File size: 2,777 Bytes
a67de01 2930be0 a67de01 2930be0 a67de01 2930be0 a67de01 2930be0 a67de01 2930be0 a67de01 2930be0 a67de01 2930be0 a67de01 2930be0 a67de01 2930be0 a67de01 2930be0 a67de01 2930be0 a67de01 2930be0 a67de01 2930be0 a67de01 |
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 |
{
"best_metric": 1.257211685180664,
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l58-l/checkpoint-2500",
"epoch": 0.2666382252559727,
"eval_steps": 500,
"global_step": 2500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.05332764505119454,
"grad_norm": 217.40109252929688,
"learning_rate": 4.911120591581342e-08,
"loss": 0.4667,
"step": 500
},
{
"epoch": 0.05332764505119454,
"eval_loss": 1.4427576065063477,
"eval_runtime": 60.328,
"eval_samples_per_second": 16.361,
"eval_steps_per_second": 2.055,
"step": 500
},
{
"epoch": 0.10665529010238908,
"grad_norm": 70.38941955566406,
"learning_rate": 4.822241183162685e-08,
"loss": 0.4534,
"step": 1000
},
{
"epoch": 0.10665529010238908,
"eval_loss": 1.3823094367980957,
"eval_runtime": 61.4884,
"eval_samples_per_second": 16.052,
"eval_steps_per_second": 2.017,
"step": 1000
},
{
"epoch": 0.1599829351535836,
"grad_norm": 389.9967956542969,
"learning_rate": 4.733361774744027e-08,
"loss": 0.3753,
"step": 1500
},
{
"epoch": 0.1599829351535836,
"eval_loss": 1.3328827619552612,
"eval_runtime": 63.0378,
"eval_samples_per_second": 15.657,
"eval_steps_per_second": 1.967,
"step": 1500
},
{
"epoch": 0.21331058020477817,
"grad_norm": 13.427445411682129,
"learning_rate": 4.6444823663253694e-08,
"loss": 0.3361,
"step": 2000
},
{
"epoch": 0.21331058020477817,
"eval_loss": 1.2922736406326294,
"eval_runtime": 63.1958,
"eval_samples_per_second": 15.618,
"eval_steps_per_second": 1.962,
"step": 2000
},
{
"epoch": 0.2666382252559727,
"grad_norm": 320.7197265625,
"learning_rate": 4.555602957906712e-08,
"loss": 0.3597,
"step": 2500
},
{
"epoch": 0.2666382252559727,
"eval_loss": 1.257211685180664,
"eval_runtime": 63.3241,
"eval_samples_per_second": 15.586,
"eval_steps_per_second": 1.958,
"step": 2500
}
],
"logging_steps": 500,
"max_steps": 28128,
"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": false
},
"attributes": {}
}
},
"total_flos": 900115394852520.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}
|