| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004093380236648545, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010233450591621363, | |
| "grad_norm": 8.796223640441895, | |
| "learning_rate": 1e-05, | |
| "loss": 19.7209, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010233450591621363, | |
| "eval_loss": 1.411039113998413, | |
| "eval_runtime": 101.1167, | |
| "eval_samples_per_second": 16.278, | |
| "eval_steps_per_second": 8.139, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020466901183242726, | |
| "grad_norm": 8.294190406799316, | |
| "learning_rate": 2e-05, | |
| "loss": 20.5799, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0020466901183242726, | |
| "eval_loss": 1.4010179042816162, | |
| "eval_runtime": 146.4917, | |
| "eval_samples_per_second": 11.236, | |
| "eval_steps_per_second": 5.618, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003070035177486409, | |
| "grad_norm": 12.467994689941406, | |
| "learning_rate": 3e-05, | |
| "loss": 24.1962, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004093380236648545, | |
| "grad_norm": 18.06902503967285, | |
| "learning_rate": 4e-05, | |
| "loss": 28.6901, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004093380236648545, | |
| "eval_loss": 1.3918755054473877, | |
| "eval_runtime": 393.5444, | |
| "eval_samples_per_second": 4.183, | |
| "eval_steps_per_second": 2.091, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5382547093585920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |