File size: 5,750 Bytes
e0267f4 |
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 |
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 1000,
"global_step": 11006,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00018171906232963838,
"grad_norm": 7.594760894775391,
"learning_rate": 0.0,
"loss": 3.1229,
"step": 1
},
{
"epoch": 0.1817190623296384,
"grad_norm": 6.193614959716797,
"learning_rate": 9.076867163365438e-06,
"loss": 2.6857,
"step": 1000
},
{
"epoch": 0.1817190623296384,
"eval_cosine_accuracy": 0.9440529942512512,
"eval_loss": 1.6310006380081177,
"eval_runtime": 21.3914,
"eval_samples_per_second": 444.525,
"eval_steps_per_second": 3.506,
"step": 1000
},
{
"epoch": 0.3634381246592768,
"grad_norm": 5.20527458190918,
"learning_rate": 1.8153734326730876e-05,
"loss": 2.0541,
"step": 2000
},
{
"epoch": 0.3634381246592768,
"eval_cosine_accuracy": 0.9472079277038574,
"eval_loss": 1.544768214225769,
"eval_runtime": 21.6963,
"eval_samples_per_second": 438.277,
"eval_steps_per_second": 3.457,
"step": 2000
},
{
"epoch": 0.5451571869889151,
"grad_norm": 4.887779712677002,
"learning_rate": 2.7239687443212796e-05,
"loss": 1.7335,
"step": 3000
},
{
"epoch": 0.5451571869889151,
"eval_cosine_accuracy": 0.948469877243042,
"eval_loss": 1.5235735177993774,
"eval_runtime": 21.262,
"eval_samples_per_second": 447.229,
"eval_steps_per_second": 3.527,
"step": 3000
},
{
"epoch": 0.7268762493185535,
"grad_norm": 6.290886878967285,
"learning_rate": 3.632564055969471e-05,
"loss": 1.2495,
"step": 4000
},
{
"epoch": 0.7268762493185535,
"eval_cosine_accuracy": 0.9433168768882751,
"eval_loss": 1.5551835298538208,
"eval_runtime": 21.377,
"eval_samples_per_second": 444.824,
"eval_steps_per_second": 3.508,
"step": 4000
},
{
"epoch": 0.9085953116481919,
"grad_norm": 8.564718246459961,
"learning_rate": 4.5411593676176635e-05,
"loss": 0.813,
"step": 5000
},
{
"epoch": 0.9085953116481919,
"eval_cosine_accuracy": 0.9472079277038574,
"eval_loss": 1.5794354677200317,
"eval_runtime": 21.6842,
"eval_samples_per_second": 438.522,
"eval_steps_per_second": 3.459,
"step": 5000
},
{
"epoch": 1.0903143739778303,
"grad_norm": 5.288447856903076,
"learning_rate": 4.8875613301835365e-05,
"loss": 1.0512,
"step": 6000
},
{
"epoch": 1.0903143739778303,
"eval_cosine_accuracy": 0.9566726088523865,
"eval_loss": 1.4543931484222412,
"eval_runtime": 23.0837,
"eval_samples_per_second": 411.936,
"eval_steps_per_second": 3.249,
"step": 6000
},
{
"epoch": 1.2720334363074688,
"grad_norm": 4.507662296295166,
"learning_rate": 4.660412502271488e-05,
"loss": 1.2912,
"step": 7000
},
{
"epoch": 1.2720334363074688,
"eval_cosine_accuracy": 0.9562519788742065,
"eval_loss": 1.4492090940475464,
"eval_runtime": 21.5059,
"eval_samples_per_second": 442.159,
"eval_steps_per_second": 3.487,
"step": 7000
},
{
"epoch": 1.453752498637107,
"grad_norm": 4.300741672515869,
"learning_rate": 4.433263674359441e-05,
"loss": 1.1994,
"step": 8000
},
{
"epoch": 1.453752498637107,
"eval_cosine_accuracy": 0.956777811050415,
"eval_loss": 1.4519122838974,
"eval_runtime": 21.4819,
"eval_samples_per_second": 442.651,
"eval_steps_per_second": 3.491,
"step": 8000
},
{
"epoch": 1.6354715609667454,
"grad_norm": 4.133264064788818,
"learning_rate": 4.206569144103217e-05,
"loss": 1.0662,
"step": 9000
},
{
"epoch": 1.6354715609667454,
"eval_cosine_accuracy": 0.9544641971588135,
"eval_loss": 1.4635158777236938,
"eval_runtime": 21.6809,
"eval_samples_per_second": 438.588,
"eval_steps_per_second": 3.459,
"step": 9000
},
{
"epoch": 1.817190623296384,
"grad_norm": 5.683165073394775,
"learning_rate": 3.9794203161911684e-05,
"loss": 0.6724,
"step": 10000
},
{
"epoch": 1.817190623296384,
"eval_cosine_accuracy": 0.9454201459884644,
"eval_loss": 1.571725845336914,
"eval_runtime": 21.3873,
"eval_samples_per_second": 444.61,
"eval_steps_per_second": 3.507,
"step": 10000
},
{
"epoch": 1.998909685626022,
"grad_norm": 7.759120464324951,
"learning_rate": 3.752498637107033e-05,
"loss": 0.4761,
"step": 11000
},
{
"epoch": 1.998909685626022,
"eval_cosine_accuracy": 0.9502576589584351,
"eval_loss": 1.550882339477539,
"eval_runtime": 22.2267,
"eval_samples_per_second": 427.818,
"eval_steps_per_second": 3.374,
"step": 11000
}
],
"logging_steps": 1000,
"max_steps": 27515,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"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": 0.0,
"train_batch_size": 128,
"trial_name": null,
"trial_params": null
}
|