ninagroot/GPT2-705Mtest

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.4932
+- Loss: 3.5144
 
 ## Model description
 
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.4196        | 0.99  | 45   | 4.4846          |
-| 3.5716        | 2.0   | 91   | 3.7327          |
-| 2.7534        | 2.97  | 135  | 3.4932          |
+| 5.4376        | 0.99  | 45   | 4.6269          |
+| 3.5916        | 2.0   | 91   | 3.7375          |
+| 2.7508        | 2.97  | 135  | 3.5144          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4552a5b5466615ad92a7df8601aeb12b396b0e729bd38657c99ae7ee2b2117a4
+oid sha256:edcdc2e8b934d6e5f57aec20c8665204d854e298d6bf9963a83ebea2ce4d8417
 size 3030220576

runs/Apr10_10-38-32_gcn8.local.snellius.surf.nl/events.out.tfevents.1712738322.gcn8.local.snellius.surf.nl.3761293.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440a46d29657f53eeb0d848fc96ff1a5205e06b8cf676d22a68bd155061a4011
+size 7081

tokenizer_config.json

@@ -13,7 +13,7 @@
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",
-  "model_max_length": 30,
+  "model_max_length": 128,
   "pad_token": "<pad>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebd58b9a0e5a6daadd81f963d70b620afd0fec2098be85f765ad1702c6773750
+oid sha256:67652905ed07950025ae0f17f985e23ba59ec1ae0e4cf668a1d90b4c0fa93ff3
 size 4984