Training in progress, epoch 1

config.json

@@ -1,17 +1,15 @@
 {
   "_name_or_path": "microsoft/biogpt",
   "activation_dropout": 0.0,
-  "activation_function": "gelu_new",
   "architectures": [
-    "GPT2ForTokenClassification"
+    "BioGptForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "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": 1024,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -25,25 +23,13 @@
     "LABEL_2": 2
   },
   "layer_norm_eps": 1e-12,
-  "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,
+  "max_position_embeddings": 1024,
+  "model_type": "biogpt",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "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": "4.38.2",
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8061775b58f26eb8df789c4ff3a64f281c29bd162081a68c5251f66990361575
-size 1387087524
+oid sha256:8231e2827d31aca14b62e1151de5182f17da6b621f74b2c426c5f627b140e7f1
+size 1387108052

runs/Apr13_04-28-07_441548a08422/events.out.tfevents.1712982885.441548a08422.2625.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ff7c296fa236f80c4f4b3fa94688fc41cbff8bc85ad748368ad1eb05c2fd04
+size 560

runs/Apr13_05-00-16_441548a08422/events.out.tfevents.1712984417.441548a08422.2625.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf2fc125ee55a1e092471459d583575207a68f8c4b245a7ce7a94632f44539a
+size 5108

runs/Apr13_05-01-53_441548a08422/events.out.tfevents.1712984514.441548a08422.2625.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1576f8c4c32f65b305847caf7a5367cd759aa02cbca8f7ebd3a9aa83bf4acf2a
+size 5417

special_tokens_map.json

@@ -1,23 +1,7 @@
 {
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,22 +1,44 @@
 {
-  "add_bos_token": false,
-  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "42384": {
-      "content": "<|endoftext|>",
+    "0": {
+      "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<|endoftext|>",
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "errors": "replace",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "eos_token": "</s>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BioGptTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dfce4f8db85d2c66e754f6b798d53343abf13e4e70e588868a4aa509f68d596
+oid sha256:8aee829f7127907d25b04ce452e5079329ae88cd4178acd8d487448a80ff6d61
 size 4984