my-great-gpt2-review-model-katie

README.md

@@ -1,6 +1,6 @@
 ---
-base_model: distilgpt2
 license: apache-2.0
+base_model: distilgpt2
 tags:
 - generated_from_trainer
 model-index:
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4783
-- Model Preparation Time: 0.0023
+- Loss: 2.6071
+- Model Preparation Time: 0.0015
 
 ## Model description
 
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.000891
+- learning_rate: 0.002151
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
@@ -47,7 +47,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Model Preparation Time |
 |:-------------:|:------:|:----:|:---------------:|:----------------------:|
-| 3.0411        | 0.3004 | 759  | 2.4783          | 0.0023                 |
+| 3.4206        | 0.3004 | 759  | 2.6071          | 0.0015                 |
 
 
 ### Framework versions

config.json

@@ -7,6 +7,7 @@
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
+  "do_sample": true,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
   "id2label": {
@@ -17,6 +18,7 @@
     "LABEL_0": 0
   },
   "layer_norm_epsilon": 1e-05,
+  "max_length": 50,
   "model_type": "gpt2",
   "n_ctx": 1024,
   "n_embd": 768,

runs/Aug15_13-45-38_d587c0aa5f9f/events.out.tfevents.1723729713.d587c0aa5f9f.6010.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4804a5fa9ad72a9ccbbeef4a1070c0e7aa6fb5ab889edc7ce70286218e4abfdc
+size 425