| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.036596523330283626, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036596523330283625, | |
| "grad_norm": 19.999160766601562, | |
| "learning_rate": 2e-05, | |
| "loss": 47.7593, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036596523330283625, | |
| "eval_loss": 11.760443687438965, | |
| "eval_runtime": 2.1942, | |
| "eval_samples_per_second": 52.411, | |
| "eval_steps_per_second": 26.433, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007319304666056725, | |
| "grad_norm": 18.94071388244629, | |
| "learning_rate": 4e-05, | |
| "loss": 48.1966, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010978956999085087, | |
| "grad_norm": 18.465423583984375, | |
| "learning_rate": 6e-05, | |
| "loss": 47.3606, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010978956999085087, | |
| "eval_loss": 11.739356994628906, | |
| "eval_runtime": 2.1635, | |
| "eval_samples_per_second": 53.154, | |
| "eval_steps_per_second": 26.808, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01463860933211345, | |
| "grad_norm": 18.778934478759766, | |
| "learning_rate": 8e-05, | |
| "loss": 47.6034, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018298261665141813, | |
| "grad_norm": 21.876300811767578, | |
| "learning_rate": 0.0001, | |
| "loss": 49.3816, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.021957913998170174, | |
| "grad_norm": 23.94161033630371, | |
| "learning_rate": 0.00012, | |
| "loss": 49.0796, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.021957913998170174, | |
| "eval_loss": 11.175296783447266, | |
| "eval_runtime": 2.2323, | |
| "eval_samples_per_second": 51.517, | |
| "eval_steps_per_second": 25.983, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025617566331198535, | |
| "grad_norm": 26.675048828125, | |
| "learning_rate": 0.00014, | |
| "loss": 42.8055, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0292772186642269, | |
| "grad_norm": 29.66798210144043, | |
| "learning_rate": 0.00016, | |
| "loss": 41.4285, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03293687099725526, | |
| "grad_norm": 33.63569641113281, | |
| "learning_rate": 0.00018, | |
| "loss": 37.7123, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03293687099725526, | |
| "eval_loss": 7.950884819030762, | |
| "eval_runtime": 2.2054, | |
| "eval_samples_per_second": 52.146, | |
| "eval_steps_per_second": 26.3, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.036596523330283626, | |
| "grad_norm": 37.08169174194336, | |
| "learning_rate": 0.0002, | |
| "loss": 33.7543, | |
| "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": 298729403842560.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |