| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013420004193751311, | |
| "eval_steps": 2, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003355001048437828, | |
| "grad_norm": 1.4193305969238281, | |
| "learning_rate": 1e-05, | |
| "loss": 14.9053, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003355001048437828, | |
| "eval_loss": 1.0040876865386963, | |
| "eval_runtime": 100.2771, | |
| "eval_samples_per_second": 5.006, | |
| "eval_steps_per_second": 2.503, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006710002096875656, | |
| "grad_norm": 1.4031709432601929, | |
| "learning_rate": 2e-05, | |
| "loss": 15.3029, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006710002096875656, | |
| "eval_loss": 0.9992220997810364, | |
| "eval_runtime": 83.9903, | |
| "eval_samples_per_second": 5.977, | |
| "eval_steps_per_second": 2.988, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010065003145313483, | |
| "grad_norm": 1.4328171014785767, | |
| "learning_rate": 3e-05, | |
| "loss": 17.7881, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013420004193751311, | |
| "grad_norm": 1.4899009466171265, | |
| "learning_rate": 4e-05, | |
| "loss": 17.0274, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013420004193751311, | |
| "eval_loss": 0.9962573051452637, | |
| "eval_runtime": 84.1722, | |
| "eval_samples_per_second": 5.964, | |
| "eval_steps_per_second": 2.982, | |
| "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": 5936670572544000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |