| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008660258075690656, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001732051615138131, | |
| "eval_loss": 3.1597797870635986, | |
| "eval_runtime": 194.7247, | |
| "eval_samples_per_second": 12.484, | |
| "eval_steps_per_second": 6.245, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008660258075690655, | |
| "grad_norm": 2.88759446144104, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0071, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001732051615138131, | |
| "grad_norm": 3.202864170074463, | |
| "learning_rate": 0.0001, | |
| "loss": 3.007, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001732051615138131, | |
| "eval_loss": 2.5920591354370117, | |
| "eval_runtime": 195.5293, | |
| "eval_samples_per_second": 12.433, | |
| "eval_steps_per_second": 6.219, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002598077422707197, | |
| "grad_norm": 3.011523485183716, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3291, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003464103230276262, | |
| "grad_norm": 2.63299822807312, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.4081, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003464103230276262, | |
| "eval_loss": 2.250953197479248, | |
| "eval_runtime": 195.6268, | |
| "eval_samples_per_second": 12.427, | |
| "eval_steps_per_second": 6.216, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004330129037845328, | |
| "grad_norm": 1.862342119216919, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.1672, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005196154845414394, | |
| "grad_norm": 2.89432430267334, | |
| "learning_rate": 5e-05, | |
| "loss": 2.099, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005196154845414394, | |
| "eval_loss": 2.1575541496276855, | |
| "eval_runtime": 196.0751, | |
| "eval_samples_per_second": 12.398, | |
| "eval_steps_per_second": 6.202, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006062180652983459, | |
| "grad_norm": 2.4008145332336426, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.9993, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006928206460552524, | |
| "grad_norm": 2.139503002166748, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.0199, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006928206460552524, | |
| "eval_loss": 2.1024301052093506, | |
| "eval_runtime": 195.6816, | |
| "eval_samples_per_second": 12.423, | |
| "eval_steps_per_second": 6.214, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00779423226812159, | |
| "grad_norm": 1.9587246179580688, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.9732, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008660258075690656, | |
| "grad_norm": 2.6692750453948975, | |
| "learning_rate": 0.0, | |
| "loss": 2.036, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008660258075690656, | |
| "eval_loss": 2.0944628715515137, | |
| "eval_runtime": 195.8471, | |
| "eval_samples_per_second": 12.413, | |
| "eval_steps_per_second": 6.209, | |
| "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": 9555457081344000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |