File size: 2,711 Bytes
cdcda1e a9ed7f0 cdcda1e abd3264 a9ed7f0 abd3264 a9ed7f0 abd3264 a9ed7f0 abd3264 a9ed7f0 abd3264 a9ed7f0 abd3264 a9ed7f0 cdcda1e a9ed7f0 abd3264 a9ed7f0 abd3264 a9ed7f0 cdcda1e a9ed7f0 cdcda1e a9ed7f0 cdcda1e a9ed7f0 cdcda1e a9ed7f0 abd3264 cdcda1e |
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 |
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 3750,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.4,
"grad_norm": 4.658291339874268,
"learning_rate": 2.8703181864639013e-06,
"loss": 0.64,
"step": 500
},
{
"epoch": 0.8,
"grad_norm": 4.34930944442749,
"learning_rate": 2.5036959095382875e-06,
"loss": 0.6413,
"step": 1000
},
{
"epoch": 1.0,
"eval_loss": 0.6420477032661438,
"eval_runtime": 20.5136,
"eval_samples_per_second": 97.497,
"eval_steps_per_second": 12.187,
"step": 1250
},
{
"epoch": 1.2,
"grad_norm": 5.983999252319336,
"learning_rate": 1.963525491562421e-06,
"loss": 0.4847,
"step": 1500
},
{
"epoch": 1.6,
"grad_norm": 5.177482604980469,
"learning_rate": 1.3432073050985201e-06,
"loss": 0.3344,
"step": 2000
},
{
"epoch": 2.0,
"grad_norm": 4.585903167724609,
"learning_rate": 7.500000000000003e-07,
"loss": 0.3318,
"step": 2500
},
{
"epoch": 2.0,
"eval_loss": 0.7324458360671997,
"eval_runtime": 20.5637,
"eval_samples_per_second": 97.259,
"eval_steps_per_second": 12.157,
"step": 2500
},
{
"epoch": 2.4,
"grad_norm": 5.989898681640625,
"learning_rate": 2.86474508437579e-07,
"loss": 0.1551,
"step": 3000
},
{
"epoch": 2.8,
"grad_norm": 5.329368591308594,
"learning_rate": 3.277859889929147e-08,
"loss": 0.1518,
"step": 3500
},
{
"epoch": 3.0,
"eval_loss": 0.994577169418335,
"eval_runtime": 20.6046,
"eval_samples_per_second": 97.066,
"eval_steps_per_second": 12.133,
"step": 3750
},
{
"epoch": 3.0,
"step": 3750,
"total_flos": 2.3924465493816115e+17,
"train_loss": 0.37510518595377607,
"train_runtime": 2372.5928,
"train_samples_per_second": 12.644,
"train_steps_per_second": 1.581
}
],
"logging_steps": 500,
"max_steps": 3750,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.3924465493816115e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
|