Training in progress, epoch 1

config.json

@@ -0,0 +1,92 @@
+{
+  "architectures": [
+    "VEDM"
+  ],
+  "decoder": {
+    "_name_or_path": "swadhindas324/Mistral-SYDNEY",
+    "add_cross_attention": true,
+    "architectures": [
+      "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 480,
+    "chunk_size_feed_forward": 0,
+    "dtype": "float32",
+    "eos_token_id": 481,
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 45,
+    "model_type": "mistral",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "num_key_value_heads": 4,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 483,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    },
+    "sliding_window": 4096,
+    "tie_word_embeddings": false,
+    "type_vocab_size": 1,
+    "use_cache": false,
+    "vocab_size": 484
+  },
+  "decoder_start_token_id": 480,
+  "dtype": "float32",
+  "encoder": {
+    "_name_or_path": "swadhindas324/convnext-vit",
+    "add_cross_attention": false,
+    "architectures": [
+      "ConvNext_Backbone"
+    ],
+    "chunk_size_feed_forward": 0,
+    "dropout_rate": 0.1,
+    "dtype": "float32",
+    "embed_dim": 1536,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "mlp_dim": 3072,
+    "model_type": "convnext_vit",
+    "num_heads": 8,
+    "num_layers": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 49,
+    "problem_type": null,
+    "return_dict": true
+  },
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 483,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.12.1",
+  "use_cache": false,
+  "vocab_size": 484
+}

generation_config.json

@@ -0,0 +1,39 @@
+{
+  "_from_model_config": false,
+  "assistant_confidence_threshold": 0.4,
+  "assistant_lookbehind": 10,
+  "bos_token_id": 480,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": true,
+  "encoder_no_repeat_ngram_size": 0,
+  "encoder_repetition_penalty": 1.0,
+  "eos_token_id": 481,
+  "epsilon_cutoff": 0.0,
+  "eta_cutoff": 0.0,
+  "length_penalty": 2.0,
+  "max_length": 40,
+  "max_new_tokens": 40,
+  "min_length": 0,
+  "model_max_length": 40,
+  "no_repeat_ngram_size": 3,
+  "num_assistant_tokens": 20,
+  "num_assistant_tokens_schedule": "constant",
+  "num_beam_groups": 1,
+  "num_beams": 5,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": 483,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "target_lookbehind": 10,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.12.1",
+  "typical_p": 1.0,
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fc79e82721e41f7b7c3df74a921b8b012d5d6ceb43bae1ed4ef3027b6f39a0e
+size 1312025496

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cb63a338ce9c2d37a6101c2674fcb79c536d9d124b457dbbdafb33f7ee7150d
+size 5393