File size: 5,889 Bytes
dca120d |
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 |
{
"best_metric": 0.9107733964920044,
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l17-l/checkpoint-6500",
"epoch": 0.693259385665529,
"eval_steps": 500,
"global_step": 6500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05332764505119454,
"grad_norm": 246.1711883544922,
"learning_rate": 9.822241183162683e-08,
"loss": 0.4515,
"step": 500
},
{
"epoch": 0.05332764505119454,
"eval_loss": 1.3850886821746826,
"eval_runtime": 63.8439,
"eval_samples_per_second": 15.46,
"eval_steps_per_second": 1.942,
"step": 500
},
{
"epoch": 0.10665529010238908,
"grad_norm": 81.48503875732422,
"learning_rate": 9.64448236632537e-08,
"loss": 0.4148,
"step": 1000
},
{
"epoch": 0.10665529010238908,
"eval_loss": 1.284144401550293,
"eval_runtime": 63.853,
"eval_samples_per_second": 15.457,
"eval_steps_per_second": 1.942,
"step": 1000
},
{
"epoch": 0.1599829351535836,
"grad_norm": 718.367919921875,
"learning_rate": 9.466723549488054e-08,
"loss": 0.3281,
"step": 1500
},
{
"epoch": 0.1599829351535836,
"eval_loss": 1.2112621068954468,
"eval_runtime": 64.127,
"eval_samples_per_second": 15.391,
"eval_steps_per_second": 1.934,
"step": 1500
},
{
"epoch": 0.21331058020477817,
"grad_norm": 4.5923566818237305,
"learning_rate": 9.288964732650739e-08,
"loss": 0.2912,
"step": 2000
},
{
"epoch": 0.21331058020477817,
"eval_loss": 1.159011960029602,
"eval_runtime": 63.7062,
"eval_samples_per_second": 15.493,
"eval_steps_per_second": 1.946,
"step": 2000
},
{
"epoch": 0.2666382252559727,
"grad_norm": 319.4483642578125,
"learning_rate": 9.111205915813424e-08,
"loss": 0.3073,
"step": 2500
},
{
"epoch": 0.2666382252559727,
"eval_loss": 1.1095446348190308,
"eval_runtime": 63.9925,
"eval_samples_per_second": 15.424,
"eval_steps_per_second": 1.938,
"step": 2500
},
{
"epoch": 0.3199658703071672,
"grad_norm": 0.00027541385497897863,
"learning_rate": 8.933447098976109e-08,
"loss": 0.2446,
"step": 3000
},
{
"epoch": 0.3199658703071672,
"eval_loss": 1.069318175315857,
"eval_runtime": 64.1107,
"eval_samples_per_second": 15.395,
"eval_steps_per_second": 1.934,
"step": 3000
},
{
"epoch": 0.37329351535836175,
"grad_norm": 5.2035698890686035,
"learning_rate": 8.755688282138793e-08,
"loss": 0.273,
"step": 3500
},
{
"epoch": 0.37329351535836175,
"eval_loss": 1.043074369430542,
"eval_runtime": 63.9447,
"eval_samples_per_second": 15.435,
"eval_steps_per_second": 1.939,
"step": 3500
},
{
"epoch": 0.42662116040955633,
"grad_norm": 3.6792104244232178,
"learning_rate": 8.57792946530148e-08,
"loss": 0.193,
"step": 4000
},
{
"epoch": 0.42662116040955633,
"eval_loss": 1.0195527076721191,
"eval_runtime": 63.8076,
"eval_samples_per_second": 15.468,
"eval_steps_per_second": 1.943,
"step": 4000
},
{
"epoch": 0.47994880546075086,
"grad_norm": 111.2447280883789,
"learning_rate": 8.400170648464163e-08,
"loss": 0.2419,
"step": 4500
},
{
"epoch": 0.47994880546075086,
"eval_loss": 0.9946303963661194,
"eval_runtime": 63.8873,
"eval_samples_per_second": 15.449,
"eval_steps_per_second": 1.941,
"step": 4500
},
{
"epoch": 0.5332764505119454,
"grad_norm": 0.024256089702248573,
"learning_rate": 8.222411831626848e-08,
"loss": 0.2577,
"step": 5000
},
{
"epoch": 0.5332764505119454,
"eval_loss": 0.9679088592529297,
"eval_runtime": 62.896,
"eval_samples_per_second": 15.693,
"eval_steps_per_second": 1.972,
"step": 5000
},
{
"epoch": 0.58660409556314,
"grad_norm": 0.05403488501906395,
"learning_rate": 8.044653014789534e-08,
"loss": 0.2468,
"step": 5500
},
{
"epoch": 0.58660409556314,
"eval_loss": 0.9470070004463196,
"eval_runtime": 64.2367,
"eval_samples_per_second": 15.365,
"eval_steps_per_second": 1.93,
"step": 5500
},
{
"epoch": 0.6399317406143344,
"grad_norm": 56.23408508300781,
"learning_rate": 7.866894197952219e-08,
"loss": 0.2148,
"step": 6000
},
{
"epoch": 0.6399317406143344,
"eval_loss": 0.9275079369544983,
"eval_runtime": 62.7425,
"eval_samples_per_second": 15.731,
"eval_steps_per_second": 1.976,
"step": 6000
},
{
"epoch": 0.693259385665529,
"grad_norm": 335.7691955566406,
"learning_rate": 7.689135381114903e-08,
"loss": 0.179,
"step": 6500
},
{
"epoch": 0.693259385665529,
"eval_loss": 0.9107733964920044,
"eval_runtime": 63.711,
"eval_samples_per_second": 15.492,
"eval_steps_per_second": 1.946,
"step": 6500
}
],
"logging_steps": 500,
"max_steps": 28128,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"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": 2339148799892520.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|