| { | |
| "best_metric": 0.3489038348197937, | |
| "best_model_checkpoint": "bert_tiny_lda_100_v1_book_sst2/checkpoint-264", | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 1584, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 8.271644592285156, | |
| "learning_rate": 4.9e-05, | |
| "loss": 0.3634, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8555045871559633, | |
| "eval_loss": 0.3489038348197937, | |
| "eval_runtime": 0.277, | |
| "eval_samples_per_second": 3148.234, | |
| "eval_steps_per_second": 14.441, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 15.306727409362793, | |
| "learning_rate": 4.8e-05, | |
| "loss": 0.2189, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8600917431192661, | |
| "eval_loss": 0.36337217688560486, | |
| "eval_runtime": 0.3273, | |
| "eval_samples_per_second": 2664.447, | |
| "eval_steps_per_second": 12.222, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 6.631307125091553, | |
| "learning_rate": 4.7e-05, | |
| "loss": 0.1528, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8646788990825688, | |
| "eval_loss": 0.4506845772266388, | |
| "eval_runtime": 0.2825, | |
| "eval_samples_per_second": 3086.85, | |
| "eval_steps_per_second": 14.16, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 2.8820979595184326, | |
| "learning_rate": 4.600000000000001e-05, | |
| "loss": 0.1199, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8761467889908257, | |
| "eval_loss": 0.382750540971756, | |
| "eval_runtime": 0.2751, | |
| "eval_samples_per_second": 3169.237, | |
| "eval_steps_per_second": 14.538, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 2.706533193588257, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.094, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8727064220183486, | |
| "eval_loss": 0.3957236707210541, | |
| "eval_runtime": 0.2958, | |
| "eval_samples_per_second": 2947.786, | |
| "eval_steps_per_second": 13.522, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 4.119465351104736, | |
| "learning_rate": 4.4000000000000006e-05, | |
| "loss": 0.0742, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8589449541284404, | |
| "eval_loss": 0.47635790705680847, | |
| "eval_runtime": 0.3084, | |
| "eval_samples_per_second": 2827.358, | |
| "eval_steps_per_second": 12.97, | |
| "step": 1584 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 1584, | |
| "total_flos": 1.0596790573590528e+16, | |
| "train_loss": 0.1705179467345729, | |
| "train_runtime": 228.7859, | |
| "train_samples_per_second": 14718.786, | |
| "train_steps_per_second": 57.696 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 13200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 5 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0596790573590528e+16, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |