Training in progress, step 500

README.md

@@ -1,15 +1,15 @@
----
-base_model: llava-hf/llava-1.5-7b-hf
-library_name: peft
-license: llama2
-tags:
-- trl
-- sft
-- generated_from_trainer
-model-index:
-- name: llava-1.5-7b-hf-train-bio2
-  results: []
----
+---
+base_model: llava-hf/llava-1.5-7b-hf
+library_name: peft
+license: llama2
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: llava-1.5-7b-hf-train-bio2
+  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. -->
@@ -52,6 +52,6 @@ The following hyperparameters were used during training:
 
 - PEFT 0.12.0
 - Transformers 4.43.2
-- Pytorch 2.3.1+cu118
+- Pytorch 2.2.1+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -1,36 +1,36 @@
-{
-  "alpha_pattern": {},
-  "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,
-  "layer_replication": null,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.0,
-  "megatron_config": null,
-  "megatron_core": "megatron.core",
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 64,
-  "rank_pattern": {},
-  "revision": null,
-  "target_modules": [
-    "k_proj",
-    "fc2up_proj",
-    "v_projfc1",
-    "q_proj",
-    "gate_proj",
-    "down_proj"
-  ],
-  "task_type": null,
-  "use_dora": false,
-  "use_rslora": false
+{
+  "alpha_pattern": {},
+  "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,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_projfc1",
+    "k_proj",
+    "fc2up_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a15e780b65a1ca6f611a43c77406c35f0f7d23923f12e1906c86e6fae7173849
+oid sha256:22574490638dcb4a3a335722f7a8378733ec6197069567c5eb1fc80ccfdfdf2f
 size 406901688

runs/Jul26_04-32-02_ip-10-192-12-151/events.out.tfevents.1721968337.ip-10-192-12-151.8017.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1371ba020ad967f7d1adacb99c70d938d06aa81d995f8d8630dba1b0d1ed0b7c
+size 7959

runs/Jul26_05-28-52_ip-10-192-12-151/events.out.tfevents.1721971749.ip-10-192-12-151.8017.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a6d5bf6dbb4ed40032a7958e768a6c74d106a6c380c98116fbd0426f2f0463
+size 6080

runs/Jul26_05-32-51_ip-10-192-12-151/events.out.tfevents.1721971982.ip-10-192-12-151.8017.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044df83ef2b89bd892a7888928db961645e1a80ceeb02ad34c24daaf7c0be339
+size 10280

special_tokens_map.json

@@ -1,30 +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
-  }
-}
+{
+  "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_config.json

@@ -1,61 +1,61 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "add_prefix_space": null,
-  "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' %} \nUSER: {% else %} \nASSISTANT: {% 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
-}
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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 an user and an artificial intelligence assistant about Science Question Answering. The assistant gives helpful, detailed, and polite answers to the user's questions.\nBased on the image and question, please choose one of the given choices that answer the question.\nGive yourself room to think by extracting the image and question before choosing the choice.\nDon't return the thinking, only return the highest accuracy choice.\nMake sure your answers are as correct as possible.\n{% for tag, content in messages.items() %}\n{% if tag == 'sample_question' %}\nUse the following examples as reference for the ideal answer style.\n{% for message in content %}\n{% if message['role'] == 'user' %} \nExample\nUSER: {% else %}ASSISTANT: {% endif %}\n{% for item in message['content'] %}\n{% if item['type'] == 'text_question' %}\nQuestion: {{ item['question'] }}\n{% elif item['type'] == 'text_choice' %}\nChoices: {{ item['choice'] }}\n{% elif item['type'] == 'text_solution' %}\nSolution: {{ item['solution'] }}\n{% elif item['type'] == 'text_answer' %}\nAnswer: {{ item['answer'] }}{% elif item['type'] == 'image' %}<image>\n{% endif %}\n{% endfor %}\n{% if message['role'] == 'user' %}\n{% else %}\n{{eos_token}}\n{% endif %}{% endfor %}{% endif %}\n\n{% if tag == 'real_question' %}\nNow use the following image and question to choose the choice:\n{% for message in content %}\n{% if message['role'] == 'user' %}USER: {% else %}ASSISTANT: {% endif %}\n{% for item in message['content'] %}\n{% if item['type'] == 'text_question' %}\nQuestion: {{ item['question'] }}\n{% elif item['type'] == 'text_choice' %}\nChoices: {{ item['choice'] }}\n{% elif item['type'] == 'text_solution' %}\nSolution: {{ item['solution'] }}\n{% elif item['type'] == 'text_answer' %}\nAnswer: {{ item['answer'] }}{% elif item['type'] == 'image' %}<image>\n{% endif %}\n{% endfor %}\n{% if message['role'] == 'user' %}\n{% else %}\n{{eos_token}}\n{% endif %}{% endfor %}{% endif %}\n{% 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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1944c9220793c15eef6b8918f0cbd0939f6bd967ed59c3cb34666c87d1e22938
+oid sha256:6e9705325b640d251bcc226e086bcb6e10a8bfdd500e23b4a747cdeb0dfa9850
 size 5496