| { |
| "best_global_step": 1044, |
| "best_metric": 0.5757657386587794, |
| "best_model_checkpoint": "outputs/sphobert/checkpoint-1044", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 1044, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.9942528735632183, |
| "grad_norm": 2.9008371829986572, |
| "learning_rate": 6.88e-06, |
| "loss": 1.8374, |
| "step": 173 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.36151603498542273, |
| "eval_loss": 1.6538399457931519, |
| "eval_macro_f1": 0.12427577080113439, |
| "eval_runtime": 2.3445, |
| "eval_samples_per_second": 292.594, |
| "eval_steps_per_second": 9.383, |
| "step": 174 |
| }, |
| { |
| "epoch": 1.9885057471264367, |
| "grad_norm": 5.04294490814209, |
| "learning_rate": 1.38e-05, |
| "loss": 1.5114, |
| "step": 346 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.5714285714285714, |
| "eval_loss": 1.288612961769104, |
| "eval_macro_f1": 0.3368739510250213, |
| "eval_runtime": 2.3333, |
| "eval_samples_per_second": 294.008, |
| "eval_steps_per_second": 9.429, |
| "step": 348 |
| }, |
| { |
| "epoch": 2.9827586206896552, |
| "grad_norm": 9.86268424987793, |
| "learning_rate": 1.999994401896218e-05, |
| "loss": 1.2061, |
| "step": 519 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.5932944606413995, |
| "eval_loss": 1.1434780359268188, |
| "eval_macro_f1": 0.44654044005012145, |
| "eval_runtime": 2.3334, |
| "eval_samples_per_second": 293.996, |
| "eval_steps_per_second": 9.428, |
| "step": 522 |
| }, |
| { |
| "epoch": 3.9770114942528734, |
| "grad_norm": 10.016560554504395, |
| "learning_rate": 1.9993697433304146e-05, |
| "loss": 0.9586, |
| "step": 692 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.6064139941690962, |
| "eval_loss": 1.098654866218567, |
| "eval_macro_f1": 0.5279342346245351, |
| "eval_runtime": 2.3198, |
| "eval_samples_per_second": 295.715, |
| "eval_steps_per_second": 9.484, |
| "step": 696 |
| }, |
| { |
| "epoch": 4.971264367816092, |
| "grad_norm": 17.420209884643555, |
| "learning_rate": 1.9977115923137912e-05, |
| "loss": 0.749, |
| "step": 865 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.607871720116618, |
| "eval_loss": 1.151617169380188, |
| "eval_macro_f1": 0.5323374869939401, |
| "eval_runtime": 2.3348, |
| "eval_samples_per_second": 293.82, |
| "eval_steps_per_second": 9.423, |
| "step": 870 |
| }, |
| { |
| "epoch": 5.9655172413793105, |
| "grad_norm": 11.11704158782959, |
| "learning_rate": 1.995021663613649e-05, |
| "loss": 0.6129, |
| "step": 1038 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.6355685131195336, |
| "eval_loss": 1.093395709991455, |
| "eval_macro_f1": 0.5757657386587794, |
| "eval_runtime": 2.333, |
| "eval_samples_per_second": 294.038, |
| "eval_steps_per_second": 9.43, |
| "step": 1044 |
| } |
| ], |
| "logging_steps": 173, |
| "max_steps": 17400, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 100, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 5, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
