Model save

README.md

@@ -3,23 +3,11 @@ license: mit
 base_model: gpt2-xl
 tags:
 - generated_from_trainer
-datasets:
-- tyzhu/lmind_hotpot_train300_eval100_v1_recite_qa
 metrics:
 - accuracy
 model-index:
 - name: lmind_hotpot_train300_eval100_v1_recite_qa_gpt2-xl
-  results:
-  - task:
-      name: Causal Language Modeling
-      type: text-generation
-    dataset:
-      name: tyzhu/lmind_hotpot_train300_eval100_v1_recite_qa
-      type: tyzhu/lmind_hotpot_train300_eval100_v1_recite_qa
-    metrics:
-    - name: Accuracy
-      type: accuracy
-      value: 0.6908442503639011
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # lmind_hotpot_train300_eval100_v1_recite_qa_gpt2-xl
 
-This model is a fine-tuned version of [gpt2-xl](https://huggingface.co/gpt2-xl) on the tyzhu/lmind_hotpot_train300_eval100_v1_recite_qa dataset.
+This model is a fine-tuned version of [gpt2-xl](https://huggingface.co/gpt2-xl) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4199
-- Accuracy: 0.6908
+- Loss: 0.4179
+- Accuracy: 0.6924
 
 ## Model description
 
@@ -54,24 +42,23 @@ The following hyperparameters were used during training:
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_ratio: 0.05
+- lr_scheduler_type: constant
 - num_epochs: 10.0
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.9548        | 1.0   | 69   | 1.7231          | 0.5813   |
-| 1.3306        | 2.0   | 138  | 1.2326          | 0.6136   |
-| 0.8853        | 3.0   | 207  | 0.8816          | 0.6421   |
-| 0.5181        | 4.0   | 276  | 0.6444          | 0.6638   |
-| 0.3236        | 5.0   | 345  | 0.5305          | 0.6771   |
-| 0.2371        | 6.0   | 414  | 0.4593          | 0.6848   |
-| 0.1839        | 7.0   | 483  | 0.4385          | 0.6881   |
-| 0.1287        | 8.0   | 552  | 0.4243          | 0.6899   |
-| 0.1241        | 9.0   | 621  | 0.4207          | 0.6905   |
-| 0.1198        | 10.0  | 690  | 0.4199          | 0.6908   |
+| 1.873         | 1.0   | 69   | 1.6160          | 0.5881   |
+| 1.1909        | 2.0   | 138  | 1.1437          | 0.6217   |
+| 0.7606        | 3.0   | 207  | 0.7853          | 0.6513   |
+| 0.4752        | 4.0   | 276  | 0.6152          | 0.6702   |
+| 0.2714        | 5.0   | 345  | 0.5010          | 0.6808   |
+| 0.2079        | 6.0   | 414  | 0.4512          | 0.6866   |
+| 0.1588        | 7.0   | 483  | 0.4343          | 0.6894   |
+| 0.1097        | 8.0   | 552  | 0.4257          | 0.6910   |
+| 0.1026        | 9.0   | 621  | 0.4243          | 0.6916   |
+| 0.096         | 10.0  | 690  | 0.4179          | 0.6924   |
 
 
 ### Framework versions