Training in progress, epoch 1

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -1,26 +1,51 @@
 {
-  "_name_or_path": "bert-base-cased",
+  "_name_or_path": "microsoft/biogpt",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu_new",
   "architectures": [
-    "BertModel"
+    "GPT2ForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-Disease",
+    "2": "I-Disease"
+  },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-Disease": 1,
+    "I-Disease": 2,
+    "O": 0
+  },
   "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "layer_norm_epsilon": 1e-05,
+  "layerdrop": 0.0,
+  "model_type": "gpt2",
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "pad_token_id": 1,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "scale_embedding": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
   "torch_dtype": "float32",
   "transformers_version": "4.28.1",
-  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 42384
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:294e00b06b15db21630b150a9bb862b0f457dcfe6451ef055d87983e7a1f4ce3
-size 433309485
+oid sha256:befd964491885b3b6d6274a370e7966849b50c2ab23155321928f3e6d42b9550
+size 1412334373

runs/Apr15_16-07-58_470c3636e847/1681574997.222783/events.out.tfevents.1681574997.470c3636e847.531.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42af8cfe31fcaf87a6139737910715e330bbce791c0a10e137433714e77f549c
+size 5852

runs/Apr15_16-07-58_470c3636e847/events.out.tfevents.1681574997.470c3636e847.531.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8248cfbb04ca35748012bded0b443885aba242511ea6350d289f22bab742f970
+size 5112

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BioGptTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89243d7b265e09483e6d0946d4b92058cfa2734ce5a4c5dfd5d975e18ed5d303
+size 3579