File size: 2,780 Bytes
c3eebca 15faad3 c3eebca 15faad3 c3eebca 15faad3 c3eebca 15faad3 c3eebca 15faad3 c3eebca 15faad3 c3eebca 15faad3 c3eebca 15faad3 c3eebca 15faad3 c3eebca 15faad3 c3eebca 15faad3 c3eebca 15faad3 c3eebca 15faad3 c3eebca 15faad3 c3eebca 15faad3 c3eebca 15faad3 c3eebca |
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": 0.7660450339317322,
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l57-l/checkpoint-2500",
"epoch": 0.46057479734708917,
"eval_steps": 500,
"global_step": 2500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.09211495946941783,
"grad_norm": 2.6780805587768555,
"learning_rate": 4.84647506755097e-07,
"loss": 0.2705,
"step": 500
},
{
"epoch": 0.09211495946941783,
"eval_loss": 1.0680681467056274,
"eval_runtime": 74.5723,
"eval_samples_per_second": 16.186,
"eval_steps_per_second": 2.025,
"step": 500
},
{
"epoch": 0.18422991893883567,
"grad_norm": 8.301130294799805,
"learning_rate": 4.69295013510194e-07,
"loss": 0.2545,
"step": 1000
},
{
"epoch": 0.18422991893883567,
"eval_loss": 0.9443553686141968,
"eval_runtime": 74.9643,
"eval_samples_per_second": 16.101,
"eval_steps_per_second": 2.014,
"step": 1000
},
{
"epoch": 0.2763448784082535,
"grad_norm": 0.018898434937000275,
"learning_rate": 4.5394252026529107e-07,
"loss": 0.234,
"step": 1500
},
{
"epoch": 0.2763448784082535,
"eval_loss": 0.876915693283081,
"eval_runtime": 75.6401,
"eval_samples_per_second": 15.957,
"eval_steps_per_second": 1.996,
"step": 1500
},
{
"epoch": 0.36845983787767134,
"grad_norm": 0.00010984255641233176,
"learning_rate": 4.385900270203881e-07,
"loss": 0.1539,
"step": 2000
},
{
"epoch": 0.36845983787767134,
"eval_loss": 0.8415330648422241,
"eval_runtime": 76.9959,
"eval_samples_per_second": 15.676,
"eval_steps_per_second": 1.961,
"step": 2000
},
{
"epoch": 0.46057479734708917,
"grad_norm": 395.890625,
"learning_rate": 4.232375337754851e-07,
"loss": 0.1766,
"step": 2500
},
{
"epoch": 0.46057479734708917,
"eval_loss": 0.7660450339317322,
"eval_runtime": 76.733,
"eval_samples_per_second": 15.73,
"eval_steps_per_second": 1.968,
"step": 2500
}
],
"logging_steps": 500,
"max_steps": 16284,
"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
}
|