{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0008945143905002571, "eval_steps": 8, "global_step": 20, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 4.472571952501286e-05, "eval_loss": 2.630528450012207, "eval_runtime": 540.3305, "eval_samples_per_second": 17.425, "eval_steps_per_second": 8.713, "step": 1 }, { "epoch": 0.00013417715857503857, "grad_norm": 3.278907060623169, "learning_rate": 6e-05, "loss": 2.3091, "step": 3 }, { "epoch": 0.00026835431715007714, "grad_norm": 3.802938461303711, "learning_rate": 0.00012, "loss": 2.0507, "step": 6 }, { "epoch": 0.00035780575620010286, "eval_loss": 1.4963546991348267, "eval_runtime": 540.1565, "eval_samples_per_second": 17.43, "eval_steps_per_second": 8.716, "step": 8 }, { "epoch": 0.00040253147572511574, "grad_norm": 3.5205678939819336, "learning_rate": 0.00018, "loss": 1.6357, "step": 9 }, { "epoch": 0.0005367086343001543, "grad_norm": 3.1275179386138916, "learning_rate": 0.00019510565162951537, "loss": 1.3408, "step": 12 }, { "epoch": 0.0006708857928751929, "grad_norm": 2.2836456298828125, "learning_rate": 0.00017071067811865476, "loss": 1.1946, "step": 15 }, { "epoch": 0.0007156115124002057, "eval_loss": 1.2563506364822388, "eval_runtime": 539.8455, "eval_samples_per_second": 17.44, "eval_steps_per_second": 8.721, "step": 16 }, { "epoch": 0.0008050629514502315, "grad_norm": 3.6944832801818848, "learning_rate": 0.00013090169943749476, "loss": 1.1612, "step": 18 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 7418872835604480.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }