Training in progress, step 20

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "tiiuae/falcon-7b-instruct",
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,10 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_4h_to_h",
-    "dense_h_to_4h",
-    "query_key_value",
-    "dense"
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_rslora": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8beee3b5b86188515676fff03ab6343d2c6cfc17cfe17a533e8767e8108eff42
-size 261131840
+oid sha256:b44c6fdabc095f8f8c47e3ecdde1d7892205596b642550286e63d4dc45b54440
+size 335604696

qual_clasification.log

@@ -53,3 +53,10 @@
 2024-02-11 19:14:07,990 - INFO - __main__ - Loaded Model ID: tiiuae/falcon-7b-instruct
 2024-02-11 19:14:08,914 - INFO - __main__ - Loaded LoRA Model
 2024-02-11 19:14:09,545 - INFO - __main__ - Instantiated Trainer
+2024-02-12 00:06:16,122 - INFO - __main__ - Completed fine-tuning
+2024-02-12 00:06:18,016 - INFO - __main__ - Saved model and tokenizer to machine_learning/llm_finetune_models/0
+2024-02-12 00:06:20,394 - INFO - __main__ - Saved model to hub
+2024-02-12 00:08:03,435 - INFO - __main__ - Completed EM Metrics evaluation
+2024-02-12 00:09:33,450 - INFO - __main__ - Loaded Model ID: mistralai/Mistral-7B-Instruct-v0.1
+2024-02-12 00:09:34,543 - INFO - __main__ - Loaded LoRA Model
+2024-02-12 00:09:35,118 - INFO - __main__ - Instantiated Trainer

qual_clasification_outputs.csv

@@ -396,7 +396,7 @@ Qualitative Keywords:
 fieldwork",QUANTITATIVE,QUANTITATIVE,NON_QUALITATIVE,NON_QUALITATIVE,"QUANTITATIVE
 
 Assistant:
-MI",RESOLVABLE
+QUAL",RESOLVABLE
 29,"Grant Abstract:
 University of Florida graduate student, Stacey A. Giroux, under the direction of Dr. H. Russell Bernard, will undertake sociocultural research on how  changes in national dietary cultures are understood and acted upon at the level of the individual and household. There is abundant evidence that eating practices are changing worldwide, converging toward similar diets that are high in fat and sugar and low in fiber. Many nations also have escalating rates of overweight and obesity. This project will investigate the social and cultural foundations of this global phenomenon.
 

special_tokens_map.json

@@ -1,23 +1,24 @@
 {
-  "additional_special_tokens": [
-    ">>TITLE<<",
-    ">>ABSTRACT<<",
-    ">>INTRODUCTION<<",
-    ">>SUMMARY<<",
-    ">>COMMENT<<",
-    ">>ANSWER<<",
-    ">>QUESTION<<",
-    ">>DOMAIN<<",
-    ">>PREFIX<<",
-    ">>SUFFIX<<",
-    ">>MIDDLE<<"
-  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "eos_token": {
-    "content": "<|endoftext|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>"
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,8 +1,9 @@
 {
-  "add_prefix_space": false,
+  "add_bos_token": true,
+  "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
-      "content": ">>TITLE<<",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -10,7 +11,7 @@
       "special": true
     },
     "1": {
-      "content": ">>ABSTRACT<<",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -18,79 +19,7 @@
       "special": true
     },
     "2": {
-      "content": ">>INTRODUCTION<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "3": {
-      "content": ">>SUMMARY<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "4": {
-      "content": ">>COMMENT<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "5": {
-      "content": ">>ANSWER<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": ">>QUESTION<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "7": {
-      "content": ">>DOMAIN<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "8": {
-      "content": ">>PREFIX<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "9": {
-      "content": ">>SUFFIX<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "10": {
-      "content": ">>MIDDLE<<",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "11": {
-      "content": "<|endoftext|>",
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -98,26 +27,17 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    ">>TITLE<<",
-    ">>ABSTRACT<<",
-    ">>INTRODUCTION<<",
-    ">>SUMMARY<<",
-    ">>COMMENT<<",
-    ">>ANSWER<<",
-    ">>QUESTION<<",
-    ">>DOMAIN<<",
-    ">>PREFIX<<",
-    ">>SUFFIX<<",
-    ">>MIDDLE<<"
-  ],
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "<|endoftext|>",
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 2048,
-  "pad_token": "<|endoftext|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "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:e1644083d38e0bb2c00d93e760709cd825c88ee0f81f16b32e50db5d6ec5db57
+oid sha256:012998525ab2ef532484346fdf004a1d7e8a3becdab229bdfbecc366e11e46cb
 size 4728