Training completed!

README.md

@@ -1,10 +1,11 @@
 ---
+license: llama2
 library_name: peft
 tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: beomi/llama-2-ko-7b
+base_model: malhajar/meditron-7b-chat
 model-index:
 - name: results
   results: []
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [beomi/llama-2-ko-7b](https://huggingface.co/beomi/llama-2-ko-7b) on an unknown dataset.
+This model is a fine-tuned version of [malhajar/meditron-7b-chat](https://huggingface.co/malhajar/meditron-7b-chat) on an unknown dataset.
 
 ## Model description
 
@@ -35,13 +36,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 4
+- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_ratio: 0.03
-- num_epochs: 10
+- num_epochs: 5
 
 ### Training results
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "beomi/llama-2-ko-7b",
+  "base_model_name_or_path": "malhajar/meditron-7b-chat",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,8 +19,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_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:d359b541e1677e634d8155b246fb0c35c892621c27675f217c533bd72321cff8
+oid sha256:2f7af9f0d1c1106dc64fc0e92974b589a50f1fff25248714baec7840b761ccf0
 size 134235048

runs/Apr04_12-17-29_eb8ec7d052f4/events.out.tfevents.1712233058.eb8ec7d052f4.989.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee769f84103e66a9d7d4edac837972b2ab632d0c8d802ad43914dac15cf4c064
+size 6204

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -25,46 +25,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "46331": {
-      "content": "<|sep|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "46332": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "46333": {
-      "content": "<|acc|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "46334": {
-      "content": "<|rrn|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "46335": {
-      "content": "<|tel|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<s>",
@@ -73,6 +33,7 @@
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "</s>",
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7c35c1860c0b4fd75740c170e307121aae01bd979213aee9ca737502a2f023f
+oid sha256:6eec22afda79e639f1fff7a0e06480a865b1b46e9c2df114745f205ecc7cc356
 size 4664