End of training

README.md

@@ -5,9 +5,24 @@ tags:
 - generated_from_trainer
 datasets:
 - samsum
+metrics:
+- rouge
 model-index:
 - name: flan-t5-base-samsum
-  results: []
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: samsum
+      type: samsum
+      config: samsum
+      split: test
+      args: samsum
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 48.1912
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,7 +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: nan
+- Loss: 1.3757
+- Rouge1: 48.1912
+- Rouge2: 24.2128
+- Rougel: 38.5371
+- Rougelsum: 44.4028
+- Gen Len: 37.2601
 
 ## Model description
 
@@ -40,28 +60,17 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3
-- mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 0.0           | 0.2606 | 120  | nan             |
-| 0.0           | 0.5212 | 240  | nan             |
-| 0.0           | 0.7818 | 360  | nan             |
-| 0.0           | 1.0423 | 480  | nan             |
-| 0.0           | 1.3029 | 600  | nan             |
-| 0.0           | 1.5635 | 720  | nan             |
-| 0.0           | 1.8241 | 840  | nan             |
-| 0.0           | 2.0847 | 960  | nan             |
-| 0.0           | 2.3453 | 1080 | nan             |
-| 0.0           | 2.6059 | 1200 | nan             |
-| 0.0           | 2.8664 | 1320 | nan             |
+| 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 |
 
 
 ### Framework versions

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "early_stopping": true,
   "eos_token_id": 1,

logs/events.out.tfevents.1720096268.54c460ec6a8d.207.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e7aed4a744ba71011799f258537290ac42d5ff6f14bbe96cee900ca725c061d
+size 6036

logs/events.out.tfevents.1720096352.54c460ec6a8d.207.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bcc7b19a04cefd5a2e6ed012a58865ab392db41e8910aa170a223e7d19554d3
+size 10286

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:197b346658905cda50c1a71fe0eb77a4d79306adaeb5d7a3c0e9208c91022d45
+oid sha256:eb2a10fcd3020a91b046961eb9a677f2a250570fed8ee8544cba6e461f811eca
 size 990345064

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 95,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 95
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "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 sha256:2a60c2ed5495b30eeb6d14c7483c484071c29e57de1d4e69ff70d7abf47fb1c7
-size 5240
+oid sha256:0e5f70f46e4a98aa09aa34c9ff74046b7681d1b2cc1b995cff988ccb929c41b2
+size 5304