| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1276595744680851, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00425531914893617, | |
| "eval_loss": 1.9588388204574585, | |
| "eval_runtime": 3.1166, | |
| "eval_samples_per_second": 31.766, | |
| "eval_steps_per_second": 16.043, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01276595744680851, | |
| "grad_norm": 2.2283847332000732, | |
| "learning_rate": 3e-05, | |
| "loss": 1.9784, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02553191489361702, | |
| "grad_norm": 1.7109663486480713, | |
| "learning_rate": 6e-05, | |
| "loss": 1.8967, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03404255319148936, | |
| "eval_loss": 1.8774304389953613, | |
| "eval_runtime": 2.605, | |
| "eval_samples_per_second": 38.004, | |
| "eval_steps_per_second": 19.194, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03829787234042553, | |
| "grad_norm": 1.7952886819839478, | |
| "learning_rate": 9e-05, | |
| "loss": 1.8761, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05106382978723404, | |
| "grad_norm": 2.2627851963043213, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.9836, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06382978723404255, | |
| "grad_norm": 2.180539131164551, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.9119, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06808510638297872, | |
| "eval_loss": 1.7505676746368408, | |
| "eval_runtime": 2.735, | |
| "eval_samples_per_second": 36.197, | |
| "eval_steps_per_second": 18.282, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07659574468085106, | |
| "grad_norm": 1.7291843891143799, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.7136, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08936170212765958, | |
| "grad_norm": 1.8185924291610718, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 1.6575, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10212765957446808, | |
| "grad_norm": 1.9106318950653076, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 1.6174, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10212765957446808, | |
| "eval_loss": 1.721806526184082, | |
| "eval_runtime": 2.6995, | |
| "eval_samples_per_second": 36.674, | |
| "eval_steps_per_second": 18.522, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1148936170212766, | |
| "grad_norm": 2.2907865047454834, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 1.8897, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1276595744680851, | |
| "grad_norm": 1.938508152961731, | |
| "learning_rate": 0.0, | |
| "loss": 1.6005, | |
| "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": 540715725619200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |