| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.5901639344262293, | |
| "eval_steps": 25, | |
| "global_step": 12, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26229508196721313, | |
| "grad_norm": 9.005887031555176, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.8263, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.26229508196721313, | |
| "eval_loss": 3.844275951385498, | |
| "eval_runtime": 1.0525, | |
| "eval_samples_per_second": 24.702, | |
| "eval_steps_per_second": 3.8, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": 6.8389058113098145, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.6364, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.7868852459016393, | |
| "grad_norm": 4.461410999298096, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.0907, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.1967213114754098, | |
| "grad_norm": 11.243925094604492, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.723, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.459016393442623, | |
| "grad_norm": 6.151476860046387, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.5321, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.721311475409836, | |
| "grad_norm": 6.525777816772461, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5686, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.1311475409836067, | |
| "grad_norm": 7.0160231590271, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 3.7585, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.3934426229508197, | |
| "grad_norm": 3.647797107696533, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.7185, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.6557377049180326, | |
| "grad_norm": 4.279379844665527, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3963, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 3.0655737704918034, | |
| "grad_norm": 7.189956188201904, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 3.5925, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.3278688524590163, | |
| "grad_norm": 3.2980616092681885, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.8792, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 3.5901639344262293, | |
| "grad_norm": 3.2593202590942383, | |
| "learning_rate": 0.0, | |
| "loss": 2.0259, | |
| "step": 12 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 12, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": 1.4818750426723123e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |