| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00038642116042274477, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.864211604227448e-05, | |
| "grad_norm": 6.751275062561035, | |
| "learning_rate": 2e-05, | |
| "loss": 11.1537, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.864211604227448e-05, | |
| "eval_loss": 2.6657960414886475, | |
| "eval_runtime": 668.9602, | |
| "eval_samples_per_second": 16.289, | |
| "eval_steps_per_second": 8.145, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.728423208454895e-05, | |
| "grad_norm": 9.377216339111328, | |
| "learning_rate": 4e-05, | |
| "loss": 12.4515, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00011592634812682343, | |
| "grad_norm": 6.549380779266357, | |
| "learning_rate": 6e-05, | |
| "loss": 10.6319, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00011592634812682343, | |
| "eval_loss": 2.6524171829223633, | |
| "eval_runtime": 668.8079, | |
| "eval_samples_per_second": 16.293, | |
| "eval_steps_per_second": 8.147, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001545684641690979, | |
| "grad_norm": 3.170842409133911, | |
| "learning_rate": 8e-05, | |
| "loss": 7.6469, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00019321058021137238, | |
| "grad_norm": 6.741440773010254, | |
| "learning_rate": 0.0001, | |
| "loss": 12.355, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00023185269625364686, | |
| "grad_norm": 6.070605754852295, | |
| "learning_rate": 0.00012, | |
| "loss": 8.3175, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00023185269625364686, | |
| "eval_loss": 2.427530527114868, | |
| "eval_runtime": 669.0339, | |
| "eval_samples_per_second": 16.288, | |
| "eval_steps_per_second": 8.145, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002704948122959213, | |
| "grad_norm": 9.322867393493652, | |
| "learning_rate": 0.00014, | |
| "loss": 10.1693, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003091369283381958, | |
| "grad_norm": 9.409482955932617, | |
| "learning_rate": 0.00016, | |
| "loss": 9.0761, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00034777904438047026, | |
| "grad_norm": 8.069720268249512, | |
| "learning_rate": 0.00018, | |
| "loss": 7.895, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00034777904438047026, | |
| "eval_loss": 1.6052180528640747, | |
| "eval_runtime": 669.2161, | |
| "eval_samples_per_second": 16.283, | |
| "eval_steps_per_second": 8.142, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00038642116042274477, | |
| "grad_norm": 6.84035062789917, | |
| "learning_rate": 0.0002, | |
| "loss": 6.5089, | |
| "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": 3094623559876608.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |