{ "best_metric": 0.22960612177848816, "best_model_checkpoint": "miner_id_24/checkpoint-25", "epoch": 0.012952528981283596, "eval_steps": 25, "global_step": 25, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005181011592513439, "grad_norm": 1.0933234691619873, "learning_rate": 5e-05, "loss": 0.8097, "step": 1 }, { "epoch": 0.0005181011592513439, "eval_loss": 1.5387746095657349, "eval_runtime": 371.4805, "eval_samples_per_second": 35.003, "eval_steps_per_second": 4.377, "step": 1 }, { "epoch": 0.0010362023185026877, "grad_norm": 1.895437240600586, "learning_rate": 0.0001, "loss": 0.9627, "step": 2 }, { "epoch": 0.0015543034777540316, "grad_norm": 3.068260431289673, "learning_rate": 9.989294616193017e-05, "loss": 1.2362, "step": 3 }, { "epoch": 0.0020724046370053754, "grad_norm": 1.628536581993103, "learning_rate": 9.957224306869053e-05, "loss": 0.8914, "step": 4 }, { "epoch": 0.0025905057962567193, "grad_norm": 1.8959904909133911, "learning_rate": 9.903926402016153e-05, "loss": 0.8333, "step": 5 }, { "epoch": 0.003108606955508063, "grad_norm": 1.580090045928955, "learning_rate": 9.829629131445342e-05, "loss": 0.6815, "step": 6 }, { "epoch": 0.0036267081147594066, "grad_norm": 1.85896635055542, "learning_rate": 9.73465064747553e-05, "loss": 0.5406, "step": 7 }, { "epoch": 0.004144809274010751, "grad_norm": 1.372404932975769, "learning_rate": 9.619397662556435e-05, "loss": 0.3193, "step": 8 }, { "epoch": 0.004662910433262095, "grad_norm": 0.8892642259597778, "learning_rate": 9.484363707663442e-05, "loss": 0.279, "step": 9 }, { "epoch": 0.005181011592513439, "grad_norm": 1.3139995336532593, "learning_rate": 9.330127018922194e-05, "loss": 0.2967, "step": 10 }, { "epoch": 0.0056991127517647825, "grad_norm": 0.9869577884674072, "learning_rate": 9.157348061512727e-05, "loss": 0.2321, "step": 11 }, { "epoch": 0.006217213911016126, "grad_norm": 0.7818941473960876, "learning_rate": 8.966766701456177e-05, "loss": 0.1574, "step": 12 }, { "epoch": 0.006735315070267469, "grad_norm": 1.7024136781692505, "learning_rate": 8.759199037394887e-05, "loss": 0.7209, "step": 13 }, { "epoch": 0.007253416229518813, "grad_norm": 1.8247325420379639, "learning_rate": 8.535533905932738e-05, "loss": 0.5797, "step": 14 }, { "epoch": 0.007771517388770157, "grad_norm": 1.555863857269287, "learning_rate": 8.296729075500344e-05, "loss": 0.4509, "step": 15 }, { "epoch": 0.008289618548021502, "grad_norm": 1.444915771484375, "learning_rate": 8.043807145043604e-05, "loss": 0.3382, "step": 16 }, { "epoch": 0.008807719707272845, "grad_norm": 1.2211135625839233, "learning_rate": 7.777851165098012e-05, "loss": 0.3352, "step": 17 }, { "epoch": 0.00932582086652419, "grad_norm": 0.8662140965461731, "learning_rate": 7.500000000000001e-05, "loss": 0.2498, "step": 18 }, { "epoch": 0.009843922025775532, "grad_norm": 0.6499209403991699, "learning_rate": 7.211443451095007e-05, "loss": 0.1979, "step": 19 }, { "epoch": 0.010362023185026877, "grad_norm": 0.46657639741897583, "learning_rate": 6.91341716182545e-05, "loss": 0.1525, "step": 20 }, { "epoch": 0.01088012434427822, "grad_norm": 0.5317853093147278, "learning_rate": 6.607197326515808e-05, "loss": 0.1744, "step": 21 }, { "epoch": 0.011398225503529565, "grad_norm": 0.6100855469703674, "learning_rate": 6.294095225512603e-05, "loss": 0.1328, "step": 22 }, { "epoch": 0.011916326662780908, "grad_norm": 0.7363041043281555, "learning_rate": 5.9754516100806423e-05, "loss": 0.18, "step": 23 }, { "epoch": 0.012434427822032253, "grad_norm": 1.291834831237793, "learning_rate": 5.6526309611002594e-05, "loss": 0.1986, "step": 24 }, { "epoch": 0.012952528981283596, "grad_norm": 0.6756670475006104, "learning_rate": 5.327015646150716e-05, "loss": 0.1654, "step": 25 }, { "epoch": 0.012952528981283596, "eval_loss": 0.22960612177848816, "eval_runtime": 370.96, "eval_samples_per_second": 35.052, "eval_steps_per_second": 4.383, "step": 25 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 25, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 1, "early_stopping_threshold": 0.0 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2.9859068337822106e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }