| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006644518272425249, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016611295681063123, | |
| "grad_norm": 1.0861163139343262, | |
| "learning_rate": 1e-05, | |
| "loss": 2.6847, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016611295681063123, | |
| "eval_loss": 3.090754985809326, | |
| "eval_runtime": 95.9531, | |
| "eval_samples_per_second": 10.568, | |
| "eval_steps_per_second": 5.284, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033222591362126247, | |
| "grad_norm": 1.2771000862121582, | |
| "learning_rate": 2e-05, | |
| "loss": 3.0488, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0033222591362126247, | |
| "eval_loss": 3.0775351524353027, | |
| "eval_runtime": 23.4866, | |
| "eval_samples_per_second": 43.174, | |
| "eval_steps_per_second": 21.587, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0049833887043189366, | |
| "grad_norm": 1.4017620086669922, | |
| "learning_rate": 3e-05, | |
| "loss": 3.0701, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006644518272425249, | |
| "grad_norm": 1.2213730812072754, | |
| "learning_rate": 4e-05, | |
| "loss": 3.2419, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006644518272425249, | |
| "eval_loss": 3.0597591400146484, | |
| "eval_runtime": 12.3835, | |
| "eval_samples_per_second": 81.883, | |
| "eval_steps_per_second": 40.942, | |
| "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": 757718373629952.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |