| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002391629297458894, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002391629297458894, | |
| "grad_norm": 1.3195282220840454, | |
| "learning_rate": 2e-05, | |
| "loss": 44.3552, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002391629297458894, | |
| "eval_loss": 11.093308448791504, | |
| "eval_runtime": 4.8423, | |
| "eval_samples_per_second": 363.666, | |
| "eval_steps_per_second": 181.936, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004783258594917788, | |
| "grad_norm": 1.5171899795532227, | |
| "learning_rate": 4e-05, | |
| "loss": 44.3894, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007174887892376681, | |
| "grad_norm": 1.4104125499725342, | |
| "learning_rate": 6e-05, | |
| "loss": 44.4284, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007174887892376681, | |
| "eval_loss": 11.09327507019043, | |
| "eval_runtime": 3.9443, | |
| "eval_samples_per_second": 446.467, | |
| "eval_steps_per_second": 223.36, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009566517189835576, | |
| "grad_norm": 1.2163171768188477, | |
| "learning_rate": 8e-05, | |
| "loss": 44.3973, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001195814648729447, | |
| "grad_norm": 1.4012264013290405, | |
| "learning_rate": 0.0001, | |
| "loss": 44.4088, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014349775784753362, | |
| "grad_norm": 1.4006203413009644, | |
| "learning_rate": 0.00012, | |
| "loss": 44.4034, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0014349775784753362, | |
| "eval_loss": 11.09300708770752, | |
| "eval_runtime": 3.988, | |
| "eval_samples_per_second": 441.57, | |
| "eval_steps_per_second": 220.91, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016741405082212257, | |
| "grad_norm": 1.4154075384140015, | |
| "learning_rate": 0.00014, | |
| "loss": 44.3932, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0019133034379671151, | |
| "grad_norm": 1.3693478107452393, | |
| "learning_rate": 0.00016, | |
| "loss": 44.3331, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0021524663677130046, | |
| "grad_norm": 1.3490021228790283, | |
| "learning_rate": 0.00018, | |
| "loss": 44.4172, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0021524663677130046, | |
| "eval_loss": 11.092469215393066, | |
| "eval_runtime": 3.9522, | |
| "eval_samples_per_second": 445.579, | |
| "eval_steps_per_second": 222.916, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002391629297458894, | |
| "grad_norm": 1.406904697418213, | |
| "learning_rate": 0.0002, | |
| "loss": 44.378, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7471104000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |