AT-Llama-2-7b-chat-Tweet-Sentiment

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TheBloke/Llama-2-7B-Chat-GPTQ](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GPTQ) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3702
+- Loss: 1.6657
 
 ## Model description
 
@@ -51,27 +51,27 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 5.422         | 0.0457 | 2    | 5.0470          |
-| 4.9414        | 0.0914 | 4    | 4.1810          |
-| 4.0188        | 0.1371 | 6    | 3.4657          |
-| 3.3677        | 0.1829 | 8    | 3.0499          |
-| 2.9535        | 0.2286 | 10   | 2.6861          |
-| 2.6161        | 0.2743 | 12   | 2.3395          |
-| 2.2863        | 0.32   | 14   | 2.1053          |
-| 2.0074        | 0.3657 | 16   | 1.8991          |
-| 1.8586        | 0.4114 | 18   | 1.7303          |
-| 1.6228        | 0.4571 | 20   | 1.5946          |
-| 1.6133        | 0.5029 | 22   | 1.4988          |
-| 1.4484        | 0.5486 | 24   | 1.5005          |
-| 1.4666        | 0.5943 | 26   | 1.4966          |
-| 1.4474        | 0.64   | 28   | 1.4517          |
-| 1.3586        | 0.6857 | 30   | 1.4138          |
-| 1.4181        | 0.7314 | 32   | 1.3979          |
-| 1.4306        | 0.7771 | 34   | 1.3889          |
-| 1.3387        | 0.8229 | 36   | 1.3809          |
-| 1.3072        | 0.8686 | 38   | 1.3747          |
-| 1.4662        | 0.9143 | 40   | 1.3714          |
-| 1.3664        | 0.96   | 42   | 1.3702          |
+| 5.422         | 0.0457 | 2    | 5.1721          |
+| 5.1534        | 0.0914 | 4    | 4.6225          |
+| 4.5268        | 0.1371 | 6    | 4.0415          |
+| 3.9455        | 0.1829 | 8    | 3.5294          |
+| 3.4478        | 0.2286 | 10   | 3.1964          |
+| 3.1897        | 0.2743 | 12   | 2.9354          |
+| 2.8951        | 0.32   | 14   | 2.6721          |
+| 2.5987        | 0.3657 | 16   | 2.4219          |
+| 2.3629        | 0.4114 | 18   | 2.2606          |
+| 2.1553        | 0.4571 | 20   | 2.1368          |
+| 2.109         | 0.5029 | 22   | 2.0289          |
+| 1.9611        | 0.5486 | 24   | 1.9382          |
+| 1.8992        | 0.5943 | 26   | 1.8638          |
+| 1.794         | 0.64   | 28   | 1.8066          |
+| 1.7374        | 0.6857 | 30   | 1.7621          |
+| 1.7599        | 0.7314 | 32   | 1.7268          |
+| 1.769         | 0.7771 | 34   | 1.7006          |
+| 1.6442        | 0.8229 | 36   | 1.6834          |
+| 1.6242        | 0.8686 | 38   | 1.6730          |
+| 1.7367        | 0.9143 | 40   | 1.6677          |
+| 1.6649        | 0.96   | 42   | 1.6657          |
 
 
 ### Framework versions

adapter_config.json

@@ -10,13 +10,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bbd1fa703e643c9f476ebdb0de822393d50edf2c6a19d2b6aabc137fd8b8194
-size 16794200
+oid sha256:7add42742d1884f0e22aebc80542c459d27314d61c4bb215cb02cf8f9c576eed
+size 134235048

runs/May11_22-15-49_ebd9bc4e0c63/events.out.tfevents.1715465784.ebd9bc4e0c63.22644.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1db416514964659892ae149249992da4860a1e2776efb0466c7b76d0f5c0ba22
+size 15642

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c357191843c737d0cac9a99bbc73f2344910551289df1ff3b16bc29b44cc33a
+oid sha256:45c97bd6b5b73d80c710fee45dcc56ec5821a919ff71ab7c456ce65cf7c553c5
 size 4984