File size: 5,627 Bytes
6fe66e4 |
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_metric": 4.464449882507324,
"best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained/en_clm/wikipedia_30/checkpoint-32000",
"epoch": 16.828819353142258,
"eval_steps": 2000,
"global_step": 32000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0518012095713911,
"eval_loss": 7.518920421600342,
"eval_runtime": 2.2399,
"eval_samples_per_second": 1422.808,
"eval_steps_per_second": 89.288,
"step": 2000
},
{
"epoch": 2.1036024191427822,
"grad_norm": 1.2947496175765991,
"learning_rate": 1e-05,
"loss": 7.6141,
"step": 4000
},
{
"epoch": 2.1036024191427822,
"eval_loss": 6.568221092224121,
"eval_runtime": 2.1236,
"eval_samples_per_second": 1500.783,
"eval_steps_per_second": 94.182,
"step": 4000
},
{
"epoch": 3.155403628714173,
"eval_loss": 6.16925573348999,
"eval_runtime": 2.1624,
"eval_samples_per_second": 1473.825,
"eval_steps_per_second": 92.49,
"step": 6000
},
{
"epoch": 4.2072048382855645,
"grad_norm": 2.330080270767212,
"learning_rate": 2e-05,
"loss": 6.2396,
"step": 8000
},
{
"epoch": 4.2072048382855645,
"eval_loss": 5.901575088500977,
"eval_runtime": 2.1326,
"eval_samples_per_second": 1494.388,
"eval_steps_per_second": 93.78,
"step": 8000
},
{
"epoch": 5.259006047856955,
"eval_loss": 5.67369270324707,
"eval_runtime": 2.1364,
"eval_samples_per_second": 1491.788,
"eval_steps_per_second": 93.617,
"step": 10000
},
{
"epoch": 6.310807257428346,
"grad_norm": 2.565220594406128,
"learning_rate": 2.99925e-05,
"loss": 5.7217,
"step": 12000
},
{
"epoch": 6.310807257428346,
"eval_loss": 5.460005760192871,
"eval_runtime": 2.1835,
"eval_samples_per_second": 1459.563,
"eval_steps_per_second": 91.595,
"step": 12000
},
{
"epoch": 7.362608466999737,
"eval_loss": 5.272489547729492,
"eval_runtime": 2.1833,
"eval_samples_per_second": 1459.691,
"eval_steps_per_second": 91.603,
"step": 14000
},
{
"epoch": 8.414409676571129,
"grad_norm": 2.7334115505218506,
"learning_rate": 3.99875e-05,
"loss": 5.3064,
"step": 16000
},
{
"epoch": 8.414409676571129,
"eval_loss": 5.1074652671813965,
"eval_runtime": 2.2402,
"eval_samples_per_second": 1422.652,
"eval_steps_per_second": 89.278,
"step": 16000
},
{
"epoch": 9.46621088614252,
"eval_loss": 4.9716596603393555,
"eval_runtime": 2.1736,
"eval_samples_per_second": 1466.258,
"eval_steps_per_second": 92.015,
"step": 18000
},
{
"epoch": 10.51801209571391,
"grad_norm": 2.6722376346588135,
"learning_rate": 4.9985e-05,
"loss": 4.9744,
"step": 20000
},
{
"epoch": 10.51801209571391,
"eval_loss": 4.864916801452637,
"eval_runtime": 2.2031,
"eval_samples_per_second": 1446.585,
"eval_steps_per_second": 90.78,
"step": 20000
},
{
"epoch": 11.569813305285301,
"eval_loss": 4.763542652130127,
"eval_runtime": 2.4382,
"eval_samples_per_second": 1307.131,
"eval_steps_per_second": 82.029,
"step": 22000
},
{
"epoch": 12.621614514856692,
"grad_norm": 2.4539408683776855,
"learning_rate": 5.9985e-05,
"loss": 4.7273,
"step": 24000
},
{
"epoch": 12.621614514856692,
"eval_loss": 4.683297634124756,
"eval_runtime": 2.452,
"eval_samples_per_second": 1299.733,
"eval_steps_per_second": 81.565,
"step": 24000
},
{
"epoch": 13.673415724428082,
"eval_loss": 4.621574401855469,
"eval_runtime": 2.1825,
"eval_samples_per_second": 1460.226,
"eval_steps_per_second": 91.636,
"step": 26000
},
{
"epoch": 14.725216933999475,
"grad_norm": 2.4913346767425537,
"learning_rate": 6.998e-05,
"loss": 4.5397,
"step": 28000
},
{
"epoch": 14.725216933999475,
"eval_loss": 4.562623977661133,
"eval_runtime": 2.201,
"eval_samples_per_second": 1447.965,
"eval_steps_per_second": 90.867,
"step": 28000
},
{
"epoch": 15.777018143570865,
"eval_loss": 4.506168842315674,
"eval_runtime": 2.2491,
"eval_samples_per_second": 1416.988,
"eval_steps_per_second": 88.923,
"step": 30000
},
{
"epoch": 16.828819353142258,
"grad_norm": 2.2661523818969727,
"learning_rate": 7.99775e-05,
"loss": 4.3839,
"step": 32000
},
{
"epoch": 16.828819353142258,
"eval_loss": 4.464449882507324,
"eval_runtime": 2.253,
"eval_samples_per_second": 1414.55,
"eval_steps_per_second": 88.77,
"step": 32000
}
],
"logging_steps": 4000,
"max_steps": 100000,
"num_input_tokens_seen": 0,
"num_train_epochs": 53,
"save_steps": 4000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 8272174718423040.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|