| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.25316455696202533, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02531645569620253, | |
| "grad_norm": 22.18537712097168, | |
| "learning_rate": 2e-05, | |
| "loss": 7.0434, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02531645569620253, | |
| "eval_loss": 1.932265281677246, | |
| "eval_runtime": 0.6006, | |
| "eval_samples_per_second": 28.304, | |
| "eval_steps_per_second": 14.985, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05063291139240506, | |
| "grad_norm": 24.977012634277344, | |
| "learning_rate": 4e-05, | |
| "loss": 7.3626, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0759493670886076, | |
| "grad_norm": 21.88210105895996, | |
| "learning_rate": 6e-05, | |
| "loss": 7.3573, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0759493670886076, | |
| "eval_loss": 1.8606997728347778, | |
| "eval_runtime": 0.599, | |
| "eval_samples_per_second": 28.379, | |
| "eval_steps_per_second": 15.024, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10126582278481013, | |
| "grad_norm": 21.373332977294922, | |
| "learning_rate": 8e-05, | |
| "loss": 7.0432, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.12658227848101267, | |
| "grad_norm": 26.960554122924805, | |
| "learning_rate": 0.0001, | |
| "loss": 6.6753, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1518987341772152, | |
| "grad_norm": 22.121986389160156, | |
| "learning_rate": 0.00012, | |
| "loss": 5.6679, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1518987341772152, | |
| "eval_loss": 1.394935131072998, | |
| "eval_runtime": 0.6007, | |
| "eval_samples_per_second": 28.301, | |
| "eval_steps_per_second": 14.983, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.17721518987341772, | |
| "grad_norm": 17.772489547729492, | |
| "learning_rate": 0.00014, | |
| "loss": 4.7804, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.20253164556962025, | |
| "grad_norm": 20.688440322875977, | |
| "learning_rate": 0.00016, | |
| "loss": 4.8731, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.22784810126582278, | |
| "grad_norm": 19.624662399291992, | |
| "learning_rate": 0.00018, | |
| "loss": 4.7893, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.22784810126582278, | |
| "eval_loss": 1.1246428489685059, | |
| "eval_runtime": 0.5994, | |
| "eval_samples_per_second": 28.364, | |
| "eval_steps_per_second": 15.016, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.25316455696202533, | |
| "grad_norm": 14.732420921325684, | |
| "learning_rate": 0.0002, | |
| "loss": 4.2114, | |
| "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": 1752669785948160.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |