File size: 3,166 Bytes
d37e911 8e96909 d37e911 8e96909 d37e911 a6ea778 3dccdb3 8e96909 d37e911 8e96909 d37e911 8e96909 d37e911 |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.40816326530612246,
"eval_steps": 3,
"global_step": 10,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.04081632653061224,
"grad_norm": 2.541314125061035,
"learning_rate": 2e-05,
"loss": 1.7373,
"step": 1
},
{
"epoch": 0.04081632653061224,
"eval_loss": 2.7169904708862305,
"eval_runtime": 1.7579,
"eval_samples_per_second": 6.257,
"eval_steps_per_second": 3.413,
"step": 1
},
{
"epoch": 0.08163265306122448,
"grad_norm": 1.641190767288208,
"learning_rate": 4e-05,
"loss": 1.2073,
"step": 2
},
{
"epoch": 0.12244897959183673,
"grad_norm": 1.9342085123062134,
"learning_rate": 6e-05,
"loss": 1.4465,
"step": 3
},
{
"epoch": 0.12244897959183673,
"eval_loss": 2.6776387691497803,
"eval_runtime": 0.3767,
"eval_samples_per_second": 29.201,
"eval_steps_per_second": 15.928,
"step": 3
},
{
"epoch": 0.16326530612244897,
"grad_norm": 2.0054235458374023,
"learning_rate": 8e-05,
"loss": 1.3989,
"step": 4
},
{
"epoch": 0.20408163265306123,
"grad_norm": 2.624239206314087,
"learning_rate": 0.0001,
"loss": 1.2946,
"step": 5
},
{
"epoch": 0.24489795918367346,
"grad_norm": 3.491370916366577,
"learning_rate": 0.00012,
"loss": 1.2136,
"step": 6
},
{
"epoch": 0.24489795918367346,
"eval_loss": 1.9611179828643799,
"eval_runtime": 0.3833,
"eval_samples_per_second": 28.695,
"eval_steps_per_second": 15.652,
"step": 6
},
{
"epoch": 0.2857142857142857,
"grad_norm": 3.4276037216186523,
"learning_rate": 0.00014,
"loss": 1.1283,
"step": 7
},
{
"epoch": 0.32653061224489793,
"grad_norm": 3.7004971504211426,
"learning_rate": 0.00016,
"loss": 0.888,
"step": 8
},
{
"epoch": 0.3673469387755102,
"grad_norm": 3.3266162872314453,
"learning_rate": 0.00018,
"loss": 0.5917,
"step": 9
},
{
"epoch": 0.3673469387755102,
"eval_loss": 0.5113109946250916,
"eval_runtime": 0.3774,
"eval_samples_per_second": 29.148,
"eval_steps_per_second": 15.899,
"step": 9
},
{
"epoch": 0.40816326530612246,
"grad_norm": 6.337663173675537,
"learning_rate": 0.0002,
"loss": 0.5944,
"step": 10
}
],
"logging_steps": 1,
"max_steps": 10,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 3,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1647822923366400.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|