File size: 5,022 Bytes
7dbd02a | 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 | {
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.433617539585871,
"eval_steps": 100,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.243605359317905,
"grad_norm": 33.11063766479492,
"learning_rate": 4.8844282238442824e-05,
"loss": 10.7343,
"step": 100
},
{
"epoch": 0.243605359317905,
"eval_loss": 4.385446548461914,
"eval_runtime": 206.0799,
"eval_samples_per_second": 7.992,
"eval_steps_per_second": 1.0,
"eval_wer": 1.0,
"step": 100
},
{
"epoch": 0.48721071863581,
"grad_norm": 2.508547067642212,
"learning_rate": 4.762773722627738e-05,
"loss": 3.1325,
"step": 200
},
{
"epoch": 0.48721071863581,
"eval_loss": 2.1581695079803467,
"eval_runtime": 206.4525,
"eval_samples_per_second": 7.978,
"eval_steps_per_second": 0.998,
"eval_wer": 0.9690996270644646,
"step": 200
},
{
"epoch": 0.730816077953715,
"grad_norm": 1.2504737377166748,
"learning_rate": 4.641119221411192e-05,
"loss": 1.6166,
"step": 300
},
{
"epoch": 0.730816077953715,
"eval_loss": 1.1347323656082153,
"eval_runtime": 206.3117,
"eval_samples_per_second": 7.983,
"eval_steps_per_second": 0.998,
"eval_wer": 0.7188184455099745,
"step": 300
},
{
"epoch": 0.97442143727162,
"grad_norm": 1.3984403610229492,
"learning_rate": 4.520681265206813e-05,
"loss": 1.1808,
"step": 400
},
{
"epoch": 0.97442143727162,
"eval_loss": 0.9792075157165527,
"eval_runtime": 206.2345,
"eval_samples_per_second": 7.986,
"eval_steps_per_second": 0.999,
"eval_wer": 0.6746581424258569,
"step": 400
},
{
"epoch": 1.2168087697929355,
"grad_norm": 10.769020080566406,
"learning_rate": 4.3990267639902676e-05,
"loss": 1.0459,
"step": 500
},
{
"epoch": 1.2168087697929355,
"eval_loss": 0.9049620032310486,
"eval_runtime": 208.2322,
"eval_samples_per_second": 7.909,
"eval_steps_per_second": 0.989,
"eval_wer": 0.6494405966968567,
"step": 500
},
{
"epoch": 1.4604141291108403,
"grad_norm": 0.8941505551338196,
"learning_rate": 4.277372262773723e-05,
"loss": 1.0317,
"step": 600
},
{
"epoch": 1.4604141291108403,
"eval_loss": 0.8543379306793213,
"eval_runtime": 205.6459,
"eval_samples_per_second": 8.009,
"eval_steps_per_second": 1.002,
"eval_wer": 0.6338128218788848,
"step": 600
},
{
"epoch": 1.7040194884287454,
"grad_norm": 0.9768113493919373,
"learning_rate": 4.1569343065693435e-05,
"loss": 0.9836,
"step": 700
},
{
"epoch": 1.7040194884287454,
"eval_loss": 0.8191400766372681,
"eval_runtime": 207.1525,
"eval_samples_per_second": 7.951,
"eval_steps_per_second": 0.994,
"eval_wer": 0.6251701888356124,
"step": 700
},
{
"epoch": 1.9476248477466505,
"grad_norm": 0.9090480208396912,
"learning_rate": 4.035279805352798e-05,
"loss": 0.9567,
"step": 800
},
{
"epoch": 1.9476248477466505,
"eval_loss": 0.7955169081687927,
"eval_runtime": 206.8205,
"eval_samples_per_second": 7.963,
"eval_steps_per_second": 0.996,
"eval_wer": 0.6124430237376428,
"step": 800
},
{
"epoch": 2.1900121802679657,
"grad_norm": 0.6563196778297424,
"learning_rate": 3.913625304136253e-05,
"loss": 0.9354,
"step": 900
},
{
"epoch": 2.1900121802679657,
"eval_loss": 0.7705180644989014,
"eval_runtime": 206.4429,
"eval_samples_per_second": 7.978,
"eval_steps_per_second": 0.998,
"eval_wer": 0.6046291363286569,
"step": 900
},
{
"epoch": 2.433617539585871,
"grad_norm": 0.8123560547828674,
"learning_rate": 3.791970802919708e-05,
"loss": 0.9037,
"step": 1000
},
{
"epoch": 2.433617539585871,
"eval_loss": 0.75263512134552,
"eval_runtime": 206.6571,
"eval_samples_per_second": 7.97,
"eval_steps_per_second": 0.997,
"eval_wer": 0.5982359557213047,
"step": 1000
}
],
"logging_steps": 100,
"max_steps": 4110,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.4109000983694397e+19,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|