| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00843775049571784, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016875500991435683, | |
| "eval_loss": 2.76141619682312, | |
| "eval_runtime": 216.0316, | |
| "eval_samples_per_second": 11.549, | |
| "eval_steps_per_second": 5.777, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008437750495717841, | |
| "grad_norm": 30.22994613647461, | |
| "learning_rate": 5e-05, | |
| "loss": 10.6076, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016875500991435683, | |
| "grad_norm": 18.776636123657227, | |
| "learning_rate": 0.0001, | |
| "loss": 8.1283, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0016875500991435683, | |
| "eval_loss": 1.477616310119629, | |
| "eval_runtime": 222.809, | |
| "eval_samples_per_second": 11.198, | |
| "eval_steps_per_second": 5.601, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0025313251487153526, | |
| "grad_norm": 23.546855926513672, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.6407, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0033751001982871365, | |
| "grad_norm": 15.05751895904541, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.0301, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0033751001982871365, | |
| "eval_loss": 1.2096279859542847, | |
| "eval_runtime": 224.5258, | |
| "eval_samples_per_second": 11.112, | |
| "eval_steps_per_second": 5.558, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00421887524785892, | |
| "grad_norm": 17.103416442871094, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.5847, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005062650297430705, | |
| "grad_norm": 14.482959747314453, | |
| "learning_rate": 5e-05, | |
| "loss": 3.858, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005062650297430705, | |
| "eval_loss": 1.1903036832809448, | |
| "eval_runtime": 222.8401, | |
| "eval_samples_per_second": 11.196, | |
| "eval_steps_per_second": 5.6, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005906425347002489, | |
| "grad_norm": 15.590099334716797, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.1778, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006750200396574273, | |
| "grad_norm": 18.384992599487305, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.5596, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006750200396574273, | |
| "eval_loss": 1.176118016242981, | |
| "eval_runtime": 222.9214, | |
| "eval_samples_per_second": 11.192, | |
| "eval_steps_per_second": 5.598, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007593975446146058, | |
| "grad_norm": 23.817644119262695, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.7036, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00843775049571784, | |
| "grad_norm": 18.593435287475586, | |
| "learning_rate": 0.0, | |
| "loss": 4.9152, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00843775049571784, | |
| "eval_loss": 1.1747710704803467, | |
| "eval_runtime": 222.5705, | |
| "eval_samples_per_second": 11.21, | |
| "eval_steps_per_second": 5.607, | |
| "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": 9157699631579136.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |