End of training

README.md

@@ -17,12 +17,12 @@ 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 None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2052
-- Rouge1: 93.6376
-- Rouge2: 85.3021
-- Rougel: 93.6414
-- Rougelsum: 93.7057
-- Gen Len: 11.8085
+- Loss: 0.1995
+- Rouge1: 93.7396
+- Rouge2: 85.7064
+- Rougel: 93.7508
+- Rougelsum: 93.861
+- Gen Len: 11.7872
 
 ## Model description
 
@@ -47,24 +47,27 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 7
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
-| No log        | 1.0   | 30   | 0.4009          | 88.5839 | 75.4069 | 88.0077 | 88.0943   | 11.0638 |
-| No log        | 2.0   | 60   | 0.2684          | 92.3038 | 81.2901 | 92.3283 | 92.4015   | 11.7234 |
-| No log        | 3.0   | 90   | 0.2302          | 93.2819 | 83.9699 | 93.2573 | 93.3585   | 11.7447 |
-| No log        | 4.0   | 120  | 0.2118          | 93.5135 | 84.8987 | 93.4549 | 93.5448   | 11.7660 |
-| No log        | 5.0   | 150  | 0.2059          | 93.7604 | 85.7113 | 93.7514 | 93.8328   | 11.7872 |
-| No log        | 6.0   | 180  | 0.2052          | 93.6376 | 85.3021 | 93.6414 | 93.7057   | 11.8085 |
-| No log        | 7.0   | 210  | 0.2060          | 93.6376 | 85.3021 | 93.6414 | 93.7057   | 11.8085 |
+| No log        | 1.0   | 30   | 0.3947          | 88.6458 | 75.4031 | 88.1675 | 88.2718   | 11.0851 |
+| No log        | 2.0   | 60   | 0.2608          | 92.2792 | 81.347  | 92.3561 | 92.3951   | 11.7234 |
+| No log        | 3.0   | 90   | 0.2242          | 93.0917 | 83.4787 | 93.1643 | 93.1916   | 11.7660 |
+| No log        | 4.0   | 120  | 0.2056          | 93.7531 | 86.045  | 93.8218 | 93.8514   | 11.8298 |
+| No log        | 5.0   | 150  | 0.1995          | 93.7396 | 85.7064 | 93.7508 | 93.861    | 11.7872 |
+| No log        | 6.0   | 180  | 0.2021          | 93.5965 | 85.2921 | 93.6819 | 93.7096   | 11.8298 |
+| No log        | 7.0   | 210  | 0.2089          | 93.5965 | 85.2921 | 93.6819 | 93.7096   | 11.8298 |
+| No log        | 8.0   | 240  | 0.2073          | 93.8289 | 85.7832 | 93.8623 | 93.9475   | 11.8298 |
+| No log        | 9.0   | 270  | 0.2083          | 93.8289 | 85.7832 | 93.8623 | 93.9475   | 11.8298 |
+| No log        | 10.0  | 300  | 0.2087          | 93.8289 | 85.7832 | 93.8623 | 93.9475   | 11.8298 |
 
 
 ### Framework versions
 
-- Transformers 4.35.0
+- Transformers 4.35.2
 - Pytorch 2.1.0+cu118
-- Datasets 2.14.6
-- Tokenizers 0.14.1
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -56,7 +56,7 @@
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.0",
+  "transformers_version": "4.35.2",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -2,5 +2,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.35.0"
+  "transformers_version": "4.35.2"
 }

logs/events.out.tfevents.1700834475.45f586c7d5ae.949.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07b3ec88a37db5bb2bc761e1af315f0e7e5c40bf57c56d94765e7075c96d8c74
+size 10823

logs/events.out.tfevents.1700834754.45f586c7d5ae.949.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011485025f7ac7b17e0dec93e24ed5af2b97df8453838f29ee2c3920d0f3141a
+size 613

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d937d0af9e44b4d45b995554067068632d89cfc4780796a905160c3c4cc37ca
+oid sha256:a087cfd2d0a4f7abf462446420d5f54adab7c04a273012b869140cbd6e07193d
 size 990345064

tokenizer.json

@@ -964,7 +964,8 @@
   "pre_tokenizer": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true
+    "add_prefix_space": true,
+    "prepend_scheme": "always"
   },
   "post_processor": {
     "type": "TemplateProcessing",
@@ -1023,7 +1024,8 @@
   "decoder": {
     "type": "Metaspace",
     "replacement": "▁",
-    "add_prefix_space": true
+    "add_prefix_space": true,
+    "prepend_scheme": "always"
   },
   "model": {
     "type": "Unigram",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e008dbf429606d9a9be31fca5545a9cbfa2603d6c56e6da7c08e243e27d594a
+oid sha256:d421d9df02370b2b2f680163ae8799d67598e42c2c4aed6d5e11518315339a9b
 size 4728