| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0002510103165240091, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.5101031652400914e-05, | |
| "grad_norm": 2.981691837310791, | |
| "learning_rate": 2e-05, | |
| "loss": 3.1149, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.5101031652400914e-05, | |
| "eval_loss": 3.9215281009674072, | |
| "eval_runtime": 716.0056, | |
| "eval_samples_per_second": 23.429, | |
| "eval_steps_per_second": 11.715, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.020206330480183e-05, | |
| "grad_norm": 0.8886885046958923, | |
| "learning_rate": 4e-05, | |
| "loss": 1.4628, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 7.530309495720274e-05, | |
| "grad_norm": 3.8731353282928467, | |
| "learning_rate": 6e-05, | |
| "loss": 3.02, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.530309495720274e-05, | |
| "eval_loss": 3.8999013900756836, | |
| "eval_runtime": 714.284, | |
| "eval_samples_per_second": 23.485, | |
| "eval_steps_per_second": 11.743, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00010040412660960366, | |
| "grad_norm": 1.4657057523727417, | |
| "learning_rate": 8e-05, | |
| "loss": 2.0341, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00012550515826200456, | |
| "grad_norm": 0.9188522696495056, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4815, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00015060618991440548, | |
| "grad_norm": 2.8464882373809814, | |
| "learning_rate": 0.00012, | |
| "loss": 2.3255, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00015060618991440548, | |
| "eval_loss": 3.5286591053009033, | |
| "eval_runtime": 714.9036, | |
| "eval_samples_per_second": 23.465, | |
| "eval_steps_per_second": 11.733, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001757072215668064, | |
| "grad_norm": 1.2822641134262085, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2277, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002008082532192073, | |
| "grad_norm": 3.9366445541381836, | |
| "learning_rate": 0.00016, | |
| "loss": 2.5245, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00022590928487160823, | |
| "grad_norm": 1.4788264036178589, | |
| "learning_rate": 0.00018, | |
| "loss": 1.7864, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00022590928487160823, | |
| "eval_loss": 2.453374147415161, | |
| "eval_runtime": 715.1252, | |
| "eval_samples_per_second": 23.457, | |
| "eval_steps_per_second": 11.729, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002510103165240091, | |
| "grad_norm": 1.6133027076721191, | |
| "learning_rate": 0.0002, | |
| "loss": 1.802, | |
| "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": 2173239174365184.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |