End of training

README.md

@@ -6,9 +6,6 @@ tags:
 - trl
 - sft
 - generated_from_trainer
-metrics:
-- bleu
-- rouge
 model-index:
 - name: sft-llava-1.5-7b-hf2
   results: []
@@ -20,15 +17,6 @@ should probably proofread and complete it, then remove this comment. -->
 # sft-llava-1.5-7b-hf2
 
 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: 0.0001
-- Bleu: 0.7828
-- Rouge1: 0.9231
-- Rouge2: 0.8333
-- Rougel: 0.9231
-- Bertscore Precision: 0.6617
-- Bertscore Recall: 0.7720
-- Bertscore F1: 0.7126
 
 ## Model description
 
@@ -58,11 +46,6 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Bleu   | Rouge1 | Rouge2 | Rougel | Bertscore Precision | Bertscore Recall | Bertscore F1 |
-|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|:------:|:-------------------:|:----------------:|:------------:|
-| 3.4619        | 0.3101 | 200  | 0.4315          | 0.8666 | 0.9600 | 0.9565 | 0.9600 | 0.6456              | 0.7676           | 0.7013       |
-| 2.4675        | 0.6202 | 400  | 0.0004          | 0.8346 | 0.9600 | 0.9565 | 0.9600 | 0.6728              | 0.7737           | 0.7197       |
-| 2.2495        | 0.9302 | 600  | 0.0001          | 0.7828 | 0.9231 | 0.8333 | 0.9231 | 0.6617              | 0.7720           | 0.7126       |
 
 
 ### Framework versions

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f91843356900248817e8135fe5e573883b76c15cc03678404972c6b79ca8a67
+oid sha256:f639391e3dbecc41e32de9824d9a25cf70b75762a7d5385535a0dc25442a9dc4
 size 4992930688

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8f35afbc08309d1ba4d642d53f20741d84ae9228a881ee4b97624ca9d3d65b8
+oid sha256:b321a7d4f41f1107f5c2eeea967a5f42fa2341809a4e86849f7ac4b99b477de5
 size 4957878552

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:146df6732dcdc6d16205b614c120678afd0a4b49dfb5a9973cf33e4a69594173
+oid sha256:c1a1f1fe5da9b2234a137dc3631d08309a212559956660139bfaa0cd2994c004
 size 4176137496

runs/Oct20_17-02-32_s1840377-6-88zz2/events.out.tfevents.1729443790.s1840377-6-88zz2.661726.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55ebb6cb888f6c803830f7171d5dc946a1b7dcb0d91ff3e42e769f8b6f08baf9
+size 9844

tokenizer.json

@@ -3,7 +3,7 @@
   "truncation": null,
   "padding": {
     "strategy": "BatchLongest",
-    "direction": "Left",
+    "direction": "Right",
     "pad_to_multiple_of": null,
     "pad_id": 32001,
     "pad_type_id": 0,

tokenizer_config.json

@@ -50,7 +50,7 @@
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "padding_side": "left",
+  "padding_side": "right",
   "processor_class": "LlavaProcessor",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a355857a5d62343050db581a14f23892bcdb2867cf765ad0c884340764d2440
+oid sha256:42fb3475e8967f0730bea31a554ad0cd50f26fa16a3f9788941ed4a7042d5f88
 size 5624