| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04296455424274973, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008592910848549946, | |
| "eval_loss": 2.4728493690490723, | |
| "eval_runtime": 32.4978, | |
| "eval_samples_per_second": 15.078, | |
| "eval_steps_per_second": 7.539, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004296455424274973, | |
| "grad_norm": 1.197363257408142, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4877, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "grad_norm": 1.2792778015136719, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1751, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "eval_loss": 2.1013641357421875, | |
| "eval_runtime": 32.7282, | |
| "eval_samples_per_second": 14.972, | |
| "eval_steps_per_second": 7.486, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01288936627282492, | |
| "grad_norm": 1.1452423334121704, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.9811, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017185821697099892, | |
| "grad_norm": 1.164590835571289, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.6291, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017185821697099892, | |
| "eval_loss": 1.8042640686035156, | |
| "eval_runtime": 32.764, | |
| "eval_samples_per_second": 14.955, | |
| "eval_steps_per_second": 7.478, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021482277121374866, | |
| "grad_norm": 1.0136661529541016, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.8227, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02577873254564984, | |
| "grad_norm": 0.9255285859107971, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6754, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02577873254564984, | |
| "eval_loss": 1.7722784280776978, | |
| "eval_runtime": 32.8002, | |
| "eval_samples_per_second": 14.939, | |
| "eval_steps_per_second": 7.469, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03007518796992481, | |
| "grad_norm": 0.8607089519500732, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.8473, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.034371643394199784, | |
| "grad_norm": 0.8679115772247314, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.762, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.034371643394199784, | |
| "eval_loss": 1.7615612745285034, | |
| "eval_runtime": 33.0524, | |
| "eval_samples_per_second": 14.825, | |
| "eval_steps_per_second": 7.412, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03866809881847476, | |
| "grad_norm": 0.9805191159248352, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7322, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04296455424274973, | |
| "grad_norm": 0.9697389006614685, | |
| "learning_rate": 0.0, | |
| "loss": 1.8069, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04296455424274973, | |
| "eval_loss": 1.7591865062713623, | |
| "eval_runtime": 32.9389, | |
| "eval_samples_per_second": 14.876, | |
| "eval_steps_per_second": 7.438, | |
| "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": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |