| { | |
| "best_metric": 11.930046081542969, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.13218770654329148, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026437541308658294, | |
| "grad_norm": 0.010745295323431492, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9318, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026437541308658294, | |
| "eval_loss": 11.931646347045898, | |
| "eval_runtime": 4.9892, | |
| "eval_samples_per_second": 510.907, | |
| "eval_steps_per_second": 63.939, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005287508261731659, | |
| "grad_norm": 0.011476602405309677, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9326, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007931262392597489, | |
| "grad_norm": 0.011935018934309483, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.9325, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010575016523463317, | |
| "grad_norm": 0.013454741798341274, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9327, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013218770654329148, | |
| "grad_norm": 0.014640376903116703, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9324, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015862524785194978, | |
| "grad_norm": 0.016238609328866005, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.932, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018506278916060808, | |
| "grad_norm": 0.015399875119328499, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.9309, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.021150033046926635, | |
| "grad_norm": 0.018817206844687462, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.931, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023793787177792465, | |
| "grad_norm": 0.01851794123649597, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.931, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026437541308658295, | |
| "grad_norm": 0.024672048166394234, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9306, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029081295439524125, | |
| "grad_norm": 0.02825287915766239, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9293, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.031725049570389956, | |
| "grad_norm": 0.036237020045518875, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.9288, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.034368803701255786, | |
| "grad_norm": 0.015837639570236206, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.932, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.037012557832121616, | |
| "grad_norm": 0.016001172363758087, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9321, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03965631196298744, | |
| "grad_norm": 0.017925556749105453, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.9316, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04230006609385327, | |
| "grad_norm": 0.01816387288272381, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.9313, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0449438202247191, | |
| "grad_norm": 0.021857665851712227, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.9313, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04758757435558493, | |
| "grad_norm": 0.019407255575060844, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9314, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05023132848645076, | |
| "grad_norm": 0.02040601335465908, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.9329, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05287508261731659, | |
| "grad_norm": 0.0221166480332613, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9299, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05551883674818242, | |
| "grad_norm": 0.03244011849164963, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.9312, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05816259087904825, | |
| "grad_norm": 0.03103022463619709, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.9303, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06080634500991408, | |
| "grad_norm": 0.028204262256622314, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.9305, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06345009914077991, | |
| "grad_norm": 0.03637426346540451, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.9293, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06609385327164574, | |
| "grad_norm": 0.06525248289108276, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.9281, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06609385327164574, | |
| "eval_loss": 11.930604934692383, | |
| "eval_runtime": 4.986, | |
| "eval_samples_per_second": 511.231, | |
| "eval_steps_per_second": 63.979, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06873760740251157, | |
| "grad_norm": 0.023965967819094658, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9315, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0713813615333774, | |
| "grad_norm": 0.028746068477630615, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.9309, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07402511566424323, | |
| "grad_norm": 0.02350783348083496, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.9309, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07666886979510905, | |
| "grad_norm": 0.023529646918177605, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.9306, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07931262392597488, | |
| "grad_norm": 0.029583023861050606, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.931, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08195637805684071, | |
| "grad_norm": 0.03481192886829376, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.9314, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08460013218770654, | |
| "grad_norm": 0.029739735648036003, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9306, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08724388631857237, | |
| "grad_norm": 0.045527901500463486, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.9296, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0898876404494382, | |
| "grad_norm": 0.04223807901144028, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.9297, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09253139458030403, | |
| "grad_norm": 0.04213787242770195, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.9264, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09517514871116986, | |
| "grad_norm": 0.05223255604505539, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.9304, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09781890284203569, | |
| "grad_norm": 0.06267008930444717, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.93, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10046265697290152, | |
| "grad_norm": 0.028014397248625755, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9311, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10310641110376735, | |
| "grad_norm": 0.027659038081765175, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.931, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10575016523463318, | |
| "grad_norm": 0.02421857975423336, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.931, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10839391936549901, | |
| "grad_norm": 0.028048740699887276, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.9312, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11103767349636484, | |
| "grad_norm": 0.029408879578113556, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.9307, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11368142762723067, | |
| "grad_norm": 0.030845344066619873, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.9309, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1163251817580965, | |
| "grad_norm": 0.037856973707675934, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9294, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11896893588896233, | |
| "grad_norm": 0.04141073301434517, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.9316, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12161269001982816, | |
| "grad_norm": 0.034333162009716034, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.9299, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12425644415069398, | |
| "grad_norm": 0.04394075274467468, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.928, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12690019828155982, | |
| "grad_norm": 0.05368373543024063, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.927, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12954395241242564, | |
| "grad_norm": 0.042175471782684326, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.9265, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13218770654329148, | |
| "grad_norm": 0.05652758851647377, | |
| "learning_rate": 0.0, | |
| "loss": 11.9265, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13218770654329148, | |
| "eval_loss": 11.930046081542969, | |
| "eval_runtime": 5.012, | |
| "eval_samples_per_second": 508.575, | |
| "eval_steps_per_second": 63.647, | |
| "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": 1042494259200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |