| { | |
| "best_metric": 11.930010795593262, | |
| "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": 0.00984097644686699, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9318, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0026437541308658294, | |
| "eval_loss": 11.931646347045898, | |
| "eval_runtime": 4.9896, | |
| "eval_samples_per_second": 510.862, | |
| "eval_steps_per_second": 63.933, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005287508261731659, | |
| "grad_norm": 0.01006829459220171, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9326, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007931262392597489, | |
| "grad_norm": 0.010929228737950325, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.9325, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010575016523463317, | |
| "grad_norm": 0.012183292768895626, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9327, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013218770654329148, | |
| "grad_norm": 0.013453771360218525, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9325, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015862524785194978, | |
| "grad_norm": 0.015635179355740547, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.932, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.018506278916060808, | |
| "grad_norm": 0.01466907374560833, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.9309, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.021150033046926635, | |
| "grad_norm": 0.01824771985411644, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.931, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.023793787177792465, | |
| "grad_norm": 0.019037945196032524, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.931, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.026437541308658295, | |
| "grad_norm": 0.025048309937119484, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9306, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.029081295439524125, | |
| "grad_norm": 0.03073783591389656, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9293, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.031725049570389956, | |
| "grad_norm": 0.034861885011196136, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.9288, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.034368803701255786, | |
| "grad_norm": 0.014655872248113155, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.932, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.037012557832121616, | |
| "grad_norm": 0.014537245035171509, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9321, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.03965631196298744, | |
| "grad_norm": 0.01639895886182785, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.9316, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04230006609385327, | |
| "grad_norm": 0.01693638414144516, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.9313, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0449438202247191, | |
| "grad_norm": 0.01980677992105484, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.9314, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04758757435558493, | |
| "grad_norm": 0.018069472163915634, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9314, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05023132848645076, | |
| "grad_norm": 0.019313743337988853, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.9329, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05287508261731659, | |
| "grad_norm": 0.020844999700784683, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9299, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05551883674818242, | |
| "grad_norm": 0.030532022938132286, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.9313, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.05816259087904825, | |
| "grad_norm": 0.035114455968141556, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.9302, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06080634500991408, | |
| "grad_norm": 0.028270551934838295, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.9305, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06345009914077991, | |
| "grad_norm": 0.039881546050310135, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.9293, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06609385327164574, | |
| "grad_norm": 0.06690806150436401, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.928, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06609385327164574, | |
| "eval_loss": 11.930581092834473, | |
| "eval_runtime": 4.9921, | |
| "eval_samples_per_second": 510.605, | |
| "eval_steps_per_second": 63.901, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06873760740251157, | |
| "grad_norm": 0.021680066362023354, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9315, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0713813615333774, | |
| "grad_norm": 0.02636795863509178, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.9309, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07402511566424323, | |
| "grad_norm": 0.0213739275932312, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.9309, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07666886979510905, | |
| "grad_norm": 0.021914826706051826, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.9306, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07931262392597488, | |
| "grad_norm": 0.027240164577960968, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.931, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08195637805684071, | |
| "grad_norm": 0.03166433423757553, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.9315, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08460013218770654, | |
| "grad_norm": 0.028662104159593582, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9306, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08724388631857237, | |
| "grad_norm": 0.041819583624601364, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.9296, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0898876404494382, | |
| "grad_norm": 0.041154589504003525, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.9297, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09253139458030403, | |
| "grad_norm": 0.04414677992463112, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.9263, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09517514871116986, | |
| "grad_norm": 0.0581209696829319, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.9303, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09781890284203569, | |
| "grad_norm": 0.07070259004831314, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.9298, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10046265697290152, | |
| "grad_norm": 0.024558354169130325, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9311, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10310641110376735, | |
| "grad_norm": 0.025274544954299927, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.931, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10575016523463318, | |
| "grad_norm": 0.021741095930337906, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.931, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10839391936549901, | |
| "grad_norm": 0.02574080228805542, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.9312, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11103767349636484, | |
| "grad_norm": 0.026061194017529488, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.9307, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11368142762723067, | |
| "grad_norm": 0.029341937974095345, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.9309, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.1163251817580965, | |
| "grad_norm": 0.03373423218727112, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.9294, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.11896893588896233, | |
| "grad_norm": 0.03698370233178139, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.9316, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12161269001982816, | |
| "grad_norm": 0.034930210560560226, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.9299, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.12425644415069398, | |
| "grad_norm": 0.04290364682674408, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.928, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12690019828155982, | |
| "grad_norm": 0.05488286167383194, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.9269, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.12954395241242564, | |
| "grad_norm": 0.047314275056123734, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.9263, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13218770654329148, | |
| "grad_norm": 0.054101306945085526, | |
| "learning_rate": 0.0, | |
| "loss": 11.9266, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13218770654329148, | |
| "eval_loss": 11.930010795593262, | |
| "eval_runtime": 5.0142, | |
| "eval_samples_per_second": 508.355, | |
| "eval_steps_per_second": 63.619, | |
| "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 | |
| } | |