anjajar/adult_goldfish_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_large
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-15 18:41:50 +08:00
commit bd8751d285
21 changed files with 447114 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_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_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: 370
- 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": 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:fb3d3396a132f4a78e350746d4186b1a095eaaea96bbc23a0422e55181b31b1e
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:c0b4374f235452239f4900e15b5b311fca430b1970372e77795aaab935db1ee0
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 sha256:9349403ec90c5e180f9b7a2ec446b09b0a12d92eac09c60b37ad32d42e3f384d
size 14645

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6fb57b215d887cf5d583e4ac0020930879d08c3daa915840c9052228240799f6
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:cbfbb4113c1dd614b42285e357529f1915132b2b5d5e676016ff2b3051ef7df0
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

895
last-checkpoint/trainer_state.json Normal file
View File

@@ -0,0 +1,895 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 37040,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08099352051835854,
"grad_norm": 1.2232078313827515,
"learning_rate": 8.08108108108108e-05,
"loss": 8.4372,
"step": 300
},
{
"epoch": 0.16198704103671707,
"grad_norm": 1.2085011005401611,
"learning_rate": 9.9375511317153e-05,
"loss": 7.116,
"step": 600
},
{
"epoch": 0.24298056155507558,
"grad_norm": 0.9084240794181824,
"learning_rate": 9.855740387237524e-05,
"loss": 6.8316,
"step": 900
},
{
"epoch": 0.32397408207343414,
"grad_norm": 0.9802172780036926,
"learning_rate": 9.77392964275975e-05,
"loss": 6.6389,
"step": 1200
},
{
"epoch": 0.40496760259179265,
"grad_norm": 1.2083544731140137,
"learning_rate": 9.692118898281974e-05,
"loss": 6.5172,
"step": 1500
},
{
"epoch": 0.48596112311015116,
"grad_norm": 1.1617285013198853,
"learning_rate": 9.610308153804201e-05,
"loss": 6.3892,
"step": 1800
},
{
"epoch": 0.5669546436285097,
"grad_norm": 1.1057401895523071,
"learning_rate": 9.528497409326425e-05,
"loss": 6.2733,
"step": 2100
},
{
"epoch": 0.6479481641468683,
"grad_norm": 1.1652714014053345,
"learning_rate": 9.446686664848651e-05,
"loss": 6.1542,
"step": 2400
},
{
"epoch": 0.7289416846652268,
"grad_norm": 1.1327797174453735,
"learning_rate": 9.364875920370875e-05,
"loss": 6.0642,
"step": 2700
},
{
"epoch": 0.8099352051835853,
"grad_norm": 1.1129639148712158,
"learning_rate": 9.283065175893101e-05,
"loss": 5.9595,
"step": 3000
},
{
"epoch": 0.8909287257019438,
"grad_norm": 1.1772035360336304,
"learning_rate": 9.201254431415327e-05,
"loss": 5.8886,
"step": 3300
},
{
"epoch": 0.9719222462203023,
"grad_norm": 1.1345826387405396,
"learning_rate": 9.119443686937551e-05,
"loss": 5.8212,
"step": 3600
},
{
"epoch": 1.0529157667386608,
"grad_norm": 1.1569806337356567,
"learning_rate": 9.037632942459777e-05,
"loss": 5.6998,
"step": 3900
},
{
"epoch": 1.1339092872570196,
"grad_norm": 1.2677946090698242,
"learning_rate": 8.955822197982002e-05,
"loss": 5.6339,
"step": 4200
},
{
"epoch": 1.214902807775378,
"grad_norm": 1.2447303533554077,
"learning_rate": 8.874011453504228e-05,
"loss": 5.6141,
"step": 4500
},
{
"epoch": 1.2958963282937366,
"grad_norm": 1.2059963941574097,
"learning_rate": 8.792200709026452e-05,
"loss": 5.5655,
"step": 4800
},
{
"epoch": 1.376889848812095,
"grad_norm": 1.2978270053863525,
"learning_rate": 8.710389964548678e-05,
"loss": 5.5272,
"step": 5100
},
{
"epoch": 1.4578833693304536,
"grad_norm": 1.2664310932159424,
"learning_rate": 8.628579220070902e-05,
"loss": 5.476,
"step": 5400
},
{
"epoch": 1.538876889848812,
"grad_norm": 1.2178924083709717,
"learning_rate": 8.546768475593129e-05,
"loss": 5.4346,
"step": 5700
},
{
"epoch": 1.6198704103671706,
"grad_norm": 1.266420841217041,
"learning_rate": 8.464957731115354e-05,
"loss": 5.4054,
"step": 6000
},
{
"epoch": 1.7008639308855291,
"grad_norm": 1.23899507522583,
"learning_rate": 8.383146986637579e-05,
"loss": 5.3561,
"step": 6300
},
{
"epoch": 1.7818574514038876,
"grad_norm": 1.3659826517105103,
"learning_rate": 8.301336242159804e-05,
"loss": 5.3211,
"step": 6600
},
{
"epoch": 1.8628509719222461,
"grad_norm": 1.2756917476654053,
"learning_rate": 8.219525497682029e-05,
"loss": 5.2925,
"step": 6900
},
{
"epoch": 1.9438444924406046,
"grad_norm": 1.329283356666565,
"learning_rate": 8.137714753204254e-05,
"loss": 5.2797,
"step": 7200
},
{
"epoch": 2.024838012958963,
"grad_norm": 1.422574758529663,
"learning_rate": 8.05590400872648e-05,
"loss": 5.1991,
"step": 7500
},
{
"epoch": 2.1058315334773217,
"grad_norm": 1.2917046546936035,
"learning_rate": 7.974093264248705e-05,
"loss": 5.0749,
"step": 7800
},
{
"epoch": 2.18682505399568,
"grad_norm": 1.3476394414901733,
"learning_rate": 7.89228251977093e-05,
"loss": 5.0792,
"step": 8100
},
{
"epoch": 2.267818574514039,
"grad_norm": 1.3360469341278076,
"learning_rate": 7.810471775293156e-05,
"loss": 5.0675,
"step": 8400
},
{
"epoch": 2.3488120950323976,
"grad_norm": 1.4274685382843018,
"learning_rate": 7.72866103081538e-05,
"loss": 5.0484,
"step": 8700
},
{
"epoch": 2.429805615550756,
"grad_norm": 1.3693740367889404,
"learning_rate": 7.646850286337606e-05,
"loss": 5.0288,
"step": 9000
},
{
"epoch": 2.5107991360691146,
"grad_norm": 1.4013055562973022,
"learning_rate": 7.56503954185983e-05,
"loss": 5.0148,
"step": 9300
},
{
"epoch": 2.591792656587473,
"grad_norm": 1.374281406402588,
"learning_rate": 7.483228797382058e-05,
"loss": 4.9978,
"step": 9600
},
{
"epoch": 2.6727861771058317,
"grad_norm": 1.4153590202331543,
"learning_rate": 7.401418052904282e-05,
"loss": 4.9705,
"step": 9900
},
{
"epoch": 2.75377969762419,
"grad_norm": 1.3654042482376099,
"learning_rate": 7.319607308426508e-05,
"loss": 4.9599,
"step": 10200
},
{
"epoch": 2.8347732181425487,
"grad_norm": 1.3114956617355347,
"learning_rate": 7.237796563948732e-05,
"loss": 4.9379,
"step": 10500
},
{
"epoch": 2.915766738660907,
"grad_norm": 1.4419208765029907,
"learning_rate": 7.155985819470958e-05,
"loss": 4.9319,
"step": 10800
},
{
"epoch": 2.9967602591792657,
"grad_norm": 1.3786503076553345,
"learning_rate": 7.074175074993182e-05,
"loss": 4.894,
"step": 11100
},
{
"epoch": 3.077753779697624,
"grad_norm": 1.406146764755249,
"learning_rate": 6.992364330515409e-05,
"loss": 4.731,
"step": 11400
},
{
"epoch": 3.1587473002159827,
"grad_norm": 1.4777101278305054,
"learning_rate": 6.910553586037633e-05,
"loss": 4.723,
"step": 11700
},
{
"epoch": 3.239740820734341,
"grad_norm": 1.5643523931503296,
"learning_rate": 6.828742841559859e-05,
"loss": 4.7243,
"step": 12000
},
{
"epoch": 3.3207343412526997,
"grad_norm": 1.4379490613937378,
"learning_rate": 6.746932097082083e-05,
"loss": 4.7216,
"step": 12300
},
{
"epoch": 3.4017278617710582,
"grad_norm": 1.5200529098510742,
"learning_rate": 6.665121352604309e-05,
"loss": 4.7187,
"step": 12600
},
{
"epoch": 3.4827213822894167,
"grad_norm": 1.573749303817749,
"learning_rate": 6.583310608126535e-05,
"loss": 4.7152,
"step": 12900
},
{
"epoch": 3.5637149028077753,
"grad_norm": 1.555275559425354,
"learning_rate": 6.50149986364876e-05,
"loss": 4.6872,
"step": 13200
},
{
"epoch": 3.6447084233261338,
"grad_norm": 1.5814576148986816,
"learning_rate": 6.419689119170985e-05,
"loss": 4.678,
"step": 13500
},
{
"epoch": 3.7257019438444923,
"grad_norm": 1.4575761556625366,
"learning_rate": 6.33787837469321e-05,
"loss": 4.6898,
"step": 13800
},
{
"epoch": 3.806695464362851,
"grad_norm": 1.4241302013397217,
"learning_rate": 6.256067630215436e-05,
"loss": 4.6746,
"step": 14100
},
{
"epoch": 3.8876889848812093,
"grad_norm": 1.4637110233306885,
"learning_rate": 6.17425688573766e-05,
"loss": 4.6634,
"step": 14400
},
{
"epoch": 3.968682505399568,
"grad_norm": 1.5187498331069946,
"learning_rate": 6.092446141259885e-05,
"loss": 4.6632,
"step": 14700
},
{
"epoch": 4.049676025917926,
"grad_norm": 1.6040258407592773,
"learning_rate": 6.010635396782111e-05,
"loss": 4.557,
"step": 15000
},
{
"epoch": 4.130669546436285,
"grad_norm": 1.6472535133361816,
"learning_rate": 5.9288246523043365e-05,
"loss": 4.4817,
"step": 15300
},
{
"epoch": 4.211663066954643,
"grad_norm": 1.6630454063415527,
"learning_rate": 5.8470139078265615e-05,
"loss": 4.4911,
"step": 15600
},
{
"epoch": 4.292656587473002,
"grad_norm": 1.5368226766586304,
"learning_rate": 5.765203163348787e-05,
"loss": 4.4818,
"step": 15900
},
{
"epoch": 4.37365010799136,
"grad_norm": 1.6154084205627441,
"learning_rate": 5.683392418871012e-05,
"loss": 4.4715,
"step": 16200
},
{
"epoch": 4.454643628509719,
"grad_norm": 1.5402164459228516,
"learning_rate": 5.601581674393237e-05,
"loss": 4.4817,
"step": 16500
},
{
"epoch": 4.535637149028078,
"grad_norm": 1.6153959035873413,
"learning_rate": 5.519770929915462e-05,
"loss": 4.4711,
"step": 16800
},
{
"epoch": 4.616630669546437,
"grad_norm": 1.5631442070007324,
"learning_rate": 5.4379601854376885e-05,
"loss": 4.463,
"step": 17100
},
{
"epoch": 4.697624190064795,
"grad_norm": 1.620991587638855,
"learning_rate": 5.3561494409599135e-05,
"loss": 4.4621,
"step": 17400
},
{
"epoch": 4.778617710583154,
"grad_norm": 1.742760181427002,
"learning_rate": 5.2743386964821385e-05,
"loss": 4.46,
"step": 17700
},
{
"epoch": 4.859611231101512,
"grad_norm": 1.6621677875518799,
"learning_rate": 5.1925279520043635e-05,
"loss": 4.4725,
"step": 18000
},
{
"epoch": 4.940604751619871,
"grad_norm": 1.553416132926941,
"learning_rate": 5.1107172075265885e-05,
"loss": 4.4523,
"step": 18300
},
{
"epoch": 5.021598272138229,
"grad_norm": 1.6929900646209717,
"learning_rate": 5.0289064630488135e-05,
"loss": 4.402,
"step": 18600
},
{
"epoch": 5.102591792656588,
"grad_norm": 1.6716270446777344,
"learning_rate": 4.947095718571039e-05,
"loss": 4.2694,
"step": 18900
},
{
"epoch": 5.183585313174946,
"grad_norm": 1.7076847553253174,
"learning_rate": 4.865284974093264e-05,
"loss": 4.2792,
"step": 19200
},
{
"epoch": 5.264578833693305,
"grad_norm": 1.6706926822662354,
"learning_rate": 4.78347422961549e-05,
"loss": 4.2939,
"step": 19500
},
{
"epoch": 5.345572354211663,
"grad_norm": 1.7526054382324219,
"learning_rate": 4.701663485137715e-05,
"loss": 4.2971,
"step": 19800
},
{
"epoch": 5.426565874730022,
"grad_norm": 1.7769668102264404,
"learning_rate": 4.61985274065994e-05,
"loss": 4.2927,
"step": 20100
},
{
"epoch": 5.50755939524838,
"grad_norm": 1.736707091331482,
"learning_rate": 4.5380419961821655e-05,
"loss": 4.3044,
"step": 20400
},
{
"epoch": 5.588552915766739,
"grad_norm": 1.7048243284225464,
"learning_rate": 4.4562312517043905e-05,
"loss": 4.2971,
"step": 20700
},
{
"epoch": 5.669546436285097,
"grad_norm": 1.7873897552490234,
"learning_rate": 4.374420507226616e-05,
"loss": 4.2918,
"step": 21000
},
{
"epoch": 5.750539956803456,
"grad_norm": 1.6965153217315674,
"learning_rate": 4.292609762748841e-05,
"loss": 4.279,
"step": 21300
},
{
"epoch": 5.831533477321814,
"grad_norm": 1.6777267456054688,
"learning_rate": 4.210799018271067e-05,
"loss": 4.3005,
"step": 21600
},
{
"epoch": 5.912526997840173,
"grad_norm": 1.7366621494293213,
"learning_rate": 4.128988273793292e-05,
"loss": 4.288,
"step": 21900
},
{
"epoch": 5.993520518358531,
"grad_norm": 1.6858952045440674,
"learning_rate": 4.047177529315517e-05,
"loss": 4.3032,
"step": 22200
},
{
"epoch": 6.07451403887689,
"grad_norm": 1.755344033241272,
"learning_rate": 3.9653667848377425e-05,
"loss": 4.1395,
"step": 22500
},
{
"epoch": 6.155507559395248,
"grad_norm": 1.8167041540145874,
"learning_rate": 3.8835560403599675e-05,
"loss": 4.1397,
"step": 22800
},
{
"epoch": 6.236501079913607,
"grad_norm": 1.777757167816162,
"learning_rate": 3.8017452958821925e-05,
"loss": 4.1328,
"step": 23100
},
{
"epoch": 6.317494600431965,
"grad_norm": 1.8104006052017212,
"learning_rate": 3.719934551404418e-05,
"loss": 4.1485,
"step": 23400
},
{
"epoch": 6.398488120950324,
"grad_norm": 2.2477872371673584,
"learning_rate": 3.638123806926643e-05,
"loss": 4.1426,
"step": 23700
},
{
"epoch": 6.479481641468682,
"grad_norm": 1.884135365486145,
"learning_rate": 3.556313062448868e-05,
"loss": 4.1408,
"step": 24000
},
{
"epoch": 6.560475161987041,
"grad_norm": 1.9256831407546997,
"learning_rate": 3.474502317971094e-05,
"loss": 4.1442,
"step": 24300
},
{
"epoch": 6.6414686825053995,
"grad_norm": 1.838258981704712,
"learning_rate": 3.392691573493319e-05,
"loss": 4.146,
"step": 24600
},
{
"epoch": 6.722462203023758,
"grad_norm": 1.8604072332382202,
"learning_rate": 3.310880829015544e-05,
"loss": 4.1371,
"step": 24900
},
{
"epoch": 6.8034557235421165,
"grad_norm": 1.8495209217071533,
"learning_rate": 3.2290700845377695e-05,
"loss": 4.1388,
"step": 25200
},
{
"epoch": 6.884449244060475,
"grad_norm": 1.8702112436294556,
"learning_rate": 3.1472593400599945e-05,
"loss": 4.1355,
"step": 25500
},
{
"epoch": 6.9654427645788335,
"grad_norm": 1.8808040618896484,
"learning_rate": 3.06544859558222e-05,
"loss": 4.1427,
"step": 25800
},
{
"epoch": 7.046436285097192,
"grad_norm": 1.8303903341293335,
"learning_rate": 2.9836378511044448e-05,
"loss": 4.0723,
"step": 26100
},
{
"epoch": 7.1274298056155505,
"grad_norm": 1.9697943925857544,
"learning_rate": 2.9018271066266705e-05,
"loss": 3.9898,
"step": 26400
},
{
"epoch": 7.208423326133909,
"grad_norm": 1.998304843902588,
"learning_rate": 2.8200163621488955e-05,
"loss": 3.997,
"step": 26700
},
{
"epoch": 7.2894168466522675,
"grad_norm": 1.962162971496582,
"learning_rate": 2.7382056176711208e-05,
"loss": 4.009,
"step": 27000
},
{
"epoch": 7.370410367170626,
"grad_norm": 1.8969253301620483,
"learning_rate": 2.6563948731933465e-05,
"loss": 4.0181,
"step": 27300
},
{
"epoch": 7.4514038876889845,
"grad_norm": 1.9282795190811157,
"learning_rate": 2.5745841287155715e-05,
"loss": 4.015,
"step": 27600
},
{
"epoch": 7.532397408207343,
"grad_norm": 1.9588371515274048,
"learning_rate": 2.4927733842377968e-05,
"loss": 4.0216,
"step": 27900
},
{
"epoch": 7.613390928725702,
"grad_norm": 2.0260281562805176,
"learning_rate": 2.4109626397600218e-05,
"loss": 4.0161,
"step": 28200
},
{
"epoch": 7.69438444924406,
"grad_norm": 1.9617438316345215,
"learning_rate": 2.329151895282247e-05,
"loss": 4.0177,
"step": 28500
},
{
"epoch": 7.775377969762419,
"grad_norm": 1.9317694902420044,
"learning_rate": 2.2473411508044725e-05,
"loss": 4.0203,
"step": 28800
},
{
"epoch": 7.856371490280777,
"grad_norm": 2.1097474098205566,
"learning_rate": 2.1655304063266975e-05,
"loss": 4.0226,
"step": 29100
},
{
"epoch": 7.937365010799136,
"grad_norm": 1.9996739625930786,
"learning_rate": 2.083719661848923e-05,
"loss": 4.0139,
"step": 29400
},
{
"epoch": 8.018358531317494,
"grad_norm": 1.9552192687988281,
"learning_rate": 2.001908917371148e-05,
"loss": 3.9961,
"step": 29700
},
{
"epoch": 8.099352051835853,
"grad_norm": 1.9899965524673462,
"learning_rate": 1.9200981728933735e-05,
"loss": 3.8958,
"step": 30000
},
{
"epoch": 8.180345572354211,
"grad_norm": 2.0817723274230957,
"learning_rate": 1.8382874284155988e-05,
"loss": 3.887,
"step": 30300
},
{
"epoch": 8.26133909287257,
"grad_norm": 2.086763858795166,
"learning_rate": 1.7564766839378238e-05,
"loss": 3.9098,
"step": 30600
},
{
"epoch": 8.342332613390928,
"grad_norm": 2.0301589965820312,
"learning_rate": 1.674665939460049e-05,
"loss": 3.8974,
"step": 30900
},
{
"epoch": 8.423326133909287,
"grad_norm": 2.0822806358337402,
"learning_rate": 1.5928551949822745e-05,
"loss": 3.9106,
"step": 31200
},
{
"epoch": 8.504319654427645,
"grad_norm": 2.1793293952941895,
"learning_rate": 1.5110444505044996e-05,
"loss": 3.9102,
"step": 31500
},
{
"epoch": 8.585313174946004,
"grad_norm": 2.0697715282440186,
"learning_rate": 1.429233706026725e-05,
"loss": 3.9044,
"step": 31800
},
{
"epoch": 8.666306695464362,
"grad_norm": 2.0902247428894043,
"learning_rate": 1.34742296154895e-05,
"loss": 3.9191,
"step": 32100
},
{
"epoch": 8.74730021598272,
"grad_norm": 2.062403917312622,
"learning_rate": 1.2656122170711755e-05,
"loss": 3.9175,
"step": 32400
},
{
"epoch": 8.82829373650108,
"grad_norm": 2.048679828643799,
"learning_rate": 1.1838014725934006e-05,
"loss": 3.9124,
"step": 32700
},
{
"epoch": 8.909287257019438,
"grad_norm": 2.103947401046753,
"learning_rate": 1.101990728115626e-05,
"loss": 3.9082,
"step": 33000
},
{
"epoch": 8.990280777537796,
"grad_norm": 2.0932586193084717,
"learning_rate": 1.0201799836378511e-05,
"loss": 3.9139,
"step": 33300
},
{
"epoch": 9.071274298056155,
"grad_norm": 2.065955877304077,
"learning_rate": 9.383692391600765e-06,
"loss": 3.8253,
"step": 33600
},
{
"epoch": 9.152267818574513,
"grad_norm": 2.127322196960449,
"learning_rate": 8.565584946823016e-06,
"loss": 3.8279,
"step": 33900
},
{
"epoch": 9.233261339092872,
"grad_norm": 2.0906572341918945,
"learning_rate": 7.74747750204527e-06,
"loss": 3.826,
"step": 34200
},
{
"epoch": 9.314254859611232,
"grad_norm": 2.142390489578247,
"learning_rate": 6.929370057267521e-06,
"loss": 3.8186,
"step": 34500
},
{
"epoch": 9.39524838012959,
"grad_norm": 2.0886802673339844,
"learning_rate": 6.111262612489774e-06,
"loss": 3.829,
"step": 34800
},
{
"epoch": 9.476241900647949,
"grad_norm": 2.1843161582946777,
"learning_rate": 5.293155167712026e-06,
"loss": 3.8274,
"step": 35100
},
{
"epoch": 9.557235421166308,
"grad_norm": 2.1167829036712646,
"learning_rate": 4.475047722934279e-06,
"loss": 3.8244,
"step": 35400
},
{
"epoch": 9.638228941684666,
"grad_norm": 2.1455206871032715,
"learning_rate": 3.6569402781565316e-06,
"loss": 3.8478,
"step": 35700
},
{
"epoch": 9.719222462203025,
"grad_norm": 2.0749266147613525,
"learning_rate": 2.838832833378784e-06,
"loss": 3.8233,
"step": 36000
},
{
"epoch": 9.800215982721383,
"grad_norm": 2.1683921813964844,
"learning_rate": 2.0207253886010365e-06,
"loss": 3.8196,
"step": 36300
},
{
"epoch": 9.881209503239742,
"grad_norm": 2.2705883979797363,
"learning_rate": 1.2026179438232888e-06,
"loss": 3.8316,
"step": 36600
},
{
"epoch": 9.9622030237581,
"grad_norm": 2.1019952297210693,
"learning_rate": 3.8451049904554137e-07,
"loss": 3.821,
"step": 36900
}
],
"logging_steps": 300,
"max_steps": 37040,
"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": 7.741560324096e+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 sha256:3c470fd27514775f519f81a7ae2ce18f7503172b8506609236b5d633c57ed26d
size 5905

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fb3d3396a132f4a78e350746d4186b1a095eaaea96bbc23a0422e55181b31b1e
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 sha256:3c470fd27514775f519f81a7ae2ce18f7503172b8506609236b5d633c57ed26d
size 5905