| { | |
| "best_metric": 0.9814814814814815, | |
| "best_model_checkpoint": "vit-base-patch16-224-Trial007-YEL_STEM2/checkpoint-20", | |
| "epoch": 44.44444444444444, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6465, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 1e-05, | |
| "loss": 0.6676, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "eval_accuracy": 0.7222222222222222, | |
| "eval_loss": 0.6180152297019958, | |
| "eval_runtime": 0.2619, | |
| "eval_samples_per_second": 206.218, | |
| "eval_steps_per_second": 3.819, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.5752, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5805, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.78, | |
| "eval_accuracy": 0.7592592592592593, | |
| "eval_loss": 0.5003750920295715, | |
| "eval_runtime": 0.2607, | |
| "eval_samples_per_second": 207.107, | |
| "eval_steps_per_second": 3.835, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.22, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.4833, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "learning_rate": 3e-05, | |
| "loss": 0.5012, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.67, | |
| "eval_accuracy": 0.9629629629629629, | |
| "eval_loss": 0.37833932042121887, | |
| "eval_runtime": 0.2715, | |
| "eval_samples_per_second": 198.886, | |
| "eval_steps_per_second": 3.683, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 3.11, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.3602, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 3.56, | |
| "learning_rate": 4e-05, | |
| "loss": 0.396, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.2794, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9629629629629629, | |
| "eval_loss": 0.22847579419612885, | |
| "eval_runtime": 0.269, | |
| "eval_samples_per_second": 200.773, | |
| "eval_steps_per_second": 3.718, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 4.44, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3094, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "learning_rate": 4.9444444444444446e-05, | |
| "loss": 0.2695, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 4.89, | |
| "eval_accuracy": 0.8888888888888888, | |
| "eval_loss": 0.25508877635002136, | |
| "eval_runtime": 0.2701, | |
| "eval_samples_per_second": 199.957, | |
| "eval_steps_per_second": 3.703, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 5.33, | |
| "learning_rate": 4.888888888888889e-05, | |
| "loss": 0.2595, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "learning_rate": 4.8333333333333334e-05, | |
| "loss": 0.2782, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "eval_accuracy": 0.9629629629629629, | |
| "eval_loss": 0.10787578672170639, | |
| "eval_runtime": 0.2599, | |
| "eval_samples_per_second": 207.776, | |
| "eval_steps_per_second": 3.848, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 6.22, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 0.1556, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "learning_rate": 4.722222222222222e-05, | |
| "loss": 0.2131, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 6.67, | |
| "eval_accuracy": 0.9629629629629629, | |
| "eval_loss": 0.12049588561058044, | |
| "eval_runtime": 0.2817, | |
| "eval_samples_per_second": 191.698, | |
| "eval_steps_per_second": 3.55, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.1482, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 7.56, | |
| "learning_rate": 4.6111111111111115e-05, | |
| "loss": 0.1872, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 0.1537, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.9629629629629629, | |
| "eval_loss": 0.18612359464168549, | |
| "eval_runtime": 0.2613, | |
| "eval_samples_per_second": 206.693, | |
| "eval_steps_per_second": 3.828, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.1043, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.1739, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 8.89, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.11719384789466858, | |
| "eval_runtime": 0.2622, | |
| "eval_samples_per_second": 205.974, | |
| "eval_steps_per_second": 3.814, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 4.388888888888889e-05, | |
| "loss": 0.3945, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.1059, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.10919703543186188, | |
| "eval_runtime": 0.2607, | |
| "eval_samples_per_second": 207.114, | |
| "eval_steps_per_second": 3.835, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 4.277777777777778e-05, | |
| "loss": 0.1378, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 4.222222222222222e-05, | |
| "loss": 0.146, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.10719860345125198, | |
| "eval_runtime": 0.2613, | |
| "eval_samples_per_second": 206.624, | |
| "eval_steps_per_second": 3.826, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 11.11, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.1155, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 11.56, | |
| "learning_rate": 4.111111111111111e-05, | |
| "loss": 0.0854, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 4.055555555555556e-05, | |
| "loss": 0.088, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.10145124793052673, | |
| "eval_runtime": 0.2622, | |
| "eval_samples_per_second": 205.964, | |
| "eval_steps_per_second": 3.814, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 12.44, | |
| "learning_rate": 4e-05, | |
| "loss": 0.09, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "learning_rate": 3.944444444444445e-05, | |
| "loss": 0.1304, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 12.89, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.11511386185884476, | |
| "eval_runtime": 0.2626, | |
| "eval_samples_per_second": 205.674, | |
| "eval_steps_per_second": 3.809, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 13.33, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.0742, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 13.78, | |
| "learning_rate": 3.8333333333333334e-05, | |
| "loss": 0.0924, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 13.78, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.131294846534729, | |
| "eval_runtime": 0.2663, | |
| "eval_samples_per_second": 202.811, | |
| "eval_steps_per_second": 3.756, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 14.22, | |
| "learning_rate": 3.777777777777778e-05, | |
| "loss": 0.0868, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 14.67, | |
| "learning_rate": 3.722222222222222e-05, | |
| "loss": 0.091, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 14.67, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.11780886352062225, | |
| "eval_runtime": 0.2589, | |
| "eval_samples_per_second": 208.602, | |
| "eval_steps_per_second": 3.863, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 15.11, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 0.1066, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 15.56, | |
| "learning_rate": 3.611111111111111e-05, | |
| "loss": 0.1028, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 3.555555555555556e-05, | |
| "loss": 0.0508, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.09711939841508865, | |
| "eval_runtime": 0.2672, | |
| "eval_samples_per_second": 202.064, | |
| "eval_steps_per_second": 3.742, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 16.44, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.1105, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 0.1004, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 16.89, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.11753766983747482, | |
| "eval_runtime": 0.2602, | |
| "eval_samples_per_second": 207.572, | |
| "eval_steps_per_second": 3.844, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 17.33, | |
| "learning_rate": 3.388888888888889e-05, | |
| "loss": 0.0688, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1097, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 17.78, | |
| "eval_accuracy": 0.9629629629629629, | |
| "eval_loss": 0.14230388402938843, | |
| "eval_runtime": 0.2664, | |
| "eval_samples_per_second": 202.739, | |
| "eval_steps_per_second": 3.754, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 18.22, | |
| "learning_rate": 3.277777777777778e-05, | |
| "loss": 0.1049, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 18.67, | |
| "learning_rate": 3.222222222222223e-05, | |
| "loss": 0.0758, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 18.67, | |
| "eval_accuracy": 0.9629629629629629, | |
| "eval_loss": 0.15965422987937927, | |
| "eval_runtime": 0.2786, | |
| "eval_samples_per_second": 193.807, | |
| "eval_steps_per_second": 3.589, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 19.11, | |
| "learning_rate": 3.1666666666666666e-05, | |
| "loss": 0.0947, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 19.56, | |
| "learning_rate": 3.111111111111111e-05, | |
| "loss": 0.0425, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 0.0687, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.12045230716466904, | |
| "eval_runtime": 0.2678, | |
| "eval_samples_per_second": 201.68, | |
| "eval_steps_per_second": 3.735, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 20.44, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0722, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 20.89, | |
| "learning_rate": 2.9444444444444448e-05, | |
| "loss": 0.0513, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 20.89, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.1106700748205185, | |
| "eval_runtime": 0.2701, | |
| "eval_samples_per_second": 199.943, | |
| "eval_steps_per_second": 3.703, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 21.33, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 0.1179, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 21.78, | |
| "learning_rate": 2.8333333333333335e-05, | |
| "loss": 0.0755, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 21.78, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.11499401181936264, | |
| "eval_runtime": 0.2594, | |
| "eval_samples_per_second": 208.189, | |
| "eval_steps_per_second": 3.855, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 22.22, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.0559, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 22.67, | |
| "learning_rate": 2.7222222222222223e-05, | |
| "loss": 0.0897, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 22.67, | |
| "eval_accuracy": 0.9629629629629629, | |
| "eval_loss": 0.13321787118911743, | |
| "eval_runtime": 0.2629, | |
| "eval_samples_per_second": 205.413, | |
| "eval_steps_per_second": 3.804, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 23.11, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.0669, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 23.56, | |
| "learning_rate": 2.6111111111111114e-05, | |
| "loss": 0.0994, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 2.5555555555555554e-05, | |
| "loss": 0.0439, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.12632034718990326, | |
| "eval_runtime": 0.263, | |
| "eval_samples_per_second": 205.294, | |
| "eval_steps_per_second": 3.802, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 24.44, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0317, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.0607, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 24.89, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.11113300919532776, | |
| "eval_runtime": 0.2772, | |
| "eval_samples_per_second": 194.823, | |
| "eval_steps_per_second": 3.608, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 25.33, | |
| "learning_rate": 2.3888888888888892e-05, | |
| "loss": 0.0379, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 25.78, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.0719, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 25.78, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.10038212686777115, | |
| "eval_runtime": 0.2604, | |
| "eval_samples_per_second": 207.335, | |
| "eval_steps_per_second": 3.84, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 26.22, | |
| "learning_rate": 2.277777777777778e-05, | |
| "loss": 0.069, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0599, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 26.67, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.10639392584562302, | |
| "eval_runtime": 0.2743, | |
| "eval_samples_per_second": 196.877, | |
| "eval_steps_per_second": 3.646, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 27.11, | |
| "learning_rate": 2.1666666666666667e-05, | |
| "loss": 0.0882, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 27.56, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 0.0658, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 2.0555555555555555e-05, | |
| "loss": 0.0613, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.1355225145816803, | |
| "eval_runtime": 0.2608, | |
| "eval_samples_per_second": 207.094, | |
| "eval_steps_per_second": 3.835, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 28.44, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0841, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 28.89, | |
| "learning_rate": 1.9444444444444445e-05, | |
| "loss": 0.0689, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 28.89, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.14443787932395935, | |
| "eval_runtime": 0.2612, | |
| "eval_samples_per_second": 206.722, | |
| "eval_steps_per_second": 3.828, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 29.33, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 0.0677, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 29.78, | |
| "learning_rate": 1.8333333333333333e-05, | |
| "loss": 0.0754, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 29.78, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.13980631530284882, | |
| "eval_runtime": 0.2608, | |
| "eval_samples_per_second": 207.038, | |
| "eval_steps_per_second": 3.834, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 30.22, | |
| "learning_rate": 1.777777777777778e-05, | |
| "loss": 0.0538, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 30.67, | |
| "learning_rate": 1.7222222222222224e-05, | |
| "loss": 0.0835, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 30.67, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.13446056842803955, | |
| "eval_runtime": 0.2647, | |
| "eval_samples_per_second": 204.022, | |
| "eval_steps_per_second": 3.778, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 31.11, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0378, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 31.56, | |
| "learning_rate": 1.6111111111111115e-05, | |
| "loss": 0.1164, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "learning_rate": 1.5555555555555555e-05, | |
| "loss": 0.0801, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.13478641211986542, | |
| "eval_runtime": 0.2726, | |
| "eval_samples_per_second": 198.093, | |
| "eval_steps_per_second": 3.668, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 32.44, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0586, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 32.89, | |
| "learning_rate": 1.4444444444444444e-05, | |
| "loss": 0.0701, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 32.89, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.13650549948215485, | |
| "eval_runtime": 0.2625, | |
| "eval_samples_per_second": 205.719, | |
| "eval_steps_per_second": 3.81, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.0728, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 33.78, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.0647, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 33.78, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.13482581079006195, | |
| "eval_runtime": 0.2622, | |
| "eval_samples_per_second": 205.981, | |
| "eval_steps_per_second": 3.814, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 34.22, | |
| "learning_rate": 1.2777777777777777e-05, | |
| "loss": 0.0499, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 34.67, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 0.0982, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 34.67, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.1346072554588318, | |
| "eval_runtime": 0.264, | |
| "eval_samples_per_second": 204.546, | |
| "eval_steps_per_second": 3.788, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 35.11, | |
| "learning_rate": 1.1666666666666668e-05, | |
| "loss": 0.0999, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 35.56, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.0657, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "learning_rate": 1.0555555555555555e-05, | |
| "loss": 0.0671, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.1377686858177185, | |
| "eval_runtime": 0.2607, | |
| "eval_samples_per_second": 207.162, | |
| "eval_steps_per_second": 3.836, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 36.44, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0674, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 36.89, | |
| "learning_rate": 9.444444444444445e-06, | |
| "loss": 0.054, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 36.89, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.1371222585439682, | |
| "eval_runtime": 0.2634, | |
| "eval_samples_per_second": 205.012, | |
| "eval_steps_per_second": 3.797, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 37.33, | |
| "learning_rate": 8.88888888888889e-06, | |
| "loss": 0.0314, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 37.78, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.0735, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 37.78, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.13551822304725647, | |
| "eval_runtime": 0.2625, | |
| "eval_samples_per_second": 205.737, | |
| "eval_steps_per_second": 3.81, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 38.22, | |
| "learning_rate": 7.777777777777777e-06, | |
| "loss": 0.0881, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 38.67, | |
| "learning_rate": 7.222222222222222e-06, | |
| "loss": 0.0736, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 38.67, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.13492508232593536, | |
| "eval_runtime": 0.2758, | |
| "eval_samples_per_second": 195.796, | |
| "eval_steps_per_second": 3.626, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 39.11, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.0648, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 39.56, | |
| "learning_rate": 6.111111111111111e-06, | |
| "loss": 0.0543, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0287, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.13293945789337158, | |
| "eval_runtime": 0.2609, | |
| "eval_samples_per_second": 207.01, | |
| "eval_steps_per_second": 3.834, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 40.44, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0417, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 40.89, | |
| "learning_rate": 4.444444444444445e-06, | |
| "loss": 0.0539, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 40.89, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.1322045475244522, | |
| "eval_runtime": 0.2653, | |
| "eval_samples_per_second": 203.574, | |
| "eval_steps_per_second": 3.77, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 41.33, | |
| "learning_rate": 3.888888888888889e-06, | |
| "loss": 0.0602, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 41.78, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.0483, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 41.78, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.13241925835609436, | |
| "eval_runtime": 0.2756, | |
| "eval_samples_per_second": 195.953, | |
| "eval_steps_per_second": 3.629, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 42.22, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.0855, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 42.67, | |
| "learning_rate": 2.2222222222222225e-06, | |
| "loss": 0.083, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 42.67, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.13193319737911224, | |
| "eval_runtime": 0.2638, | |
| "eval_samples_per_second": 204.69, | |
| "eval_steps_per_second": 3.791, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 43.11, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 0.0501, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 43.56, | |
| "learning_rate": 1.1111111111111112e-06, | |
| "loss": 0.0751, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "learning_rate": 5.555555555555556e-07, | |
| "loss": 0.0558, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.1318960040807724, | |
| "eval_runtime": 0.2634, | |
| "eval_samples_per_second": 204.99, | |
| "eval_steps_per_second": 3.796, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "learning_rate": 0.0, | |
| "loss": 0.0752, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "eval_accuracy": 0.9814814814814815, | |
| "eval_loss": 0.13192817568778992, | |
| "eval_runtime": 0.2735, | |
| "eval_samples_per_second": 197.452, | |
| "eval_steps_per_second": 3.657, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 44.44, | |
| "step": 100, | |
| "total_flos": 1.6586385457107272e+18, | |
| "train_loss": 0.13114935230463742, | |
| "train_runtime": 687.5457, | |
| "train_samples_per_second": 34.979, | |
| "train_steps_per_second": 0.145 | |
| } | |
| ], | |
| "max_steps": 100, | |
| "num_train_epochs": 50, | |
| "total_flos": 1.6586385457107272e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |