| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0063399170933918555, | |
| "eval_steps": 13, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001625619767536373, | |
| "eval_loss": 1.515768051147461, | |
| "eval_runtime": 89.6369, | |
| "eval_samples_per_second": 28.905, | |
| "eval_steps_per_second": 14.458, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016256197675363732, | |
| "grad_norm": 2.4211690425872803, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 6.082, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002113305697797285, | |
| "eval_loss": 1.3606616258621216, | |
| "eval_runtime": 89.6419, | |
| "eval_samples_per_second": 28.904, | |
| "eval_steps_per_second": 14.458, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0032512395350727465, | |
| "grad_norm": 2.4349851608276367, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 5.5587, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00422661139559457, | |
| "eval_loss": 1.2548069953918457, | |
| "eval_runtime": 89.7488, | |
| "eval_samples_per_second": 28.869, | |
| "eval_steps_per_second": 14.44, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.00487685930260912, | |
| "grad_norm": 1.642345905303955, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 5.1682, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0063399170933918555, | |
| "eval_loss": 1.2337496280670166, | |
| "eval_runtime": 89.7814, | |
| "eval_samples_per_second": 28.859, | |
| "eval_steps_per_second": 14.435, | |
| "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": 6677871892365312.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |