| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.028421202216853774, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005684240443370755, | |
| "eval_loss": 1.7579647302627563, | |
| "eval_runtime": 55.1355, | |
| "eval_samples_per_second": 13.44, | |
| "eval_steps_per_second": 6.729, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002842120221685377, | |
| "grad_norm": 0.6500794887542725, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7961, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005684240443370754, | |
| "grad_norm": 0.509131133556366, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7088, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005684240443370754, | |
| "eval_loss": 1.7291897535324097, | |
| "eval_runtime": 54.7873, | |
| "eval_samples_per_second": 13.525, | |
| "eval_steps_per_second": 6.772, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008526360665056132, | |
| "grad_norm": 0.7104833722114563, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.8415, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011368480886741509, | |
| "grad_norm": 0.6715155243873596, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3906, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011368480886741509, | |
| "eval_loss": 1.5854151248931885, | |
| "eval_runtime": 54.9652, | |
| "eval_samples_per_second": 13.481, | |
| "eval_steps_per_second": 6.75, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014210601108426887, | |
| "grad_norm": 0.6591376662254333, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.7109, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017052721330112264, | |
| "grad_norm": 0.5782737731933594, | |
| "learning_rate": 5e-05, | |
| "loss": 1.629, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017052721330112264, | |
| "eval_loss": 1.5050691366195679, | |
| "eval_runtime": 55.0316, | |
| "eval_samples_per_second": 13.465, | |
| "eval_steps_per_second": 6.742, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019894841551797642, | |
| "grad_norm": 0.9463327527046204, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3634, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.022736961773483017, | |
| "grad_norm": 0.4819091856479645, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.4302, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.022736961773483017, | |
| "eval_loss": 1.472131371498108, | |
| "eval_runtime": 55.0593, | |
| "eval_samples_per_second": 13.458, | |
| "eval_steps_per_second": 6.738, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025579081995168396, | |
| "grad_norm": 0.7316758632659912, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.5369, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.028421202216853774, | |
| "grad_norm": 0.9361283779144287, | |
| "learning_rate": 0.0, | |
| "loss": 1.6478, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.028421202216853774, | |
| "eval_loss": 1.4672110080718994, | |
| "eval_runtime": 54.9651, | |
| "eval_samples_per_second": 13.481, | |
| "eval_steps_per_second": 6.75, | |
| "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": 9763350820945920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |