Upload folder using huggingface_hub

README.md

@@ -0,0 +1,108 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
+model-index:
+- name: pos_final_mono_nl
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# pos_final_mono_nl
+
+This model is a fine-tuned version of [pdelobelle/robbert-v2-dutch-base](https://huggingface.co/pdelobelle/robbert-v2-dutch-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1115
+- Precision: 0.9783
+- Recall: 0.9784
+- F1: 0.9783
+- Accuracy: 0.9791
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 256
+- eval_batch_size: 256
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 1024
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 40.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| No log        | 1.0   | 69   | 3.7703          | 0.2597    | 0.1252 | 0.1689 | 0.2575   |
+| No log        | 2.0   | 138  | 1.0148          | 0.8058    | 0.8008 | 0.8033 | 0.8066   |
+| No log        | 3.0   | 207  | 0.3402          | 0.9302    | 0.9278 | 0.9290 | 0.9299   |
+| No log        | 4.0   | 276  | 0.2016          | 0.9559    | 0.9551 | 0.9555 | 0.9561   |
+| No log        | 5.0   | 345  | 0.1486          | 0.9643    | 0.9638 | 0.9641 | 0.9648   |
+| No log        | 6.0   | 414  | 0.1206          | 0.9697    | 0.9696 | 0.9697 | 0.9702   |
+| No log        | 7.0   | 483  | 0.1063          | 0.9720    | 0.9719 | 0.9720 | 0.9727   |
+| 1.2192        | 8.0   | 552  | 0.0983          | 0.9734    | 0.9735 | 0.9735 | 0.9742   |
+| 1.2192        | 9.0   | 621  | 0.0947          | 0.9746    | 0.9747 | 0.9746 | 0.9754   |
+| 1.2192        | 10.0  | 690  | 0.0913          | 0.9753    | 0.9755 | 0.9754 | 0.9761   |
+| 1.2192        | 11.0  | 759  | 0.0885          | 0.9761    | 0.9763 | 0.9762 | 0.9770   |
+| 1.2192        | 12.0  | 828  | 0.0877          | 0.9764    | 0.9765 | 0.9764 | 0.9772   |
+| 1.2192        | 13.0  | 897  | 0.0878          | 0.9767    | 0.9769 | 0.9768 | 0.9775   |
+| 1.2192        | 14.0  | 966  | 0.0873          | 0.9767    | 0.9769 | 0.9768 | 0.9776   |
+| 0.0688        | 15.0  | 1035 | 0.0877          | 0.9771    | 0.9773 | 0.9772 | 0.9779   |
+| 0.0688        | 16.0  | 1104 | 0.0878          | 0.9773    | 0.9774 | 0.9773 | 0.9781   |
+| 0.0688        | 17.0  | 1173 | 0.0897          | 0.9772    | 0.9773 | 0.9773 | 0.9781   |
+| 0.0688        | 18.0  | 1242 | 0.0909          | 0.9775    | 0.9776 | 0.9776 | 0.9783   |
+| 0.0688        | 19.0  | 1311 | 0.0917          | 0.9776    | 0.9778 | 0.9777 | 0.9785   |
+| 0.0688        | 20.0  | 1380 | 0.0924          | 0.9778    | 0.9780 | 0.9779 | 0.9787   |
+| 0.0688        | 21.0  | 1449 | 0.0949          | 0.9777    | 0.9779 | 0.9778 | 0.9785   |
+| 0.0366        | 22.0  | 1518 | 0.0956          | 0.9776    | 0.9777 | 0.9777 | 0.9784   |
+| 0.0366        | 23.0  | 1587 | 0.0962          | 0.9778    | 0.9780 | 0.9779 | 0.9786   |
+| 0.0366        | 24.0  | 1656 | 0.0992          | 0.9777    | 0.9780 | 0.9779 | 0.9786   |
+| 0.0366        | 25.0  | 1725 | 0.0999          | 0.9779    | 0.9781 | 0.9780 | 0.9787   |
+| 0.0366        | 26.0  | 1794 | 0.1007          | 0.9780    | 0.9782 | 0.9781 | 0.9789   |
+| 0.0366        | 27.0  | 1863 | 0.1022          | 0.9781    | 0.9782 | 0.9782 | 0.9789   |
+| 0.0366        | 28.0  | 1932 | 0.1030          | 0.9781    | 0.9783 | 0.9782 | 0.9790   |
+| 0.0226        | 29.0  | 2001 | 0.1055          | 0.9781    | 0.9782 | 0.9781 | 0.9789   |
+| 0.0226        | 30.0  | 2070 | 0.1057          | 0.9780    | 0.9782 | 0.9781 | 0.9789   |
+| 0.0226        | 31.0  | 2139 | 0.1067          | 0.9780    | 0.9781 | 0.9780 | 0.9788   |
+| 0.0226        | 32.0  | 2208 | 0.1077          | 0.9780    | 0.9782 | 0.9781 | 0.9789   |
+| 0.0226        | 33.0  | 2277 | 0.1085          | 0.9780    | 0.9781 | 0.9781 | 0.9789   |
+| 0.0226        | 34.0  | 2346 | 0.1094          | 0.9781    | 0.9782 | 0.9781 | 0.9789   |
+| 0.0226        | 35.0  | 2415 | 0.1095          | 0.9783    | 0.9784 | 0.9783 | 0.9791   |
+| 0.0226        | 36.0  | 2484 | 0.1101          | 0.9780    | 0.9782 | 0.9781 | 0.9789   |
+| 0.0159        | 37.0  | 2553 | 0.1114          | 0.9782    | 0.9784 | 0.9783 | 0.9791   |
+| 0.0159        | 38.0  | 2622 | 0.1111          | 0.9782    | 0.9784 | 0.9783 | 0.9791   |
+| 0.0159        | 39.0  | 2691 | 0.1114          | 0.9782    | 0.9784 | 0.9783 | 0.9791   |
+| 0.0159        | 40.0  | 2760 | 0.1115          | 0.9783    | 0.9784 | 0.9783 | 0.9791   |
+
+
+### Framework versions
+
+- Transformers 4.25.1
+- Pytorch 1.12.0
+- Datasets 2.18.0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 40.0,
+    "eval_accuracy": 0.9791272496102441,
+    "eval_f1": 0.9783398772157638,
+    "eval_loss": 0.1115424633026123,
+    "eval_precision": 0.9782571951013384,
+    "eval_recall": 0.978422573307924,
+    "eval_runtime": 10.375,
+    "eval_samples": 2619,
+    "eval_samples_per_second": 758.46,
+    "eval_steps_per_second": 2.988,
+    "train_loss": 0.24823836001796998,
+    "train_runtime": 2048.5615,
+    "train_samples": 70812,
+    "train_samples_per_second": 1382.668,
+    "train_steps_per_second": 1.347
+}

config.json

@@ -0,0 +1,360 @@
+{
+  "_name_or_path": "pdelobelle/robbert-v2-dutch-base",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "finetuning_task": "pos",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "",
+    "1": "ADJ(postnom,basis,met-s)",
+    "2": "VNW(onbep,grad,basis)",
+    "3": "VNW(pers,pron,3m,ev)",
+    "4": "BW()",
+    "5": "ADJ(nom,sup,met-e,mv-n)",
+    "6": "VNW(pers,pron,3,mv)",
+    "7": "VNW(vb,pron,3v,ev)",
+    "8": "VG(onder)",
+    "9": "N(soort,ev,basis,onz,stan)",
+    "10": "VNW(pers,pron,1,mv)",
+    "11": "VNW(pers,pron,3,ev,masc)",
+    "12": "TW(rang,nom,zonder-n)",
+    "13": "TSW()",
+    "14": "#not\t#",
+    "15": "WW(vd,nom,met-e,mv-n)",
+    "16": "ADJ(postnom,comp,zonder)",
+    "17": "TW(hoofd,nom,mv-n,basis)",
+    "18": "LID(bep)",
+    "19": "VNW(aanw,pron,3o,ev)",
+    "20": "N(eigen,mv,dim)",
+    "21": "SPEC(deeleigen)",
+    "22": "VNW(excl,pron,3,getal)",
+    "23": "WW(vd,prenom,met-e)",
+    "24": "VNW(refl,pron,3,getal)",
+    "25": "VNW(pers,pron,3,ev,onz)",
+    "26": "WW(inf,vrij,zonder)",
+    "27": "VNW(pers,pron,1,ev)",
+    "28": "ADJ(vrij,dim,zonder)",
+    "29": "TW(rang,nom,mv-n)",
+    "30": "VNW(vb,det)",
+    "31": "TW(hoofd,prenom,stan)",
+    "32": "SPEC(symb)",
+    "33": "VNW(betr,pron,3,ev)",
+    "34": "U",
+    "35": "WW(pv,conj,ev)",
+    "36": "N(soort,ev,dim,onz,stan)",
+    "37": "N(soort,ev,basis,zijd,stan)",
+    "38": "ADJ(prenom,comp,met-e,stan)",
+    "39": "zonder-n)",
+    "40": "ADJ(vrij,verder,zonder)",
+    "41": "N(eigen,ev,basis,onz,stan)",
+    "42": "N(eigen,ev,basis,gen)",
+    "43": "VNW(pr,pron,2,getal)",
+    "44": "@",
+    "45": "VNW(vb,pron,3m,ev)",
+    "46": "VNW(pers,pron,2,getal)",
+    "47": "VNW(bez,det,1,mv)",
+    "48": "N(soort,mv,dim)",
+    "49": "VZ(fin)",
+    "50": "WW(pv,tgw,mv)",
+    "51": "ADJ(nom,basis,zonder,zonder-n)",
+    "52": "VNW(aanw,adv-pron,3,getal)",
+    "53": "VNW(bez,det,3v,ev)",
+    "54": "TW(rang,prenom,stan)",
+    "55": "WW(inf,prenom,met-e)",
+    "56": "ADJ(nom,basis,met-e,zonder-n,bijz)",
+    "57": "Boulevard\tN(eigen,ev,basis,genus,stan)",
+    "58": "WW(od,nom,met-e,zonder-n)",
+    "59": "ADJ(nom,sup,met-e,zonder-n,stan)",
+    "60": "VNW(pers,pron,3,getal,fem)",
+    "61": "VNW(bez,det,3,mv)",
+    "62": "VNW(pers,pron,3m,ev,masc)",
+    "63": "VG(neven)",
+    "64": "VNW(recip,pron,persoon,mv)",
+    "65": "ADJ(nom,basis,zonder,mv-n)",
+    "66": "VNW(bez,det,3,ev)",
+    "67": "WW(od,nom,met-e,mv-n)",
+    "68": "VNW(vb,pron,3p,mv)",
+    "69": "VNW(onbep,adv-pron,3o,getal)",
+    "70": "ADJ(nom,comp,met-e,zonder-n,stan)",
+    "71": "ADJ(nom,basis,met-e,mv-n)",
+    "72": "N(eigen,ev,basis,zijd,stan)",
+    "73": "#",
+    "74": "VNW(aanw,adv-pron,3o,getal)",
+    "75": "VNW(bez,det,3p,mv)",
+    "76": "FW",
+    "77": "ADJ(nom,sup,zonder,zonder-n)",
+    "78": "VNW(bez,det,1,ev)",
+    "79": "VNW(pers,pron,3,ev,fem)",
+    "80": "WW(inf,prenom,zonder)",
+    "81": "WW(pv,tgw,met-t)",
+    "82": "VNW(pers,pron,2v,ev)",
+    "83": "VNW(pers,pron,3v,ev,fem)",
+    "84": "ADJ(nom,comp,met-e,mv-n)",
+    "85": "VNW(bez,det,2,getal)",
+    "86": "WW(pv,tegw,ev)",
+    "87": "VNW(pers,pron,3p,ev,masc)",
+    "88": "VNW(pr,pron,1,ev)",
+    "89": "VNW(onbep,det)",
+    "90": "N(eigen,mv,basis)",
+    "91": "VNW(aanw,det)",
+    "92": "VNW(bez,det,3m,ev)",
+    "93": "VZ(versm)",
+    "94": "N(soort,ev,basis,genus,stan)",
+    "95": "VNW(betr,det)",
+    "96": "TW(rang,prenom,bijz)",
+    "97": "TW(hoofd,nom,zonder-n,dim)",
+    "98": "VNW(pr,pron,1,mv)",
+    "99": "SPEC(afgebr)",
+    "100": "VNW(bez,det,2,mv)",
+    "101": "VNW(pers,pron,2v,mv)",
+    "102": "VNW(onbep,adv-pron,3,getal)",
+    "103": "TW(hoofd,nom,zonder,zonder-n)",
+    "104": "ADJ(postnom,basis,zonder)",
+    "105": "WW(pv,verl,mv)",
+    "106": "VNW(vb,pron,3p,getal)",
+    "107": "LET()",
+    "108": "ADJ(prenom,basis,zonder)",
+    "109": "ADJ(vrij,basis,zonder)",
+    "110": "ADJ(prenom,sup,zonder)",
+    "111": "N(soort,mv,basis)",
+    "112": "VNW(onbep,grad,sup)",
+    "113": "#NS\t#",
+    "114": "VNW(aanw,pron,3,getal)",
+    "115": "WW(vd,nom,met-e,zonder-n)",
+    "116": "~",
+    "117": "TW(hoofd,prenom,bijz)",
+    "118": "SPEC(vreemd)",
+    "119": "ADJ(vrij,sup,zonder)",
+    "120": "WW(od,prenom,met-e)",
+    "121": "ADJ(postnom,comp,met-s)",
+    "122": "TW(hoofd,vrij)",
+    "123": "VNW(bez,det,2v,ev)",
+    "124": "ADJ(prenom,basis,met-e,bijz)",
+    "125": "N(eigen,ev,basis,genus,stan)",
+    "126": "ADJ(vrij,comp,zonder)",
+    "127": "N(eigen,ev,dim,onz,stan)",
+    "128": "WW(inf,nom,zonder,zonder-n)",
+    "129": "WW(od,prenom,zonder)",
+    "130": "ADJ(prenom,sup,met-e,stan)",
+    "131": "SPEC(meta)",
+    "132": "VNW(pers,pron,3v,getal,fem)",
+    "133": "SPEC(enof)",
+    "134": "WW(vd,prenom,zonder)",
+    "135": "Jan",
+    "136": "WW(vd,vrij,zonder)",
+    "137": "VNW(aanw,pron,3m,ev)",
+    "138": "TW(hoofd,nom,zonder-n,basis)",
+    "139": "ADJ(prenom,basis,met-e,stan)",
+    "140": "ADJ(nom,basis,met-e,zonder-n,stan)",
+    "141": "SPEC(afk)",
+    "142": "N(soort,mv,basis,zijd,stan)",
+    "143": "VNW(vb,pron,3o,ev)",
+    "144": "LID(onbep)",
+    "145": "ADJ(prenom,comp,zonder)",
+    "146": "VNW(onbep,pron,3p,ev)",
+    "147": "VNW(onbep,pron,3o,ev)",
+    "148": "VGW()",
+    "149": "N(soort,ev,basis,dat)",
+    "150": "WW(pv,tgw,ev)",
+    "151": "VNW(pr,pron,2v,getal)",
+    "152": "WW(pv,verl,ev)",
+    "153": "VNW(vb,adv-pron,3o,getal)",
+    "154": "VNW(pers,pron,3p,mv)",
+    "155": "WW(od,vrij,zonder)",
+    "156": "VNW(pers,pron,2b,getal)",
+    "157": "VZ(init)",
+    "158": "VNW(bez,det,2v,mv)",
+    "159": "ADJ(prenom,basis,zonder,stan)",
+    "160": "VNW(onbep,grad,comp)",
+    "161": "N(soort,ev,basis,gen)",
+    "162": "VNW(betr,pron,persoon,getal)"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "": 0,
+    "#": 73,
+    "#NS\t#": 113,
+    "#not\t#": 14,
+    "@": 44,
+    "ADJ(nom,basis,met-e,mv-n)": 71,
+    "ADJ(nom,basis,met-e,zonder-n,bijz)": 56,
+    "ADJ(nom,basis,met-e,zonder-n,stan)": 140,
+    "ADJ(nom,basis,zonder,mv-n)": 65,
+    "ADJ(nom,basis,zonder,zonder-n)": 51,
+    "ADJ(nom,comp,met-e,mv-n)": 84,
+    "ADJ(nom,comp,met-e,zonder-n,stan)": 70,
+    "ADJ(nom,sup,met-e,mv-n)": 5,
+    "ADJ(nom,sup,met-e,zonder-n,stan)": 59,
+    "ADJ(nom,sup,zonder,zonder-n)": 77,
+    "ADJ(postnom,basis,met-s)": 1,
+    "ADJ(postnom,basis,zonder)": 104,
+    "ADJ(postnom,comp,met-s)": 121,
+    "ADJ(postnom,comp,zonder)": 16,
+    "ADJ(prenom,basis,met-e,bijz)": 124,
+    "ADJ(prenom,basis,met-e,stan)": 139,
+    "ADJ(prenom,basis,zonder)": 108,
+    "ADJ(prenom,basis,zonder,stan)": 159,
+    "ADJ(prenom,comp,met-e,stan)": 38,
+    "ADJ(prenom,comp,zonder)": 145,
+    "ADJ(prenom,sup,met-e,stan)": 130,
+    "ADJ(prenom,sup,zonder)": 110,
+    "ADJ(vrij,basis,zonder)": 109,
+    "ADJ(vrij,comp,zonder)": 126,
+    "ADJ(vrij,dim,zonder)": 28,
+    "ADJ(vrij,sup,zonder)": 119,
+    "ADJ(vrij,verder,zonder)": 40,
+    "BW()": 4,
+    "Boulevard\tN(eigen,ev,basis,genus,stan)": 57,
+    "FW": 76,
+    "Jan": 135,
+    "LET()": 107,
+    "LID(bep)": 18,
+    "LID(onbep)": 144,
+    "N(eigen,ev,basis,gen)": 42,
+    "N(eigen,ev,basis,genus,stan)": 125,
+    "N(eigen,ev,basis,onz,stan)": 41,
+    "N(eigen,ev,basis,zijd,stan)": 72,
+    "N(eigen,ev,dim,onz,stan)": 127,
+    "N(eigen,mv,basis)": 90,
+    "N(eigen,mv,dim)": 20,
+    "N(soort,ev,basis,dat)": 149,
+    "N(soort,ev,basis,gen)": 161,
+    "N(soort,ev,basis,genus,stan)": 94,
+    "N(soort,ev,basis,onz,stan)": 9,
+    "N(soort,ev,basis,zijd,stan)": 37,
+    "N(soort,ev,dim,onz,stan)": 36,
+    "N(soort,mv,basis)": 111,
+    "N(soort,mv,basis,zijd,stan)": 142,
+    "N(soort,mv,dim)": 48,
+    "SPEC(afgebr)": 99,
+    "SPEC(afk)": 141,
+    "SPEC(deeleigen)": 21,
+    "SPEC(enof)": 133,
+    "SPEC(meta)": 131,
+    "SPEC(symb)": 32,
+    "SPEC(vreemd)": 118,
+    "TSW()": 13,
+    "TW(hoofd,nom,mv-n,basis)": 17,
+    "TW(hoofd,nom,zonder,zonder-n)": 103,
+    "TW(hoofd,nom,zonder-n,basis)": 138,
+    "TW(hoofd,nom,zonder-n,dim)": 97,
+    "TW(hoofd,prenom,bijz)": 117,
+    "TW(hoofd,prenom,stan)": 31,
+    "TW(hoofd,vrij)": 122,
+    "TW(rang,nom,mv-n)": 29,
+    "TW(rang,nom,zonder-n)": 12,
+    "TW(rang,prenom,bijz)": 96,
+    "TW(rang,prenom,stan)": 54,
+    "U": 34,
+    "VG(neven)": 63,
+    "VG(onder)": 8,
+    "VGW()": 148,
+    "VNW(aanw,adv-pron,3,getal)": 52,
+    "VNW(aanw,adv-pron,3o,getal)": 74,
+    "VNW(aanw,det)": 91,
+    "VNW(aanw,pron,3,getal)": 114,
+    "VNW(aanw,pron,3m,ev)": 137,
+    "VNW(aanw,pron,3o,ev)": 19,
+    "VNW(betr,det)": 95,
+    "VNW(betr,pron,3,ev)": 33,
+    "VNW(betr,pron,persoon,getal)": 162,
+    "VNW(bez,det,1,ev)": 78,
+    "VNW(bez,det,1,mv)": 47,
+    "VNW(bez,det,2,getal)": 85,
+    "VNW(bez,det,2,mv)": 100,
+    "VNW(bez,det,2v,ev)": 123,
+    "VNW(bez,det,2v,mv)": 158,
+    "VNW(bez,det,3,ev)": 66,
+    "VNW(bez,det,3,mv)": 61,
+    "VNW(bez,det,3m,ev)": 92,
+    "VNW(bez,det,3p,mv)": 75,
+    "VNW(bez,det,3v,ev)": 53,
+    "VNW(excl,pron,3,getal)": 22,
+    "VNW(onbep,adv-pron,3,getal)": 102,
+    "VNW(onbep,adv-pron,3o,getal)": 69,
+    "VNW(onbep,det)": 89,
+    "VNW(onbep,grad,basis)": 2,
+    "VNW(onbep,grad,comp)": 160,
+    "VNW(onbep,grad,sup)": 112,
+    "VNW(onbep,pron,3o,ev)": 147,
+    "VNW(onbep,pron,3p,ev)": 146,
+    "VNW(pers,pron,1,ev)": 27,
+    "VNW(pers,pron,1,mv)": 10,
+    "VNW(pers,pron,2,getal)": 46,
+    "VNW(pers,pron,2b,getal)": 156,
+    "VNW(pers,pron,2v,ev)": 82,
+    "VNW(pers,pron,2v,mv)": 101,
+    "VNW(pers,pron,3,ev,fem)": 79,
+    "VNW(pers,pron,3,ev,masc)": 11,
+    "VNW(pers,pron,3,ev,onz)": 25,
+    "VNW(pers,pron,3,getal,fem)": 60,
+    "VNW(pers,pron,3,mv)": 6,
+    "VNW(pers,pron,3m,ev)": 3,
+    "VNW(pers,pron,3m,ev,masc)": 62,
+    "VNW(pers,pron,3p,ev,masc)": 87,
+    "VNW(pers,pron,3p,mv)": 154,
+    "VNW(pers,pron,3v,ev,fem)": 83,
+    "VNW(pers,pron,3v,getal,fem)": 132,
+    "VNW(pr,pron,1,ev)": 88,
+    "VNW(pr,pron,1,mv)": 98,
+    "VNW(pr,pron,2,getal)": 43,
+    "VNW(pr,pron,2v,getal)": 151,
+    "VNW(recip,pron,persoon,mv)": 64,
+    "VNW(refl,pron,3,getal)": 24,
+    "VNW(vb,adv-pron,3o,getal)": 153,
+    "VNW(vb,det)": 30,
+    "VNW(vb,pron,3m,ev)": 45,
+    "VNW(vb,pron,3o,ev)": 143,
+    "VNW(vb,pron,3p,getal)": 106,
+    "VNW(vb,pron,3p,mv)": 68,
+    "VNW(vb,pron,3v,ev)": 7,
+    "VZ(fin)": 49,
+    "VZ(init)": 157,
+    "VZ(versm)": 93,
+    "WW(inf,nom,zonder,zonder-n)": 128,
+    "WW(inf,prenom,met-e)": 55,
+    "WW(inf,prenom,zonder)": 80,
+    "WW(inf,vrij,zonder)": 26,
+    "WW(od,nom,met-e,mv-n)": 67,
+    "WW(od,nom,met-e,zonder-n)": 58,
+    "WW(od,prenom,met-e)": 120,
+    "WW(od,prenom,zonder)": 129,
+    "WW(od,vrij,zonder)": 155,
+    "WW(pv,conj,ev)": 35,
+    "WW(pv,tegw,ev)": 86,
+    "WW(pv,tgw,ev)": 150,
+    "WW(pv,tgw,met-t)": 81,
+    "WW(pv,tgw,mv)": 50,
+    "WW(pv,verl,ev)": 152,
+    "WW(pv,verl,mv)": 105,
+    "WW(vd,nom,met-e,mv-n)": 15,
+    "WW(vd,nom,met-e,zonder-n)": 115,
+    "WW(vd,prenom,met-e)": 23,
+    "WW(vd,prenom,zonder)": 134,
+    "WW(vd,vrij,zonder)": 136,
+    "zonder-n)": 39,
+    "~": 116
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 40000
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 40.0,
+    "eval_accuracy": 0.9791272496102441,
+    "eval_f1": 0.9783398772157638,
+    "eval_loss": 0.1115424633026123,
+    "eval_precision": 0.9782571951013384,
+    "eval_recall": 0.978422573307924,
+    "eval_runtime": 10.375,
+    "eval_samples": 2619,
+    "eval_samples_per_second": 758.46,
+    "eval_steps_per_second": 2.988
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79795fe75400a2c8af49b37d5dc1a7b63e6c510916a1999033bee8928df0d779
+size 465258545

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,67 @@
+{
+  "add_prefix_space": true,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "max_length": 128,
+  "model_max_length": 512,
+  "name_or_path": "pdelobelle/robbert-v2-dutch-base",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": "./robbert-v2-dutch-base/special_tokens_map.json",
+  "token": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 40.0,
+    "train_loss": 0.24823836001796998,
+    "train_runtime": 2048.5615,
+    "train_samples": 70812,
+    "train_samples_per_second": 1382.668,
+    "train_steps_per_second": 1.347
+}

trainer_state.json

@@ -0,0 +1,535 @@
+{
+  "best_metric": 0.9783398772157638,
+  "best_model_checkpoint": "models/pos_final_mono_nl/checkpoint-2760",
+  "epoch": 39.99638989169675,
+  "global_step": 2760,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.2575113142718755,
+      "eval_f1": 0.16891972475874908,
+      "eval_loss": 3.770303726196289,
+      "eval_precision": 0.25972286447785947,
+      "eval_recall": 0.12516136964406466,
+      "eval_runtime": 10.2346,
+      "eval_samples_per_second": 768.865,
+      "eval_steps_per_second": 3.029,
+      "step": 69
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8066356880136831,
+      "eval_f1": 0.8033051608452517,
+      "eval_loss": 1.0147907733917236,
+      "eval_precision": 0.8057864338897609,
+      "eval_recall": 0.8008391221491363,
+      "eval_runtime": 10.7861,
+      "eval_samples_per_second": 729.548,
+      "eval_steps_per_second": 2.874,
+      "step": 138
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.929904490895606,
+      "eval_f1": 0.9289770104330163,
+      "eval_loss": 0.3402073085308075,
+      "eval_precision": 0.9301506840872673,
+      "eval_recall": 0.9278062949529723,
+      "eval_runtime": 10.421,
+      "eval_samples_per_second": 755.108,
+      "eval_steps_per_second": 2.975,
+      "step": 207
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9560597575188824,
+      "eval_f1": 0.9555069516784352,
+      "eval_loss": 0.20157238841056824,
+      "eval_precision": 0.9559442226785728,
+      "eval_recall": 0.9550700805311366,
+      "eval_runtime": 10.4533,
+      "eval_samples_per_second": 752.775,
+      "eval_steps_per_second": 2.966,
+      "step": 276
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.964831156250473,
+      "eval_f1": 0.964063779010111,
+      "eval_loss": 0.14858682453632355,
+      "eval_precision": 0.9642898327887757,
+      "eval_recall": 0.9638378311919837,
+      "eval_runtime": 11.0648,
+      "eval_samples_per_second": 711.175,
+      "eval_steps_per_second": 2.802,
+      "step": 345
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9701515128581591,
+      "eval_f1": 0.9696606418295832,
+      "eval_loss": 0.12055634707212448,
+      "eval_precision": 0.9697202582231786,
+      "eval_recall": 0.969601032765722,
+      "eval_runtime": 10.8285,
+      "eval_samples_per_second": 726.696,
+      "eval_steps_per_second": 2.863,
+      "step": 414
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.972701954076922,
+      "eval_f1": 0.9719634068091613,
+      "eval_loss": 0.10631231963634491,
+      "eval_precision": 0.9719820795967141,
+      "eval_recall": 0.9719447347390422,
+      "eval_runtime": 10.4365,
+      "eval_samples_per_second": 753.985,
+      "eval_steps_per_second": 2.97,
+      "step": 483
+    },
+    {
+      "epoch": 7.25,
+      "learning_rate": 5e-05,
+      "loss": 1.2192,
+      "step": 500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9742231371183798,
+      "eval_f1": 0.9734790710183069,
+      "eval_loss": 0.09831023961305618,
+      "eval_precision": 0.9734304527887268,
+      "eval_recall": 0.973527694104629,
+      "eval_runtime": 10.9399,
+      "eval_samples_per_second": 719.291,
+      "eval_steps_per_second": 2.834,
+      "step": 552
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.975388620642681,
+      "eval_f1": 0.9746202254443189,
+      "eval_loss": 0.09469176828861237,
+      "eval_precision": 0.974567806377257,
+      "eval_recall": 0.9746726501506117,
+      "eval_runtime": 10.9888,
+      "eval_samples_per_second": 716.095,
+      "eval_steps_per_second": 2.821,
+      "step": 621
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.9761454281259934,
+      "eval_f1": 0.9753816837883316,
+      "eval_loss": 0.09128155559301376,
+      "eval_precision": 0.9752992516787289,
+      "eval_recall": 0.975464129833405,
+      "eval_runtime": 10.3458,
+      "eval_samples_per_second": 760.6,
+      "eval_steps_per_second": 2.996,
+      "step": 690
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.9770081886569695,
+      "eval_f1": 0.9762231314470121,
+      "eval_loss": 0.08845613151788712,
+      "eval_precision": 0.9761368787406173,
+      "eval_recall": 0.9763093993975533,
+      "eval_runtime": 10.591,
+      "eval_samples_per_second": 742.993,
+      "eval_steps_per_second": 2.927,
+      "step": 759
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.9772200947522969,
+      "eval_f1": 0.9764375477837924,
+      "eval_loss": 0.08773986995220184,
+      "eval_precision": 0.9763812802053,
+      "eval_recall": 0.976493821847913,
+      "eval_runtime": 10.1848,
+      "eval_samples_per_second": 772.621,
+      "eval_steps_per_second": 3.044,
+      "step": 828
+    },
+    {
+      "epoch": 13.0,
+      "eval_accuracy": 0.977530385820455,
+      "eval_f1": 0.9767615183960107,
+      "eval_loss": 0.0878407210111618,
+      "eval_precision": 0.9766527100218952,
+      "eval_recall": 0.9768703510173972,
+      "eval_runtime": 10.414,
+      "eval_samples_per_second": 755.619,
+      "eval_steps_per_second": 2.977,
+      "step": 897
+    },
+    {
+      "epoch": 14.0,
+      "eval_accuracy": 0.9775909304191199,
+      "eval_f1": 0.9767761714683069,
+      "eval_loss": 0.08732089400291443,
+      "eval_precision": 0.9766973731723995,
+      "eval_recall": 0.9768549824798672,
+      "eval_runtime": 10.2517,
+      "eval_samples_per_second": 767.579,
+      "eval_steps_per_second": 3.024,
+      "step": 966
+    },
+    {
+      "epoch": 14.49,
+      "learning_rate": 3.893805309734514e-05,
+      "loss": 0.0688,
+      "step": 1000
+    },
+    {
+      "epoch": 15.0,
+      "eval_accuracy": 0.9779466299362768,
+      "eval_f1": 0.9771878601613523,
+      "eval_loss": 0.08772371709346771,
+      "eval_precision": 0.9770827571371501,
+      "eval_recall": 0.9772929857994713,
+      "eval_runtime": 10.4702,
+      "eval_samples_per_second": 751.563,
+      "eval_steps_per_second": 2.961,
+      "step": 1035
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.9781282637322718,
+      "eval_f1": 0.9773326264186318,
+      "eval_loss": 0.08782745897769928,
+      "eval_precision": 0.9772800614675374,
+      "eval_recall": 0.9773851970246511,
+      "eval_runtime": 10.0217,
+      "eval_samples_per_second": 785.196,
+      "eval_steps_per_second": 3.093,
+      "step": 1104
+    },
+    {
+      "epoch": 17.0,
+      "eval_accuracy": 0.9780601510587736,
+      "eval_f1": 0.9772529072559422,
+      "eval_loss": 0.08969255536794662,
+      "eval_precision": 0.9771590568603499,
+      "eval_recall": 0.9773467756808262,
+      "eval_runtime": 10.2237,
+      "eval_samples_per_second": 769.681,
+      "eval_steps_per_second": 3.032,
+      "step": 1173
+    },
+    {
+      "epoch": 18.0,
+      "eval_accuracy": 0.978325033677933,
+      "eval_f1": 0.9775826100987749,
+      "eval_loss": 0.09088694304227829,
+      "eval_precision": 0.9775187663749587,
+      "eval_recall": 0.9776464621626606,
+      "eval_runtime": 10.2448,
+      "eval_samples_per_second": 768.099,
+      "eval_steps_per_second": 3.026,
+      "step": 1242
+    },
+    {
+      "epoch": 19.0,
+      "eval_accuracy": 0.9784536909500962,
+      "eval_f1": 0.9776833564477773,
+      "eval_loss": 0.09170977026224136,
+      "eval_precision": 0.9775819549334296,
+      "eval_recall": 0.9777847790004304,
+      "eval_runtime": 10.5329,
+      "eval_samples_per_second": 747.089,
+      "eval_steps_per_second": 2.943,
+      "step": 1311
+    },
+    {
+      "epoch": 20.0,
+      "eval_accuracy": 0.978695869344756,
+      "eval_f1": 0.977932645393286,
+      "eval_loss": 0.09237655997276306,
+      "eval_precision": 0.977849997695109,
+      "eval_recall": 0.9780153070633798,
+      "eval_runtime": 10.1755,
+      "eval_samples_per_second": 773.331,
+      "eval_steps_per_second": 3.047,
+      "step": 1380
+    },
+    {
+      "epoch": 21.0,
+      "eval_accuracy": 0.9785369397732605,
+      "eval_f1": 0.9777796559381027,
+      "eval_loss": 0.09489051252603531,
+      "eval_precision": 0.9776669790882412,
+      "eval_recall": 0.9778923587631401,
+      "eval_runtime": 10.3245,
+      "eval_samples_per_second": 762.165,
+      "eval_steps_per_second": 3.003,
+      "step": 1449
+    },
+    {
+      "epoch": 21.74,
+      "learning_rate": 2.7876106194690264e-05,
+      "loss": 0.0366,
+      "step": 1500
+    },
+    {
+      "epoch": 22.0,
+      "eval_accuracy": 0.9783931463514312,
+      "eval_f1": 0.977655520039341,
+      "eval_loss": 0.09559858590364456,
+      "eval_precision": 0.9775954268854877,
+      "eval_recall": 0.9777156205815455,
+      "eval_runtime": 10.2656,
+      "eval_samples_per_second": 766.54,
+      "eval_steps_per_second": 3.02,
+      "step": 1518
+    },
+    {
+      "epoch": 23.0,
+      "eval_accuracy": 0.9785899162970924,
+      "eval_f1": 0.9778600762968741,
+      "eval_loss": 0.0962114930152893,
+      "eval_precision": 0.977758656453831,
+      "eval_recall": 0.977961517182025,
+      "eval_runtime": 10.2847,
+      "eval_samples_per_second": 765.116,
+      "eval_steps_per_second": 3.014,
+      "step": 1587
+    },
+    {
+      "epoch": 24.0,
+      "eval_accuracy": 0.978627756671258,
+      "eval_f1": 0.9778800497871751,
+      "eval_loss": 0.09919747710227966,
+      "eval_precision": 0.9777448299173401,
+      "eval_recall": 0.9780153070633798,
+      "eval_runtime": 10.2497,
+      "eval_samples_per_second": 767.73,
+      "eval_steps_per_second": 3.024,
+      "step": 1656
+    },
+    {
+      "epoch": 25.0,
+      "eval_accuracy": 0.9787488458685879,
+      "eval_f1": 0.9779865998709163,
+      "eval_loss": 0.09993624687194824,
+      "eval_precision": 0.9778964351567302,
+      "eval_recall": 0.9780767812134997,
+      "eval_runtime": 10.4654,
+      "eval_samples_per_second": 751.908,
+      "eval_steps_per_second": 2.962,
+      "step": 1725
+    },
+    {
+      "epoch": 26.0,
+      "eval_accuracy": 0.9788699350659179,
+      "eval_f1": 0.9781095368349878,
+      "eval_loss": 0.10065959393978119,
+      "eval_precision": 0.978019360786724,
+      "eval_recall": 0.9781997295137395,
+      "eval_runtime": 10.3069,
+      "eval_samples_per_second": 763.466,
+      "eval_steps_per_second": 3.008,
+      "step": 1794
+    },
+    {
+      "epoch": 27.0,
+      "eval_accuracy": 0.9789229115897498,
+      "eval_f1": 0.9781592282543133,
+      "eval_loss": 0.10217240452766418,
+      "eval_precision": 0.97808031838472,
+      "eval_recall": 0.9782381508575644,
+      "eval_runtime": 10.3246,
+      "eval_samples_per_second": 762.158,
+      "eval_steps_per_second": 3.003,
+      "step": 1863
+    },
+    {
+      "epoch": 28.0,
+      "eval_accuracy": 0.9790061604129142,
+      "eval_f1": 0.9782287156594198,
+      "eval_loss": 0.10301286727190018,
+      "eval_precision": 0.9781347715521547,
+      "eval_recall": 0.9783226778139792,
+      "eval_runtime": 10.6685,
+      "eval_samples_per_second": 737.591,
+      "eval_steps_per_second": 2.906,
+      "step": 1932
+    },
+    {
+      "epoch": 28.98,
+      "learning_rate": 1.6814159292035402e-05,
+      "loss": 0.0226,
+      "step": 2000
+    },
+    {
+      "epoch": 29.0,
+      "eval_accuracy": 0.9789456158142492,
+      "eval_f1": 0.9781276533619175,
+      "eval_loss": 0.10546565800905228,
+      "eval_precision": 0.9780863177791267,
+      "eval_recall": 0.9781689924386795,
+      "eval_runtime": 10.2106,
+      "eval_samples_per_second": 770.668,
+      "eval_steps_per_second": 3.036,
+      "step": 2001
+    },
+    {
+      "epoch": 30.0,
+      "eval_accuracy": 0.9788775031407511,
+      "eval_f1": 0.9781016850177108,
+      "eval_loss": 0.10569430887699127,
+      "eval_precision": 0.9780190230335438,
+      "eval_recall": 0.9781843609762095,
+      "eval_runtime": 10.1623,
+      "eval_samples_per_second": 774.335,
+      "eval_steps_per_second": 3.051,
+      "step": 2070
+    },
+    {
+      "epoch": 31.0,
+      "eval_accuracy": 0.9788169585420861,
+      "eval_f1": 0.9780400473314586,
+      "eval_loss": 0.10669872909784317,
+      "eval_precision": 0.9779649036540766,
+      "eval_recall": 0.9781152025573246,
+      "eval_runtime": 10.228,
+      "eval_samples_per_second": 769.357,
+      "eval_steps_per_second": 3.031,
+      "step": 2139
+    },
+    {
+      "epoch": 32.0,
+      "eval_accuracy": 0.9788850712155842,
+      "eval_f1": 0.9781134626983792,
+      "eval_loss": 0.10771454125642776,
+      "eval_precision": 0.9780195296594217,
+      "eval_recall": 0.9782074137825044,
+      "eval_runtime": 10.2465,
+      "eval_samples_per_second": 767.969,
+      "eval_steps_per_second": 3.025,
+      "step": 2208
+    },
+    {
+      "epoch": 33.0,
+      "eval_accuracy": 0.9788547989162517,
+      "eval_f1": 0.9780702765419577,
+      "eval_loss": 0.10846679657697678,
+      "eval_precision": 0.9780176719170188,
+      "eval_recall": 0.9781228868260896,
+      "eval_runtime": 10.262,
+      "eval_samples_per_second": 766.809,
+      "eval_steps_per_second": 3.021,
+      "step": 2277
+    },
+    {
+      "epoch": 34.0,
+      "eval_accuracy": 0.9789153435149167,
+      "eval_f1": 0.9781402710760058,
+      "eval_loss": 0.10942833125591278,
+      "eval_precision": 0.9780500921942225,
+      "eval_recall": 0.9782304665887994,
+      "eval_runtime": 10.2289,
+      "eval_samples_per_second": 769.29,
+      "eval_steps_per_second": 3.031,
+      "step": 2346
+    },
+    {
+      "epoch": 35.0,
+      "eval_accuracy": 0.9791272496102441,
+      "eval_f1": 0.9783318606170041,
+      "eval_loss": 0.10954407602548599,
+      "eval_precision": 0.9782642100895862,
+      "eval_recall": 0.978399520501629,
+      "eval_runtime": 10.2671,
+      "eval_samples_per_second": 766.432,
+      "eval_steps_per_second": 3.019,
+      "step": 2415
+    },
+    {
+      "epoch": 36.0,
+      "eval_accuracy": 0.9788775031407511,
+      "eval_f1": 0.9780747081173908,
+      "eval_loss": 0.11010610312223434,
+      "eval_precision": 0.9779958050661893,
+      "eval_recall": 0.9781536239011496,
+      "eval_runtime": 10.1692,
+      "eval_samples_per_second": 773.807,
+      "eval_steps_per_second": 3.048,
+      "step": 2484
+    },
+    {
+      "epoch": 36.23,
+      "learning_rate": 5.752212389380531e-06,
+      "loss": 0.0159,
+      "step": 2500
+    },
+    {
+      "epoch": 37.0,
+      "eval_accuracy": 0.9791045453857448,
+      "eval_f1": 0.9783088094048946,
+      "eval_loss": 0.11143232136964798,
+      "eval_precision": 0.9782411604714415,
+      "eval_recall": 0.9783764676953342,
+      "eval_runtime": 10.184,
+      "eval_samples_per_second": 772.684,
+      "eval_steps_per_second": 3.044,
+      "step": 2553
+    },
+    {
+      "epoch": 38.0,
+      "eval_accuracy": 0.9791272496102441,
+      "eval_f1": 0.9783286015589884,
+      "eval_loss": 0.11111290007829666,
+      "eval_precision": 0.9782346478591898,
+      "eval_recall": 0.978422573307924,
+      "eval_runtime": 10.011,
+      "eval_samples_per_second": 786.035,
+      "eval_steps_per_second": 3.097,
+      "step": 2622
+    },
+    {
+      "epoch": 39.0,
+      "eval_accuracy": 0.9790894092360786,
+      "eval_f1": 0.9782975339329141,
+      "eval_loss": 0.11137838661670685,
+      "eval_precision": 0.978218612905952,
+      "eval_recall": 0.9783764676953342,
+      "eval_runtime": 10.1814,
+      "eval_samples_per_second": 772.882,
+      "eval_steps_per_second": 3.045,
+      "step": 2691
+    },
+    {
+      "epoch": 40.0,
+      "eval_accuracy": 0.9791272496102441,
+      "eval_f1": 0.9783398772157638,
+      "eval_loss": 0.1115424633026123,
+      "eval_precision": 0.9782571951013384,
+      "eval_recall": 0.978422573307924,
+      "eval_runtime": 10.2449,
+      "eval_samples_per_second": 768.087,
+      "eval_steps_per_second": 3.026,
+      "step": 2760
+    },
+    {
+      "epoch": 40.0,
+      "step": 2760,
+      "total_flos": 1.3845487354146643e+17,
+      "train_loss": 0.24823836001796998,
+      "train_runtime": 2048.5615,
+      "train_samples_per_second": 1382.668,
+      "train_steps_per_second": 1.347
+    }
+  ],
+  "max_steps": 2760,
+  "num_train_epochs": 40,
+  "total_flos": 1.3845487354146643e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bf4de53a5ef20802f03f57efada97b2e49b1138c6761b6e66f5b4ae2aed8958
+size 3439