| { | |
| "best_metric": 0.801605504587156, | |
| "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-2108", | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 3162, | |
| "is_hyper_param_search": true, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 12.377176284790039, | |
| "learning_rate": 1.5980854192157344e-05, | |
| "loss": 3.0218, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7672018348623854, | |
| "eval_loss": 2.191861391067505, | |
| "eval_runtime": 2.5906, | |
| "eval_samples_per_second": 336.603, | |
| "eval_steps_per_second": 2.702, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": Infinity, | |
| "learning_rate": 1.2796813034327135e-05, | |
| "loss": 2.0797, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.7809633027522935, | |
| "eval_loss": 1.8230279684066772, | |
| "eval_runtime": 2.5719, | |
| "eval_samples_per_second": 339.043, | |
| "eval_steps_per_second": 2.722, | |
| "step": 1054 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 40.96967315673828, | |
| "learning_rate": 9.600642195895665e-06, | |
| "loss": 1.697, | |
| "step": 1581 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.786697247706422, | |
| "eval_loss": 1.7212010622024536, | |
| "eval_runtime": 2.549, | |
| "eval_samples_per_second": 342.099, | |
| "eval_steps_per_second": 2.746, | |
| "step": 1581 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 35.09682846069336, | |
| "learning_rate": 6.4044713574641965e-06, | |
| "loss": 1.5166, | |
| "step": 2108 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.801605504587156, | |
| "eval_loss": 1.6234298944473267, | |
| "eval_runtime": 2.5722, | |
| "eval_samples_per_second": 339.013, | |
| "eval_steps_per_second": 2.721, | |
| "step": 2108 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 10.431685447692871, | |
| "learning_rate": 3.208300519032727e-06, | |
| "loss": 1.4053, | |
| "step": 2635 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.7993119266055045, | |
| "eval_loss": 1.5793094635009766, | |
| "eval_runtime": 2.5626, | |
| "eval_samples_per_second": 340.279, | |
| "eval_steps_per_second": 2.732, | |
| "step": 2635 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 31.159494400024414, | |
| "learning_rate": 1.2129680601257947e-08, | |
| "loss": 1.3567, | |
| "step": 3162 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8004587155963303, | |
| "eval_loss": 1.5706629753112793, | |
| "eval_runtime": 2.5683, | |
| "eval_samples_per_second": 339.518, | |
| "eval_steps_per_second": 2.725, | |
| "step": 3162 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 3162, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "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": 48527917525620.0, | |
| "train_batch_size": 128, | |
| "trial_name": null, | |
| "trial_params": { | |
| "alpha": 0.275210688972374, | |
| "learning_rate": 1.9177025030588814e-05, | |
| "num_train_epochs": 6, | |
| "temperature": 6 | |
| } | |
| } | |