Training in progress, step 265

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "epfl-llm/meditron-7b",
+  "base_model_name_or_path": "unsloth/llama-2-7b-chat-bnb-4bit",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
     "up_proj",
-    "o_proj",
-    "v_proj",
+    "k_proj",
     "q_proj",
-    "gate_proj"
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9809602631f53f593605bdc35d559c88bd9496ff59f012c3c26d7e75e45de6ba
+oid sha256:18b97d1c23158519bf1ae810d3922a872561ba30e8beb2584aa04baec5c2e7a7
 size 5117112704

runs/Oct18_19-56-32_b9c4e637b51c/events.out.tfevents.1729281396.b9c4e637b51c.6221.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bee92d62519a4d1fa04bb7ec0baabf7025218efd2075c4fcf175926514613bcf
+size 11557

special_tokens_map.json

@@ -1,28 +1,7 @@
 {
-  "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
@@ -30,26 +9,12 @@
   "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>",
+    "content": "<unk>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
@@ -58,7 +23,7 @@
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -1,12 +1,12 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
-  "add_prefix_space": true,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -14,7 +14,7 @@
     "1": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -22,174 +22,21 @@
     "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]",
-      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "[bib_ref]",
-    "[/bib_ref]",
-    "[fig_ref]",
-    "[/fig_ref]",
-    "[bib]",
-    "[/bib]",
-    "[fig]",
-    "[/fig]",
-    "[table]",
-    "[/table]",
-    "[formula]",
-    "[/formula]"
-  ],
   "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "<CLS>",
   "eos_token": "</s>",
   "legacy": false,
-  "mask_token": "<MASK>",
   "model_max_length": 4096,
-  "pad_token": "<PAD>",
+  "pad_token": "<unk>",
   "padding_side": "right",
-  "sep_token": "<SEP>",
   "sp_model_kwargs": {},
-  "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:236bb0f2118cd2d2cc800861787f9d3c9c2d447b0a8b79b4777de831321f9e7d
+oid sha256:c60f9cfc7e9c83a0c06145e2a7609cca95ba652065569a1cee831cd648f1fcd3
 size 5496