End of training

README.md

@@ -6,16 +6,16 @@ tags:
 - sft
 - generated_from_trainer
 model-index:
-- name: llva-1.5-7b-scicap
+- name: model
   results: []
 ---
 
 <!-- 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. -->
 
-# llava-1.5-7b-scicap
+# model
 
-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.
+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 the None dataset.
 
 ## Model description
 
@@ -35,12 +35,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1.4e-05
-- train_batch_size: 1
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -51,6 +51,6 @@ The following hyperparameters were used during training:
 
 - PEFT 0.11.1
 - Transformers 4.42.3
-- Pytorch 2.2.1+cu121
-- Datasets 2.20.0
+- Pytorch 2.1.0
+- Datasets 2.15.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -23,19 +23,19 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "out_proj",
     "fc1",
-    "k_proj",
-    "q_proj",
+    "down_proj",
     "linear_2",
+    "o_proj",
+    "q_proj",
+    "out_proj",
+    "up_proj",
+    "k_proj",
     "linear_1",
     "gate_proj",
-    "fc2",
     "v_proj",
-    "up_proj",
-    "o_proj",
-    "lm_head",
-    "down_proj"
+    "fc2",
+    "lm_head"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67eb1dade3c2ab276d2dd076bc187862220fe6795cd66396a9298d9fa4dad38d
+oid sha256:d3fa5a15365ef64e08deff7b334b15ae2ef70b5b17762115e326c6c87c26f6e5
 size 1290994752

tokenizer.json

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

tokenizer_config.json

@@ -51,7 +51,7 @@
   "legacy": false,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
-  "padding_side": "right",
+  "padding_side": "left",
   "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:ddbf295c5a2ef0434f285b9ba8f00bb42b9d89b6870450dba188ed6f4f362492
+oid sha256:fb3854861ed3b77e539fb7b3de4d44f9b985c327f59999bdf9a3a0d074515c2c
 size 5112