| { |
| "best_global_step": 20, |
| "best_metric": 0.709900975227356, |
| "best_model_checkpoint": "distilbert_km_100_v1_rte/checkpoint-20", |
| "epoch": 7.0, |
| "eval_steps": 500, |
| "global_step": 70, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.3206048011779785, |
| "learning_rate": 4.9e-05, |
| "loss": 0.7053, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.4404332129963899, |
| "eval_loss": 0.7317661046981812, |
| "eval_runtime": 0.1301, |
| "eval_samples_per_second": 2128.445, |
| "eval_steps_per_second": 15.368, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.1321948766708374, |
| "learning_rate": 4.8e-05, |
| "loss": 0.6741, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.5018050541516246, |
| "eval_loss": 0.709900975227356, |
| "eval_runtime": 0.1312, |
| "eval_samples_per_second": 2111.602, |
| "eval_steps_per_second": 15.246, |
| "step": 20 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.9745191335678101, |
| "learning_rate": 4.7e-05, |
| "loss": 0.6343, |
| "step": 30 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.5306859205776173, |
| "eval_loss": 0.723558783531189, |
| "eval_runtime": 0.1309, |
| "eval_samples_per_second": 2116.444, |
| "eval_steps_per_second": 15.281, |
| "step": 30 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 1.0989468097686768, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.5864, |
| "step": 40 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.5342960288808665, |
| "eval_loss": 0.7434954047203064, |
| "eval_runtime": 0.1389, |
| "eval_samples_per_second": 1993.949, |
| "eval_steps_per_second": 14.397, |
| "step": 40 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 1.200851559638977, |
| "learning_rate": 4.5e-05, |
| "loss": 0.5129, |
| "step": 50 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.5451263537906137, |
| "eval_loss": 0.8149299621582031, |
| "eval_runtime": 0.1426, |
| "eval_samples_per_second": 1942.372, |
| "eval_steps_per_second": 14.024, |
| "step": 50 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 1.3032196760177612, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.4216, |
| "step": 60 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.5018050541516246, |
| "eval_loss": 0.9012248516082764, |
| "eval_runtime": 0.1331, |
| "eval_samples_per_second": 2080.94, |
| "eval_steps_per_second": 15.025, |
| "step": 60 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 1.6370849609375, |
| "learning_rate": 4.3e-05, |
| "loss": 0.2957, |
| "step": 70 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_accuracy": 0.5270758122743683, |
| "eval_loss": 1.1130335330963135, |
| "eval_runtime": 0.125, |
| "eval_samples_per_second": 2216.731, |
| "eval_steps_per_second": 16.005, |
| "step": 70 |
| }, |
| { |
| "epoch": 7.0, |
| "step": 70, |
| "total_flos": 1154453379287040.0, |
| "train_loss": 0.547214869090489, |
| "train_runtime": 25.3672, |
| "train_samples_per_second": 4907.911, |
| "train_steps_per_second": 19.71 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 500, |
| "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": 1154453379287040.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
