{ "best_global_step": 69, "best_metric": 0.7231942415237427, "best_model_checkpoint": "/home/workspace/Projects/NeuralAI/checkpoints/v2_model/checkpoint-69", "epoch": 3.0, "eval_steps": 500, "global_step": 69, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.44077134986225897, "grad_norm": 0.8227247595787048, "learning_rate": 3.6e-05, "loss": 2.102004623413086, "step": 10 }, { "epoch": 0.8815426997245179, "grad_norm": 0.770205557346344, "learning_rate": 7.6e-05, "loss": 1.942721176147461, "step": 20 }, { "epoch": 1.0, "eval_loss": 1.6713197231292725, "eval_runtime": 23.3461, "eval_samples_per_second": 1.756, "eval_steps_per_second": 1.756, "step": 23 }, { "epoch": 1.3085399449035813, "grad_norm": 0.45185327529907227, "learning_rate": 0.000116, "loss": 1.6010663986206055, "step": 30 }, { "epoch": 1.7493112947658402, "grad_norm": 0.3300871253013611, "learning_rate": 0.00015600000000000002, "loss": 1.1151976585388184, "step": 40 }, { "epoch": 2.0, "eval_loss": 0.896889865398407, "eval_runtime": 17.5969, "eval_samples_per_second": 2.33, "eval_steps_per_second": 2.33, "step": 46 }, { "epoch": 2.1763085399449036, "grad_norm": 0.31101763248443604, "learning_rate": 0.000196, "loss": 0.9162005424499512, "step": 50 }, { "epoch": 2.6170798898071626, "grad_norm": 0.32379862666130066, "learning_rate": 0.00010825793454723325, "loss": 0.7014970779418945, "step": 60 }, { "epoch": 3.0, "eval_loss": 0.7231942415237427, "eval_runtime": 17.6154, "eval_samples_per_second": 2.328, "eval_steps_per_second": 2.328, "step": 69 } ], "logging_steps": 10, "max_steps": 69, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 134948060628480.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }