End of training

README.md

@@ -1,11 +1,7 @@
 ---
 library_name: transformers
-license: mit
-base_model: FacebookAI/roberta-large-mnli
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
 model-index:
 - name: pair_function_conservation_gc_roberta
   results: []
@@ -16,10 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # pair_function_conservation_gc_roberta
 
-This model is a fine-tuned version of [FacebookAI/roberta-large-mnli](https://huggingface.co/FacebookAI/roberta-large-mnli) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.4641
-- Accuracy: 0.7861
+This model was trained from scratch on an unknown dataset.
 
 ## Model description
 
@@ -38,24 +31,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 32
-- eval_batch_size: 32
-- seed: 0
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: polynomial
-- num_epochs: 5
-
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 383  | 0.4504          | 0.8057   |
-| 0.5472        | 2.0   | 766  | 0.4365          | 0.8130   |
-| 0.5126        | 3.0   | 1149 | 0.4522          | 0.7856   |
-| 0.4779        | 4.0   | 1532 | 0.4573          | 0.7780   |
-| 0.4779        | 5.0   | 1915 | 0.4641          | 0.7861   |
-
+- lr_scheduler_type: linear
+- num_epochs: 3.0
 
 ### Framework versions
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "FacebookAI/roberta-large-mnli",
+  "_name_or_path": "/content/pair_function_conservation_gc_roberta/checkpoint-1149",
   "_num_labels": 3,
   "architectures": [
     "RobertaForSequenceClassification"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e765b3b7c1995f4f4f588b848d7401cc0ec5f8b7d1e3370db70b0afeb3cf532
+oid sha256:68dcb62af728633487b8da5c997d18f0ea755ff8dc12a27163cb66615ed400a4
 size 1421495416

runs/Dec18_11-22-57_5216bb07b6be/events.out.tfevents.1734522626.5216bb07b6be.1166.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f5ced6b6cc0f33823f2880c54ae9f58c6853fb405396ffba0c863f2e744b17c
+size 7819

runs/Dec18_12-15-24_5216bb07b6be/events.out.tfevents.1734524135.5216bb07b6be.1166.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b2f5fe0e9020f09c3c6b7c4f6994a51461f6b029e33b63e750e8c46b43466fb
+size 10242

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ccd87f650b4fb932c806069dc0f358bb572cd24b9626d744efe91e691a6051a
-size 5368
+oid sha256:e234742a556765ce2afce07a4ea5b6ceef31abdc4fc973cfe4efe6f82bf1e948
+size 5304