| { | |
| "best_metric": 0.7901376146788991, | |
| "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-1054", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 1054, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 7.264369964599609, | |
| "learning_rate": 2.1662503772415e-05, | |
| "loss": 0.9021, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.783256880733945, | |
| "eval_loss": 0.7694150805473328, | |
| "eval_runtime": 2.5918, | |
| "eval_samples_per_second": 336.446, | |
| "eval_steps_per_second": 2.701, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 13.286161422729492, | |
| "learning_rate": 0.0, | |
| "loss": 0.6713, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7901376146788991, | |
| "eval_loss": 0.7401114702224731, | |
| "eval_runtime": 2.6174, | |
| "eval_samples_per_second": 333.153, | |
| "eval_steps_per_second": 2.674, | |
| "step": 1054 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1054, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 16141525436100.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.8796304515753969, | |
| "learning_rate": 4.332500754483e-05, | |
| "num_train_epochs": 2, | |
| "temperature": 9 | |
| } | |
| } | |