| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01178967224711153, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002357934449422306, | |
| "eval_loss": 1.7095842361450195, | |
| "eval_runtime": 15.8117, | |
| "eval_samples_per_second": 56.477, | |
| "eval_steps_per_second": 28.27, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002357934449422306, | |
| "grad_norm": 2.182602882385254, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6215, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0030653147842489977, | |
| "eval_loss": 1.5580748319625854, | |
| "eval_runtime": 14.6495, | |
| "eval_samples_per_second": 60.958, | |
| "eval_steps_per_second": 30.513, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004715868898844612, | |
| "grad_norm": 1.5342705249786377, | |
| "learning_rate": 0.0002, | |
| "loss": 1.5709, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0061306295684979955, | |
| "eval_loss": 1.5492371320724487, | |
| "eval_runtime": 14.9616, | |
| "eval_samples_per_second": 59.686, | |
| "eval_steps_per_second": 29.876, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007073803348266918, | |
| "grad_norm": 1.9849066734313965, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4983, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009195944352746994, | |
| "eval_loss": 1.5431400537490845, | |
| "eval_runtime": 14.9638, | |
| "eval_samples_per_second": 59.678, | |
| "eval_steps_per_second": 29.872, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.009431737797689225, | |
| "grad_norm": 1.7911757230758667, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4923, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01178967224711153, | |
| "grad_norm": 1.890875220298767, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8385, | |
| "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": 265309413703680.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |