File size: 2,786 Bytes
03c9ba9 932f5a7 03c9ba9 932f5a7 03c9ba9 932f5a7 03c9ba9 932f5a7 03c9ba9 932f5a7 03c9ba9 932f5a7 03c9ba9 932f5a7 03c9ba9 932f5a7 03c9ba9 932f5a7 03c9ba9 932f5a7 03c9ba9 932f5a7 03c9ba9 932f5a7 03c9ba9 932f5a7 03c9ba9 |
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": 1.1896915435791016,
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l58-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": 20.28152847290039,
"learning_rate": 4.8848563006632274e-08,
"loss": 0.3758,
"step": 500
},
{
"epoch": 0.09211495946941783,
"eval_loss": 1.418367862701416,
"eval_runtime": 73.4439,
"eval_samples_per_second": 16.434,
"eval_steps_per_second": 2.056,
"step": 500
},
{
"epoch": 0.18422991893883567,
"grad_norm": 47.29538345336914,
"learning_rate": 4.7697126013264556e-08,
"loss": 0.4104,
"step": 1000
},
{
"epoch": 0.18422991893883567,
"eval_loss": 1.3491536378860474,
"eval_runtime": 74.3404,
"eval_samples_per_second": 16.236,
"eval_steps_per_second": 2.031,
"step": 1000
},
{
"epoch": 0.2763448784082535,
"grad_norm": 0.5450155138969421,
"learning_rate": 4.6545689019896826e-08,
"loss": 0.4325,
"step": 1500
},
{
"epoch": 0.2763448784082535,
"eval_loss": 1.2877168655395508,
"eval_runtime": 75.3303,
"eval_samples_per_second": 16.023,
"eval_steps_per_second": 2.005,
"step": 1500
},
{
"epoch": 0.36845983787767134,
"grad_norm": 0.11449883133172989,
"learning_rate": 4.539425202652911e-08,
"loss": 0.3423,
"step": 2000
},
{
"epoch": 0.36845983787767134,
"eval_loss": 1.2384389638900757,
"eval_runtime": 76.113,
"eval_samples_per_second": 15.858,
"eval_steps_per_second": 1.984,
"step": 2000
},
{
"epoch": 0.46057479734708917,
"grad_norm": 389.7380065917969,
"learning_rate": 4.4242815033161385e-08,
"loss": 0.3645,
"step": 2500
},
{
"epoch": 0.46057479734708917,
"eval_loss": 1.1896915435791016,
"eval_runtime": 76.23,
"eval_samples_per_second": 15.834,
"eval_steps_per_second": 1.981,
"step": 2500
}
],
"logging_steps": 500,
"max_steps": 21712,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"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
}
|