GPT2 fine tune on bodo pos data

all_results.json

@@ -0,0 +1 @@
+{"eval_precision": 0.22749664128974473, "eval_recall": 0.15587603559374041, "eval_f1": 0.18499635833940278, "eval_accuracy": 0.36907910555421974}

config.json

@@ -0,0 +1,115 @@
+{
+  "_name_or_path": "./bodo-gpt2-clm-setencepiece",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2ForTokenClassification"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "RD_UNK",
+    "1": "DM_DMD",
+    "2": "N_NNV",
+    "3": "QT_QTO",
+    "4": "N_NST",
+    "5": "PR_PRC",
+    "6": "CC_CCS",
+    "7": "RP_NEG",
+    "8": "QT_QTF",
+    "9": "N_NNP",
+    "10": "CC_CCD",
+    "11": "PR_PRQ",
+    "12": "DM_DMR",
+    "13": "QT_QTC",
+    "14": "DM_DMI",
+    "15": "PR_PRF",
+    "16": "RB",
+    "17": "PSP",
+    "18": "V_VAUX_VF",
+    "19": "PR_PRP",
+    "20": "RD_RDF",
+    "21": "RP_RPD",
+    "22": "JJ",
+    "23": "RP_INJ",
+    "24": "V_VM",
+    "25": "V_VM_VF",
+    "26": "PR_PRL",
+    "27": "RD_PUNC",
+    "28": "RP_INTF",
+    "29": "DM_DMQ",
+    "30": "RD_ECH",
+    "31": "RD_SYM",
+    "32": "N_NN",
+    "33": "PR_PRI",
+    "34": "V_VM_VNF",
+    "35": "V_VAUX"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "CC_CCD": 10,
+    "CC_CCS": 6,
+    "DM_DMD": 1,
+    "DM_DMI": 14,
+    "DM_DMQ": 29,
+    "DM_DMR": 12,
+    "JJ": 22,
+    "N_NN": 32,
+    "N_NNP": 9,
+    "N_NNV": 2,
+    "N_NST": 4,
+    "PR_PRC": 5,
+    "PR_PRF": 15,
+    "PR_PRI": 33,
+    "PR_PRL": 26,
+    "PR_PRP": 19,
+    "PR_PRQ": 11,
+    "PSP": 17,
+    "QT_QTC": 13,
+    "QT_QTF": 8,
+    "QT_QTO": 3,
+    "RB": 16,
+    "RD_ECH": 30,
+    "RD_PUNC": 27,
+    "RD_RDF": 20,
+    "RD_SYM": 31,
+    "RD_UNK": 0,
+    "RP_INJ": 23,
+    "RP_INTF": 28,
+    "RP_NEG": 7,
+    "RP_RPD": 21,
+    "V_VAUX": 35,
+    "V_VAUX_VF": 18,
+    "V_VM": 24,
+    "V_VM_VF": 25,
+    "V_VM_VNF": 34
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.0,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7218a73e13d4b9b1702742178bf21e983ae3999768997d1bf6587a6ba9f627e7
+size 497943013

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<cls>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": true,
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 512,
+  "special_tokens": [
+    "<s>",
+    "<pad>",
+    "</s>",
+    "<unk>",
+    "<cls>",
+    "<sep>",
+    "<mask>"
+  ],
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}