| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004193751310547285, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004193751310547285, | |
| "grad_norm": 0.7540253400802612, | |
| "learning_rate": 2e-05, | |
| "loss": 2.3195, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004193751310547285, | |
| "eval_loss": 3.386383295059204, | |
| "eval_runtime": 118.0055, | |
| "eval_samples_per_second": 34.032, | |
| "eval_steps_per_second": 4.254, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000838750262109457, | |
| "grad_norm": 1.1561161279678345, | |
| "learning_rate": 4e-05, | |
| "loss": 2.3969, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0012581253931641854, | |
| "grad_norm": 2.3864729404449463, | |
| "learning_rate": 6e-05, | |
| "loss": 2.5621, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012581253931641854, | |
| "eval_loss": 3.3637778759002686, | |
| "eval_runtime": 117.9642, | |
| "eval_samples_per_second": 34.044, | |
| "eval_steps_per_second": 4.256, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001677500524218914, | |
| "grad_norm": 1.1608229875564575, | |
| "learning_rate": 8e-05, | |
| "loss": 2.7168, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0020968756552736424, | |
| "grad_norm": 1.706879734992981, | |
| "learning_rate": 0.0001, | |
| "loss": 2.883, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0025162507863283707, | |
| "grad_norm": 1.8335435390472412, | |
| "learning_rate": 0.00012, | |
| "loss": 2.4499, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0025162507863283707, | |
| "eval_loss": 3.006551504135132, | |
| "eval_runtime": 118.0062, | |
| "eval_samples_per_second": 34.032, | |
| "eval_steps_per_second": 4.254, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002935625917383099, | |
| "grad_norm": 0.8932392597198486, | |
| "learning_rate": 0.00014, | |
| "loss": 2.427, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003355001048437828, | |
| "grad_norm": 2.029635190963745, | |
| "learning_rate": 0.00016, | |
| "loss": 2.0816, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003774376179492556, | |
| "grad_norm": 3.7211058139801025, | |
| "learning_rate": 0.00018, | |
| "loss": 2.3502, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.003774376179492556, | |
| "eval_loss": 1.9476796388626099, | |
| "eval_runtime": 118.531, | |
| "eval_samples_per_second": 33.881, | |
| "eval_steps_per_second": 4.235, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004193751310547285, | |
| "grad_norm": 1.9227848052978516, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3378, | |
| "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": 2.235874343387136e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |