| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02236302646291465, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007454342154304882, | |
| "eval_loss": 3.5526232719421387, | |
| "eval_runtime": 9.0217, | |
| "eval_samples_per_second": 62.627, | |
| "eval_steps_per_second": 31.369, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022363026462914647, | |
| "grad_norm": 1.7465190887451172, | |
| "learning_rate": 6e-05, | |
| "loss": 3.4371, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004472605292582929, | |
| "grad_norm": 1.784867525100708, | |
| "learning_rate": 0.00012, | |
| "loss": 3.419, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005963473723443906, | |
| "eval_loss": 2.901203155517578, | |
| "eval_runtime": 7.8582, | |
| "eval_samples_per_second": 71.9, | |
| "eval_steps_per_second": 36.013, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006708907938874394, | |
| "grad_norm": 1.8665266036987305, | |
| "learning_rate": 0.00018, | |
| "loss": 3.0066, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008945210585165859, | |
| "grad_norm": 1.5807294845581055, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.4554, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011181513231457324, | |
| "grad_norm": 2.061957836151123, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.0364, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011926947446887812, | |
| "eval_loss": 1.6609691381454468, | |
| "eval_runtime": 7.9127, | |
| "eval_samples_per_second": 71.404, | |
| "eval_steps_per_second": 35.765, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013417815877748788, | |
| "grad_norm": 2.554117202758789, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.6773, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015654118524040254, | |
| "grad_norm": 5.221904277801514, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.3178, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.017890421170331718, | |
| "grad_norm": 1.6797155141830444, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.0641, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017890421170331718, | |
| "eval_loss": 1.0564405918121338, | |
| "eval_runtime": 8.0102, | |
| "eval_samples_per_second": 70.535, | |
| "eval_steps_per_second": 35.33, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02012672381662318, | |
| "grad_norm": 2.032195806503296, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.9839, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02236302646291465, | |
| "grad_norm": 2.377633571624756, | |
| "learning_rate": 0.0, | |
| "loss": 0.9328, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 208256379125760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |