File size: 3,141 Bytes
9925ee0 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0144927536231885,
"eval_steps": 25,
"global_step": 13,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2318840579710145,
"grad_norm": NaN,
"learning_rate": 9.869238178417235e-05,
"loss": 0.0,
"step": 1
},
{
"epoch": 0.2318840579710145,
"eval_loss": NaN,
"eval_runtime": 3.5318,
"eval_samples_per_second": 14.157,
"eval_steps_per_second": 3.681,
"step": 1
},
{
"epoch": 0.463768115942029,
"grad_norm": NaN,
"learning_rate": 9.484552115439445e-05,
"loss": 0.0,
"step": 2
},
{
"epoch": 0.6956521739130435,
"grad_norm": NaN,
"learning_rate": 8.868298366769954e-05,
"loss": 0.0,
"step": 3
},
{
"epoch": 0.927536231884058,
"grad_norm": NaN,
"learning_rate": 8.056291360290201e-05,
"loss": 0.0,
"step": 4
},
{
"epoch": 1.1594202898550725,
"grad_norm": NaN,
"learning_rate": 7.095721991691411e-05,
"loss": 0.0,
"step": 5
},
{
"epoch": 1.391304347826087,
"grad_norm": NaN,
"learning_rate": 6.042415061148954e-05,
"loss": 0.0,
"step": 6
},
{
"epoch": 1.6231884057971016,
"grad_norm": NaN,
"learning_rate": 4.9575849388510473e-05,
"loss": 0.0,
"step": 7
},
{
"epoch": 1.855072463768116,
"grad_norm": NaN,
"learning_rate": 3.904278008308589e-05,
"loss": 0.0,
"step": 8
},
{
"epoch": 2.0869565217391304,
"grad_norm": NaN,
"learning_rate": 2.9437086397097995e-05,
"loss": 0.0,
"step": 9
},
{
"epoch": 2.318840579710145,
"grad_norm": NaN,
"learning_rate": 2.1317016332300447e-05,
"loss": 0.0,
"step": 10
},
{
"epoch": 2.550724637681159,
"grad_norm": NaN,
"learning_rate": 1.515447884560556e-05,
"loss": 0.0,
"step": 11
},
{
"epoch": 2.782608695652174,
"grad_norm": NaN,
"learning_rate": 1.130761821582766e-05,
"loss": 0.0,
"step": 12
},
{
"epoch": 3.0144927536231885,
"grad_norm": NaN,
"learning_rate": 1e-05,
"loss": 0.0,
"step": 13
}
],
"logging_steps": 1,
"max_steps": 13,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"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": true
},
"attributes": {}
}
},
"total_flos": 1.3673680792348262e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|