| { | |
| "best_metric": 0.8873636722564697, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.8588298443370908, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017176596886741814, | |
| "grad_norm": 4.154102802276611, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6771, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017176596886741814, | |
| "eval_loss": 1.8637187480926514, | |
| "eval_runtime": 2.0289, | |
| "eval_samples_per_second": 24.644, | |
| "eval_steps_per_second": 6.407, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03435319377348363, | |
| "grad_norm": 4.533133506774902, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7352, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05152979066022544, | |
| "grad_norm": 2.388911724090576, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.5509, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06870638754696726, | |
| "grad_norm": 1.9075318574905396, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.3695, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08588298443370908, | |
| "grad_norm": 1.3614083528518677, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.2724, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10305958132045089, | |
| "grad_norm": 1.086213231086731, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.172, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1202361782071927, | |
| "grad_norm": 0.8740226626396179, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.107, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1374127750939345, | |
| "grad_norm": 0.9693662524223328, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.092, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15458937198067632, | |
| "grad_norm": 0.7072402834892273, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.0412, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.17176596886741816, | |
| "grad_norm": 0.6936845779418945, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.0111, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18894256575415996, | |
| "grad_norm": 0.5797188878059387, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.9895, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.20611916264090177, | |
| "grad_norm": 0.5784722566604614, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.9451, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22329575952764358, | |
| "grad_norm": 0.7698427438735962, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.9752, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2404723564143854, | |
| "grad_norm": 0.5441662669181824, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.9613, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2576489533011272, | |
| "grad_norm": 0.623111367225647, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.9865, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.274825550187869, | |
| "grad_norm": 0.7599939107894897, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.9696, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.29200214707461086, | |
| "grad_norm": 0.7438961267471313, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.9727, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.30917874396135264, | |
| "grad_norm": 1.5077787637710571, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.949, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3263553408480945, | |
| "grad_norm": 0.9674938917160034, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.9476, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3435319377348363, | |
| "grad_norm": 1.347849726676941, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.9312, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3607085346215781, | |
| "grad_norm": 0.989067018032074, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.9118, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.3778851315083199, | |
| "grad_norm": 0.6485913991928101, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.931, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.6245312094688416, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.9088, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.41223832528180354, | |
| "grad_norm": 0.44044724106788635, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.889, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4294149221685454, | |
| "grad_norm": 0.5456480383872986, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.8676, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.4294149221685454, | |
| "eval_loss": 0.9322059154510498, | |
| "eval_runtime": 2.0599, | |
| "eval_samples_per_second": 24.273, | |
| "eval_steps_per_second": 6.311, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.44659151905528716, | |
| "grad_norm": 1.0108604431152344, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.9222, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.463768115942029, | |
| "grad_norm": 0.724280834197998, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.9274, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4809447128287708, | |
| "grad_norm": 0.5844231247901917, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.9069, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4981213097155126, | |
| "grad_norm": 0.7787989974021912, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.918, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5152979066022544, | |
| "grad_norm": 0.5017805695533752, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.9007, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5324745034889963, | |
| "grad_norm": 0.5055813193321228, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.9085, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.549651100375738, | |
| "grad_norm": 0.8349924087524414, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.8921, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5668276972624798, | |
| "grad_norm": 0.6210905909538269, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.9028, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5840042941492217, | |
| "grad_norm": 0.363650381565094, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.885, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6011808910359635, | |
| "grad_norm": 0.49789223074913025, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.88, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6183574879227053, | |
| "grad_norm": 0.4954957067966461, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.8947, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6355340848094472, | |
| "grad_norm": 0.43311986327171326, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.8592, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.652710681696189, | |
| "grad_norm": 0.46934106945991516, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.892, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6698872785829307, | |
| "grad_norm": 0.6024031043052673, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.8857, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6870638754696726, | |
| "grad_norm": 0.711588442325592, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.8997, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7042404723564144, | |
| "grad_norm": 0.5287402868270874, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.8813, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7214170692431562, | |
| "grad_norm": 0.5963271856307983, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.8864, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.738593666129898, | |
| "grad_norm": 0.8385568857192993, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.8777, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7557702630166399, | |
| "grad_norm": 0.6774641275405884, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.8688, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7729468599033816, | |
| "grad_norm": 0.3524174690246582, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.8618, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.3650965690612793, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.8891, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8073000536768653, | |
| "grad_norm": 0.489184707403183, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.904, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8244766505636071, | |
| "grad_norm": 0.35907652974128723, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.8735, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8416532474503489, | |
| "grad_norm": 0.6156330704689026, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.8704, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8588298443370908, | |
| "grad_norm": 0.4536202847957611, | |
| "learning_rate": 1e-05, | |
| "loss": 0.8143, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8588298443370908, | |
| "eval_loss": 0.8873636722564697, | |
| "eval_runtime": 2.0378, | |
| "eval_samples_per_second": 24.536, | |
| "eval_steps_per_second": 6.379, | |
| "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": 1.589463780163584e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |