File size: 1,981 Bytes
5923246 24b5092 fe97464 5923246 fe97464 5923246 24b5092 fe97464 24b5092 5923246 24b5092 fe97464 5923246 24b5092 fe97464 24b5092 5923246 fe97464 24b5092 fe97464 24b5092 fe97464 5923246 fe97464 5923246 fe97464 5923246 fe97464 5923246 |
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 |
{
"best_metric": 0.28125,
"best_model_checkpoint": "resnet-18-finetuned-resnet/checkpoint-6",
"epoch": 2.6666666666666665,
"eval_steps": 500,
"global_step": 18,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.8888888888888888,
"eval_accuracy": 0.28125,
"eval_loss": 3.1846918359351296e+16,
"eval_runtime": 0.3291,
"eval_samples_per_second": 291.681,
"eval_steps_per_second": 9.115,
"step": 6
},
{
"epoch": 1.4814814814814814,
"grad_norm": 34356422656.0,
"learning_rate": 2.5e-05,
"loss": 2.9760391893693236e+16,
"step": 10
},
{
"epoch": 1.925925925925926,
"eval_accuracy": 0.28125,
"eval_loss": 3.1846918359351296e+16,
"eval_runtime": 0.3235,
"eval_samples_per_second": 296.738,
"eval_steps_per_second": 9.273,
"step": 13
},
{
"epoch": 2.6666666666666665,
"eval_accuracy": 0.28125,
"eval_loss": 3.1846918359351296e+16,
"eval_runtime": 0.4136,
"eval_samples_per_second": 232.081,
"eval_steps_per_second": 7.253,
"step": 18
},
{
"epoch": 2.6666666666666665,
"step": 18,
"total_flos": 2.326039595266867e+16,
"train_loss": 2.9779228284041444e+16,
"train_runtime": 15.5478,
"train_samples_per_second": 166.712,
"train_steps_per_second": 1.158
}
],
"logging_steps": 10,
"max_steps": 18,
"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": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.326039595266867e+16,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}
|