File size: 2,822 Bytes
3ae8bb2 8c178d2 3ae8bb2 8c178d2 3ae8bb2 8c178d2 7947b64 8c178d2 7947b64 3ae8bb2 8c178d2 7947b64 8c178d2 7947b64 3ae8bb2 8c178d2 7947b64 8c178d2 7947b64 3ae8bb2 8c178d2 7947b64 8c178d2 7947b64 3ae8bb2 8c178d2 7947b64 8c178d2 7947b64 3ae8bb2 8c178d2 7947b64 8c178d2 7947b64 3ae8bb2 8c178d2 7947b64 8c178d2 7947b64 3ae8bb2 8c178d2 7947b64 8c178d2 7947b64 3ae8bb2 8c178d2 7947b64 8c178d2 7947b64 3ae8bb2 8c178d2 7947b64 8c178d2 7947b64 3ae8bb2 8c178d2 7947b64 8c178d2 7947b64 8c178d2 7947b64 8c178d2 7947b64 8c178d2 7947b64 3ae8bb2 8c178d2 3ae8bb2 7947b64 3ae8bb2 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.84,
"eval_steps": 500,
"global_step": 24,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.32,
"grad_norm": 1.0203443765640259,
"learning_rate": 0.00018333333333333334,
"loss": 9.4828,
"step": 2
},
{
"epoch": 0.64,
"grad_norm": 1.6231805086135864,
"learning_rate": 0.0001666666666666667,
"loss": 9.1586,
"step": 4
},
{
"epoch": 0.96,
"grad_norm": 2.2771148681640625,
"learning_rate": 0.00015000000000000001,
"loss": 8.6907,
"step": 6
},
{
"epoch": 1.28,
"grad_norm": 2.1158745288848877,
"learning_rate": 0.00013333333333333334,
"loss": 8.2535,
"step": 8
},
{
"epoch": 1.6,
"grad_norm": 1.86466646194458,
"learning_rate": 0.00011666666666666668,
"loss": 7.8775,
"step": 10
},
{
"epoch": 1.92,
"grad_norm": 1.410565972328186,
"learning_rate": 0.0001,
"loss": 7.5684,
"step": 12
},
{
"epoch": 2.24,
"grad_norm": 0.9350765347480774,
"learning_rate": 8.333333333333334e-05,
"loss": 7.4331,
"step": 14
},
{
"epoch": 2.56,
"grad_norm": 0.9051127433776855,
"learning_rate": 6.666666666666667e-05,
"loss": 7.3164,
"step": 16
},
{
"epoch": 2.88,
"grad_norm": 0.8144361972808838,
"learning_rate": 5e-05,
"loss": 7.2426,
"step": 18
},
{
"epoch": 3.2,
"grad_norm": 1.0328956842422485,
"learning_rate": 3.3333333333333335e-05,
"loss": 7.2851,
"step": 20
},
{
"epoch": 3.52,
"grad_norm": 0.9490511417388916,
"learning_rate": 1.6666666666666667e-05,
"loss": 7.213,
"step": 22
},
{
"epoch": 3.84,
"grad_norm": 0.826574981212616,
"learning_rate": 0.0,
"loss": 7.1788,
"step": 24
},
{
"epoch": 3.84,
"step": 24,
"total_flos": 107168334014400.0,
"train_loss": 7.891708850860596,
"train_runtime": 637.8922,
"train_samples_per_second": 0.627,
"train_steps_per_second": 0.038
}
],
"logging_steps": 2,
"max_steps": 24,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 107168334014400.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|