File size: 5,654 Bytes
a907900 |
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 |
{
"best_metric": 0.6860001087188721,
"best_model_checkpoint": "llama2_short/checkpoint-300",
"epoch": 2.857142857142857,
"eval_steps": 25,
"global_step": 300,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.23809523809523808,
"grad_norm": 0.09585642069578171,
"learning_rate": 9.986018985905901e-05,
"loss": 0.8756,
"step": 25
},
{
"epoch": 0.23809523809523808,
"eval_loss": 0.8215582370758057,
"eval_runtime": 31.8561,
"eval_samples_per_second": 3.484,
"eval_steps_per_second": 0.439,
"step": 25
},
{
"epoch": 0.47619047619047616,
"grad_norm": 0.09733700007200241,
"learning_rate": 9.944154131125642e-05,
"loss": 0.789,
"step": 50
},
{
"epoch": 0.47619047619047616,
"eval_loss": 0.7655627131462097,
"eval_runtime": 31.8837,
"eval_samples_per_second": 3.481,
"eval_steps_per_second": 0.439,
"step": 50
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.11074452102184296,
"learning_rate": 9.874639560909117e-05,
"loss": 0.759,
"step": 75
},
{
"epoch": 0.7142857142857143,
"eval_loss": 0.7467875480651855,
"eval_runtime": 31.8741,
"eval_samples_per_second": 3.482,
"eval_steps_per_second": 0.439,
"step": 75
},
{
"epoch": 0.9523809523809523,
"grad_norm": 0.10002691298723221,
"learning_rate": 9.777864028930705e-05,
"loss": 0.7402,
"step": 100
},
{
"epoch": 0.9523809523809523,
"eval_loss": 0.7353290915489197,
"eval_runtime": 31.8697,
"eval_samples_per_second": 3.483,
"eval_steps_per_second": 0.439,
"step": 100
},
{
"epoch": 1.1904761904761905,
"grad_norm": 0.12271334230899811,
"learning_rate": 9.654368743221022e-05,
"loss": 0.7267,
"step": 125
},
{
"epoch": 1.1904761904761905,
"eval_loss": 0.7255786657333374,
"eval_runtime": 31.8838,
"eval_samples_per_second": 3.481,
"eval_steps_per_second": 0.439,
"step": 125
},
{
"epoch": 1.4285714285714286,
"grad_norm": 0.15203851461410522,
"learning_rate": 9.504844339512095e-05,
"loss": 0.7228,
"step": 150
},
{
"epoch": 1.4285714285714286,
"eval_loss": 0.7192813754081726,
"eval_runtime": 31.8619,
"eval_samples_per_second": 3.484,
"eval_steps_per_second": 0.439,
"step": 150
},
{
"epoch": 1.6666666666666665,
"grad_norm": 0.1312723308801651,
"learning_rate": 9.330127018922194e-05,
"loss": 0.7173,
"step": 175
},
{
"epoch": 1.6666666666666665,
"eval_loss": 0.7122732400894165,
"eval_runtime": 31.8673,
"eval_samples_per_second": 3.483,
"eval_steps_per_second": 0.439,
"step": 175
},
{
"epoch": 1.9047619047619047,
"grad_norm": 0.1437642127275467,
"learning_rate": 9.131193871579975e-05,
"loss": 0.7194,
"step": 200
},
{
"epoch": 1.9047619047619047,
"eval_loss": 0.7064856886863708,
"eval_runtime": 31.8744,
"eval_samples_per_second": 3.482,
"eval_steps_per_second": 0.439,
"step": 200
},
{
"epoch": 2.142857142857143,
"grad_norm": 0.16143007576465607,
"learning_rate": 8.90915741234015e-05,
"loss": 0.6987,
"step": 225
},
{
"epoch": 2.142857142857143,
"eval_loss": 0.7001689076423645,
"eval_runtime": 31.8599,
"eval_samples_per_second": 3.484,
"eval_steps_per_second": 0.439,
"step": 225
},
{
"epoch": 2.380952380952381,
"grad_norm": 0.1549287736415863,
"learning_rate": 8.665259359149132e-05,
"loss": 0.6941,
"step": 250
},
{
"epoch": 2.380952380952381,
"eval_loss": 0.6950200200080872,
"eval_runtime": 31.9601,
"eval_samples_per_second": 3.473,
"eval_steps_per_second": 0.438,
"step": 250
},
{
"epoch": 2.619047619047619,
"grad_norm": 0.15042544901371002,
"learning_rate": 8.400863688854597e-05,
"loss": 0.6987,
"step": 275
},
{
"epoch": 2.619047619047619,
"eval_loss": 0.6901896595954895,
"eval_runtime": 31.9342,
"eval_samples_per_second": 3.476,
"eval_steps_per_second": 0.438,
"step": 275
},
{
"epoch": 2.857142857142857,
"grad_norm": 0.17507144808769226,
"learning_rate": 8.117449009293668e-05,
"loss": 0.6953,
"step": 300
},
{
"epoch": 2.857142857142857,
"eval_loss": 0.6860001087188721,
"eval_runtime": 31.8997,
"eval_samples_per_second": 3.48,
"eval_steps_per_second": 0.439,
"step": 300
}
],
"logging_steps": 25,
"max_steps": 1050,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 10,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.953532674488402e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
|