{ "best_metric": 1.0584245920181274, "best_model_checkpoint": "miner_id_24/checkpoint-50", "epoch": 1.2903225806451613, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.025806451612903226, "grad_norm": 0.8154280185699463, "learning_rate": 5e-05, "loss": 2.036, "step": 1 }, { "epoch": 0.025806451612903226, "eval_loss": 1.9736554622650146, "eval_runtime": 3.0347, "eval_samples_per_second": 86.334, "eval_steps_per_second": 10.874, "step": 1 }, { "epoch": 0.05161290322580645, "grad_norm": 0.9636016488075256, "learning_rate": 0.0001, "loss": 1.953, "step": 2 }, { "epoch": 0.07741935483870968, "grad_norm": 1.0712406635284424, "learning_rate": 9.989294616193017e-05, "loss": 1.8551, "step": 3 }, { "epoch": 0.1032258064516129, "grad_norm": 0.9042462110519409, "learning_rate": 9.957224306869053e-05, "loss": 1.6841, "step": 4 }, { "epoch": 0.12903225806451613, "grad_norm": 0.9828581809997559, "learning_rate": 9.903926402016153e-05, "loss": 1.4698, "step": 5 }, { "epoch": 0.15483870967741936, "grad_norm": 1.0596216917037964, "learning_rate": 9.829629131445342e-05, "loss": 1.4499, "step": 6 }, { "epoch": 0.18064516129032257, "grad_norm": 1.1427077054977417, "learning_rate": 9.73465064747553e-05, "loss": 1.3559, "step": 7 }, { "epoch": 0.2064516129032258, "grad_norm": 1.011368751525879, "learning_rate": 9.619397662556435e-05, "loss": 1.2267, "step": 8 }, { "epoch": 0.23225806451612904, "grad_norm": 0.8033608794212341, "learning_rate": 9.484363707663442e-05, "loss": 0.9945, "step": 9 }, { "epoch": 0.25806451612903225, "grad_norm": 1.294642686843872, "learning_rate": 9.330127018922194e-05, "loss": 1.661, "step": 10 }, { "epoch": 0.2838709677419355, "grad_norm": 1.1089555025100708, "learning_rate": 9.157348061512727e-05, "loss": 1.5621, "step": 11 }, { "epoch": 0.3096774193548387, "grad_norm": 0.6231883764266968, "learning_rate": 8.966766701456177e-05, "loss": 1.448, "step": 12 }, { "epoch": 0.33548387096774196, "grad_norm": 0.7332714796066284, "learning_rate": 8.759199037394887e-05, "loss": 1.3044, "step": 13 }, { "epoch": 0.36129032258064514, "grad_norm": 0.8896142840385437, "learning_rate": 8.535533905932738e-05, "loss": 1.0781, "step": 14 }, { "epoch": 0.3870967741935484, "grad_norm": 0.7502830028533936, "learning_rate": 8.296729075500344e-05, "loss": 1.0254, "step": 15 }, { "epoch": 0.4129032258064516, "grad_norm": 0.6011187434196472, "learning_rate": 8.043807145043604e-05, "loss": 1.0411, "step": 16 }, { "epoch": 0.43870967741935485, "grad_norm": 0.5312099456787109, "learning_rate": 7.777851165098012e-05, "loss": 1.0013, "step": 17 }, { "epoch": 0.4645161290322581, "grad_norm": 0.5888484716415405, "learning_rate": 7.500000000000001e-05, "loss": 0.9215, "step": 18 }, { "epoch": 0.49032258064516127, "grad_norm": 0.6311532855033875, "learning_rate": 7.211443451095007e-05, "loss": 0.7885, "step": 19 }, { "epoch": 0.5161290322580645, "grad_norm": 0.7916381359100342, "learning_rate": 6.91341716182545e-05, "loss": 1.652, "step": 20 }, { "epoch": 0.5419354838709678, "grad_norm": 0.743448793888092, "learning_rate": 6.607197326515808e-05, "loss": 1.4368, "step": 21 }, { "epoch": 0.567741935483871, "grad_norm": 0.6138935089111328, "learning_rate": 6.294095225512603e-05, "loss": 1.2923, "step": 22 }, { "epoch": 0.5935483870967742, "grad_norm": 0.5238935351371765, "learning_rate": 5.9754516100806423e-05, "loss": 1.1441, "step": 23 }, { "epoch": 0.6193548387096774, "grad_norm": 0.4640217125415802, "learning_rate": 5.6526309611002594e-05, "loss": 1.0112, "step": 24 }, { "epoch": 0.6451612903225806, "grad_norm": 0.5122854709625244, "learning_rate": 5.327015646150716e-05, "loss": 1.0068, "step": 25 }, { "epoch": 0.6451612903225806, "eval_loss": 1.1054987907409668, "eval_runtime": 3.0392, "eval_samples_per_second": 86.206, "eval_steps_per_second": 10.858, "step": 25 }, { "epoch": 0.6709677419354839, "grad_norm": 0.5813565254211426, "learning_rate": 5e-05, "loss": 0.9636, "step": 26 }, { "epoch": 0.6967741935483871, "grad_norm": 0.7932458519935608, "learning_rate": 4.6729843538492847e-05, "loss": 1.0167, "step": 27 }, { "epoch": 0.7225806451612903, "grad_norm": 0.9700523614883423, "learning_rate": 4.347369038899744e-05, "loss": 0.8829, "step": 28 }, { "epoch": 0.7483870967741936, "grad_norm": 0.5052369832992554, "learning_rate": 4.0245483899193595e-05, "loss": 1.4428, "step": 29 }, { "epoch": 0.7741935483870968, "grad_norm": 0.47946470975875854, "learning_rate": 3.705904774487396e-05, "loss": 1.4643, "step": 30 }, { "epoch": 0.8, "grad_norm": 0.558689534664154, "learning_rate": 3.392802673484193e-05, "loss": 1.4191, "step": 31 }, { "epoch": 0.8258064516129032, "grad_norm": 0.5564653277397156, "learning_rate": 3.086582838174551e-05, "loss": 1.1855, "step": 32 }, { "epoch": 0.8516129032258064, "grad_norm": 0.5914702415466309, "learning_rate": 2.7885565489049946e-05, "loss": 1.0954, "step": 33 }, { "epoch": 0.8774193548387097, "grad_norm": 0.5616559982299805, "learning_rate": 2.500000000000001e-05, "loss": 0.9159, "step": 34 }, { "epoch": 0.9032258064516129, "grad_norm": 0.49449753761291504, "learning_rate": 2.2221488349019903e-05, "loss": 1.0043, "step": 35 }, { "epoch": 0.9290322580645162, "grad_norm": 0.4511263072490692, "learning_rate": 1.9561928549563968e-05, "loss": 1.0054, "step": 36 }, { "epoch": 0.9548387096774194, "grad_norm": 0.48819997906684875, "learning_rate": 1.703270924499656e-05, "loss": 0.8986, "step": 37 }, { "epoch": 0.9806451612903225, "grad_norm": 0.902423083782196, "learning_rate": 1.4644660940672627e-05, "loss": 0.797, "step": 38 }, { "epoch": 1.0064516129032257, "grad_norm": 0.4955236613750458, "learning_rate": 1.2408009626051137e-05, "loss": 1.4944, "step": 39 }, { "epoch": 1.032258064516129, "grad_norm": 0.4850037395954132, "learning_rate": 1.0332332985438248e-05, "loss": 1.4419, "step": 40 }, { "epoch": 1.0580645161290323, "grad_norm": 0.452665239572525, "learning_rate": 8.426519384872733e-06, "loss": 1.2644, "step": 41 }, { "epoch": 1.0838709677419356, "grad_norm": 0.4906958043575287, "learning_rate": 6.698729810778065e-06, "loss": 1.0876, "step": 42 }, { "epoch": 1.1096774193548387, "grad_norm": 0.4720699191093445, "learning_rate": 5.156362923365588e-06, "loss": 1.05, "step": 43 }, { "epoch": 1.135483870967742, "grad_norm": 0.48330122232437134, "learning_rate": 3.8060233744356633e-06, "loss": 0.9107, "step": 44 }, { "epoch": 1.1612903225806452, "grad_norm": 0.47461310029029846, "learning_rate": 2.653493525244721e-06, "loss": 0.8799, "step": 45 }, { "epoch": 1.1870967741935483, "grad_norm": 0.5562615394592285, "learning_rate": 1.70370868554659e-06, "loss": 0.8838, "step": 46 }, { "epoch": 1.2129032258064516, "grad_norm": 0.5205037593841553, "learning_rate": 9.607359798384785e-07, "loss": 0.9087, "step": 47 }, { "epoch": 1.238709677419355, "grad_norm": 0.5238860845565796, "learning_rate": 4.277569313094809e-07, "loss": 0.6349, "step": 48 }, { "epoch": 1.2645161290322582, "grad_norm": 0.5059917569160461, "learning_rate": 1.0705383806982606e-07, "loss": 1.8134, "step": 49 }, { "epoch": 1.2903225806451613, "grad_norm": 0.4797428250312805, "learning_rate": 0.0, "loss": 1.44, "step": 50 }, { "epoch": 1.2903225806451613, "eval_loss": 1.0584245920181274, "eval_runtime": 3.038, "eval_samples_per_second": 86.24, "eval_steps_per_second": 10.862, "step": 50 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": true }, "attributes": {} } }, "total_flos": 1.059536353886208e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }