Training in progress, step 1

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "GitForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 101,
+  "classifier_dropout": null,
+  "eos_token_id": 102,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 1024,
+  "model_type": "git",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "num_image_with_embedding": null,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.1",
+  "use_cache": true,
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-05,
+    "model_type": "git_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 512,
+    "torch_dtype": "float32"
+  },
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48eef7e5f77cd148653f406cd52b958e99bbe7668d3aaca0447eba66fd662c3
+size 706516040

runs/Sep18_15-56-56_LAPTOP-AVJNT38D/events.out.tfevents.1758182246.LAPTOP-AVJNT38D.4508.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86d916fa3d6b48c2bd8ba25d5f609a9ba6851bbfb8c17704cd02bd886e234441
+size 5970

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd554a360b869f1ff679829aeea102192739a5076a236842607f38432a3d463
+size 5368