| { | |
| "best_metric": 1.1206928491592407, | |
| "best_model_checkpoint": "/kaggle/working/results/checkpoint-800", | |
| "epoch": 0.057916455512922606, | |
| "eval_steps": 200, | |
| "global_step": 800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.014479113878230651, | |
| "eval_loss": 1.4317502975463867, | |
| "eval_runtime": 122.3776, | |
| "eval_samples_per_second": 63.737, | |
| "eval_steps_per_second": 0.498, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.028958227756461303, | |
| "eval_loss": 1.2947503328323364, | |
| "eval_runtime": 122.3265, | |
| "eval_samples_per_second": 63.764, | |
| "eval_steps_per_second": 0.499, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.03619778469557663, | |
| "grad_norm": 10.083489418029785, | |
| "learning_rate": 0.00019276044306088468, | |
| "loss": 1.6511, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.043437341634691956, | |
| "eval_loss": 1.2087372541427612, | |
| "eval_runtime": 122.3404, | |
| "eval_samples_per_second": 63.757, | |
| "eval_steps_per_second": 0.499, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.057916455512922606, | |
| "eval_loss": 1.1206928491592407, | |
| "eval_runtime": 122.0821, | |
| "eval_samples_per_second": 63.891, | |
| "eval_steps_per_second": 0.5, | |
| "step": 800 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 13813, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6737094456115200.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |