Training in progress, step 500

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "attention_dropout": 0.3,
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.3,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "caption": {
+      "early_stopping": true,
+      "length_penalty": 1.0,
+      "max_length": 64,
+      "num_beams": 4,
+      "prefix": "caption: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 32128
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c727a2f6f12c3c3f5daea53b1bc2730f6f87e690d68b10a08484e27141d163c0
+size 242041896

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68344941eb8e49220ffc32fa7a148f88d1ecfdd7dec5917d76161ba462208260
+size 5304