End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [LanguageBind/Video-LLaVA-7B-hf](https://huggingface.co/LanguageBind/Video-LLaVA-7B-hf) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.9957
+- Loss: 8.5023
 
 ## Model description
 
@@ -34,7 +34,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 0.0002
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42
@@ -42,25 +42,13 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 9.4715        | 0.2266 | 10   | 9.3002          |
-| 8.448         | 0.4533 | 20   | 8.1185          |
-| 8.0506        | 0.6799 | 30   | 7.6170          |
-| 7.3195        | 0.9065 | 40   | 7.3867          |
-| 6.9419        | 1.1331 | 50   | 7.2530          |
-| 7.3337        | 1.3598 | 60   | 7.1755          |
-| 7.1611        | 1.5864 | 70   | 7.1151          |
-| 7.075         | 1.8130 | 80   | 7.0700          |
-| 7.2556        | 2.0397 | 90   | 7.0422          |
-| 6.7634        | 2.2663 | 100  | 7.0307          |
-| 6.8423        | 2.4929 | 110  | 7.0106          |
-| 7.0453        | 2.7195 | 120  | 7.0038          |
-| 7.2777        | 2.9462 | 130  | 6.9957          |
+| 8.317         | 1.1940 | 10   | 8.5023          |
 
 
 ### Framework versions

adapter_config.json

@@ -16,9 +16,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "k_proj",
     "o_proj",
-    "gate_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64d61c352f24d352df8f8766f2a6cfce6c1fd47e20af4353ac6e53d4eba8081d
+oid sha256:6e351e5170f9dd54ffe9c5fea0c8f97a30a36cfb94e95350ed744d585d74c4a7
 size 375459936

runs/Sep29_20-15-00_dgx01/events.out.tfevents.1727615720.dgx01.2660548.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd3efeceaff2685eaa5d9e352deebe508ff588f7e7f3d93b9a2d5f17a35877fb
+size 9151

runs/Sep30_13-21-10_dgx01/events.out.tfevents.1727677274.dgx01.3392663.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc9bdb2eafe30e28f83c5243c731b8e0fbe0292db091bf3587be08bd5671be40
+size 13136

runs/Sep30_14-48-25_dgx01/events.out.tfevents.1727682527.dgx01.3460407.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2534dde803bb7979273682f81abc2dc9e900c83de1a4704669f6f195dcef65
+size 6608

runs/Sep30_15-11-50_dgx01/events.out.tfevents.1727683911.dgx01.3460407.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b4f44105e9605f9a72acbde7cede589f0807b6825dfbaf31d66ae6507602fb
+size 17808

runs/Sep30_15-13-05_dgx01/events.out.tfevents.1727683987.dgx01.3392663.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aac4cdba9b5763085b38e9b8faa263f898d8759171f5a0ea2862cb48f03895c
+size 7850

runs/Sep30_15-36-14_dgx01/events.out.tfevents.1727685382.dgx01.3500101.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73d3d3132c6fb2375def501d6e22d4ac345dafe0a867b16ede4335ead91244c8
+size 17808

runs/Sep30_22-16-17_dgx01/events.out.tfevents.1727709383.dgx01.3831800.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de7593a649a151d543265c6c4eb50c5f8f419345e32663c7c0fe79262ae4dff
+size 9706

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9771e5343ed94f0d0369ace435b8d172aea02dfb001c42a800c70abc36ac6f56
+oid sha256:e455fbc21e74f6a6dcc9cee5b79b115afcd31859bc62363fd1c22b56e4dc6b83
 size 5176