| { | |
| "best_metric": 11.760108947753906, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-75", | |
| "epoch": 0.04805959389643157, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006407945852857543, | |
| "grad_norm": 0.018796086311340332, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 11.7657, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006407945852857543, | |
| "eval_loss": 11.764625549316406, | |
| "eval_runtime": 0.2382, | |
| "eval_samples_per_second": 209.889, | |
| "eval_steps_per_second": 54.571, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012815891705715086, | |
| "grad_norm": 0.01367566641420126, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 11.7661, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.001922383755857263, | |
| "grad_norm": 0.014899961650371552, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7662, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002563178341143017, | |
| "grad_norm": 0.015141118317842484, | |
| "learning_rate": 9.99571699711836e-05, | |
| "loss": 11.7662, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0032039729264287716, | |
| "grad_norm": 0.014948413707315922, | |
| "learning_rate": 9.982876141412856e-05, | |
| "loss": 11.7664, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003844767511714526, | |
| "grad_norm": 0.01567680388689041, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.7656, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00448556209700028, | |
| "grad_norm": 0.016142114996910095, | |
| "learning_rate": 9.931634888554937e-05, | |
| "loss": 11.7657, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005126356682286034, | |
| "grad_norm": 0.014875160530209541, | |
| "learning_rate": 9.893332032039701e-05, | |
| "loss": 11.7652, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005767151267571789, | |
| "grad_norm": 0.015255581587553024, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 11.7652, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006407945852857543, | |
| "grad_norm": 0.014767582528293133, | |
| "learning_rate": 9.791726278367022e-05, | |
| "loss": 11.7645, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007048740438143298, | |
| "grad_norm": 0.01818861812353134, | |
| "learning_rate": 9.728616793536588e-05, | |
| "loss": 11.7651, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007689535023429052, | |
| "grad_norm": 0.017870761454105377, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 11.7646, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008330329608714807, | |
| "grad_norm": 0.01960948295891285, | |
| "learning_rate": 9.578385041664925e-05, | |
| "loss": 11.7654, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00897112419400056, | |
| "grad_norm": 0.0150187062099576, | |
| "learning_rate": 9.491548749301997e-05, | |
| "loss": 11.7652, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009611918779286315, | |
| "grad_norm": 0.015270842239260674, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 11.7649, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010252713364572069, | |
| "grad_norm": 0.018579093739390373, | |
| "learning_rate": 9.295261506157986e-05, | |
| "loss": 11.7654, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010893507949857825, | |
| "grad_norm": 0.018623633310198784, | |
| "learning_rate": 9.186184199300464e-05, | |
| "loss": 11.7655, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.011534302535143579, | |
| "grad_norm": 0.021639393642544746, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 11.764, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012175097120429332, | |
| "grad_norm": 0.023298516869544983, | |
| "learning_rate": 8.947199994035401e-05, | |
| "loss": 11.7645, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012815891705715086, | |
| "grad_norm": 0.023485591635107994, | |
| "learning_rate": 8.817748015645558e-05, | |
| "loss": 11.7654, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01345668629100084, | |
| "grad_norm": 0.021341130137443542, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 11.7633, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014097480876286596, | |
| "grad_norm": 0.01896008849143982, | |
| "learning_rate": 8.540155934270471e-05, | |
| "loss": 11.7641, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01473827546157235, | |
| "grad_norm": 0.02342885173857212, | |
| "learning_rate": 8.392544243589427e-05, | |
| "loss": 11.7632, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.015379070046858104, | |
| "grad_norm": 0.02347911335527897, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 11.7628, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01601986463214386, | |
| "grad_norm": 0.025197699666023254, | |
| "learning_rate": 8.081093963579707e-05, | |
| "loss": 11.7631, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01601986463214386, | |
| "eval_loss": 11.763106346130371, | |
| "eval_runtime": 0.2386, | |
| "eval_samples_per_second": 209.58, | |
| "eval_steps_per_second": 54.491, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016660659217429614, | |
| "grad_norm": 0.02223326452076435, | |
| "learning_rate": 7.917848237560709e-05, | |
| "loss": 11.7637, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.017301453802715368, | |
| "grad_norm": 0.020472681149840355, | |
| "learning_rate": 7.75e-05, | |
| "loss": 11.7644, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01794224838800112, | |
| "grad_norm": 0.023782216012477875, | |
| "learning_rate": 7.577868759557654e-05, | |
| "loss": 11.7642, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.018583042973286876, | |
| "grad_norm": 0.0240348968654871, | |
| "learning_rate": 7.401782177833148e-05, | |
| "loss": 11.765, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.01922383755857263, | |
| "grad_norm": 0.028316188603639603, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 11.7643, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019864632143858384, | |
| "grad_norm": 0.02909417264163494, | |
| "learning_rate": 7.03909064496551e-05, | |
| "loss": 11.763, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.020505426729144138, | |
| "grad_norm": 0.029121633619070053, | |
| "learning_rate": 6.853176097769229e-05, | |
| "loss": 11.763, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02114622131442989, | |
| "grad_norm": 0.0339232012629509, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 11.7627, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02178701589971565, | |
| "grad_norm": 0.03640107810497284, | |
| "learning_rate": 6.473978262721463e-05, | |
| "loss": 11.7633, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.022427810485001403, | |
| "grad_norm": 0.03253023698925972, | |
| "learning_rate": 6.281416799501188e-05, | |
| "loss": 11.7621, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.023068605070287157, | |
| "grad_norm": 0.028020696714520454, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 11.7629, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02370939965557291, | |
| "grad_norm": 0.031051475554704666, | |
| "learning_rate": 5.8922008423644624e-05, | |
| "loss": 11.7626, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.024350194240858665, | |
| "grad_norm": 0.04053696244955063, | |
| "learning_rate": 5.696287243144013e-05, | |
| "loss": 11.7636, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02499098882614442, | |
| "grad_norm": 0.029524900019168854, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 11.7634, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.025631783411430173, | |
| "grad_norm": 0.03623311594128609, | |
| "learning_rate": 5.303712756855988e-05, | |
| "loss": 11.7624, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026272577996715927, | |
| "grad_norm": 0.03804594278335571, | |
| "learning_rate": 5.107799157635538e-05, | |
| "loss": 11.763, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02691337258200168, | |
| "grad_norm": 0.03952088952064514, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 11.7628, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.027554167167287435, | |
| "grad_norm": 0.037932537496089935, | |
| "learning_rate": 4.718583200498814e-05, | |
| "loss": 11.763, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.028194961752573192, | |
| "grad_norm": 0.04360462725162506, | |
| "learning_rate": 4.526021737278538e-05, | |
| "loss": 11.7623, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.028835756337858946, | |
| "grad_norm": 0.04510717839002609, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 11.762, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0294765509231447, | |
| "grad_norm": 0.03812625631690025, | |
| "learning_rate": 4.146823902230772e-05, | |
| "loss": 11.762, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.030117345508430454, | |
| "grad_norm": 0.04157785326242447, | |
| "learning_rate": 3.960909355034491e-05, | |
| "loss": 11.7614, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.030758140093716208, | |
| "grad_norm": 0.044761281460523605, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 11.762, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03139893467900196, | |
| "grad_norm": 0.04416681081056595, | |
| "learning_rate": 3.598217822166854e-05, | |
| "loss": 11.7618, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03203972926428772, | |
| "grad_norm": 0.0453573577105999, | |
| "learning_rate": 3.422131240442349e-05, | |
| "loss": 11.7605, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03203972926428772, | |
| "eval_loss": 11.761113166809082, | |
| "eval_runtime": 0.2345, | |
| "eval_samples_per_second": 213.264, | |
| "eval_steps_per_second": 55.449, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03268052384957347, | |
| "grad_norm": 0.03685550019145012, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 11.7635, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.03332131843485923, | |
| "grad_norm": 0.04207245260477066, | |
| "learning_rate": 3.082151762439293e-05, | |
| "loss": 11.7628, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.03396211302014498, | |
| "grad_norm": 0.047665830701589584, | |
| "learning_rate": 2.9189060364202943e-05, | |
| "loss": 11.7617, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.034602907605430736, | |
| "grad_norm": 0.050436247140169144, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 11.7613, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.035243702190716486, | |
| "grad_norm": 0.04612034186720848, | |
| "learning_rate": 2.6074557564105727e-05, | |
| "loss": 11.7613, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03588449677600224, | |
| "grad_norm": 0.04736921191215515, | |
| "learning_rate": 2.459844065729529e-05, | |
| "loss": 11.7612, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.036525291361287994, | |
| "grad_norm": 0.05022180452942848, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 11.7604, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.03716608594657375, | |
| "grad_norm": 0.04974595829844475, | |
| "learning_rate": 2.1822519843544424e-05, | |
| "loss": 11.76, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.03780688053185951, | |
| "grad_norm": 0.047848932445049286, | |
| "learning_rate": 2.0528000059645997e-05, | |
| "loss": 11.7615, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.03844767511714526, | |
| "grad_norm": 0.04960588365793228, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 11.7612, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03908846970243102, | |
| "grad_norm": 0.05584871768951416, | |
| "learning_rate": 1.8138158006995364e-05, | |
| "loss": 11.7601, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.03972926428771677, | |
| "grad_norm": 0.04442853853106499, | |
| "learning_rate": 1.7047384938420154e-05, | |
| "loss": 11.7609, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.040370058873002525, | |
| "grad_norm": 0.04721665382385254, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 11.7637, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.041010853458288275, | |
| "grad_norm": 0.04801863431930542, | |
| "learning_rate": 1.5084512506980026e-05, | |
| "loss": 11.7612, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.04165164804357403, | |
| "grad_norm": 0.04716704413294792, | |
| "learning_rate": 1.4216149583350754e-05, | |
| "loss": 11.7627, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.04229244262885978, | |
| "grad_norm": 0.05011888965964317, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 11.761, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.04293323721414554, | |
| "grad_norm": 0.04726472124457359, | |
| "learning_rate": 1.2713832064634126e-05, | |
| "loss": 11.7608, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.0435740317994313, | |
| "grad_norm": 0.053742505609989166, | |
| "learning_rate": 1.2082737216329794e-05, | |
| "loss": 11.76, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.04421482638471705, | |
| "grad_norm": 0.05879789963364601, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 11.7597, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.044855620970002806, | |
| "grad_norm": 0.05244609713554382, | |
| "learning_rate": 1.1066679679603e-05, | |
| "loss": 11.7611, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04549641555528856, | |
| "grad_norm": 0.05740131437778473, | |
| "learning_rate": 1.0683651114450641e-05, | |
| "loss": 11.7612, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.046137210140574314, | |
| "grad_norm": 0.04920673370361328, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 11.7614, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.046778004725860065, | |
| "grad_norm": 0.05816422030329704, | |
| "learning_rate": 1.017123858587145e-05, | |
| "loss": 11.7607, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.04741879931114582, | |
| "grad_norm": 0.05213126912713051, | |
| "learning_rate": 1.00428300288164e-05, | |
| "loss": 11.7598, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.04805959389643157, | |
| "grad_norm": 0.061734773218631744, | |
| "learning_rate": 1e-05, | |
| "loss": 11.7597, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.04805959389643157, | |
| "eval_loss": 11.760108947753906, | |
| "eval_runtime": 0.2399, | |
| "eval_samples_per_second": 208.462, | |
| "eval_steps_per_second": 54.2, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "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": 246955923210240.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |