File size: 5,756 Bytes
90f6285 1b9db6b fe60359 90f6285 fe60359 90f6285 33f884e cd4c54b 2b2d81a 85c319e 7a9c692 305f1b2 d1db2b9 5b3c323 a6d5803 32a485a a5b7a27 f6cd8b9 451cc14 75ac716 bbb4d0f 1b9db6b d050c93 fb90102 fe60359 90f6285 33f884e 90f6285 fe60359 90f6285 |
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 |
{
"best_metric": 0.9877104163169861,
"best_model_checkpoint": "./opt_trained/checkpoint-3216",
"epoch": 19.0,
"eval_steps": 500,
"global_step": 3819,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"eval_loss": 1.0177865028381348,
"eval_runtime": 77.0752,
"eval_samples_per_second": 37.055,
"eval_steps_per_second": 9.264,
"step": 201
},
{
"epoch": 2.0,
"eval_loss": 1.0106526613235474,
"eval_runtime": 77.338,
"eval_samples_per_second": 36.929,
"eval_steps_per_second": 9.232,
"step": 402
},
{
"epoch": 2.488169364881694,
"grad_norm": 1.6413393020629883,
"learning_rate": 0.0003501,
"loss": 1.0175,
"step": 500
},
{
"epoch": 3.0,
"eval_loss": 1.0082063674926758,
"eval_runtime": 77.1371,
"eval_samples_per_second": 37.025,
"eval_steps_per_second": 9.256,
"step": 603
},
{
"epoch": 4.0,
"eval_loss": 1.0058513879776,
"eval_runtime": 76.7488,
"eval_samples_per_second": 37.212,
"eval_steps_per_second": 9.303,
"step": 804
},
{
"epoch": 4.976338729763388,
"grad_norm": 1.9620177745819092,
"learning_rate": 0.00030010000000000003,
"loss": 0.9962,
"step": 1000
},
{
"epoch": 5.0,
"eval_loss": 1.0030816793441772,
"eval_runtime": 76.8119,
"eval_samples_per_second": 37.182,
"eval_steps_per_second": 9.295,
"step": 1005
},
{
"epoch": 6.0,
"eval_loss": 1.0030088424682617,
"eval_runtime": 76.8319,
"eval_samples_per_second": 37.172,
"eval_steps_per_second": 9.293,
"step": 1206
},
{
"epoch": 7.0,
"eval_loss": 0.9996200203895569,
"eval_runtime": 77.0477,
"eval_samples_per_second": 37.068,
"eval_steps_per_second": 9.267,
"step": 1407
},
{
"epoch": 7.463262764632628,
"grad_norm": 1.7347174882888794,
"learning_rate": 0.0002501,
"loss": 0.9871,
"step": 1500
},
{
"epoch": 8.0,
"eval_loss": 0.9977834820747375,
"eval_runtime": 76.773,
"eval_samples_per_second": 37.201,
"eval_steps_per_second": 9.3,
"step": 1608
},
{
"epoch": 9.0,
"eval_loss": 0.9954783320426941,
"eval_runtime": 76.956,
"eval_samples_per_second": 37.112,
"eval_steps_per_second": 9.278,
"step": 1809
},
{
"epoch": 9.951432129514322,
"grad_norm": 1.4501839876174927,
"learning_rate": 0.0002001,
"loss": 0.9774,
"step": 2000
},
{
"epoch": 10.0,
"eval_loss": 0.995110273361206,
"eval_runtime": 77.0387,
"eval_samples_per_second": 37.072,
"eval_steps_per_second": 9.268,
"step": 2010
},
{
"epoch": 11.0,
"eval_loss": 0.9924370050430298,
"eval_runtime": 77.2049,
"eval_samples_per_second": 36.992,
"eval_steps_per_second": 9.248,
"step": 2211
},
{
"epoch": 12.0,
"eval_loss": 0.9905564785003662,
"eval_runtime": 77.3311,
"eval_samples_per_second": 36.932,
"eval_steps_per_second": 9.233,
"step": 2412
},
{
"epoch": 12.438356164383562,
"grad_norm": 1.4806139469146729,
"learning_rate": 0.0001501,
"loss": 0.9638,
"step": 2500
},
{
"epoch": 13.0,
"eval_loss": 0.990676999092102,
"eval_runtime": 77.0729,
"eval_samples_per_second": 37.056,
"eval_steps_per_second": 9.264,
"step": 2613
},
{
"epoch": 14.0,
"eval_loss": 0.988075315952301,
"eval_runtime": 77.0166,
"eval_samples_per_second": 37.083,
"eval_steps_per_second": 9.271,
"step": 2814
},
{
"epoch": 14.926525529265255,
"grad_norm": 1.8893911838531494,
"learning_rate": 0.0001001,
"loss": 0.9428,
"step": 3000
},
{
"epoch": 15.0,
"eval_loss": 0.9882552027702332,
"eval_runtime": 77.0864,
"eval_samples_per_second": 37.049,
"eval_steps_per_second": 9.262,
"step": 3015
},
{
"epoch": 16.0,
"eval_loss": 0.9877104163169861,
"eval_runtime": 77.0222,
"eval_samples_per_second": 37.08,
"eval_steps_per_second": 9.27,
"step": 3216
},
{
"epoch": 17.0,
"eval_loss": 0.9905799031257629,
"eval_runtime": 76.8333,
"eval_samples_per_second": 37.171,
"eval_steps_per_second": 9.293,
"step": 3417
},
{
"epoch": 17.413449564134496,
"grad_norm": 1.899855136871338,
"learning_rate": 5.0100000000000005e-05,
"loss": 0.9154,
"step": 3500
},
{
"epoch": 18.0,
"eval_loss": 0.9950315952301025,
"eval_runtime": 76.8254,
"eval_samples_per_second": 37.175,
"eval_steps_per_second": 9.294,
"step": 3618
},
{
"epoch": 19.0,
"eval_loss": 0.9973178505897522,
"eval_runtime": 77.4812,
"eval_samples_per_second": 36.861,
"eval_steps_per_second": 9.215,
"step": 3819
}
],
"logging_steps": 500,
"max_steps": 4000,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"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": 1.2856067083008e+17,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|