| { |
| "best_global_step": 10, |
| "best_metric": 0.6875281929969788, |
| "best_model_checkpoint": "distilbert_rand_20_v1_rte/checkpoint-10", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 60, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.7315937280654907, |
| "learning_rate": 4.9e-05, |
| "loss": 0.6968, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.5379061371841155, |
| "eval_loss": 0.6875281929969788, |
| "eval_runtime": 0.129, |
| "eval_samples_per_second": 2148.018, |
| "eval_steps_per_second": 15.509, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.026312232017517, |
| "learning_rate": 4.8e-05, |
| "loss": 0.6728, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.4981949458483754, |
| "eval_loss": 0.7257199287414551, |
| "eval_runtime": 0.165, |
| "eval_samples_per_second": 1678.315, |
| "eval_steps_per_second": 12.118, |
| "step": 20 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.97349214553833, |
| "learning_rate": 4.7e-05, |
| "loss": 0.6257, |
| "step": 30 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.5018050541516246, |
| "eval_loss": 0.7571867108345032, |
| "eval_runtime": 0.128, |
| "eval_samples_per_second": 2164.018, |
| "eval_steps_per_second": 15.625, |
| "step": 30 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 2.8390111923217773, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.524, |
| "step": 40 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.48375451263537905, |
| "eval_loss": 0.9253872632980347, |
| "eval_runtime": 0.1328, |
| "eval_samples_per_second": 2085.774, |
| "eval_steps_per_second": 15.06, |
| "step": 40 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 2.225590944290161, |
| "learning_rate": 4.5e-05, |
| "loss": 0.3844, |
| "step": 50 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.4729241877256318, |
| "eval_loss": 1.1273629665374756, |
| "eval_runtime": 0.1386, |
| "eval_samples_per_second": 1998.528, |
| "eval_steps_per_second": 14.43, |
| "step": 50 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 5.133143901824951, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.2725, |
| "step": 60 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.47653429602888087, |
| "eval_loss": 1.4233369827270508, |
| "eval_runtime": 0.1484, |
| "eval_samples_per_second": 1866.999, |
| "eval_steps_per_second": 13.48, |
| "step": 60 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 60, |
| "total_flos": 989531467960320.0, |
| "train_loss": 0.5293523112932841, |
| "train_runtime": 22.3991, |
| "train_samples_per_second": 5558.266, |
| "train_steps_per_second": 22.322 |
| } |
| ], |
| "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": 989531467960320.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
