File size: 5,037 Bytes
be570c1 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.5673940949935816,
"eval_steps": 250,
"global_step": 2750,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2333994631812347,
"grad_norm": 1.2788289785385132,
"learning_rate": 9.992757124875143e-05,
"loss": 0.3573,
"step": 250
},
{
"epoch": 0.2333994631812347,
"eval_loss": 0.18718622624874115,
"eval_runtime": 18.4863,
"eval_samples_per_second": 4.706,
"eval_steps_per_second": 4.706,
"step": 250
},
{
"epoch": 0.4667989263624694,
"grad_norm": 1.7301123142242432,
"learning_rate": 9.895259863857224e-05,
"loss": 0.1155,
"step": 500
},
{
"epoch": 0.4667989263624694,
"eval_loss": 0.11222057044506073,
"eval_runtime": 18.4689,
"eval_samples_per_second": 4.711,
"eval_steps_per_second": 4.711,
"step": 500
},
{
"epoch": 0.7001983895437041,
"grad_norm": 0.40849488973617554,
"learning_rate": 9.686044398977847e-05,
"loss": 0.079,
"step": 750
},
{
"epoch": 0.7001983895437041,
"eval_loss": 0.0827888771891594,
"eval_runtime": 18.4255,
"eval_samples_per_second": 4.722,
"eval_steps_per_second": 4.722,
"step": 750
},
{
"epoch": 0.9335978527249388,
"grad_norm": 0.27379560470581055,
"learning_rate": 9.369885385026829e-05,
"loss": 0.0672,
"step": 1000
},
{
"epoch": 0.9335978527249388,
"eval_loss": 0.07405883818864822,
"eval_runtime": 18.0866,
"eval_samples_per_second": 4.81,
"eval_steps_per_second": 4.81,
"step": 1000
},
{
"epoch": 1.1669973159061735,
"grad_norm": 0.15424582362174988,
"learning_rate": 8.953998111520053e-05,
"loss": 0.0555,
"step": 1250
},
{
"epoch": 1.1669973159061735,
"eval_loss": 0.07201890647411346,
"eval_runtime": 18.1777,
"eval_samples_per_second": 4.786,
"eval_steps_per_second": 4.786,
"step": 1250
},
{
"epoch": 1.4003967790874081,
"grad_norm": 0.1671038419008255,
"learning_rate": 8.447873837450339e-05,
"loss": 0.055,
"step": 1500
},
{
"epoch": 1.4003967790874081,
"eval_loss": 0.07005530595779419,
"eval_runtime": 18.0977,
"eval_samples_per_second": 4.807,
"eval_steps_per_second": 4.807,
"step": 1500
},
{
"epoch": 1.6337962422686427,
"grad_norm": 0.12481052428483963,
"learning_rate": 7.863063184521596e-05,
"loss": 0.053,
"step": 1750
},
{
"epoch": 1.6337962422686427,
"eval_loss": 0.06806331127882004,
"eval_runtime": 18.1718,
"eval_samples_per_second": 4.788,
"eval_steps_per_second": 4.788,
"step": 1750
},
{
"epoch": 1.8671957054498773,
"grad_norm": 0.14744804799556732,
"learning_rate": 7.212912532203201e-05,
"loss": 0.0526,
"step": 2000
},
{
"epoch": 1.8671957054498773,
"eval_loss": 0.06636130809783936,
"eval_runtime": 18.0865,
"eval_samples_per_second": 4.81,
"eval_steps_per_second": 4.81,
"step": 2000
},
{
"epoch": 2.100595168631112,
"grad_norm": 0.07688289880752563,
"learning_rate": 6.51225943052036e-05,
"loss": 0.047,
"step": 2250
},
{
"epoch": 2.100595168631112,
"eval_loss": 0.06469345092773438,
"eval_runtime": 18.051,
"eval_samples_per_second": 4.82,
"eval_steps_per_second": 4.82,
"step": 2250
},
{
"epoch": 2.333994631812347,
"grad_norm": 0.09491775184869766,
"learning_rate": 5.777093981781615e-05,
"loss": 0.0406,
"step": 2500
},
{
"epoch": 2.333994631812347,
"eval_loss": 0.06455763429403305,
"eval_runtime": 18.0482,
"eval_samples_per_second": 4.82,
"eval_steps_per_second": 4.82,
"step": 2500
},
{
"epoch": 2.5673940949935816,
"grad_norm": 0.09282498061656952,
"learning_rate": 5.024193919091694e-05,
"loss": 0.0411,
"step": 2750
},
{
"epoch": 2.5673940949935816,
"eval_loss": 0.062036558985710144,
"eval_runtime": 18.1073,
"eval_samples_per_second": 4.805,
"eval_steps_per_second": 4.805,
"step": 2750
}
],
"logging_steps": 250,
"max_steps": 5355,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 250,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 9.966518159792947e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|