": 50
},
{
"epoch": 0.13819095477386933,
"grad_norm": 2.703125,
"learning_rate": 1.82010582010582e-05,
"loss": 1.6803802490234374,
"step": 55
},
{
"epoch": 0.1507537688442211,
"grad_norm": 2.109375,
"learning_rate": 1.7936507936507937e-05,
"loss": 1.6128549575805664,
"step": 60
},
{
"epoch": 0.16331658291457288,
"grad_norm": 2.484375,
"learning_rate": 1.7671957671957673e-05,
"loss": 1.6951425552368165,
"step": 65
},
{
"epoch": 0.17587939698492464,
"grad_norm": 2.078125,
"learning_rate": 1.740740740740741e-05,
"loss": 1.662872886657715,
"step": 70
},
{
"epoch": 0.1884422110552764,
"grad_norm": 2.296875,
"learning_rate": 1.7142857142857142e-05,
"loss": 1.6751840591430665,
"step": 75
},
{
"epoch": 0.20100502512562815,
"grad_norm": 2.859375,
"learning_rate": 1.687830687830688e-05,
"loss": 1.7192909240722656,
"step": 80
},
{
"epoch": 0.2135678391959799,
"grad_norm": 2.59375,
"learning_rate": 1.6613756613756614e-05,
"loss": 1.5769388198852539,
"step": 85
},
{
"epoch": 0.22613065326633167,
"grad_norm": 2.390625,
"learning_rate": 1.634920634920635e-05,
"loss": 1.5676084518432618,
"step": 90
},
{
"epoch": 0.23869346733668342,
"grad_norm": 2.5625,
"learning_rate": 1.6084656084656086e-05,
"loss": 1.6453401565551757,
"step": 95
},
{
"epoch": 0.25125628140703515,
"grad_norm": 2.375,
"learning_rate": 1.5820105820105822e-05,
"loss": 1.5511817932128906,
"step": 100
},
{
"epoch": 0.2638190954773869,
"grad_norm": 2.546875,
"learning_rate": 1.555555555555556e-05,
"loss": 1.5268743515014649,
"step": 105
},
{
"epoch": 0.27638190954773867,
"grad_norm": 2.828125,
"learning_rate": 1.529100529100529e-05,
"loss": 1.530481719970703,
"step": 110
},
{
"epoch": 0.2889447236180904,
"grad_norm": 2.234375,
"learning_rate": 1.5026455026455027e-05,
"loss": 1.5688664436340332,
"step": 115
},
{
"epoch": 0.3015075376884422,
"grad_norm": 2.359375,
"learning_rate": 1.4761904761904763e-05,
"loss": 1.5435178756713868,
"step": 120
},
{
"epoch": 0.314070351758794,
"grad_norm": 1.9609375,
"learning_rate": 1.44973544973545e-05,
"loss": 1.622827911376953,
"step": 125
},
{
"epoch": 0.32663316582914576,
"grad_norm": 2.421875,
"learning_rate": 1.4232804232804234e-05,
"loss": 1.534958839416504,
"step": 130
},
{
"epoch": 0.3391959798994975,
"grad_norm": 2.328125,
"learning_rate": 1.3968253968253968e-05,
"loss": 1.5641840934753417,
"step": 135
},
{
"epoch": 0.35175879396984927,
"grad_norm": 1.8359375,
"learning_rate": 1.3703703703703706e-05,
"loss": 1.6128816604614258,
"step": 140
},
{
"epoch": 0.36432160804020103,
"grad_norm": 1.96875,
"learning_rate": 1.343915343915344e-05,
"loss": 1.5031535148620605,
"step": 145
},
{
"epoch": 0.3768844221105528,
"grad_norm": 2.40625,
"learning_rate": 1.3174603174603176e-05,
"loss": 1.5201923370361328,
"step": 150
},
{
"epoch": 0.38944723618090454,
"grad_norm": 2.171875,
"learning_rate": 1.291005291005291e-05,
"loss": 1.5293109893798829,
"step": 155
},
{
"epoch": 0.4020100502512563,
"grad_norm": 2.375,
"learning_rate": 1.2645502645502647e-05,
"loss": 1.532673454284668,
"step": 160
},
{
"epoch": 0.41457286432160806,
"grad_norm": 2.046875,
"learning_rate": 1.2380952380952383e-05,
"loss": 1.5430846214294434,
"step": 165
},
{
"epoch": 0.4271356783919598,
"grad_norm": 2.15625,
"learning_rate": 1.2116402116402117e-05,
"loss": 1.5211373329162599,
"step": 170
},
{
"epoch": 0.4396984924623116,
"grad_norm": 2.328125,
"learning_rate": 1.1851851851851852e-05,
"loss": 1.5185907363891602,
"step": 175
},
{
"epoch": 0.45226130653266333,
"grad_norm": 2.234375,
"learning_rate": 1.158730158730159e-05,
"loss": 1.4886056900024414,
"step": 180
},
{
"epoch": 0.4648241206030151,
"grad_norm": 2.28125,
"learning_rate": 1.1322751322751324e-05,
"loss": 1.4682801246643067,
"step": 185
},
{
"epoch": 0.47738693467336685,
"grad_norm": 4.34375,
"learning_rate": 1.105820105820106e-05,
"loss": 1.5117271423339844,
"step": 190
},
{
"epoch": 0.4899497487437186,
"grad_norm": 2.265625,
"learning_rate": 1.0793650793650794e-05,
"loss": 1.544318389892578,
"step": 195
},
{
"epoch": 0.5025125628140703,
"grad_norm": 2.21875,
"learning_rate": 1.052910052910053e-05,
"loss": 1.5679922103881836,
"step": 200
},
{
"epoch": 0.5150753768844221,
"grad_norm": 2.1875,
"learning_rate": 1.0264550264550266e-05,
"loss": 1.5708157539367675,
"step": 205
},
{
"epoch": 0.5276381909547738,
"grad_norm": 2.703125,
"learning_rate": 1e-05,
"loss": 1.449632453918457,
"step": 210
},
{
"epoch": 0.5402010050251256,
"grad_norm": 2.03125,
"learning_rate": 9.735449735449735e-06,
"loss": 1.4999945640563965,
"step": 215
},
{
"epoch": 0.5527638190954773,
"grad_norm": 2.4375,
"learning_rate": 9.470899470899471e-06,
"loss": 1.5098167419433595,
"step": 220
},
{
"epoch": 0.5653266331658291,
"grad_norm": 1.8984375,
"learning_rate": 9.206349206349207e-06,
"loss": 1.4984207153320312,
"step": 225
},
{
"epoch": 0.5778894472361809,
"grad_norm": 2.125,
"learning_rate": 8.941798941798942e-06,
"loss": 1.4724366188049316,
"step": 230
},
{
"epoch": 0.5904522613065326,
"grad_norm": 2.09375,
"learning_rate": 8.677248677248678e-06,
"loss": 1.486234474182129,
"step": 235
},
{
"epoch": 0.6030150753768844,
"grad_norm": 2.828125,
"learning_rate": 8.412698412698414e-06,
"loss": 1.5106399536132813,
"step": 240
},
{
"epoch": 0.6155778894472361,
"grad_norm": 2.0625,
"learning_rate": 8.148148148148148e-06,
"loss": 1.5564719200134278,
"step": 245
},
{
"epoch": 0.628140703517588,
"grad_norm": 2.25,
"learning_rate": 7.883597883597884e-06,
"loss": 1.480449390411377,
"step": 250
},
{
"epoch": 0.6407035175879398,
"grad_norm": 2.046875,
"learning_rate": 7.61904761904762e-06,
"loss": 1.4469252586364747,
"step": 255
},
{
"epoch": 0.6532663316582915,
"grad_norm": 1.75,
"learning_rate": 7.354497354497355e-06,
"loss": 1.4990968704223633,
"step": 260
},
{
"epoch": 0.6658291457286433,
"grad_norm": 2.75,
"learning_rate": 7.08994708994709e-06,
"loss": 1.448952579498291,
"step": 265
},
{
"epoch": 0.678391959798995,
"grad_norm": 2.359375,
"learning_rate": 6.825396825396826e-06,
"loss": 1.4773205757141112,
"step": 270
},
{
"epoch": 0.6909547738693468,
"grad_norm": 2.6875,
"learning_rate": 6.560846560846561e-06,
"loss": 1.485036277770996,
"step": 275
},
{
"epoch": 0.7035175879396985,
"grad_norm": 1.9140625,
"learning_rate": 6.296296296296297e-06,
"loss": 1.4918421745300292,
"step": 280
},
{
"epoch": 0.7160804020100503,
"grad_norm": 2.1875,
"learning_rate": 6.031746031746032e-06,
"loss": 1.4894933700561523,
"step": 285
},
{
"epoch": 0.7286432160804021,
"grad_norm": 2.578125,
"learning_rate": 5.767195767195768e-06,
"loss": 1.4480770111083985,
"step": 290
},
{
"epoch": 0.7412060301507538,
"grad_norm": 1.9765625,
"learning_rate": 5.502645502645503e-06,
"loss": 1.4752997398376464,
"step": 295
},
{
"epoch": 0.7537688442211056,
"grad_norm": 2.171875,
"learning_rate": 5.2380952380952384e-06,
"loss": 1.4711036682128906,
"step": 300
},
{
"epoch": 0.7663316582914573,
"grad_norm": 3.109375,
"learning_rate": 4.973544973544974e-06,
"loss": 1.4894997596740722,
"step": 305
},
{
"epoch": 0.7788944723618091,
"grad_norm": 1.921875,
"learning_rate": 4.708994708994709e-06,
"loss": 1.4980501174926757,
"step": 310
},
{
"epoch": 0.7914572864321608,
"grad_norm": 2.046875,
"learning_rate": 4.444444444444444e-06,
"loss": 1.4688381195068358,
"step": 315
},
{
"epoch": 0.8040201005025126,
"grad_norm": 2.546875,
"learning_rate": 4.17989417989418e-06,
"loss": 1.4227490425109863,
"step": 320
},
{
"epoch": 0.8165829145728644,
"grad_norm": 2.359375,
"learning_rate": 3.9153439153439155e-06,
"loss": 1.5430548667907715,
"step": 325
},
{
"epoch": 0.8291457286432161,
"grad_norm": 1.9921875,
"learning_rate": 3.6507936507936507e-06,
"loss": 1.4949950218200683,
"step": 330
},
{
"epoch": 0.8417085427135679,
"grad_norm": 2.09375,
"learning_rate": 3.3862433862433864e-06,
"loss": 1.508356475830078,
"step": 335
},
{
"epoch": 0.8542713567839196,
"grad_norm": 2.0625,
"learning_rate": 3.1216931216931216e-06,
"loss": 1.4609917640686034,
"step": 340
},
{
"epoch": 0.8668341708542714,
"grad_norm": 2.15625,
"learning_rate": 2.8571428571428573e-06,
"loss": 1.4494487762451171,
"step": 345
},
{
"epoch": 0.8793969849246231,
"grad_norm": 2.1875,
"learning_rate": 2.5925925925925925e-06,
"loss": 1.5313102722167968,
"step": 350
},
{
"epoch": 0.8919597989949749,
"grad_norm": 2.265625,
"learning_rate": 2.328042328042328e-06,
"loss": 1.4682437896728515,
"step": 355
},
{
"epoch": 0.9045226130653267,
"grad_norm": 2.125,
"learning_rate": 2.0634920634920634e-06,
"loss": 1.5278240203857423,
"step": 360
},
{
"epoch": 0.9170854271356784,
"grad_norm": 2.25,
"learning_rate": 1.798941798941799e-06,
"loss": 1.4803818702697753,
"step": 365
},
{
"epoch": 0.9296482412060302,
"grad_norm": 1.90625,
"learning_rate": 1.5343915343915345e-06,
"loss": 1.4913017272949218,
"step": 370
},
{
"epoch": 0.9422110552763819,
"grad_norm": 2.421875,
"learning_rate": 1.26984126984127e-06,
"loss": 1.4437126159667968,
"step": 375
},
{
"epoch": 0.9547738693467337,
"grad_norm": 2.4375,
"learning_rate": 1.0052910052910054e-06,
"loss": 1.4650879859924317,
"step": 380
},
{
"epoch": 0.9673366834170855,
"grad_norm": 2.140625,
"learning_rate": 7.407407407407407e-07,
"loss": 1.54934663772583,
"step": 385
},
{
"epoch": 0.9798994974874372,
"grad_norm": 2.984375,
"learning_rate": 4.7619047619047623e-07,
"loss": 1.4588896751403808,
"step": 390
},
{
"epoch": 0.992462311557789,
"grad_norm": 2.578125,
"learning_rate": 2.1164021164021165e-07,
"loss": 1.4410962104797362,
"step": 395
},
{
"epoch": 1.0,
"step": 398,
"total_flos": 1.9165347193492685e+17,
"train_loss": 1.5956898921698182,
"train_runtime": 3205.1567,
"train_samples_per_second": 0.497,
"train_steps_per_second": 0.124
}
],
"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 sha256:2285c0fc33223a1182ea9a231d153f60da657239f7ce411fded036acab172d81
size 6033

BIN
training_loss.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 43 KiB