End of training

README.md

@@ -4,7 +4,7 @@ tags:
 - trl
 - sft
 - generated_from_trainer
-base_model: llava-hf/llava-1.5-7b-hf
+base_model: llava_21
 model-index:
 - name: llava-1.5-7b-hf-med
   results: []
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llava-1.5-7b-hf-med
 
-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.
+This model was trained from scratch on the None dataset.
 
 ## Model description
 
@@ -35,22 +35,18 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1.4e-05
-- train_batch_size: 8
+- train_batch_size: 2
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 7
+- num_epochs: 1
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
 - PEFT 0.10.0
-- Transformers 4.40.1
-- Pytorch 2.1.2
-- Datasets 2.18.0
+- Transformers 4.41.0.dev0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -4,7 +4,7 @@
     "base_model_class": "LlavaForConditionalGeneration",
     "parent_library": "transformers.models.llava.modeling_llava"
   },
-  "base_model_name_or_path": "llava-hf/llava-1.5-7b-hf",
+  "base_model_name_or_path": "llava_21",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -13,8 +13,8 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.0,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -23,19 +23,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "fc1",
     "q_proj",
-    "fc2",
-    "lm_head",
-    "linear_1",
-    "up_proj",
-    "k_proj",
-    "gate_proj",
-    "out_proj",
-    "linear_2",
-    "o_proj",
-    "v_proj"
+    "v_proj",
+    "k_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d078f9ad4f57d6398492cbf74fcfec22ef6899f3cbc6a9a265f8b7f27e2cffe
-size 621143576
+oid sha256:e4eba1d1f6b79d77e9a1c87d7bd24fc279216dd80e221c7123468f1c28870607
+size 29936104

tokenizer_config.json

@@ -44,6 +44,7 @@
     }
   },
   "bos_token": "<s>",
+  "chat_template": "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.USER: <image> {{ messages['question'] }} ASSISTANT: {{ messages['answer'] }}{{eos_token}}",
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ba08ee91fa367aef9023e12eba1e71c794d30577bfd3ed1d898775fd7ec640e
-size 5048
+oid sha256:efb93992f6f82189a888c13c6ec2648a4251642a1b6fe37169bdb644fee48c28
+size 4984