Training in progress, step 1

config.json

@@ -12,20 +12,38 @@
     "model_type": "blip_2_qformer"
   },
   "text_config": {
-    "_name_or_path": "facebook/opt-2.7b",
-    "activation_dropout": 0.0,
+    "_name_or_path": "heegyu/kogpt-j-350m",
+    "activation_function": "gelu_new",
     "architectures": [
-      "OPTForCausalLM"
+      "GPTJForCausalLM"
     ],
-    "eos_token_id": 50118,
-    "ffn_dim": 10240,
-    "hidden_size": 2560,
-    "model_type": "opt",
-    "num_attention_heads": 32,
-    "num_hidden_layers": 32,
-    "prefix": "</s>",
-    "torch_dtype": "float16",
-    "word_embed_proj_dim": 2560
+    "attn_pdrop": 0.1,
+    "bos_token_id": 1,
+    "embd_pdrop": 0.1,
+    "eos_token_id": 2,
+    "gradient_checkpointing": false,
+    "initializer_range": 0.02,
+    "layer_norm_epsilon": 1e-05,
+    "model_type": "gptj",
+    "n_embd": 1024,
+    "n_head": 16,
+    "n_inner": null,
+    "n_layer": 20,
+    "n_positions": 1024,
+    "pad_token_id": 0,
+    "resid_pdrop": 0.0,
+    "rotary_dim": 32,
+    "scale_attn_weights": true,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "tie_word_embeddings": false,
+    "tokenizer_class": "GPT2Tokenizer",
+    "torch_dtype": "float32",
+    "unk_token_id": 5,
+    "vocab_size": 51200
   },
   "torch_dtype": "float32",
   "transformers_version": "4.36.2",

tmp-checkpoint-6000/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "Salesforce/blip2-opt-2.7b",
+  "architectures": [
+    "Blip2ForConditionalGeneration"
+  ],
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "model_type": "blip-2",
+  "num_query_tokens": 32,
+  "qformer_config": {
+    "classifier_dropout": null,
+    "model_type": "blip_2_qformer"
+  },
+  "text_config": {
+    "_name_or_path": "facebook/opt-2.7b",
+    "activation_dropout": 0.0,
+    "architectures": [
+      "OPTForCausalLM"
+    ],
+    "eos_token_id": 50118,
+    "ffn_dim": 10240,
+    "hidden_size": 2560,
+    "model_type": "opt",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "prefix": "</s>",
+    "torch_dtype": "float16",
+    "word_embed_proj_dim": 2560
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "use_decoder_only_language_model": true,
+  "vision_config": {
+    "dropout": 0.0,
+    "initializer_factor": 1.0,
+    "model_type": "blip_2_vision_model",
+    "num_channels": 3,
+    "projection_dim": 512
+  }
+}

tmp-checkpoint-6000/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": "4.36.2"
+}

tmp-checkpoint-6000/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c8a8202b3b41c36759d42b4b85d9e338575287bb51a6cb080ff86b2b5bb7d4
+size 4986896152

tmp-checkpoint-6000/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0607aceca704911d20a3ecd4322594460b9e1d94d139bb955a306caae061f311
+size 4982878872

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06b1cb71df64cad1cf9c3cecfb832c96e2f54b9b3a74efd198c25fb735938b71
+oid sha256:4b962e979ddd766add1ea5cafc6ba56b3d5eb1ad10a8a3576320b6048871569e
 size 4664