| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 24, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 7.303779602050781, | |
| "learning_rate": 0.00018333333333333334, | |
| "loss": 76.2529, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.9657784700393677, | |
| "learning_rate": 0.0001666666666666667, | |
| "loss": 42.0132, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.6400000000000001, | |
| "grad_norm": 12.851223945617676, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 70.1639, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 2.692147731781006, | |
| "learning_rate": 0.00014166666666666668, | |
| "loss": 38.0473, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 16.04373550415039, | |
| "learning_rate": 0.000125, | |
| "loss": 65.5546, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 2.8774943351745605, | |
| "learning_rate": 0.00010833333333333333, | |
| "loss": 35.1272, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "grad_norm": 10.880264282226562, | |
| "learning_rate": 9.166666666666667e-05, | |
| "loss": 61.4732, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 3.491534471511841, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 33.673, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "grad_norm": 9.359137535095215, | |
| "learning_rate": 5.833333333333334e-05, | |
| "loss": 59.0955, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 3.1624951362609863, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 34.0901, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "grad_norm": 13.993888854980469, | |
| "learning_rate": 2.5e-05, | |
| "loss": 59.1404, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 2.413996934890747, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 33.2533, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 24, | |
| "total_flos": 74759151624528.0, | |
| "train_loss": 50.65707619984945, | |
| "train_runtime": 98.7071, | |
| "train_samples_per_second": 4.052, | |
| "train_steps_per_second": 0.243 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 24, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 74759151624528.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |