health-assistant-v1

README.md

@@ -9,9 +9,6 @@ base_model: microsoft/phi-2
 model-index:
 - name: medical
   results: []
-language:
-- en
-pipeline_tag: conversational
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,8 +40,9 @@ The following hyperparameters were used during training:
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 1
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- training_steps: 500
 
 ### Training results
 
@@ -53,7 +51,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.7.2.dev0
-- Transformers 4.38.0.dev0
-- Pytorch 2.1.0+cu121
+- Transformers 4.37.1
+- Pytorch 2.1.2+cu121
 - Datasets 2.16.1
 - Tokenizers 0.15.1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "microsoft/phi-2",
+  "base_model_name_or_path": null,
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -9,21 +9,18 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 64,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "fc2",
-    "q_proj",
-    "k_proj",
-    "v_proj",
-    "dense",
+    "Wqkv",
     "fc1"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c132c6d9ca6e90c576373c0597d6e5ddc8abf3ead848cd5225bf8d2ca2ad9b3
-size 94422368
+oid sha256:629ac58a2a288f05c82f9e6abcb9919b1fb3902e226fe86d5f49052e30bb8579
+size 188814192

tokenizer_config.json

@@ -1,4 +1,6 @@
 {
+  "add_bos_token": true,
+  "add_eos_token": true,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "50256": {
@@ -317,8 +319,10 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "errors": "replace",
   "model_max_length": 2048,
   "pad_token": "<|endoftext|>",
+  "padding_side": "left",
   "tokenizer_class": "CodeGenTokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b89e647d42e38c3dfff9c2cfc1566acd2fd9be63f465d45ea5d2f4fed7049ac7
-size 4728
+oid sha256:7ff903669e02c7a64a326fa91b78408c6dd0c58c9a68f32fc72fc615b4368d20
+size 4664