File size: 4,246 Bytes
5561a29 |
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 |
{
"best_metric": 132.4391645909178,
"best_model_checkpoint": "./whisper-tiny-ha/checkpoint-500",
"epoch": 3.1847133757961785,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1592356687898089,
"grad_norm": 30.159414291381836,
"learning_rate": 4.2000000000000004e-06,
"loss": 3.418,
"step": 25
},
{
"epoch": 0.3184713375796178,
"grad_norm": 21.70500373840332,
"learning_rate": 9.200000000000002e-06,
"loss": 2.553,
"step": 50
},
{
"epoch": 0.47770700636942676,
"grad_norm": 18.039278030395508,
"learning_rate": 1e-05,
"loss": 2.3832,
"step": 75
},
{
"epoch": 0.6369426751592356,
"grad_norm": 18.557083129882812,
"learning_rate": 1e-05,
"loss": 2.3115,
"step": 100
},
{
"epoch": 0.7961783439490446,
"grad_norm": 16.37763023376465,
"learning_rate": 1e-05,
"loss": 2.2126,
"step": 125
},
{
"epoch": 0.9554140127388535,
"grad_norm": 18.549989700317383,
"learning_rate": 1e-05,
"loss": 2.1729,
"step": 150
},
{
"epoch": 1.1146496815286624,
"grad_norm": 16.92412757873535,
"learning_rate": 1e-05,
"loss": 1.9976,
"step": 175
},
{
"epoch": 1.2738853503184713,
"grad_norm": 17.25154685974121,
"learning_rate": 1e-05,
"loss": 1.8783,
"step": 200
},
{
"epoch": 1.4331210191082802,
"grad_norm": 16.648714065551758,
"learning_rate": 1e-05,
"loss": 1.902,
"step": 225
},
{
"epoch": 1.5923566878980893,
"grad_norm": 16.841991424560547,
"learning_rate": 1e-05,
"loss": 1.925,
"step": 250
},
{
"epoch": 1.7515923566878981,
"grad_norm": 19.01357650756836,
"learning_rate": 1e-05,
"loss": 1.8552,
"step": 275
},
{
"epoch": 1.910828025477707,
"grad_norm": 16.73857879638672,
"learning_rate": 1e-05,
"loss": 1.8734,
"step": 300
},
{
"epoch": 2.070063694267516,
"grad_norm": 16.232080459594727,
"learning_rate": 1e-05,
"loss": 1.756,
"step": 325
},
{
"epoch": 2.229299363057325,
"grad_norm": 16.035682678222656,
"learning_rate": 1e-05,
"loss": 1.584,
"step": 350
},
{
"epoch": 2.388535031847134,
"grad_norm": 15.77041244506836,
"learning_rate": 1e-05,
"loss": 1.5446,
"step": 375
},
{
"epoch": 2.5477707006369426,
"grad_norm": 17.873939514160156,
"learning_rate": 1e-05,
"loss": 1.5419,
"step": 400
},
{
"epoch": 2.7070063694267517,
"grad_norm": 16.445964813232422,
"learning_rate": 1e-05,
"loss": 1.6085,
"step": 425
},
{
"epoch": 2.8662420382165603,
"grad_norm": 16.27969741821289,
"learning_rate": 1e-05,
"loss": 1.6325,
"step": 450
},
{
"epoch": 3.0254777070063694,
"grad_norm": 15.765183448791504,
"learning_rate": 1e-05,
"loss": 1.4205,
"step": 475
},
{
"epoch": 3.1847133757961785,
"grad_norm": 14.563206672668457,
"learning_rate": 1e-05,
"loss": 1.3176,
"step": 500
},
{
"epoch": 3.1847133757961785,
"eval_loss": 2.107278823852539,
"eval_runtime": 154.4492,
"eval_samples_per_second": 4.273,
"eval_steps_per_second": 0.272,
"eval_wer": 132.4391645909178,
"eval_wer_ortho": 133.80859375,
"step": 500
}
],
"logging_steps": 25,
"max_steps": 2355,
"num_input_tokens_seen": 0,
"num_train_epochs": 15,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.9665565433856e+17,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|