| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04299889746416759, | |
| "eval_steps": 13, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011025358324145535, | |
| "eval_loss": 1.7347309589385986, | |
| "eval_runtime": 22.6132, | |
| "eval_samples_per_second": 16.893, | |
| "eval_steps_per_second": 8.446, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011025358324145534, | |
| "grad_norm": 10.759740829467773, | |
| "learning_rate": 0.0002, | |
| "loss": 6.1733, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014332965821389196, | |
| "eval_loss": 1.1028164625167847, | |
| "eval_runtime": 22.0765, | |
| "eval_samples_per_second": 17.303, | |
| "eval_steps_per_second": 8.652, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.022050716648291068, | |
| "grad_norm": 7.973440170288086, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 4.1389, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02866593164277839, | |
| "eval_loss": 0.7895432710647583, | |
| "eval_runtime": 22.0927, | |
| "eval_samples_per_second": 17.291, | |
| "eval_steps_per_second": 8.645, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03307607497243661, | |
| "grad_norm": 4.080863952636719, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3461, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04299889746416759, | |
| "eval_loss": 0.7252407670021057, | |
| "eval_runtime": 22.0948, | |
| "eval_samples_per_second": 17.289, | |
| "eval_steps_per_second": 8.645, | |
| "step": 39 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.3670832182132736e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |