Training in progress epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: t5-small
+license: openrail
+base_model: humarin/chatgpt_paraphraser_on_T5_base
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,10 +13,10 @@ probably proofread and complete it, then remove this comment. -->
 
 # codingfaf/paraSci
 
-This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
+This model is a fine-tuned version of [humarin/chatgpt_paraphraser_on_T5_base](https://huggingface.co/humarin/chatgpt_paraphraser_on_T5_base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 3.1310
-- Validation Loss: 2.8794
+- Train Loss: 2.8070
+- Validation Loss: 2.2901
 - Epoch: 0
 
 ## Model description
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 3.1310     | 2.8794          | 0     |
+| 2.8070     | 2.2901          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "humarin/chatgpt_paraphraser_on_T5_base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
+  "d_ff": 3072,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -18,14 +18,20 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 6,
-  "num_heads": 8,
-  "num_layers": 6,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "task_specific_params": {
+    "paraphrase": {
+      "early_stopping": true,
+      "max_length": 128,
+      "num_beams": 5,
+      "prefix": "paraphrase: "
+    },
     "summarization": {
       "early_stopping": true,
       "length_penalty": 2.0,
@@ -54,6 +60,7 @@
       "prefix": "translate English to Romanian: "
     }
   },
+  "torch_dtype": "float32",
   "transformers_version": "4.35.2",
   "use_cache": true,
   "vocab_size": 32128

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b6ee2c9dc208ae1cdc2483a87210f38d3dabe14cb0f24b909337f4ae07b7b15
-size 373902664
+oid sha256:da8606c5013994a4fa7718a152f73daaed5180a56a62a1a935dab830cb6749c3
+size 1089544048

tokenizer_config.json

@@ -930,8 +930,15 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
+  "max_length": 128,
   "model_max_length": 512,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
   "tokenizer_class": "T5Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }