anjajar/baby_goldfish_new
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/baby_goldfish_new
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-15 17:57:17 +08:00
commit 065cf68cba
21 changed files with 447156 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_small_config.json
tags:
- generated_from_trainer
model-index:
- name: baby_goldfish_new
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. -->
# baby_goldfish_new
This model is a fine-tuned version of [gpt_small_config.json](https://huggingface.co/gpt_small_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: 387
- num_epochs: 10
- 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": 512,
"n_head": 8,
"n_inner": 2048,
"n_layer": 4,
"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": 512,
"n_head": 8,
"n_inner": 2048,
"n_layer": 4,
"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 sha256:045584847064d2eb5dc229653586e0327ef2a4dfbb5e56b830944e62cb173418
size 156353584

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce56a644b43a957d344559794c779a3624f1264caad1d97458aedabe7db4314e
size 312741835

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e8425ffa539cd7299756c17d804955693f3af2c98cd1bdd1a958b1cbe0c28550
size 14645

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5c4faeb7590b14fb868d259d539b68ad8bbe516624c9eb07f67bcb75d3c509da
size 1383

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:609cf1da746d897de6995be7207b46d4bd7fddf35a26103e7fae174d3583b315
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

937
last-checkpoint/trainer_state.json Normal file
View File

@@ -0,0 +1,937 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 38780,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.07735946364105209,
"grad_norm": 1.558766484260559,
"learning_rate": 7.726098191214471e-05,
"loss": 7.285,
"step": 300
},
{
"epoch": 0.15471892728210418,
"grad_norm": 0.9385259747505188,
"learning_rate": 9.944781600812648e-05,
"loss": 4.7972,
"step": 600
},
{
"epoch": 0.23207839092315627,
"grad_norm": 0.9864380359649658,
"learning_rate": 9.866642356679604e-05,
"loss": 4.5563,
"step": 900
},
{
"epoch": 0.30943785456420836,
"grad_norm": 0.971341073513031,
"learning_rate": 9.788503112546558e-05,
"loss": 4.4545,
"step": 1200
},
{
"epoch": 0.3867973182052604,
"grad_norm": 0.8991674184799194,
"learning_rate": 9.710363868413513e-05,
"loss": 4.3616,
"step": 1500
},
{
"epoch": 0.46415678184631254,
"grad_norm": 0.9576361775398254,
"learning_rate": 9.632224624280469e-05,
"loss": 4.2695,
"step": 1800
},
{
"epoch": 0.5415162454873647,
"grad_norm": 0.9536678791046143,
"learning_rate": 9.554085380147423e-05,
"loss": 4.2254,
"step": 2100
},
{
"epoch": 0.6188757091284167,
"grad_norm": 0.892548680305481,
"learning_rate": 9.475946136014378e-05,
"loss": 4.1759,
"step": 2400
},
{
"epoch": 0.6962351727694688,
"grad_norm": 0.9262155294418335,
"learning_rate": 9.397806891881334e-05,
"loss": 4.1328,
"step": 2700
},
{
"epoch": 0.7735946364105208,
"grad_norm": 1.055438756942749,
"learning_rate": 9.319667647748288e-05,
"loss": 4.0732,
"step": 3000
},
{
"epoch": 0.850954100051573,
"grad_norm": 1.0588972568511963,
"learning_rate": 9.241528403615243e-05,
"loss": 4.0574,
"step": 3300
},
{
"epoch": 0.9283135636926251,
"grad_norm": 1.344167947769165,
"learning_rate": 9.163389159482197e-05,
"loss": 4.0472,
"step": 3600
},
{
"epoch": 1.0056730273336771,
"grad_norm": 0.9573405981063843,
"learning_rate": 9.085249915349152e-05,
"loss": 3.972,
"step": 3900
},
{
"epoch": 1.0830324909747293,
"grad_norm": 1.0597045421600342,
"learning_rate": 9.007110671216108e-05,
"loss": 3.8933,
"step": 4200
},
{
"epoch": 1.1603919546157813,
"grad_norm": 1.1895560026168823,
"learning_rate": 8.928971427083062e-05,
"loss": 3.8657,
"step": 4500
},
{
"epoch": 1.2377514182568334,
"grad_norm": 1.1971007585525513,
"learning_rate": 8.850832182950017e-05,
"loss": 3.8486,
"step": 4800
},
{
"epoch": 1.3151108818978856,
"grad_norm": 1.2342840433120728,
"learning_rate": 8.772692938816972e-05,
"loss": 3.8417,
"step": 5100
},
{
"epoch": 1.3924703455389376,
"grad_norm": 1.213428258895874,
"learning_rate": 8.694553694683926e-05,
"loss": 3.8048,
"step": 5400
},
{
"epoch": 1.4698298091799897,
"grad_norm": 1.191662073135376,
"learning_rate": 8.616414450550882e-05,
"loss": 3.7818,
"step": 5700
},
{
"epoch": 1.5471892728210417,
"grad_norm": 1.3016968965530396,
"learning_rate": 8.538275206417838e-05,
"loss": 3.7365,
"step": 6000
},
{
"epoch": 1.6245487364620939,
"grad_norm": 1.179246187210083,
"learning_rate": 8.460135962284792e-05,
"loss": 3.7605,
"step": 6300
},
{
"epoch": 1.701908200103146,
"grad_norm": 1.2382755279541016,
"learning_rate": 8.381996718151747e-05,
"loss": 3.6887,
"step": 6600
},
{
"epoch": 1.7792676637441982,
"grad_norm": 1.209956169128418,
"learning_rate": 8.303857474018702e-05,
"loss": 3.7204,
"step": 6900
},
{
"epoch": 1.8566271273852502,
"grad_norm": 1.119544267654419,
"learning_rate": 8.225718229885656e-05,
"loss": 3.6682,
"step": 7200
},
{
"epoch": 1.933986591026302,
"grad_norm": 1.2890771627426147,
"learning_rate": 8.147578985752612e-05,
"loss": 3.6434,
"step": 7500
},
{
"epoch": 2.0113460546673543,
"grad_norm": 1.2189580202102661,
"learning_rate": 8.069439741619567e-05,
"loss": 3.6477,
"step": 7800
},
{
"epoch": 2.0887055183084065,
"grad_norm": 1.4200156927108765,
"learning_rate": 7.991300497486521e-05,
"loss": 3.5883,
"step": 8100
},
{
"epoch": 2.1660649819494586,
"grad_norm": 1.1501333713531494,
"learning_rate": 7.913161253353476e-05,
"loss": 3.6023,
"step": 8400
},
{
"epoch": 2.2434244455905104,
"grad_norm": 1.321439504623413,
"learning_rate": 7.83502200922043e-05,
"loss": 3.5765,
"step": 8700
},
{
"epoch": 2.3207839092315625,
"grad_norm": 1.4532771110534668,
"learning_rate": 7.756882765087386e-05,
"loss": 3.5858,
"step": 9000
},
{
"epoch": 2.3981433728726147,
"grad_norm": 1.2922136783599854,
"learning_rate": 7.67874352095434e-05,
"loss": 3.5483,
"step": 9300
},
{
"epoch": 2.475502836513667,
"grad_norm": 1.459169864654541,
"learning_rate": 7.600604276821297e-05,
"loss": 3.551,
"step": 9600
},
{
"epoch": 2.552862300154719,
"grad_norm": 1.3106615543365479,
"learning_rate": 7.522465032688251e-05,
"loss": 3.5216,
"step": 9900
},
{
"epoch": 2.630221763795771,
"grad_norm": 1.4244039058685303,
"learning_rate": 7.444325788555206e-05,
"loss": 3.5251,
"step": 10200
},
{
"epoch": 2.707581227436823,
"grad_norm": 1.3957465887069702,
"learning_rate": 7.366186544422162e-05,
"loss": 3.5245,
"step": 10500
},
{
"epoch": 2.784940691077875,
"grad_norm": 1.4246965646743774,
"learning_rate": 7.288047300289116e-05,
"loss": 3.4938,
"step": 10800
},
{
"epoch": 2.8623001547189273,
"grad_norm": 1.3009408712387085,
"learning_rate": 7.209908056156071e-05,
"loss": 3.4972,
"step": 11100
},
{
"epoch": 2.9396596183599795,
"grad_norm": 1.2788194417953491,
"learning_rate": 7.131768812023025e-05,
"loss": 3.4835,
"step": 11400
},
{
"epoch": 3.0170190820010316,
"grad_norm": 1.415262222290039,
"learning_rate": 7.05362956788998e-05,
"loss": 3.4686,
"step": 11700
},
{
"epoch": 3.0943785456420834,
"grad_norm": 1.3552271127700806,
"learning_rate": 6.975490323756934e-05,
"loss": 3.4434,
"step": 12000
},
{
"epoch": 3.1717380092831355,
"grad_norm": 1.2953003644943237,
"learning_rate": 6.89735107962389e-05,
"loss": 3.406,
"step": 12300
},
{
"epoch": 3.2490974729241877,
"grad_norm": 1.2616957426071167,
"learning_rate": 6.819211835490845e-05,
"loss": 3.4219,
"step": 12600
},
{
"epoch": 3.32645693656524,
"grad_norm": 1.3086093664169312,
"learning_rate": 6.7410725913578e-05,
"loss": 3.4327,
"step": 12900
},
{
"epoch": 3.403816400206292,
"grad_norm": 1.5225331783294678,
"learning_rate": 6.662933347224755e-05,
"loss": 3.3881,
"step": 13200
},
{
"epoch": 3.4811758638473442,
"grad_norm": 1.3017733097076416,
"learning_rate": 6.58479410309171e-05,
"loss": 3.4253,
"step": 13500
},
{
"epoch": 3.558535327488396,
"grad_norm": 1.4945634603500366,
"learning_rate": 6.506654858958666e-05,
"loss": 3.3739,
"step": 13800
},
{
"epoch": 3.635894791129448,
"grad_norm": 1.3506596088409424,
"learning_rate": 6.42851561482562e-05,
"loss": 3.3795,
"step": 14100
},
{
"epoch": 3.7132542547705003,
"grad_norm": 1.3715941905975342,
"learning_rate": 6.350376370692575e-05,
"loss": 3.3621,
"step": 14400
},
{
"epoch": 3.7906137184115525,
"grad_norm": 1.4353686571121216,
"learning_rate": 6.27223712655953e-05,
"loss": 3.3625,
"step": 14700
},
{
"epoch": 3.867973182052604,
"grad_norm": 1.4907252788543701,
"learning_rate": 6.194097882426484e-05,
"loss": 3.3694,
"step": 15000
},
{
"epoch": 3.9453326456936564,
"grad_norm": 1.3906782865524292,
"learning_rate": 6.11595863829344e-05,
"loss": 3.3778,
"step": 15300
},
{
"epoch": 4.0226921093347086,
"grad_norm": 1.4113860130310059,
"learning_rate": 6.0378193941603944e-05,
"loss": 3.3418,
"step": 15600
},
{
"epoch": 4.100051572975761,
"grad_norm": 1.371813416481018,
"learning_rate": 5.959680150027349e-05,
"loss": 3.2831,
"step": 15900
},
{
"epoch": 4.177411036616813,
"grad_norm": 1.433017611503601,
"learning_rate": 5.881540905894304e-05,
"loss": 3.2937,
"step": 16200
},
{
"epoch": 4.254770500257865,
"grad_norm": 1.454952597618103,
"learning_rate": 5.803401661761259e-05,
"loss": 3.2925,
"step": 16500
},
{
"epoch": 4.332129963898917,
"grad_norm": 1.4268256425857544,
"learning_rate": 5.725262417628213e-05,
"loss": 3.3171,
"step": 16800
},
{
"epoch": 4.409489427539969,
"grad_norm": 1.4231845140457153,
"learning_rate": 5.647123173495169e-05,
"loss": 3.3303,
"step": 17100
},
{
"epoch": 4.486848891181021,
"grad_norm": 1.358296275138855,
"learning_rate": 5.568983929362124e-05,
"loss": 3.3273,
"step": 17400
},
{
"epoch": 4.564208354822073,
"grad_norm": 1.4314409494400024,
"learning_rate": 5.490844685229078e-05,
"loss": 3.3027,
"step": 17700
},
{
"epoch": 4.641567818463125,
"grad_norm": 1.447662353515625,
"learning_rate": 5.4127054410960335e-05,
"loss": 3.2779,
"step": 18000
},
{
"epoch": 4.718927282104177,
"grad_norm": 1.498307466506958,
"learning_rate": 5.334566196962988e-05,
"loss": 3.2733,
"step": 18300
},
{
"epoch": 4.796286745745229,
"grad_norm": 1.3249318599700928,
"learning_rate": 5.256426952829944e-05,
"loss": 3.2159,
"step": 18600
},
{
"epoch": 4.873646209386282,
"grad_norm": 1.7372560501098633,
"learning_rate": 5.1782877086968985e-05,
"loss": 3.2769,
"step": 18900
},
{
"epoch": 4.951005673027334,
"grad_norm": 1.475892186164856,
"learning_rate": 5.100148464563853e-05,
"loss": 3.2724,
"step": 19200
},
{
"epoch": 5.028365136668386,
"grad_norm": 1.5225096940994263,
"learning_rate": 5.0220092204308076e-05,
"loss": 3.2132,
"step": 19500
},
{
"epoch": 5.105724600309438,
"grad_norm": 1.5637928247451782,
"learning_rate": 4.943869976297763e-05,
"loss": 3.2313,
"step": 19800
},
{
"epoch": 5.18308406395049,
"grad_norm": 1.5115944147109985,
"learning_rate": 4.865730732164718e-05,
"loss": 3.2163,
"step": 20100
},
{
"epoch": 5.260443527591542,
"grad_norm": 1.4446969032287598,
"learning_rate": 4.7875914880316726e-05,
"loss": 3.1997,
"step": 20400
},
{
"epoch": 5.337802991232594,
"grad_norm": 1.4487448930740356,
"learning_rate": 4.709452243898628e-05,
"loss": 3.2236,
"step": 20700
},
{
"epoch": 5.415162454873646,
"grad_norm": 1.5380080938339233,
"learning_rate": 4.6313129997655824e-05,
"loss": 3.2076,
"step": 21000
},
{
"epoch": 5.492521918514698,
"grad_norm": 1.4626458883285522,
"learning_rate": 4.5531737556325376e-05,
"loss": 3.2204,
"step": 21300
},
{
"epoch": 5.56988138215575,
"grad_norm": 1.6070873737335205,
"learning_rate": 4.475034511499492e-05,
"loss": 3.182,
"step": 21600
},
{
"epoch": 5.647240845796802,
"grad_norm": 1.5365498065948486,
"learning_rate": 4.3968952673664474e-05,
"loss": 3.1846,
"step": 21900
},
{
"epoch": 5.724600309437855,
"grad_norm": 1.6350524425506592,
"learning_rate": 4.3187560232334026e-05,
"loss": 3.2233,
"step": 22200
},
{
"epoch": 5.801959773078907,
"grad_norm": 1.5178848505020142,
"learning_rate": 4.240616779100357e-05,
"loss": 3.2046,
"step": 22500
},
{
"epoch": 5.879319236719959,
"grad_norm": 1.5043169260025024,
"learning_rate": 4.162477534967312e-05,
"loss": 3.16,
"step": 22800
},
{
"epoch": 5.956678700361011,
"grad_norm": 1.371469259262085,
"learning_rate": 4.084338290834267e-05,
"loss": 3.2134,
"step": 23100
},
{
"epoch": 6.034038164002063,
"grad_norm": 1.660897970199585,
"learning_rate": 4.0061990467012215e-05,
"loss": 3.1417,
"step": 23400
},
{
"epoch": 6.111397627643115,
"grad_norm": 1.6934055089950562,
"learning_rate": 3.928059802568177e-05,
"loss": 3.1623,
"step": 23700
},
{
"epoch": 6.188757091284167,
"grad_norm": 1.6035997867584229,
"learning_rate": 3.849920558435132e-05,
"loss": 3.1501,
"step": 24000
},
{
"epoch": 6.266116554925219,
"grad_norm": 1.618349313735962,
"learning_rate": 3.7717813143020865e-05,
"loss": 3.1305,
"step": 24300
},
{
"epoch": 6.343476018566271,
"grad_norm": 1.519572377204895,
"learning_rate": 3.693642070169042e-05,
"loss": 3.1529,
"step": 24600
},
{
"epoch": 6.420835482207323,
"grad_norm": 1.5830146074295044,
"learning_rate": 3.615502826035996e-05,
"loss": 3.1571,
"step": 24900
},
{
"epoch": 6.498194945848375,
"grad_norm": 1.6157386302947998,
"learning_rate": 3.537363581902951e-05,
"loss": 3.1564,
"step": 25200
},
{
"epoch": 6.575554409489428,
"grad_norm": 1.5344434976577759,
"learning_rate": 3.459224337769906e-05,
"loss": 3.1638,
"step": 25500
},
{
"epoch": 6.65291387313048,
"grad_norm": 1.6386032104492188,
"learning_rate": 3.381085093636861e-05,
"loss": 3.0942,
"step": 25800
},
{
"epoch": 6.730273336771532,
"grad_norm": 1.5561423301696777,
"learning_rate": 3.302945849503816e-05,
"loss": 3.121,
"step": 26100
},
{
"epoch": 6.807632800412584,
"grad_norm": 1.6447923183441162,
"learning_rate": 3.224806605370771e-05,
"loss": 3.1108,
"step": 26400
},
{
"epoch": 6.884992264053636,
"grad_norm": 1.6027878522872925,
"learning_rate": 3.1466673612377256e-05,
"loss": 3.1331,
"step": 26700
},
{
"epoch": 6.9623517276946885,
"grad_norm": 1.6786209344863892,
"learning_rate": 3.068528117104681e-05,
"loss": 3.1515,
"step": 27000
},
{
"epoch": 7.03971119133574,
"grad_norm": 1.725610613822937,
"learning_rate": 2.9903888729716357e-05,
"loss": 3.1025,
"step": 27300
},
{
"epoch": 7.117070654976792,
"grad_norm": 1.6194796562194824,
"learning_rate": 2.9122496288385903e-05,
"loss": 3.0819,
"step": 27600
},
{
"epoch": 7.194430118617844,
"grad_norm": 1.7126758098602295,
"learning_rate": 2.8341103847055455e-05,
"loss": 3.1056,
"step": 27900
},
{
"epoch": 7.271789582258896,
"grad_norm": 1.610686182975769,
"learning_rate": 2.7559711405725004e-05,
"loss": 3.0932,
"step": 28200
},
{
"epoch": 7.349149045899948,
"grad_norm": 1.6700507402420044,
"learning_rate": 2.677831896439455e-05,
"loss": 3.0938,
"step": 28500
},
{
"epoch": 7.426508509541001,
"grad_norm": 1.5000895261764526,
"learning_rate": 2.59969265230641e-05,
"loss": 3.0911,
"step": 28800
},
{
"epoch": 7.503867973182053,
"grad_norm": 1.6568007469177246,
"learning_rate": 2.521553408173365e-05,
"loss": 3.0938,
"step": 29100
},
{
"epoch": 7.581227436823105,
"grad_norm": 1.7494336366653442,
"learning_rate": 2.44341416404032e-05,
"loss": 3.0711,
"step": 29400
},
{
"epoch": 7.658586900464157,
"grad_norm": 1.7158912420272827,
"learning_rate": 2.3652749199072748e-05,
"loss": 3.072,
"step": 29700
},
{
"epoch": 7.735946364105208,
"grad_norm": 1.7721878290176392,
"learning_rate": 2.2871356757742297e-05,
"loss": 3.1069,
"step": 30000
},
{
"epoch": 7.813305827746261,
"grad_norm": 1.5379910469055176,
"learning_rate": 2.2089964316411846e-05,
"loss": 3.0882,
"step": 30300
},
{
"epoch": 7.890665291387313,
"grad_norm": 1.6254152059555054,
"learning_rate": 2.1308571875081395e-05,
"loss": 3.0506,
"step": 30600
},
{
"epoch": 7.968024755028365,
"grad_norm": 1.6591140031814575,
"learning_rate": 2.0527179433750944e-05,
"loss": 3.0912,
"step": 30900
},
{
"epoch": 8.045384218669417,
"grad_norm": 1.4908177852630615,
"learning_rate": 1.9745786992420496e-05,
"loss": 3.0567,
"step": 31200
},
{
"epoch": 8.12274368231047,
"grad_norm": 1.6893351078033447,
"learning_rate": 1.896439455109004e-05,
"loss": 3.0538,
"step": 31500
},
{
"epoch": 8.200103145951521,
"grad_norm": 1.6335694789886475,
"learning_rate": 1.818300210975959e-05,
"loss": 3.0596,
"step": 31800
},
{
"epoch": 8.277462609592574,
"grad_norm": 1.814844012260437,
"learning_rate": 1.7401609668429143e-05,
"loss": 3.0789,
"step": 32100
},
{
"epoch": 8.354822073233626,
"grad_norm": 1.666052222251892,
"learning_rate": 1.662021722709869e-05,
"loss": 3.0435,
"step": 32400
},
{
"epoch": 8.432181536874678,
"grad_norm": 1.8534607887268066,
"learning_rate": 1.5838824785768237e-05,
"loss": 3.0542,
"step": 32700
},
{
"epoch": 8.50954100051573,
"grad_norm": 1.8089135885238647,
"learning_rate": 1.5057432344437788e-05,
"loss": 3.0435,
"step": 33000
},
{
"epoch": 8.586900464156782,
"grad_norm": 1.5717253684997559,
"learning_rate": 1.4276039903107338e-05,
"loss": 3.0323,
"step": 33300
},
{
"epoch": 8.664259927797834,
"grad_norm": 1.681136131286621,
"learning_rate": 1.3494647461776889e-05,
"loss": 3.0528,
"step": 33600
},
{
"epoch": 8.741619391438887,
"grad_norm": 1.700218915939331,
"learning_rate": 1.2713255020446434e-05,
"loss": 3.0454,
"step": 33900
},
{
"epoch": 8.818978855079939,
"grad_norm": 1.8672676086425781,
"learning_rate": 1.1931862579115985e-05,
"loss": 3.0757,
"step": 34200
},
{
"epoch": 8.896338318720991,
"grad_norm": 1.7094194889068604,
"learning_rate": 1.1150470137785534e-05,
"loss": 3.0514,
"step": 34500
},
{
"epoch": 8.973697782362041,
"grad_norm": 1.7016539573669434,
"learning_rate": 1.0369077696455083e-05,
"loss": 3.022,
"step": 34800
},
{
"epoch": 9.051057246003094,
"grad_norm": 1.7859755754470825,
"learning_rate": 9.587685255124633e-06,
"loss": 3.0189,
"step": 35100
},
{
"epoch": 9.128416709644146,
"grad_norm": 1.6786860227584839,
"learning_rate": 8.80629281379418e-06,
"loss": 3.0062,
"step": 35400
},
{
"epoch": 9.205776173285198,
"grad_norm": 1.7441751956939697,
"learning_rate": 8.024900372463731e-06,
"loss": 3.0036,
"step": 35700
},
{
"epoch": 9.28313563692625,
"grad_norm": 1.6931071281433105,
"learning_rate": 7.243507931133279e-06,
"loss": 3.0179,
"step": 36000
},
{
"epoch": 9.360495100567302,
"grad_norm": 1.5787148475646973,
"learning_rate": 6.46211548980283e-06,
"loss": 3.045,
"step": 36300
},
{
"epoch": 9.437854564208354,
"grad_norm": 1.8229496479034424,
"learning_rate": 5.680723048472378e-06,
"loss": 3.0025,
"step": 36600
},
{
"epoch": 9.515214027849407,
"grad_norm": 1.8122637271881104,
"learning_rate": 4.899330607141927e-06,
"loss": 3.0239,
"step": 36900
},
{
"epoch": 9.592573491490459,
"grad_norm": 1.5085257291793823,
"learning_rate": 4.117938165811476e-06,
"loss": 3.0226,
"step": 37200
},
{
"epoch": 9.669932955131511,
"grad_norm": 1.8228789567947388,
"learning_rate": 3.336545724481025e-06,
"loss": 3.0286,
"step": 37500
},
{
"epoch": 9.747292418772563,
"grad_norm": 1.5136455297470093,
"learning_rate": 2.5551532831505747e-06,
"loss": 3.0184,
"step": 37800
},
{
"epoch": 9.824651882413615,
"grad_norm": 1.7498648166656494,
"learning_rate": 1.7737608418201238e-06,
"loss": 3.002,
"step": 38100
},
{
"epoch": 9.902011346054667,
"grad_norm": 1.625130534172058,
"learning_rate": 9.923684004896727e-07,
"loss": 3.0423,
"step": 38400
},
{
"epoch": 9.97937080969572,
"grad_norm": 1.782974362373352,
"learning_rate": 2.1097595915922174e-07,
"loss": 3.023,
"step": 38700
}
],
"logging_steps": 300,
"max_steps": 38780,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 300,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.20181986164736e+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:eb41a6a22dfdaf4e03f114cbb5893d8e2bed45157fad3f8de27661c34562afea
size 5841

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:045584847064d2eb5dc229653586e0327ef2a4dfbb5e56b830944e62cb173418
size 156353584

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:eb41a6a22dfdaf4e03f114cbb5893d8e2bed45157fad3f8de27661c34562afea
size 5841