End of training

README.md

@@ -15,14 +15,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # maximo-t5-chat
 
-This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on an unknown dataset.
+This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.9662
-- Rouge1: 40.75
-- Rouge2: 29.1975
-- Rougel: 37.9379
-- Rougelsum: 38.4814
-- Gen Len: 16.0
+- Loss: 2.2093
+- Rouge1: 27.8954
+- Rouge2: 7.9325
+- Rougel: 27.8954
+- Rougelsum: 27.0723
+- Gen Len: 12.6667
 
 ## Model description
 
@@ -47,26 +47,25 @@ 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: 10
+- num_epochs: 8
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
-| No log        | 1.0   | 2    | 2.3093          | 19.8026 | 2.37    | 17.9508 | 17.9508   | 8.25    |
-| No log        | 2.0   | 4    | 2.1217          | 27.8825 | 7.1408  | 24.4377 | 25.5648   | 15.5    |
-| No log        | 3.0   | 6    | 2.0575          | 43.9982 | 32.2234 | 40.0719 | 40.8556   | 15.75   |
-| No log        | 4.0   | 8    | 2.0250          | 41.0247 | 30.6915 | 39.0215 | 40.4149   | 16.0    |
-| No log        | 5.0   | 10   | 2.0107          | 40.751  | 30.1882 | 36.6149 | 38.1412   | 16.0    |
-| No log        | 6.0   | 12   | 2.0020          | 38.2692 | 27.9512 | 34.5122 | 36.6315   | 16.0    |
-| No log        | 7.0   | 14   | 1.9886          | 41.4727 | 29.7718 | 37.1689 | 37.2678   | 16.0    |
-| No log        | 8.0   | 16   | 1.9752          | 41.4727 | 29.7718 | 37.1689 | 37.2678   | 16.0    |
-| No log        | 9.0   | 18   | 1.9695          | 39.4309 | 29.1975 | 35.6826 | 37.226    | 16.0    |
-| No log        | 10.0  | 20   | 1.9662          | 40.75   | 29.1975 | 37.9379 | 38.4814   | 16.0    |
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
+| No log        | 1.0   | 3    | 2.8591          | 15.4762 | 2.439  | 15.0794 | 15.4762   | 16.1667 |
+| No log        | 2.0   | 6    | 2.5612          | 13.0291 | 2.439  | 12.6323 | 13.0291   | 16.1667 |
+| No log        | 3.0   | 9    | 2.4590          | 14.6825 | 2.439  | 14.2857 | 14.2857   | 10.6667 |
+| No log        | 4.0   | 12   | 2.3716          | 14.6825 | 2.439  | 14.2857 | 14.2857   | 12.0    |
+| No log        | 5.0   | 15   | 2.2986          | 19.4444 | 2.439  | 19.0476 | 19.0476   | 13.0    |
+| No log        | 6.0   | 18   | 2.2474          | 27.1017 | 7.9325 | 27.1017 | 26.2787   | 11.3333 |
+| No log        | 7.0   | 21   | 2.2220          | 27.8954 | 7.9325 | 27.8954 | 27.0723   | 12.6667 |
+| No log        | 8.0   | 24   | 2.2093          | 27.8954 | 7.9325 | 27.8954 | 27.0723   | 12.6667 |
 
 
 ### Framework versions
 
 - Transformers 4.35.2
 - Pytorch 2.1.0+cu118
+- Datasets 2.15.0
 - Tokenizers 0.15.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:602284453f9e86b63e4f436b0becd589cd7398f061253c30e294c7aadb1c7d2a
+oid sha256:41200cec214955e004363b87de4d984852058b6bd738aeb7f24f0dd943b6bc67
 size 307867048

runs/Dec06_08-52-03_7bb9bb6007a1/events.out.tfevents.1701852743.7bb9bb6007a1.626.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2333b33ce80f7f3fc2f10caacbecdcca82634668a3639fa022ec01a642006545
+size 9758

special_tokens_map.json

@@ -101,25 +101,7 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
 }

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 134,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 134
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -930,16 +930,9 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
   "extra_ids": 100,
-  "max_length": 134,
   "model_max_length": 512,
-  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sp_model_kwargs": {},
-  "stride": 0,
   "tokenizer_class": "T5Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c193ab31dda15c1846281b635b2135ef67cda13e731cc9a4cc7a77cd56f15ed9
-size 4792
+oid sha256:acbc58e0ec061e0c46176aaca4d853d3e1fe77ba3d9d25358bb1eca822836e4c
+size 4728