|
{ |
|
"best_metric": 0.09556835144758224, |
|
"best_model_checkpoint": "finetuned-Leukemia-cell/checkpoint-600", |
|
"epoch": 20.0, |
|
"eval_steps": 100, |
|
"global_step": 680, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.00019764705882352942, |
|
"loss": 1.7578, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 0.0001947058823529412, |
|
"loss": 1.016, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 0.00019176470588235295, |
|
"loss": 0.9006, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 1.18, |
|
"learning_rate": 0.00018882352941176472, |
|
"loss": 0.7129, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 0.00018588235294117648, |
|
"loss": 0.3781, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 0.00018294117647058825, |
|
"loss": 0.4442, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"learning_rate": 0.00018, |
|
"loss": 0.3716, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 2.35, |
|
"learning_rate": 0.00017705882352941178, |
|
"loss": 0.371, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 0.00017411764705882354, |
|
"loss": 0.3183, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"learning_rate": 0.0001711764705882353, |
|
"loss": 0.3464, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 2.94, |
|
"eval_accuracy": 0.9285714285714286, |
|
"eval_loss": 0.2377004772424698, |
|
"eval_runtime": 103.2565, |
|
"eval_samples_per_second": 2.576, |
|
"eval_steps_per_second": 0.329, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 3.24, |
|
"learning_rate": 0.00016823529411764707, |
|
"loss": 0.2195, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 3.53, |
|
"learning_rate": 0.0001652941176470588, |
|
"loss": 0.3354, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 3.82, |
|
"learning_rate": 0.0001623529411764706, |
|
"loss": 0.3365, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 4.12, |
|
"learning_rate": 0.00015941176470588237, |
|
"loss": 0.2152, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 4.41, |
|
"learning_rate": 0.00015647058823529413, |
|
"loss": 0.3078, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 4.71, |
|
"learning_rate": 0.0001535294117647059, |
|
"loss": 0.2712, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 0.00015058823529411766, |
|
"loss": 0.133, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 5.29, |
|
"learning_rate": 0.00014764705882352943, |
|
"loss": 0.3753, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 5.59, |
|
"learning_rate": 0.0001447058823529412, |
|
"loss": 0.2242, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 5.88, |
|
"learning_rate": 0.00014176470588235296, |
|
"loss": 0.153, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 5.88, |
|
"eval_accuracy": 0.9060150375939849, |
|
"eval_loss": 0.2518657147884369, |
|
"eval_runtime": 2.626, |
|
"eval_samples_per_second": 101.294, |
|
"eval_steps_per_second": 12.947, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 6.18, |
|
"learning_rate": 0.00013882352941176472, |
|
"loss": 0.2496, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 6.47, |
|
"learning_rate": 0.00013588235294117649, |
|
"loss": 0.2584, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 6.76, |
|
"learning_rate": 0.00013294117647058822, |
|
"loss": 0.1437, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 7.06, |
|
"learning_rate": 0.00013000000000000002, |
|
"loss": 0.1991, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 7.35, |
|
"learning_rate": 0.00012705882352941175, |
|
"loss": 0.1776, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 7.65, |
|
"learning_rate": 0.00012411764705882355, |
|
"loss": 0.133, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 7.94, |
|
"learning_rate": 0.0001211764705882353, |
|
"loss": 0.1119, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 8.24, |
|
"learning_rate": 0.00011823529411764706, |
|
"loss": 0.087, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 8.53, |
|
"learning_rate": 0.00011529411764705881, |
|
"loss": 0.0795, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 8.82, |
|
"learning_rate": 0.00011235294117647059, |
|
"loss": 0.1663, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 8.82, |
|
"eval_accuracy": 0.9398496240601504, |
|
"eval_loss": 0.1752895563840866, |
|
"eval_runtime": 2.5567, |
|
"eval_samples_per_second": 104.042, |
|
"eval_steps_per_second": 13.299, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 9.12, |
|
"learning_rate": 0.00010941176470588237, |
|
"loss": 0.1149, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 9.41, |
|
"learning_rate": 0.00010647058823529412, |
|
"loss": 0.1415, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 9.71, |
|
"learning_rate": 0.0001035294117647059, |
|
"loss": 0.0998, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 10.0, |
|
"learning_rate": 0.00010058823529411765, |
|
"loss": 0.1299, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 10.29, |
|
"learning_rate": 9.764705882352942e-05, |
|
"loss": 0.1028, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 10.59, |
|
"learning_rate": 9.470588235294118e-05, |
|
"loss": 0.0636, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 10.88, |
|
"learning_rate": 9.176470588235295e-05, |
|
"loss": 0.1064, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 11.18, |
|
"learning_rate": 8.882352941176471e-05, |
|
"loss": 0.1138, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 11.47, |
|
"learning_rate": 8.588235294117646e-05, |
|
"loss": 0.0469, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 11.76, |
|
"learning_rate": 8.294117647058824e-05, |
|
"loss": 0.0962, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 11.76, |
|
"eval_accuracy": 0.9398496240601504, |
|
"eval_loss": 0.20087337493896484, |
|
"eval_runtime": 2.1402, |
|
"eval_samples_per_second": 124.286, |
|
"eval_steps_per_second": 15.886, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 12.06, |
|
"learning_rate": 8e-05, |
|
"loss": 0.1099, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 12.35, |
|
"learning_rate": 7.705882352941177e-05, |
|
"loss": 0.0475, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 12.65, |
|
"learning_rate": 7.411764705882354e-05, |
|
"loss": 0.0448, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 12.94, |
|
"learning_rate": 7.11764705882353e-05, |
|
"loss": 0.0782, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 13.24, |
|
"learning_rate": 6.823529411764707e-05, |
|
"loss": 0.0543, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 13.53, |
|
"learning_rate": 6.529411764705883e-05, |
|
"loss": 0.0252, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 13.82, |
|
"learning_rate": 6.23529411764706e-05, |
|
"loss": 0.0517, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 14.12, |
|
"learning_rate": 5.9411764705882355e-05, |
|
"loss": 0.0179, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 14.41, |
|
"learning_rate": 5.647058823529412e-05, |
|
"loss": 0.0661, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 14.71, |
|
"learning_rate": 5.3529411764705884e-05, |
|
"loss": 0.0612, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 14.71, |
|
"eval_accuracy": 0.9586466165413534, |
|
"eval_loss": 0.13481324911117554, |
|
"eval_runtime": 2.1446, |
|
"eval_samples_per_second": 124.03, |
|
"eval_steps_per_second": 15.853, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 15.0, |
|
"learning_rate": 5.058823529411765e-05, |
|
"loss": 0.0611, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 15.29, |
|
"learning_rate": 4.7647058823529414e-05, |
|
"loss": 0.0208, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 15.59, |
|
"learning_rate": 4.470588235294118e-05, |
|
"loss": 0.0838, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 15.88, |
|
"learning_rate": 4.1764705882352944e-05, |
|
"loss": 0.0558, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 16.18, |
|
"learning_rate": 3.882352941176471e-05, |
|
"loss": 0.0544, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 16.47, |
|
"learning_rate": 3.5882352941176474e-05, |
|
"loss": 0.0729, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 16.76, |
|
"learning_rate": 3.294117647058824e-05, |
|
"loss": 0.0799, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 17.06, |
|
"learning_rate": 3e-05, |
|
"loss": 0.011, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 17.35, |
|
"learning_rate": 2.7058823529411766e-05, |
|
"loss": 0.0749, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 17.65, |
|
"learning_rate": 2.411764705882353e-05, |
|
"loss": 0.0341, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 17.65, |
|
"eval_accuracy": 0.9661654135338346, |
|
"eval_loss": 0.09556835144758224, |
|
"eval_runtime": 2.4514, |
|
"eval_samples_per_second": 108.508, |
|
"eval_steps_per_second": 13.869, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 17.94, |
|
"learning_rate": 2.1176470588235296e-05, |
|
"loss": 0.0134, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 18.24, |
|
"learning_rate": 1.8235294117647057e-05, |
|
"loss": 0.0339, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 18.53, |
|
"learning_rate": 1.5294117647058826e-05, |
|
"loss": 0.0383, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 18.82, |
|
"learning_rate": 1.2352941176470589e-05, |
|
"loss": 0.0209, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 19.12, |
|
"learning_rate": 9.411764705882354e-06, |
|
"loss": 0.0418, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 19.41, |
|
"learning_rate": 6.470588235294119e-06, |
|
"loss": 0.0431, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 19.71, |
|
"learning_rate": 3.5294117647058825e-06, |
|
"loss": 0.0334, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"learning_rate": 5.882352941176471e-07, |
|
"loss": 0.0208, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 20.0, |
|
"step": 680, |
|
"total_flos": 1.646033084688384e+18, |
|
"train_loss": 0.19354178275474732, |
|
"train_runtime": 444.6785, |
|
"train_samples_per_second": 47.765, |
|
"train_steps_per_second": 1.529 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 680, |
|
"num_train_epochs": 20, |
|
"save_steps": 100, |
|
"total_flos": 1.646033084688384e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|