| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.14018691588785046, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004672897196261682, | |
| "eval_loss": 2.9198622703552246, | |
| "eval_runtime": 12.4797, | |
| "eval_samples_per_second": 7.292, | |
| "eval_steps_per_second": 3.686, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.014018691588785047, | |
| "grad_norm": 1.3729437589645386, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9464, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.028037383177570093, | |
| "grad_norm": 1.4899441003799438, | |
| "learning_rate": 0.0001992114701314478, | |
| "loss": 2.6909, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.037383177570093455, | |
| "eval_loss": 2.327054977416992, | |
| "eval_runtime": 11.7416, | |
| "eval_samples_per_second": 7.75, | |
| "eval_steps_per_second": 3.918, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04205607476635514, | |
| "grad_norm": 1.3411593437194824, | |
| "learning_rate": 0.00018763066800438636, | |
| "loss": 2.4553, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.056074766355140186, | |
| "grad_norm": 1.2581491470336914, | |
| "learning_rate": 0.000163742398974869, | |
| "loss": 2.2679, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07009345794392523, | |
| "grad_norm": 0.9910542964935303, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.2259, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07476635514018691, | |
| "eval_loss": 2.1382386684417725, | |
| "eval_runtime": 11.7953, | |
| "eval_samples_per_second": 7.715, | |
| "eval_steps_per_second": 3.9, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.08411214953271028, | |
| "grad_norm": 0.8965132236480713, | |
| "learning_rate": 9.372094804706867e-05, | |
| "loss": 2.0835, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.09813084112149532, | |
| "grad_norm": 0.9645207524299622, | |
| "learning_rate": 5.7422070843492734e-05, | |
| "loss": 2.2096, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "grad_norm": 0.9482259154319763, | |
| "learning_rate": 2.7103137257858868e-05, | |
| "loss": 2.1528, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11214953271028037, | |
| "eval_loss": 2.0866520404815674, | |
| "eval_runtime": 11.8434, | |
| "eval_samples_per_second": 7.684, | |
| "eval_steps_per_second": 3.884, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1261682242990654, | |
| "grad_norm": 0.9348795413970947, | |
| "learning_rate": 7.022351411174866e-06, | |
| "loss": 2.0408, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.14018691588785046, | |
| "grad_norm": 0.897182047367096, | |
| "learning_rate": 0.0, | |
| "loss": 2.0947, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "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 | |
| } | |