Model save

README.md

@@ -4,8 +4,6 @@ license: mit
 base_model: EleutherAI/gpt-neo-1.3B
 tags:
 - generated_from_trainer
-datasets:
-- Ben10x/MedMentions-MTI881-NER
 metrics:
 - precision
 - recall
@@ -13,26 +11,7 @@ metrics:
 - accuracy
 model-index:
 - name: gpt-medmentions
-  results:
-  - task:
-      name: Token Classification
-      type: token-classification
-    dataset:
-      name: Ben10x/MedMentions-MTI881-NER
-      type: Ben10x/MedMentions-MTI881-NER
-    metrics:
-    - name: Precision
-      type: precision
-      value: 0.44823898474262086
-    - name: Recall
-      type: recall
-      value: 0.546458061712299
-    - name: F1
-      type: f1
-      value: 0.4924993145587718
-    - name: Accuracy
-      type: accuracy
-      value: 0.846457800511509
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,13 +19,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gpt-medmentions
 
-This model is a fine-tuned version of [EleutherAI/gpt-neo-1.3B](https://huggingface.co/EleutherAI/gpt-neo-1.3B) on the Ben10x/MedMentions-MTI881-NER dataset.
+This model is a fine-tuned version of [EleutherAI/gpt-neo-1.3B](https://huggingface.co/EleutherAI/gpt-neo-1.3B) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5086
-- Precision: 0.4482
-- Recall: 0.5465
-- F1: 0.4925
-- Accuracy: 0.8465
+- Loss: 1.1011
+- Precision: 0.4748
+- Recall: 0.5144
+- F1: 0.4938
+- Accuracy: 0.8506
 
 ## Model description
 
@@ -72,16 +51,17 @@ The following hyperparameters were used during training:
 - 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: 5.0
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.5389        | 1.0   | 5834  | 0.5594          | 0.4351    | 0.4355 | 0.4353 | 0.8351   |
-| 0.3762        | 2.0   | 11668 | 0.5086          | 0.4482    | 0.5465 | 0.4925 | 0.8465   |
-| 0.1736        | 3.0   | 17502 | 0.6310          | 0.4591    | 0.5364 | 0.4947 | 0.8487   |
-| 0.0777        | 4.0   | 23336 | 0.9268          | 0.4809    | 0.5195 | 0.4994 | 0.8521   |
-| 0.0394        | 5.0   | 29170 | 1.0743          | 0.4822    | 0.5298 | 0.5049 | 0.8531   |
+| 0.5309        | 1.0   | 5850  | 0.5358          | 0.4123    | 0.4673 | 0.4381 | 0.8330   |
+| 0.3521        | 2.0   | 11700 | 0.5186          | 0.4426    | 0.5341 | 0.4841 | 0.8431   |
+| 0.1695        | 3.0   | 17550 | 0.6351          | 0.4681    | 0.4846 | 0.4762 | 0.8485   |
+| 0.0711        | 4.0   | 23400 | 0.9214          | 0.4716    | 0.5156 | 0.4926 | 0.8498   |
+| 0.0384        | 5.0   | 29250 | 1.1011          | 0.4748    | 0.5144 | 0.4938 | 0.8506   |
 
 
 ### Framework versions

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c81baad810fd1acc36164ab439c5a32b0aef12ca56937259729ae0b7caf378d
+oid sha256:c13c7e7a9d42ced8de5d49456583c47553fc8c66a601a815ccfa04591f418dc4
 size 4993794184

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c5d08fd4c2d74927f48269db20048892effe29c2df2f2f8aa938e5bdd750387
+oid sha256:cf9249629233d92cd6703b4ad3d151ac06c574d57fcc01d87e3ac15e62c2cb6f
 size 269429120