| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0017287578874578616, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00017287578874578615, | |
| "grad_norm": 3.482372760772705, | |
| "learning_rate": 2e-05, | |
| "loss": 10.147, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017287578874578615, | |
| "eval_loss": 10.197986602783203, | |
| "eval_runtime": 67.4855, | |
| "eval_samples_per_second": 36.097, | |
| "eval_steps_per_second": 18.048, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003457515774915723, | |
| "grad_norm": 3.57196044921875, | |
| "learning_rate": 4e-05, | |
| "loss": 9.9026, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0005186273662373585, | |
| "grad_norm": 3.3633735179901123, | |
| "learning_rate": 6e-05, | |
| "loss": 9.9502, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005186273662373585, | |
| "eval_loss": 10.191715240478516, | |
| "eval_runtime": 67.4992, | |
| "eval_samples_per_second": 36.089, | |
| "eval_steps_per_second": 18.045, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006915031549831446, | |
| "grad_norm": 3.694139242172241, | |
| "learning_rate": 8e-05, | |
| "loss": 10.109, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008643789437289308, | |
| "grad_norm": 3.5772221088409424, | |
| "learning_rate": 0.0001, | |
| "loss": 10.1954, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001037254732474717, | |
| "grad_norm": 3.585089683532715, | |
| "learning_rate": 0.00012, | |
| "loss": 10.2633, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001037254732474717, | |
| "eval_loss": 10.106863975524902, | |
| "eval_runtime": 67.0671, | |
| "eval_samples_per_second": 36.322, | |
| "eval_steps_per_second": 18.161, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001210130521220503, | |
| "grad_norm": 3.840843439102173, | |
| "learning_rate": 0.00014, | |
| "loss": 10.4198, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013830063099662892, | |
| "grad_norm": 3.3266236782073975, | |
| "learning_rate": 0.00016, | |
| "loss": 10.0992, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0015558820987120754, | |
| "grad_norm": 3.247655153274536, | |
| "learning_rate": 0.00018, | |
| "loss": 10.0575, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015558820987120754, | |
| "eval_loss": 9.946037292480469, | |
| "eval_runtime": 67.5398, | |
| "eval_samples_per_second": 36.068, | |
| "eval_steps_per_second": 18.034, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017287578874578616, | |
| "grad_norm": 3.7988805770874023, | |
| "learning_rate": 0.0002, | |
| "loss": 9.8737, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5429904015360.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |