End of training

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.0229
+- Loss: 2.0078
 
 ## Model description
 
@@ -45,8 +45,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 2.2359        | 1.0   | 342  | 2.2158          |
-| 2.0363        | 2.0   | 684  | 2.0229          |
+| 2.2204        | 1.0   | 342  | 2.1990          |
+| 2.0238        | 2.0   | 684  | 2.0078          |
 
 
 ### Framework versions

config.json

@@ -1 +1,46 @@
-{"vocab_size": 97, "d_model": 256, "encoder_layers": 4, "decoder_layers": 4, "attention_heads": 8, "ff_dropout": 0.1, "activation_function": "gelu", "max_position_embeddings": 256, "pad_token_id": 0, "bos_token_id": 1, "eos_token_id": 2, "use_cache": true}
+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_heads": 8,
+  "bos_token_id": 1,
+  "classifier_dropout": 0.0,
+  "d_model": 256,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 4,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 4,
+  "eos_token_id": 2,
+  "ff_dropout": 0.1,
+  "forced_eos_token_id": 2,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 256,
+  "model_type": "bart",
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "vocab_size": 97
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b47c74a1b0595e3636a6513e559a8f5c22f6bed0081d68df426c57bbb10f75c
+oid sha256:ba9d51d065e9054ae4bf7a2fc96364ac469e9ab4fe1b0ca5fbbb000565f69fc6
 size 80573244