| { |
| "best_global_step": 18750, |
| "best_metric": 0.9103205410380567, |
| "best_model_checkpoint": "./results_colab/checkpoint-18750", |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 18750, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.14992, |
| "grad_norm": 14.149627685546875, |
| "learning_rate": 9.930666666666668e-06, |
| "loss": 0.4914, |
| "step": 937 |
| }, |
| { |
| "epoch": 0.29984, |
| "grad_norm": 8.850069046020508, |
| "learning_rate": 1.9925333333333334e-05, |
| "loss": 0.3457, |
| "step": 1874 |
| }, |
| { |
| "epoch": 0.44976, |
| "grad_norm": 6.119201183319092, |
| "learning_rate": 1.889777777777778e-05, |
| "loss": 0.3199, |
| "step": 2811 |
| }, |
| { |
| "epoch": 0.59968, |
| "grad_norm": 10.599540710449219, |
| "learning_rate": 1.778725925925926e-05, |
| "loss": 0.3056, |
| "step": 3748 |
| }, |
| { |
| "epoch": 0.7496, |
| "grad_norm": 9.924508094787598, |
| "learning_rate": 1.6677925925925925e-05, |
| "loss": 0.2968, |
| "step": 4685 |
| }, |
| { |
| "epoch": 0.89952, |
| "grad_norm": 7.44782018661499, |
| "learning_rate": 1.556740740740741e-05, |
| "loss": 0.2951, |
| "step": 5622 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.89456, |
| "eval_f1": 0.8978136145138781, |
| "eval_loss": 0.28082841634750366, |
| "eval_runtime": 40.5573, |
| "eval_samples_per_second": 616.412, |
| "eval_steps_per_second": 19.281, |
| "step": 6250 |
| }, |
| { |
| "epoch": 1.04944, |
| "grad_norm": 29.62865447998047, |
| "learning_rate": 1.445688888888889e-05, |
| "loss": 0.2643, |
| "step": 6559 |
| }, |
| { |
| "epoch": 1.19936, |
| "grad_norm": 3.2325656414031982, |
| "learning_rate": 1.3348740740740742e-05, |
| "loss": 0.2375, |
| "step": 7496 |
| }, |
| { |
| "epoch": 1.34928, |
| "grad_norm": 13.932371139526367, |
| "learning_rate": 1.2238222222222222e-05, |
| "loss": 0.2456, |
| "step": 8433 |
| }, |
| { |
| "epoch": 1.4992, |
| "grad_norm": 21.482507705688477, |
| "learning_rate": 1.1127703703703705e-05, |
| "loss": 0.2427, |
| "step": 9370 |
| }, |
| { |
| "epoch": 1.64912, |
| "grad_norm": 13.899144172668457, |
| "learning_rate": 1.0017185185185185e-05, |
| "loss": 0.2296, |
| "step": 10307 |
| }, |
| { |
| "epoch": 1.79904, |
| "grad_norm": 10.691402435302734, |
| "learning_rate": 8.906666666666667e-06, |
| "loss": 0.2344, |
| "step": 11244 |
| }, |
| { |
| "epoch": 1.94896, |
| "grad_norm": 24.025405883789062, |
| "learning_rate": 7.797333333333334e-06, |
| "loss": 0.2338, |
| "step": 12181 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.90812, |
| "eval_f1": 0.9074797599387764, |
| "eval_loss": 0.2600798010826111, |
| "eval_runtime": 40.4948, |
| "eval_samples_per_second": 617.364, |
| "eval_steps_per_second": 19.311, |
| "step": 12500 |
| }, |
| { |
| "epoch": 2.09888, |
| "grad_norm": 19.96436882019043, |
| "learning_rate": 6.686814814814815e-06, |
| "loss": 0.2024, |
| "step": 13118 |
| }, |
| { |
| "epoch": 2.2488, |
| "grad_norm": 16.892995834350586, |
| "learning_rate": 5.577481481481481e-06, |
| "loss": 0.1841, |
| "step": 14055 |
| }, |
| { |
| "epoch": 2.39872, |
| "grad_norm": 32.59613037109375, |
| "learning_rate": 4.468148148148149e-06, |
| "loss": 0.1809, |
| "step": 14992 |
| }, |
| { |
| "epoch": 2.54864, |
| "grad_norm": 21.280284881591797, |
| "learning_rate": 3.35762962962963e-06, |
| "loss": 0.1873, |
| "step": 15929 |
| }, |
| { |
| "epoch": 2.69856, |
| "grad_norm": 59.44868850708008, |
| "learning_rate": 2.2471111111111115e-06, |
| "loss": 0.1905, |
| "step": 16866 |
| }, |
| { |
| "epoch": 2.84848, |
| "grad_norm": 0.4454441964626312, |
| "learning_rate": 1.1365925925925928e-06, |
| "loss": 0.1787, |
| "step": 17803 |
| }, |
| { |
| "epoch": 2.9984, |
| "grad_norm": 19.224084854125977, |
| "learning_rate": 2.725925925925926e-08, |
| "loss": 0.1906, |
| "step": 18740 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.91036, |
| "eval_f1": 0.9103205410380567, |
| "eval_loss": 0.33635860681533813, |
| "eval_runtime": 40.5996, |
| "eval_samples_per_second": 615.77, |
| "eval_steps_per_second": 19.261, |
| "step": 18750 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 18750, |
| "total_flos": 1.955528518972608e+16, |
| "train_loss": 0.25284169124603273, |
| "train_runtime": 4088.9553, |
| "train_samples_per_second": 73.368, |
| "train_steps_per_second": 4.586 |
| } |
| ], |
| "logging_steps": 937, |
| "max_steps": 18750, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 0 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.955528518972608e+16, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
