ganse/word_wizards_final_t5-small

README.md

@@ -17,7 +17,7 @@ should 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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0079
+- Loss: 0.0000
 - Rouge1: 1.0
 - Rouge2: 1.0
 - Rougel: 1.0
@@ -42,8 +42,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -54,10 +54,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 5    | 3.1320          | 0.0    | 0.0    | 0.0    | 0.0       | 20.0    |
-| No log        | 2.0   | 10   | 0.4823          | 0.8571 | 0.4    | 0.8571 | 0.8571    | 13.0    |
-| No log        | 3.0   | 15   | 0.0376          | 1.0    | 1.0    | 1.0    | 1.0       | 11.0    |
-| No log        | 4.0   | 20   | 0.0079          | 1.0    | 1.0    | 1.0    | 1.0       | 11.0    |
+| No log        | 1.0   | 20   | 0.0000          | 1.0    | 1.0    | 1.0    | 1.0       | 11.0    |
+| No log        | 2.0   | 40   | 0.0000          | 1.0    | 1.0    | 1.0    | 1.0       | 11.0    |
+| No log        | 3.0   | 60   | 0.0000          | 1.0    | 1.0    | 1.0    | 1.0       | 11.0    |
+| No log        | 4.0   | 80   | 0.0000          | 1.0    | 1.0    | 1.0    | 1.0       | 11.0    |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf78485844ddc506560f3a2300a1df7b3e08dbeb98d5c9a80b48a0e4dfefeb18
+oid sha256:0a93942db999c71eab17aedce483ba403156c7aa7aa2ebea8f0680fbfcb5b145
 size 557912620

runs/Dec06_23-59-20_26c4abc7d069/events.out.tfevents.1701907165.26c4abc7d069.27607.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25270c45dd1e1c27219e1f67e21ab241f4a00c42c194043b38cc0d0066b63ef1
+size 7887

tokenizer.json

@@ -2,11 +2,18 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 128,
+    "max_length": 1024,
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 1,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eed8ee15e58f7e8fac2adb7d45030da052a165595fc3531eac8c41a8da9af27c
+oid sha256:12ffdc30787a7a409d110ca14d7724e78101735fc3fccda585633e2b6dedb6b4
 size 4728