| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "global_step": 52940, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 1.8000377786173025e-05, |
| "loss": 0.1263, |
| "step": 5293 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy_thresh": 0.9616630673408508, |
| "eval_f1_macro": 0.16946832551734195, |
| "eval_f1_micro": 0.23566588370481772, |
| "eval_loss": 0.11356716603040695, |
| "eval_runtime": 48.6873, |
| "eval_samples_per_second": 859.506, |
| "eval_steps_per_second": 26.865, |
| "step": 5294 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 1.6000755572346052e-05, |
| "loss": 0.1102, |
| "step": 10586 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy_thresh": 0.9620087146759033, |
| "eval_f1_macro": 0.17900886975226568, |
| "eval_f1_micro": 0.2526954290189805, |
| "eval_loss": 0.11111615598201752, |
| "eval_runtime": 47.7242, |
| "eval_samples_per_second": 876.85, |
| "eval_steps_per_second": 27.407, |
| "step": 10588 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 1.400113335851908e-05, |
| "loss": 0.1051, |
| "step": 15879 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy_thresh": 0.9615273475646973, |
| "eval_f1_macro": 0.2072184242961422, |
| "eval_f1_micro": 0.27365762031219637, |
| "eval_loss": 0.1117364689707756, |
| "eval_runtime": 47.6559, |
| "eval_samples_per_second": 878.107, |
| "eval_steps_per_second": 27.447, |
| "step": 15882 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 1.2001511144692106e-05, |
| "loss": 0.1008, |
| "step": 21172 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy_thresh": 0.9611817002296448, |
| "eval_f1_macro": 0.22506513860997251, |
| "eval_f1_micro": 0.2893829659382017, |
| "eval_loss": 0.11295813322067261, |
| "eval_runtime": 48.0019, |
| "eval_samples_per_second": 871.779, |
| "eval_steps_per_second": 27.249, |
| "step": 21176 |
| }, |
| { |
| "epoch": 5.0, |
| "learning_rate": 1.0001888930865132e-05, |
| "loss": 0.0969, |
| "step": 26465 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy_thresh": 0.9608395099639893, |
| "eval_f1_macro": 0.2055009373845579, |
| "eval_f1_micro": 0.28528452452579245, |
| "eval_loss": 0.11423922330141068, |
| "eval_runtime": 47.8236, |
| "eval_samples_per_second": 875.029, |
| "eval_steps_per_second": 27.351, |
| "step": 26470 |
| }, |
| { |
| "epoch": 6.0, |
| "learning_rate": 8.002266717038157e-06, |
| "loss": 0.0935, |
| "step": 31758 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy_thresh": 0.9599553346633911, |
| "eval_f1_macro": 0.24715534791751095, |
| "eval_f1_micro": 0.31626149162404954, |
| "eval_loss": 0.11684752255678177, |
| "eval_runtime": 47.548, |
| "eval_samples_per_second": 880.101, |
| "eval_steps_per_second": 27.509, |
| "step": 31764 |
| }, |
| { |
| "epoch": 7.0, |
| "learning_rate": 6.002644503211182e-06, |
| "loss": 0.0905, |
| "step": 37051 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy_thresh": 0.9595038294792175, |
| "eval_f1_macro": 0.2441714312173638, |
| "eval_f1_micro": 0.3219438566376134, |
| "eval_loss": 0.11869944632053375, |
| "eval_runtime": 47.7399, |
| "eval_samples_per_second": 876.562, |
| "eval_steps_per_second": 27.398, |
| "step": 37058 |
| }, |
| { |
| "epoch": 8.0, |
| "learning_rate": 4.003022289384209e-06, |
| "loss": 0.088, |
| "step": 42344 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_accuracy_thresh": 0.9587323069572449, |
| "eval_f1_macro": 0.2548664525024525, |
| "eval_f1_micro": 0.32230417164679476, |
| "eval_loss": 0.12079060822725296, |
| "eval_runtime": 47.4927, |
| "eval_samples_per_second": 881.125, |
| "eval_steps_per_second": 27.541, |
| "step": 42352 |
| }, |
| { |
| "epoch": 9.0, |
| "learning_rate": 2.0034000755572347e-06, |
| "loss": 0.0858, |
| "step": 47637 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_accuracy_thresh": 0.958522379398346, |
| "eval_f1_macro": 0.25593002791116004, |
| "eval_f1_micro": 0.326565974528547, |
| "eval_loss": 0.12228038907051086, |
| "eval_runtime": 47.6614, |
| "eval_samples_per_second": 878.006, |
| "eval_steps_per_second": 27.444, |
| "step": 47646 |
| }, |
| { |
| "epoch": 10.0, |
| "learning_rate": 3.777861730260673e-09, |
| "loss": 0.0841, |
| "step": 52930 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_accuracy_thresh": 0.9580487012863159, |
| "eval_f1_macro": 0.26093237174433664, |
| "eval_f1_micro": 0.3314736272807492, |
| "eval_loss": 0.12347622960805893, |
| "eval_runtime": 47.9519, |
| "eval_samples_per_second": 872.686, |
| "eval_steps_per_second": 27.277, |
| "step": 52940 |
| } |
| ], |
| "max_steps": 52940, |
| "num_train_epochs": 10, |
| "total_flos": 1.603873359628872e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
