| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06109979633401222, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002036659877800407, | |
| "eval_loss": 9.511523246765137, | |
| "eval_runtime": 27.1172, | |
| "eval_samples_per_second": 7.634, | |
| "eval_steps_per_second": 3.835, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006109979633401222, | |
| "grad_norm": 17.13298225402832, | |
| "learning_rate": 6e-05, | |
| "loss": 9.8003, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012219959266802444, | |
| "grad_norm": 8.734164237976074, | |
| "learning_rate": 0.00012, | |
| "loss": 8.2865, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016293279022403257, | |
| "eval_loss": 2.3545432090759277, | |
| "eval_runtime": 26.5451, | |
| "eval_samples_per_second": 7.798, | |
| "eval_steps_per_second": 3.918, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.018329938900203666, | |
| "grad_norm": 10.335521697998047, | |
| "learning_rate": 0.00018, | |
| "loss": 4.3444, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024439918533604887, | |
| "grad_norm": 10.39284610748291, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.8416, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03054989816700611, | |
| "grad_norm": 16.74129867553711, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.5524, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.032586558044806514, | |
| "eval_loss": 0.2602912485599518, | |
| "eval_runtime": 26.5855, | |
| "eval_samples_per_second": 7.786, | |
| "eval_steps_per_second": 3.912, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03665987780040733, | |
| "grad_norm": 3.2154951095581055, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.2707, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04276985743380855, | |
| "grad_norm": 1.8151304721832275, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.229, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.048879837067209775, | |
| "grad_norm": 4.890005588531494, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.3406, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.048879837067209775, | |
| "eval_loss": 0.25264063477516174, | |
| "eval_runtime": 26.6422, | |
| "eval_samples_per_second": 7.77, | |
| "eval_steps_per_second": 3.904, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.054989816700611, | |
| "grad_norm": 1.2037434577941895, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.2391, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06109979633401222, | |
| "grad_norm": 2.0474212169647217, | |
| "learning_rate": 0.0, | |
| "loss": 0.2311, | |
| "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": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |