| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07890743550834597, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0020232675771370764, | |
| "eval_loss": 1.7532789707183838, | |
| "eval_runtime": 22.6911, | |
| "eval_samples_per_second": 9.211, | |
| "eval_steps_per_second": 4.627, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010116337885685382, | |
| "grad_norm": 2.5933752059936523, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5813, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.020232675771370764, | |
| "grad_norm": 1.89445161819458, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1502, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.020232675771370764, | |
| "eval_loss": 0.7085664868354797, | |
| "eval_runtime": 23.9995, | |
| "eval_samples_per_second": 8.709, | |
| "eval_steps_per_second": 4.375, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.030349013657056147, | |
| "grad_norm": 0.9080146551132202, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5644, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04046535154274153, | |
| "grad_norm": 0.6127835512161255, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.3534, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04046535154274153, | |
| "eval_loss": 0.32802435755729675, | |
| "eval_runtime": 24.4681, | |
| "eval_samples_per_second": 8.542, | |
| "eval_steps_per_second": 4.291, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05058168942842691, | |
| "grad_norm": 0.552888035774231, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.2888, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06069802731411229, | |
| "grad_norm": 0.5705128908157349, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2478, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06069802731411229, | |
| "eval_loss": 0.24784217774868011, | |
| "eval_runtime": 24.6368, | |
| "eval_samples_per_second": 8.483, | |
| "eval_steps_per_second": 4.262, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07081436519979767, | |
| "grad_norm": 0.3076908588409424, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2376, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9969328686366720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |