| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10572687224669604, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003524229074889868, | |
| "eval_loss": 10.381552696228027, | |
| "eval_runtime": 0.5836, | |
| "eval_samples_per_second": 205.603, | |
| "eval_steps_per_second": 102.801, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010572687224669603, | |
| "grad_norm": 0.09532614797353745, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3794, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.021145374449339206, | |
| "grad_norm": 0.054097481071949005, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3808, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028193832599118944, | |
| "eval_loss": 10.380975723266602, | |
| "eval_runtime": 0.6028, | |
| "eval_samples_per_second": 199.057, | |
| "eval_steps_per_second": 99.528, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03171806167400881, | |
| "grad_norm": 0.05583056062459946, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3842, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04229074889867841, | |
| "grad_norm": 0.05073745548725128, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 10.3817, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05286343612334802, | |
| "grad_norm": 0.05803139880299568, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.3758, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05638766519823789, | |
| "eval_loss": 10.379494667053223, | |
| "eval_runtime": 0.647, | |
| "eval_samples_per_second": 185.462, | |
| "eval_steps_per_second": 92.731, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.06343612334801763, | |
| "grad_norm": 0.0619657076895237, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.3799, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07400881057268723, | |
| "grad_norm": 0.05669896677136421, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 10.3788, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.08458149779735682, | |
| "grad_norm": 0.05713118985295296, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 10.3763, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08458149779735682, | |
| "eval_loss": 10.378570556640625, | |
| "eval_runtime": 0.6514, | |
| "eval_samples_per_second": 184.207, | |
| "eval_steps_per_second": 92.103, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.09515418502202644, | |
| "grad_norm": 0.07598796486854553, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 10.3819, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.10572687224669604, | |
| "grad_norm": 0.07423160970211029, | |
| "learning_rate": 0.0, | |
| "loss": 10.3778, | |
| "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": 784536698880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |