End of training

README.md

@@ -0,0 +1,71 @@
+---
+license: llama2
+base_model: llava-hf/llava-1.5-7b-hf
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: llava-1.5-7b-hf-ft-mix-vsft
+  results: []
+library_name: peft
+---
+
+<!-- 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-hf-ft-mix-vsft
+
+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.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- _load_in_8bit: False
+- _load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+- load_in_4bit: True
+- load_in_8bit: False
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1.4e-05
+- train_batch_size: 4
+- 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
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.4.0
+- Transformers 4.38.2
+- Pytorch 2.0.0+cu117
+- Datasets 2.20.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "auto_mapping": {
+    "base_model_class": "LlavaForConditionalGeneration",
+    "parent_library": "transformers.models.llava.modeling_llava"
+  },
+  "base_model_name_or_path": "llava-hf/llava-1.5-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "linear_2",
+    "linear_1",
+    "o_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2a9d1f0c5b0c1f62a44b9ca9bc4e889d63440fe63941d3968c25f70c523860
+size 680879440

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<image>": 32000,
+  "<pad>": 32001
+}

runs/Jul24_06-28-44_e2e-101-73/events.out.tfevents.1721802574.e2e-101-73.1357.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee23faaca8c2c689645069f8f34acb3e34cf8a80b0f86260214609f77fb5613
+size 5380

runs/Jul24_06-36-31_e2e-101-73/events.out.tfevents.1721803032.e2e-101-73.1519.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0606feeab8f6539cdc4c26270d8f995858393c86028203464218044068094fe3
+size 5380

runs/Jul24_06-40-39_e2e-101-73/events.out.tfevents.1721803286.e2e-101-73.1645.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4efce6014f06f53e257b9b331e37693e9629f41e74624cca1cf6d4e73f55f4d9
+size 8071

runs/Jul24_07-14-06_e2e-101-73/events.out.tfevents.1721805290.e2e-101-73.1806.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cce952f00848cecf9806dc1dd6f5ecc24aa2bfa0898ec96e9663ce1a9dee09
+size 5380

runs/Jul24_07-18-28_e2e-101-73/events.out.tfevents.1721805549.e2e-101-73.1967.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efbde4021a9e0d4a21fde383449bcd09fe982ee1bcf8a04a434e9a2734918e32
+size 6763

runs/Jul24_07-47-58_e2e-101-73/events.out.tfevents.1721807319.e2e-101-73.2143.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f72ad7c7705d42aa54548985115f253958a66f70dd7a401884c180a8b351e2c
+size 6763

runs/Jul24_08-03-46_e2e-101-73/events.out.tfevents.1721808276.e2e-101-73.2309.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a0f4de9af3fe08f7fc75339314d25356bdf06855fb762ed404b214df1ef9403
+size 6763

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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.                         {% for message in messages %}{% if message['role'] == 'user' %}                        USER: {% else %}ASSISTANT: {% endif %}{% for item in message['content'] %}{% if item['type'] == 'text' %}{{ item['text'] }}{% elif item['type'] == 'image' %}<image>{% endif %}{% endfor %}                        {% if message['role'] == 'user' %} {% else %}{{eos_token}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "LlavaProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a597d2ae6d943177c27f679d598bf9d52f32e092629adee9d130355936a00248
+size 4475