| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001859773107680863, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003719546215361726, | |
| "grad_norm": 28.77135467529297, | |
| "learning_rate": 2e-05, | |
| "loss": 45.9604, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003719546215361726, | |
| "eval_loss": 11.40648078918457, | |
| "eval_runtime": 137.0275, | |
| "eval_samples_per_second": 8.261, | |
| "eval_steps_per_second": 4.131, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007439092430723452, | |
| "grad_norm": 23.410951614379883, | |
| "learning_rate": 4e-05, | |
| "loss": 46.8527, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007439092430723452, | |
| "eval_loss": 11.40257453918457, | |
| "eval_runtime": 137.8996, | |
| "eval_samples_per_second": 8.209, | |
| "eval_steps_per_second": 4.104, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011158638646085177, | |
| "grad_norm": 33.30792999267578, | |
| "learning_rate": 6e-05, | |
| "loss": 44.8008, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0014878184861446904, | |
| "grad_norm": 27.510290145874023, | |
| "learning_rate": 8e-05, | |
| "loss": 48.3234, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014878184861446904, | |
| "eval_loss": 11.253341674804688, | |
| "eval_runtime": 138.0011, | |
| "eval_samples_per_second": 8.203, | |
| "eval_steps_per_second": 4.101, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.001859773107680863, | |
| "grad_norm": 23.642324447631836, | |
| "learning_rate": 0.0001, | |
| "loss": 42.2976, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3166204172697600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |