Training in progress epoch 0

README.md

@@ -15,14 +15,14 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.5428
-- Validation Loss: 3.5532
-- Train Rouge1: 26.3837
-- Train Rouge2: 9.2192
-- Train Rougel: 21.8441
-- Train Rougelsum: 21.7351
-- Train Gen Len: 20.0
-- Epoch: 5
+- Train Loss: 3.9877
+- Validation Loss: 3.5287
+- Train Rouge1: 32.1820
+- Train Rouge2: 9.3543
+- Train Rougel: 22.3531
+- Train Rougelsum: 25.9513
+- Train Gen Len: 52.0625
+- Epoch: 0
 
 ## Model description
 
@@ -48,12 +48,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Train Rouge1 | Train Rouge2 | Train Rougel | Train Rougelsum | Train Gen Len | Epoch |
 |:----------:|:---------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:-----:|
-| 3.9333     | 3.5188          | 26.6086      | 6.7680       | 20.7580      | 20.5472         | 20.0          | 0     |
-| 3.3063     | 3.5640          | 27.2760      | 6.7716       | 21.4322      | 20.8327         | 20.0          | 1     |
-| 3.0764     | 3.5048          | 27.4389      | 7.4962       | 21.7549      | 21.5366         | 20.0          | 2     |
-| 2.8770     | 3.5305          | 26.4536      | 8.0238       | 21.3939      | 21.0272         | 20.0          | 3     |
-| 2.6977     | 3.5499          | 27.1909      | 9.8630       | 22.4824      | 22.2501         | 20.0          | 4     |
-| 2.5428     | 3.5532          | 26.3837      | 9.2192       | 21.8441      | 21.7351         | 20.0          | 5     |
+| 3.9877     | 3.5287          | 32.1820      | 9.3543       | 22.3531      | 25.9513         | 52.0625       | 0     |
 
 
 ### Framework versions

checkpoint/extra_data.pickle

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:905eed494bc22129f765ac78b4be18e82fc28c1f5982a6c9e9485acb0bb875d2
+oid sha256:e7d83bb1e267833d00dd05d467facf7bb0eab45df7c74dc8de85cdb7a72066d2
 size 1115383533

checkpoint/weights.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa1d48069c62c85699ceffa40b09d959fef96068f07d641f2717ccf90ab6b17
+oid sha256:0af9614bc39d0d557c4e0e2d75b2f8c5a21dec1dd3137983cd8ba273c6f98981
 size 558172300

config.json

@@ -7,7 +7,7 @@
   "architectures": [
     "BartForConditionalGeneration"
   ],
-  "attention_dropout": 0.1,
+  "attention_dropout": 0.3,
   "bos_token_id": 0,
   "classif_dropout": 0.1,
   "classifier_dropout": 0.0,

generation_config.json

@@ -2,12 +2,16 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "decoder_start_token_id": 2,
+  "do_sample": true,
   "early_stopping": true,
   "eos_token_id": 2,
   "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
+  "length_penalty": 3,
+  "max_new_tokens": 60,
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,
+  "temperature": 0.5,
   "transformers_version": "4.35.2"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aa1d48069c62c85699ceffa40b09d959fef96068f07d641f2717ccf90ab6b17
+oid sha256:0af9614bc39d0d557c4e0e2d75b2f8c5a21dec1dd3137983cd8ba273c6f98981
 size 558172300