| { |
| "best_global_step": 264, |
| "best_metric": 0.4364422559738159, |
| "best_model_checkpoint": "distilbert_km_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": 8.095394134521484, |
| "learning_rate": 4.9e-05, |
| "loss": 0.4298, |
| "step": 264 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8096330275229358, |
| "eval_loss": 0.4364422559738159, |
| "eval_runtime": 0.3786, |
| "eval_samples_per_second": 2303.256, |
| "eval_steps_per_second": 10.565, |
| "step": 264 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 6.766868591308594, |
| "learning_rate": 4.8e-05, |
| "loss": 0.2336, |
| "step": 528 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8222477064220184, |
| "eval_loss": 0.4899478852748871, |
| "eval_runtime": 0.4009, |
| "eval_samples_per_second": 2175.254, |
| "eval_steps_per_second": 9.978, |
| "step": 528 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 6.997402191162109, |
| "learning_rate": 4.7e-05, |
| "loss": 0.1729, |
| "step": 792 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8061926605504587, |
| "eval_loss": 0.5473707914352417, |
| "eval_runtime": 0.3708, |
| "eval_samples_per_second": 2351.652, |
| "eval_steps_per_second": 10.787, |
| "step": 792 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 6.317209243774414, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.1327, |
| "step": 1056 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8153669724770642, |
| "eval_loss": 0.540567934513092, |
| "eval_runtime": 0.3793, |
| "eval_samples_per_second": 2299.186, |
| "eval_steps_per_second": 10.547, |
| "step": 1056 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 9.744099617004395, |
| "learning_rate": 4.5e-05, |
| "loss": 0.0988, |
| "step": 1320 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8119266055045872, |
| "eval_loss": 0.6099979281425476, |
| "eval_runtime": 0.3709, |
| "eval_samples_per_second": 2351.04, |
| "eval_steps_per_second": 10.785, |
| "step": 1320 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 2.087759256362915, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.0754, |
| "step": 1584 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.805045871559633, |
| "eval_loss": 0.7531437277793884, |
| "eval_runtime": 0.3814, |
| "eval_samples_per_second": 2286.506, |
| "eval_steps_per_second": 10.489, |
| "step": 1584 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 1584, |
| "total_flos": 2.676464049624883e+16, |
| "train_loss": 0.19055030803487757, |
| "train_runtime": 375.8259, |
| "train_samples_per_second": 8960.133, |
| "train_steps_per_second": 35.123 |
| } |
| ], |
| "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 |
| } |
|
|
