| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9795918367346939, | |
| "eval_steps": 2, | |
| "global_step": 6, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 1.509329080581665, | |
| "learning_rate": 1e-05, | |
| "loss": 1.4429, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "eval_loss": 2.717928171157837, | |
| "eval_runtime": 95.8731, | |
| "eval_samples_per_second": 0.115, | |
| "eval_steps_per_second": 0.063, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 1.883664846420288, | |
| "learning_rate": 2e-05, | |
| "loss": 1.5643, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "eval_loss": 2.6112759113311768, | |
| "eval_runtime": 0.2845, | |
| "eval_samples_per_second": 38.663, | |
| "eval_steps_per_second": 21.089, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 1.697153091430664, | |
| "learning_rate": 3e-05, | |
| "loss": 1.3637, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 1.6881253719329834, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2991, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "eval_loss": 2.5000574588775635, | |
| "eval_runtime": 0.2857, | |
| "eval_samples_per_second": 38.508, | |
| "eval_steps_per_second": 21.004, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 1.609917402267456, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1747, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "grad_norm": 1.8385484218597412, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1581, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "eval_loss": 2.186253309249878, | |
| "eval_runtime": 0.2832, | |
| "eval_samples_per_second": 38.836, | |
| "eval_steps_per_second": 21.183, | |
| "step": 6 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 7, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 3995970589163520.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |