Spaces:
Build error
Build error
File size: 3,574 Bytes
e1e71f5 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.99288256227758,
"eval_steps": 35,
"global_step": 70,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1423487544483986,
"grad_norm": 5.176560878753662,
"learning_rate": 2.380952380952381e-05,
"loss": 2.7275,
"step": 5
},
{
"epoch": 0.2846975088967972,
"grad_norm": 3.7604565620422363,
"learning_rate": 4.761904761904762e-05,
"loss": 2.3848,
"step": 10
},
{
"epoch": 0.42704626334519574,
"grad_norm": 1.9476191997528076,
"learning_rate": 7.142857142857143e-05,
"loss": 1.9534,
"step": 15
},
{
"epoch": 0.5693950177935944,
"grad_norm": 1.1864774227142334,
"learning_rate": 9.523809523809524e-05,
"loss": 1.7776,
"step": 20
},
{
"epoch": 0.7117437722419929,
"grad_norm": 1.2619398832321167,
"learning_rate": 9.988952191691925e-05,
"loss": 1.6551,
"step": 25
},
{
"epoch": 0.8540925266903915,
"grad_norm": 1.204907774925232,
"learning_rate": 9.944154131125642e-05,
"loss": 1.6106,
"step": 30
},
{
"epoch": 0.99644128113879,
"grad_norm": 1.030988097190857,
"learning_rate": 9.865224352899119e-05,
"loss": 1.6196,
"step": 35
},
{
"epoch": 0.99644128113879,
"eval_loss": 1.531648874282837,
"eval_runtime": 3.1223,
"eval_samples_per_second": 14.733,
"eval_steps_per_second": 14.733,
"step": 35
},
{
"epoch": 1.1387900355871885,
"grad_norm": 1.0289065837860107,
"learning_rate": 9.752707744739145e-05,
"loss": 1.4904,
"step": 40
},
{
"epoch": 1.281138790035587,
"grad_norm": 1.2606865167617798,
"learning_rate": 9.607381059352038e-05,
"loss": 1.4244,
"step": 45
},
{
"epoch": 1.4234875444839858,
"grad_norm": 1.2899017333984375,
"learning_rate": 9.430247552150673e-05,
"loss": 1.4003,
"step": 50
},
{
"epoch": 1.5658362989323842,
"grad_norm": 1.3828767538070679,
"learning_rate": 9.22253005533154e-05,
"loss": 1.3709,
"step": 55
},
{
"epoch": 1.708185053380783,
"grad_norm": 1.5857073068618774,
"learning_rate": 8.985662536114613e-05,
"loss": 1.3789,
"step": 60
},
{
"epoch": 1.8505338078291815,
"grad_norm": 1.4692878723144531,
"learning_rate": 8.721280197423258e-05,
"loss": 1.3579,
"step": 65
},
{
"epoch": 1.99288256227758,
"grad_norm": 1.452291488647461,
"learning_rate": 8.43120818934367e-05,
"loss": 1.3654,
"step": 70
},
{
"epoch": 1.99288256227758,
"eval_loss": 1.4582531452178955,
"eval_runtime": 3.0596,
"eval_samples_per_second": 15.035,
"eval_steps_per_second": 15.035,
"step": 70
}
],
"logging_steps": 5,
"max_steps": 210,
"num_input_tokens_seen": 0,
"num_train_epochs": 6,
"save_steps": 35,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 9.920445563260109e+16,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}
|