| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00019160391638405088, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.916039163840509e-05, | |
| "grad_norm": 3.5441946983337402, | |
| "learning_rate": 2e-05, | |
| "loss": 22.1609, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.916039163840509e-05, | |
| "eval_loss": 4.944888114929199, | |
| "eval_runtime": 479.6833, | |
| "eval_samples_per_second": 45.814, | |
| "eval_steps_per_second": 22.907, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.832078327681018e-05, | |
| "grad_norm": 2.601649761199951, | |
| "learning_rate": 4e-05, | |
| "loss": 19.9052, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.748117491521527e-05, | |
| "grad_norm": 2.268070697784424, | |
| "learning_rate": 6e-05, | |
| "loss": 18.0389, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.748117491521527e-05, | |
| "eval_loss": 4.944944381713867, | |
| "eval_runtime": 743.0766, | |
| "eval_samples_per_second": 29.574, | |
| "eval_steps_per_second": 14.787, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.664156655362036e-05, | |
| "grad_norm": 2.20841646194458, | |
| "learning_rate": 8e-05, | |
| "loss": 17.2621, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 9.580195819202544e-05, | |
| "grad_norm": 2.6768314838409424, | |
| "learning_rate": 0.0001, | |
| "loss": 21.0941, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00011496234983043054, | |
| "grad_norm": 2.986056089401245, | |
| "learning_rate": 0.00012, | |
| "loss": 22.1982, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00011496234983043054, | |
| "eval_loss": 4.939687728881836, | |
| "eval_runtime": 803.8833, | |
| "eval_samples_per_second": 27.337, | |
| "eval_steps_per_second": 13.669, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00013412274146883563, | |
| "grad_norm": 2.6154625415802, | |
| "learning_rate": 0.00014, | |
| "loss": 19.6519, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0001532831331072407, | |
| "grad_norm": 2.987260580062866, | |
| "learning_rate": 0.00016, | |
| "loss": 21.143, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001724435247456458, | |
| "grad_norm": 3.562917947769165, | |
| "learning_rate": 0.00018, | |
| "loss": 23.8628, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001724435247456458, | |
| "eval_loss": 4.913156509399414, | |
| "eval_runtime": 471.9561, | |
| "eval_samples_per_second": 46.564, | |
| "eval_steps_per_second": 23.282, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00019160391638405088, | |
| "grad_norm": 2.964939594268799, | |
| "learning_rate": 0.0002, | |
| "loss": 19.1079, | |
| "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": 21222716866560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |