| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09467455621301775, | |
| "eval_steps": 20, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001183431952662722, | |
| "eval_loss": 11.93152904510498, | |
| "eval_runtime": 4.308, | |
| "eval_samples_per_second": 348.651, | |
| "eval_steps_per_second": 21.82, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011834319526627219, | |
| "grad_norm": 0.5202497839927673, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 11.9327, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023668639053254437, | |
| "grad_norm": 0.41039279103279114, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 11.9349, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.023668639053254437, | |
| "eval_loss": 11.930181503295898, | |
| "eval_runtime": 4.2088, | |
| "eval_samples_per_second": 356.87, | |
| "eval_steps_per_second": 22.334, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03550295857988166, | |
| "grad_norm": 0.6066334247589111, | |
| "learning_rate": 4.8e-05, | |
| "loss": 11.9306, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.047337278106508875, | |
| "grad_norm": 0.46611225605010986, | |
| "learning_rate": 6.400000000000001e-05, | |
| "loss": 11.9262, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.047337278106508875, | |
| "eval_loss": 11.922493934631348, | |
| "eval_runtime": 4.1897, | |
| "eval_samples_per_second": 358.499, | |
| "eval_steps_per_second": 22.436, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05917159763313609, | |
| "grad_norm": 0.8674926161766052, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9178, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07100591715976332, | |
| "grad_norm": 0.7298563718795776, | |
| "learning_rate": 9.6e-05, | |
| "loss": 11.9053, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07100591715976332, | |
| "eval_loss": 11.886744499206543, | |
| "eval_runtime": 4.2071, | |
| "eval_samples_per_second": 357.015, | |
| "eval_steps_per_second": 22.343, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.08284023668639054, | |
| "grad_norm": 0.8911345601081848, | |
| "learning_rate": 0.00011200000000000001, | |
| "loss": 11.8688, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.09467455621301775, | |
| "grad_norm": 0.7649126052856445, | |
| "learning_rate": 0.00012800000000000002, | |
| "loss": 11.7895, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09467455621301775, | |
| "eval_loss": 11.73801040649414, | |
| "eval_runtime": 4.214, | |
| "eval_samples_per_second": 356.427, | |
| "eval_steps_per_second": 22.306, | |
| "step": 80 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 40, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 78927896772608.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |