End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: facebook/bart-base
+base_model: eugenesiow/bart-paraphrase
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
+This model is a fine-tuned version of [eugenesiow/bart-paraphrase](https://huggingface.co/eugenesiow/bart-paraphrase) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3230
+- Loss: 1.2646
 
 ## Model description
 
@@ -49,11 +49,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 3.5447        | 1.0   | 374  | 2.8453          |
-| 2.4051        | 2.0   | 748  | 1.9441          |
-| 1.9409        | 3.0   | 1122 | 1.6404          |
-| 1.7783        | 4.0   | 1496 | 1.4134          |
-| 1.7258        | 5.0   | 1870 | 1.3602          |
+| 3.2858        | 1.0   | 374  | 2.7202          |
+| 2.4028        | 2.0   | 748  | 1.8768          |
+| 1.9304        | 3.0   | 1122 | 1.5375          |
+| 1.5841        | 4.0   | 1496 | 1.3241          |
+| 1.4944        | 5.0   | 1870 | 1.2363          |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/bart-base",
+  "_name_or_path": "eugenesiow/bart-paraphrase",
   "activation_dropout": 0.1,
   "activation_function": "gelu",
   "add_bias_logits": false,
@@ -11,20 +11,19 @@
   "bos_token_id": 0,
   "classif_dropout": 0.1,
   "classifier_dropout": 0.0,
-  "d_model": 768,
-  "decoder_attention_heads": 12,
-  "decoder_ffn_dim": 3072,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
   "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
+  "decoder_layers": 12,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
   "early_stopping": true,
-  "encoder_attention_heads": 12,
-  "encoder_ffn_dim": 3072,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
   "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
+  "encoder_layers": 12,
   "eos_token_id": 2,
-  "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
   "gradient_checkpointing": false,
   "id2label": {
@@ -43,9 +42,8 @@
   "model_type": "bart",
   "no_repeat_ngram_size": 3,
   "normalize_before": false,
-  "normalize_embedding": true,
   "num_beams": 4,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "scale_embedding": false,
   "task_specific_params": {

generation_config.json

@@ -4,7 +4,6 @@
   "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,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328dd1ccb6bb5e4216bf6430dfcdb6e53511f5d755d1cd4250605f1a7f0e6bf1
-size 557912620
+oid sha256:4880c32a236be7c4e61021c8703aec350d901a9b2f76fbabb67ff7e0ec58d1e6
+size 1625426996