| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00028650216667263544, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.8650216667263546e-05, | |
| "grad_norm": 1.226650357246399, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9984, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.8650216667263546e-05, | |
| "eval_loss": 1.0276609659194946, | |
| "eval_runtime": 145.3216, | |
| "eval_samples_per_second": 101.134, | |
| "eval_steps_per_second": 50.571, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.730043333452709e-05, | |
| "grad_norm": 1.2134617567062378, | |
| "learning_rate": 4e-05, | |
| "loss": 0.8721, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 8.595065000179063e-05, | |
| "grad_norm": 1.621222972869873, | |
| "learning_rate": 6e-05, | |
| "loss": 1.067, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.595065000179063e-05, | |
| "eval_loss": 1.024950623512268, | |
| "eval_runtime": 145.3387, | |
| "eval_samples_per_second": 101.122, | |
| "eval_steps_per_second": 50.565, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00011460086666905418, | |
| "grad_norm": 1.3076165914535522, | |
| "learning_rate": 8e-05, | |
| "loss": 0.8629, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00014325108333631772, | |
| "grad_norm": 1.1513737440109253, | |
| "learning_rate": 0.0001, | |
| "loss": 0.996, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00017190130000358127, | |
| "grad_norm": 1.021554946899414, | |
| "learning_rate": 0.00012, | |
| "loss": 0.8655, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00017190130000358127, | |
| "eval_loss": 0.98174649477005, | |
| "eval_runtime": 143.4647, | |
| "eval_samples_per_second": 102.443, | |
| "eval_steps_per_second": 51.225, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00020055151667084482, | |
| "grad_norm": 1.3280445337295532, | |
| "learning_rate": 0.00014, | |
| "loss": 0.7227, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00022920173333810837, | |
| "grad_norm": 0.8306891918182373, | |
| "learning_rate": 0.00016, | |
| "loss": 0.9452, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002578519500053719, | |
| "grad_norm": 0.9781473278999329, | |
| "learning_rate": 0.00018, | |
| "loss": 0.8849, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002578519500053719, | |
| "eval_loss": 0.8975035548210144, | |
| "eval_runtime": 143.4712, | |
| "eval_samples_per_second": 102.439, | |
| "eval_steps_per_second": 51.223, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00028650216667263544, | |
| "grad_norm": 0.6823318004608154, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9904, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 68585300951040.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |