Model save

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
-license: mit
-base_model: gpt2
+license: apache-2.0
+base_model: albert-base-v2
 tags:
 - generated_from_trainer
 model-index:
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # squadsciencemodeling
 
-This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
 
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 5e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -47,11 +47,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 5.0728        | 1.0   | 4000  | nan             |
-| 4.3841        | 2.0   | 8000  | nan             |
-| 3.9124        | 3.0   | 12000 | nan             |
-| 3.7628        | 4.0   | 16000 | nan             |
-| 3.338         | 5.0   | 20000 | nan             |
+| 8.8412        | 1.0   | 2000  | nan             |
+| 8.3313        | 2.0   | 4000  | nan             |
+| 8.5025        | 3.0   | 6000  | nan             |
+| 8.0306        | 4.0   | 8000  | nan             |
+| 8.2097        | 5.0   | 10000 | nan             |
 
 
 ### Framework versions

generation_config.json

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "pad_token_id": 0,
   "transformers_version": "4.46.3"
 }

runs/Dec05_22-57-45_xtaco/events.out.tfevents.1733468268.xtaco.28020.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9ef17816d498222f14a48aebda8b573eadd51618b69079410f7a39a7833f8c0
-size 10581
+oid sha256:be77094acb12ef102d5df5b6876b9ac058e6bba7386e209bad91edcf777b554c
+size 11206