End of training

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ai-forever/rugpt3medium_based_on_gpt2](https://huggingface.co/ai-forever/rugpt3medium_based_on_gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3125
+- Loss: 0.3788
 
 ## Model description
 
@@ -42,7 +42,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000
-- num_epochs: 30
+- num_epochs: 40
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -53,6 +53,7 @@ The following hyperparameters were used during training:
 | 0.858         | 13.95 | 200  | 0.4355          |
 | 0.7697        | 20.93 | 300  | 0.3482          |
 | 0.6343        | 27.91 | 400  | 0.3125          |
+| 0.5486        | 34.88 | 500  | 0.3788          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:414be22f741a1ce18a2a50fd06220ce1122e699d9fe79d0fc19bc7ced2259d9e
+oid sha256:ec537447e6aacbae0ef5403f98d16ae87f0401bab3e5ca8b6072edada1e55aa5
 size 1423517184

runs/Dec22_19-40-42_3eb6c8de2272/events.out.tfevents.1703274051.3eb6c8de2272.747.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f99c426becbcc1b854a61178fc7c5092dd2a16e68b6fd6a812ee91cabdfdb0e0
+size 7032

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03d3628a82b54f48e6868b8c475746728044b98893635fbf9132ad4a3a68aa4c
+oid sha256:0de7fd704906bbd1651828a08d4985b88ae85a99f603e7868d3c32b33f102320
 size 4536