File size: 5,240 Bytes
3b04d38 | 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 | {
"best_global_step": 7670,
"best_metric": 0.8703352808952332,
"best_model_checkpoint": "tiny_bert_km_50_v2_mnli/checkpoint-7670",
"epoch": 10.0,
"eval_steps": 500,
"global_step": 15340,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 1.0268884897232056,
"learning_rate": 4.9e-05,
"loss": 1.0026,
"step": 1534
},
{
"epoch": 1.0,
"eval_accuracy": 0.5339786041772797,
"eval_loss": 0.9471800327301025,
"eval_runtime": 2.9599,
"eval_samples_per_second": 3316.032,
"eval_steps_per_second": 13.176,
"step": 1534
},
{
"epoch": 2.0,
"grad_norm": 1.3657726049423218,
"learning_rate": 4.8e-05,
"loss": 0.9203,
"step": 3068
},
{
"epoch": 2.0,
"eval_accuracy": 0.5731023942944473,
"eval_loss": 0.9026528000831604,
"eval_runtime": 2.8075,
"eval_samples_per_second": 3496.041,
"eval_steps_per_second": 13.892,
"step": 3068
},
{
"epoch": 3.0,
"grad_norm": 1.3580602407455444,
"learning_rate": 4.7e-05,
"loss": 0.8675,
"step": 4602
},
{
"epoch": 3.0,
"eval_accuracy": 0.5897096281202241,
"eval_loss": 0.8775414228439331,
"eval_runtime": 2.8127,
"eval_samples_per_second": 3489.517,
"eval_steps_per_second": 13.866,
"step": 4602
},
{
"epoch": 4.0,
"grad_norm": 1.4758466482162476,
"learning_rate": 4.600000000000001e-05,
"loss": 0.8211,
"step": 6136
},
{
"epoch": 4.0,
"eval_accuracy": 0.5985736118186449,
"eval_loss": 0.8704348802566528,
"eval_runtime": 2.781,
"eval_samples_per_second": 3529.336,
"eval_steps_per_second": 14.024,
"step": 6136
},
{
"epoch": 5.0,
"grad_norm": 1.6115995645523071,
"learning_rate": 4.5e-05,
"loss": 0.7773,
"step": 7670
},
{
"epoch": 5.0,
"eval_accuracy": 0.6070300560366786,
"eval_loss": 0.8703352808952332,
"eval_runtime": 2.9126,
"eval_samples_per_second": 3369.849,
"eval_steps_per_second": 13.39,
"step": 7670
},
{
"epoch": 6.0,
"grad_norm": 1.9444777965545654,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.7352,
"step": 9204
},
{
"epoch": 6.0,
"eval_accuracy": 0.6116148751910341,
"eval_loss": 0.8939315676689148,
"eval_runtime": 2.8219,
"eval_samples_per_second": 3478.123,
"eval_steps_per_second": 13.82,
"step": 9204
},
{
"epoch": 7.0,
"grad_norm": 2.15396785736084,
"learning_rate": 4.3e-05,
"loss": 0.6939,
"step": 10738
},
{
"epoch": 7.0,
"eval_accuracy": 0.6115129903209373,
"eval_loss": 0.9022112488746643,
"eval_runtime": 2.8175,
"eval_samples_per_second": 3483.619,
"eval_steps_per_second": 13.842,
"step": 10738
},
{
"epoch": 8.0,
"grad_norm": 2.317307233810425,
"learning_rate": 4.2e-05,
"loss": 0.6533,
"step": 12272
},
{
"epoch": 8.0,
"eval_accuracy": 0.6104941416199694,
"eval_loss": 0.9489761590957642,
"eval_runtime": 2.8028,
"eval_samples_per_second": 3501.863,
"eval_steps_per_second": 13.915,
"step": 12272
},
{
"epoch": 9.0,
"grad_norm": 2.4730122089385986,
"learning_rate": 4.1e-05,
"loss": 0.6136,
"step": 13806
},
{
"epoch": 9.0,
"eval_accuracy": 0.6111054508405501,
"eval_loss": 0.9655206203460693,
"eval_runtime": 2.7965,
"eval_samples_per_second": 3509.691,
"eval_steps_per_second": 13.946,
"step": 13806
},
{
"epoch": 10.0,
"grad_norm": 3.071944236755371,
"learning_rate": 4e-05,
"loss": 0.5745,
"step": 15340
},
{
"epoch": 10.0,
"eval_accuracy": 0.6065206316861946,
"eval_loss": 1.0082168579101562,
"eval_runtime": 2.8128,
"eval_samples_per_second": 3489.463,
"eval_steps_per_second": 13.865,
"step": 15340
},
{
"epoch": 10.0,
"step": 15340,
"total_flos": 1.029836100834816e+17,
"train_loss": 0.7659492064952229,
"train_runtime": 2074.047,
"train_samples_per_second": 9467.047,
"train_steps_per_second": 36.981
}
],
"logging_steps": 1,
"max_steps": 76700,
"num_input_tokens_seen": 0,
"num_train_epochs": 50,
"save_steps": 500,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 5
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.029836100834816e+17,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}
|