Mistral-7B-v0.3-chat-medical-NLP_project

README.md

@@ -5,7 +5,7 @@ tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: google-bert/bert-base-multilingual-cased
+base_model: mistralai/Mistral-7B-v0.3
 model-index:
 - name: results
   results: []
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [google-bert/bert-base-multilingual-cased](https://huggingface.co/google-bert/bert-base-multilingual-cased) on the None dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the None dataset.
 
 ## Model description
 
@@ -44,6 +44,10 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.03
 - num_epochs: 1
 
+### Training results
+
+
+
 ### Framework versions
 
 - PEFT 0.11.1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google-bert/bert-base-multilingual-cased",
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "value",
-    "query"
+    "v_proj",
+    "q_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:d88f99263fea9d970673f80929149af6475760135c30c11fafcbe42b8bd2d580
-size 9443984
+oid sha256:2b6729f61411c6fc5beb6df6e3f5dd324d3d06a458f2ae475fefab25f7526442
+size 109069176

runs/May26_14-41-30_4c4794af6a38/events.out.tfevents.1716734496.4c4794af6a38.1591.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ad7a82c14615ade4390e7c8b9c7b656f3619d037bc997cb4353b371a071f8e2
+size 6895

special_tokens_map.json

@@ -1,7 +1,24 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
-size 499723
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4e2c6c9d10298a0e89bee3a1c2d77bb23516d9b7f228e8ab024a727190092bc
+oid sha256:6e8ef039206e1047eef10a698ec75f152d9dc5cb38447a30fb9cf2459bf7c7f6
 size 5112