| { |
| "best_global_step": 10, |
| "best_metric": 0.7021660804748535, |
| "best_model_checkpoint": "bert_base_rand_100_v2_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": 2.031578779220581, |
| "learning_rate": 4.9e-05, |
| "loss": 0.7068, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.4729241877256318, |
| "eval_loss": 0.7021660804748535, |
| "eval_runtime": 0.1901, |
| "eval_samples_per_second": 1457.417, |
| "eval_steps_per_second": 10.523, |
| "step": 10 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.5852528810501099, |
| "learning_rate": 4.8e-05, |
| "loss": 0.6917, |
| "step": 20 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.5018050541516246, |
| "eval_loss": 0.7029910087585449, |
| "eval_runtime": 0.1962, |
| "eval_samples_per_second": 1412.158, |
| "eval_steps_per_second": 10.196, |
| "step": 20 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.466256022453308, |
| "learning_rate": 4.7e-05, |
| "loss": 0.6548, |
| "step": 30 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.5415162454873647, |
| "eval_loss": 0.7343326807022095, |
| "eval_runtime": 0.2015, |
| "eval_samples_per_second": 1374.928, |
| "eval_steps_per_second": 9.927, |
| "step": 30 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 2.608441114425659, |
| "learning_rate": 4.600000000000001e-05, |
| "loss": 0.5524, |
| "step": 40 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.5234657039711191, |
| "eval_loss": 0.9990543127059937, |
| "eval_runtime": 0.2012, |
| "eval_samples_per_second": 1376.633, |
| "eval_steps_per_second": 9.94, |
| "step": 40 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 4.1827392578125, |
| "learning_rate": 4.5e-05, |
| "loss": 0.3992, |
| "step": 50 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.5126353790613718, |
| "eval_loss": 1.0803521871566772, |
| "eval_runtime": 0.192, |
| "eval_samples_per_second": 1442.795, |
| "eval_steps_per_second": 10.417, |
| "step": 50 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 10.96815013885498, |
| "learning_rate": 4.4000000000000006e-05, |
| "loss": 0.3246, |
| "step": 60 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.5090252707581228, |
| "eval_loss": 1.4221433401107788, |
| "eval_runtime": 0.212, |
| "eval_samples_per_second": 1306.615, |
| "eval_steps_per_second": 9.434, |
| "step": 60 |
| }, |
| { |
| "epoch": 6.0, |
| "step": 60, |
| "total_flos": 1965439583539200.0, |
| "train_loss": 0.5549075762430827, |
| "train_runtime": 38.3792, |
| "train_samples_per_second": 3243.943, |
| "train_steps_per_second": 13.028 |
| } |
| ], |
| "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": 1965439583539200.0, |
| "train_batch_size": 256, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
