| { |
| "best_global_step": 264, |
| "best_metric": 0.4330384135246277, |
| "best_model_checkpoint": "distilbert_rand_100_v1_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": 9.514628410339355, |
| "learning_rate": 4.9e-05, |
| "loss": 0.3969, |
| "step": 264 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8222477064220184, |
| "eval_loss": 0.4330384135246277, |
| "eval_runtime": 0.3723, |
| "eval_samples_per_second": 2342.49, |
| "eval_steps_per_second": 10.745, |
| "step": 264 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 6.883841037750244, |
| "learning_rate": 4.8e-05, |
| "loss": 0.2239, |
| "step": 528 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8176605504587156, |
| "eval_loss": 0.4783160090446472, |
| "eval_runtime": 0.3655, |
| "eval_samples_per_second": 2385.515, |
| "eval_steps_per_second": 10.943, |
| "step": 528 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 4.657165050506592, |
| "learning_rate": 4.7e-05, |
| "loss": 0.1657, |
| "step": 792 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8119266055045872, |
| "eval_loss": 0.49851399660110474, |
| "eval_runtime": 0.3767, |
| "eval_samples_per_second": 2314.857, |
| "eval_steps_per_second": 10.619, |
| "step": 792 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 7.434548854827881, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.1252, |
| "step": 1056 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8004587155963303, |
| "eval_loss": 0.6079992055892944, |
| "eval_runtime": 0.3962, |
| "eval_samples_per_second": 2201.167, |
| "eval_steps_per_second": 10.097, |
| "step": 1056 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 5.460722923278809, |
| "learning_rate": 4.5e-05, |
| "loss": 0.0942, |
| "step": 1320 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8107798165137615, |
| "eval_loss": 0.6070181727409363, |
| "eval_runtime": 0.3821, |
| "eval_samples_per_second": 2281.949, |
| "eval_steps_per_second": 10.468, |
| "step": 1320 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 12.805521965026855, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.0745, |
| "step": 1584 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8153669724770642, |
| "eval_loss": 0.7813127636909485, |
| "eval_runtime": 0.3722, |
| "eval_samples_per_second": 2342.651, |
| "eval_steps_per_second": 10.746, |
| "step": 1584 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 1584, |
| "total_flos": 2.676464049624883e+16, |
| "train_loss": 0.18007493741584546, |
| "train_runtime": 376.8276, |
| "train_samples_per_second": 8936.315, |
| "train_steps_per_second": 35.029 |
| } |
| ], |
| "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": 2.676464049624883e+16, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
