| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005198180636777128, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005198180636777127, | |
| "grad_norm": 24.27457046508789, | |
| "learning_rate": 2e-05, | |
| "loss": 6.7677, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005198180636777127, | |
| "eval_loss": 1.7232974767684937, | |
| "eval_runtime": 11.1873, | |
| "eval_samples_per_second": 72.493, | |
| "eval_steps_per_second": 36.291, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010396361273554255, | |
| "grad_norm": 24.204254150390625, | |
| "learning_rate": 4e-05, | |
| "loss": 6.6812, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0015594541910331384, | |
| "grad_norm": 20.464141845703125, | |
| "learning_rate": 6e-05, | |
| "loss": 6.3096, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015594541910331384, | |
| "eval_loss": 1.726916790008545, | |
| "eval_runtime": 10.2288, | |
| "eval_samples_per_second": 79.286, | |
| "eval_steps_per_second": 39.692, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002079272254710851, | |
| "grad_norm": 19.11884880065918, | |
| "learning_rate": 8e-05, | |
| "loss": 6.3229, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002599090318388564, | |
| "grad_norm": 23.759124755859375, | |
| "learning_rate": 0.0001, | |
| "loss": 6.5674, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0031189083820662767, | |
| "grad_norm": 19.746706008911133, | |
| "learning_rate": 0.00012, | |
| "loss": 7.0789, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0031189083820662767, | |
| "eval_loss": 1.7117472887039185, | |
| "eval_runtime": 10.6662, | |
| "eval_samples_per_second": 76.034, | |
| "eval_steps_per_second": 38.064, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0036387264457439896, | |
| "grad_norm": 26.317747116088867, | |
| "learning_rate": 0.00014, | |
| "loss": 7.4776, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004158544509421702, | |
| "grad_norm": 28.559688568115234, | |
| "learning_rate": 0.00016, | |
| "loss": 7.0161, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004678362573099415, | |
| "grad_norm": 22.01544761657715, | |
| "learning_rate": 0.00018, | |
| "loss": 6.6051, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004678362573099415, | |
| "eval_loss": 1.6880614757537842, | |
| "eval_runtime": 10.1221, | |
| "eval_samples_per_second": 80.122, | |
| "eval_steps_per_second": 40.11, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005198180636777128, | |
| "grad_norm": 24.867834091186523, | |
| "learning_rate": 0.0002, | |
| "loss": 6.5073, | |
| "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": 175457131560960.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |