| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.016842105263157894, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016842105263157896, | |
| "grad_norm": 22.114229202270508, | |
| "learning_rate": 2e-05, | |
| "loss": 11.0946, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016842105263157896, | |
| "eval_loss": 2.922970771789551, | |
| "eval_runtime": 3.2226, | |
| "eval_samples_per_second": 77.578, | |
| "eval_steps_per_second": 38.789, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003368421052631579, | |
| "grad_norm": 36.19076156616211, | |
| "learning_rate": 4e-05, | |
| "loss": 9.4751, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0050526315789473685, | |
| "grad_norm": 26.007158279418945, | |
| "learning_rate": 6e-05, | |
| "loss": 11.6861, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0050526315789473685, | |
| "eval_loss": 2.92002534866333, | |
| "eval_runtime": 2.8778, | |
| "eval_samples_per_second": 86.873, | |
| "eval_steps_per_second": 43.437, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006736842105263158, | |
| "grad_norm": 31.165403366088867, | |
| "learning_rate": 8e-05, | |
| "loss": 9.9852, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008421052631578947, | |
| "grad_norm": 43.4960823059082, | |
| "learning_rate": 0.0001, | |
| "loss": 10.1151, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010105263157894737, | |
| "grad_norm": 25.6102352142334, | |
| "learning_rate": 0.00012, | |
| "loss": 10.5071, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010105263157894737, | |
| "eval_loss": 2.913226366043091, | |
| "eval_runtime": 2.9521, | |
| "eval_samples_per_second": 84.685, | |
| "eval_steps_per_second": 42.342, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011789473684210527, | |
| "grad_norm": 30.639087677001953, | |
| "learning_rate": 0.00014, | |
| "loss": 9.0807, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013473684210526317, | |
| "grad_norm": 35.956634521484375, | |
| "learning_rate": 0.00016, | |
| "loss": 12.1441, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015157894736842105, | |
| "grad_norm": 42.816471099853516, | |
| "learning_rate": 0.00018, | |
| "loss": 13.4272, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015157894736842105, | |
| "eval_loss": 2.8832435607910156, | |
| "eval_runtime": 2.976, | |
| "eval_samples_per_second": 84.006, | |
| "eval_steps_per_second": 42.003, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016842105263157894, | |
| "grad_norm": 47.24085998535156, | |
| "learning_rate": 0.0002, | |
| "loss": 10.6155, | |
| "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": 87728565780480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |