joelb/mistral-7b-instruct-ccai-scotland

README.md

@@ -35,13 +35,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 5e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- training_steps: 100
 
 ### Training results
 

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3978840d7c163f13df9d3f79ea177df60d8e975d08964cafbceadc02e3ff60a0
-size 54543184
+oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
+size 48

runs/Aug02_21-23-14_d5a55981d54d/events.out.tfevents.1722633812.d5a55981d54d.15171.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b687765e09780d505ce1a9b64664c784b162d46690063cb5e30848b046b600
+size 15316

runs/Aug02_21-26-55_d5a55981d54d/events.out.tfevents.1722634035.d5a55981d54d.15171.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04b23228d14ac483eddd9db82bc4b4541f4f0d4ba0a82f6875a119e6cf0f6394
+size 20752

runs/Aug02_21-36-09_d5a55981d54d/events.out.tfevents.1722634592.d5a55981d54d.15171.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae183e6dbbbbed29f51ffd5af53a0e9cb979eb1678b4225acaa331efe269c8b
+size 20752

runs/Aug02_21-49-00_d5a55981d54d/events.out.tfevents.1722635376.d5a55981d54d.21668.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0314d15b45ed2d935e71f217abeb7c9358c0c4906349227675f66b1edbb4053
+size 20456

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,6 +1,11 @@
 {
   "version": "1.0",
-  "truncation": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:820a7baaf734c873694c5ce17201e7e1e20535388be57929db75445375d8671b
+oid sha256:4942072b2e9076eda35a8ae39ff7cda855315e7c4618163c1c3cfce0c10ffd54
 size 4984