| { | |
| "best_metric": 0.1482105553150177, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.3410214168039538, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.026359143327841845, | |
| "grad_norm": 1.786991000175476, | |
| "learning_rate": 5e-05, | |
| "loss": 2.424, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026359143327841845, | |
| "eval_loss": 3.623441457748413, | |
| "eval_runtime": 1.5455, | |
| "eval_samples_per_second": 32.351, | |
| "eval_steps_per_second": 8.411, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05271828665568369, | |
| "grad_norm": 2.6462996006011963, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7332, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07907742998352553, | |
| "grad_norm": 2.920393943786621, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.8657, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10543657331136738, | |
| "grad_norm": 2.5311219692230225, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 2.5304, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.13179571663920922, | |
| "grad_norm": 2.6077513694763184, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 2.4377, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15815485996705106, | |
| "grad_norm": 2.9473812580108643, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 2.3731, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.18451400329489293, | |
| "grad_norm": 2.8991787433624268, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.4028, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.21087314662273476, | |
| "grad_norm": 3.1987361907958984, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 2.4361, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2372322899505766, | |
| "grad_norm": 4.290524005889893, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.7377, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.26359143327841844, | |
| "grad_norm": 2.7644436359405518, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.7703, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2899505766062603, | |
| "grad_norm": 2.7842302322387695, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.2086, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3163097199341021, | |
| "grad_norm": 2.316791296005249, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.0678, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.342668863261944, | |
| "grad_norm": 1.990553379058838, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.0031, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.36902800658978585, | |
| "grad_norm": 1.9706357717514038, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.9653, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3953871499176277, | |
| "grad_norm": 1.715912103652954, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.1122, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.42174629324546953, | |
| "grad_norm": 1.8408265113830566, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.0778, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.44810543657331137, | |
| "grad_norm": 1.8062630891799927, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.1266, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4744645799011532, | |
| "grad_norm": 2.897865056991577, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2596, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.500823723228995, | |
| "grad_norm": 2.2896714210510254, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.1906, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.5271828665568369, | |
| "grad_norm": 1.7460556030273438, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.6186, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5535420098846787, | |
| "grad_norm": 1.413374423980713, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.4566, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5799011532125206, | |
| "grad_norm": 1.3679693937301636, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.4401, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6062602965403624, | |
| "grad_norm": 1.1918940544128418, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.4332, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.6326194398682042, | |
| "grad_norm": 1.4845181703567505, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4871, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6589785831960461, | |
| "grad_norm": 2.532322645187378, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.5879, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6589785831960461, | |
| "eval_loss": 0.5001410841941833, | |
| "eval_runtime": 1.146, | |
| "eval_samples_per_second": 43.628, | |
| "eval_steps_per_second": 11.343, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.685337726523888, | |
| "grad_norm": 2.631470203399658, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.6052, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.7116968698517299, | |
| "grad_norm": 3.366347551345825, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.6785, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.7380560131795717, | |
| "grad_norm": 2.787581443786621, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.6834, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.7644151565074135, | |
| "grad_norm": 2.7616989612579346, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.521, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.7907742998352554, | |
| "grad_norm": 1.800349473953247, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.1854, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.8171334431630972, | |
| "grad_norm": 1.3683643341064453, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.1933, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.8434925864909391, | |
| "grad_norm": 1.2189134359359741, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.1998, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.8698517298187809, | |
| "grad_norm": 0.9834485054016113, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.1772, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.8962108731466227, | |
| "grad_norm": 1.4624574184417725, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.2667, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.9225700164744646, | |
| "grad_norm": 2.1892504692077637, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.3295, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.9489291598023064, | |
| "grad_norm": 2.554065704345703, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.3938, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.9752883031301482, | |
| "grad_norm": 4.097619533538818, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.4655, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.0247116968698518, | |
| "grad_norm": 4.688210964202881, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.6527, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0510708401976936, | |
| "grad_norm": 1.0379397869110107, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.1263, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.0774299835255354, | |
| "grad_norm": 1.0427350997924805, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.1028, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.1037891268533773, | |
| "grad_norm": 1.8991127014160156, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.1048, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.130148270181219, | |
| "grad_norm": 1.0854698419570923, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.0931, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.156507413509061, | |
| "grad_norm": 1.1111361980438232, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.1551, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.1828665568369028, | |
| "grad_norm": 1.4815325736999512, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.1946, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.2092257001647446, | |
| "grad_norm": 1.8528581857681274, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.2864, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.2355848434925865, | |
| "grad_norm": 3.5704665184020996, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.3412, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.2619439868204283, | |
| "grad_norm": 2.261692762374878, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.2793, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.2883031301482701, | |
| "grad_norm": 1.0988763570785522, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.0969, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.314662273476112, | |
| "grad_norm": 0.856013298034668, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.0607, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.3410214168039538, | |
| "grad_norm": 0.9837825894355774, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0639, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.3410214168039538, | |
| "eval_loss": 0.1482105553150177, | |
| "eval_runtime": 1.1545, | |
| "eval_samples_per_second": 43.307, | |
| "eval_steps_per_second": 11.26, | |
| "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 | |
| } | |