End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: slava-medvedev/zelensky-gpt2-v2
+base_model: slava-medvedev/zelensky-gpt2-125m
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zelensky-gpt2-125m
 
-This model is a fine-tuned version of [slava-medvedev/zelensky-gpt2-v2](https://huggingface.co/slava-medvedev/zelensky-gpt2-v2) on the None dataset.
+This model is a fine-tuned version of [slava-medvedev/zelensky-gpt2-125m](https://huggingface.co/slava-medvedev/zelensky-gpt2-125m) on the None dataset.
 
 ## Model description
 
@@ -33,11 +33,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0005
-- train_batch_size: 2
+- train_batch_size: 3
 - eval_batch_size: 20
 - seed: 42
 - gradient_accumulation_steps: 128
-- total_train_batch_size: 256
+- total_train_batch_size: 384
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 1000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "slava-medvedev/zelensky-gpt2-v2",
+  "_name_or_path": "slava-medvedev/zelensky-gpt2-125m",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd868c2043b883addee755c09ba3254435651e9403558298e58c3da3e1c84286
+oid sha256:634215e2779d1ba8171e25055378316c8f119c382f18b56a3c62eea16c9a24a2
 size 497774208

runs/Jan25_15-38-24_1c64b36d1abb/events.out.tfevents.1706197105.1c64b36d1abb.674.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf69c2084469072621b8b7ba1e931866ff70ea22e73ac9ee6fbb1f6186925a73
+size 4862

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a415cd808b2cf27e4244a92abe0ebba0662a1e5dac2f00bc93f234d1ba9df7b6
+oid sha256:53c0a87fefaafd26a0a7b80c221d9c9f087c42fbc83aac1f088f15d9bc0cce9c
 size 4536