| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.021383513311237036, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004276702662247407, | |
| "eval_loss": 3.4804275035858154, | |
| "eval_runtime": 15.2889, | |
| "eval_samples_per_second": 64.426, | |
| "eval_steps_per_second": 32.246, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0021383513311237037, | |
| "grad_norm": 0.7456838488578796, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6062, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004276702662247407, | |
| "grad_norm": 1.261491060256958, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4641, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004276702662247407, | |
| "eval_loss": 3.438182830810547, | |
| "eval_runtime": 15.358, | |
| "eval_samples_per_second": 64.136, | |
| "eval_steps_per_second": 32.1, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006415053993371111, | |
| "grad_norm": 0.6130003333091736, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.4281, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008553405324494815, | |
| "grad_norm": 0.9023367166519165, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.2662, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008553405324494815, | |
| "eval_loss": 3.300909996032715, | |
| "eval_runtime": 15.3919, | |
| "eval_samples_per_second": 63.995, | |
| "eval_steps_per_second": 32.03, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010691756655618518, | |
| "grad_norm": 0.7119651436805725, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.1671, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012830107986742221, | |
| "grad_norm": 0.8098892569541931, | |
| "learning_rate": 5e-05, | |
| "loss": 3.2848, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012830107986742221, | |
| "eval_loss": 3.19399094581604, | |
| "eval_runtime": 15.3698, | |
| "eval_samples_per_second": 64.087, | |
| "eval_steps_per_second": 32.076, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014968459317865926, | |
| "grad_norm": 0.7773975133895874, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.937, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01710681064898963, | |
| "grad_norm": 0.9677534103393555, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.1459, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01710681064898963, | |
| "eval_loss": 3.132866621017456, | |
| "eval_runtime": 15.3849, | |
| "eval_samples_per_second": 64.024, | |
| "eval_steps_per_second": 32.044, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01924516198011333, | |
| "grad_norm": 1.0127432346343994, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.2155, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.021383513311237036, | |
| "grad_norm": 0.9054535031318665, | |
| "learning_rate": 0.0, | |
| "loss": 3.195, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.021383513311237036, | |
| "eval_loss": 3.121145009994507, | |
| "eval_runtime": 15.0793, | |
| "eval_samples_per_second": 65.321, | |
| "eval_steps_per_second": 32.694, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 171463252377600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |