End of training

config.json

@@ -1,6 +1,5 @@
 {
-  "_name_or_path": "distilgpt2",
-  "_num_labels": 1,
+  "_name_or_path": "ai-forever/rugpt3small_based_on_gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -9,21 +8,16 @@
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
-  "id2label": {
-    "0": "LABEL_0"
-  },
+  "gradient_checkpointing": false,
   "initializer_range": 0.02,
-  "label2id": {
-    "LABEL_0": 0
-  },
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_ctx": 1024,
+  "n_ctx": 2048,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
-  "n_layer": 6,
-  "n_positions": 1024,
+  "n_layer": 12,
+  "n_positions": 2048,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -33,14 +27,8 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
   "torch_dtype": "float32",
   "transformers_version": "4.30.2",
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 50264
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36a08c8014b81153d56256b85e2dac3a985edda93b0c8cd81db5c1ec695c0198
-size 327674773
+oid sha256:5f053dfa8e2e38d66ed5ea9d1eb73f23a8f51c8081e70e570e16287b4848e181
+size 500974429

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd3d4073e870942c57acadc77e19cc47ce27beabc5cb84f2cddfc0032d36efad
+oid sha256:11107f34f5f90561d93bd451540ae9b98410beeaf5378c8c5f7b5e4b761b54d1
 size 3899