| { |
| "best_global_step": 264, |
| "best_metric": 0.43278712034225464, |
| "best_model_checkpoint": "distilbert_rand_20_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": 8.38988208770752, |
| "learning_rate": 4.9e-05, |
| "loss": 0.3899, |
| "step": 264 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8073394495412844, |
| "eval_loss": 0.43278712034225464, |
| "eval_runtime": 0.3738, |
| "eval_samples_per_second": 2332.664, |
| "eval_steps_per_second": 10.7, |
| "step": 264 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 10.207254409790039, |
| "learning_rate": 4.8e-05, |
| "loss": 0.2191, |
| "step": 528 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.8107798165137615, |
| "eval_loss": 0.5030353665351868, |
| "eval_runtime": 0.3692, |
| "eval_samples_per_second": 2361.96, |
| "eval_steps_per_second": 10.835, |
| "step": 528 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 5.3224005699157715, |
| "learning_rate": 4.7e-05, |
| "loss": 0.1602, |
| "step": 792 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.8188073394495413, |
| "eval_loss": 0.49767008423805237, |
| "eval_runtime": 0.369, |
| "eval_samples_per_second": 2362.857, |
| "eval_steps_per_second": 10.839, |
| "step": 792 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 4.78076171875, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.1186, |
| "step": 1056 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.8119266055045872, |
| "eval_loss": 0.6430910229682922, |
| "eval_runtime": 0.3695, |
| "eval_samples_per_second": 2359.768, |
| "eval_steps_per_second": 10.825, |
| "step": 1056 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 11.568105697631836, |
| "learning_rate": 4.5e-05, |
| "loss": 0.0907, |
| "step": 1320 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.8211009174311926, |
| "eval_loss": 0.564026951789856, |
| "eval_runtime": 0.3702, |
| "eval_samples_per_second": 2355.636, |
| "eval_steps_per_second": 10.806, |
| "step": 1320 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 5.003893852233887, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.0713, |
| "step": 1584 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.8130733944954128, |
| "eval_loss": 0.7440786361694336, |
| "eval_runtime": 0.3693, |
| "eval_samples_per_second": 2361.104, |
| "eval_steps_per_second": 10.831, |
| "step": 1584 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 1584, |
| "total_flos": 2.676464049624883e+16, |
| "train_loss": 0.17497296766801315, |
| "train_runtime": 377.617, |
| "train_samples_per_second": 8917.634, |
| "train_steps_per_second": 34.956 |
| } |
| ], |
| "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 |
| } |
|
|
