| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.032388663967611336, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010796221322537112, | |
| "eval_loss": 1.667862057685852, | |
| "eval_runtime": 70.9897, | |
| "eval_samples_per_second": 5.494, | |
| "eval_steps_per_second": 2.747, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0032388663967611335, | |
| "grad_norm": 20.768577575683594, | |
| "learning_rate": 3e-05, | |
| "loss": 6.8403, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006477732793522267, | |
| "grad_norm": 12.299406051635742, | |
| "learning_rate": 6e-05, | |
| "loss": 5.5678, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00863697705802969, | |
| "eval_loss": 0.9197894930839539, | |
| "eval_runtime": 71.9425, | |
| "eval_samples_per_second": 5.421, | |
| "eval_steps_per_second": 2.71, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009716599190283401, | |
| "grad_norm": 6.3478779792785645, | |
| "learning_rate": 9e-05, | |
| "loss": 4.0375, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012955465587044534, | |
| "grad_norm": 6.927234172821045, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.8379, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.016194331983805668, | |
| "grad_norm": 4.13843297958374, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.8404, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01727395411605938, | |
| "eval_loss": 0.5986152291297913, | |
| "eval_runtime": 71.9635, | |
| "eval_samples_per_second": 5.419, | |
| "eval_steps_per_second": 2.71, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.019433198380566803, | |
| "grad_norm": 5.2277727127075195, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 2.4912, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.022672064777327937, | |
| "grad_norm": 3.7330214977264404, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 2.5327, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.025910931174089068, | |
| "grad_norm": 3.6300361156463623, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 2.5282, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.025910931174089068, | |
| "eval_loss": 0.5655854940414429, | |
| "eval_runtime": 71.935, | |
| "eval_samples_per_second": 5.422, | |
| "eval_steps_per_second": 2.711, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.029149797570850202, | |
| "grad_norm": 3.8471691608428955, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 2.102, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.032388663967611336, | |
| "grad_norm": 2.6132402420043945, | |
| "learning_rate": 0.0, | |
| "loss": 1.8928, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2920004538269696e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |