Jlonge4/rag-rel

README.md

@@ -16,12 +16,13 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/grounded-ai-rag-relevance/runs/oius6vlo)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/grounded-ai-rag-relevance/runs/7nacy5gw)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/josh-longenecker1-groundedai/grounded-ai-rag-relevance/runs/7nacy5gw)
 # grounded-ai-rag-3
 
 This model is a fine-tuned version of [microsoft/Phi-3.5-mini-instruct](https://huggingface.co/microsoft/Phi-3.5-mini-instruct) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3813
+- Loss: 0.5557
 - Rouge1: 1.0
 - Rouge2: 0.0
 - Rougel: 1.0
@@ -53,26 +54,20 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 15
-- training_steps: 150
+- training_steps: 40
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
-| 1.7953        | 5.0   | 5    | 1.8076          | 1.0    | 0.0    | 1.0    | 1.0       |
-| 1.4603        | 10.0  | 10   | 1.6034          | 1.0    | 0.0    | 1.0    | 1.0       |
-| 1.2107        | 15.0  | 15   | 1.4092          | 1.0    | 0.0    | 1.0    | 1.0       |
-| 0.911         | 20.0  | 20   | 1.2036          | 1.0    | 0.0    | 1.0    | 1.0       |
-| 0.5225        | 25.0  | 25   | 1.0263          | 1.0    | 0.0    | 1.0    | 1.0       |
-| 0.2248        | 30.0  | 30   | 0.9228          | 1.0    | 0.0    | 1.0    | 1.0       |
-| 0.1138        | 35.0  | 35   | 0.9692          | 1.0    | 0.0    | 1.0    | 1.0       |
-| 0.0533        | 40.0  | 40   | 1.1089          | 1.0    | 0.0    | 1.0    | 1.0       |
-| 0.0197        | 45.0  | 45   | 1.1951          | 1.0    | 0.0    | 1.0    | 1.0       |
-| 0.0066        | 50.0  | 50   | 1.2534          | 1.0    | 0.0    | 1.0    | 1.0       |
-| 0.0051        | 55.0  | 55   | 1.3186          | 1.0    | 0.0    | 1.0    | 1.0       |
-| 0.0036        | 60.0  | 60   | 1.3523          | 1.0    | 0.0    | 1.0    | 1.0       |
-| 0.0047        | 65.0  | 65   | 1.3669          | 1.0    | 0.0    | 1.0    | 1.0       |
-| 0.0037        | 70.0  | 70   | 1.3813          | 1.0    | 0.0    | 1.0    | 1.0       |
+| 1.8222        | 5.0   | 5    | 1.9460          | 1.0    | 0.0    | 1.0    | 1.0       |
+| 1.7609        | 10.0  | 10   | 1.6547          | 1.0    | 0.0    | 1.0    | 1.0       |
+| 1.4433        | 15.0  | 15   | 1.3821          | 1.0    | 0.0    | 1.0    | 1.0       |
+| 1.2307        | 20.0  | 20   | 1.1176          | 1.0    | 0.0    | 1.0    | 1.0       |
+| 0.9889        | 25.0  | 25   | 0.7975          | 1.0    | 0.0    | 1.0    | 1.0       |
+| 0.6934        | 30.0  | 30   | 0.6240          | 1.0    | 0.0    | 1.0    | 1.0       |
+| 0.5838        | 35.0  | 35   | 0.5633          | 1.0    | 0.0    | 1.0    | 1.0       |
+| 0.5625        | 40.0  | 40   | 0.5557          | 1.0    | 0.0    | 1.0    | 1.0       |
 
 
 ### Framework versions

adapter_config.json

@@ -11,7 +11,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
-  "lora_dropout": 0.3,
+  "lora_dropout": 0.4,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "v_proj",
-    "up_proj",
     "down_proj",
+    "gate_proj",
     "o_proj",
+    "up_proj",
     "q_proj",
     "k_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3adb363beb9ab4b7603afdf9abfceea13dc71393dd559126e4c5f1df8b239fc
+oid sha256:49bd1cff42f1c1e1b356b1e9a3a35cf9bbfd67c5de5d5999fb9b70df38147f5b
 size 35668592

runs/Oct13_18-32-11_48c91bda07e0/events.out.tfevents.1728844332.48c91bda07e0.14392.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9f32ed295d19adaa425bd23cf3fd246fc1483803b4ed4af71faed8987f29ad1
+size 22668

runs/Oct13_18-33-22_48c91bda07e0/events.out.tfevents.1728844403.48c91bda07e0.14392.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ed341522ef5d240a35a9f0df4415d5becc0fde131a57b32d9c98765b577f22
+size 20480

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a889510aa783638fd8cea9b7ae4b0fa932377333e913d51cf0ca21ff3e6acc08
+oid sha256:c3f4d12ba775f54699cbc14db01368aed7d1d5cfca0fa13b06b3a34736334737
 size 5432