End of training

README.md

@@ -17,12 +17,12 @@ model-index:
       name: samsum
       type: samsum
       config: samsum
-      split: test
+      split: validation
       args: samsum
     metrics:
     - name: Rouge1
       type: rouge
-      value: 48.1912
+      value: 48.5717
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,12 +32,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the samsum dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3757
-- Rouge1: 48.1912
-- Rouge2: 24.2128
-- Rougel: 38.5371
-- Rougelsum: 44.4028
-- Gen Len: 37.2601
+- Loss: 1.3743
+- Rouge1: 48.5717
+- Rouge2: 24.9633
+- Rougel: 39.1532
+- Rougelsum: 45.0174
+- Gen Len: 36.8362
 
 ## Model description
 
@@ -68,9 +68,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
-| 1.4527        | 1.0   | 1842 | 1.3877          | 47.3547 | 23.666  | 37.8589 | 43.9796   | 37.3907 |
-| 1.3395        | 2.0   | 3684 | 1.3770          | 47.5502 | 23.8731 | 38.0121 | 43.8511   | 37.4554 |
-| 1.2926        | 3.0   | 5526 | 1.3757          | 48.1912 | 24.2128 | 38.5371 | 44.4028   | 37.2601 |
+| 1.452         | 1.0   | 1842 | 1.3851          | 48.5682 | 25.1167 | 39.2504 | 45.1912   | 36.8753 |
+| 1.3402        | 2.0   | 3684 | 1.3743          | 48.5717 | 24.9633 | 39.1532 | 45.0174   | 36.8362 |
+| 1.2928        | 3.0   | 5526 | 1.3748          | 48.7401 | 25.0144 | 39.1959 | 45.1242   | 36.9438 |
 
 
 ### Framework versions

generation_config.json

@@ -1,18 +1,12 @@
 {
-  max_length=128,
-    min_length=30,
-    # length_penalty=1.0, 
-    # num_beams=8,
-    max_new_tokens=40,       # max_target_length, 
-    do_sample=True,
-    top_p=0.9,
-    early_stopping=True,
-    bos_token_id=model.config.bos_token_id,
-    decoder_start_token_id=model.config.decoder_start_token_id,
-    no_repeat_ngram_size = 3,
-    eos_token_id = model.generation_config.eos_token_id,
-    pad_token_id = model.generation_config.pad_token_id,
-    forced_bos_token_id = 0,
-    forced_eos_token_id = 2,
-    top_k=0
+  "decoder_start_token_id": 0,
+  "early_stopping": true,
+  "eos_token_id": 1,
+  "length_penalty": 2.0,
+  "max_length": 200,
+  "min_length": 30,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.3"
 }

logs/events.out.tfevents.1720196349.234005ae3c44.359.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3479a6a4adc1f5bd1e18c1ad0c9aec24007a730e109052ab3c36e70f2c495dfa
+size 10286

logs/events.out.tfevents.1720204799.234005ae3c44.359.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e81d8a092ea862e1696b879c9bdbf7a54767c67b3611ec5f08d42399ed3e41
+size 613

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb2a10fcd3020a91b046961eb9a677f2a250570fed8ee8544cba6e461f811eca
+oid sha256:0717b46811c95a40d76c6e45a697546c1f04d16a430de4a45c7d6acb7d076ee8
 size 990345064