End of training

README.md

@@ -21,14 +21,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [llava-hf/llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9503
-- Bleu: 0.1431
-- Rouge1: 0.4595
-- Rouge2: 0.1862
-- Rougel: 0.3572
-- Bertscore Precision: 0.6764
-- Bertscore Recall: 0.7669
-- Bertscore F1: 0.7187
+- Loss: 1.9504
+- Bleu: 0.1425
+- Rouge1: 0.4583
+- Rouge2: 0.1850
+- Rougel: 0.3579
+- Bertscore Precision: 0.6782
+- Bertscore Recall: 0.7679
+- Bertscore F1: 0.7201
 
 ## Model description
 
@@ -61,8 +61,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Bleu   | Rouge1 | Rouge2 | Rougel | Bertscore Precision | Bertscore Recall | Bertscore F1 |
 |:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|:------:|:-------------------:|:----------------:|:------------:|
-| 1.9971        | 0.9922 | 80   | 1.9960          | 0.1392 | 0.4511 | 0.1839 | 0.3524 | 0.6747              | 0.7687           | 0.7185       |
-| 1.9335        | 1.9845 | 160  | 1.9503          | 0.1431 | 0.4595 | 0.1862 | 0.3572 | 0.6764              | 0.7669           | 0.7187       |
+| 1.9977        | 0.9922 | 80   | 1.9963          | 0.1395 | 0.4530 | 0.1844 | 0.3520 | 0.6764              | 0.7670           | 0.7188       |
+| 1.9336        | 1.9845 | 160  | 1.9504          | 0.1425 | 0.4583 | 0.1850 | 0.3579 | 0.6782              | 0.7679           | 0.7201       |
 
 
 ### Framework versions

adapter_config.json

@@ -20,19 +20,19 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "out_proj",
-    "v_proj",
+    "linear_2",
     "q_proj",
+    "k_proj",
     "lm_head",
     "fc1",
-    "fc2",
-    "linear_1",
     "o_proj",
-    "k_proj",
-    "linear_2",
+    "out_proj",
+    "gate_proj",
+    "fc2",
     "up_proj",
-    "gate_proj"
+    "down_proj",
+    "linear_1",
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63a53256ce5f4248a3c862fd668a60ce0fcdf8cfa0a268ead0e3fae4253c1de6
+oid sha256:e6c63fcad0228e2178d7f3151a675d66d7bbdf31e9e3b19985b9fcf726356f1f
 size 454168240

runs/Oct17_23-04-42_s1840377-4-6lkqx/events.out.tfevents.1729206396.s1840377-4-6lkqx.1587656.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec413d9392222b21509e54b71f22eba04a987c6b0bc6e7956b9dc4662eaddb7
+size 14428

test_predictions.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:420df26f6bfcdf695e1f16079a6e9cb1443246afca6f133b231ed00fb5fc1304
-size 33364
+oid sha256:b62de2ca213a2060bc4d1cfafe56e0d6c1b5fab4422825f7c7b80e5ee7bb02e3
+size 33329

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62feaa51a2e8790b76e3f26c4df8d3f74904f3a0cefe49b3aa018c343ccbab50
+oid sha256:599b731d5983f786cb511a53823e7ac721d837be32254f19e84900c51e0a45f1
 size 5560