Upload TFBartForConditionalGeneration

README.md

@@ -1,5 +1,5 @@
 ---
-license: apache-2.0
+license: mit
 tags:
 - generated_from_keras_callback
 model-index:
@@ -12,11 +12,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # bart-example
 
-This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
+This model is a fine-tuned version of [facebook/bart-large-mnli](https://huggingface.co/facebook/bart-large-mnli) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.7877
-- Validation Loss: 2.4972
-- Epoch: 4
+- Train Loss: 2.2557
+- Validation Loss: 2.4455
+- Epoch: 1
 
 ## Model description
 
@@ -42,16 +42,13 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 6.3670     | 3.2462          | 0     |
-| 3.5143     | 2.7551          | 1     |
-| 3.0299     | 2.5620          | 2     |
-| 2.9364     | 2.7830          | 3     |
-| 2.7877     | 2.4972          | 4     |
+| 3.4871     | 2.5716          | 0     |
+| 2.2557     | 2.4455          | 1     |
 
 
 ### Framework versions
 
-- Transformers 4.26.0
-- TensorFlow 2.9.2
-- Datasets 2.9.0
-- Tokenizers 0.13.2
+- Transformers 4.29.2
+- TensorFlow 2.8.0
+- Datasets 2.12.0
+- Tokenizers 0.13.3

config.json

@@ -1,15 +1,15 @@
 {
-  "_name_or_path": "facebook/bart-large",
-  "activation_dropout": 0.1,
+  "_name_or_path": "facebook/bart-large-mnli",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
   "activation_function": "gelu",
-  "add_bias_logits": false,
   "add_final_layer_norm": false,
   "architectures": [
     "BartForConditionalGeneration"
   ],
-  "attention_dropout": 0.1,
+  "attention_dropout": 0.0,
   "bos_token_id": 0,
-  "classif_dropout": 0.1,
+  "classif_dropout": 0.0,
   "classifier_dropout": 0.0,
   "d_model": 1024,
   "decoder_attention_heads": 16,
@@ -18,56 +18,33 @@
   "decoder_layers": 12,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
-  "early_stopping": true,
   "encoder_attention_heads": 16,
   "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
   "encoder_layers": 12,
   "eos_token_id": 2,
-  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
   "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
+    "0": "contradiction",
+    "1": "neutral",
+    "2": "entailment"
   },
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
+    "contradiction": 0,
+    "entailment": 2,
+    "neutral": 1
   },
   "max_position_embeddings": 1024,
   "model_type": "bart",
-  "no_repeat_ngram_size": 3,
   "normalize_before": false,
-  "num_beams": 4,
   "num_hidden_layers": 12,
+  "output_past": false,
   "pad_token_id": 1,
   "scale_embedding": false,
-  "task_specific_params": {
-    "summarization": {
-      "length_penalty": 1.0,
-      "max_length": 128,
-      "min_length": 12,
-      "num_beams": 4
-    },
-    "summarization_cnn": {
-      "length_penalty": 2.0,
-      "max_length": 142,
-      "min_length": 56,
-      "num_beams": 4
-    },
-    "summarization_xsum": {
-      "length_penalty": 1.0,
-      "max_length": 62,
-      "min_length": 11,
-      "num_beams": 6
-    }
-  },
-  "transformers_version": "4.26.0",
+  "transformers_version": "4.29.2",
   "use_cache": true,
   "vocab_size": 50265
 }

generation_config.json

@@ -2,12 +2,8 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "decoder_start_token_id": 2,
-  "early_stopping": true,
   "eos_token_id": 2,
-  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
-  "no_repeat_ngram_size": 3,
-  "num_beams": 4,
   "pad_token_id": 1,
-  "transformers_version": "4.26.0"
+  "transformers_version": "4.29.2"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca865a715fda8a4fb8e5a82eafa49e5eb7274e13f20ca479763ca969d62ae828
-size 1625925476
+oid sha256:48296e9c9faed0c24eca96884c089f555f8efc1b4d19a25be8e44ccdd1deecc8
+size 1625925412