End of training

README.md

@@ -1,4 +1,5 @@
 ---
+library_name: transformers
 license: apache-2.0
 base_model: google/flan-t5-small
 tags:
@@ -36,9 +37,9 @@ The following hyperparameters were used during training:
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 10
 
 ### Training results
 
@@ -46,7 +47,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.36.2
-- Pytorch 2.1.2+cu121
-- Datasets 2.16.1
-- Tokenizers 0.15.2
+- Transformers 4.46.1
+- Pytorch 2.5.0+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2e927ea1b19cc324a97b48d48228febb5bbb5c3a8a692c88315b066ddb18447
+oid sha256:9872397413d34b38322526da7648d65c03d9be2759b91a740e4c59757a8828d5
 size 243128252

runs/Nov04_13-56-10_raptor/events.out.tfevents.1730708777.raptor.1485474.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:286a69c9100a992e2d7574d4d4f2919f236f1a6912ffb34f88ee828b76b1a412
-size 42674
+oid sha256:8ba4eafe8cbffa54ea3e9ddb4b2101f9ad789e3dfb8179151199faf257e03bb3
+size 47119

tokenizer.json

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

tokenizer_config.json

@@ -927,7 +927,7 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_ids": 100,
   "model_max_length": 512,