Training complete

README.md

@@ -1,11 +1,11 @@
 ---
-license: apache-2.0
-base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+base_model: jianghc/medical_chatbot
 tags:
 - generated_from_trainer
 model-index:
 - name: results
   results: []
+library_name: peft
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
+This model is a fine-tuned version of [jianghc/medical_chatbot](https://huggingface.co/jianghc/medical_chatbot) on an unknown dataset.
 
 ## Model description
 
@@ -29,25 +29,36 @@ More information needed
 
 ## Training procedure
 
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: False
+- load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float16
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0004
-- train_batch_size: 4
+- learning_rate: 0.0002
+- train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
+- lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 4
-
-### Training results
-
-
+- training_steps: 10000
 
 ### Framework versions
 
-- Transformers 4.31.0
+- PEFT 0.4.0
+- Transformers 4.37.2
 - Pytorch 2.1.0+cu121
-- Datasets 2.17.0
-- Tokenizers 0.13.3
+- Datasets 2.17.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -1,21 +1,22 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "base_model_name_or_path": "jianghc/medical_chatbot",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
   "layers_pattern": null,
   "layers_to_transform": null,
-  "lora_alpha": 16,
-  "lora_dropout": 0.1,
+  "lora_alpha": 32,
+  "lora_dropout": 0.25,
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 12,
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "c_attn",
+    "c_proj",
+    "lm_head"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:398103d1de6af29af38ff1c1c2b18c4061b97748471c221bf807fdb54c47029f
+size 44788888

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|endoftext|>": 28896,
+  "[PAD]": 28895
+}

runs/Feb27_06-25-37_4bfb014b2b3a/events.out.tfevents.1709015347.4bfb014b2b3a.214.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b21499756af066a27639486752ab86641f565a95ea88c5170f64225a96a62b
+size 20697

special_tokens_map.json

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

tokenizer_config.json

@@ -1,40 +1,31 @@
 {
+  "add_bos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "0": {
-      "content": "<unk>",
+    "28895": {
+      "content": "[PAD]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "28896": {
+      "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "2": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "legacy": false,
-  "model_max_length": 2048,
-  "pad_token": "</s>",
-  "padding_side": "right",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "[PAD]",
+  "errors": "replace",
+  "model_max_length": 1024,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53fc804dfd16f4f066e9877f2f3282899568d2565040d4d215aebd03071e12e6
-size 4408
+oid sha256:baf2b0b16f703f1effef0c504aa2d2c39e98631970685415209c5a4c23dab422
+size 4664