File size: 3,021 Bytes
1f5f03f ea3cf07 1f5f03f ea3cf07 1f5f03f ea3cf07 1f5f03f ea3cf07 1f5f03f ea3cf07 1f5f03f ea3cf07 1f5f03f ea3cf07 1f5f03f ea3cf07 1f5f03f ea3cf07 1f5f03f ea3cf07 1f5f03f ea3cf07 1f5f03f ea3cf07 1f5f03f |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"eval_steps": 500,
"global_step": 1340,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 9.199758529663086,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.61,
"step": 268
},
{
"epoch": 1.0,
"eval_loss": 0.581834614276886,
"eval_matthews_correlation": 0.1605505486389139,
"eval_runtime": 8.5337,
"eval_samples_per_second": 122.221,
"eval_steps_per_second": 7.734,
"step": 268
},
{
"epoch": 2.0,
"grad_norm": 7.077225685119629,
"learning_rate": 1.2e-05,
"loss": 0.5265,
"step": 536
},
{
"epoch": 2.0,
"eval_loss": 0.5488986968994141,
"eval_matthews_correlation": 0.3414642281150747,
"eval_runtime": 8.5064,
"eval_samples_per_second": 122.614,
"eval_steps_per_second": 7.759,
"step": 536
},
{
"epoch": 3.0,
"grad_norm": 9.864019393920898,
"learning_rate": 8.000000000000001e-06,
"loss": 0.4161,
"step": 804
},
{
"epoch": 3.0,
"eval_loss": 0.5453676581382751,
"eval_matthews_correlation": 0.3451229816764349,
"eval_runtime": 8.5021,
"eval_samples_per_second": 122.676,
"eval_steps_per_second": 7.763,
"step": 804
},
{
"epoch": 4.0,
"grad_norm": 5.3014726638793945,
"learning_rate": 4.000000000000001e-06,
"loss": 0.3324,
"step": 1072
},
{
"epoch": 4.0,
"eval_loss": 0.574592113494873,
"eval_matthews_correlation": 0.3868717129142223,
"eval_runtime": 8.4987,
"eval_samples_per_second": 122.724,
"eval_steps_per_second": 7.766,
"step": 1072
},
{
"epoch": 5.0,
"grad_norm": 17.219274520874023,
"learning_rate": 0.0,
"loss": 0.2657,
"step": 1340
},
{
"epoch": 5.0,
"eval_loss": 0.6475589275360107,
"eval_matthews_correlation": 0.3934207280665654,
"eval_runtime": 8.5544,
"eval_samples_per_second": 121.926,
"eval_steps_per_second": 7.715,
"step": 1340
},
{
"epoch": 5.0,
"step": 1340,
"total_flos": 7603507301468160.0,
"train_loss": 0.4301326410094304,
"train_runtime": 814.307,
"train_samples_per_second": 52.505,
"train_steps_per_second": 1.646
}
],
"logging_steps": 500,
"max_steps": 1340,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"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": 7603507301468160.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|