| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0002184002184002184, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.42666909333576e-05, | |
| "grad_norm": 8.195829391479492, | |
| "learning_rate": 2e-05, | |
| "loss": 13.288, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.42666909333576e-05, | |
| "eval_loss": 3.190768003463745, | |
| "eval_runtime": 287.5377, | |
| "eval_samples_per_second": 60.343, | |
| "eval_steps_per_second": 30.173, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.85333818667152e-05, | |
| "grad_norm": 5.681870460510254, | |
| "learning_rate": 4e-05, | |
| "loss": 13.1977, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 7.28000728000728e-05, | |
| "grad_norm": 8.005084991455078, | |
| "learning_rate": 6e-05, | |
| "loss": 13.2657, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.28000728000728e-05, | |
| "eval_loss": 3.1813180446624756, | |
| "eval_runtime": 286.5928, | |
| "eval_samples_per_second": 60.542, | |
| "eval_steps_per_second": 30.273, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.70667637334304e-05, | |
| "grad_norm": 9.094429016113281, | |
| "learning_rate": 8e-05, | |
| "loss": 13.8729, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000121333454666788, | |
| "grad_norm": 9.367225646972656, | |
| "learning_rate": 0.0001, | |
| "loss": 13.548, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001456001456001456, | |
| "grad_norm": 5.921675205230713, | |
| "learning_rate": 0.00012, | |
| "loss": 11.6533, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001456001456001456, | |
| "eval_loss": 3.0957133769989014, | |
| "eval_runtime": 287.9578, | |
| "eval_samples_per_second": 60.255, | |
| "eval_steps_per_second": 30.129, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001698668365335032, | |
| "grad_norm": 4.545871257781982, | |
| "learning_rate": 0.00014, | |
| "loss": 11.2224, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0001941335274668608, | |
| "grad_norm": 11.329343795776367, | |
| "learning_rate": 0.00016, | |
| "loss": 14.2415, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002184002184002184, | |
| "grad_norm": 6.399060249328613, | |
| "learning_rate": 0.00018, | |
| "loss": 11.4404, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002184002184002184, | |
| "eval_loss": 2.872811794281006, | |
| "eval_runtime": 287.5926, | |
| "eval_samples_per_second": 60.332, | |
| "eval_steps_per_second": 30.168, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 603978124492800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |