| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.974025974025974, | |
| "eval_steps": 100, | |
| "global_step": 76, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2597402597402597, | |
| "grad_norm": 1.0983422913092455, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.8718, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5194805194805194, | |
| "grad_norm": 0.817384469436946, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9287, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7792207792207793, | |
| "grad_norm": 0.7731335837941871, | |
| "learning_rate": 4.6168104980707107e-05, | |
| "loss": 0.5966, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0389610389610389, | |
| "grad_norm": 0.5256264680619972, | |
| "learning_rate": 3.5847093477938956e-05, | |
| "loss": 0.4953, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2987012987012987, | |
| "grad_norm": 0.32201925598994324, | |
| "learning_rate": 2.2200888097417307e-05, | |
| "loss": 0.4969, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5584415584415585, | |
| "grad_norm": 0.2677727233240022, | |
| "learning_rate": 9.412754953531663e-06, | |
| "loss": 0.4889, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.8181818181818183, | |
| "grad_norm": 0.7394265901847812, | |
| "learning_rate": 1.4029167422908107e-06, | |
| "loss": 0.5113, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.974025974025974, | |
| "step": 76, | |
| "total_flos": 34479036694528.0, | |
| "train_loss": 0.6159840069319072, | |
| "train_runtime": 412.9286, | |
| "train_samples_per_second": 2.95, | |
| "train_steps_per_second": 0.184 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 76, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 34479036694528.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |