End of training
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +113 -0
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9491525423728815,
|
| 3 |
+
"eval_accuracy": 0.9608938547486033,
|
| 4 |
+
"eval_loss": 0.2215021550655365,
|
| 5 |
+
"eval_runtime": 154.076,
|
| 6 |
+
"eval_samples_per_second": 3.485,
|
| 7 |
+
"eval_steps_per_second": 0.11,
|
| 8 |
+
"total_flos": 8.603314901828076e+17,
|
| 9 |
+
"train_loss": 0.5041907244715197,
|
| 10 |
+
"train_runtime": 12510.0722,
|
| 11 |
+
"train_samples_per_second": 0.901,
|
| 12 |
+
"train_steps_per_second": 0.007
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9491525423728815,
|
| 3 |
+
"eval_accuracy": 0.9608938547486033,
|
| 4 |
+
"eval_loss": 0.2215021550655365,
|
| 5 |
+
"eval_runtime": 154.076,
|
| 6 |
+
"eval_samples_per_second": 3.485,
|
| 7 |
+
"eval_steps_per_second": 0.11
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9491525423728815,
|
| 3 |
+
"total_flos": 8.603314901828076e+17,
|
| 4 |
+
"train_loss": 0.5041907244715197,
|
| 5 |
+
"train_runtime": 12510.0722,
|
| 6 |
+
"train_samples_per_second": 0.901,
|
| 7 |
+
"train_steps_per_second": 0.007
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9608938547486033,
|
| 3 |
+
"best_model_checkpoint": "vit-base-patch16-224-in21k-finetuned-CT\\checkpoint-87",
|
| 4 |
+
"epoch": 2.9491525423728815,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 87,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.3389830508474576,
|
| 13 |
+
"grad_norm": 1.1623811721801758,
|
| 14 |
+
"learning_rate": 4.935897435897436e-05,
|
| 15 |
+
"loss": 1.3079,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.6779661016949152,
|
| 20 |
+
"grad_norm": 1.0423816442489624,
|
| 21 |
+
"learning_rate": 4.294871794871795e-05,
|
| 22 |
+
"loss": 0.9129,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.9830508474576272,
|
| 27 |
+
"eval_accuracy": 0.9329608938547486,
|
| 28 |
+
"eval_loss": 0.45367431640625,
|
| 29 |
+
"eval_runtime": 189.2542,
|
| 30 |
+
"eval_samples_per_second": 2.837,
|
| 31 |
+
"eval_steps_per_second": 0.09,
|
| 32 |
+
"step": 29
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.0169491525423728,
|
| 36 |
+
"grad_norm": 1.0528792142868042,
|
| 37 |
+
"learning_rate": 3.653846153846154e-05,
|
| 38 |
+
"loss": 0.5782,
|
| 39 |
+
"step": 30
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.3559322033898304,
|
| 43 |
+
"grad_norm": 1.0269708633422852,
|
| 44 |
+
"learning_rate": 3.012820512820513e-05,
|
| 45 |
+
"loss": 0.3838,
|
| 46 |
+
"step": 40
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.694915254237288,
|
| 50 |
+
"grad_norm": 1.0555919408798218,
|
| 51 |
+
"learning_rate": 2.3717948717948718e-05,
|
| 52 |
+
"loss": 0.3054,
|
| 53 |
+
"step": 50
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 2.0,
|
| 57 |
+
"eval_accuracy": 0.9553072625698324,
|
| 58 |
+
"eval_loss": 0.24561791121959686,
|
| 59 |
+
"eval_runtime": 176.6607,
|
| 60 |
+
"eval_samples_per_second": 3.04,
|
| 61 |
+
"eval_steps_per_second": 0.096,
|
| 62 |
+
"step": 59
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.0338983050847457,
|
| 66 |
+
"grad_norm": 0.6921894550323486,
|
| 67 |
+
"learning_rate": 1.730769230769231e-05,
|
| 68 |
+
"loss": 0.2698,
|
| 69 |
+
"step": 60
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.3728813559322033,
|
| 73 |
+
"grad_norm": 1.0234838724136353,
|
| 74 |
+
"learning_rate": 1.0897435897435898e-05,
|
| 75 |
+
"loss": 0.2378,
|
| 76 |
+
"step": 70
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 2.711864406779661,
|
| 80 |
+
"grad_norm": 1.1442369222640991,
|
| 81 |
+
"learning_rate": 4.487179487179488e-06,
|
| 82 |
+
"loss": 0.2369,
|
| 83 |
+
"step": 80
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.9491525423728815,
|
| 87 |
+
"eval_accuracy": 0.9608938547486033,
|
| 88 |
+
"eval_loss": 0.2215021550655365,
|
| 89 |
+
"eval_runtime": 177.0384,
|
| 90 |
+
"eval_samples_per_second": 3.033,
|
| 91 |
+
"eval_steps_per_second": 0.096,
|
| 92 |
+
"step": 87
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.9491525423728815,
|
| 96 |
+
"step": 87,
|
| 97 |
+
"total_flos": 8.603314901828076e+17,
|
| 98 |
+
"train_loss": 0.5041907244715197,
|
| 99 |
+
"train_runtime": 12510.0722,
|
| 100 |
+
"train_samples_per_second": 0.901,
|
| 101 |
+
"train_steps_per_second": 0.007
|
| 102 |
+
}
|
| 103 |
+
],
|
| 104 |
+
"logging_steps": 10,
|
| 105 |
+
"max_steps": 87,
|
| 106 |
+
"num_input_tokens_seen": 0,
|
| 107 |
+
"num_train_epochs": 3,
|
| 108 |
+
"save_steps": 500,
|
| 109 |
+
"total_flos": 8.603314901828076e+17,
|
| 110 |
+
"train_batch_size": 32,
|
| 111 |
+
"trial_name": null,
|
| 112 |
+
"trial_params": null
|
| 113 |
+
}
|