| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10810810810810811, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036036036036036037, | |
| "eval_loss": 2.2794220447540283, | |
| "eval_runtime": 26.8968, | |
| "eval_samples_per_second": 4.35, | |
| "eval_steps_per_second": 2.194, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010810810810810811, | |
| "grad_norm": 2.1002256870269775, | |
| "learning_rate": 6e-05, | |
| "loss": 8.4494, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.021621621621621623, | |
| "grad_norm": 1.9935013055801392, | |
| "learning_rate": 0.00012, | |
| "loss": 7.9289, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02882882882882883, | |
| "eval_loss": 2.152761459350586, | |
| "eval_runtime": 27.3965, | |
| "eval_samples_per_second": 4.271, | |
| "eval_steps_per_second": 2.154, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.032432432432432434, | |
| "grad_norm": 2.8687124252319336, | |
| "learning_rate": 0.00018, | |
| "loss": 9.3747, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.043243243243243246, | |
| "grad_norm": 6.517963409423828, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 8.6243, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05405405405405406, | |
| "grad_norm": 3.6777079105377197, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 7.1935, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05765765765765766, | |
| "eval_loss": 1.937667965888977, | |
| "eval_runtime": 27.4846, | |
| "eval_samples_per_second": 4.257, | |
| "eval_steps_per_second": 2.147, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06486486486486487, | |
| "grad_norm": 5.357371807098389, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 7.749, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07567567567567568, | |
| "grad_norm": 7.000950336456299, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 6.8093, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08648648648648649, | |
| "grad_norm": 5.712538719177246, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 7.2086, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08648648648648649, | |
| "eval_loss": 1.784159779548645, | |
| "eval_runtime": 27.5082, | |
| "eval_samples_per_second": 4.253, | |
| "eval_steps_per_second": 2.145, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0972972972972973, | |
| "grad_norm": 3.0364809036254883, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 7.2025, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10810810810810811, | |
| "grad_norm": 6.837973594665527, | |
| "learning_rate": 0.0, | |
| "loss": 7.2177, | |
| "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": 1.90434898870272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |