| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.29239766081871343, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005847953216374269, | |
| "eval_loss": 4.58418083190918, | |
| "eval_runtime": 4.0022, | |
| "eval_samples_per_second": 17.99, | |
| "eval_steps_per_second": 8.995, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.029239766081871343, | |
| "grad_norm": 3.0935211181640625, | |
| "learning_rate": 5e-05, | |
| "loss": 4.5876, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.05847953216374269, | |
| "grad_norm": 3.019068717956543, | |
| "learning_rate": 0.0001, | |
| "loss": 4.2658, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05847953216374269, | |
| "eval_loss": 4.069548606872559, | |
| "eval_runtime": 4.0436, | |
| "eval_samples_per_second": 17.806, | |
| "eval_steps_per_second": 8.903, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08771929824561403, | |
| "grad_norm": 3.4410085678100586, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.7752, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11695906432748537, | |
| "grad_norm": 3.8444201946258545, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.4693, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11695906432748537, | |
| "eval_loss": 3.4060192108154297, | |
| "eval_runtime": 4.0256, | |
| "eval_samples_per_second": 17.885, | |
| "eval_steps_per_second": 8.943, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14619883040935672, | |
| "grad_norm": 2.9396581649780273, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.3762, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 3.386218309402466, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9384, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "eval_loss": 3.2552380561828613, | |
| "eval_runtime": 4.0323, | |
| "eval_samples_per_second": 17.856, | |
| "eval_steps_per_second": 8.928, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2046783625730994, | |
| "grad_norm": 3.572996139526367, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.2517, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.23391812865497075, | |
| "grad_norm": 3.5481719970703125, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.9318, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.23391812865497075, | |
| "eval_loss": 3.1777260303497314, | |
| "eval_runtime": 4.0747, | |
| "eval_samples_per_second": 17.67, | |
| "eval_steps_per_second": 8.835, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 5.325904369354248, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.2349, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.29239766081871343, | |
| "grad_norm": 3.5925145149230957, | |
| "learning_rate": 0.0, | |
| "loss": 3.0101, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.29239766081871343, | |
| "eval_loss": 3.164489507675171, | |
| "eval_runtime": 4.0276, | |
| "eval_samples_per_second": 17.877, | |
| "eval_steps_per_second": 8.938, | |
| "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": 2500486653542400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |