End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 6.4423
+- Loss: 4.6477
 
 ## Model description
 
@@ -42,20 +42,32 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- num_epochs: 8
+- num_epochs: 20
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 0.96  | 3    | 7.7950          |
-| No log        | 1.92  | 6    | 6.9879          |
-| No log        | 2.88  | 9    | 6.6631          |
-| 7.658         | 3.84  | 12   | 6.5423          |
-| 7.658         | 4.8   | 15   | 6.4882          |
-| 7.658         | 5.76  | 18   | 6.4637          |
-| 6.5857        | 6.72  | 21   | 6.4457          |
-| 6.5857        | 7.68  | 24   | 6.4423          |
+| No log        | 0.98  | 6    | 10.0906         |
+| 9.1486        | 1.96  | 12   | 6.7033          |
+| 9.1486        | 2.94  | 18   | 5.8931          |
+| 6.8583        | 3.92  | 24   | 5.6861          |
+| 6.6191        | 4.9   | 30   | 5.6068          |
+| 6.6191        | 5.88  | 36   | 5.5426          |
+| 6.3742        | 6.86  | 42   | 5.4848          |
+| 6.3742        | 8.0   | 49   | 5.3937          |
+| 6.3911        | 8.98  | 55   | 5.3093          |
+| 6.3445        | 9.96  | 61   | 5.2252          |
+| 6.3445        | 10.94 | 67   | 5.1060          |
+| 6.1275        | 11.92 | 73   | 4.9838          |
+| 6.1275        | 12.9  | 79   | 4.8939          |
+| 6.108         | 13.88 | 85   | 4.8286          |
+| 5.9782        | 14.86 | 91   | 4.7518          |
+| 5.9782        | 16.0  | 98   | 4.7024          |
+| 5.9191        | 16.98 | 104  | 4.6739          |
+| 5.869         | 17.96 | 110  | 4.6599          |
+| 5.869         | 18.94 | 116  | 4.6488          |
+| 5.7407        | 19.59 | 120  | 4.6477          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:933699a9b7c2f094e47eeccbaf9a51566ed49e2e27c25012e374b0123bcc1316
+oid sha256:bfa4447b378eec9c913be4daa5273c384c53af848a654bdcee1908a69e8dd35f
 size 497777280

runs/May21_08-27-55_e261ca047b2e/events.out.tfevents.1716280081.e261ca047b2e.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44739e41d7186ecd48bbd01b02aab3888eaa9a7ae90b7d58531d0f02f1805626
+size 16568

runs/May21_09-13-44_e261ca047b2e/events.out.tfevents.1716282828.e261ca047b2e.34.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15703648ceaf6c3b808606d1bbfb5d85614886a86798613c75f0cf7e9181e3f3
+size 17754

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd184e8ac67157d06e0ba504579693b3ef687794176186fc2d9a4a5615154b5
+oid sha256:54bb2bda263ecf9eff76d0435dfea29cce1f553560be1f5a38f4365f73b97087
 size 4920