End of training

README.md

@@ -0,0 +1,48 @@
+---
+license: mit
+base_model: Salesforce/blip2-opt-2.7b-coco
+tags:
+- generated_from_trainer
+model-index:
+- name: BLIP2SeaLLMs-1.5B
+  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. -->
+
+# BLIP2SeaLLMs-1.5B
+
+This model is a fine-tuned version of [Salesforce/blip2-opt-2.7b-coco](https://huggingface.co/Salesforce/blip2-opt-2.7b-coco) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,53 @@
+{
+  "_name_or_path": "Salesforce/blip2-opt-2.7b-coco",
+  "architectures": [
+    "Blip2ForConditionalGeneration"
+  ],
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "model_type": "blip-2",
+  "num_query_tokens": 32,
+  "pad_token_id": 151643,
+  "qformer_config": {
+    "classifier_dropout": null,
+    "model_type": "blip_2_qformer"
+  },
+  "text_config": {
+    "_name_or_path": "SeaLLMs/SeaLLMs-v3-1.5B-Chat",
+    "architectures": [
+      "Qwen2ForCausalLM"
+    ],
+    "bos_token_id": 151643,
+    "eos_token_id": 151643,
+    "hidden_act": "silu",
+    "hidden_size": 1536,
+    "initializer_range": 0.02,
+    "intermediate_size": 8960,
+    "max_position_embeddings": 131072,
+    "max_window_layers": 28,
+    "model_type": "qwen2",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 2,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "sliding_window": 131072,
+    "tie_word_embeddings": true,
+    "torch_dtype": "bfloat16",
+    "use_cache": false,
+    "use_sliding_window": false,
+    "vocab_size": 151936
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_decoder_only_language_model": true,
+  "vision_config": {
+    "dropout": 0.0,
+    "image_size": 364,
+    "initializer_factor": 1.0,
+    "model_type": "blip_2_vision_model",
+    "num_channels": 3,
+    "projection_dim": 512
+  }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 50118,
+  "pad_token_id": 1,
+  "transformers_version": "4.42.4"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1103ac4ce01126b930568f794be1d73e3f84cf20297fd544eac21722a3507a
+size 4998048696

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5cfdd121611941eb8e4e67bb694396ae2172c431921e77deab4589103659f3c
+size 2461061832

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec5be36593e7cbfc778ab986d123d40811f9d98e70775c36402639db01d4ae14
+size 5176