| { | |
| "best_metric": 0.01752311922609806, | |
| "best_model_checkpoint": "C:/Users/rajlq7/Desktop/NER_model/my_combined_ner_model\\checkpoint-40000", | |
| "epoch": 2.927400468384075, | |
| "eval_steps": 4000, | |
| "global_step": 40000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.036592505854800936, | |
| "grad_norm": 2.485658645629883, | |
| "learning_rate": 1.9756049960967995e-05, | |
| "loss": 0.207, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07318501170960187, | |
| "grad_norm": 1.7012395858764648, | |
| "learning_rate": 1.951209992193599e-05, | |
| "loss": 0.109, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.10977751756440281, | |
| "grad_norm": 13.03831958770752, | |
| "learning_rate": 1.9268149882903983e-05, | |
| "loss": 0.1058, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.14637002341920374, | |
| "grad_norm": 1.5959351062774658, | |
| "learning_rate": 1.9024199843871977e-05, | |
| "loss": 0.0948, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.1829625292740047, | |
| "grad_norm": 2.3129115104675293, | |
| "learning_rate": 1.878024980483997e-05, | |
| "loss": 0.0911, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.21955503512880561, | |
| "grad_norm": 1.924460530281067, | |
| "learning_rate": 1.8536299765807964e-05, | |
| "loss": 0.0843, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.25614754098360654, | |
| "grad_norm": 0.8139033913612366, | |
| "learning_rate": 1.8292349726775958e-05, | |
| "loss": 0.0863, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.2927400468384075, | |
| "grad_norm": 1.4802559614181519, | |
| "learning_rate": 1.804839968774395e-05, | |
| "loss": 0.0808, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.2927400468384075, | |
| "eval_accuracy": 0.9727209828272099, | |
| "eval_f1": 0.7573410160066887, | |
| "eval_loss": 0.06899960339069366, | |
| "eval_precision": 0.7385410322403191, | |
| "eval_recall": 0.7771231290829406, | |
| "eval_runtime": 325.6276, | |
| "eval_samples_per_second": 145.648, | |
| "eval_steps_per_second": 9.105, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.32933255269320844, | |
| "grad_norm": 1.8496237993240356, | |
| "learning_rate": 1.7804449648711945e-05, | |
| "loss": 0.0779, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.3659250585480094, | |
| "grad_norm": 1.2550444602966309, | |
| "learning_rate": 1.756049960967994e-05, | |
| "loss": 0.076, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.4025175644028103, | |
| "grad_norm": 1.4540296792984009, | |
| "learning_rate": 1.7316549570647933e-05, | |
| "loss": 0.0764, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.43911007025761123, | |
| "grad_norm": 2.8307697772979736, | |
| "learning_rate": 1.7072599531615927e-05, | |
| "loss": 0.0721, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.4757025761124122, | |
| "grad_norm": 0.6466274261474609, | |
| "learning_rate": 1.682864949258392e-05, | |
| "loss": 0.071, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.5122950819672131, | |
| "grad_norm": 1.7545057535171509, | |
| "learning_rate": 1.6584699453551914e-05, | |
| "loss": 0.072, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.5488875878220141, | |
| "grad_norm": 2.4494643211364746, | |
| "learning_rate": 1.6340749414519908e-05, | |
| "loss": 0.0683, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.585480093676815, | |
| "grad_norm": 1.7280840873718262, | |
| "learning_rate": 1.6096799375487902e-05, | |
| "loss": 0.0689, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.585480093676815, | |
| "eval_accuracy": 0.9829471473258827, | |
| "eval_f1": 0.8463664158043275, | |
| "eval_loss": 0.04604918137192726, | |
| "eval_precision": 0.8045495193382517, | |
| "eval_recall": 0.8927685437856612, | |
| "eval_runtime": 324.6599, | |
| "eval_samples_per_second": 146.082, | |
| "eval_steps_per_second": 9.133, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.622072599531616, | |
| "grad_norm": 1.3416178226470947, | |
| "learning_rate": 1.5852849336455895e-05, | |
| "loss": 0.0672, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.6586651053864169, | |
| "grad_norm": 2.533535957336426, | |
| "learning_rate": 1.560889929742389e-05, | |
| "loss": 0.0639, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.6952576112412178, | |
| "grad_norm": 1.449155569076538, | |
| "learning_rate": 1.5364949258391883e-05, | |
| "loss": 0.0624, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.7318501170960188, | |
| "grad_norm": 1.132238507270813, | |
| "learning_rate": 1.5120999219359875e-05, | |
| "loss": 0.0674, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.7684426229508197, | |
| "grad_norm": 0.9931765198707581, | |
| "learning_rate": 1.4877049180327869e-05, | |
| "loss": 0.0609, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.8050351288056206, | |
| "grad_norm": 1.1966588497161865, | |
| "learning_rate": 1.4633099141295863e-05, | |
| "loss": 0.0613, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.8416276346604216, | |
| "grad_norm": 1.7174360752105713, | |
| "learning_rate": 1.4389149102263858e-05, | |
| "loss": 0.065, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.8782201405152225, | |
| "grad_norm": 1.3579859733581543, | |
| "learning_rate": 1.4145199063231852e-05, | |
| "loss": 0.0623, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.8782201405152225, | |
| "eval_accuracy": 0.9869972841669858, | |
| "eval_f1": 0.8741255251838767, | |
| "eval_loss": 0.03630911931395531, | |
| "eval_precision": 0.8449576508267254, | |
| "eval_recall": 0.9053791449598941, | |
| "eval_runtime": 326.0426, | |
| "eval_samples_per_second": 145.463, | |
| "eval_steps_per_second": 9.094, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.9148126463700235, | |
| "grad_norm": 0.6756965517997742, | |
| "learning_rate": 1.3901249024199846e-05, | |
| "loss": 0.0578, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.9514051522248244, | |
| "grad_norm": 1.5516036748886108, | |
| "learning_rate": 1.365729898516784e-05, | |
| "loss": 0.0566, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.9879976580796253, | |
| "grad_norm": 3.253239393234253, | |
| "learning_rate": 1.3413348946135833e-05, | |
| "loss": 0.0589, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.0245901639344261, | |
| "grad_norm": 0.3872215449810028, | |
| "learning_rate": 1.3169398907103825e-05, | |
| "loss": 0.0479, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.0611826697892273, | |
| "grad_norm": 4.215191841125488, | |
| "learning_rate": 1.2925448868071819e-05, | |
| "loss": 0.0462, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.0977751756440282, | |
| "grad_norm": 1.3691105842590332, | |
| "learning_rate": 1.2681498829039813e-05, | |
| "loss": 0.0449, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.134367681498829, | |
| "grad_norm": 1.2835749387741089, | |
| "learning_rate": 1.2437548790007808e-05, | |
| "loss": 0.0401, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.17096018735363, | |
| "grad_norm": 0.6553089022636414, | |
| "learning_rate": 1.2193598750975802e-05, | |
| "loss": 0.0457, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.17096018735363, | |
| "eval_accuracy": 0.9873510995638026, | |
| "eval_f1": 0.8786805445622923, | |
| "eval_loss": 0.0350942388176918, | |
| "eval_precision": 0.8425996204933587, | |
| "eval_recall": 0.9179897461341272, | |
| "eval_runtime": 319.3009, | |
| "eval_samples_per_second": 148.534, | |
| "eval_steps_per_second": 9.286, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.2075526932084308, | |
| "grad_norm": 0.7736335396766663, | |
| "learning_rate": 1.1949648711943796e-05, | |
| "loss": 0.0421, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.2441451990632317, | |
| "grad_norm": 4.953197479248047, | |
| "learning_rate": 1.170569867291179e-05, | |
| "loss": 0.0401, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.2807377049180328, | |
| "grad_norm": 2.2808141708374023, | |
| "learning_rate": 1.1461748633879783e-05, | |
| "loss": 0.0393, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.3173302107728337, | |
| "grad_norm": 1.0953513383865356, | |
| "learning_rate": 1.1217798594847775e-05, | |
| "loss": 0.0391, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.3539227166276346, | |
| "grad_norm": 0.8463391065597534, | |
| "learning_rate": 1.0973848555815769e-05, | |
| "loss": 0.0401, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.3905152224824355, | |
| "grad_norm": 1.9214259386062622, | |
| "learning_rate": 1.0729898516783763e-05, | |
| "loss": 0.0401, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.4271077283372366, | |
| "grad_norm": 1.556010127067566, | |
| "learning_rate": 1.0485948477751758e-05, | |
| "loss": 0.0398, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.4637002341920375, | |
| "grad_norm": 1.6337586641311646, | |
| "learning_rate": 1.0241998438719752e-05, | |
| "loss": 0.0392, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.4637002341920375, | |
| "eval_accuracy": 0.9903870155746239, | |
| "eval_f1": 0.9021800909386164, | |
| "eval_loss": 0.028108540922403336, | |
| "eval_precision": 0.8861352579950554, | |
| "eval_recall": 0.91881667080129, | |
| "eval_runtime": 324.5009, | |
| "eval_samples_per_second": 146.154, | |
| "eval_steps_per_second": 9.137, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.5002927400468384, | |
| "grad_norm": 0.4936879873275757, | |
| "learning_rate": 9.998048399687746e-06, | |
| "loss": 0.0355, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.5368852459016393, | |
| "grad_norm": 0.44287028908729553, | |
| "learning_rate": 9.754098360655738e-06, | |
| "loss": 0.038, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.5734777517564402, | |
| "grad_norm": 2.042206048965454, | |
| "learning_rate": 9.510148321623731e-06, | |
| "loss": 0.0364, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.6100702576112411, | |
| "grad_norm": 0.20257487893104553, | |
| "learning_rate": 9.266198282591727e-06, | |
| "loss": 0.0364, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.646662763466042, | |
| "grad_norm": 1.1672091484069824, | |
| "learning_rate": 9.022248243559719e-06, | |
| "loss": 0.039, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.6832552693208431, | |
| "grad_norm": 1.7546871900558472, | |
| "learning_rate": 8.778298204527713e-06, | |
| "loss": 0.0369, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.719847775175644, | |
| "grad_norm": 0.5296183228492737, | |
| "learning_rate": 8.534348165495706e-06, | |
| "loss": 0.0362, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.756440281030445, | |
| "grad_norm": 0.9226844310760498, | |
| "learning_rate": 8.290398126463702e-06, | |
| "loss": 0.0353, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.756440281030445, | |
| "eval_accuracy": 0.9916860877836988, | |
| "eval_f1": 0.9128583245677638, | |
| "eval_loss": 0.024503452703356743, | |
| "eval_precision": 0.9020161859976993, | |
| "eval_recall": 0.9239642768543785, | |
| "eval_runtime": 323.4112, | |
| "eval_samples_per_second": 146.646, | |
| "eval_steps_per_second": 9.168, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.793032786885246, | |
| "grad_norm": 0.8019408583641052, | |
| "learning_rate": 8.046448087431694e-06, | |
| "loss": 0.0333, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.829625292740047, | |
| "grad_norm": 0.33608609437942505, | |
| "learning_rate": 7.802498048399688e-06, | |
| "loss": 0.0378, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.8662177985948478, | |
| "grad_norm": 1.2636245489120483, | |
| "learning_rate": 7.558548009367682e-06, | |
| "loss": 0.0318, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.9028103044496487, | |
| "grad_norm": 2.5859830379486084, | |
| "learning_rate": 7.314597970335676e-06, | |
| "loss": 0.0334, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.9394028103044496, | |
| "grad_norm": 1.2064955234527588, | |
| "learning_rate": 7.070647931303669e-06, | |
| "loss": 0.033, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.9759953161592505, | |
| "grad_norm": 3.731419086456299, | |
| "learning_rate": 6.826697892271663e-06, | |
| "loss": 0.0327, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.0125878220140514, | |
| "grad_norm": 0.4465324282646179, | |
| "learning_rate": 6.582747853239657e-06, | |
| "loss": 0.0302, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 2.0491803278688523, | |
| "grad_norm": 0.5257351994514465, | |
| "learning_rate": 6.338797814207651e-06, | |
| "loss": 0.0245, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 2.0491803278688523, | |
| "eval_accuracy": 0.9928802147479553, | |
| "eval_f1": 0.9221538555729024, | |
| "eval_loss": 0.021617736667394638, | |
| "eval_precision": 0.9104757299159766, | |
| "eval_recall": 0.9341354502604813, | |
| "eval_runtime": 323.2092, | |
| "eval_samples_per_second": 146.738, | |
| "eval_steps_per_second": 9.174, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 2.085772833723653, | |
| "grad_norm": 1.0085893869400024, | |
| "learning_rate": 6.094847775175644e-06, | |
| "loss": 0.0248, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 2.1223653395784545, | |
| "grad_norm": 1.1426091194152832, | |
| "learning_rate": 5.850897736143638e-06, | |
| "loss": 0.0261, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 2.1589578454332554, | |
| "grad_norm": 2.455578088760376, | |
| "learning_rate": 5.606947697111632e-06, | |
| "loss": 0.0258, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 2.1955503512880563, | |
| "grad_norm": 0.8838162422180176, | |
| "learning_rate": 5.362997658079626e-06, | |
| "loss": 0.0253, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 2.232142857142857, | |
| "grad_norm": 1.7397871017456055, | |
| "learning_rate": 5.119047619047619e-06, | |
| "loss": 0.0251, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 2.268735362997658, | |
| "grad_norm": 1.5480948686599731, | |
| "learning_rate": 4.875097580015613e-06, | |
| "loss": 0.024, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 2.305327868852459, | |
| "grad_norm": 1.4262340068817139, | |
| "learning_rate": 4.631147540983607e-06, | |
| "loss": 0.0237, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 2.34192037470726, | |
| "grad_norm": 1.02517569065094, | |
| "learning_rate": 4.3871975019516e-06, | |
| "loss": 0.0266, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 2.34192037470726, | |
| "eval_accuracy": 0.9937655028488885, | |
| "eval_f1": 0.9320011383964872, | |
| "eval_loss": 0.018857913091778755, | |
| "eval_precision": 0.9167199872030712, | |
| "eval_recall": 0.9478003803853469, | |
| "eval_runtime": 321.9655, | |
| "eval_samples_per_second": 147.305, | |
| "eval_steps_per_second": 9.209, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 2.378512880562061, | |
| "grad_norm": 5.398736953735352, | |
| "learning_rate": 4.143247462919595e-06, | |
| "loss": 0.0223, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 2.4151053864168617, | |
| "grad_norm": 4.433107852935791, | |
| "learning_rate": 3.899297423887588e-06, | |
| "loss": 0.0242, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 2.4516978922716626, | |
| "grad_norm": 7.640819549560547, | |
| "learning_rate": 3.655347384855582e-06, | |
| "loss": 0.0245, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 2.4882903981264635, | |
| "grad_norm": 0.7216879725456238, | |
| "learning_rate": 3.4113973458235757e-06, | |
| "loss": 0.0245, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 2.524882903981265, | |
| "grad_norm": 2.4471447467803955, | |
| "learning_rate": 3.1674473067915695e-06, | |
| "loss": 0.0274, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 2.5614754098360657, | |
| "grad_norm": 1.0936299562454224, | |
| "learning_rate": 2.923497267759563e-06, | |
| "loss": 0.0219, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 2.5980679156908666, | |
| "grad_norm": 1.52741277217865, | |
| "learning_rate": 2.679547228727557e-06, | |
| "loss": 0.0214, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 2.6346604215456675, | |
| "grad_norm": 1.9226934909820557, | |
| "learning_rate": 2.4355971896955503e-06, | |
| "loss": 0.0224, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 2.6346604215456675, | |
| "eval_accuracy": 0.9941957783526445, | |
| "eval_f1": 0.9347719770143049, | |
| "eval_loss": 0.01891487091779709, | |
| "eval_precision": 0.9215887174541948, | |
| "eval_recall": 0.9483378814190028, | |
| "eval_runtime": 321.3091, | |
| "eval_samples_per_second": 147.606, | |
| "eval_steps_per_second": 9.228, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 2.6712529274004684, | |
| "grad_norm": 9.9463529586792, | |
| "learning_rate": 2.191647150663544e-06, | |
| "loss": 0.0239, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 2.7078454332552693, | |
| "grad_norm": 10.356738090515137, | |
| "learning_rate": 1.947697111631538e-06, | |
| "loss": 0.025, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 2.74443793911007, | |
| "grad_norm": 1.4051014184951782, | |
| "learning_rate": 1.7037470725995318e-06, | |
| "loss": 0.0214, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 2.781030444964871, | |
| "grad_norm": 5.380222797393799, | |
| "learning_rate": 1.4597970335675255e-06, | |
| "loss": 0.0216, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 2.817622950819672, | |
| "grad_norm": 0.6108382940292358, | |
| "learning_rate": 1.215846994535519e-06, | |
| "loss": 0.024, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 2.8542154566744733, | |
| "grad_norm": 0.12093303352594376, | |
| "learning_rate": 9.718969555035128e-07, | |
| "loss": 0.0216, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 2.8908079625292737, | |
| "grad_norm": 2.0885472297668457, | |
| "learning_rate": 7.279469164715067e-07, | |
| "loss": 0.0215, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 2.927400468384075, | |
| "grad_norm": 1.3261560201644897, | |
| "learning_rate": 4.839968774395005e-07, | |
| "loss": 0.0217, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 2.927400468384075, | |
| "eval_accuracy": 0.9944656375536064, | |
| "eval_f1": 0.938253777786817, | |
| "eval_loss": 0.01752311922609806, | |
| "eval_precision": 0.9232878357282952, | |
| "eval_recall": 0.9537128917555611, | |
| "eval_runtime": 320.8148, | |
| "eval_samples_per_second": 147.833, | |
| "eval_steps_per_second": 9.242, | |
| "step": 40000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 40992, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 4000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.294273552996448e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |