| { | |
| "best_global_step": 592, | |
| "best_metric": 0.830290675163269, | |
| "best_model_checkpoint": "./results_billsum/checkpoint-592", | |
| "epoch": 1.9963060686015832, | |
| "eval_steps": 500, | |
| "global_step": 592, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.33773087071240104, | |
| "grad_norm": 838200.5, | |
| "learning_rate": 1.7544483985765128e-05, | |
| "loss": 3.203, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6754617414248021, | |
| "grad_norm": 158957.71875, | |
| "learning_rate": 1.3985765124555162e-05, | |
| "loss": 1.4957, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.8794804811477661, | |
| "eval_runtime": 1277.7764, | |
| "eval_samples_per_second": 2.558, | |
| "eval_steps_per_second": 0.64, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 1.010131926121372, | |
| "grad_norm": 73460.7890625, | |
| "learning_rate": 1.0427046263345197e-05, | |
| "loss": 1.1737, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.347862796833773, | |
| "grad_norm": 66100.03125, | |
| "learning_rate": 6.868327402135232e-06, | |
| "loss": 1.0938, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.6855936675461742, | |
| "grad_norm": 63527.66796875, | |
| "learning_rate": 3.309608540925267e-06, | |
| "loss": 1.0639, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.9963060686015832, | |
| "eval_loss": 0.830290675163269, | |
| "eval_runtime": 1279.4932, | |
| "eval_samples_per_second": 2.555, | |
| "eval_steps_per_second": 0.639, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 1.9963060686015832, | |
| "step": 592, | |
| "total_flos": 1.0987423797624422e+17, | |
| "train_loss": 1.5217120325243152, | |
| "train_runtime": 38602.7875, | |
| "train_samples_per_second": 0.982, | |
| "train_steps_per_second": 0.015 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 592, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0987423797624422e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |