Model save

README.md

@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the wikisql dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0562
+- Loss: 0.0457
 
 ## Model description
 
@@ -54,7 +54,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.0664        | 1.0   | 263  | 0.0562          |
+| 0.0482        | 1.0   | 263  | 0.0457          |
 
 
 ### Framework versions

adapter_config.json

@@ -19,14 +19,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "up_proj",
-    "embed_tokens",
+    "q_proj",
     "down_proj",
-    "o_proj",
     "v_proj",
-    "q_proj",
-    "lm_head",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:235d1bf7bb0a017a1da20cef0977c5d6507e56bfcb0c08336f1d44faf561be0b
-size 551740408
+oid sha256:163b8c71767bb6675fae40f92c4bab0d491181d5560e921665fa31f276452bf4
+size 25271744

runs/Jan17_06-54-16_hf-dgx-01/events.out.tfevents.1705470859.hf-dgx-01.2323147.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda4e71e29986c23024a8322410bb20aecac6c7a6b25d9f9917527fb4398a34d
+size 13170

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54665397da31f83aabde86527007bad96daaf3abdbbc8eee2c378f30ec28f5c8
+oid sha256:dd7494a366eab6dfdab91658ee32de530ff5e3a039463d7000aebcd686a9241d
 size 4728