| { |
| "best_metric": 0.8965343146604436, |
| "best_model_checkpoint": "training_with_callbacks/checkpoint-16560", |
| "epoch": 10.0, |
| "global_step": 18400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.27, |
| "learning_rate": 1.9457608695652174e-05, |
| "loss": 0.3778, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 1.891521739130435e-05, |
| "loss": 0.3215, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 1.8372826086956523e-05, |
| "loss": 0.3086, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8627715237038212, |
| "eval_loss": 0.2784997820854187, |
| "eval_macro_f1": 0.8626735051064052, |
| "eval_micro_f1": 0.8627715237038212, |
| "eval_runtime": 53.6768, |
| "eval_samples_per_second": 234.999, |
| "eval_steps_per_second": 14.699, |
| "step": 1840 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 1.7830434782608696e-05, |
| "loss": 0.2987, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 1.728695652173913e-05, |
| "loss": 0.2549, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 1.6743478260869566e-05, |
| "loss": 0.2578, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.9, |
| "learning_rate": 1.6201086956521742e-05, |
| "loss": 0.2513, |
| "step": 3500 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8756143967020771, |
| "eval_loss": 0.26244285702705383, |
| "eval_macro_f1": 0.8755535151960584, |
| "eval_micro_f1": 0.8756143967020771, |
| "eval_runtime": 53.7192, |
| "eval_samples_per_second": 234.814, |
| "eval_steps_per_second": 14.687, |
| "step": 3680 |
| }, |
| { |
| "epoch": 2.17, |
| "learning_rate": 1.5657608695652177e-05, |
| "loss": 0.2369, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.45, |
| "learning_rate": 1.511413043478261e-05, |
| "loss": 0.2101, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.72, |
| "learning_rate": 1.4570652173913045e-05, |
| "loss": 0.2086, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.99, |
| "learning_rate": 1.402717391304348e-05, |
| "loss": 0.2054, |
| "step": 5500 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8752972887268115, |
| "eval_loss": 0.2643134295940399, |
| "eval_macro_f1": 0.8747081066407124, |
| "eval_micro_f1": 0.8752972887268115, |
| "eval_runtime": 53.4868, |
| "eval_samples_per_second": 235.834, |
| "eval_steps_per_second": 14.751, |
| "step": 5520 |
| }, |
| { |
| "epoch": 3.26, |
| "learning_rate": 1.3483695652173915e-05, |
| "loss": 0.1676, |
| "step": 6000 |
| }, |
| { |
| "epoch": 3.53, |
| "learning_rate": 1.2940217391304348e-05, |
| "loss": 0.166, |
| "step": 6500 |
| }, |
| { |
| "epoch": 3.8, |
| "learning_rate": 1.2396739130434783e-05, |
| "loss": 0.1687, |
| "step": 7000 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8905977485333756, |
| "eval_loss": 0.2898699641227722, |
| "eval_macro_f1": 0.8905713282411306, |
| "eval_micro_f1": 0.8905977485333756, |
| "eval_runtime": 53.2546, |
| "eval_samples_per_second": 236.862, |
| "eval_steps_per_second": 14.816, |
| "step": 7360 |
| }, |
| { |
| "epoch": 4.08, |
| "learning_rate": 1.1853260869565217e-05, |
| "loss": 0.1576, |
| "step": 7500 |
| }, |
| { |
| "epoch": 4.35, |
| "learning_rate": 1.1309782608695654e-05, |
| "loss": 0.1337, |
| "step": 8000 |
| }, |
| { |
| "epoch": 4.62, |
| "learning_rate": 1.0766304347826089e-05, |
| "loss": 0.132, |
| "step": 8500 |
| }, |
| { |
| "epoch": 4.89, |
| "learning_rate": 1.0223913043478262e-05, |
| "loss": 0.1362, |
| "step": 9000 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8894085936261297, |
| "eval_loss": 0.31742656230926514, |
| "eval_macro_f1": 0.8893640862987704, |
| "eval_micro_f1": 0.8894085936261297, |
| "eval_runtime": 53.5229, |
| "eval_samples_per_second": 235.675, |
| "eval_steps_per_second": 14.741, |
| "step": 9200 |
| }, |
| { |
| "epoch": 5.16, |
| "learning_rate": 9.680434782608696e-06, |
| "loss": 0.1243, |
| "step": 9500 |
| }, |
| { |
| "epoch": 5.43, |
| "learning_rate": 9.136956521739131e-06, |
| "loss": 0.1091, |
| "step": 10000 |
| }, |
| { |
| "epoch": 5.71, |
| "learning_rate": 8.593478260869566e-06, |
| "loss": 0.1092, |
| "step": 10500 |
| }, |
| { |
| "epoch": 5.98, |
| "learning_rate": 8.050000000000001e-06, |
| "loss": 0.1094, |
| "step": 11000 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8942444902489297, |
| "eval_loss": 0.36500877141952515, |
| "eval_macro_f1": 0.8942443599760673, |
| "eval_micro_f1": 0.8942444902489296, |
| "eval_runtime": 53.6838, |
| "eval_samples_per_second": 234.969, |
| "eval_steps_per_second": 14.697, |
| "step": 11040 |
| }, |
| { |
| "epoch": 6.25, |
| "learning_rate": 7.5076086956521745e-06, |
| "loss": 0.0934, |
| "step": 11500 |
| }, |
| { |
| "epoch": 6.52, |
| "learning_rate": 6.9641304347826085e-06, |
| "loss": 0.087, |
| "step": 12000 |
| }, |
| { |
| "epoch": 6.79, |
| "learning_rate": 6.420652173913044e-06, |
| "loss": 0.0921, |
| "step": 12500 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.8950372601870937, |
| "eval_loss": 0.3785378932952881, |
| "eval_macro_f1": 0.8949877111068857, |
| "eval_micro_f1": 0.8950372601870938, |
| "eval_runtime": 52.9409, |
| "eval_samples_per_second": 238.266, |
| "eval_steps_per_second": 14.903, |
| "step": 12880 |
| }, |
| { |
| "epoch": 7.07, |
| "learning_rate": 5.877173913043479e-06, |
| "loss": 0.0833, |
| "step": 13000 |
| }, |
| { |
| "epoch": 7.34, |
| "learning_rate": 5.333695652173914e-06, |
| "loss": 0.073, |
| "step": 13500 |
| }, |
| { |
| "epoch": 7.61, |
| "learning_rate": 4.790217391304348e-06, |
| "loss": 0.0758, |
| "step": 14000 |
| }, |
| { |
| "epoch": 7.88, |
| "learning_rate": 4.246739130434783e-06, |
| "loss": 0.077, |
| "step": 14500 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy": 0.8950372601870937, |
| "eval_loss": 0.48974281549453735, |
| "eval_macro_f1": 0.8950314309820686, |
| "eval_micro_f1": 0.8950372601870938, |
| "eval_runtime": 52.5947, |
| "eval_samples_per_second": 239.834, |
| "eval_steps_per_second": 15.001, |
| "step": 14720 |
| }, |
| { |
| "epoch": 8.15, |
| "learning_rate": 3.704347826086957e-06, |
| "loss": 0.0666, |
| "step": 15000 |
| }, |
| { |
| "epoch": 8.42, |
| "learning_rate": 3.1608695652173916e-06, |
| "loss": 0.0588, |
| "step": 15500 |
| }, |
| { |
| "epoch": 8.7, |
| "learning_rate": 2.617391304347826e-06, |
| "loss": 0.061, |
| "step": 16000 |
| }, |
| { |
| "epoch": 8.97, |
| "learning_rate": 2.0739130434782612e-06, |
| "loss": 0.059, |
| "step": 16500 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy": 0.8965435230696052, |
| "eval_loss": 0.5619444847106934, |
| "eval_macro_f1": 0.8965343146604436, |
| "eval_micro_f1": 0.8965435230696052, |
| "eval_runtime": 52.94, |
| "eval_samples_per_second": 238.27, |
| "eval_steps_per_second": 14.904, |
| "step": 16560 |
| }, |
| { |
| "epoch": 9.24, |
| "learning_rate": 1.5304347826086956e-06, |
| "loss": 0.052, |
| "step": 17000 |
| }, |
| { |
| "epoch": 9.51, |
| "learning_rate": 9.869565217391304e-07, |
| "loss": 0.0495, |
| "step": 17500 |
| }, |
| { |
| "epoch": 9.78, |
| "learning_rate": 4.445652173913044e-07, |
| "loss": 0.0467, |
| "step": 18000 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy": 0.8951165371809101, |
| "eval_loss": 0.6173644065856934, |
| "eval_macro_f1": 0.8951162464835035, |
| "eval_micro_f1": 0.8951165371809101, |
| "eval_runtime": 53.4503, |
| "eval_samples_per_second": 235.995, |
| "eval_steps_per_second": 14.761, |
| "step": 18400 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 18400, |
| "total_flos": 1.548750605165568e+17, |
| "train_loss": 0.148325269014939, |
| "train_runtime": 6107.1251, |
| "train_samples_per_second": 96.384, |
| "train_steps_per_second": 3.013 |
| } |
| ], |
| "max_steps": 18400, |
| "num_train_epochs": 10, |
| "total_flos": 1.548750605165568e+17, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
