Commit
·
5c07823
1
Parent(s):
93400b2
Model training update with 5 epochs
Browse files- README.md +2 -2
- checkpoints/checkpoint-10500/trainer_state.json +0 -181
- checkpoints/checkpoint-11000/trainer_state.json +0 -188
- checkpoints/checkpoint-11295/trainer_state.json +0 -188
- checkpoints/{checkpoint-10500 → checkpoint-8500}/config.json +0 -0
- checkpoints/{checkpoint-10500 → checkpoint-8500}/generation_config.json +0 -0
- checkpoints/{checkpoint-10500 → checkpoint-8500}/model.safetensors +1 -1
- checkpoints/{checkpoint-11000 → checkpoint-8500}/optimizer.pt +1 -1
- checkpoints/{checkpoint-11000 → checkpoint-8500}/rng_state.pth +1 -1
- checkpoints/{checkpoint-11295 → checkpoint-8500}/scaler.pt +1 -1
- checkpoints/{checkpoint-10500 → checkpoint-8500}/scheduler.pt +1 -1
- checkpoints/{checkpoint-10500 → checkpoint-8500}/special_tokens_map.json +0 -0
- checkpoints/{checkpoint-10500 → checkpoint-8500}/tokenizer.json +2 -16
- checkpoints/{checkpoint-10500 → checkpoint-8500}/tokenizer_config.json +0 -0
- checkpoints/checkpoint-8500/trainer_state.json +153 -0
- checkpoints/{checkpoint-11000 → checkpoint-8500}/training_args.bin +1 -1
- checkpoints/{checkpoint-11000 → checkpoint-9000}/config.json +0 -0
- checkpoints/{checkpoint-11000 → checkpoint-9000}/generation_config.json +0 -0
- checkpoints/{checkpoint-11000 → checkpoint-9000}/model.safetensors +1 -1
- checkpoints/{checkpoint-10500 → checkpoint-9000}/optimizer.pt +1 -1
- checkpoints/{checkpoint-11295 → checkpoint-9000}/rng_state.pth +1 -1
- checkpoints/{checkpoint-11000 → checkpoint-9000}/scaler.pt +1 -1
- checkpoints/{checkpoint-11000 → checkpoint-9000}/scheduler.pt +1 -1
- checkpoints/{checkpoint-11000 → checkpoint-9000}/special_tokens_map.json +0 -0
- checkpoints/{checkpoint-11000 → checkpoint-9000}/tokenizer.json +2 -16
- checkpoints/{checkpoint-11000 → checkpoint-9000}/tokenizer_config.json +0 -0
- checkpoints/checkpoint-9000/trainer_state.json +160 -0
- checkpoints/{checkpoint-10500 → checkpoint-9000}/training_args.bin +1 -1
- checkpoints/{checkpoint-11295 → checkpoint-9410}/config.json +0 -0
- checkpoints/{checkpoint-11295 → checkpoint-9410}/generation_config.json +0 -0
- checkpoints/{checkpoint-11295 → checkpoint-9410}/model.safetensors +1 -1
- checkpoints/{checkpoint-11295 → checkpoint-9410}/optimizer.pt +1 -1
- checkpoints/{checkpoint-10500 → checkpoint-9410}/rng_state.pth +1 -1
- checkpoints/{checkpoint-10500 → checkpoint-9410}/scaler.pt +1 -1
- checkpoints/{checkpoint-11295 → checkpoint-9410}/scheduler.pt +1 -1
- checkpoints/{checkpoint-11295 → checkpoint-9410}/special_tokens_map.json +0 -0
- checkpoints/{checkpoint-11295 → checkpoint-9410}/tokenizer.json +2 -16
- checkpoints/{checkpoint-11295 → checkpoint-9410}/tokenizer_config.json +0 -0
- checkpoints/checkpoint-9410/trainer_state.json +160 -0
- checkpoints/{checkpoint-11295 → checkpoint-9410}/training_args.bin +1 -1
- checkpoints/config.json +0 -60
- checkpoints/generation_config.json +0 -7
- checkpoints/model.safetensors +0 -3
- checkpoints/special_tokens_map.json +0 -125
- checkpoints/tokenizer.json +0 -0
- checkpoints/tokenizer_config.json +0 -939
- model.safetensors +1 -1
- src/train_t5.py +3 -2
- tokenizer.json +2 -16
README.md
CHANGED
|
@@ -79,11 +79,11 @@ print(output)
|
|
| 79 |
If you use DalaT5 in research of derivative works, feel free to cite:
|
| 80 |
|
| 81 |
```
|
| 82 |
-
@misc{
|
| 83 |
author = {Rodrigo Pereira Cruz},
|
| 84 |
title = {DalaT5: Cyrillic-to-Latin Kazakh transliterator on fine-tuned T5},
|
| 85 |
year = 2025,
|
| 86 |
-
url = {https://huggingface.co/crossroderick/
|
| 87 |
}
|
| 88 |
```
|
| 89 |
|
|
|
|
| 79 |
If you use DalaT5 in research of derivative works, feel free to cite:
|
| 80 |
|
| 81 |
```
|
| 82 |
+
@misc{crossroderick_dalat5_2025,
|
| 83 |
author = {Rodrigo Pereira Cruz},
|
| 84 |
title = {DalaT5: Cyrillic-to-Latin Kazakh transliterator on fine-tuned T5},
|
| 85 |
year = 2025,
|
| 86 |
+
url = {https://huggingface.co/crossroderick/dalat5}
|
| 87 |
}
|
| 88 |
```
|
| 89 |
|
checkpoints/checkpoint-10500/trainer_state.json
DELETED
|
@@ -1,181 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": null,
|
| 3 |
-
"best_metric": null,
|
| 4 |
-
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 2.7887136929460583,
|
| 6 |
-
"eval_steps": 500,
|
| 7 |
-
"global_step": 10500,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 0.13278008298755187,
|
| 14 |
-
"grad_norm": 0.6228527426719666,
|
| 15 |
-
"learning_rate": 4.779991146525011e-05,
|
| 16 |
-
"loss": 2.8908,
|
| 17 |
-
"step": 500
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.26556016597510373,
|
| 21 |
-
"grad_norm": 0.5307347774505615,
|
| 22 |
-
"learning_rate": 4.558654271801682e-05,
|
| 23 |
-
"loss": 1.7206,
|
| 24 |
-
"step": 1000
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 0.3983402489626556,
|
| 28 |
-
"grad_norm": 0.5170541405677795,
|
| 29 |
-
"learning_rate": 4.337317397078354e-05,
|
| 30 |
-
"loss": 1.4092,
|
| 31 |
-
"step": 1500
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 0.5311203319502075,
|
| 35 |
-
"grad_norm": 0.4364624619483948,
|
| 36 |
-
"learning_rate": 4.115980522355025e-05,
|
| 37 |
-
"loss": 1.2569,
|
| 38 |
-
"step": 2000
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.6639004149377593,
|
| 42 |
-
"grad_norm": 0.4466415345668793,
|
| 43 |
-
"learning_rate": 3.894643647631695e-05,
|
| 44 |
-
"loss": 1.1577,
|
| 45 |
-
"step": 2500
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.7966804979253111,
|
| 49 |
-
"grad_norm": 0.45460325479507446,
|
| 50 |
-
"learning_rate": 3.673306772908366e-05,
|
| 51 |
-
"loss": 1.0893,
|
| 52 |
-
"step": 3000
|
| 53 |
-
},
|
| 54 |
-
{
|
| 55 |
-
"epoch": 0.9294605809128631,
|
| 56 |
-
"grad_norm": 0.7568681240081787,
|
| 57 |
-
"learning_rate": 3.451969898185038e-05,
|
| 58 |
-
"loss": 1.0312,
|
| 59 |
-
"step": 3500
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 1.0624066390041493,
|
| 63 |
-
"grad_norm": 0.3818189203739166,
|
| 64 |
-
"learning_rate": 3.230633023461709e-05,
|
| 65 |
-
"loss": 0.9992,
|
| 66 |
-
"step": 4000
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"epoch": 1.1951867219917012,
|
| 70 |
-
"grad_norm": 0.4406893253326416,
|
| 71 |
-
"learning_rate": 3.0092961487383796e-05,
|
| 72 |
-
"loss": 0.9602,
|
| 73 |
-
"step": 4500
|
| 74 |
-
},
|
| 75 |
-
{
|
| 76 |
-
"epoch": 1.327966804979253,
|
| 77 |
-
"grad_norm": 0.36375248432159424,
|
| 78 |
-
"learning_rate": 2.7879592740150513e-05,
|
| 79 |
-
"loss": 0.9394,
|
| 80 |
-
"step": 5000
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 1.4607468879668049,
|
| 84 |
-
"grad_norm": 0.36876386404037476,
|
| 85 |
-
"learning_rate": 2.566622399291722e-05,
|
| 86 |
-
"loss": 0.9134,
|
| 87 |
-
"step": 5500
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 1.5935269709543567,
|
| 91 |
-
"grad_norm": 0.3677332401275635,
|
| 92 |
-
"learning_rate": 2.3452855245683933e-05,
|
| 93 |
-
"loss": 0.8895,
|
| 94 |
-
"step": 6000
|
| 95 |
-
},
|
| 96 |
-
{
|
| 97 |
-
"epoch": 1.7263070539419088,
|
| 98 |
-
"grad_norm": 0.3990885317325592,
|
| 99 |
-
"learning_rate": 2.1239486498450643e-05,
|
| 100 |
-
"loss": 0.8724,
|
| 101 |
-
"step": 6500
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 1.8590871369294606,
|
| 105 |
-
"grad_norm": 0.3901934325695038,
|
| 106 |
-
"learning_rate": 1.9026117751217353e-05,
|
| 107 |
-
"loss": 0.8629,
|
| 108 |
-
"step": 7000
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"epoch": 1.9918672199170124,
|
| 112 |
-
"grad_norm": 0.4042441248893738,
|
| 113 |
-
"learning_rate": 1.6812749003984067e-05,
|
| 114 |
-
"loss": 0.8588,
|
| 115 |
-
"step": 7500
|
| 116 |
-
},
|
| 117 |
-
{
|
| 118 |
-
"epoch": 2.1248132780082987,
|
| 119 |
-
"grad_norm": 0.36618518829345703,
|
| 120 |
-
"learning_rate": 1.4599380256750775e-05,
|
| 121 |
-
"loss": 0.8444,
|
| 122 |
-
"step": 8000
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 2.2575933609958505,
|
| 126 |
-
"grad_norm": 0.37356874346733093,
|
| 127 |
-
"learning_rate": 1.2386011509517487e-05,
|
| 128 |
-
"loss": 0.8317,
|
| 129 |
-
"step": 8500
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 2.3903734439834023,
|
| 133 |
-
"grad_norm": 0.3973379135131836,
|
| 134 |
-
"learning_rate": 1.0172642762284197e-05,
|
| 135 |
-
"loss": 0.8296,
|
| 136 |
-
"step": 9000
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 2.5231535269709546,
|
| 140 |
-
"grad_norm": 0.389436811208725,
|
| 141 |
-
"learning_rate": 7.959274015050907e-06,
|
| 142 |
-
"loss": 0.8228,
|
| 143 |
-
"step": 9500
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 2.655933609958506,
|
| 147 |
-
"grad_norm": NaN,
|
| 148 |
-
"learning_rate": 5.745905267817619e-06,
|
| 149 |
-
"loss": 0.8213,
|
| 150 |
-
"step": 10000
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 2.7887136929460583,
|
| 154 |
-
"grad_norm": 0.453697144985199,
|
| 155 |
-
"learning_rate": 3.5369632580787958e-06,
|
| 156 |
-
"loss": 0.8136,
|
| 157 |
-
"step": 10500
|
| 158 |
-
}
|
| 159 |
-
],
|
| 160 |
-
"logging_steps": 500,
|
| 161 |
-
"max_steps": 11295,
|
| 162 |
-
"num_input_tokens_seen": 0,
|
| 163 |
-
"num_train_epochs": 3,
|
| 164 |
-
"save_steps": 500,
|
| 165 |
-
"stateful_callbacks": {
|
| 166 |
-
"TrainerControl": {
|
| 167 |
-
"args": {
|
| 168 |
-
"should_epoch_stop": false,
|
| 169 |
-
"should_evaluate": false,
|
| 170 |
-
"should_log": false,
|
| 171 |
-
"should_save": true,
|
| 172 |
-
"should_training_stop": false
|
| 173 |
-
},
|
| 174 |
-
"attributes": {}
|
| 175 |
-
}
|
| 176 |
-
},
|
| 177 |
-
"total_flos": 2.2738505381707776e+16,
|
| 178 |
-
"train_batch_size": 8,
|
| 179 |
-
"trial_name": null,
|
| 180 |
-
"trial_params": null
|
| 181 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-11000/trainer_state.json
DELETED
|
@@ -1,188 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": null,
|
| 3 |
-
"best_metric": null,
|
| 4 |
-
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 2.9214937759336097,
|
| 6 |
-
"eval_steps": 500,
|
| 7 |
-
"global_step": 11000,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 0.13278008298755187,
|
| 14 |
-
"grad_norm": 0.6228527426719666,
|
| 15 |
-
"learning_rate": 4.779991146525011e-05,
|
| 16 |
-
"loss": 2.8908,
|
| 17 |
-
"step": 500
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.26556016597510373,
|
| 21 |
-
"grad_norm": 0.5307347774505615,
|
| 22 |
-
"learning_rate": 4.558654271801682e-05,
|
| 23 |
-
"loss": 1.7206,
|
| 24 |
-
"step": 1000
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 0.3983402489626556,
|
| 28 |
-
"grad_norm": 0.5170541405677795,
|
| 29 |
-
"learning_rate": 4.337317397078354e-05,
|
| 30 |
-
"loss": 1.4092,
|
| 31 |
-
"step": 1500
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 0.5311203319502075,
|
| 35 |
-
"grad_norm": 0.4364624619483948,
|
| 36 |
-
"learning_rate": 4.115980522355025e-05,
|
| 37 |
-
"loss": 1.2569,
|
| 38 |
-
"step": 2000
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.6639004149377593,
|
| 42 |
-
"grad_norm": 0.4466415345668793,
|
| 43 |
-
"learning_rate": 3.894643647631695e-05,
|
| 44 |
-
"loss": 1.1577,
|
| 45 |
-
"step": 2500
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.7966804979253111,
|
| 49 |
-
"grad_norm": 0.45460325479507446,
|
| 50 |
-
"learning_rate": 3.673306772908366e-05,
|
| 51 |
-
"loss": 1.0893,
|
| 52 |
-
"step": 3000
|
| 53 |
-
},
|
| 54 |
-
{
|
| 55 |
-
"epoch": 0.9294605809128631,
|
| 56 |
-
"grad_norm": 0.7568681240081787,
|
| 57 |
-
"learning_rate": 3.451969898185038e-05,
|
| 58 |
-
"loss": 1.0312,
|
| 59 |
-
"step": 3500
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 1.0624066390041493,
|
| 63 |
-
"grad_norm": 0.3818189203739166,
|
| 64 |
-
"learning_rate": 3.230633023461709e-05,
|
| 65 |
-
"loss": 0.9992,
|
| 66 |
-
"step": 4000
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"epoch": 1.1951867219917012,
|
| 70 |
-
"grad_norm": 0.4406893253326416,
|
| 71 |
-
"learning_rate": 3.0092961487383796e-05,
|
| 72 |
-
"loss": 0.9602,
|
| 73 |
-
"step": 4500
|
| 74 |
-
},
|
| 75 |
-
{
|
| 76 |
-
"epoch": 1.327966804979253,
|
| 77 |
-
"grad_norm": 0.36375248432159424,
|
| 78 |
-
"learning_rate": 2.7879592740150513e-05,
|
| 79 |
-
"loss": 0.9394,
|
| 80 |
-
"step": 5000
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 1.4607468879668049,
|
| 84 |
-
"grad_norm": 0.36876386404037476,
|
| 85 |
-
"learning_rate": 2.566622399291722e-05,
|
| 86 |
-
"loss": 0.9134,
|
| 87 |
-
"step": 5500
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 1.5935269709543567,
|
| 91 |
-
"grad_norm": 0.3677332401275635,
|
| 92 |
-
"learning_rate": 2.3452855245683933e-05,
|
| 93 |
-
"loss": 0.8895,
|
| 94 |
-
"step": 6000
|
| 95 |
-
},
|
| 96 |
-
{
|
| 97 |
-
"epoch": 1.7263070539419088,
|
| 98 |
-
"grad_norm": 0.3990885317325592,
|
| 99 |
-
"learning_rate": 2.1239486498450643e-05,
|
| 100 |
-
"loss": 0.8724,
|
| 101 |
-
"step": 6500
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 1.8590871369294606,
|
| 105 |
-
"grad_norm": 0.3901934325695038,
|
| 106 |
-
"learning_rate": 1.9026117751217353e-05,
|
| 107 |
-
"loss": 0.8629,
|
| 108 |
-
"step": 7000
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"epoch": 1.9918672199170124,
|
| 112 |
-
"grad_norm": 0.4042441248893738,
|
| 113 |
-
"learning_rate": 1.6812749003984067e-05,
|
| 114 |
-
"loss": 0.8588,
|
| 115 |
-
"step": 7500
|
| 116 |
-
},
|
| 117 |
-
{
|
| 118 |
-
"epoch": 2.1248132780082987,
|
| 119 |
-
"grad_norm": 0.36618518829345703,
|
| 120 |
-
"learning_rate": 1.4599380256750775e-05,
|
| 121 |
-
"loss": 0.8444,
|
| 122 |
-
"step": 8000
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 2.2575933609958505,
|
| 126 |
-
"grad_norm": 0.37356874346733093,
|
| 127 |
-
"learning_rate": 1.2386011509517487e-05,
|
| 128 |
-
"loss": 0.8317,
|
| 129 |
-
"step": 8500
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 2.3903734439834023,
|
| 133 |
-
"grad_norm": 0.3973379135131836,
|
| 134 |
-
"learning_rate": 1.0172642762284197e-05,
|
| 135 |
-
"loss": 0.8296,
|
| 136 |
-
"step": 9000
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 2.5231535269709546,
|
| 140 |
-
"grad_norm": 0.389436811208725,
|
| 141 |
-
"learning_rate": 7.959274015050907e-06,
|
| 142 |
-
"loss": 0.8228,
|
| 143 |
-
"step": 9500
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 2.655933609958506,
|
| 147 |
-
"grad_norm": NaN,
|
| 148 |
-
"learning_rate": 5.745905267817619e-06,
|
| 149 |
-
"loss": 0.8213,
|
| 150 |
-
"step": 10000
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 2.7887136929460583,
|
| 154 |
-
"grad_norm": 0.453697144985199,
|
| 155 |
-
"learning_rate": 3.5369632580787958e-06,
|
| 156 |
-
"loss": 0.8136,
|
| 157 |
-
"step": 10500
|
| 158 |
-
},
|
| 159 |
-
{
|
| 160 |
-
"epoch": 2.9214937759336097,
|
| 161 |
-
"grad_norm": 0.3989506661891937,
|
| 162 |
-
"learning_rate": 1.323594510845507e-06,
|
| 163 |
-
"loss": 0.812,
|
| 164 |
-
"step": 11000
|
| 165 |
-
}
|
| 166 |
-
],
|
| 167 |
-
"logging_steps": 500,
|
| 168 |
-
"max_steps": 11295,
|
| 169 |
-
"num_input_tokens_seen": 0,
|
| 170 |
-
"num_train_epochs": 3,
|
| 171 |
-
"save_steps": 500,
|
| 172 |
-
"stateful_callbacks": {
|
| 173 |
-
"TrainerControl": {
|
| 174 |
-
"args": {
|
| 175 |
-
"should_epoch_stop": false,
|
| 176 |
-
"should_evaluate": false,
|
| 177 |
-
"should_log": false,
|
| 178 |
-
"should_save": true,
|
| 179 |
-
"should_training_stop": false
|
| 180 |
-
},
|
| 181 |
-
"attributes": {}
|
| 182 |
-
}
|
| 183 |
-
},
|
| 184 |
-
"total_flos": 2.3821239793483776e+16,
|
| 185 |
-
"train_batch_size": 8,
|
| 186 |
-
"trial_name": null,
|
| 187 |
-
"trial_params": null
|
| 188 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/checkpoint-11295/trainer_state.json
DELETED
|
@@ -1,188 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_global_step": null,
|
| 3 |
-
"best_metric": null,
|
| 4 |
-
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 2.9998340248962654,
|
| 6 |
-
"eval_steps": 500,
|
| 7 |
-
"global_step": 11295,
|
| 8 |
-
"is_hyper_param_search": false,
|
| 9 |
-
"is_local_process_zero": true,
|
| 10 |
-
"is_world_process_zero": true,
|
| 11 |
-
"log_history": [
|
| 12 |
-
{
|
| 13 |
-
"epoch": 0.13278008298755187,
|
| 14 |
-
"grad_norm": 0.6228527426719666,
|
| 15 |
-
"learning_rate": 4.779991146525011e-05,
|
| 16 |
-
"loss": 2.8908,
|
| 17 |
-
"step": 500
|
| 18 |
-
},
|
| 19 |
-
{
|
| 20 |
-
"epoch": 0.26556016597510373,
|
| 21 |
-
"grad_norm": 0.5307347774505615,
|
| 22 |
-
"learning_rate": 4.558654271801682e-05,
|
| 23 |
-
"loss": 1.7206,
|
| 24 |
-
"step": 1000
|
| 25 |
-
},
|
| 26 |
-
{
|
| 27 |
-
"epoch": 0.3983402489626556,
|
| 28 |
-
"grad_norm": 0.5170541405677795,
|
| 29 |
-
"learning_rate": 4.337317397078354e-05,
|
| 30 |
-
"loss": 1.4092,
|
| 31 |
-
"step": 1500
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"epoch": 0.5311203319502075,
|
| 35 |
-
"grad_norm": 0.4364624619483948,
|
| 36 |
-
"learning_rate": 4.115980522355025e-05,
|
| 37 |
-
"loss": 1.2569,
|
| 38 |
-
"step": 2000
|
| 39 |
-
},
|
| 40 |
-
{
|
| 41 |
-
"epoch": 0.6639004149377593,
|
| 42 |
-
"grad_norm": 0.4466415345668793,
|
| 43 |
-
"learning_rate": 3.894643647631695e-05,
|
| 44 |
-
"loss": 1.1577,
|
| 45 |
-
"step": 2500
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch": 0.7966804979253111,
|
| 49 |
-
"grad_norm": 0.45460325479507446,
|
| 50 |
-
"learning_rate": 3.673306772908366e-05,
|
| 51 |
-
"loss": 1.0893,
|
| 52 |
-
"step": 3000
|
| 53 |
-
},
|
| 54 |
-
{
|
| 55 |
-
"epoch": 0.9294605809128631,
|
| 56 |
-
"grad_norm": 0.7568681240081787,
|
| 57 |
-
"learning_rate": 3.451969898185038e-05,
|
| 58 |
-
"loss": 1.0312,
|
| 59 |
-
"step": 3500
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 1.0624066390041493,
|
| 63 |
-
"grad_norm": 0.3818189203739166,
|
| 64 |
-
"learning_rate": 3.230633023461709e-05,
|
| 65 |
-
"loss": 0.9992,
|
| 66 |
-
"step": 4000
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"epoch": 1.1951867219917012,
|
| 70 |
-
"grad_norm": 0.4406893253326416,
|
| 71 |
-
"learning_rate": 3.0092961487383796e-05,
|
| 72 |
-
"loss": 0.9602,
|
| 73 |
-
"step": 4500
|
| 74 |
-
},
|
| 75 |
-
{
|
| 76 |
-
"epoch": 1.327966804979253,
|
| 77 |
-
"grad_norm": 0.36375248432159424,
|
| 78 |
-
"learning_rate": 2.7879592740150513e-05,
|
| 79 |
-
"loss": 0.9394,
|
| 80 |
-
"step": 5000
|
| 81 |
-
},
|
| 82 |
-
{
|
| 83 |
-
"epoch": 1.4607468879668049,
|
| 84 |
-
"grad_norm": 0.36876386404037476,
|
| 85 |
-
"learning_rate": 2.566622399291722e-05,
|
| 86 |
-
"loss": 0.9134,
|
| 87 |
-
"step": 5500
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 1.5935269709543567,
|
| 91 |
-
"grad_norm": 0.3677332401275635,
|
| 92 |
-
"learning_rate": 2.3452855245683933e-05,
|
| 93 |
-
"loss": 0.8895,
|
| 94 |
-
"step": 6000
|
| 95 |
-
},
|
| 96 |
-
{
|
| 97 |
-
"epoch": 1.7263070539419088,
|
| 98 |
-
"grad_norm": 0.3990885317325592,
|
| 99 |
-
"learning_rate": 2.1239486498450643e-05,
|
| 100 |
-
"loss": 0.8724,
|
| 101 |
-
"step": 6500
|
| 102 |
-
},
|
| 103 |
-
{
|
| 104 |
-
"epoch": 1.8590871369294606,
|
| 105 |
-
"grad_norm": 0.3901934325695038,
|
| 106 |
-
"learning_rate": 1.9026117751217353e-05,
|
| 107 |
-
"loss": 0.8629,
|
| 108 |
-
"step": 7000
|
| 109 |
-
},
|
| 110 |
-
{
|
| 111 |
-
"epoch": 1.9918672199170124,
|
| 112 |
-
"grad_norm": 0.4042441248893738,
|
| 113 |
-
"learning_rate": 1.6812749003984067e-05,
|
| 114 |
-
"loss": 0.8588,
|
| 115 |
-
"step": 7500
|
| 116 |
-
},
|
| 117 |
-
{
|
| 118 |
-
"epoch": 2.1248132780082987,
|
| 119 |
-
"grad_norm": 0.36618518829345703,
|
| 120 |
-
"learning_rate": 1.4599380256750775e-05,
|
| 121 |
-
"loss": 0.8444,
|
| 122 |
-
"step": 8000
|
| 123 |
-
},
|
| 124 |
-
{
|
| 125 |
-
"epoch": 2.2575933609958505,
|
| 126 |
-
"grad_norm": 0.37356874346733093,
|
| 127 |
-
"learning_rate": 1.2386011509517487e-05,
|
| 128 |
-
"loss": 0.8317,
|
| 129 |
-
"step": 8500
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 2.3903734439834023,
|
| 133 |
-
"grad_norm": 0.3973379135131836,
|
| 134 |
-
"learning_rate": 1.0172642762284197e-05,
|
| 135 |
-
"loss": 0.8296,
|
| 136 |
-
"step": 9000
|
| 137 |
-
},
|
| 138 |
-
{
|
| 139 |
-
"epoch": 2.5231535269709546,
|
| 140 |
-
"grad_norm": 0.389436811208725,
|
| 141 |
-
"learning_rate": 7.959274015050907e-06,
|
| 142 |
-
"loss": 0.8228,
|
| 143 |
-
"step": 9500
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 2.655933609958506,
|
| 147 |
-
"grad_norm": NaN,
|
| 148 |
-
"learning_rate": 5.745905267817619e-06,
|
| 149 |
-
"loss": 0.8213,
|
| 150 |
-
"step": 10000
|
| 151 |
-
},
|
| 152 |
-
{
|
| 153 |
-
"epoch": 2.7887136929460583,
|
| 154 |
-
"grad_norm": 0.453697144985199,
|
| 155 |
-
"learning_rate": 3.5369632580787958e-06,
|
| 156 |
-
"loss": 0.8136,
|
| 157 |
-
"step": 10500
|
| 158 |
-
},
|
| 159 |
-
{
|
| 160 |
-
"epoch": 2.9214937759336097,
|
| 161 |
-
"grad_norm": 0.3989506661891937,
|
| 162 |
-
"learning_rate": 1.323594510845507e-06,
|
| 163 |
-
"loss": 0.812,
|
| 164 |
-
"step": 11000
|
| 165 |
-
}
|
| 166 |
-
],
|
| 167 |
-
"logging_steps": 500,
|
| 168 |
-
"max_steps": 11295,
|
| 169 |
-
"num_input_tokens_seen": 0,
|
| 170 |
-
"num_train_epochs": 3,
|
| 171 |
-
"save_steps": 500,
|
| 172 |
-
"stateful_callbacks": {
|
| 173 |
-
"TrainerControl": {
|
| 174 |
-
"args": {
|
| 175 |
-
"should_epoch_stop": false,
|
| 176 |
-
"should_evaluate": false,
|
| 177 |
-
"should_log": false,
|
| 178 |
-
"should_save": true,
|
| 179 |
-
"should_training_stop": true
|
| 180 |
-
},
|
| 181 |
-
"attributes": {}
|
| 182 |
-
}
|
| 183 |
-
},
|
| 184 |
-
"total_flos": 2.4460053096431616e+16,
|
| 185 |
-
"train_batch_size": 8,
|
| 186 |
-
"trial_name": null,
|
| 187 |
-
"trial_params": null
|
| 188 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/{checkpoint-10500 → checkpoint-8500}/config.json
RENAMED
|
File without changes
|
checkpoints/{checkpoint-10500 → checkpoint-8500}/generation_config.json
RENAMED
|
File without changes
|
checkpoints/{checkpoint-10500 → checkpoint-8500}/model.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 242041896
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:099bb1c8c42a74550254fb5fcb14f9da8d95dbe52a4f92a925e7ff4761442f0f
|
| 3 |
size 242041896
|
checkpoints/{checkpoint-11000 → checkpoint-8500}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 484163514
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1cbd3e585a640c2213514e2a2b6b133d128ce865508f3556b4336cfe5260f41
|
| 3 |
size 484163514
|
checkpoints/{checkpoint-11000 → checkpoint-8500}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cff220eace7c69859d8fbd62a4c67d275aeb247933de3ec0ca02703f87351d0
|
| 3 |
size 14244
|
checkpoints/{checkpoint-11295 → checkpoint-8500}/scaler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 988
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7783f9544b279d0ae395116a4ef839913989d191585a47871c5d7d34778c019f
|
| 3 |
size 988
|
checkpoints/{checkpoint-10500 → checkpoint-8500}/scheduler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:559c3b6e85f97a92dd50a2b91366d7f62d18f6b41bfa38aef84b3235b7b2db5e
|
| 3 |
size 1064
|
checkpoints/{checkpoint-10500 → checkpoint-8500}/special_tokens_map.json
RENAMED
|
File without changes
|
checkpoints/{checkpoint-10500 → checkpoint-8500}/tokenizer.json
RENAMED
|
@@ -1,21 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 128,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": {
|
| 11 |
-
"Fixed": 128
|
| 12 |
-
},
|
| 13 |
-
"direction": "Right",
|
| 14 |
-
"pad_to_multiple_of": null,
|
| 15 |
-
"pad_id": 0,
|
| 16 |
-
"pad_type_id": 0,
|
| 17 |
-
"pad_token": "<pad>"
|
| 18 |
-
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
checkpoints/{checkpoint-10500 → checkpoint-8500}/tokenizer_config.json
RENAMED
|
File without changes
|
checkpoints/checkpoint-8500/trainer_state.json
ADDED
|
@@ -0,0 +1,153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.516231826329417,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 8500,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.26555135099249816,
|
| 14 |
+
"grad_norm": 0.47810718417167664,
|
| 15 |
+
"learning_rate": 4.736450584484591e-05,
|
| 16 |
+
"loss": 2.7717,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5311027019849963,
|
| 21 |
+
"grad_norm": 0.413313627243042,
|
| 22 |
+
"learning_rate": 4.470775770456961e-05,
|
| 23 |
+
"loss": 1.591,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7966540529774945,
|
| 28 |
+
"grad_norm": 0.31432437896728516,
|
| 29 |
+
"learning_rate": 4.205100956429331e-05,
|
| 30 |
+
"loss": 1.3043,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0626701188342296,
|
| 35 |
+
"grad_norm": 0.36749106645584106,
|
| 36 |
+
"learning_rate": 3.9394261424017006e-05,
|
| 37 |
+
"loss": 1.1595,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.3282214698267278,
|
| 42 |
+
"grad_norm": 0.29507818818092346,
|
| 43 |
+
"learning_rate": 3.6737513283740703e-05,
|
| 44 |
+
"loss": 1.0709,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.5937728208192259,
|
| 49 |
+
"grad_norm": 0.3084051012992859,
|
| 50 |
+
"learning_rate": 3.40807651434644e-05,
|
| 51 |
+
"loss": 1.005,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.859324171811724,
|
| 56 |
+
"grad_norm": 0.2812994718551636,
|
| 57 |
+
"learning_rate": 3.14240170031881e-05,
|
| 58 |
+
"loss": 0.9559,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.125340237668459,
|
| 63 |
+
"grad_norm": 0.3291400074958801,
|
| 64 |
+
"learning_rate": 2.8767268862911793e-05,
|
| 65 |
+
"loss": 0.9273,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.390891588660957,
|
| 70 |
+
"grad_norm": 0.28141409158706665,
|
| 71 |
+
"learning_rate": 2.6110520722635495e-05,
|
| 72 |
+
"loss": 0.8928,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.6564429396534557,
|
| 77 |
+
"grad_norm": 0.2757486402988434,
|
| 78 |
+
"learning_rate": 2.3453772582359192e-05,
|
| 79 |
+
"loss": 0.8714,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.9219942906459537,
|
| 84 |
+
"grad_norm": 0.2808317542076111,
|
| 85 |
+
"learning_rate": 2.079702444208289e-05,
|
| 86 |
+
"loss": 0.8498,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.188010356502689,
|
| 91 |
+
"grad_norm": 0.25909456610679626,
|
| 92 |
+
"learning_rate": 1.8140276301806588e-05,
|
| 93 |
+
"loss": 0.8322,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 3.453561707495187,
|
| 98 |
+
"grad_norm": 0.2701779901981354,
|
| 99 |
+
"learning_rate": 1.5483528161530286e-05,
|
| 100 |
+
"loss": 0.8248,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 3.719113058487685,
|
| 105 |
+
"grad_norm": 0.2889029085636139,
|
| 106 |
+
"learning_rate": 1.2826780021253987e-05,
|
| 107 |
+
"loss": 0.8087,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.984664409480183,
|
| 112 |
+
"grad_norm": 0.2585383653640747,
|
| 113 |
+
"learning_rate": 1.0170031880977683e-05,
|
| 114 |
+
"loss": 0.8027,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 4.250680475336918,
|
| 119 |
+
"grad_norm": 0.2610950171947479,
|
| 120 |
+
"learning_rate": 7.513283740701383e-06,
|
| 121 |
+
"loss": 0.7994,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 4.516231826329417,
|
| 126 |
+
"grad_norm": 0.27488183975219727,
|
| 127 |
+
"learning_rate": 4.85653560042508e-06,
|
| 128 |
+
"loss": 0.7947,
|
| 129 |
+
"step": 8500
|
| 130 |
+
}
|
| 131 |
+
],
|
| 132 |
+
"logging_steps": 500,
|
| 133 |
+
"max_steps": 9410,
|
| 134 |
+
"num_input_tokens_seen": 0,
|
| 135 |
+
"num_train_epochs": 5,
|
| 136 |
+
"save_steps": 500,
|
| 137 |
+
"stateful_callbacks": {
|
| 138 |
+
"TrainerControl": {
|
| 139 |
+
"args": {
|
| 140 |
+
"should_epoch_stop": false,
|
| 141 |
+
"should_evaluate": false,
|
| 142 |
+
"should_log": false,
|
| 143 |
+
"should_save": true,
|
| 144 |
+
"should_training_stop": false
|
| 145 |
+
},
|
| 146 |
+
"attributes": {}
|
| 147 |
+
}
|
| 148 |
+
},
|
| 149 |
+
"total_flos": 3.68173009380311e+16,
|
| 150 |
+
"train_batch_size": 16,
|
| 151 |
+
"trial_name": null,
|
| 152 |
+
"trial_params": null
|
| 153 |
+
}
|
checkpoints/{checkpoint-11000 → checkpoint-8500}/training_args.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2067c784529f8fe2c2e4f09f57bcd2f668958cc835cfbd5a037d77580dd52cb6
|
| 3 |
size 5240
|
checkpoints/{checkpoint-11000 → checkpoint-9000}/config.json
RENAMED
|
File without changes
|
checkpoints/{checkpoint-11000 → checkpoint-9000}/generation_config.json
RENAMED
|
File without changes
|
checkpoints/{checkpoint-11000 → checkpoint-9000}/model.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 242041896
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bc7a6d65c9b7421a91c72d1dec0d4f9b537f9b8ffde358969cd8173e4dbdc36
|
| 3 |
size 242041896
|
checkpoints/{checkpoint-10500 → checkpoint-9000}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 484163514
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a98e0330442ac50b48e2cbd8da416200695a4ddd237c8f960fda0e58d677f421
|
| 3 |
size 484163514
|
checkpoints/{checkpoint-11295 → checkpoint-9000}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e000f5cd5963eb68569b2bbfb3b5a89c397ee45872387e8a2d164a5b8897bd75
|
| 3 |
size 14244
|
checkpoints/{checkpoint-11000 → checkpoint-9000}/scaler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 988
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d8ca94441765fa0c615f07e68b441bc9c63cda9f9e3ce738ffd6f3deb621cec
|
| 3 |
size 988
|
checkpoints/{checkpoint-11000 → checkpoint-9000}/scheduler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4936b40fea92cafe7e9f57beefc1e6297923a92e80d4ea4d36ae312cc8d0567
|
| 3 |
size 1064
|
checkpoints/{checkpoint-11000 → checkpoint-9000}/special_tokens_map.json
RENAMED
|
File without changes
|
checkpoints/{checkpoint-11000 → checkpoint-9000}/tokenizer.json
RENAMED
|
@@ -1,21 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 128,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": {
|
| 11 |
-
"Fixed": 128
|
| 12 |
-
},
|
| 13 |
-
"direction": "Right",
|
| 14 |
-
"pad_to_multiple_of": null,
|
| 15 |
-
"pad_id": 0,
|
| 16 |
-
"pad_type_id": 0,
|
| 17 |
-
"pad_token": "<pad>"
|
| 18 |
-
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
checkpoints/{checkpoint-11000 → checkpoint-9000}/tokenizer_config.json
RENAMED
|
File without changes
|
checkpoints/checkpoint-9000/trainer_state.json
ADDED
|
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.781783177321914,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 9000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.26555135099249816,
|
| 14 |
+
"grad_norm": 0.47810718417167664,
|
| 15 |
+
"learning_rate": 4.736450584484591e-05,
|
| 16 |
+
"loss": 2.7717,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5311027019849963,
|
| 21 |
+
"grad_norm": 0.413313627243042,
|
| 22 |
+
"learning_rate": 4.470775770456961e-05,
|
| 23 |
+
"loss": 1.591,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7966540529774945,
|
| 28 |
+
"grad_norm": 0.31432437896728516,
|
| 29 |
+
"learning_rate": 4.205100956429331e-05,
|
| 30 |
+
"loss": 1.3043,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0626701188342296,
|
| 35 |
+
"grad_norm": 0.36749106645584106,
|
| 36 |
+
"learning_rate": 3.9394261424017006e-05,
|
| 37 |
+
"loss": 1.1595,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.3282214698267278,
|
| 42 |
+
"grad_norm": 0.29507818818092346,
|
| 43 |
+
"learning_rate": 3.6737513283740703e-05,
|
| 44 |
+
"loss": 1.0709,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.5937728208192259,
|
| 49 |
+
"grad_norm": 0.3084051012992859,
|
| 50 |
+
"learning_rate": 3.40807651434644e-05,
|
| 51 |
+
"loss": 1.005,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.859324171811724,
|
| 56 |
+
"grad_norm": 0.2812994718551636,
|
| 57 |
+
"learning_rate": 3.14240170031881e-05,
|
| 58 |
+
"loss": 0.9559,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.125340237668459,
|
| 63 |
+
"grad_norm": 0.3291400074958801,
|
| 64 |
+
"learning_rate": 2.8767268862911793e-05,
|
| 65 |
+
"loss": 0.9273,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.390891588660957,
|
| 70 |
+
"grad_norm": 0.28141409158706665,
|
| 71 |
+
"learning_rate": 2.6110520722635495e-05,
|
| 72 |
+
"loss": 0.8928,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.6564429396534557,
|
| 77 |
+
"grad_norm": 0.2757486402988434,
|
| 78 |
+
"learning_rate": 2.3453772582359192e-05,
|
| 79 |
+
"loss": 0.8714,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.9219942906459537,
|
| 84 |
+
"grad_norm": 0.2808317542076111,
|
| 85 |
+
"learning_rate": 2.079702444208289e-05,
|
| 86 |
+
"loss": 0.8498,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.188010356502689,
|
| 91 |
+
"grad_norm": 0.25909456610679626,
|
| 92 |
+
"learning_rate": 1.8140276301806588e-05,
|
| 93 |
+
"loss": 0.8322,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 3.453561707495187,
|
| 98 |
+
"grad_norm": 0.2701779901981354,
|
| 99 |
+
"learning_rate": 1.5483528161530286e-05,
|
| 100 |
+
"loss": 0.8248,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 3.719113058487685,
|
| 105 |
+
"grad_norm": 0.2889029085636139,
|
| 106 |
+
"learning_rate": 1.2826780021253987e-05,
|
| 107 |
+
"loss": 0.8087,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.984664409480183,
|
| 112 |
+
"grad_norm": 0.2585383653640747,
|
| 113 |
+
"learning_rate": 1.0170031880977683e-05,
|
| 114 |
+
"loss": 0.8027,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 4.250680475336918,
|
| 119 |
+
"grad_norm": 0.2610950171947479,
|
| 120 |
+
"learning_rate": 7.513283740701383e-06,
|
| 121 |
+
"loss": 0.7994,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 4.516231826329417,
|
| 126 |
+
"grad_norm": 0.27488183975219727,
|
| 127 |
+
"learning_rate": 4.85653560042508e-06,
|
| 128 |
+
"loss": 0.7947,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.781783177321914,
|
| 133 |
+
"grad_norm": 0.22057265043258667,
|
| 134 |
+
"learning_rate": 2.1997874601487783e-06,
|
| 135 |
+
"loss": 0.7842,
|
| 136 |
+
"step": 9000
|
| 137 |
+
}
|
| 138 |
+
],
|
| 139 |
+
"logging_steps": 500,
|
| 140 |
+
"max_steps": 9410,
|
| 141 |
+
"num_input_tokens_seen": 0,
|
| 142 |
+
"num_train_epochs": 5,
|
| 143 |
+
"save_steps": 500,
|
| 144 |
+
"stateful_callbacks": {
|
| 145 |
+
"TrainerControl": {
|
| 146 |
+
"args": {
|
| 147 |
+
"should_epoch_stop": false,
|
| 148 |
+
"should_evaluate": false,
|
| 149 |
+
"should_log": false,
|
| 150 |
+
"should_save": true,
|
| 151 |
+
"should_training_stop": false
|
| 152 |
+
},
|
| 153 |
+
"attributes": {}
|
| 154 |
+
}
|
| 155 |
+
},
|
| 156 |
+
"total_flos": 3.89827697615831e+16,
|
| 157 |
+
"train_batch_size": 16,
|
| 158 |
+
"trial_name": null,
|
| 159 |
+
"trial_params": null
|
| 160 |
+
}
|
checkpoints/{checkpoint-10500 → checkpoint-9000}/training_args.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2067c784529f8fe2c2e4f09f57bcd2f668958cc835cfbd5a037d77580dd52cb6
|
| 3 |
size 5240
|
checkpoints/{checkpoint-11295 → checkpoint-9410}/config.json
RENAMED
|
File without changes
|
checkpoints/{checkpoint-11295 → checkpoint-9410}/generation_config.json
RENAMED
|
File without changes
|
checkpoints/{checkpoint-11295 → checkpoint-9410}/model.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 242041896
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cee34848014a7023f7c44bcd836df67292a4f1655c491368c20d8d7294b9ebb
|
| 3 |
size 242041896
|
checkpoints/{checkpoint-11295 → checkpoint-9410}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 484163514
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:672e63dc4c447d76eec534a78581bf8e4109db5311b1e83a2718dccd669c5aed
|
| 3 |
size 484163514
|
checkpoints/{checkpoint-10500 → checkpoint-9410}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e543512c54779f4d268ad2028f33638bbd516a8989271d848b128b9f441a110
|
| 3 |
size 14244
|
checkpoints/{checkpoint-10500 → checkpoint-9410}/scaler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 988
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cfd9bc312260feb910a4759784b508d71564bb32d50da0e9bf3fbf3f20f8e9b
|
| 3 |
size 988
|
checkpoints/{checkpoint-11295 → checkpoint-9410}/scheduler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec0019f5b0ff4782538d43eaea19125b6d8430858f1e93f4e77e38ca6d897aa9
|
| 3 |
size 1064
|
checkpoints/{checkpoint-11295 → checkpoint-9410}/special_tokens_map.json
RENAMED
|
File without changes
|
checkpoints/{checkpoint-11295 → checkpoint-9410}/tokenizer.json
RENAMED
|
@@ -1,21 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 128,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": {
|
| 11 |
-
"Fixed": 128
|
| 12 |
-
},
|
| 13 |
-
"direction": "Right",
|
| 14 |
-
"pad_to_multiple_of": null,
|
| 15 |
-
"pad_id": 0,
|
| 16 |
-
"pad_type_id": 0,
|
| 17 |
-
"pad_token": "<pad>"
|
| 18 |
-
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
checkpoints/{checkpoint-11295 → checkpoint-9410}/tokenizer_config.json
RENAMED
|
File without changes
|
checkpoints/checkpoint-9410/trainer_state.json
ADDED
|
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.999535285135763,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 9410,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.26555135099249816,
|
| 14 |
+
"grad_norm": 0.47810718417167664,
|
| 15 |
+
"learning_rate": 4.736450584484591e-05,
|
| 16 |
+
"loss": 2.7717,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5311027019849963,
|
| 21 |
+
"grad_norm": 0.413313627243042,
|
| 22 |
+
"learning_rate": 4.470775770456961e-05,
|
| 23 |
+
"loss": 1.591,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7966540529774945,
|
| 28 |
+
"grad_norm": 0.31432437896728516,
|
| 29 |
+
"learning_rate": 4.205100956429331e-05,
|
| 30 |
+
"loss": 1.3043,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0626701188342296,
|
| 35 |
+
"grad_norm": 0.36749106645584106,
|
| 36 |
+
"learning_rate": 3.9394261424017006e-05,
|
| 37 |
+
"loss": 1.1595,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.3282214698267278,
|
| 42 |
+
"grad_norm": 0.29507818818092346,
|
| 43 |
+
"learning_rate": 3.6737513283740703e-05,
|
| 44 |
+
"loss": 1.0709,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.5937728208192259,
|
| 49 |
+
"grad_norm": 0.3084051012992859,
|
| 50 |
+
"learning_rate": 3.40807651434644e-05,
|
| 51 |
+
"loss": 1.005,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.859324171811724,
|
| 56 |
+
"grad_norm": 0.2812994718551636,
|
| 57 |
+
"learning_rate": 3.14240170031881e-05,
|
| 58 |
+
"loss": 0.9559,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.125340237668459,
|
| 63 |
+
"grad_norm": 0.3291400074958801,
|
| 64 |
+
"learning_rate": 2.8767268862911793e-05,
|
| 65 |
+
"loss": 0.9273,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.390891588660957,
|
| 70 |
+
"grad_norm": 0.28141409158706665,
|
| 71 |
+
"learning_rate": 2.6110520722635495e-05,
|
| 72 |
+
"loss": 0.8928,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.6564429396534557,
|
| 77 |
+
"grad_norm": 0.2757486402988434,
|
| 78 |
+
"learning_rate": 2.3453772582359192e-05,
|
| 79 |
+
"loss": 0.8714,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.9219942906459537,
|
| 84 |
+
"grad_norm": 0.2808317542076111,
|
| 85 |
+
"learning_rate": 2.079702444208289e-05,
|
| 86 |
+
"loss": 0.8498,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.188010356502689,
|
| 91 |
+
"grad_norm": 0.25909456610679626,
|
| 92 |
+
"learning_rate": 1.8140276301806588e-05,
|
| 93 |
+
"loss": 0.8322,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 3.453561707495187,
|
| 98 |
+
"grad_norm": 0.2701779901981354,
|
| 99 |
+
"learning_rate": 1.5483528161530286e-05,
|
| 100 |
+
"loss": 0.8248,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 3.719113058487685,
|
| 105 |
+
"grad_norm": 0.2889029085636139,
|
| 106 |
+
"learning_rate": 1.2826780021253987e-05,
|
| 107 |
+
"loss": 0.8087,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 3.984664409480183,
|
| 112 |
+
"grad_norm": 0.2585383653640747,
|
| 113 |
+
"learning_rate": 1.0170031880977683e-05,
|
| 114 |
+
"loss": 0.8027,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 4.250680475336918,
|
| 119 |
+
"grad_norm": 0.2610950171947479,
|
| 120 |
+
"learning_rate": 7.513283740701383e-06,
|
| 121 |
+
"loss": 0.7994,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 4.516231826329417,
|
| 126 |
+
"grad_norm": 0.27488183975219727,
|
| 127 |
+
"learning_rate": 4.85653560042508e-06,
|
| 128 |
+
"loss": 0.7947,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.781783177321914,
|
| 133 |
+
"grad_norm": 0.22057265043258667,
|
| 134 |
+
"learning_rate": 2.1997874601487783e-06,
|
| 135 |
+
"loss": 0.7842,
|
| 136 |
+
"step": 9000
|
| 137 |
+
}
|
| 138 |
+
],
|
| 139 |
+
"logging_steps": 500,
|
| 140 |
+
"max_steps": 9410,
|
| 141 |
+
"num_input_tokens_seen": 0,
|
| 142 |
+
"num_train_epochs": 5,
|
| 143 |
+
"save_steps": 500,
|
| 144 |
+
"stateful_callbacks": {
|
| 145 |
+
"TrainerControl": {
|
| 146 |
+
"args": {
|
| 147 |
+
"should_epoch_stop": false,
|
| 148 |
+
"should_evaluate": false,
|
| 149 |
+
"should_log": false,
|
| 150 |
+
"should_save": true,
|
| 151 |
+
"should_training_stop": true
|
| 152 |
+
},
|
| 153 |
+
"attributes": {}
|
| 154 |
+
}
|
| 155 |
+
},
|
| 156 |
+
"total_flos": 4.075845419689574e+16,
|
| 157 |
+
"train_batch_size": 16,
|
| 158 |
+
"trial_name": null,
|
| 159 |
+
"trial_params": null
|
| 160 |
+
}
|
checkpoints/{checkpoint-11295 → checkpoint-9410}/training_args.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2067c784529f8fe2c2e4f09f57bcd2f668958cc835cfbd5a037d77580dd52cb6
|
| 3 |
size 5240
|
checkpoints/config.json
DELETED
|
@@ -1,60 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"T5ForConditionalGeneration"
|
| 4 |
-
],
|
| 5 |
-
"classifier_dropout": 0.0,
|
| 6 |
-
"d_ff": 2048,
|
| 7 |
-
"d_kv": 64,
|
| 8 |
-
"d_model": 512,
|
| 9 |
-
"decoder_start_token_id": 0,
|
| 10 |
-
"dense_act_fn": "relu",
|
| 11 |
-
"dropout_rate": 0.1,
|
| 12 |
-
"eos_token_id": 1,
|
| 13 |
-
"feed_forward_proj": "relu",
|
| 14 |
-
"initializer_factor": 1.0,
|
| 15 |
-
"is_encoder_decoder": true,
|
| 16 |
-
"is_gated_act": false,
|
| 17 |
-
"layer_norm_epsilon": 1e-06,
|
| 18 |
-
"model_type": "t5",
|
| 19 |
-
"n_positions": 512,
|
| 20 |
-
"num_decoder_layers": 6,
|
| 21 |
-
"num_heads": 8,
|
| 22 |
-
"num_layers": 6,
|
| 23 |
-
"output_past": true,
|
| 24 |
-
"pad_token_id": 0,
|
| 25 |
-
"relative_attention_max_distance": 128,
|
| 26 |
-
"relative_attention_num_buckets": 32,
|
| 27 |
-
"task_specific_params": {
|
| 28 |
-
"summarization": {
|
| 29 |
-
"early_stopping": true,
|
| 30 |
-
"length_penalty": 2.0,
|
| 31 |
-
"max_length": 200,
|
| 32 |
-
"min_length": 30,
|
| 33 |
-
"no_repeat_ngram_size": 3,
|
| 34 |
-
"num_beams": 4,
|
| 35 |
-
"prefix": "summarize: "
|
| 36 |
-
},
|
| 37 |
-
"translation_en_to_de": {
|
| 38 |
-
"early_stopping": true,
|
| 39 |
-
"max_length": 300,
|
| 40 |
-
"num_beams": 4,
|
| 41 |
-
"prefix": "translate English to German: "
|
| 42 |
-
},
|
| 43 |
-
"translation_en_to_fr": {
|
| 44 |
-
"early_stopping": true,
|
| 45 |
-
"max_length": 300,
|
| 46 |
-
"num_beams": 4,
|
| 47 |
-
"prefix": "translate English to French: "
|
| 48 |
-
},
|
| 49 |
-
"translation_en_to_ro": {
|
| 50 |
-
"early_stopping": true,
|
| 51 |
-
"max_length": 300,
|
| 52 |
-
"num_beams": 4,
|
| 53 |
-
"prefix": "translate English to Romanian: "
|
| 54 |
-
}
|
| 55 |
-
},
|
| 56 |
-
"torch_dtype": "float32",
|
| 57 |
-
"transformers_version": "4.51.2",
|
| 58 |
-
"use_cache": true,
|
| 59 |
-
"vocab_size": 32128
|
| 60 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/generation_config.json
DELETED
|
@@ -1,7 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"decoder_start_token_id": 0,
|
| 4 |
-
"eos_token_id": 1,
|
| 5 |
-
"pad_token_id": 0,
|
| 6 |
-
"transformers_version": "4.51.2"
|
| 7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:80481dfb73aba8fc1ae3e878935241e0bf8bc4be3d69d2f59b714bd66c0c2e40
|
| 3 |
-
size 242041896
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/special_tokens_map.json
DELETED
|
@@ -1,125 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<extra_id_0>",
|
| 4 |
-
"<extra_id_1>",
|
| 5 |
-
"<extra_id_2>",
|
| 6 |
-
"<extra_id_3>",
|
| 7 |
-
"<extra_id_4>",
|
| 8 |
-
"<extra_id_5>",
|
| 9 |
-
"<extra_id_6>",
|
| 10 |
-
"<extra_id_7>",
|
| 11 |
-
"<extra_id_8>",
|
| 12 |
-
"<extra_id_9>",
|
| 13 |
-
"<extra_id_10>",
|
| 14 |
-
"<extra_id_11>",
|
| 15 |
-
"<extra_id_12>",
|
| 16 |
-
"<extra_id_13>",
|
| 17 |
-
"<extra_id_14>",
|
| 18 |
-
"<extra_id_15>",
|
| 19 |
-
"<extra_id_16>",
|
| 20 |
-
"<extra_id_17>",
|
| 21 |
-
"<extra_id_18>",
|
| 22 |
-
"<extra_id_19>",
|
| 23 |
-
"<extra_id_20>",
|
| 24 |
-
"<extra_id_21>",
|
| 25 |
-
"<extra_id_22>",
|
| 26 |
-
"<extra_id_23>",
|
| 27 |
-
"<extra_id_24>",
|
| 28 |
-
"<extra_id_25>",
|
| 29 |
-
"<extra_id_26>",
|
| 30 |
-
"<extra_id_27>",
|
| 31 |
-
"<extra_id_28>",
|
| 32 |
-
"<extra_id_29>",
|
| 33 |
-
"<extra_id_30>",
|
| 34 |
-
"<extra_id_31>",
|
| 35 |
-
"<extra_id_32>",
|
| 36 |
-
"<extra_id_33>",
|
| 37 |
-
"<extra_id_34>",
|
| 38 |
-
"<extra_id_35>",
|
| 39 |
-
"<extra_id_36>",
|
| 40 |
-
"<extra_id_37>",
|
| 41 |
-
"<extra_id_38>",
|
| 42 |
-
"<extra_id_39>",
|
| 43 |
-
"<extra_id_40>",
|
| 44 |
-
"<extra_id_41>",
|
| 45 |
-
"<extra_id_42>",
|
| 46 |
-
"<extra_id_43>",
|
| 47 |
-
"<extra_id_44>",
|
| 48 |
-
"<extra_id_45>",
|
| 49 |
-
"<extra_id_46>",
|
| 50 |
-
"<extra_id_47>",
|
| 51 |
-
"<extra_id_48>",
|
| 52 |
-
"<extra_id_49>",
|
| 53 |
-
"<extra_id_50>",
|
| 54 |
-
"<extra_id_51>",
|
| 55 |
-
"<extra_id_52>",
|
| 56 |
-
"<extra_id_53>",
|
| 57 |
-
"<extra_id_54>",
|
| 58 |
-
"<extra_id_55>",
|
| 59 |
-
"<extra_id_56>",
|
| 60 |
-
"<extra_id_57>",
|
| 61 |
-
"<extra_id_58>",
|
| 62 |
-
"<extra_id_59>",
|
| 63 |
-
"<extra_id_60>",
|
| 64 |
-
"<extra_id_61>",
|
| 65 |
-
"<extra_id_62>",
|
| 66 |
-
"<extra_id_63>",
|
| 67 |
-
"<extra_id_64>",
|
| 68 |
-
"<extra_id_65>",
|
| 69 |
-
"<extra_id_66>",
|
| 70 |
-
"<extra_id_67>",
|
| 71 |
-
"<extra_id_68>",
|
| 72 |
-
"<extra_id_69>",
|
| 73 |
-
"<extra_id_70>",
|
| 74 |
-
"<extra_id_71>",
|
| 75 |
-
"<extra_id_72>",
|
| 76 |
-
"<extra_id_73>",
|
| 77 |
-
"<extra_id_74>",
|
| 78 |
-
"<extra_id_75>",
|
| 79 |
-
"<extra_id_76>",
|
| 80 |
-
"<extra_id_77>",
|
| 81 |
-
"<extra_id_78>",
|
| 82 |
-
"<extra_id_79>",
|
| 83 |
-
"<extra_id_80>",
|
| 84 |
-
"<extra_id_81>",
|
| 85 |
-
"<extra_id_82>",
|
| 86 |
-
"<extra_id_83>",
|
| 87 |
-
"<extra_id_84>",
|
| 88 |
-
"<extra_id_85>",
|
| 89 |
-
"<extra_id_86>",
|
| 90 |
-
"<extra_id_87>",
|
| 91 |
-
"<extra_id_88>",
|
| 92 |
-
"<extra_id_89>",
|
| 93 |
-
"<extra_id_90>",
|
| 94 |
-
"<extra_id_91>",
|
| 95 |
-
"<extra_id_92>",
|
| 96 |
-
"<extra_id_93>",
|
| 97 |
-
"<extra_id_94>",
|
| 98 |
-
"<extra_id_95>",
|
| 99 |
-
"<extra_id_96>",
|
| 100 |
-
"<extra_id_97>",
|
| 101 |
-
"<extra_id_98>",
|
| 102 |
-
"<extra_id_99>"
|
| 103 |
-
],
|
| 104 |
-
"eos_token": {
|
| 105 |
-
"content": "</s>",
|
| 106 |
-
"lstrip": false,
|
| 107 |
-
"normalized": false,
|
| 108 |
-
"rstrip": false,
|
| 109 |
-
"single_word": false
|
| 110 |
-
},
|
| 111 |
-
"pad_token": {
|
| 112 |
-
"content": "<pad>",
|
| 113 |
-
"lstrip": false,
|
| 114 |
-
"normalized": false,
|
| 115 |
-
"rstrip": false,
|
| 116 |
-
"single_word": false
|
| 117 |
-
},
|
| 118 |
-
"unk_token": {
|
| 119 |
-
"content": "<unk>",
|
| 120 |
-
"lstrip": false,
|
| 121 |
-
"normalized": false,
|
| 122 |
-
"rstrip": false,
|
| 123 |
-
"single_word": false
|
| 124 |
-
}
|
| 125 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/tokenizer_config.json
DELETED
|
@@ -1,939 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": null,
|
| 3 |
-
"added_tokens_decoder": {
|
| 4 |
-
"0": {
|
| 5 |
-
"content": "<pad>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": false,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"1": {
|
| 13 |
-
"content": "</s>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
},
|
| 20 |
-
"2": {
|
| 21 |
-
"content": "<unk>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": false,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false,
|
| 26 |
-
"special": true
|
| 27 |
-
},
|
| 28 |
-
"32000": {
|
| 29 |
-
"content": "<extra_id_99>",
|
| 30 |
-
"lstrip": false,
|
| 31 |
-
"normalized": false,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": true
|
| 35 |
-
},
|
| 36 |
-
"32001": {
|
| 37 |
-
"content": "<extra_id_98>",
|
| 38 |
-
"lstrip": false,
|
| 39 |
-
"normalized": false,
|
| 40 |
-
"rstrip": false,
|
| 41 |
-
"single_word": false,
|
| 42 |
-
"special": true
|
| 43 |
-
},
|
| 44 |
-
"32002": {
|
| 45 |
-
"content": "<extra_id_97>",
|
| 46 |
-
"lstrip": false,
|
| 47 |
-
"normalized": false,
|
| 48 |
-
"rstrip": false,
|
| 49 |
-
"single_word": false,
|
| 50 |
-
"special": true
|
| 51 |
-
},
|
| 52 |
-
"32003": {
|
| 53 |
-
"content": "<extra_id_96>",
|
| 54 |
-
"lstrip": false,
|
| 55 |
-
"normalized": false,
|
| 56 |
-
"rstrip": false,
|
| 57 |
-
"single_word": false,
|
| 58 |
-
"special": true
|
| 59 |
-
},
|
| 60 |
-
"32004": {
|
| 61 |
-
"content": "<extra_id_95>",
|
| 62 |
-
"lstrip": false,
|
| 63 |
-
"normalized": false,
|
| 64 |
-
"rstrip": false,
|
| 65 |
-
"single_word": false,
|
| 66 |
-
"special": true
|
| 67 |
-
},
|
| 68 |
-
"32005": {
|
| 69 |
-
"content": "<extra_id_94>",
|
| 70 |
-
"lstrip": false,
|
| 71 |
-
"normalized": false,
|
| 72 |
-
"rstrip": false,
|
| 73 |
-
"single_word": false,
|
| 74 |
-
"special": true
|
| 75 |
-
},
|
| 76 |
-
"32006": {
|
| 77 |
-
"content": "<extra_id_93>",
|
| 78 |
-
"lstrip": false,
|
| 79 |
-
"normalized": false,
|
| 80 |
-
"rstrip": false,
|
| 81 |
-
"single_word": false,
|
| 82 |
-
"special": true
|
| 83 |
-
},
|
| 84 |
-
"32007": {
|
| 85 |
-
"content": "<extra_id_92>",
|
| 86 |
-
"lstrip": false,
|
| 87 |
-
"normalized": false,
|
| 88 |
-
"rstrip": false,
|
| 89 |
-
"single_word": false,
|
| 90 |
-
"special": true
|
| 91 |
-
},
|
| 92 |
-
"32008": {
|
| 93 |
-
"content": "<extra_id_91>",
|
| 94 |
-
"lstrip": false,
|
| 95 |
-
"normalized": false,
|
| 96 |
-
"rstrip": false,
|
| 97 |
-
"single_word": false,
|
| 98 |
-
"special": true
|
| 99 |
-
},
|
| 100 |
-
"32009": {
|
| 101 |
-
"content": "<extra_id_90>",
|
| 102 |
-
"lstrip": false,
|
| 103 |
-
"normalized": false,
|
| 104 |
-
"rstrip": false,
|
| 105 |
-
"single_word": false,
|
| 106 |
-
"special": true
|
| 107 |
-
},
|
| 108 |
-
"32010": {
|
| 109 |
-
"content": "<extra_id_89>",
|
| 110 |
-
"lstrip": false,
|
| 111 |
-
"normalized": false,
|
| 112 |
-
"rstrip": false,
|
| 113 |
-
"single_word": false,
|
| 114 |
-
"special": true
|
| 115 |
-
},
|
| 116 |
-
"32011": {
|
| 117 |
-
"content": "<extra_id_88>",
|
| 118 |
-
"lstrip": false,
|
| 119 |
-
"normalized": false,
|
| 120 |
-
"rstrip": false,
|
| 121 |
-
"single_word": false,
|
| 122 |
-
"special": true
|
| 123 |
-
},
|
| 124 |
-
"32012": {
|
| 125 |
-
"content": "<extra_id_87>",
|
| 126 |
-
"lstrip": false,
|
| 127 |
-
"normalized": false,
|
| 128 |
-
"rstrip": false,
|
| 129 |
-
"single_word": false,
|
| 130 |
-
"special": true
|
| 131 |
-
},
|
| 132 |
-
"32013": {
|
| 133 |
-
"content": "<extra_id_86>",
|
| 134 |
-
"lstrip": false,
|
| 135 |
-
"normalized": false,
|
| 136 |
-
"rstrip": false,
|
| 137 |
-
"single_word": false,
|
| 138 |
-
"special": true
|
| 139 |
-
},
|
| 140 |
-
"32014": {
|
| 141 |
-
"content": "<extra_id_85>",
|
| 142 |
-
"lstrip": false,
|
| 143 |
-
"normalized": false,
|
| 144 |
-
"rstrip": false,
|
| 145 |
-
"single_word": false,
|
| 146 |
-
"special": true
|
| 147 |
-
},
|
| 148 |
-
"32015": {
|
| 149 |
-
"content": "<extra_id_84>",
|
| 150 |
-
"lstrip": false,
|
| 151 |
-
"normalized": false,
|
| 152 |
-
"rstrip": false,
|
| 153 |
-
"single_word": false,
|
| 154 |
-
"special": true
|
| 155 |
-
},
|
| 156 |
-
"32016": {
|
| 157 |
-
"content": "<extra_id_83>",
|
| 158 |
-
"lstrip": false,
|
| 159 |
-
"normalized": false,
|
| 160 |
-
"rstrip": false,
|
| 161 |
-
"single_word": false,
|
| 162 |
-
"special": true
|
| 163 |
-
},
|
| 164 |
-
"32017": {
|
| 165 |
-
"content": "<extra_id_82>",
|
| 166 |
-
"lstrip": false,
|
| 167 |
-
"normalized": false,
|
| 168 |
-
"rstrip": false,
|
| 169 |
-
"single_word": false,
|
| 170 |
-
"special": true
|
| 171 |
-
},
|
| 172 |
-
"32018": {
|
| 173 |
-
"content": "<extra_id_81>",
|
| 174 |
-
"lstrip": false,
|
| 175 |
-
"normalized": false,
|
| 176 |
-
"rstrip": false,
|
| 177 |
-
"single_word": false,
|
| 178 |
-
"special": true
|
| 179 |
-
},
|
| 180 |
-
"32019": {
|
| 181 |
-
"content": "<extra_id_80>",
|
| 182 |
-
"lstrip": false,
|
| 183 |
-
"normalized": false,
|
| 184 |
-
"rstrip": false,
|
| 185 |
-
"single_word": false,
|
| 186 |
-
"special": true
|
| 187 |
-
},
|
| 188 |
-
"32020": {
|
| 189 |
-
"content": "<extra_id_79>",
|
| 190 |
-
"lstrip": false,
|
| 191 |
-
"normalized": false,
|
| 192 |
-
"rstrip": false,
|
| 193 |
-
"single_word": false,
|
| 194 |
-
"special": true
|
| 195 |
-
},
|
| 196 |
-
"32021": {
|
| 197 |
-
"content": "<extra_id_78>",
|
| 198 |
-
"lstrip": false,
|
| 199 |
-
"normalized": false,
|
| 200 |
-
"rstrip": false,
|
| 201 |
-
"single_word": false,
|
| 202 |
-
"special": true
|
| 203 |
-
},
|
| 204 |
-
"32022": {
|
| 205 |
-
"content": "<extra_id_77>",
|
| 206 |
-
"lstrip": false,
|
| 207 |
-
"normalized": false,
|
| 208 |
-
"rstrip": false,
|
| 209 |
-
"single_word": false,
|
| 210 |
-
"special": true
|
| 211 |
-
},
|
| 212 |
-
"32023": {
|
| 213 |
-
"content": "<extra_id_76>",
|
| 214 |
-
"lstrip": false,
|
| 215 |
-
"normalized": false,
|
| 216 |
-
"rstrip": false,
|
| 217 |
-
"single_word": false,
|
| 218 |
-
"special": true
|
| 219 |
-
},
|
| 220 |
-
"32024": {
|
| 221 |
-
"content": "<extra_id_75>",
|
| 222 |
-
"lstrip": false,
|
| 223 |
-
"normalized": false,
|
| 224 |
-
"rstrip": false,
|
| 225 |
-
"single_word": false,
|
| 226 |
-
"special": true
|
| 227 |
-
},
|
| 228 |
-
"32025": {
|
| 229 |
-
"content": "<extra_id_74>",
|
| 230 |
-
"lstrip": false,
|
| 231 |
-
"normalized": false,
|
| 232 |
-
"rstrip": false,
|
| 233 |
-
"single_word": false,
|
| 234 |
-
"special": true
|
| 235 |
-
},
|
| 236 |
-
"32026": {
|
| 237 |
-
"content": "<extra_id_73>",
|
| 238 |
-
"lstrip": false,
|
| 239 |
-
"normalized": false,
|
| 240 |
-
"rstrip": false,
|
| 241 |
-
"single_word": false,
|
| 242 |
-
"special": true
|
| 243 |
-
},
|
| 244 |
-
"32027": {
|
| 245 |
-
"content": "<extra_id_72>",
|
| 246 |
-
"lstrip": false,
|
| 247 |
-
"normalized": false,
|
| 248 |
-
"rstrip": false,
|
| 249 |
-
"single_word": false,
|
| 250 |
-
"special": true
|
| 251 |
-
},
|
| 252 |
-
"32028": {
|
| 253 |
-
"content": "<extra_id_71>",
|
| 254 |
-
"lstrip": false,
|
| 255 |
-
"normalized": false,
|
| 256 |
-
"rstrip": false,
|
| 257 |
-
"single_word": false,
|
| 258 |
-
"special": true
|
| 259 |
-
},
|
| 260 |
-
"32029": {
|
| 261 |
-
"content": "<extra_id_70>",
|
| 262 |
-
"lstrip": false,
|
| 263 |
-
"normalized": false,
|
| 264 |
-
"rstrip": false,
|
| 265 |
-
"single_word": false,
|
| 266 |
-
"special": true
|
| 267 |
-
},
|
| 268 |
-
"32030": {
|
| 269 |
-
"content": "<extra_id_69>",
|
| 270 |
-
"lstrip": false,
|
| 271 |
-
"normalized": false,
|
| 272 |
-
"rstrip": false,
|
| 273 |
-
"single_word": false,
|
| 274 |
-
"special": true
|
| 275 |
-
},
|
| 276 |
-
"32031": {
|
| 277 |
-
"content": "<extra_id_68>",
|
| 278 |
-
"lstrip": false,
|
| 279 |
-
"normalized": false,
|
| 280 |
-
"rstrip": false,
|
| 281 |
-
"single_word": false,
|
| 282 |
-
"special": true
|
| 283 |
-
},
|
| 284 |
-
"32032": {
|
| 285 |
-
"content": "<extra_id_67>",
|
| 286 |
-
"lstrip": false,
|
| 287 |
-
"normalized": false,
|
| 288 |
-
"rstrip": false,
|
| 289 |
-
"single_word": false,
|
| 290 |
-
"special": true
|
| 291 |
-
},
|
| 292 |
-
"32033": {
|
| 293 |
-
"content": "<extra_id_66>",
|
| 294 |
-
"lstrip": false,
|
| 295 |
-
"normalized": false,
|
| 296 |
-
"rstrip": false,
|
| 297 |
-
"single_word": false,
|
| 298 |
-
"special": true
|
| 299 |
-
},
|
| 300 |
-
"32034": {
|
| 301 |
-
"content": "<extra_id_65>",
|
| 302 |
-
"lstrip": false,
|
| 303 |
-
"normalized": false,
|
| 304 |
-
"rstrip": false,
|
| 305 |
-
"single_word": false,
|
| 306 |
-
"special": true
|
| 307 |
-
},
|
| 308 |
-
"32035": {
|
| 309 |
-
"content": "<extra_id_64>",
|
| 310 |
-
"lstrip": false,
|
| 311 |
-
"normalized": false,
|
| 312 |
-
"rstrip": false,
|
| 313 |
-
"single_word": false,
|
| 314 |
-
"special": true
|
| 315 |
-
},
|
| 316 |
-
"32036": {
|
| 317 |
-
"content": "<extra_id_63>",
|
| 318 |
-
"lstrip": false,
|
| 319 |
-
"normalized": false,
|
| 320 |
-
"rstrip": false,
|
| 321 |
-
"single_word": false,
|
| 322 |
-
"special": true
|
| 323 |
-
},
|
| 324 |
-
"32037": {
|
| 325 |
-
"content": "<extra_id_62>",
|
| 326 |
-
"lstrip": false,
|
| 327 |
-
"normalized": false,
|
| 328 |
-
"rstrip": false,
|
| 329 |
-
"single_word": false,
|
| 330 |
-
"special": true
|
| 331 |
-
},
|
| 332 |
-
"32038": {
|
| 333 |
-
"content": "<extra_id_61>",
|
| 334 |
-
"lstrip": false,
|
| 335 |
-
"normalized": false,
|
| 336 |
-
"rstrip": false,
|
| 337 |
-
"single_word": false,
|
| 338 |
-
"special": true
|
| 339 |
-
},
|
| 340 |
-
"32039": {
|
| 341 |
-
"content": "<extra_id_60>",
|
| 342 |
-
"lstrip": false,
|
| 343 |
-
"normalized": false,
|
| 344 |
-
"rstrip": false,
|
| 345 |
-
"single_word": false,
|
| 346 |
-
"special": true
|
| 347 |
-
},
|
| 348 |
-
"32040": {
|
| 349 |
-
"content": "<extra_id_59>",
|
| 350 |
-
"lstrip": false,
|
| 351 |
-
"normalized": false,
|
| 352 |
-
"rstrip": false,
|
| 353 |
-
"single_word": false,
|
| 354 |
-
"special": true
|
| 355 |
-
},
|
| 356 |
-
"32041": {
|
| 357 |
-
"content": "<extra_id_58>",
|
| 358 |
-
"lstrip": false,
|
| 359 |
-
"normalized": false,
|
| 360 |
-
"rstrip": false,
|
| 361 |
-
"single_word": false,
|
| 362 |
-
"special": true
|
| 363 |
-
},
|
| 364 |
-
"32042": {
|
| 365 |
-
"content": "<extra_id_57>",
|
| 366 |
-
"lstrip": false,
|
| 367 |
-
"normalized": false,
|
| 368 |
-
"rstrip": false,
|
| 369 |
-
"single_word": false,
|
| 370 |
-
"special": true
|
| 371 |
-
},
|
| 372 |
-
"32043": {
|
| 373 |
-
"content": "<extra_id_56>",
|
| 374 |
-
"lstrip": false,
|
| 375 |
-
"normalized": false,
|
| 376 |
-
"rstrip": false,
|
| 377 |
-
"single_word": false,
|
| 378 |
-
"special": true
|
| 379 |
-
},
|
| 380 |
-
"32044": {
|
| 381 |
-
"content": "<extra_id_55>",
|
| 382 |
-
"lstrip": false,
|
| 383 |
-
"normalized": false,
|
| 384 |
-
"rstrip": false,
|
| 385 |
-
"single_word": false,
|
| 386 |
-
"special": true
|
| 387 |
-
},
|
| 388 |
-
"32045": {
|
| 389 |
-
"content": "<extra_id_54>",
|
| 390 |
-
"lstrip": false,
|
| 391 |
-
"normalized": false,
|
| 392 |
-
"rstrip": false,
|
| 393 |
-
"single_word": false,
|
| 394 |
-
"special": true
|
| 395 |
-
},
|
| 396 |
-
"32046": {
|
| 397 |
-
"content": "<extra_id_53>",
|
| 398 |
-
"lstrip": false,
|
| 399 |
-
"normalized": false,
|
| 400 |
-
"rstrip": false,
|
| 401 |
-
"single_word": false,
|
| 402 |
-
"special": true
|
| 403 |
-
},
|
| 404 |
-
"32047": {
|
| 405 |
-
"content": "<extra_id_52>",
|
| 406 |
-
"lstrip": false,
|
| 407 |
-
"normalized": false,
|
| 408 |
-
"rstrip": false,
|
| 409 |
-
"single_word": false,
|
| 410 |
-
"special": true
|
| 411 |
-
},
|
| 412 |
-
"32048": {
|
| 413 |
-
"content": "<extra_id_51>",
|
| 414 |
-
"lstrip": false,
|
| 415 |
-
"normalized": false,
|
| 416 |
-
"rstrip": false,
|
| 417 |
-
"single_word": false,
|
| 418 |
-
"special": true
|
| 419 |
-
},
|
| 420 |
-
"32049": {
|
| 421 |
-
"content": "<extra_id_50>",
|
| 422 |
-
"lstrip": false,
|
| 423 |
-
"normalized": false,
|
| 424 |
-
"rstrip": false,
|
| 425 |
-
"single_word": false,
|
| 426 |
-
"special": true
|
| 427 |
-
},
|
| 428 |
-
"32050": {
|
| 429 |
-
"content": "<extra_id_49>",
|
| 430 |
-
"lstrip": false,
|
| 431 |
-
"normalized": false,
|
| 432 |
-
"rstrip": false,
|
| 433 |
-
"single_word": false,
|
| 434 |
-
"special": true
|
| 435 |
-
},
|
| 436 |
-
"32051": {
|
| 437 |
-
"content": "<extra_id_48>",
|
| 438 |
-
"lstrip": false,
|
| 439 |
-
"normalized": false,
|
| 440 |
-
"rstrip": false,
|
| 441 |
-
"single_word": false,
|
| 442 |
-
"special": true
|
| 443 |
-
},
|
| 444 |
-
"32052": {
|
| 445 |
-
"content": "<extra_id_47>",
|
| 446 |
-
"lstrip": false,
|
| 447 |
-
"normalized": false,
|
| 448 |
-
"rstrip": false,
|
| 449 |
-
"single_word": false,
|
| 450 |
-
"special": true
|
| 451 |
-
},
|
| 452 |
-
"32053": {
|
| 453 |
-
"content": "<extra_id_46>",
|
| 454 |
-
"lstrip": false,
|
| 455 |
-
"normalized": false,
|
| 456 |
-
"rstrip": false,
|
| 457 |
-
"single_word": false,
|
| 458 |
-
"special": true
|
| 459 |
-
},
|
| 460 |
-
"32054": {
|
| 461 |
-
"content": "<extra_id_45>",
|
| 462 |
-
"lstrip": false,
|
| 463 |
-
"normalized": false,
|
| 464 |
-
"rstrip": false,
|
| 465 |
-
"single_word": false,
|
| 466 |
-
"special": true
|
| 467 |
-
},
|
| 468 |
-
"32055": {
|
| 469 |
-
"content": "<extra_id_44>",
|
| 470 |
-
"lstrip": false,
|
| 471 |
-
"normalized": false,
|
| 472 |
-
"rstrip": false,
|
| 473 |
-
"single_word": false,
|
| 474 |
-
"special": true
|
| 475 |
-
},
|
| 476 |
-
"32056": {
|
| 477 |
-
"content": "<extra_id_43>",
|
| 478 |
-
"lstrip": false,
|
| 479 |
-
"normalized": false,
|
| 480 |
-
"rstrip": false,
|
| 481 |
-
"single_word": false,
|
| 482 |
-
"special": true
|
| 483 |
-
},
|
| 484 |
-
"32057": {
|
| 485 |
-
"content": "<extra_id_42>",
|
| 486 |
-
"lstrip": false,
|
| 487 |
-
"normalized": false,
|
| 488 |
-
"rstrip": false,
|
| 489 |
-
"single_word": false,
|
| 490 |
-
"special": true
|
| 491 |
-
},
|
| 492 |
-
"32058": {
|
| 493 |
-
"content": "<extra_id_41>",
|
| 494 |
-
"lstrip": false,
|
| 495 |
-
"normalized": false,
|
| 496 |
-
"rstrip": false,
|
| 497 |
-
"single_word": false,
|
| 498 |
-
"special": true
|
| 499 |
-
},
|
| 500 |
-
"32059": {
|
| 501 |
-
"content": "<extra_id_40>",
|
| 502 |
-
"lstrip": false,
|
| 503 |
-
"normalized": false,
|
| 504 |
-
"rstrip": false,
|
| 505 |
-
"single_word": false,
|
| 506 |
-
"special": true
|
| 507 |
-
},
|
| 508 |
-
"32060": {
|
| 509 |
-
"content": "<extra_id_39>",
|
| 510 |
-
"lstrip": false,
|
| 511 |
-
"normalized": false,
|
| 512 |
-
"rstrip": false,
|
| 513 |
-
"single_word": false,
|
| 514 |
-
"special": true
|
| 515 |
-
},
|
| 516 |
-
"32061": {
|
| 517 |
-
"content": "<extra_id_38>",
|
| 518 |
-
"lstrip": false,
|
| 519 |
-
"normalized": false,
|
| 520 |
-
"rstrip": false,
|
| 521 |
-
"single_word": false,
|
| 522 |
-
"special": true
|
| 523 |
-
},
|
| 524 |
-
"32062": {
|
| 525 |
-
"content": "<extra_id_37>",
|
| 526 |
-
"lstrip": false,
|
| 527 |
-
"normalized": false,
|
| 528 |
-
"rstrip": false,
|
| 529 |
-
"single_word": false,
|
| 530 |
-
"special": true
|
| 531 |
-
},
|
| 532 |
-
"32063": {
|
| 533 |
-
"content": "<extra_id_36>",
|
| 534 |
-
"lstrip": false,
|
| 535 |
-
"normalized": false,
|
| 536 |
-
"rstrip": false,
|
| 537 |
-
"single_word": false,
|
| 538 |
-
"special": true
|
| 539 |
-
},
|
| 540 |
-
"32064": {
|
| 541 |
-
"content": "<extra_id_35>",
|
| 542 |
-
"lstrip": false,
|
| 543 |
-
"normalized": false,
|
| 544 |
-
"rstrip": false,
|
| 545 |
-
"single_word": false,
|
| 546 |
-
"special": true
|
| 547 |
-
},
|
| 548 |
-
"32065": {
|
| 549 |
-
"content": "<extra_id_34>",
|
| 550 |
-
"lstrip": false,
|
| 551 |
-
"normalized": false,
|
| 552 |
-
"rstrip": false,
|
| 553 |
-
"single_word": false,
|
| 554 |
-
"special": true
|
| 555 |
-
},
|
| 556 |
-
"32066": {
|
| 557 |
-
"content": "<extra_id_33>",
|
| 558 |
-
"lstrip": false,
|
| 559 |
-
"normalized": false,
|
| 560 |
-
"rstrip": false,
|
| 561 |
-
"single_word": false,
|
| 562 |
-
"special": true
|
| 563 |
-
},
|
| 564 |
-
"32067": {
|
| 565 |
-
"content": "<extra_id_32>",
|
| 566 |
-
"lstrip": false,
|
| 567 |
-
"normalized": false,
|
| 568 |
-
"rstrip": false,
|
| 569 |
-
"single_word": false,
|
| 570 |
-
"special": true
|
| 571 |
-
},
|
| 572 |
-
"32068": {
|
| 573 |
-
"content": "<extra_id_31>",
|
| 574 |
-
"lstrip": false,
|
| 575 |
-
"normalized": false,
|
| 576 |
-
"rstrip": false,
|
| 577 |
-
"single_word": false,
|
| 578 |
-
"special": true
|
| 579 |
-
},
|
| 580 |
-
"32069": {
|
| 581 |
-
"content": "<extra_id_30>",
|
| 582 |
-
"lstrip": false,
|
| 583 |
-
"normalized": false,
|
| 584 |
-
"rstrip": false,
|
| 585 |
-
"single_word": false,
|
| 586 |
-
"special": true
|
| 587 |
-
},
|
| 588 |
-
"32070": {
|
| 589 |
-
"content": "<extra_id_29>",
|
| 590 |
-
"lstrip": false,
|
| 591 |
-
"normalized": false,
|
| 592 |
-
"rstrip": false,
|
| 593 |
-
"single_word": false,
|
| 594 |
-
"special": true
|
| 595 |
-
},
|
| 596 |
-
"32071": {
|
| 597 |
-
"content": "<extra_id_28>",
|
| 598 |
-
"lstrip": false,
|
| 599 |
-
"normalized": false,
|
| 600 |
-
"rstrip": false,
|
| 601 |
-
"single_word": false,
|
| 602 |
-
"special": true
|
| 603 |
-
},
|
| 604 |
-
"32072": {
|
| 605 |
-
"content": "<extra_id_27>",
|
| 606 |
-
"lstrip": false,
|
| 607 |
-
"normalized": false,
|
| 608 |
-
"rstrip": false,
|
| 609 |
-
"single_word": false,
|
| 610 |
-
"special": true
|
| 611 |
-
},
|
| 612 |
-
"32073": {
|
| 613 |
-
"content": "<extra_id_26>",
|
| 614 |
-
"lstrip": false,
|
| 615 |
-
"normalized": false,
|
| 616 |
-
"rstrip": false,
|
| 617 |
-
"single_word": false,
|
| 618 |
-
"special": true
|
| 619 |
-
},
|
| 620 |
-
"32074": {
|
| 621 |
-
"content": "<extra_id_25>",
|
| 622 |
-
"lstrip": false,
|
| 623 |
-
"normalized": false,
|
| 624 |
-
"rstrip": false,
|
| 625 |
-
"single_word": false,
|
| 626 |
-
"special": true
|
| 627 |
-
},
|
| 628 |
-
"32075": {
|
| 629 |
-
"content": "<extra_id_24>",
|
| 630 |
-
"lstrip": false,
|
| 631 |
-
"normalized": false,
|
| 632 |
-
"rstrip": false,
|
| 633 |
-
"single_word": false,
|
| 634 |
-
"special": true
|
| 635 |
-
},
|
| 636 |
-
"32076": {
|
| 637 |
-
"content": "<extra_id_23>",
|
| 638 |
-
"lstrip": false,
|
| 639 |
-
"normalized": false,
|
| 640 |
-
"rstrip": false,
|
| 641 |
-
"single_word": false,
|
| 642 |
-
"special": true
|
| 643 |
-
},
|
| 644 |
-
"32077": {
|
| 645 |
-
"content": "<extra_id_22>",
|
| 646 |
-
"lstrip": false,
|
| 647 |
-
"normalized": false,
|
| 648 |
-
"rstrip": false,
|
| 649 |
-
"single_word": false,
|
| 650 |
-
"special": true
|
| 651 |
-
},
|
| 652 |
-
"32078": {
|
| 653 |
-
"content": "<extra_id_21>",
|
| 654 |
-
"lstrip": false,
|
| 655 |
-
"normalized": false,
|
| 656 |
-
"rstrip": false,
|
| 657 |
-
"single_word": false,
|
| 658 |
-
"special": true
|
| 659 |
-
},
|
| 660 |
-
"32079": {
|
| 661 |
-
"content": "<extra_id_20>",
|
| 662 |
-
"lstrip": false,
|
| 663 |
-
"normalized": false,
|
| 664 |
-
"rstrip": false,
|
| 665 |
-
"single_word": false,
|
| 666 |
-
"special": true
|
| 667 |
-
},
|
| 668 |
-
"32080": {
|
| 669 |
-
"content": "<extra_id_19>",
|
| 670 |
-
"lstrip": false,
|
| 671 |
-
"normalized": false,
|
| 672 |
-
"rstrip": false,
|
| 673 |
-
"single_word": false,
|
| 674 |
-
"special": true
|
| 675 |
-
},
|
| 676 |
-
"32081": {
|
| 677 |
-
"content": "<extra_id_18>",
|
| 678 |
-
"lstrip": false,
|
| 679 |
-
"normalized": false,
|
| 680 |
-
"rstrip": false,
|
| 681 |
-
"single_word": false,
|
| 682 |
-
"special": true
|
| 683 |
-
},
|
| 684 |
-
"32082": {
|
| 685 |
-
"content": "<extra_id_17>",
|
| 686 |
-
"lstrip": false,
|
| 687 |
-
"normalized": false,
|
| 688 |
-
"rstrip": false,
|
| 689 |
-
"single_word": false,
|
| 690 |
-
"special": true
|
| 691 |
-
},
|
| 692 |
-
"32083": {
|
| 693 |
-
"content": "<extra_id_16>",
|
| 694 |
-
"lstrip": false,
|
| 695 |
-
"normalized": false,
|
| 696 |
-
"rstrip": false,
|
| 697 |
-
"single_word": false,
|
| 698 |
-
"special": true
|
| 699 |
-
},
|
| 700 |
-
"32084": {
|
| 701 |
-
"content": "<extra_id_15>",
|
| 702 |
-
"lstrip": false,
|
| 703 |
-
"normalized": false,
|
| 704 |
-
"rstrip": false,
|
| 705 |
-
"single_word": false,
|
| 706 |
-
"special": true
|
| 707 |
-
},
|
| 708 |
-
"32085": {
|
| 709 |
-
"content": "<extra_id_14>",
|
| 710 |
-
"lstrip": false,
|
| 711 |
-
"normalized": false,
|
| 712 |
-
"rstrip": false,
|
| 713 |
-
"single_word": false,
|
| 714 |
-
"special": true
|
| 715 |
-
},
|
| 716 |
-
"32086": {
|
| 717 |
-
"content": "<extra_id_13>",
|
| 718 |
-
"lstrip": false,
|
| 719 |
-
"normalized": false,
|
| 720 |
-
"rstrip": false,
|
| 721 |
-
"single_word": false,
|
| 722 |
-
"special": true
|
| 723 |
-
},
|
| 724 |
-
"32087": {
|
| 725 |
-
"content": "<extra_id_12>",
|
| 726 |
-
"lstrip": false,
|
| 727 |
-
"normalized": false,
|
| 728 |
-
"rstrip": false,
|
| 729 |
-
"single_word": false,
|
| 730 |
-
"special": true
|
| 731 |
-
},
|
| 732 |
-
"32088": {
|
| 733 |
-
"content": "<extra_id_11>",
|
| 734 |
-
"lstrip": false,
|
| 735 |
-
"normalized": false,
|
| 736 |
-
"rstrip": false,
|
| 737 |
-
"single_word": false,
|
| 738 |
-
"special": true
|
| 739 |
-
},
|
| 740 |
-
"32089": {
|
| 741 |
-
"content": "<extra_id_10>",
|
| 742 |
-
"lstrip": false,
|
| 743 |
-
"normalized": false,
|
| 744 |
-
"rstrip": false,
|
| 745 |
-
"single_word": false,
|
| 746 |
-
"special": true
|
| 747 |
-
},
|
| 748 |
-
"32090": {
|
| 749 |
-
"content": "<extra_id_9>",
|
| 750 |
-
"lstrip": false,
|
| 751 |
-
"normalized": false,
|
| 752 |
-
"rstrip": false,
|
| 753 |
-
"single_word": false,
|
| 754 |
-
"special": true
|
| 755 |
-
},
|
| 756 |
-
"32091": {
|
| 757 |
-
"content": "<extra_id_8>",
|
| 758 |
-
"lstrip": false,
|
| 759 |
-
"normalized": false,
|
| 760 |
-
"rstrip": false,
|
| 761 |
-
"single_word": false,
|
| 762 |
-
"special": true
|
| 763 |
-
},
|
| 764 |
-
"32092": {
|
| 765 |
-
"content": "<extra_id_7>",
|
| 766 |
-
"lstrip": false,
|
| 767 |
-
"normalized": false,
|
| 768 |
-
"rstrip": false,
|
| 769 |
-
"single_word": false,
|
| 770 |
-
"special": true
|
| 771 |
-
},
|
| 772 |
-
"32093": {
|
| 773 |
-
"content": "<extra_id_6>",
|
| 774 |
-
"lstrip": false,
|
| 775 |
-
"normalized": false,
|
| 776 |
-
"rstrip": false,
|
| 777 |
-
"single_word": false,
|
| 778 |
-
"special": true
|
| 779 |
-
},
|
| 780 |
-
"32094": {
|
| 781 |
-
"content": "<extra_id_5>",
|
| 782 |
-
"lstrip": false,
|
| 783 |
-
"normalized": false,
|
| 784 |
-
"rstrip": false,
|
| 785 |
-
"single_word": false,
|
| 786 |
-
"special": true
|
| 787 |
-
},
|
| 788 |
-
"32095": {
|
| 789 |
-
"content": "<extra_id_4>",
|
| 790 |
-
"lstrip": false,
|
| 791 |
-
"normalized": false,
|
| 792 |
-
"rstrip": false,
|
| 793 |
-
"single_word": false,
|
| 794 |
-
"special": true
|
| 795 |
-
},
|
| 796 |
-
"32096": {
|
| 797 |
-
"content": "<extra_id_3>",
|
| 798 |
-
"lstrip": false,
|
| 799 |
-
"normalized": false,
|
| 800 |
-
"rstrip": false,
|
| 801 |
-
"single_word": false,
|
| 802 |
-
"special": true
|
| 803 |
-
},
|
| 804 |
-
"32097": {
|
| 805 |
-
"content": "<extra_id_2>",
|
| 806 |
-
"lstrip": false,
|
| 807 |
-
"normalized": false,
|
| 808 |
-
"rstrip": false,
|
| 809 |
-
"single_word": false,
|
| 810 |
-
"special": true
|
| 811 |
-
},
|
| 812 |
-
"32098": {
|
| 813 |
-
"content": "<extra_id_1>",
|
| 814 |
-
"lstrip": false,
|
| 815 |
-
"normalized": false,
|
| 816 |
-
"rstrip": false,
|
| 817 |
-
"single_word": false,
|
| 818 |
-
"special": true
|
| 819 |
-
},
|
| 820 |
-
"32099": {
|
| 821 |
-
"content": "<extra_id_0>",
|
| 822 |
-
"lstrip": false,
|
| 823 |
-
"normalized": false,
|
| 824 |
-
"rstrip": false,
|
| 825 |
-
"single_word": false,
|
| 826 |
-
"special": true
|
| 827 |
-
}
|
| 828 |
-
},
|
| 829 |
-
"additional_special_tokens": [
|
| 830 |
-
"<extra_id_0>",
|
| 831 |
-
"<extra_id_1>",
|
| 832 |
-
"<extra_id_2>",
|
| 833 |
-
"<extra_id_3>",
|
| 834 |
-
"<extra_id_4>",
|
| 835 |
-
"<extra_id_5>",
|
| 836 |
-
"<extra_id_6>",
|
| 837 |
-
"<extra_id_7>",
|
| 838 |
-
"<extra_id_8>",
|
| 839 |
-
"<extra_id_9>",
|
| 840 |
-
"<extra_id_10>",
|
| 841 |
-
"<extra_id_11>",
|
| 842 |
-
"<extra_id_12>",
|
| 843 |
-
"<extra_id_13>",
|
| 844 |
-
"<extra_id_14>",
|
| 845 |
-
"<extra_id_15>",
|
| 846 |
-
"<extra_id_16>",
|
| 847 |
-
"<extra_id_17>",
|
| 848 |
-
"<extra_id_18>",
|
| 849 |
-
"<extra_id_19>",
|
| 850 |
-
"<extra_id_20>",
|
| 851 |
-
"<extra_id_21>",
|
| 852 |
-
"<extra_id_22>",
|
| 853 |
-
"<extra_id_23>",
|
| 854 |
-
"<extra_id_24>",
|
| 855 |
-
"<extra_id_25>",
|
| 856 |
-
"<extra_id_26>",
|
| 857 |
-
"<extra_id_27>",
|
| 858 |
-
"<extra_id_28>",
|
| 859 |
-
"<extra_id_29>",
|
| 860 |
-
"<extra_id_30>",
|
| 861 |
-
"<extra_id_31>",
|
| 862 |
-
"<extra_id_32>",
|
| 863 |
-
"<extra_id_33>",
|
| 864 |
-
"<extra_id_34>",
|
| 865 |
-
"<extra_id_35>",
|
| 866 |
-
"<extra_id_36>",
|
| 867 |
-
"<extra_id_37>",
|
| 868 |
-
"<extra_id_38>",
|
| 869 |
-
"<extra_id_39>",
|
| 870 |
-
"<extra_id_40>",
|
| 871 |
-
"<extra_id_41>",
|
| 872 |
-
"<extra_id_42>",
|
| 873 |
-
"<extra_id_43>",
|
| 874 |
-
"<extra_id_44>",
|
| 875 |
-
"<extra_id_45>",
|
| 876 |
-
"<extra_id_46>",
|
| 877 |
-
"<extra_id_47>",
|
| 878 |
-
"<extra_id_48>",
|
| 879 |
-
"<extra_id_49>",
|
| 880 |
-
"<extra_id_50>",
|
| 881 |
-
"<extra_id_51>",
|
| 882 |
-
"<extra_id_52>",
|
| 883 |
-
"<extra_id_53>",
|
| 884 |
-
"<extra_id_54>",
|
| 885 |
-
"<extra_id_55>",
|
| 886 |
-
"<extra_id_56>",
|
| 887 |
-
"<extra_id_57>",
|
| 888 |
-
"<extra_id_58>",
|
| 889 |
-
"<extra_id_59>",
|
| 890 |
-
"<extra_id_60>",
|
| 891 |
-
"<extra_id_61>",
|
| 892 |
-
"<extra_id_62>",
|
| 893 |
-
"<extra_id_63>",
|
| 894 |
-
"<extra_id_64>",
|
| 895 |
-
"<extra_id_65>",
|
| 896 |
-
"<extra_id_66>",
|
| 897 |
-
"<extra_id_67>",
|
| 898 |
-
"<extra_id_68>",
|
| 899 |
-
"<extra_id_69>",
|
| 900 |
-
"<extra_id_70>",
|
| 901 |
-
"<extra_id_71>",
|
| 902 |
-
"<extra_id_72>",
|
| 903 |
-
"<extra_id_73>",
|
| 904 |
-
"<extra_id_74>",
|
| 905 |
-
"<extra_id_75>",
|
| 906 |
-
"<extra_id_76>",
|
| 907 |
-
"<extra_id_77>",
|
| 908 |
-
"<extra_id_78>",
|
| 909 |
-
"<extra_id_79>",
|
| 910 |
-
"<extra_id_80>",
|
| 911 |
-
"<extra_id_81>",
|
| 912 |
-
"<extra_id_82>",
|
| 913 |
-
"<extra_id_83>",
|
| 914 |
-
"<extra_id_84>",
|
| 915 |
-
"<extra_id_85>",
|
| 916 |
-
"<extra_id_86>",
|
| 917 |
-
"<extra_id_87>",
|
| 918 |
-
"<extra_id_88>",
|
| 919 |
-
"<extra_id_89>",
|
| 920 |
-
"<extra_id_90>",
|
| 921 |
-
"<extra_id_91>",
|
| 922 |
-
"<extra_id_92>",
|
| 923 |
-
"<extra_id_93>",
|
| 924 |
-
"<extra_id_94>",
|
| 925 |
-
"<extra_id_95>",
|
| 926 |
-
"<extra_id_96>",
|
| 927 |
-
"<extra_id_97>",
|
| 928 |
-
"<extra_id_98>",
|
| 929 |
-
"<extra_id_99>"
|
| 930 |
-
],
|
| 931 |
-
"clean_up_tokenization_spaces": true,
|
| 932 |
-
"eos_token": "</s>",
|
| 933 |
-
"extra_ids": 100,
|
| 934 |
-
"extra_special_tokens": {},
|
| 935 |
-
"model_max_length": 512,
|
| 936 |
-
"pad_token": "<pad>",
|
| 937 |
-
"tokenizer_class": "T5Tokenizer",
|
| 938 |
-
"unk_token": "<unk>"
|
| 939 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 242041896
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cee34848014a7023f7c44bcd836df67292a4f1655c491368c20d8d7294b9ebb
|
| 3 |
size 242041896
|
src/train_t5.py
CHANGED
|
@@ -8,6 +8,7 @@ from transformers import (
|
|
| 8 |
T5ForConditionalGeneration
|
| 9 |
)
|
| 10 |
|
|
|
|
| 11 |
# Path config
|
| 12 |
base_model = "t5-small"
|
| 13 |
data_path = "src/data/clean_corpus.jsonl"
|
|
@@ -48,8 +49,8 @@ data_collator = DataCollatorForSeq2Seq(tokenizer = tokeniser, model = model)
|
|
| 48 |
training_args = TrainingArguments(
|
| 49 |
output_dir = output_dir,
|
| 50 |
overwrite_output_dir = True,
|
| 51 |
-
num_train_epochs =
|
| 52 |
-
per_device_train_batch_size =
|
| 53 |
gradient_accumulation_steps = 8,
|
| 54 |
save_strategy = "steps",
|
| 55 |
save_steps = 500,
|
|
|
|
| 8 |
T5ForConditionalGeneration
|
| 9 |
)
|
| 10 |
|
| 11 |
+
|
| 12 |
# Path config
|
| 13 |
base_model = "t5-small"
|
| 14 |
data_path = "src/data/clean_corpus.jsonl"
|
|
|
|
| 49 |
training_args = TrainingArguments(
|
| 50 |
output_dir = output_dir,
|
| 51 |
overwrite_output_dir = True,
|
| 52 |
+
num_train_epochs = 5,
|
| 53 |
+
per_device_train_batch_size = 16,
|
| 54 |
gradient_accumulation_steps = 8,
|
| 55 |
save_strategy = "steps",
|
| 56 |
save_steps = 500,
|
tokenizer.json
CHANGED
|
@@ -1,21 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 128,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": {
|
| 11 |
-
"Fixed": 128
|
| 12 |
-
},
|
| 13 |
-
"direction": "Right",
|
| 14 |
-
"pad_to_multiple_of": null,
|
| 15 |
-
"pad_id": 0,
|
| 16 |
-
"pad_type_id": 0,
|
| 17 |
-
"pad_token": "<pad>"
|
| 18 |
-
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|