| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004319001446865485, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.63800289373097e-05, | |
| "eval_loss": 2.5873870849609375, | |
| "eval_runtime": 229.4917, | |
| "eval_samples_per_second": 21.243, | |
| "eval_steps_per_second": 10.623, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000863800289373097, | |
| "grad_norm": 2.5288102626800537, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 10.0511, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001122940376185026, | |
| "eval_loss": 2.345015287399292, | |
| "eval_runtime": 228.355, | |
| "eval_samples_per_second": 21.348, | |
| "eval_steps_per_second": 10.676, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001727600578746194, | |
| "grad_norm": 2.8154540061950684, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 9.2001, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002245880752370052, | |
| "eval_loss": 2.198758363723755, | |
| "eval_runtime": 228.53, | |
| "eval_samples_per_second": 21.332, | |
| "eval_steps_per_second": 10.668, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0025914008681192906, | |
| "grad_norm": 2.327564239501953, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 8.6316, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.003368821128555078, | |
| "eval_loss": 2.156334400177002, | |
| "eval_runtime": 228.4604, | |
| "eval_samples_per_second": 21.338, | |
| "eval_steps_per_second": 10.671, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.003455201157492388, | |
| "grad_norm": 2.3207147121429443, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 8.7712, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004319001446865485, | |
| "grad_norm": 2.3708016872406006, | |
| "learning_rate": 0.0, | |
| "loss": 8.5769, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.5998284701106176e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |