End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "sberbank-ai/rugpt3small_based_on_gpt2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 2048,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 2048,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 50264
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c19f38b0359b8baed915f6c5e7bc8851ae208a86a3257cc27d9fedfdfc45115d
+size 551317929

runs/Mar13_12-10-03_6f516247768c/1647173408.9640512/events.out.tfevents.1647173408.6f516247768c.60.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73d0f0fc140fb8a7bd916300367d807bb3b59802cc5a2f8d90f551e5ec9c9555
+size 4739

runs/Mar13_12-10-03_6f516247768c/events.out.tfevents.1647173408.6f516247768c.60.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b4f6f4c015b06265aa0b05b6d5ac8a16b1c5431e18349f44a34aaa7b161c32e
+size 3829

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa5b9fb2b3d85467ed44cb6db186a58d2c23356226599f10121234edd85273f7
+size 2991