End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- train_results.json +8 -0
- trainer_state.json +499 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 0.26187804341316223,
|
| 4 |
+
"eval_runtime": 722.142,
|
| 5 |
+
"eval_samples": 15941,
|
| 6 |
+
"eval_samples_per_second": 22.075,
|
| 7 |
+
"eval_steps_per_second": 1.381,
|
| 8 |
+
"eval_wer": 0.24574541380398318,
|
| 9 |
+
"train_loss": 1.788894365302016,
|
| 10 |
+
"train_runtime": 52105.5599,
|
| 11 |
+
"train_samples": 395042,
|
| 12 |
+
"train_samples_per_second": 15.163,
|
| 13 |
+
"train_steps_per_second": 0.118
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_loss": 0.26187804341316223,
|
| 4 |
+
"eval_runtime": 722.142,
|
| 5 |
+
"eval_samples": 15941,
|
| 6 |
+
"eval_samples_per_second": 22.075,
|
| 7 |
+
"eval_steps_per_second": 1.381,
|
| 8 |
+
"eval_wer": 0.24574541380398318
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 1.788894365302016,
|
| 4 |
+
"train_runtime": 52105.5599,
|
| 5 |
+
"train_samples": 395042,
|
| 6 |
+
"train_samples_per_second": 15.163,
|
| 7 |
+
"train_steps_per_second": 0.118
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,499 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.26187804341316223,
|
| 3 |
+
"best_model_checkpoint": "./checkpoint-6000",
|
| 4 |
+
"epoch": 1.9998784982382245,
|
| 5 |
+
"global_step": 6172,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 3.7499999999999997e-06,
|
| 13 |
+
"loss": 12.1043,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 7.499999999999999e-06,
|
| 19 |
+
"loss": 6.4771,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.1,
|
| 24 |
+
"learning_rate": 1.1249999999999999e-05,
|
| 25 |
+
"loss": 4.4866,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.13,
|
| 30 |
+
"learning_rate": 1.4999999999999999e-05,
|
| 31 |
+
"loss": 3.8842,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.16,
|
| 36 |
+
"learning_rate": 1.8712499999999997e-05,
|
| 37 |
+
"loss": 3.495,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.16,
|
| 42 |
+
"eval_loss": 3.3882696628570557,
|
| 43 |
+
"eval_runtime": 721.337,
|
| 44 |
+
"eval_samples_per_second": 22.099,
|
| 45 |
+
"eval_steps_per_second": 1.382,
|
| 46 |
+
"eval_wer": 1.0,
|
| 47 |
+
"step": 500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.19,
|
| 51 |
+
"learning_rate": 2.2462499999999997e-05,
|
| 52 |
+
"loss": 3.171,
|
| 53 |
+
"step": 600
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.23,
|
| 57 |
+
"learning_rate": 2.6212499999999997e-05,
|
| 58 |
+
"loss": 3.0275,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.26,
|
| 63 |
+
"learning_rate": 2.99625e-05,
|
| 64 |
+
"loss": 2.9681,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.29,
|
| 69 |
+
"learning_rate": 3.37125e-05,
|
| 70 |
+
"loss": 2.9347,
|
| 71 |
+
"step": 900
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.32,
|
| 75 |
+
"learning_rate": 3.7462499999999996e-05,
|
| 76 |
+
"loss": 2.9095,
|
| 77 |
+
"step": 1000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.32,
|
| 81 |
+
"eval_loss": 2.9152133464813232,
|
| 82 |
+
"eval_runtime": 718.1623,
|
| 83 |
+
"eval_samples_per_second": 22.197,
|
| 84 |
+
"eval_steps_per_second": 1.388,
|
| 85 |
+
"eval_wer": 0.9999871219487068,
|
| 86 |
+
"step": 1000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.36,
|
| 90 |
+
"learning_rate": 4.12125e-05,
|
| 91 |
+
"loss": 2.8888,
|
| 92 |
+
"step": 1100
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.39,
|
| 96 |
+
"learning_rate": 4.4962499999999995e-05,
|
| 97 |
+
"loss": 2.8347,
|
| 98 |
+
"step": 1200
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.42,
|
| 102 |
+
"learning_rate": 4.871249999999999e-05,
|
| 103 |
+
"loss": 2.5318,
|
| 104 |
+
"step": 1300
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.45,
|
| 108 |
+
"learning_rate": 5.2462499999999994e-05,
|
| 109 |
+
"loss": 2.0502,
|
| 110 |
+
"step": 1400
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.49,
|
| 114 |
+
"learning_rate": 5.62125e-05,
|
| 115 |
+
"loss": 1.8434,
|
| 116 |
+
"step": 1500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.49,
|
| 120 |
+
"eval_loss": 1.0473320484161377,
|
| 121 |
+
"eval_runtime": 720.1235,
|
| 122 |
+
"eval_samples_per_second": 22.136,
|
| 123 |
+
"eval_steps_per_second": 1.384,
|
| 124 |
+
"eval_wer": 0.7446153648029981,
|
| 125 |
+
"step": 1500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.52,
|
| 129 |
+
"learning_rate": 5.9962499999999994e-05,
|
| 130 |
+
"loss": 1.7339,
|
| 131 |
+
"step": 1600
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.55,
|
| 135 |
+
"learning_rate": 6.367499999999999e-05,
|
| 136 |
+
"loss": 1.6535,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.58,
|
| 141 |
+
"learning_rate": 6.7425e-05,
|
| 142 |
+
"loss": 1.5793,
|
| 143 |
+
"step": 1800
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.62,
|
| 147 |
+
"learning_rate": 7.1175e-05,
|
| 148 |
+
"loss": 1.5056,
|
| 149 |
+
"step": 1900
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.65,
|
| 153 |
+
"learning_rate": 7.492499999999999e-05,
|
| 154 |
+
"loss": 1.4298,
|
| 155 |
+
"step": 2000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.65,
|
| 159 |
+
"eval_loss": 0.5728740692138672,
|
| 160 |
+
"eval_runtime": 712.5783,
|
| 161 |
+
"eval_samples_per_second": 22.371,
|
| 162 |
+
"eval_steps_per_second": 1.399,
|
| 163 |
+
"eval_wer": 0.5129521000882147,
|
| 164 |
+
"step": 2000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.68,
|
| 168 |
+
"learning_rate": 7.325623202301054e-05,
|
| 169 |
+
"loss": 1.3592,
|
| 170 |
+
"step": 2100
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.71,
|
| 174 |
+
"learning_rate": 7.145853307766058e-05,
|
| 175 |
+
"loss": 1.2917,
|
| 176 |
+
"step": 2200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.75,
|
| 180 |
+
"learning_rate": 6.966083413231063e-05,
|
| 181 |
+
"loss": 1.2536,
|
| 182 |
+
"step": 2300
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.78,
|
| 186 |
+
"learning_rate": 6.788111217641419e-05,
|
| 187 |
+
"loss": 1.2345,
|
| 188 |
+
"step": 2400
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.81,
|
| 192 |
+
"learning_rate": 6.608341323106423e-05,
|
| 193 |
+
"loss": 1.1937,
|
| 194 |
+
"step": 2500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.81,
|
| 198 |
+
"eval_loss": 0.3795304000377655,
|
| 199 |
+
"eval_runtime": 716.4435,
|
| 200 |
+
"eval_samples_per_second": 22.25,
|
| 201 |
+
"eval_steps_per_second": 1.392,
|
| 202 |
+
"eval_wer": 0.34504806732645216,
|
| 203 |
+
"step": 2500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.84,
|
| 207 |
+
"learning_rate": 6.428571428571427e-05,
|
| 208 |
+
"loss": 1.1806,
|
| 209 |
+
"step": 2600
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.87,
|
| 213 |
+
"learning_rate": 6.248801534036433e-05,
|
| 214 |
+
"loss": 1.1651,
|
| 215 |
+
"step": 2700
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.91,
|
| 219 |
+
"learning_rate": 6.069031639501438e-05,
|
| 220 |
+
"loss": 1.1455,
|
| 221 |
+
"step": 2800
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.94,
|
| 225 |
+
"learning_rate": 5.889261744966442e-05,
|
| 226 |
+
"loss": 1.1312,
|
| 227 |
+
"step": 2900
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.97,
|
| 231 |
+
"learning_rate": 5.709491850431447e-05,
|
| 232 |
+
"loss": 1.1248,
|
| 233 |
+
"step": 3000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.97,
|
| 237 |
+
"eval_loss": 0.3320523500442505,
|
| 238 |
+
"eval_runtime": 716.2808,
|
| 239 |
+
"eval_samples_per_second": 22.255,
|
| 240 |
+
"eval_steps_per_second": 1.392,
|
| 241 |
+
"eval_wer": 0.30515830344552264,
|
| 242 |
+
"step": 3000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.0,
|
| 246 |
+
"learning_rate": 5.5297219558964525e-05,
|
| 247 |
+
"loss": 1.1017,
|
| 248 |
+
"step": 3100
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.04,
|
| 252 |
+
"learning_rate": 5.3499520613614567e-05,
|
| 253 |
+
"loss": 1.0978,
|
| 254 |
+
"step": 3200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.07,
|
| 258 |
+
"learning_rate": 5.1701821668264615e-05,
|
| 259 |
+
"loss": 1.0954,
|
| 260 |
+
"step": 3300
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.1,
|
| 264 |
+
"learning_rate": 4.990412272291467e-05,
|
| 265 |
+
"loss": 1.0867,
|
| 266 |
+
"step": 3400
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.13,
|
| 270 |
+
"learning_rate": 4.812440076701821e-05,
|
| 271 |
+
"loss": 1.0835,
|
| 272 |
+
"step": 3500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.13,
|
| 276 |
+
"eval_loss": 0.3037940561771393,
|
| 277 |
+
"eval_runtime": 714.1597,
|
| 278 |
+
"eval_samples_per_second": 22.321,
|
| 279 |
+
"eval_steps_per_second": 1.396,
|
| 280 |
+
"eval_wer": 0.2805032742445413,
|
| 281 |
+
"step": 3500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.17,
|
| 285 |
+
"learning_rate": 4.632670182166826e-05,
|
| 286 |
+
"loss": 1.0808,
|
| 287 |
+
"step": 3600
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.2,
|
| 291 |
+
"learning_rate": 4.4529002876318304e-05,
|
| 292 |
+
"loss": 1.0648,
|
| 293 |
+
"step": 3700
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.23,
|
| 297 |
+
"learning_rate": 4.273130393096836e-05,
|
| 298 |
+
"loss": 1.0541,
|
| 299 |
+
"step": 3800
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.26,
|
| 303 |
+
"learning_rate": 4.093360498561841e-05,
|
| 304 |
+
"loss": 1.0621,
|
| 305 |
+
"step": 3900
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.3,
|
| 309 |
+
"learning_rate": 3.913590604026845e-05,
|
| 310 |
+
"loss": 1.0479,
|
| 311 |
+
"step": 4000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.3,
|
| 315 |
+
"eval_loss": 0.2910499572753906,
|
| 316 |
+
"eval_runtime": 718.1665,
|
| 317 |
+
"eval_samples_per_second": 22.197,
|
| 318 |
+
"eval_steps_per_second": 1.388,
|
| 319 |
+
"eval_wer": 0.26888727197800427,
|
| 320 |
+
"step": 4000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.33,
|
| 324 |
+
"learning_rate": 3.7338207094918506e-05,
|
| 325 |
+
"loss": 1.0428,
|
| 326 |
+
"step": 4100
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.36,
|
| 330 |
+
"learning_rate": 3.555848513902205e-05,
|
| 331 |
+
"loss": 1.047,
|
| 332 |
+
"step": 4200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.39,
|
| 336 |
+
"learning_rate": 3.37607861936721e-05,
|
| 337 |
+
"loss": 1.0397,
|
| 338 |
+
"step": 4300
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.43,
|
| 342 |
+
"learning_rate": 3.1963087248322145e-05,
|
| 343 |
+
"loss": 1.0347,
|
| 344 |
+
"step": 4400
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.46,
|
| 348 |
+
"learning_rate": 3.0165388302972194e-05,
|
| 349 |
+
"loss": 1.0413,
|
| 350 |
+
"step": 4500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.46,
|
| 354 |
+
"eval_loss": 0.27976545691490173,
|
| 355 |
+
"eval_runtime": 713.7382,
|
| 356 |
+
"eval_samples_per_second": 22.335,
|
| 357 |
+
"eval_steps_per_second": 1.397,
|
| 358 |
+
"eval_wer": 0.2592995627901586,
|
| 359 |
+
"step": 4500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.49,
|
| 363 |
+
"learning_rate": 2.836768935762224e-05,
|
| 364 |
+
"loss": 1.0238,
|
| 365 |
+
"step": 4600
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.52,
|
| 369 |
+
"learning_rate": 2.656999041227229e-05,
|
| 370 |
+
"loss": 1.0269,
|
| 371 |
+
"step": 4700
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.56,
|
| 375 |
+
"learning_rate": 2.4772291466922337e-05,
|
| 376 |
+
"loss": 1.021,
|
| 377 |
+
"step": 4800
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.59,
|
| 381 |
+
"learning_rate": 2.2974592521572386e-05,
|
| 382 |
+
"loss": 1.0186,
|
| 383 |
+
"step": 4900
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.62,
|
| 387 |
+
"learning_rate": 2.1176893576222434e-05,
|
| 388 |
+
"loss": 1.014,
|
| 389 |
+
"step": 5000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.62,
|
| 393 |
+
"eval_loss": 0.27265554666519165,
|
| 394 |
+
"eval_runtime": 707.3075,
|
| 395 |
+
"eval_samples_per_second": 22.538,
|
| 396 |
+
"eval_steps_per_second": 1.41,
|
| 397 |
+
"eval_wer": 0.25117351242409997,
|
| 398 |
+
"step": 5000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.65,
|
| 402 |
+
"learning_rate": 1.9379194630872483e-05,
|
| 403 |
+
"loss": 1.0074,
|
| 404 |
+
"step": 5100
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.68,
|
| 408 |
+
"learning_rate": 1.759947267497603e-05,
|
| 409 |
+
"loss": 1.0193,
|
| 410 |
+
"step": 5200
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.72,
|
| 414 |
+
"learning_rate": 1.5801773729626078e-05,
|
| 415 |
+
"loss": 1.0044,
|
| 416 |
+
"step": 5300
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.75,
|
| 420 |
+
"learning_rate": 1.4004074784276125e-05,
|
| 421 |
+
"loss": 1.0005,
|
| 422 |
+
"step": 5400
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.78,
|
| 426 |
+
"learning_rate": 1.2206375838926173e-05,
|
| 427 |
+
"loss": 1.004,
|
| 428 |
+
"step": 5500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.78,
|
| 432 |
+
"eval_loss": 0.26460376381874084,
|
| 433 |
+
"eval_runtime": 719.6956,
|
| 434 |
+
"eval_samples_per_second": 22.15,
|
| 435 |
+
"eval_steps_per_second": 1.385,
|
| 436 |
+
"eval_wer": 0.2470782921128375,
|
| 437 |
+
"step": 5500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.81,
|
| 441 |
+
"learning_rate": 1.0408676893576222e-05,
|
| 442 |
+
"loss": 1.0048,
|
| 443 |
+
"step": 5600
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.85,
|
| 447 |
+
"learning_rate": 8.610977948226269e-06,
|
| 448 |
+
"loss": 0.9988,
|
| 449 |
+
"step": 5700
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.88,
|
| 453 |
+
"learning_rate": 6.813279002876318e-06,
|
| 454 |
+
"loss": 0.9919,
|
| 455 |
+
"step": 5800
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.91,
|
| 459 |
+
"learning_rate": 5.015580057526366e-06,
|
| 460 |
+
"loss": 0.9886,
|
| 461 |
+
"step": 5900
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.94,
|
| 465 |
+
"learning_rate": 3.217881112176414e-06,
|
| 466 |
+
"loss": 0.9949,
|
| 467 |
+
"step": 6000
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.94,
|
| 471 |
+
"eval_loss": 0.26187804341316223,
|
| 472 |
+
"eval_runtime": 717.4473,
|
| 473 |
+
"eval_samples_per_second": 22.219,
|
| 474 |
+
"eval_steps_per_second": 1.39,
|
| 475 |
+
"eval_wer": 0.24574541380398318,
|
| 476 |
+
"step": 6000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.98,
|
| 480 |
+
"learning_rate": 1.4201821668264622e-06,
|
| 481 |
+
"loss": 0.9931,
|
| 482 |
+
"step": 6100
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.0,
|
| 486 |
+
"step": 6172,
|
| 487 |
+
"total_flos": 1.1573983785360925e+20,
|
| 488 |
+
"train_loss": 1.788894365302016,
|
| 489 |
+
"train_runtime": 52105.5599,
|
| 490 |
+
"train_samples_per_second": 15.163,
|
| 491 |
+
"train_steps_per_second": 0.118
|
| 492 |
+
}
|
| 493 |
+
],
|
| 494 |
+
"max_steps": 6172,
|
| 495 |
+
"num_train_epochs": 2,
|
| 496 |
+
"total_flos": 1.1573983785360925e+20,
|
| 497 |
+
"trial_name": null,
|
| 498 |
+
"trial_params": null
|
| 499 |
+
}
|