Commit
•
789fd07
1
Parent(s):
a4180c5
End of training
Browse files
.ipynb_checkpoints/README-checkpoint.md
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-xls-r-300m-ar
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# wav2vec2-xls-r-300m-ar
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 0.0005
|
| 37 |
+
- train_batch_size: 64
|
| 38 |
+
- eval_batch_size: 64
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- lr_scheduler_warmup_steps: 2000
|
| 43 |
+
- num_epochs: 5
|
| 44 |
+
- mixed_precision_training: Native AMP
|
| 45 |
+
|
| 46 |
+
### Framework versions
|
| 47 |
+
|
| 48 |
+
- Transformers 4.17.0.dev0
|
| 49 |
+
- Pytorch 1.10.2+cu102
|
| 50 |
+
- Datasets 1.18.2.dev0
|
| 51 |
+
- Tokenizers 0.11.0
|
.ipynb_checkpoints/eval_results-checkpoint.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_loss": 6.937458515167236,
|
| 4 |
+
"eval_runtime": 5.7217,
|
| 5 |
+
"eval_samples": 128,
|
| 6 |
+
"eval_samples_per_second": 22.371,
|
| 7 |
+
"eval_steps_per_second": 0.35,
|
| 8 |
+
"eval_wer": 1.0
|
| 9 |
+
}
|
.ipynb_checkpoints/trainer_state-checkpoint.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 340,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.15,
|
| 12 |
+
"learning_rate": 1.1750000000000001e-05,
|
| 13 |
+
"loss": 15.017,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.29,
|
| 18 |
+
"learning_rate": 2.425e-05,
|
| 19 |
+
"loss": 6.7134,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.44,
|
| 24 |
+
"learning_rate": 3.675e-05,
|
| 25 |
+
"loss": 4.3869,
|
| 26 |
+
"step": 150
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.59,
|
| 30 |
+
"learning_rate": 4.9250000000000004e-05,
|
| 31 |
+
"loss": 3.6209,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.74,
|
| 36 |
+
"learning_rate": 6.175e-05,
|
| 37 |
+
"loss": 3.2011,
|
| 38 |
+
"step": 250
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.88,
|
| 42 |
+
"learning_rate": 7.425e-05,
|
| 43 |
+
"loss": 3.0513,
|
| 44 |
+
"step": 300
|
| 45 |
+
}
|
| 46 |
+
],
|
| 47 |
+
"max_steps": 1700,
|
| 48 |
+
"num_train_epochs": 5,
|
| 49 |
+
"total_flos": 1.7302176965482906e+18,
|
| 50 |
+
"trial_name": null,
|
| 51 |
+
"trial_params": null
|
| 52 |
+
}
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
-
"eval_loss":
|
| 4 |
"eval_runtime": 5.7217,
|
| 5 |
-
"eval_samples":
|
| 6 |
"eval_samples_per_second": 22.371,
|
| 7 |
"eval_steps_per_second": 0.35,
|
| 8 |
"eval_wer": 1.0,
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 20.0,
|
| 3 |
+
"eval_loss": 3.0191357135772705,
|
| 4 |
"eval_runtime": 5.7217,
|
| 5 |
+
"eval_samples": 7622,
|
| 6 |
"eval_samples_per_second": 22.371,
|
| 7 |
"eval_steps_per_second": 0.35,
|
| 8 |
"eval_wer": 1.0,
|
eval_results.json
CHANGED
|
@@ -1,9 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"eval_runtime": 5.7217,
|
| 5 |
-
"eval_samples": 128,
|
| 6 |
-
"eval_samples_per_second": 22.371,
|
| 7 |
-
"eval_steps_per_second": 0.35,
|
| 8 |
"eval_wer": 1.0
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"eval_loss": 3.0191357135772705,
|
| 3 |
+
"eval_samples": 7622,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"eval_wer": 1.0
|
| 5 |
}
|
trainer_state.json
CHANGED
|
@@ -1,325 +1,52 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch":
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss":
|
| 14 |
-
"step":
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch":
|
| 18 |
-
"
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"eval_steps_per_second": 0.377,
|
| 22 |
-
"eval_wer": 1.0,
|
| 23 |
-
"step": 2
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch":
|
| 27 |
-
"learning_rate":
|
| 28 |
-
"loss":
|
| 29 |
-
"step":
|
| 30 |
},
|
| 31 |
{
|
| 32 |
-
"epoch":
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"eval_steps_per_second": 0.378,
|
| 37 |
-
"eval_wer": 1.0,
|
| 38 |
-
"step": 4
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"learning_rate": 6.
|
| 43 |
-
"loss":
|
| 44 |
-
"step":
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"
|
| 51 |
-
"eval_steps_per_second": 0.379,
|
| 52 |
-
"eval_wer": 1.0,
|
| 53 |
-
"step": 6
|
| 54 |
-
},
|
| 55 |
-
{
|
| 56 |
-
"epoch": 4.0,
|
| 57 |
-
"learning_rate": 6.5625e-05,
|
| 58 |
-
"loss": 14.7415,
|
| 59 |
-
"step": 8
|
| 60 |
-
},
|
| 61 |
-
{
|
| 62 |
-
"epoch": 4.0,
|
| 63 |
-
"eval_loss": 22.918315887451172,
|
| 64 |
-
"eval_runtime": 5.4291,
|
| 65 |
-
"eval_samples_per_second": 23.577,
|
| 66 |
-
"eval_steps_per_second": 0.368,
|
| 67 |
-
"eval_wer": 1.0,
|
| 68 |
-
"step": 8
|
| 69 |
-
},
|
| 70 |
-
{
|
| 71 |
-
"epoch": 5.0,
|
| 72 |
-
"learning_rate": 6.187499999999999e-05,
|
| 73 |
-
"loss": 11.8071,
|
| 74 |
-
"step": 10
|
| 75 |
-
},
|
| 76 |
-
{
|
| 77 |
-
"epoch": 5.0,
|
| 78 |
-
"eval_loss": 17.507305145263672,
|
| 79 |
-
"eval_runtime": 5.3146,
|
| 80 |
-
"eval_samples_per_second": 24.085,
|
| 81 |
-
"eval_steps_per_second": 0.376,
|
| 82 |
-
"eval_wer": 1.0,
|
| 83 |
-
"step": 10
|
| 84 |
-
},
|
| 85 |
-
{
|
| 86 |
-
"epoch": 6.0,
|
| 87 |
-
"learning_rate": 5.8124999999999997e-05,
|
| 88 |
-
"loss": 9.7675,
|
| 89 |
-
"step": 12
|
| 90 |
-
},
|
| 91 |
-
{
|
| 92 |
-
"epoch": 6.0,
|
| 93 |
-
"eval_loss": 14.17426872253418,
|
| 94 |
-
"eval_runtime": 5.4054,
|
| 95 |
-
"eval_samples_per_second": 23.68,
|
| 96 |
-
"eval_steps_per_second": 0.37,
|
| 97 |
-
"eval_wer": 1.0,
|
| 98 |
-
"step": 12
|
| 99 |
-
},
|
| 100 |
-
{
|
| 101 |
-
"epoch": 7.0,
|
| 102 |
-
"learning_rate": 5.4374999999999994e-05,
|
| 103 |
-
"loss": 8.4193,
|
| 104 |
-
"step": 14
|
| 105 |
-
},
|
| 106 |
-
{
|
| 107 |
-
"epoch": 7.0,
|
| 108 |
-
"eval_loss": 12.122542381286621,
|
| 109 |
-
"eval_runtime": 5.2782,
|
| 110 |
-
"eval_samples_per_second": 24.251,
|
| 111 |
-
"eval_steps_per_second": 0.379,
|
| 112 |
-
"eval_wer": 1.0,
|
| 113 |
-
"step": 14
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 8.0,
|
| 117 |
-
"learning_rate": 5.0625e-05,
|
| 118 |
-
"loss": 7.4746,
|
| 119 |
-
"step": 16
|
| 120 |
-
},
|
| 121 |
-
{
|
| 122 |
-
"epoch": 8.0,
|
| 123 |
-
"eval_loss": 10.744585037231445,
|
| 124 |
-
"eval_runtime": 5.3374,
|
| 125 |
-
"eval_samples_per_second": 23.982,
|
| 126 |
-
"eval_steps_per_second": 0.375,
|
| 127 |
-
"eval_wer": 1.0,
|
| 128 |
-
"step": 16
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 9.0,
|
| 132 |
-
"learning_rate": 4.6874999999999994e-05,
|
| 133 |
-
"loss": 6.8442,
|
| 134 |
-
"step": 18
|
| 135 |
-
},
|
| 136 |
-
{
|
| 137 |
-
"epoch": 9.0,
|
| 138 |
-
"eval_loss": 9.794867515563965,
|
| 139 |
-
"eval_runtime": 5.2577,
|
| 140 |
-
"eval_samples_per_second": 24.345,
|
| 141 |
-
"eval_steps_per_second": 0.38,
|
| 142 |
-
"eval_wer": 1.0,
|
| 143 |
-
"step": 18
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 10.0,
|
| 147 |
-
"learning_rate": 4.312499999999999e-05,
|
| 148 |
-
"loss": 6.3765,
|
| 149 |
-
"step": 20
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 10.0,
|
| 153 |
-
"eval_loss": 9.114768981933594,
|
| 154 |
-
"eval_runtime": 5.2827,
|
| 155 |
-
"eval_samples_per_second": 24.23,
|
| 156 |
-
"eval_steps_per_second": 0.379,
|
| 157 |
-
"eval_wer": 1.0,
|
| 158 |
-
"step": 20
|
| 159 |
-
},
|
| 160 |
-
{
|
| 161 |
-
"epoch": 11.0,
|
| 162 |
-
"learning_rate": 3.9374999999999995e-05,
|
| 163 |
-
"loss": 6.0321,
|
| 164 |
-
"step": 22
|
| 165 |
-
},
|
| 166 |
-
{
|
| 167 |
-
"epoch": 11.0,
|
| 168 |
-
"eval_loss": 8.59341812133789,
|
| 169 |
-
"eval_runtime": 5.2171,
|
| 170 |
-
"eval_samples_per_second": 24.535,
|
| 171 |
-
"eval_steps_per_second": 0.383,
|
| 172 |
-
"eval_wer": 1.0,
|
| 173 |
-
"step": 22
|
| 174 |
-
},
|
| 175 |
-
{
|
| 176 |
-
"epoch": 12.0,
|
| 177 |
-
"learning_rate": 3.5625e-05,
|
| 178 |
-
"loss": 5.7783,
|
| 179 |
-
"step": 24
|
| 180 |
-
},
|
| 181 |
-
{
|
| 182 |
-
"epoch": 12.0,
|
| 183 |
-
"eval_loss": 8.198293685913086,
|
| 184 |
-
"eval_runtime": 5.3204,
|
| 185 |
-
"eval_samples_per_second": 24.058,
|
| 186 |
-
"eval_steps_per_second": 0.376,
|
| 187 |
-
"eval_wer": 1.0,
|
| 188 |
-
"step": 24
|
| 189 |
-
},
|
| 190 |
-
{
|
| 191 |
-
"epoch": 13.0,
|
| 192 |
-
"learning_rate": 3.1874999999999996e-05,
|
| 193 |
-
"loss": 5.5827,
|
| 194 |
-
"step": 26
|
| 195 |
-
},
|
| 196 |
-
{
|
| 197 |
-
"epoch": 13.0,
|
| 198 |
-
"eval_loss": 7.877962112426758,
|
| 199 |
-
"eval_runtime": 5.2188,
|
| 200 |
-
"eval_samples_per_second": 24.527,
|
| 201 |
-
"eval_steps_per_second": 0.383,
|
| 202 |
-
"eval_wer": 1.0,
|
| 203 |
-
"step": 26
|
| 204 |
-
},
|
| 205 |
-
{
|
| 206 |
-
"epoch": 14.0,
|
| 207 |
-
"learning_rate": 2.8125e-05,
|
| 208 |
-
"loss": 5.4249,
|
| 209 |
-
"step": 28
|
| 210 |
-
},
|
| 211 |
-
{
|
| 212 |
-
"epoch": 14.0,
|
| 213 |
-
"eval_loss": 7.628803730010986,
|
| 214 |
-
"eval_runtime": 5.2811,
|
| 215 |
-
"eval_samples_per_second": 24.238,
|
| 216 |
-
"eval_steps_per_second": 0.379,
|
| 217 |
-
"eval_wer": 1.0,
|
| 218 |
-
"step": 28
|
| 219 |
-
},
|
| 220 |
-
{
|
| 221 |
-
"epoch": 15.0,
|
| 222 |
-
"learning_rate": 2.4375e-05,
|
| 223 |
-
"loss": 5.3088,
|
| 224 |
-
"step": 30
|
| 225 |
-
},
|
| 226 |
-
{
|
| 227 |
-
"epoch": 15.0,
|
| 228 |
-
"eval_loss": 7.427917003631592,
|
| 229 |
-
"eval_runtime": 5.236,
|
| 230 |
-
"eval_samples_per_second": 24.446,
|
| 231 |
-
"eval_steps_per_second": 0.382,
|
| 232 |
-
"eval_wer": 1.0,
|
| 233 |
-
"step": 30
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 16.0,
|
| 237 |
-
"learning_rate": 2.0625e-05,
|
| 238 |
-
"loss": 5.2078,
|
| 239 |
-
"step": 32
|
| 240 |
-
},
|
| 241 |
-
{
|
| 242 |
-
"epoch": 16.0,
|
| 243 |
-
"eval_loss": 7.268764972686768,
|
| 244 |
-
"eval_runtime": 5.2941,
|
| 245 |
-
"eval_samples_per_second": 24.178,
|
| 246 |
-
"eval_steps_per_second": 0.378,
|
| 247 |
-
"eval_wer": 1.0,
|
| 248 |
-
"step": 32
|
| 249 |
-
},
|
| 250 |
-
{
|
| 251 |
-
"epoch": 17.0,
|
| 252 |
-
"learning_rate": 1.6875e-05,
|
| 253 |
-
"loss": 5.1289,
|
| 254 |
-
"step": 34
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 17.0,
|
| 258 |
-
"eval_loss": 7.145933628082275,
|
| 259 |
-
"eval_runtime": 5.2685,
|
| 260 |
-
"eval_samples_per_second": 24.295,
|
| 261 |
-
"eval_steps_per_second": 0.38,
|
| 262 |
-
"eval_wer": 1.0,
|
| 263 |
-
"step": 34
|
| 264 |
-
},
|
| 265 |
-
{
|
| 266 |
-
"epoch": 18.0,
|
| 267 |
-
"learning_rate": 1.3124999999999999e-05,
|
| 268 |
-
"loss": 5.0697,
|
| 269 |
-
"step": 36
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 18.0,
|
| 273 |
-
"eval_loss": 7.052780628204346,
|
| 274 |
-
"eval_runtime": 5.263,
|
| 275 |
-
"eval_samples_per_second": 24.321,
|
| 276 |
-
"eval_steps_per_second": 0.38,
|
| 277 |
-
"eval_wer": 1.0,
|
| 278 |
-
"step": 36
|
| 279 |
-
},
|
| 280 |
-
{
|
| 281 |
-
"epoch": 19.0,
|
| 282 |
-
"learning_rate": 9.375e-06,
|
| 283 |
-
"loss": 5.0227,
|
| 284 |
-
"step": 38
|
| 285 |
-
},
|
| 286 |
-
{
|
| 287 |
-
"epoch": 19.0,
|
| 288 |
-
"eval_loss": 6.983470916748047,
|
| 289 |
-
"eval_runtime": 5.2829,
|
| 290 |
-
"eval_samples_per_second": 24.229,
|
| 291 |
-
"eval_steps_per_second": 0.379,
|
| 292 |
-
"eval_wer": 1.0,
|
| 293 |
-
"step": 38
|
| 294 |
-
},
|
| 295 |
-
{
|
| 296 |
-
"epoch": 20.0,
|
| 297 |
-
"learning_rate": 5.6249999999999995e-06,
|
| 298 |
-
"loss": 4.9853,
|
| 299 |
-
"step": 40
|
| 300 |
-
},
|
| 301 |
-
{
|
| 302 |
-
"epoch": 20.0,
|
| 303 |
-
"eval_loss": 6.937458515167236,
|
| 304 |
-
"eval_runtime": 5.3165,
|
| 305 |
-
"eval_samples_per_second": 24.076,
|
| 306 |
-
"eval_steps_per_second": 0.376,
|
| 307 |
-
"eval_wer": 1.0,
|
| 308 |
-
"step": 40
|
| 309 |
-
},
|
| 310 |
-
{
|
| 311 |
-
"epoch": 20.0,
|
| 312 |
-
"step": 40,
|
| 313 |
-
"total_flos": 5.430583918308557e+17,
|
| 314 |
-
"train_loss": 8.69529299736023,
|
| 315 |
-
"train_runtime": 243.8197,
|
| 316 |
-
"train_samples_per_second": 10.5,
|
| 317 |
-
"train_steps_per_second": 0.164
|
| 318 |
}
|
| 319 |
],
|
| 320 |
-
"max_steps":
|
| 321 |
-
"num_train_epochs":
|
| 322 |
-
"total_flos":
|
| 323 |
"trial_name": null,
|
| 324 |
"trial_params": null
|
| 325 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 340,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.15,
|
| 12 |
+
"learning_rate": 1.1750000000000001e-05,
|
| 13 |
+
"loss": 15.017,
|
| 14 |
+
"step": 50
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.29,
|
| 18 |
+
"learning_rate": 2.425e-05,
|
| 19 |
+
"loss": 6.7134,
|
| 20 |
+
"step": 100
|
|
|
|
|
|
|
|
|
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.44,
|
| 24 |
+
"learning_rate": 3.675e-05,
|
| 25 |
+
"loss": 4.3869,
|
| 26 |
+
"step": 150
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.59,
|
| 30 |
+
"learning_rate": 4.9250000000000004e-05,
|
| 31 |
+
"loss": 3.6209,
|
| 32 |
+
"step": 200
|
|
|
|
|
|
|
|
|
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.74,
|
| 36 |
+
"learning_rate": 6.175e-05,
|
| 37 |
+
"loss": 3.2011,
|
| 38 |
+
"step": 250
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.88,
|
| 42 |
+
"learning_rate": 7.425e-05,
|
| 43 |
+
"loss": 3.0513,
|
| 44 |
+
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
}
|
| 46 |
],
|
| 47 |
+
"max_steps": 1700,
|
| 48 |
+
"num_train_epochs": 5,
|
| 49 |
+
"total_flos": 1.7302176965482906e+18,
|
| 50 |
"trial_name": null,
|
| 51 |
"trial_params": null
|
| 52 |
}
|