| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11019283746556474, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036730945821854912, | |
| "eval_loss": 1.9807047843933105, | |
| "eval_runtime": 10.3944, | |
| "eval_samples_per_second": 11.064, | |
| "eval_steps_per_second": 5.58, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011019283746556474, | |
| "grad_norm": 2.4493484497070312, | |
| "learning_rate": 6e-05, | |
| "loss": 7.8643, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02203856749311295, | |
| "grad_norm": 2.7967722415924072, | |
| "learning_rate": 0.00012, | |
| "loss": 8.0013, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02938475665748393, | |
| "eval_loss": 1.7155823707580566, | |
| "eval_runtime": 10.4101, | |
| "eval_samples_per_second": 11.047, | |
| "eval_steps_per_second": 5.572, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03305785123966942, | |
| "grad_norm": 3.061476707458496, | |
| "learning_rate": 0.00018, | |
| "loss": 7.0556, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0440771349862259, | |
| "grad_norm": 2.7618675231933594, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 6.3589, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05509641873278237, | |
| "grad_norm": 3.2486019134521484, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 5.2735, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05876951331496786, | |
| "eval_loss": 1.0837904214859009, | |
| "eval_runtime": 10.4912, | |
| "eval_samples_per_second": 10.962, | |
| "eval_steps_per_second": 5.528, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06611570247933884, | |
| "grad_norm": 3.703312397003174, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 4.3512, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07713498622589532, | |
| "grad_norm": 2.991180419921875, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 3.8412, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0881542699724518, | |
| "grad_norm": 3.2314670085906982, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 3.2882, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0881542699724518, | |
| "eval_loss": 0.7786951065063477, | |
| "eval_runtime": 10.5393, | |
| "eval_samples_per_second": 10.912, | |
| "eval_steps_per_second": 5.503, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09917355371900827, | |
| "grad_norm": 5.712580680847168, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 3.264, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11019283746556474, | |
| "grad_norm": 3.50492787361145, | |
| "learning_rate": 0.0, | |
| "loss": 2.9104, | |
| "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": 1.9043369091072e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |