| { |
| "best_global_step": 3, |
| "best_metric": 0.7006492018699646, |
| "best_model_checkpoint": "distilbert_rand_20_v2_wnli/checkpoint-3", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 18, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 1.2801612615585327, |
| "learning_rate": 4.9e-05, |
| "loss": 0.7225, |
| "step": 3 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5633802816901409, |
| "eval_loss": 0.7006492018699646, |
| "eval_runtime": 0.0398, |
| "eval_samples_per_second": 1784.874, |
| "eval_steps_per_second": 25.139, |
| "step": 3 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.4510947465896606, |
| "learning_rate": 4.8e-05, |
| "loss": 0.6961, |
| "step": 6 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.4225352112676056, |
| "eval_loss": 0.7346500158309937, |
| "eval_runtime": 0.0496, |
| "eval_samples_per_second": 1431.097, |
| "eval_steps_per_second": 20.156, |
| "step": 6 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.7189109325408936, |
| "learning_rate": 4.7e-05, |
| "loss": 0.6963, |
| "step": 9 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.5211267605633803, |
| "eval_loss": 0.7164391279220581, |
| "eval_runtime": 0.0554, |
| "eval_samples_per_second": 1280.571, |
| "eval_steps_per_second": 18.036, |
| "step": 9 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 1.8902215957641602, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.6977, |
| "step": 12 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.4507042253521127, |
| "eval_loss": 0.7276627421379089, |
| "eval_runtime": 0.0504, |
| "eval_samples_per_second": 1407.93, |
| "eval_steps_per_second": 19.83, |
| "step": 12 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.918549120426178, |
| "learning_rate": 4.5e-05, |
| "loss": 0.6889, |
| "step": 15 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.30985915492957744, |
| "eval_loss": 0.7601781487464905, |
| "eval_runtime": 0.0542, |
| "eval_samples_per_second": 1309.245, |
| "eval_steps_per_second": 18.44, |
| "step": 15 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 1.9303950071334839, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.6955, |
| "step": 18 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.15492957746478872, |
| "eval_loss": 0.7657351493835449, |
| "eval_runtime": 0.0419, |
| "eval_samples_per_second": 1692.761, |
| "eval_steps_per_second": 23.842, |
| "step": 18 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 18, |
| "total_flos": 252350394439680.0, |
| "train_loss": 0.6994986534118652, |
| "train_runtime": 11.9361, |
| "train_samples_per_second": 2659.993, |
| "train_steps_per_second": 12.567 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 150, |
| "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": 252350394439680.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
