File size: 6,643 Bytes
cb72cb1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 |
{
"best_metric": 0.24462078511714935,
"best_model_checkpoint": "/scratch/skscla001/speech/results/xls-r-1b-bemgen-combined-model/checkpoint-1500",
"epoch": 3.3871543264942017,
"eval_steps": 100,
"global_step": 1900,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1784121320249777,
"eval_loss": 3.441302537918091,
"eval_runtime": 39.9204,
"eval_samples_per_second": 13.552,
"eval_steps_per_second": 3.407,
"eval_wer": 1.0002904865649964,
"step": 100
},
{
"epoch": 0.3568242640499554,
"eval_loss": 2.914942979812622,
"eval_runtime": 39.4152,
"eval_samples_per_second": 13.726,
"eval_steps_per_second": 3.45,
"eval_wer": 1.0,
"step": 200
},
{
"epoch": 0.5352363960749331,
"eval_loss": 0.7767665386199951,
"eval_runtime": 39.9772,
"eval_samples_per_second": 13.533,
"eval_steps_per_second": 3.402,
"eval_wer": 0.9234567901234568,
"step": 300
},
{
"epoch": 0.7136485280999108,
"eval_loss": 0.605692446231842,
"eval_runtime": 39.422,
"eval_samples_per_second": 13.723,
"eval_steps_per_second": 3.45,
"eval_wer": 0.904720406681191,
"step": 400
},
{
"epoch": 0.8920606601248885,
"grad_norm": 3.2083628177642822,
"learning_rate": 2.976e-05,
"loss": 5.3372,
"step": 500
},
{
"epoch": 0.8920606601248885,
"eval_loss": 0.43167629837989807,
"eval_runtime": 39.6193,
"eval_samples_per_second": 13.655,
"eval_steps_per_second": 3.433,
"eval_wer": 0.6720406681190995,
"step": 500
},
{
"epoch": 1.0695807314897412,
"eval_loss": 0.3997327983379364,
"eval_runtime": 39.7537,
"eval_samples_per_second": 13.609,
"eval_steps_per_second": 3.421,
"eval_wer": 0.6704429920116195,
"step": 600
},
{
"epoch": 1.247992863514719,
"eval_loss": 0.3610936999320984,
"eval_runtime": 39.4379,
"eval_samples_per_second": 13.718,
"eval_steps_per_second": 3.448,
"eval_wer": 0.6405228758169934,
"step": 700
},
{
"epoch": 1.4264049955396967,
"eval_loss": 0.34406763315200806,
"eval_runtime": 39.4181,
"eval_samples_per_second": 13.725,
"eval_steps_per_second": 3.45,
"eval_wer": 0.5603485838779957,
"step": 800
},
{
"epoch": 1.6048171275646745,
"eval_loss": 0.2945486903190613,
"eval_runtime": 39.8239,
"eval_samples_per_second": 13.585,
"eval_steps_per_second": 3.415,
"eval_wer": 0.49135802469135803,
"step": 900
},
{
"epoch": 1.783229259589652,
"grad_norm": 3.3745229244232178,
"learning_rate": 2.908711656441718e-05,
"loss": 0.6459,
"step": 1000
},
{
"epoch": 1.783229259589652,
"eval_loss": 0.3041314482688904,
"eval_runtime": 39.339,
"eval_samples_per_second": 13.752,
"eval_steps_per_second": 3.457,
"eval_wer": 0.4923747276688453,
"step": 1000
},
{
"epoch": 1.9616413916146298,
"eval_loss": 0.2805267870426178,
"eval_runtime": 39.2725,
"eval_samples_per_second": 13.776,
"eval_steps_per_second": 3.463,
"eval_wer": 0.46811909949164854,
"step": 1100
},
{
"epoch": 2.1391614629794824,
"eval_loss": 0.2774401605129242,
"eval_runtime": 39.4398,
"eval_samples_per_second": 13.717,
"eval_steps_per_second": 3.448,
"eval_wer": 0.5108206245461148,
"step": 1200
},
{
"epoch": 2.3175735950044603,
"eval_loss": 0.26826903223991394,
"eval_runtime": 39.6616,
"eval_samples_per_second": 13.64,
"eval_steps_per_second": 3.429,
"eval_wer": 0.42541757443718226,
"step": 1300
},
{
"epoch": 2.495985727029438,
"eval_loss": 0.2643994987010956,
"eval_runtime": 39.3737,
"eval_samples_per_second": 13.74,
"eval_steps_per_second": 3.454,
"eval_wer": 0.4381989832970225,
"step": 1400
},
{
"epoch": 2.674397859054416,
"grad_norm": 2.350830554962158,
"learning_rate": 2.816687116564417e-05,
"loss": 0.4599,
"step": 1500
},
{
"epoch": 2.674397859054416,
"eval_loss": 0.24462078511714935,
"eval_runtime": 39.5477,
"eval_samples_per_second": 13.68,
"eval_steps_per_second": 3.439,
"eval_wer": 0.4142338416848221,
"step": 1500
},
{
"epoch": 2.8528099910793934,
"eval_loss": 0.24734348058700562,
"eval_runtime": 39.4462,
"eval_samples_per_second": 13.715,
"eval_steps_per_second": 3.448,
"eval_wer": 0.4117647058823529,
"step": 1600
},
{
"epoch": 3.0303300624442464,
"eval_loss": 0.24915921688079834,
"eval_runtime": 39.9106,
"eval_samples_per_second": 13.555,
"eval_steps_per_second": 3.408,
"eval_wer": 0.396078431372549,
"step": 1700
},
{
"epoch": 3.208742194469224,
"eval_loss": 0.24668627977371216,
"eval_runtime": 39.4647,
"eval_samples_per_second": 13.708,
"eval_steps_per_second": 3.446,
"eval_wer": 0.40697167755991287,
"step": 1800
},
{
"epoch": 3.3871543264942017,
"eval_loss": 0.25092557072639465,
"eval_runtime": 39.3684,
"eval_samples_per_second": 13.742,
"eval_steps_per_second": 3.455,
"eval_wer": 0.39230210602759624,
"step": 1900
},
{
"epoch": 3.3871543264942017,
"step": 1900,
"total_flos": 1.1803978917941375e+19,
"train_loss": 1.775066086618524,
"train_runtime": 3182.4103,
"train_samples_per_second": 42.251,
"train_steps_per_second": 5.279
}
],
"logging_steps": 500,
"max_steps": 16800,
"num_input_tokens_seen": 0,
"num_train_epochs": 30,
"save_steps": 400,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 4,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 1
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.1803978917941375e+19,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|