Training in progress, step 500

adapter_config.json

@@ -1,31 +1,25 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "epfl-llm/meditron-7b",
+  "base_model_name_or_path": "stanford-crfm/BioMedLM",
   "bias": "none",
-  "fan_in_fan_out": false,
+  "fan_in_fan_out": true,
   "inference_mode": true,
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 32,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
-    "q_proj",
-    "down_proj",
-    "k_proj",
-    "gate_proj",
-    "v_proj"
+    "c_attn"
   ],
-  "task_type": "CAUSAL_LM"
+  "task_type": "SEQ_CLS"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0bdb04d25933246176af14be1eeb714946941189d2540499c399afed3b685cc
-size 40036488
+oid sha256:7f2a043e5013a1b6b883749ce2c9bfc8a0ceb433669b4561c143004d7857d950
+size 21000432

added_tokens.json

@@ -1,19 +1,3 @@
 {
-  "<CLS>": 32000,
-  "<EOD>": 32002,
-  "<MASK>": 32003,
-  "<PAD>": 32004,
-  "<SEP>": 32001,
-  "[/bib]": 32010,
-  "[/bib_ref]": 32006,
-  "[/fig]": 32012,
-  "[/fig_ref]": 32008,
-  "[/formula]": 32016,
-  "[/table]": 32014,
-  "[bib]": 32009,
-  "[bib_ref]": 32005,
-  "[fig]": 32011,
-  "[fig_ref]": 32007,
-  "[formula]": 32015,
-  "[table]": 32013
+  "<|endoftext|>": 28895
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "michiyasunaga/BioLinkBERT-base",
+  "_name_or_path": "michiyasunaga/BioLinkBERT-large",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -8,14 +8,14 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63afe1487612581394ca79b22a1082ff01c70e53b3a52c045f8806699543bd09
-size 432960488
+oid sha256:43aba0e9eab150cefb6e248c29f5300d333e549f65072fa9f683e29c14cbc1eb
+size 1333958568

special_tokens_map.json

@@ -1,65 +1,6 @@
 {
-  "additional_special_tokens": [
-    "[bib_ref]",
-    "[/bib_ref]",
-    "[fig_ref]",
-    "[/fig_ref]",
-    "[bib]",
-    "[/bib]",
-    "[fig]",
-    "[/fig]",
-    "[table]",
-    "[/table]",
-    "[formula]",
-    "[/formula]"
-  ],
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<CLS>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "<MASK>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<PAD>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "<SEP>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -1,161 +1,8 @@
 {
-  "add_bos_token": true,
-  "add_eos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "1": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32000": {
-      "content": "<CLS>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32001": {
-      "content": "<SEP>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32002": {
-      "content": "<EOD>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32003": {
-      "content": "<MASK>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32004": {
-      "content": "<PAD>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32005": {
-      "content": "[bib_ref]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32006": {
-      "content": "[/bib_ref]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32007": {
-      "content": "[fig_ref]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32008": {
-      "content": "[/fig_ref]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32009": {
-      "content": "[bib]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32010": {
-      "content": "[/bib]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32011": {
-      "content": "[fig]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32012": {
-      "content": "[/fig]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32013": {
-      "content": "[table]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32014": {
-      "content": "[/table]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32015": {
-      "content": "[formula]",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32016": {
-      "content": "[/formula]",
+    "28895": {
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -163,31 +10,11 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "[bib_ref]",
-    "[/bib_ref]",
-    "[fig_ref]",
-    "[/fig_ref]",
-    "[bib]",
-    "[/bib]",
-    "[fig]",
-    "[/fig]",
-    "[table]",
-    "[/table]",
-    "[formula]",
-    "[/formula]"
-  ],
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "cls_token": "<CLS>",
-  "eos_token": "</s>",
-  "legacy": true,
-  "mask_token": "<MASK>",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<PAD>",
-  "sep_token": "<SEP>",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
 }