anjajar/adult_goldfish_rus_large
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: anjajar/adult_goldfish_rus_large
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-05 14:55:20 +08:00
commit 6b43b29ab1
21 changed files with 446932 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.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

54
README.md Normal file
View File

@@ -0,0 +1,54 @@
---
library_name: transformers
base_model: gpt_base_config.json
tags:
- generated_from_trainer
model-index:
- name: adult_goldfish_rus_large
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. -->
# adult_goldfish_rus_large
This model is a fine-tuned version of [gpt_base_config.json](https://huggingface.co/gpt_base_config.json) on the None 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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 43
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2940
- num_epochs: 100
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1

34
config.json Normal file
View File

@@ -0,0 +1,34 @@
{
"activation_function": "gelu",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50000,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 50001,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 512,
"n_embd": 768,
"n_head": 12,
"n_inner": 3072,
"n_layer": 12,
"n_positions": 512,
"pad_token_id": 50002,
"prefix": "[CLS]",
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"transformers_version": "4.57.3",
"use_cache": true,
"vocab_size": 51200
}

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 50000,
"eos_token_id": 50001,
"pad_token_id": 50002,
"transformers_version": "4.57.3"
}

34
last-checkpoint/config.json Normal file
View File

@@ -0,0 +1,34 @@
{
"activation_function": "gelu",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50000,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 50001,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 512,
"n_embd": 768,
"n_head": 12,
"n_inner": 3072,
"n_layer": 12,
"n_positions": 512,
"pad_token_id": 50002,
"prefix": "[CLS]",
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"transformers_version": "4.57.3",
"use_cache": true,
"vocab_size": 51200
}

7
last-checkpoint/generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 50000,
"eos_token_id": 50001,
"pad_token_id": 50002,
"transformers_version": "4.57.3"
}

3
last-checkpoint/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ad83f0891299f4b93995614cb44dd15f4f2b3944abf24a917e14d0a9d57fe51d
size 499098240

3
last-checkpoint/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fa775898023b4b49f1048fc30a632b9525cdda67bba221d20af76c5c045cf092
size 998292875

3
last-checkpoint/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ada7cf0c02a0e0a40d16f772b0e2ca598a27b13a6323e0945b708fdf5c70169a
size 14645

3
last-checkpoint/scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3525da2f7dbc46bbe78c5e8beeb81cd57781bdcd526ea4ab3f54c5ac8a5edbac
size 1383

3
last-checkpoint/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac8014c9ad4b910751ad0530680311249c3e8967b019256cb2be39c16e9a2cef
size 1465

1243
last-checkpoint/special_tokens_map.json Normal file
View File

File diff suppressed because it is too large Load Diff

210940
last-checkpoint/tokenizer.json Normal file
View File

File diff suppressed because one or more lines are too long

10829
last-checkpoint/tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

713
last-checkpoint/trainer_state.json Normal file
View File

@@ -0,0 +1,713 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 98.9795918367347,
"eval_steps": 500,
"global_step": 29100,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0204081632653061,
"grad_norm": 1.544520378112793,
"learning_rate": 1.0170068027210885e-05,
"loss": 9.6915,
"step": 300
},
{
"epoch": 2.0408163265306123,
"grad_norm": 1.6265058517456055,
"learning_rate": 2.0374149659863947e-05,
"loss": 8.3327,
"step": 600
},
{
"epoch": 3.061224489795918,
"grad_norm": 2.0470693111419678,
"learning_rate": 3.0578231292517004e-05,
"loss": 7.7972,
"step": 900
},
{
"epoch": 4.081632653061225,
"grad_norm": 1.7373660802841187,
"learning_rate": 4.078231292517007e-05,
"loss": 7.508,
"step": 1200
},
{
"epoch": 5.1020408163265305,
"grad_norm": 2.189188241958618,
"learning_rate": 5.0986394557823136e-05,
"loss": 7.2126,
"step": 1500
},
{
"epoch": 6.122448979591836,
"grad_norm": 2.1524977684020996,
"learning_rate": 6.11904761904762e-05,
"loss": 6.9194,
"step": 1800
},
{
"epoch": 7.142857142857143,
"grad_norm": 2.03401517868042,
"learning_rate": 7.139455782312926e-05,
"loss": 6.6392,
"step": 2100
},
{
"epoch": 8.16326530612245,
"grad_norm": 2.0746707916259766,
"learning_rate": 8.159863945578233e-05,
"loss": 6.3837,
"step": 2400
},
{
"epoch": 9.183673469387756,
"grad_norm": 2.1161186695098877,
"learning_rate": 9.180272108843538e-05,
"loss": 6.1311,
"step": 2700
},
{
"epoch": 10.204081632653061,
"grad_norm": 2.1764469146728516,
"learning_rate": 9.977702191987907e-05,
"loss": 5.8614,
"step": 3000
},
{
"epoch": 11.224489795918368,
"grad_norm": 2.414827823638916,
"learning_rate": 9.86432350718065e-05,
"loss": 5.5985,
"step": 3300
},
{
"epoch": 12.244897959183673,
"grad_norm": 2.5662031173706055,
"learning_rate": 9.750944822373394e-05,
"loss": 5.3029,
"step": 3600
},
{
"epoch": 13.26530612244898,
"grad_norm": 2.821119785308838,
"learning_rate": 9.637566137566139e-05,
"loss": 5.0116,
"step": 3900
},
{
"epoch": 14.285714285714286,
"grad_norm": 3.0048000812530518,
"learning_rate": 9.524187452758882e-05,
"loss": 4.7344,
"step": 4200
},
{
"epoch": 15.306122448979592,
"grad_norm": 3.242598295211792,
"learning_rate": 9.410808767951625e-05,
"loss": 4.4621,
"step": 4500
},
{
"epoch": 16.3265306122449,
"grad_norm": 3.316965103149414,
"learning_rate": 9.29743008314437e-05,
"loss": 4.2054,
"step": 4800
},
{
"epoch": 17.346938775510203,
"grad_norm": 3.7419989109039307,
"learning_rate": 9.184051398337114e-05,
"loss": 3.9517,
"step": 5100
},
{
"epoch": 18.367346938775512,
"grad_norm": 3.7479987144470215,
"learning_rate": 9.070672713529857e-05,
"loss": 3.7011,
"step": 5400
},
{
"epoch": 19.387755102040817,
"grad_norm": 3.7604148387908936,
"learning_rate": 8.9572940287226e-05,
"loss": 3.4686,
"step": 5700
},
{
"epoch": 20.408163265306122,
"grad_norm": 4.052367210388184,
"learning_rate": 8.843915343915344e-05,
"loss": 3.2285,
"step": 6000
},
{
"epoch": 21.428571428571427,
"grad_norm": 4.340782642364502,
"learning_rate": 8.730536659108089e-05,
"loss": 3.0094,
"step": 6300
},
{
"epoch": 22.448979591836736,
"grad_norm": 4.590024948120117,
"learning_rate": 8.617157974300832e-05,
"loss": 2.7901,
"step": 6600
},
{
"epoch": 23.46938775510204,
"grad_norm": 4.343008995056152,
"learning_rate": 8.503779289493575e-05,
"loss": 2.5887,
"step": 6900
},
{
"epoch": 24.489795918367346,
"grad_norm": 4.200931549072266,
"learning_rate": 8.39040060468632e-05,
"loss": 2.3804,
"step": 7200
},
{
"epoch": 25.510204081632654,
"grad_norm": 4.765750408172607,
"learning_rate": 8.277021919879064e-05,
"loss": 2.1853,
"step": 7500
},
{
"epoch": 26.53061224489796,
"grad_norm": 4.196296215057373,
"learning_rate": 8.163643235071807e-05,
"loss": 2.0026,
"step": 7800
},
{
"epoch": 27.551020408163264,
"grad_norm": 4.485163688659668,
"learning_rate": 8.05026455026455e-05,
"loss": 1.8218,
"step": 8100
},
{
"epoch": 28.571428571428573,
"grad_norm": 4.515989780426025,
"learning_rate": 7.936885865457294e-05,
"loss": 1.6588,
"step": 8400
},
{
"epoch": 29.591836734693878,
"grad_norm": 4.492111682891846,
"learning_rate": 7.823507180650039e-05,
"loss": 1.4945,
"step": 8700
},
{
"epoch": 30.612244897959183,
"grad_norm": 4.51740026473999,
"learning_rate": 7.710128495842782e-05,
"loss": 1.3481,
"step": 9000
},
{
"epoch": 31.632653061224488,
"grad_norm": 4.193362236022949,
"learning_rate": 7.596749811035526e-05,
"loss": 1.2062,
"step": 9300
},
{
"epoch": 32.6530612244898,
"grad_norm": 4.017958164215088,
"learning_rate": 7.483371126228269e-05,
"loss": 1.0725,
"step": 9600
},
{
"epoch": 33.673469387755105,
"grad_norm": 4.180546283721924,
"learning_rate": 7.369992441421014e-05,
"loss": 0.9466,
"step": 9900
},
{
"epoch": 34.69387755102041,
"grad_norm": 4.280745983123779,
"learning_rate": 7.256613756613757e-05,
"loss": 0.8416,
"step": 10200
},
{
"epoch": 35.714285714285715,
"grad_norm": 3.9538300037384033,
"learning_rate": 7.143235071806501e-05,
"loss": 0.7401,
"step": 10500
},
{
"epoch": 36.734693877551024,
"grad_norm": 4.204588890075684,
"learning_rate": 7.029856386999244e-05,
"loss": 0.6532,
"step": 10800
},
{
"epoch": 37.755102040816325,
"grad_norm": 3.8845582008361816,
"learning_rate": 6.916477702191987e-05,
"loss": 0.5701,
"step": 11100
},
{
"epoch": 38.775510204081634,
"grad_norm": 3.7283339500427246,
"learning_rate": 6.803099017384732e-05,
"loss": 0.5032,
"step": 11400
},
{
"epoch": 39.795918367346935,
"grad_norm": 3.3194797039031982,
"learning_rate": 6.689720332577476e-05,
"loss": 0.4403,
"step": 11700
},
{
"epoch": 40.816326530612244,
"grad_norm": 3.4429259300231934,
"learning_rate": 6.57634164777022e-05,
"loss": 0.3887,
"step": 12000
},
{
"epoch": 41.83673469387755,
"grad_norm": 3.080552577972412,
"learning_rate": 6.462962962962962e-05,
"loss": 0.3442,
"step": 12300
},
{
"epoch": 42.857142857142854,
"grad_norm": 3.2737112045288086,
"learning_rate": 6.349584278155707e-05,
"loss": 0.3071,
"step": 12600
},
{
"epoch": 43.87755102040816,
"grad_norm": 2.8895883560180664,
"learning_rate": 6.236205593348451e-05,
"loss": 0.275,
"step": 12900
},
{
"epoch": 44.89795918367347,
"grad_norm": 3.075352430343628,
"learning_rate": 6.122826908541194e-05,
"loss": 0.2475,
"step": 13200
},
{
"epoch": 45.91836734693877,
"grad_norm": 2.932194471359253,
"learning_rate": 6.009448223733938e-05,
"loss": 0.2239,
"step": 13500
},
{
"epoch": 46.93877551020408,
"grad_norm": 2.5952064990997314,
"learning_rate": 5.896069538926682e-05,
"loss": 0.2045,
"step": 13800
},
{
"epoch": 47.95918367346939,
"grad_norm": 2.456416606903076,
"learning_rate": 5.7826908541194255e-05,
"loss": 0.1875,
"step": 14100
},
{
"epoch": 48.97959183673469,
"grad_norm": 2.836243152618408,
"learning_rate": 5.66931216931217e-05,
"loss": 0.1717,
"step": 14400
},
{
"epoch": 50.0,
"grad_norm": 2.4769959449768066,
"learning_rate": 5.5559334845049137e-05,
"loss": 0.1582,
"step": 14700
},
{
"epoch": 51.02040816326531,
"grad_norm": 1.9502800703048706,
"learning_rate": 5.442554799697657e-05,
"loss": 0.1468,
"step": 15000
},
{
"epoch": 52.04081632653061,
"grad_norm": 2.145501136779785,
"learning_rate": 5.3291761148904005e-05,
"loss": 0.1366,
"step": 15300
},
{
"epoch": 53.06122448979592,
"grad_norm": 1.8530632257461548,
"learning_rate": 5.215797430083145e-05,
"loss": 0.1266,
"step": 15600
},
{
"epoch": 54.08163265306123,
"grad_norm": 2.0811140537261963,
"learning_rate": 5.1024187452758886e-05,
"loss": 0.1179,
"step": 15900
},
{
"epoch": 55.10204081632653,
"grad_norm": 1.8534563779830933,
"learning_rate": 4.9890400604686324e-05,
"loss": 0.1096,
"step": 16200
},
{
"epoch": 56.12244897959184,
"grad_norm": 1.7965441942214966,
"learning_rate": 4.875661375661376e-05,
"loss": 0.1032,
"step": 16500
},
{
"epoch": 57.142857142857146,
"grad_norm": 1.824494481086731,
"learning_rate": 4.76228269085412e-05,
"loss": 0.0967,
"step": 16800
},
{
"epoch": 58.16326530612245,
"grad_norm": 1.6980013847351074,
"learning_rate": 4.6489040060468636e-05,
"loss": 0.0907,
"step": 17100
},
{
"epoch": 59.183673469387756,
"grad_norm": 1.6149917840957642,
"learning_rate": 4.5355253212396074e-05,
"loss": 0.085,
"step": 17400
},
{
"epoch": 60.204081632653065,
"grad_norm": 1.788779854774475,
"learning_rate": 4.422146636432351e-05,
"loss": 0.0804,
"step": 17700
},
{
"epoch": 61.224489795918366,
"grad_norm": 1.7672044038772583,
"learning_rate": 4.308767951625094e-05,
"loss": 0.0759,
"step": 18000
},
{
"epoch": 62.244897959183675,
"grad_norm": 1.5566641092300415,
"learning_rate": 4.1953892668178386e-05,
"loss": 0.0722,
"step": 18300
},
{
"epoch": 63.265306122448976,
"grad_norm": 1.291110873222351,
"learning_rate": 4.082010582010582e-05,
"loss": 0.0678,
"step": 18600
},
{
"epoch": 64.28571428571429,
"grad_norm": 1.596009373664856,
"learning_rate": 3.968631897203326e-05,
"loss": 0.0639,
"step": 18900
},
{
"epoch": 65.3061224489796,
"grad_norm": 1.4961538314819336,
"learning_rate": 3.85525321239607e-05,
"loss": 0.0605,
"step": 19200
},
{
"epoch": 66.3265306122449,
"grad_norm": 1.383008599281311,
"learning_rate": 3.7418745275888136e-05,
"loss": 0.0571,
"step": 19500
},
{
"epoch": 67.34693877551021,
"grad_norm": 1.1882243156433105,
"learning_rate": 3.628495842781557e-05,
"loss": 0.0541,
"step": 19800
},
{
"epoch": 68.36734693877551,
"grad_norm": 1.4175117015838623,
"learning_rate": 3.515117157974301e-05,
"loss": 0.0515,
"step": 20100
},
{
"epoch": 69.38775510204081,
"grad_norm": 1.412561058998108,
"learning_rate": 3.401738473167045e-05,
"loss": 0.0492,
"step": 20400
},
{
"epoch": 70.40816326530613,
"grad_norm": 1.358535885810852,
"learning_rate": 3.2883597883597886e-05,
"loss": 0.0462,
"step": 20700
},
{
"epoch": 71.42857142857143,
"grad_norm": 1.338392972946167,
"learning_rate": 3.174981103552532e-05,
"loss": 0.0443,
"step": 21000
},
{
"epoch": 72.44897959183673,
"grad_norm": 1.3225773572921753,
"learning_rate": 3.061602418745276e-05,
"loss": 0.0419,
"step": 21300
},
{
"epoch": 73.46938775510205,
"grad_norm": 1.1727213859558105,
"learning_rate": 2.9482237339380198e-05,
"loss": 0.0394,
"step": 21600
},
{
"epoch": 74.48979591836735,
"grad_norm": 1.25161612033844,
"learning_rate": 2.834845049130764e-05,
"loss": 0.0375,
"step": 21900
},
{
"epoch": 75.51020408163265,
"grad_norm": 1.240116834640503,
"learning_rate": 2.7214663643235073e-05,
"loss": 0.0358,
"step": 22200
},
{
"epoch": 76.53061224489795,
"grad_norm": 0.9712527394294739,
"learning_rate": 2.6080876795162514e-05,
"loss": 0.0339,
"step": 22500
},
{
"epoch": 77.55102040816327,
"grad_norm": 1.147048830986023,
"learning_rate": 2.4947089947089948e-05,
"loss": 0.0323,
"step": 22800
},
{
"epoch": 78.57142857142857,
"grad_norm": 1.0916506052017212,
"learning_rate": 2.3813303099017385e-05,
"loss": 0.0308,
"step": 23100
},
{
"epoch": 79.59183673469387,
"grad_norm": 1.128098964691162,
"learning_rate": 2.2679516250944823e-05,
"loss": 0.0294,
"step": 23400
},
{
"epoch": 80.61224489795919,
"grad_norm": 1.0495482683181763,
"learning_rate": 2.154572940287226e-05,
"loss": 0.0276,
"step": 23700
},
{
"epoch": 81.63265306122449,
"grad_norm": 0.8648446798324585,
"learning_rate": 2.0411942554799698e-05,
"loss": 0.0261,
"step": 24000
},
{
"epoch": 82.65306122448979,
"grad_norm": 1.1346194744110107,
"learning_rate": 1.9278155706727135e-05,
"loss": 0.0245,
"step": 24300
},
{
"epoch": 83.6734693877551,
"grad_norm": 0.9076672196388245,
"learning_rate": 1.8144368858654572e-05,
"loss": 0.0237,
"step": 24600
},
{
"epoch": 84.6938775510204,
"grad_norm": 1.0035544633865356,
"learning_rate": 1.701058201058201e-05,
"loss": 0.0222,
"step": 24900
},
{
"epoch": 85.71428571428571,
"grad_norm": 0.769279956817627,
"learning_rate": 1.587679516250945e-05,
"loss": 0.0211,
"step": 25200
},
{
"epoch": 86.73469387755102,
"grad_norm": 0.9665892124176025,
"learning_rate": 1.4743008314436888e-05,
"loss": 0.0202,
"step": 25500
},
{
"epoch": 87.75510204081633,
"grad_norm": 0.9066174626350403,
"learning_rate": 1.3609221466364324e-05,
"loss": 0.0193,
"step": 25800
},
{
"epoch": 88.77551020408163,
"grad_norm": 0.9459673166275024,
"learning_rate": 1.2475434618291761e-05,
"loss": 0.0183,
"step": 26100
},
{
"epoch": 89.79591836734694,
"grad_norm": 0.8062217235565186,
"learning_rate": 1.1341647770219199e-05,
"loss": 0.0174,
"step": 26400
},
{
"epoch": 90.81632653061224,
"grad_norm": 0.8470116853713989,
"learning_rate": 1.0207860922146636e-05,
"loss": 0.0167,
"step": 26700
},
{
"epoch": 91.83673469387755,
"grad_norm": 0.7526578903198242,
"learning_rate": 9.074074074074075e-06,
"loss": 0.016,
"step": 27000
},
{
"epoch": 92.85714285714286,
"grad_norm": 0.6859294176101685,
"learning_rate": 7.940287226001513e-06,
"loss": 0.0154,
"step": 27300
},
{
"epoch": 93.87755102040816,
"grad_norm": 0.574286937713623,
"learning_rate": 6.8065003779289495e-06,
"loss": 0.0147,
"step": 27600
},
{
"epoch": 94.89795918367346,
"grad_norm": 0.9053287506103516,
"learning_rate": 5.672713529856388e-06,
"loss": 0.0143,
"step": 27900
},
{
"epoch": 95.91836734693878,
"grad_norm": 0.5810430645942688,
"learning_rate": 4.538926681783825e-06,
"loss": 0.0137,
"step": 28200
},
{
"epoch": 96.93877551020408,
"grad_norm": 0.5778042674064636,
"learning_rate": 3.4051398337112627e-06,
"loss": 0.0132,
"step": 28500
},
{
"epoch": 97.95918367346938,
"grad_norm": 0.5646163821220398,
"learning_rate": 2.2713529856387e-06,
"loss": 0.0129,
"step": 28800
},
{
"epoch": 98.9795918367347,
"grad_norm": 0.6283496022224426,
"learning_rate": 1.1375661375661376e-06,
"loss": 0.0126,
"step": 29100
}
],
"logging_steps": 300,
"max_steps": 29400,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 300,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.08287850496e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}

3
last-checkpoint/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aa5b38365f561f5bba4531f37658b5bf167235b63f34a2cb9c81142ad61b1898
size 5905

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:45f09aba5c0968c76a181f94e3d09cf7040fbad13eb0e961978ea1d0097ea8ed
size 499098240

1243
special_tokens_map.json Normal file
View File

File diff suppressed because it is too large Load Diff

210940
tokenizer.json Normal file
View File

File diff suppressed because one or more lines are too long

10829
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aa5b38365f561f5bba4531f37658b5bf167235b63f34a2cb9c81142ad61b1898
size 5905