File size: 5,120 Bytes
a6b523e |
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 |
{
"best_metric": 63.60403082394783,
"best_model_checkpoint": "./whisper-tiny-hi2_test/checkpoint-200",
"epoch": 6.34375,
"eval_steps": 40,
"global_step": 203,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.625,
"grad_norm": 10.62358283996582,
"learning_rate": 1e-05,
"loss": 2.3669,
"step": 20
},
{
"epoch": 1.25,
"grad_norm": 7.5668721199035645,
"learning_rate": 1e-05,
"loss": 1.1887,
"step": 40
},
{
"epoch": 1.25,
"eval_loss": 0.9953901171684265,
"eval_runtime": 571.1605,
"eval_samples_per_second": 1.751,
"eval_steps_per_second": 1.751,
"eval_wer": 87.29782369379288,
"step": 40
},
{
"epoch": 1.875,
"grad_norm": 6.932765960693359,
"learning_rate": 1e-05,
"loss": 0.855,
"step": 60
},
{
"epoch": 2.5,
"grad_norm": 6.589940547943115,
"learning_rate": 1e-05,
"loss": 0.6663,
"step": 80
},
{
"epoch": 2.5,
"eval_loss": 0.6780964136123657,
"eval_runtime": 554.1893,
"eval_samples_per_second": 1.804,
"eval_steps_per_second": 1.804,
"eval_wer": 73.29155728681515,
"step": 80
},
{
"epoch": 3.125,
"grad_norm": 6.102142810821533,
"learning_rate": 1e-05,
"loss": 0.5761,
"step": 100
},
{
"epoch": 3.75,
"grad_norm": 5.4204583168029785,
"learning_rate": 1e-05,
"loss": 0.5053,
"step": 120
},
{
"epoch": 3.75,
"eval_loss": 0.5857690572738647,
"eval_runtime": 567.8481,
"eval_samples_per_second": 1.761,
"eval_steps_per_second": 1.761,
"eval_wer": 66.22914726056398,
"step": 120
},
{
"epoch": 4.375,
"grad_norm": 4.851945400238037,
"learning_rate": 1e-05,
"loss": 0.4369,
"step": 140
},
{
"epoch": 5.0,
"grad_norm": 9.788898468017578,
"learning_rate": 1e-05,
"loss": 0.406,
"step": 160
},
{
"epoch": 5.0,
"eval_loss": 0.5440137982368469,
"eval_runtime": 560.2795,
"eval_samples_per_second": 1.785,
"eval_steps_per_second": 1.785,
"eval_wer": 66.13599796765179,
"step": 160
},
{
"epoch": 5.625,
"grad_norm": 4.664266109466553,
"learning_rate": 1e-05,
"loss": 0.356,
"step": 180
},
{
"epoch": 6.25,
"grad_norm": 4.6183037757873535,
"learning_rate": 1e-05,
"loss": 0.3236,
"step": 200
},
{
"epoch": 6.25,
"eval_loss": 0.5290657877922058,
"eval_runtime": 553.81,
"eval_samples_per_second": 1.806,
"eval_steps_per_second": 1.806,
"eval_wer": 63.60403082394783,
"step": 200
},
{
"epoch": 6.25,
"step": 200,
"total_flos": 1.5401574531072e+17,
"train_loss": 0.7680861353874207,
"train_runtime": 3626.9505,
"train_samples_per_second": 1.765,
"train_steps_per_second": 0.055
},
{
"epoch": 6.28125,
"step": 201,
"total_flos": 1.5480354963456e+17,
"train_loss": 0.002653346132876268,
"train_runtime": 7.7901,
"train_samples_per_second": 821.558,
"train_steps_per_second": 25.674
},
{
"epoch": 6.28125,
"eval_loss": 0.5290657877922058,
"eval_runtime": 551.3177,
"eval_samples_per_second": 1.814,
"eval_steps_per_second": 1.814,
"eval_wer": 63.60403082394783,
"step": 201
},
{
"epoch": 6.3125,
"step": 202,
"total_flos": 1.555913539584e+17,
"train_loss": 0.002912604867821873,
"train_runtime": 7.6856,
"train_samples_per_second": 832.727,
"train_steps_per_second": 26.023
},
{
"epoch": 6.3125,
"eval_loss": 0.5290657877922058,
"eval_runtime": 543.8685,
"eval_samples_per_second": 1.839,
"eval_steps_per_second": 1.839,
"eval_wer": 63.60403082394783,
"step": 202
},
{
"epoch": 6.34375,
"step": 203,
"total_flos": 1.5637915828224e+17,
"train_loss": 0.0022250449128926094,
"train_runtime": 7.6745,
"train_samples_per_second": 833.935,
"train_steps_per_second": 26.06
},
{
"epoch": 6.34375,
"eval_loss": 0.5290657877922058,
"eval_runtime": 542.3404,
"eval_samples_per_second": 1.844,
"eval_steps_per_second": 1.844,
"eval_wer": 63.60403082394783,
"step": 203
}
],
"logging_steps": 20,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 7,
"save_steps": 40,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.5637915828224e+17,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|