| { | |
| "best_metric": 3.585186243057251, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.007033430775655537, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014066861551311076, | |
| "grad_norm": 0.9218872785568237, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2525, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014066861551311076, | |
| "eval_loss": 5.381374359130859, | |
| "eval_runtime": 4.3276, | |
| "eval_samples_per_second": 11.554, | |
| "eval_steps_per_second": 3.004, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028133723102622153, | |
| "grad_norm": 1.4398459196090698, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0518, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00042200584653933227, | |
| "grad_norm": 1.8477466106414795, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.6471, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005626744620524431, | |
| "grad_norm": 2.2851502895355225, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 4.4055, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007033430775655537, | |
| "grad_norm": 3.3054018020629883, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.6705, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008440116930786645, | |
| "grad_norm": 3.301938056945801, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.4529, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009846803085917753, | |
| "grad_norm": 2.362037420272827, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.2649, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011253489241048861, | |
| "grad_norm": 2.303856372833252, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.3427, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0012660175396179967, | |
| "grad_norm": 2.2928717136383057, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.2532, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014066861551311075, | |
| "grad_norm": 2.7700459957122803, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.1642, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0015473547706442183, | |
| "grad_norm": 3.446438789367676, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.4021, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001688023386157329, | |
| "grad_norm": 4.7801079750061035, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.6508, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0018286920016704399, | |
| "grad_norm": 3.1333518028259277, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.4654, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0019693606171835507, | |
| "grad_norm": 3.198070526123047, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.8728, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0021100292326966612, | |
| "grad_norm": 2.388134002685547, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.9741, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0022506978482097722, | |
| "grad_norm": 2.387596368789673, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.3491, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.002391366463722883, | |
| "grad_norm": 3.9135308265686035, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.8081, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0025320350792359934, | |
| "grad_norm": 2.6444458961486816, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.7437, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0026727036947491044, | |
| "grad_norm": 1.9664329290390015, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.9872, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.002813372310262215, | |
| "grad_norm": 1.8564341068267822, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.9519, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002954040925775326, | |
| "grad_norm": 2.011428117752075, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.7962, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0030947095412884366, | |
| "grad_norm": 2.2582523822784424, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.0475, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0032353781568015476, | |
| "grad_norm": 2.4788050651550293, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.9397, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.003376046772314658, | |
| "grad_norm": 2.514291763305664, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 4.2982, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0035167153878277687, | |
| "grad_norm": 3.6239752769470215, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.8512, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0035167153878277687, | |
| "eval_loss": 3.6986312866210938, | |
| "eval_runtime": 4.3224, | |
| "eval_samples_per_second": 11.568, | |
| "eval_steps_per_second": 3.008, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0036573840033408797, | |
| "grad_norm": 0.6881301403045654, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.8389, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0037980526188539903, | |
| "grad_norm": 0.792911171913147, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.5026, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.003938721234367101, | |
| "grad_norm": 0.8642730116844177, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.9211, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0040793898498802115, | |
| "grad_norm": 1.2017244100570679, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.4445, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0042200584653933225, | |
| "grad_norm": 1.1826562881469727, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.6573, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0043607270809064335, | |
| "grad_norm": 1.3540639877319336, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.7198, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0045013956964195445, | |
| "grad_norm": 1.3807733058929443, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.6719, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.004642064311932655, | |
| "grad_norm": 1.3128817081451416, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 3.7725, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.004782732927445766, | |
| "grad_norm": 1.4953864812850952, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 3.7893, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.004923401542958877, | |
| "grad_norm": 1.6556501388549805, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 3.9066, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.005064070158471987, | |
| "grad_norm": 1.7631824016571045, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 4.0591, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.005204738773985098, | |
| "grad_norm": 2.5257699489593506, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 4.4642, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.005345407389498209, | |
| "grad_norm": 0.6542789936065674, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 1.8916, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00548607600501132, | |
| "grad_norm": 0.5933400392532349, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.3769, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.00562674462052443, | |
| "grad_norm": 0.7565528154373169, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.7812, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005767413236037541, | |
| "grad_norm": 0.8536903858184814, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.0485, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.005908081851550652, | |
| "grad_norm": 0.993644654750824, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.5119, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.006048750467063762, | |
| "grad_norm": 1.0827058553695679, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.5816, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.006189419082576873, | |
| "grad_norm": 1.3338035345077515, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.7165, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.006330087698089984, | |
| "grad_norm": 1.4324630498886108, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.7711, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.006470756313603095, | |
| "grad_norm": 1.5651832818984985, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 3.6286, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.006611424929116205, | |
| "grad_norm": 1.6895540952682495, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.5996, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.006752093544629316, | |
| "grad_norm": 2.1800448894500732, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 3.9122, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.006892762160142427, | |
| "grad_norm": 2.110852003097534, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 4.0356, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.007033430775655537, | |
| "grad_norm": 3.81133770942688, | |
| "learning_rate": 1e-05, | |
| "loss": 4.6192, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007033430775655537, | |
| "eval_loss": 3.585186243057251, | |
| "eval_runtime": 4.3231, | |
| "eval_samples_per_second": 11.566, | |
| "eval_steps_per_second": 3.007, | |
| "step": 50 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.968083617316864e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |