Instructions to use genies-models/llama-13b-wrong_arc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use genies-models/llama-13b-wrong_arc with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("models/llama-13b") model = PeftModel.from_pretrained(base_model, "genies-models/llama-13b-wrong_arc") - Notebooks
- Google Colab
- Kaggle
Invalid JSON:Unexpected non-whitespace character after JSONat line 1595, column 2
| [ | |
| { | |
| "loss": 0.707, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.05, | |
| "step": 1 | |
| }, | |
| { | |
| "loss": 0.6703, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.11, | |
| "step": 2 | |
| }, | |
| { | |
| "loss": 0.6967, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.16, | |
| "step": 3 | |
| }, | |
| { | |
| "loss": 0.685, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.21, | |
| "step": 4 | |
| }, | |
| { | |
| "loss": 0.682, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.26, | |
| "step": 5 | |
| }, | |
| { | |
| "loss": 0.6038, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.32, | |
| "step": 6 | |
| }, | |
| { | |
| "loss": 0.6138, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.37, | |
| "step": 7 | |
| }, | |
| { | |
| "loss": 0.6577, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.42, | |
| "step": 8 | |
| }, | |
| { | |
| "loss": 0.5438, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.47, | |
| "step": 9 | |
| }, | |
| { | |
| "loss": 0.5512, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.53, | |
| "step": 10 | |
| }, | |
| { | |
| "loss": 0.479, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.58, | |
| "step": 11 | |
| }, | |
| { | |
| "loss": 0.4623, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.63, | |
| "step": 12 | |
| }, | |
| { | |
| "loss": 0.4422, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.68, | |
| "step": 13 | |
| }, | |
| { | |
| "loss": 0.5196, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.74, | |
| "step": 14 | |
| }, | |
| { | |
| "loss": 0.3411, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.79, | |
| "step": 15 | |
| }, | |
| { | |
| "loss": 0.4444, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.84, | |
| "step": 16 | |
| }, | |
| { | |
| "loss": 0.1711, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.89, | |
| "step": 17 | |
| }, | |
| { | |
| "loss": 0.4954, | |
| "learning_rate": 0.0002, | |
| "epoch": 0.95, | |
| "step": 18 | |
| }, | |
| { | |
| "loss": 0.3889, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.0, | |
| "step": 19 | |
| }, | |
| { | |
| "loss": 0.2282, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.05, | |
| "step": 20 | |
| }, | |
| { | |
| "loss": 0.1157, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.11, | |
| "step": 21 | |
| }, | |
| { | |
| "loss": 0.2022, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.16, | |
| "step": 22 | |
| }, | |
| { | |
| "loss": 0.1762, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.21, | |
| "step": 23 | |
| }, | |
| { | |
| "loss": 0.0903, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.26, | |
| "step": 24 | |
| }, | |
| { | |
| "loss": 0.2237, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.32, | |
| "step": 25 | |
| }, | |
| { | |
| "eval_wrong_arc_loss": 0.31779786944389343, | |
| "eval_wrong_arc_score": -0.09653245657682419, | |
| "eval_wrong_arc_brier_score": 0.09653245657682419, | |
| "eval_wrong_arc_average_probability": 0.850647509098053, | |
| "eval_wrong_arc_accuracy": 0.87, | |
| "eval_wrong_arc_probabilities": [ | |
| 0.9949164390563965, | |
| 0.9353755712509155, | |
| 0.7644833922386169, | |
| 0.9593828916549683, | |
| 0.697745680809021, | |
| 0.9824218153953552, | |
| 0.9620522856712341, | |
| 0.9999982118606567, | |
| 0.9999933242797852, | |
| 0.9914826154708862, | |
| 0.9999730587005615, | |
| 0.0027928014751523733, | |
| 0.999648928642273, | |
| 0.9999988079071045, | |
| 0.2169899195432663, | |
| 0.14227867126464844, | |
| 0.9830546975135803, | |
| 0.08066574484109879, | |
| 0.9953468441963196, | |
| 0.999848484992981, | |
| 0.3419247269630432, | |
| 0.9998832941055298, | |
| 0.9928345680236816, | |
| 0.9999328851699829, | |
| 0.7026811838150024, | |
| 0.9999877214431763, | |
| 0.9439877867698669, | |
| 0.9234603047370911, | |
| 0.993335485458374, | |
| 0.9999537467956543, | |
| 0.999914288520813, | |
| 0.978789210319519, | |
| 0.9999513626098633, | |
| 0.8677543997764587, | |
| 0.9819746613502502, | |
| 0.994938850402832, | |
| 0.9999839067459106, | |
| 0.7330987453460693, | |
| 0.9999618530273438, | |
| 0.9975399971008301, | |
| 0.8879246711730957, | |
| 0.9973451495170593, | |
| 0.9998656511306763, | |
| 0.9988055229187012, | |
| 0.9999786615371704, | |
| 0.8484535813331604, | |
| 0.9999874830245972, | |
| 0.09196758270263672, | |
| 0.8213191628456116, | |
| 0.7427552938461304, | |
| 0.22687996923923492, | |
| 0.9859835505485535, | |
| 0.9945969581604004, | |
| 0.9998565912246704, | |
| 0.9992465972900391, | |
| 0.9995290040969849, | |
| 0.9784048199653625, | |
| 0.9979854822158813, | |
| 0.9431190490722656, | |
| 0.9343425631523132, | |
| 0.9915185570716858, | |
| 0.2861595153808594, | |
| 0.9942342638969421, | |
| 0.9299052357673645, | |
| 0.9991299510002136, | |
| 0.9999862909317017, | |
| 0.9772287607192993, | |
| 0.9494120478630066, | |
| 0.9998931884765625, | |
| 0.8808120489120483, | |
| 0.9999508857727051, | |
| 0.7354373931884766, | |
| 0.9986085295677185, | |
| 0.571506917476654, | |
| 0.9952765703201294, | |
| 0.9269403219223022, | |
| 0.9688220620155334, | |
| 0.9999642372131348, | |
| 0.9966638684272766, | |
| 0.5050497651100159, | |
| 0.73870849609375, | |
| 0.9932193160057068, | |
| 0.997025191783905, | |
| 0.9769225120544434, | |
| 0.08747178316116333, | |
| 0.9999977350234985, | |
| 0.9761525392532349, | |
| 0.3850123882293701, | |
| 0.36245715618133545, | |
| 0.9998225569725037, | |
| 0.9943840503692627, | |
| 0.32138052582740784, | |
| 0.9995785355567932, | |
| 0.9999967813491821, | |
| 0.9982578158378601, | |
| 0.9642506837844849, | |
| 0.9215475916862488, | |
| 0.03343123942613602, | |
| 0.9999994039535522, | |
| 0.9999529123306274 | |
| ], | |
| "eval_wrong_arc_runtime": 27.1292, | |
| "eval_wrong_arc_samples_per_second": 3.686, | |
| "eval_wrong_arc_steps_per_second": 0.147, | |
| "epoch": 1.32, | |
| "step": 25 | |
| }, | |
| { | |
| "loss": 0.2647, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.37, | |
| "step": 26 | |
| }, | |
| { | |
| "loss": 0.115, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.42, | |
| "step": 27 | |
| }, | |
| { | |
| "loss": 0.1356, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.47, | |
| "step": 28 | |
| }, | |
| { | |
| "loss": 0.1851, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.53, | |
| "step": 29 | |
| }, | |
| { | |
| "loss": 0.1795, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.58, | |
| "step": 30 | |
| }, | |
| { | |
| "loss": 0.1912, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.63, | |
| "step": 31 | |
| }, | |
| { | |
| "loss": 0.2682, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.68, | |
| "step": 32 | |
| }, | |
| { | |
| "loss": 0.1157, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.74, | |
| "step": 33 | |
| }, | |
| { | |
| "loss": 0.0837, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.79, | |
| "step": 34 | |
| }, | |
| { | |
| "loss": 0.165, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.84, | |
| "step": 35 | |
| }, | |
| { | |
| "loss": 0.2499, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.89, | |
| "step": 36 | |
| }, | |
| { | |
| "loss": 0.2334, | |
| "learning_rate": 0.0002, | |
| "epoch": 1.95, | |
| "step": 37 | |
| }, | |
| { | |
| "loss": 0.1283, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.0, | |
| "step": 38 | |
| }, | |
| { | |
| "loss": 0.0602, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.05, | |
| "step": 39 | |
| }, | |
| { | |
| "loss": 0.0408, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.11, | |
| "step": 40 | |
| }, | |
| { | |
| "loss": 0.0633, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.16, | |
| "step": 41 | |
| }, | |
| { | |
| "loss": 0.0492, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.21, | |
| "step": 42 | |
| }, | |
| { | |
| "loss": 0.0132, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.26, | |
| "step": 43 | |
| }, | |
| { | |
| "loss": 0.0197, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.32, | |
| "step": 44 | |
| }, | |
| { | |
| "loss": 0.0572, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.37, | |
| "step": 45 | |
| }, | |
| { | |
| "loss": 0.0029, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.42, | |
| "step": 46 | |
| }, | |
| { | |
| "loss": 0.0137, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.47, | |
| "step": 47 | |
| }, | |
| { | |
| "loss": 0.01, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.53, | |
| "step": 48 | |
| }, | |
| { | |
| "loss": 0.0089, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.58, | |
| "step": 49 | |
| }, | |
| { | |
| "loss": 0.0205, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.63, | |
| "step": 50 | |
| }, | |
| { | |
| "eval_wrong_arc_loss": 0.4763663113117218, | |
| "eval_wrong_arc_score": -0.09404512494802475, | |
| "eval_wrong_arc_brier_score": 0.09404512494802475, | |
| "eval_wrong_arc_average_probability": 0.8855934143066406, | |
| "eval_wrong_arc_accuracy": 0.88, | |
| "eval_wrong_arc_probabilities": [ | |
| 1.0, | |
| 0.99899822473526, | |
| 0.9932013154029846, | |
| 0.998995840549469, | |
| 1.0, | |
| 0.9999959468841553, | |
| 0.9999867677688599, | |
| 1.0, | |
| 1.0, | |
| 0.9998041987419128, | |
| 1.0, | |
| 1.4548309081874322e-06, | |
| 0.9999998807907104, | |
| 1.0, | |
| 0.9960408210754395, | |
| 0.0234504546970129, | |
| 0.9998432397842407, | |
| 0.005773774813860655, | |
| 1.0, | |
| 0.9999970197677612, | |
| 0.3375290632247925, | |
| 1.0, | |
| 0.9999998807907104, | |
| 1.0, | |
| 0.9240821599960327, | |
| 1.0, | |
| 0.3293816149234772, | |
| 0.9999961853027344, | |
| 0.9999998807907104, | |
| 0.9999995231628418, | |
| 1.0, | |
| 0.999996542930603, | |
| 1.0, | |
| 0.9996373653411865, | |
| 0.9441826939582825, | |
| 0.9999996423721313, | |
| 1.0, | |
| 0.989042341709137, | |
| 0.9999955892562866, | |
| 0.9999998807907104, | |
| 1.0, | |
| 0.9999998807907104, | |
| 0.9999997615814209, | |
| 1.0, | |
| 1.0, | |
| 0.4591082036495209, | |
| 1.0, | |
| 0.08987987041473389, | |
| 0.9349956512451172, | |
| 0.7867553234100342, | |
| 0.7942191958427429, | |
| 0.9996621608734131, | |
| 0.9999998807907104, | |
| 0.9999998807907104, | |
| 0.9999914169311523, | |
| 0.9967323541641235, | |
| 0.9999876022338867, | |
| 1.0, | |
| 0.9900093078613281, | |
| 0.9892578721046448, | |
| 0.9999821186065674, | |
| 0.04106198996305466, | |
| 0.9999974966049194, | |
| 0.9999639987945557, | |
| 1.0, | |
| 1.0, | |
| 0.9986782670021057, | |
| 0.9997395873069763, | |
| 1.0, | |
| 0.9481080770492554, | |
| 0.999998927116394, | |
| 0.9999971389770508, | |
| 0.9992423057556152, | |
| 0.8539270758628845, | |
| 0.9998891353607178, | |
| 0.9936362504959106, | |
| 0.9999405145645142, | |
| 0.9999992847442627, | |
| 0.9999995231628418, | |
| 0.9999629259109497, | |
| 0.9887006878852844, | |
| 0.9999761581420898, | |
| 0.999996542930603, | |
| 0.9935442209243774, | |
| 0.008169939741492271, | |
| 1.0, | |
| 0.9999994039535522, | |
| 0.8693860769271851, | |
| 0.259015291929245, | |
| 0.9999996423721313, | |
| 0.9999901056289673, | |
| 0.07492787390947342, | |
| 0.9999983310699463, | |
| 1.0, | |
| 0.9999576807022095, | |
| 0.9535649418830872, | |
| 0.9974631071090698, | |
| 1.7836279084804119e-06, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_wrong_arc_runtime": 27.1222, | |
| "eval_wrong_arc_samples_per_second": 3.687, | |
| "eval_wrong_arc_steps_per_second": 0.147, | |
| "epoch": 2.63, | |
| "step": 50 | |
| }, | |
| { | |
| "loss": 0.0104, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.68, | |
| "step": 51 | |
| }, | |
| { | |
| "loss": 0.0094, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.74, | |
| "step": 52 | |
| }, | |
| { | |
| "loss": 0.0256, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.79, | |
| "step": 53 | |
| }, | |
| { | |
| "loss": 0.0183, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.84, | |
| "step": 54 | |
| }, | |
| { | |
| "loss": 0.0059, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.89, | |
| "step": 55 | |
| }, | |
| { | |
| "loss": 0.0012, | |
| "learning_rate": 0.0002, | |
| "epoch": 2.95, | |
| "step": 56 | |
| }, | |
| { | |
| "loss": 0.0016, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.0, | |
| "step": 57 | |
| }, | |
| { | |
| "loss": 0.0001, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.05, | |
| "step": 58 | |
| }, | |
| { | |
| "loss": 0.0004, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.11, | |
| "step": 59 | |
| }, | |
| { | |
| "loss": 0.0001, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.16, | |
| "step": 60 | |
| }, | |
| { | |
| "loss": 0.001, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.21, | |
| "step": 61 | |
| }, | |
| { | |
| "loss": 0.0001, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.26, | |
| "step": 62 | |
| }, | |
| { | |
| "loss": 0.0001, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.32, | |
| "step": 63 | |
| }, | |
| { | |
| "loss": 0.0006, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.37, | |
| "step": 64 | |
| }, | |
| { | |
| "loss": 0.0011, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.42, | |
| "step": 65 | |
| }, | |
| { | |
| "loss": 0.0025, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.47, | |
| "step": 66 | |
| }, | |
| { | |
| "loss": 0.0001, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.53, | |
| "step": 67 | |
| }, | |
| { | |
| "loss": 0.0001, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.58, | |
| "step": 68 | |
| }, | |
| { | |
| "loss": 0.0007, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.63, | |
| "step": 69 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.68, | |
| "step": 70 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.74, | |
| "step": 71 | |
| }, | |
| { | |
| "loss": 0.0005, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.79, | |
| "step": 72 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.84, | |
| "step": 73 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.89, | |
| "step": 74 | |
| }, | |
| { | |
| "loss": 0.0013, | |
| "learning_rate": 0.0002, | |
| "epoch": 3.95, | |
| "step": 75 | |
| }, | |
| { | |
| "eval_wrong_arc_loss": 0.5926003456115723, | |
| "eval_wrong_arc_score": -0.07276186347007751, | |
| "eval_wrong_arc_brier_score": 0.07276186347007751, | |
| "eval_wrong_arc_average_probability": 0.9136401414871216, | |
| "eval_wrong_arc_accuracy": 0.92, | |
| "eval_wrong_arc_probabilities": [ | |
| 1.0, | |
| 0.9999997615814209, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999967813491821, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 9.088809633794881e-07, | |
| 1.0, | |
| 1.0, | |
| 0.9973475933074951, | |
| 0.029377752915024757, | |
| 1.0, | |
| 9.702794123711556e-10, | |
| 1.0, | |
| 1.0, | |
| 0.7551511526107788, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.999847412109375, | |
| 1.0, | |
| 0.8491736054420471, | |
| 0.9995237588882446, | |
| 1.0, | |
| 1.0, | |
| 0.9999997615814209, | |
| 1.0, | |
| 1.0, | |
| 0.9999996423721313, | |
| 0.9994509816169739, | |
| 1.0, | |
| 1.0, | |
| 0.9935528039932251, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999997615814209, | |
| 1.0, | |
| 0.10383431613445282, | |
| 0.802496612071991, | |
| 0.9888101816177368, | |
| 0.7771538496017456, | |
| 0.9999984502792358, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999998807907104, | |
| 0.9999727010726929, | |
| 1.0, | |
| 0.9999934434890747, | |
| 0.9999992847442627, | |
| 1.0, | |
| 0.23791329562664032, | |
| 0.9999997615814209, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999957084655762, | |
| 0.9999734163284302, | |
| 1.0, | |
| 0.869653582572937, | |
| 1.0, | |
| 0.9999969005584717, | |
| 0.9999442100524902, | |
| 0.8350331783294678, | |
| 1.0, | |
| 0.999065101146698, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999904632568359, | |
| 0.9983235001564026, | |
| 1.0, | |
| 0.9986498951911926, | |
| 0.9999990463256836, | |
| 0.9886378645896912, | |
| 1.0, | |
| 1.0, | |
| 0.999653697013855, | |
| 0.00734851835295558, | |
| 1.0, | |
| 1.0, | |
| 0.13457897305488586, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9995729327201843, | |
| 1.0, | |
| 1.7961000742250377e-10, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_wrong_arc_runtime": 27.1293, | |
| "eval_wrong_arc_samples_per_second": 3.686, | |
| "eval_wrong_arc_steps_per_second": 0.147, | |
| "epoch": 3.95, | |
| "step": 75 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.0, | |
| "step": 76 | |
| }, | |
| { | |
| "loss": 0.0001, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.05, | |
| "step": 77 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.11, | |
| "step": 78 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.16, | |
| "step": 79 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.21, | |
| "step": 80 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.26, | |
| "step": 81 | |
| }, | |
| { | |
| "loss": 0.0001, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.32, | |
| "step": 82 | |
| }, | |
| { | |
| "loss": 0.0005, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.37, | |
| "step": 83 | |
| }, | |
| { | |
| "loss": 0.0001, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.42, | |
| "step": 84 | |
| }, | |
| { | |
| "loss": 0.0004, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.47, | |
| "step": 85 | |
| }, | |
| { | |
| "loss": 0.0001, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.53, | |
| "step": 86 | |
| }, | |
| { | |
| "loss": 0.0003, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.58, | |
| "step": 87 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.63, | |
| "step": 88 | |
| }, | |
| { | |
| "loss": 0.0001, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.68, | |
| "step": 89 | |
| }, | |
| { | |
| "loss": 0.0001, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.74, | |
| "step": 90 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.79, | |
| "step": 91 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.84, | |
| "step": 92 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.89, | |
| "step": 93 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 4.95, | |
| "step": 94 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.0, | |
| "step": 95 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.05, | |
| "step": 96 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.11, | |
| "step": 97 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.16, | |
| "step": 98 | |
| }, | |
| { | |
| "loss": 0.0001, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.21, | |
| "step": 99 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.26, | |
| "step": 100 | |
| }, | |
| { | |
| "eval_wrong_arc_loss": 0.5509288311004639, | |
| "eval_wrong_arc_score": -0.07344645261764526, | |
| "eval_wrong_arc_brier_score": 0.07344645261764526, | |
| "eval_wrong_arc_average_probability": 0.9117353558540344, | |
| "eval_wrong_arc_accuracy": 0.92, | |
| "eval_wrong_arc_probabilities": [ | |
| 1.0, | |
| 0.9999996423721313, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999953508377075, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.6129989717228455e-06, | |
| 1.0, | |
| 1.0, | |
| 0.9919439554214478, | |
| 0.018666794523596764, | |
| 1.0, | |
| 1.2420014350311703e-08, | |
| 1.0, | |
| 0.9999996423721313, | |
| 0.8571034073829651, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9987161159515381, | |
| 1.0, | |
| 0.6483784914016724, | |
| 0.9997910857200623, | |
| 1.0, | |
| 1.0, | |
| 0.9999966621398926, | |
| 1.0, | |
| 1.0, | |
| 0.9999996423721313, | |
| 0.9997026324272156, | |
| 1.0, | |
| 1.0, | |
| 0.9978145360946655, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999991655349731, | |
| 1.0, | |
| 0.1459464579820633, | |
| 0.6189136505126953, | |
| 0.9851900935173035, | |
| 0.7363576292991638, | |
| 0.9999982118606567, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999840259552002, | |
| 1.0, | |
| 0.9999675750732422, | |
| 0.9999966621398926, | |
| 1.0, | |
| 0.20978191494941711, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999326467514038, | |
| 0.9999445676803589, | |
| 1.0, | |
| 0.8867464661598206, | |
| 1.0, | |
| 0.9999626874923706, | |
| 0.9998075366020203, | |
| 0.9183639287948608, | |
| 1.0, | |
| 0.9977478384971619, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999990463256836, | |
| 0.9991897940635681, | |
| 1.0, | |
| 0.9972585439682007, | |
| 0.9999983310699463, | |
| 0.976452648639679, | |
| 1.0, | |
| 1.0, | |
| 0.9989743232727051, | |
| 0.013659379445016384, | |
| 1.0, | |
| 1.0, | |
| 0.17794698476791382, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9993108510971069, | |
| 1.0, | |
| 2.26134377889764e-09, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_wrong_arc_runtime": 27.1216, | |
| "eval_wrong_arc_samples_per_second": 3.687, | |
| "eval_wrong_arc_steps_per_second": 0.147, | |
| "epoch": 5.26, | |
| "step": 100 | |
| }, | |
| { | |
| "loss": 0.0001, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.32, | |
| "step": 101 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.37, | |
| "step": 102 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.42, | |
| "step": 103 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.47, | |
| "step": 104 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.53, | |
| "step": 105 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.58, | |
| "step": 106 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.63, | |
| "step": 107 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.68, | |
| "step": 108 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.74, | |
| "step": 109 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.79, | |
| "step": 110 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.84, | |
| "step": 111 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.89, | |
| "step": 112 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 5.95, | |
| "step": 113 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.0, | |
| "step": 114 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.05, | |
| "step": 115 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.11, | |
| "step": 116 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.16, | |
| "step": 117 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.21, | |
| "step": 118 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.26, | |
| "step": 119 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.32, | |
| "step": 120 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.37, | |
| "step": 121 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.42, | |
| "step": 122 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.47, | |
| "step": 123 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.53, | |
| "step": 124 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.58, | |
| "step": 125 | |
| }, | |
| { | |
| "eval_wrong_arc_loss": 0.5689963698387146, | |
| "eval_wrong_arc_score": -0.0729750245809555, | |
| "eval_wrong_arc_brier_score": 0.0729750245809555, | |
| "eval_wrong_arc_average_probability": 0.91292405128479, | |
| "eval_wrong_arc_accuracy": 0.92, | |
| "eval_wrong_arc_probabilities": [ | |
| 1.0, | |
| 0.9999998807907104, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999984502792358, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 3.220020516891964e-07, | |
| 1.0, | |
| 1.0, | |
| 0.9938602447509766, | |
| 0.010313266888260841, | |
| 1.0, | |
| 2.105494800730412e-08, | |
| 1.0, | |
| 0.9999998807907104, | |
| 0.8445565700531006, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9979133009910583, | |
| 1.0, | |
| 0.6891838312149048, | |
| 0.9998979568481445, | |
| 1.0, | |
| 1.0, | |
| 0.9999984502792358, | |
| 1.0, | |
| 1.0, | |
| 0.9999992847442627, | |
| 0.9992020726203918, | |
| 1.0, | |
| 1.0, | |
| 0.9966176152229309, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999995231628418, | |
| 1.0, | |
| 0.14272429049015045, | |
| 0.6626131534576416, | |
| 0.9902004599571228, | |
| 0.7526479959487915, | |
| 0.9999991655349731, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999927282333374, | |
| 1.0, | |
| 0.9999755620956421, | |
| 0.9999974966049194, | |
| 1.0, | |
| 0.22156904637813568, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999606609344482, | |
| 0.9999654293060303, | |
| 1.0, | |
| 0.9209628105163574, | |
| 1.0, | |
| 0.9999822378158569, | |
| 0.9999001026153564, | |
| 0.926228404045105, | |
| 1.0, | |
| 0.9985692501068115, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999996423721313, | |
| 0.9996111989021301, | |
| 1.0, | |
| 0.9991627931594849, | |
| 0.9999974966049194, | |
| 0.9701893329620361, | |
| 1.0, | |
| 1.0, | |
| 0.9993740916252136, | |
| 0.01545325480401516, | |
| 1.0, | |
| 1.0, | |
| 0.16376018524169922, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9980265498161316, | |
| 1.0, | |
| 2.4979855961504427e-09, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_wrong_arc_runtime": 27.1003, | |
| "eval_wrong_arc_samples_per_second": 3.69, | |
| "eval_wrong_arc_steps_per_second": 0.148, | |
| "epoch": 6.58, | |
| "step": 125 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.63, | |
| "step": 126 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.68, | |
| "step": 127 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.74, | |
| "step": 128 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.79, | |
| "step": 129 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.84, | |
| "step": 130 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.89, | |
| "step": 131 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 6.95, | |
| "step": 132 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.0, | |
| "step": 133 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.05, | |
| "step": 134 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.11, | |
| "step": 135 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.16, | |
| "step": 136 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.21, | |
| "step": 137 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.26, | |
| "step": 138 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.32, | |
| "step": 139 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.37, | |
| "step": 140 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.42, | |
| "step": 141 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.47, | |
| "step": 142 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.53, | |
| "step": 143 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.58, | |
| "step": 144 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.63, | |
| "step": 145 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.68, | |
| "step": 146 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.74, | |
| "step": 147 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.79, | |
| "step": 148 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.84, | |
| "step": 149 | |
| }, | |
| { | |
| "loss": 0.0, | |
| "learning_rate": 0.0002, | |
| "epoch": 7.89, | |
| "step": 150 | |
| }, | |
| { | |
| "eval_wrong_arc_loss": 0.5786136984825134, | |
| "eval_wrong_arc_score": -0.0726059228181839, | |
| "eval_wrong_arc_brier_score": 0.0726059228181839, | |
| "eval_wrong_arc_average_probability": 0.9138116240501404, | |
| "eval_wrong_arc_accuracy": 0.92, | |
| "eval_wrong_arc_probabilities": [ | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999992847442627, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0384997040091548e-07, | |
| 1.0, | |
| 1.0, | |
| 0.9941185712814331, | |
| 0.00717101339250803, | |
| 1.0, | |
| 3.6523953639289175e-08, | |
| 1.0, | |
| 0.9999998807907104, | |
| 0.8171164393424988, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.997463583946228, | |
| 1.0, | |
| 0.7272890210151672, | |
| 0.9999433755874634, | |
| 1.0, | |
| 1.0, | |
| 0.9999991655349731, | |
| 1.0, | |
| 1.0, | |
| 0.9999983310699463, | |
| 0.9981958270072937, | |
| 1.0, | |
| 1.0, | |
| 0.9946656227111816, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999996423721313, | |
| 1.0, | |
| 0.1446363925933838, | |
| 0.7109227776527405, | |
| 0.9918368458747864, | |
| 0.7632880806922913, | |
| 0.9999995231628418, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999998807907104, | |
| 0.999996542930603, | |
| 1.0, | |
| 0.9999793767929077, | |
| 0.9999978542327881, | |
| 1.0, | |
| 0.22515763342380524, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999756813049316, | |
| 0.9999755620956421, | |
| 1.0, | |
| 0.9459772109985352, | |
| 1.0, | |
| 0.9999910593032837, | |
| 0.9999386072158813, | |
| 0.9337203502655029, | |
| 1.0, | |
| 0.9990092515945435, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.9999997615814209, | |
| 0.999772846698761, | |
| 1.0, | |
| 0.9996604919433594, | |
| 0.999996542930603, | |
| 0.9684516191482544, | |
| 1.0, | |
| 1.0, | |
| 0.9995811581611633, | |
| 0.01707574352622032, | |
| 1.0, | |
| 1.0, | |
| 0.1509828120470047, | |
| 1.0, | |
| 1.0, | |
| 1.0, | |
| 0.995280921459198, | |
| 0.9999998807907104, | |
| 3.5318605817735715e-09, | |
| 1.0, | |
| 1.0 | |
| ], | |
| "eval_wrong_arc_runtime": 27.097, | |
| "eval_wrong_arc_samples_per_second": 3.69, | |
| "eval_wrong_arc_steps_per_second": 0.148, | |
| "epoch": 7.89, | |
| "step": 150 | |
| }, | |
| { | |
| "train_runtime": 3186.2345, | |
| "train_samples_per_second": 1.506, | |
| "train_steps_per_second": 0.047, | |
| "total_flos": 0.0, | |
| "train_loss": 0.09300446018680494, | |
| "epoch": 7.89, | |
| "step": 150 | |
| } | |
| ]] |