trained_sentiment

README.md

@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6323
+- Loss: 1.8211
 
 ## Model description
 
@@ -51,17 +51,17 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 1.4554        | 0.9944 | 155  | 1.4685          |
-| 1.1957        | 1.9952 | 311  | 1.4965          |
-| 0.8349        | 2.9832 | 465  | 1.6323          |
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.5093        | 1.0   | 491  | 1.6536          |
+| 1.1833        | 2.0   | 982  | 1.6768          |
+| 0.8405        | 3.0   | 1473 | 1.8211          |
 
 
 ### Framework versions
 
-- PEFT 0.11.1
-- Transformers 4.42.3
-- Pytorch 2.1.2
-- Datasets 2.20.0
+- PEFT 0.12.0
+- Transformers 4.44.0
+- Pytorch 2.4.0
+- Datasets 2.21.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "up_proj",
     "v_proj",
     "o_proj",
+    "gate_proj",
     "q_proj",
-    "k_proj",
-    "down_proj",
-    "gate_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34a05f13213775cb104190a181b2113ed30b2cc23177371d7f3c40217b07f100
+oid sha256:efc11587817c99a14e37e37e10aea341c71f10924ee0e80c77f5622c2980ca6b
 size 671149168

runs/Sep05_09-04-16_b5c5cac84dd7/events.out.tfevents.1725527063.b5c5cac84dd7.36.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1876c0e32854a12392097c1eee6760e07c397cf8edd147d2e3f2a66e106025ac
+size 19236

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdd23b45d841263f7f3b48244046d2a75da29add7542f463dfd1cc990fa90478
-size 5432
+oid sha256:02407104359185f38047ae92f1530f30f89a09007915a37c292ceb7b619082c5
+size 5496