anjajar/baby_goldfish_large_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_large_new
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-15 17:54:52 +08:00
commit e1061fd1d5
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: baby_goldfish_large_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_large_new
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:bb714a54e7436386cbe4a6dd08d96875ccf875b3b479c198da494f3d4c279318
size 499098240

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5cbd356aa7c72514b5cd5e47f061b8047d8a4daac4248848a1064c1d17f62ea7
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 sha256:36749db9fd0cc32a73244ea2a1cf9b08a71aa3e0ade1991dd0abd26aeb8596ff
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:becbfb948a617a6400f03ed7d70ce73773a652f3d6de4b768b318aed59db3053
size 1383

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:37882662793e589338bcedd1bf979ae6a790c5499d3ceec610dbfa1b3cbdd0ff
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": 9.970278303161308,
"eval_steps": 500,
"global_step": 36900,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0810591731964334,
"grad_norm": 1.3518340587615967,
"learning_rate": 8.08108108108108e-05,
"loss": 6.5209,
"step": 300
},
{
"epoch": 0.1621183463928668,
"grad_norm": 1.4490776062011719,
"learning_rate": 9.9375e-05,
"loss": 4.8248,
"step": 600
},
{
"epoch": 0.2431775195893002,
"grad_norm": 0.9239162802696228,
"learning_rate": 9.855622270742358e-05,
"loss": 4.6051,
"step": 900
},
{
"epoch": 0.3242366927857336,
"grad_norm": 0.8636089563369751,
"learning_rate": 9.773744541484717e-05,
"loss": 4.5204,
"step": 1200
},
{
"epoch": 0.405295865982167,
"grad_norm": 0.8884899020195007,
"learning_rate": 9.691866812227075e-05,
"loss": 4.4294,
"step": 1500
},
{
"epoch": 0.4863550391786004,
"grad_norm": 0.9425375461578369,
"learning_rate": 9.609989082969433e-05,
"loss": 4.3436,
"step": 1800
},
{
"epoch": 0.5674142123750338,
"grad_norm": 0.9191689491271973,
"learning_rate": 9.528111353711791e-05,
"loss": 4.3269,
"step": 2100
},
{
"epoch": 0.6484733855714672,
"grad_norm": 0.8771488666534424,
"learning_rate": 9.446233624454149e-05,
"loss": 4.2743,
"step": 2400
},
{
"epoch": 0.7295325587679006,
"grad_norm": 0.9781838059425354,
"learning_rate": 9.364355895196507e-05,
"loss": 4.1491,
"step": 2700
},
{
"epoch": 0.810591731964334,
"grad_norm": 1.0138261318206787,
"learning_rate": 9.282478165938865e-05,
"loss": 4.047,
"step": 3000
},
{
"epoch": 0.8916509051607674,
"grad_norm": 1.063523769378662,
"learning_rate": 9.200600436681222e-05,
"loss": 4.0248,
"step": 3300
},
{
"epoch": 0.9727100783572008,
"grad_norm": 0.9346688389778137,
"learning_rate": 9.118722707423582e-05,
"loss": 3.9609,
"step": 3600
},
{
"epoch": 1.053769251553634,
"grad_norm": 0.9149222373962402,
"learning_rate": 9.036844978165939e-05,
"loss": 3.9169,
"step": 3900
},
{
"epoch": 1.1348284247500675,
"grad_norm": 1.1430439949035645,
"learning_rate": 8.954967248908297e-05,
"loss": 3.8597,
"step": 4200
},
{
"epoch": 1.215887597946501,
"grad_norm": 0.9831075072288513,
"learning_rate": 8.873089519650656e-05,
"loss": 3.8311,
"step": 4500
},
{
"epoch": 1.2969467711429343,
"grad_norm": 1.0454624891281128,
"learning_rate": 8.791211790393013e-05,
"loss": 3.7607,
"step": 4800
},
{
"epoch": 1.3780059443393677,
"grad_norm": 0.9663439393043518,
"learning_rate": 8.709334061135371e-05,
"loss": 3.7721,
"step": 5100
},
{
"epoch": 1.4590651175358011,
"grad_norm": 1.133966326713562,
"learning_rate": 8.627456331877731e-05,
"loss": 3.7393,
"step": 5400
},
{
"epoch": 1.5401242907322346,
"grad_norm": 0.9640753865242004,
"learning_rate": 8.545578602620087e-05,
"loss": 3.7126,
"step": 5700
},
{
"epoch": 1.621183463928668,
"grad_norm": 1.0320396423339844,
"learning_rate": 8.463700873362446e-05,
"loss": 3.6677,
"step": 6000
},
{
"epoch": 1.7022426371251014,
"grad_norm": 0.991076648235321,
"learning_rate": 8.381823144104804e-05,
"loss": 3.6452,
"step": 6300
},
{
"epoch": 1.7833018103215346,
"grad_norm": 1.1129027605056763,
"learning_rate": 8.299945414847162e-05,
"loss": 3.6468,
"step": 6600
},
{
"epoch": 1.864360983517968,
"grad_norm": 1.1750997304916382,
"learning_rate": 8.21806768558952e-05,
"loss": 3.6052,
"step": 6900
},
{
"epoch": 1.9454201567144014,
"grad_norm": 1.077567219734192,
"learning_rate": 8.136189956331878e-05,
"loss": 3.5974,
"step": 7200
},
{
"epoch": 2.026479329910835,
"grad_norm": 1.1307553052902222,
"learning_rate": 8.054312227074236e-05,
"loss": 3.5258,
"step": 7500
},
{
"epoch": 2.107538503107268,
"grad_norm": 0.9726724028587341,
"learning_rate": 7.972434497816595e-05,
"loss": 3.473,
"step": 7800
},
{
"epoch": 2.1885976763037016,
"grad_norm": 1.080590844154358,
"learning_rate": 7.890556768558953e-05,
"loss": 3.4878,
"step": 8100
},
{
"epoch": 2.269656849500135,
"grad_norm": 1.0957530736923218,
"learning_rate": 7.808679039301311e-05,
"loss": 3.473,
"step": 8400
},
{
"epoch": 2.3507160226965684,
"grad_norm": 1.1584407091140747,
"learning_rate": 7.726801310043669e-05,
"loss": 3.4178,
"step": 8700
},
{
"epoch": 2.431775195893002,
"grad_norm": 1.1033746004104614,
"learning_rate": 7.644923580786027e-05,
"loss": 3.4216,
"step": 9000
},
{
"epoch": 2.5128343690894352,
"grad_norm": 1.035995364189148,
"learning_rate": 7.563045851528384e-05,
"loss": 3.4284,
"step": 9300
},
{
"epoch": 2.5938935422858687,
"grad_norm": 1.1373919248580933,
"learning_rate": 7.481168122270743e-05,
"loss": 3.419,
"step": 9600
},
{
"epoch": 2.674952715482302,
"grad_norm": 1.0167981386184692,
"learning_rate": 7.3992903930131e-05,
"loss": 3.3995,
"step": 9900
},
{
"epoch": 2.7560118886787355,
"grad_norm": 1.1506949663162231,
"learning_rate": 7.317412663755458e-05,
"loss": 3.4456,
"step": 10200
},
{
"epoch": 2.837071061875169,
"grad_norm": 1.281085729598999,
"learning_rate": 7.235534934497818e-05,
"loss": 3.3682,
"step": 10500
},
{
"epoch": 2.9181302350716023,
"grad_norm": 1.1729835271835327,
"learning_rate": 7.153657205240175e-05,
"loss": 3.3507,
"step": 10800
},
{
"epoch": 2.9991894082680357,
"grad_norm": 1.1416144371032715,
"learning_rate": 7.071779475982533e-05,
"loss": 3.3374,
"step": 11100
},
{
"epoch": 3.080248581464469,
"grad_norm": 1.2445170879364014,
"learning_rate": 6.989901746724891e-05,
"loss": 3.2347,
"step": 11400
},
{
"epoch": 3.1613077546609025,
"grad_norm": 1.1831103563308716,
"learning_rate": 6.908024017467249e-05,
"loss": 3.2341,
"step": 11700
},
{
"epoch": 3.242366927857336,
"grad_norm": 1.1428508758544922,
"learning_rate": 6.826146288209607e-05,
"loss": 3.2382,
"step": 12000
},
{
"epoch": 3.3234261010537693,
"grad_norm": 1.2155035734176636,
"learning_rate": 6.744268558951965e-05,
"loss": 3.2109,
"step": 12300
},
{
"epoch": 3.4044852742502028,
"grad_norm": 1.1355677843093872,
"learning_rate": 6.662390829694324e-05,
"loss": 3.2283,
"step": 12600
},
{
"epoch": 3.485544447446636,
"grad_norm": 1.2202376127243042,
"learning_rate": 6.580513100436682e-05,
"loss": 3.2252,
"step": 12900
},
{
"epoch": 3.5666036206430696,
"grad_norm": 1.2496229410171509,
"learning_rate": 6.49863537117904e-05,
"loss": 3.2408,
"step": 13200
},
{
"epoch": 3.647662793839503,
"grad_norm": 1.1879061460494995,
"learning_rate": 6.416757641921398e-05,
"loss": 3.1999,
"step": 13500
},
{
"epoch": 3.7287219670359364,
"grad_norm": 1.2078286409378052,
"learning_rate": 6.334879912663756e-05,
"loss": 3.184,
"step": 13800
},
{
"epoch": 3.80978114023237,
"grad_norm": 1.157354712486267,
"learning_rate": 6.253002183406114e-05,
"loss": 3.1967,
"step": 14100
},
{
"epoch": 3.8908403134288028,
"grad_norm": 1.0799527168273926,
"learning_rate": 6.171124454148471e-05,
"loss": 3.1845,
"step": 14400
},
{
"epoch": 3.9718994866252366,
"grad_norm": 1.162443995475769,
"learning_rate": 6.0892467248908306e-05,
"loss": 3.1956,
"step": 14700
},
{
"epoch": 4.05295865982167,
"grad_norm": 1.362560749053955,
"learning_rate": 6.007368995633188e-05,
"loss": 3.0933,
"step": 15000
},
{
"epoch": 4.134017833018103,
"grad_norm": 1.3539903163909912,
"learning_rate": 5.9254912663755455e-05,
"loss": 3.0665,
"step": 15300
},
{
"epoch": 4.215077006214536,
"grad_norm": 1.2945058345794678,
"learning_rate": 5.843613537117904e-05,
"loss": 3.0822,
"step": 15600
},
{
"epoch": 4.29613617941097,
"grad_norm": 1.2873772382736206,
"learning_rate": 5.7617358078602625e-05,
"loss": 3.032,
"step": 15900
},
{
"epoch": 4.377195352607403,
"grad_norm": 1.3318586349487305,
"learning_rate": 5.67985807860262e-05,
"loss": 3.0344,
"step": 16200
},
{
"epoch": 4.458254525803837,
"grad_norm": 1.3891690969467163,
"learning_rate": 5.597980349344979e-05,
"loss": 3.0648,
"step": 16500
},
{
"epoch": 4.53931369900027,
"grad_norm": 1.3675804138183594,
"learning_rate": 5.516102620087337e-05,
"loss": 3.0373,
"step": 16800
},
{
"epoch": 4.620372872196704,
"grad_norm": 1.3631969690322876,
"learning_rate": 5.4342248908296944e-05,
"loss": 3.0216,
"step": 17100
},
{
"epoch": 4.701432045393137,
"grad_norm": 1.534043550491333,
"learning_rate": 5.352347161572052e-05,
"loss": 3.068,
"step": 17400
},
{
"epoch": 4.782491218589571,
"grad_norm": 1.3604155778884888,
"learning_rate": 5.2704694323144114e-05,
"loss": 3.04,
"step": 17700
},
{
"epoch": 4.863550391786004,
"grad_norm": 1.4917387962341309,
"learning_rate": 5.188591703056769e-05,
"loss": 3.0478,
"step": 18000
},
{
"epoch": 4.9446095649824375,
"grad_norm": 1.4303983449935913,
"learning_rate": 5.106713973799126e-05,
"loss": 3.012,
"step": 18300
},
{
"epoch": 5.0256687381788705,
"grad_norm": 1.5453460216522217,
"learning_rate": 5.024836244541485e-05,
"loss": 2.9692,
"step": 18600
},
{
"epoch": 5.106727911375304,
"grad_norm": 1.4777169227600098,
"learning_rate": 4.942958515283843e-05,
"loss": 2.9011,
"step": 18900
},
{
"epoch": 5.187787084571737,
"grad_norm": 1.5853521823883057,
"learning_rate": 4.861080786026201e-05,
"loss": 2.9105,
"step": 19200
},
{
"epoch": 5.268846257768171,
"grad_norm": 1.4681776762008667,
"learning_rate": 4.779203056768559e-05,
"loss": 2.8882,
"step": 19500
},
{
"epoch": 5.349905430964604,
"grad_norm": 1.3525965213775635,
"learning_rate": 4.697325327510918e-05,
"loss": 2.9123,
"step": 19800
},
{
"epoch": 5.430964604161037,
"grad_norm": 1.4700337648391724,
"learning_rate": 4.615447598253275e-05,
"loss": 2.8784,
"step": 20100
},
{
"epoch": 5.512023777357471,
"grad_norm": 1.5051637887954712,
"learning_rate": 4.533569868995633e-05,
"loss": 2.9082,
"step": 20400
},
{
"epoch": 5.593082950553905,
"grad_norm": 1.4689549207687378,
"learning_rate": 4.4516921397379915e-05,
"loss": 2.9082,
"step": 20700
},
{
"epoch": 5.674142123750338,
"grad_norm": 1.5370858907699585,
"learning_rate": 4.3698144104803496e-05,
"loss": 2.9034,
"step": 21000
},
{
"epoch": 5.755201296946771,
"grad_norm": 1.5931947231292725,
"learning_rate": 4.287936681222708e-05,
"loss": 2.8862,
"step": 21300
},
{
"epoch": 5.836260470143205,
"grad_norm": 1.4349807500839233,
"learning_rate": 4.206058951965066e-05,
"loss": 2.891,
"step": 21600
},
{
"epoch": 5.917319643339638,
"grad_norm": 1.625874400138855,
"learning_rate": 4.124181222707424e-05,
"loss": 2.87,
"step": 21900
},
{
"epoch": 5.998378816536071,
"grad_norm": 1.4641919136047363,
"learning_rate": 4.0423034934497815e-05,
"loss": 2.8981,
"step": 22200
},
{
"epoch": 6.079437989732504,
"grad_norm": 1.3958481550216675,
"learning_rate": 3.96042576419214e-05,
"loss": 2.7289,
"step": 22500
},
{
"epoch": 6.160497162928938,
"grad_norm": 1.586595058441162,
"learning_rate": 3.8785480349344985e-05,
"loss": 2.7348,
"step": 22800
},
{
"epoch": 6.241556336125371,
"grad_norm": 1.7938852310180664,
"learning_rate": 3.796670305676856e-05,
"loss": 2.7383,
"step": 23100
},
{
"epoch": 6.322615509321805,
"grad_norm": 1.7327919006347656,
"learning_rate": 3.714792576419214e-05,
"loss": 2.7897,
"step": 23400
},
{
"epoch": 6.403674682518238,
"grad_norm": 1.5519119501113892,
"learning_rate": 3.632914847161572e-05,
"loss": 2.7947,
"step": 23700
},
{
"epoch": 6.484733855714672,
"grad_norm": 1.7375255823135376,
"learning_rate": 3.5510371179039304e-05,
"loss": 2.79,
"step": 24000
},
{
"epoch": 6.565793028911105,
"grad_norm": 1.8126753568649292,
"learning_rate": 3.4691593886462886e-05,
"loss": 2.7754,
"step": 24300
},
{
"epoch": 6.646852202107539,
"grad_norm": 1.8342634439468384,
"learning_rate": 3.387281659388647e-05,
"loss": 2.7628,
"step": 24600
},
{
"epoch": 6.727911375303972,
"grad_norm": 1.7573124170303345,
"learning_rate": 3.305403930131005e-05,
"loss": 2.7771,
"step": 24900
},
{
"epoch": 6.8089705485004055,
"grad_norm": 1.7912206649780273,
"learning_rate": 3.2235262008733623e-05,
"loss": 2.7588,
"step": 25200
},
{
"epoch": 6.8900297216968385,
"grad_norm": 1.5853058099746704,
"learning_rate": 3.1416484716157205e-05,
"loss": 2.7534,
"step": 25500
},
{
"epoch": 6.971088894893272,
"grad_norm": 1.6281930208206177,
"learning_rate": 3.0597707423580786e-05,
"loss": 2.7513,
"step": 25800
},
{
"epoch": 7.052148068089705,
"grad_norm": 1.8934043645858765,
"learning_rate": 2.9778930131004368e-05,
"loss": 2.7019,
"step": 26100
},
{
"epoch": 7.133207241286139,
"grad_norm": 1.7691494226455688,
"learning_rate": 2.896015283842795e-05,
"loss": 2.6608,
"step": 26400
},
{
"epoch": 7.214266414482572,
"grad_norm": 1.8065195083618164,
"learning_rate": 2.8141375545851527e-05,
"loss": 2.6537,
"step": 26700
},
{
"epoch": 7.295325587679006,
"grad_norm": 1.902382254600525,
"learning_rate": 2.7322598253275112e-05,
"loss": 2.6414,
"step": 27000
},
{
"epoch": 7.376384760875439,
"grad_norm": 1.7119675874710083,
"learning_rate": 2.6503820960698687e-05,
"loss": 2.6422,
"step": 27300
},
{
"epoch": 7.457443934071873,
"grad_norm": 1.9427614212036133,
"learning_rate": 2.5685043668122272e-05,
"loss": 2.6449,
"step": 27600
},
{
"epoch": 7.538503107268306,
"grad_norm": 1.9298570156097412,
"learning_rate": 2.4866266375545853e-05,
"loss": 2.642,
"step": 27900
},
{
"epoch": 7.61956228046474,
"grad_norm": 1.762351393699646,
"learning_rate": 2.404748908296943e-05,
"loss": 2.6455,
"step": 28200
},
{
"epoch": 7.700621453661173,
"grad_norm": 1.7794419527053833,
"learning_rate": 2.3228711790393016e-05,
"loss": 2.6509,
"step": 28500
},
{
"epoch": 7.781680626857606,
"grad_norm": 1.777873158454895,
"learning_rate": 2.2409934497816594e-05,
"loss": 2.6572,
"step": 28800
},
{
"epoch": 7.862739800054039,
"grad_norm": 1.815291166305542,
"learning_rate": 2.1591157205240176e-05,
"loss": 2.6432,
"step": 29100
},
{
"epoch": 7.943798973250473,
"grad_norm": 1.8740344047546387,
"learning_rate": 2.0772379912663757e-05,
"loss": 2.663,
"step": 29400
},
{
"epoch": 8.024858146446906,
"grad_norm": 1.8893027305603027,
"learning_rate": 1.9953602620087335e-05,
"loss": 2.5881,
"step": 29700
},
{
"epoch": 8.10591731964334,
"grad_norm": 1.9792145490646362,
"learning_rate": 1.913482532751092e-05,
"loss": 2.5475,
"step": 30000
},
{
"epoch": 8.186976492839772,
"grad_norm": 1.8607609272003174,
"learning_rate": 1.83160480349345e-05,
"loss": 2.5636,
"step": 30300
},
{
"epoch": 8.268035666036207,
"grad_norm": 1.8906886577606201,
"learning_rate": 1.749727074235808e-05,
"loss": 2.5569,
"step": 30600
},
{
"epoch": 8.34909483923264,
"grad_norm": 2.0039448738098145,
"learning_rate": 1.667849344978166e-05,
"loss": 2.553,
"step": 30900
},
{
"epoch": 8.430154012429073,
"grad_norm": 1.9279450178146362,
"learning_rate": 1.585971615720524e-05,
"loss": 2.5327,
"step": 31200
},
{
"epoch": 8.511213185625508,
"grad_norm": 2.061372756958008,
"learning_rate": 1.5040938864628823e-05,
"loss": 2.5668,
"step": 31500
},
{
"epoch": 8.59227235882194,
"grad_norm": 2.1464438438415527,
"learning_rate": 1.4222161572052402e-05,
"loss": 2.5658,
"step": 31800
},
{
"epoch": 8.673331532018373,
"grad_norm": 2.0610902309417725,
"learning_rate": 1.3403384279475984e-05,
"loss": 2.5592,
"step": 32100
},
{
"epoch": 8.754390705214806,
"grad_norm": 2.092325448989868,
"learning_rate": 1.2584606986899564e-05,
"loss": 2.543,
"step": 32400
},
{
"epoch": 8.83544987841124,
"grad_norm": 2.0462098121643066,
"learning_rate": 1.1765829694323145e-05,
"loss": 2.5544,
"step": 32700
},
{
"epoch": 8.916509051607674,
"grad_norm": 2.0339772701263428,
"learning_rate": 1.0947052401746725e-05,
"loss": 2.5651,
"step": 33000
},
{
"epoch": 8.997568224804107,
"grad_norm": 2.069972276687622,
"learning_rate": 1.0128275109170306e-05,
"loss": 2.5323,
"step": 33300
},
{
"epoch": 9.07862739800054,
"grad_norm": 2.0698232650756836,
"learning_rate": 9.309497816593888e-06,
"loss": 2.4645,
"step": 33600
},
{
"epoch": 9.159686571196973,
"grad_norm": 2.0408966541290283,
"learning_rate": 8.490720524017468e-06,
"loss": 2.4776,
"step": 33900
},
{
"epoch": 9.240745744393408,
"grad_norm": 2.258899688720703,
"learning_rate": 7.671943231441048e-06,
"loss": 2.5065,
"step": 34200
},
{
"epoch": 9.32180491758984,
"grad_norm": 1.9570540189743042,
"learning_rate": 6.853165938864629e-06,
"loss": 2.4528,
"step": 34500
},
{
"epoch": 9.402864090786274,
"grad_norm": 2.107398509979248,
"learning_rate": 6.03438864628821e-06,
"loss": 2.4907,
"step": 34800
},
{
"epoch": 9.483923263982707,
"grad_norm": 1.9422398805618286,
"learning_rate": 5.21561135371179e-06,
"loss": 2.4871,
"step": 35100
},
{
"epoch": 9.564982437179141,
"grad_norm": 2.015700340270996,
"learning_rate": 4.396834061135372e-06,
"loss": 2.476,
"step": 35400
},
{
"epoch": 9.646041610375574,
"grad_norm": 2.022306203842163,
"learning_rate": 3.5780567685589524e-06,
"loss": 2.4837,
"step": 35700
},
{
"epoch": 9.727100783572007,
"grad_norm": 2.170642375946045,
"learning_rate": 2.759279475982533e-06,
"loss": 2.4854,
"step": 36000
},
{
"epoch": 9.80815995676844,
"grad_norm": 2.0419552326202393,
"learning_rate": 1.9405021834061136e-06,
"loss": 2.4956,
"step": 36300
},
{
"epoch": 9.889219129964875,
"grad_norm": 2.17526912689209,
"learning_rate": 1.1217248908296945e-06,
"loss": 2.5115,
"step": 36600
},
{
"epoch": 9.970278303161308,
"grad_norm": 1.8749662637710571,
"learning_rate": 3.0294759825327515e-07,
"loss": 2.4465,
"step": 36900
}
],
"logging_steps": 300,
"max_steps": 37010,
"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": false
},
"attributes": {}
}
},
"total_flos": 7.7119298076672e+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 sha256:3872bdb655c67bdf5919cf9e0b02424ebb9d7fb07e8fa96ab22b7bdf3fb19645
size 5905

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e80668711160fe88c57b19b95bce171c5525abdaf0bc18b28a1aaec9c8a69340
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 sha256:3872bdb655c67bdf5919cf9e0b02424ebb9d7fb07e8fa96ab22b7bdf3fb19645
size 5905