Training in progress, step 500

.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": "4.27.3",
+  "use_cache": true,
+  "vocab_size": 50264
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccd3fb431cea24b7763e66acb368b6ca3127f4baf6873790f072b41bfbb00618
+size 551313981

runs/Mar26_12-17-18_0347cd8c57d5/1679833069.58219/events.out.tfevents.1679833069.0347cd8c57d5.302.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38b26826d451dbff4b5ae7f89780e04eed90b9337ee585ad3710de29a953bab1
+size 5871

runs/Mar26_12-17-18_0347cd8c57d5/events.out.tfevents.1679833069.0347cd8c57d5.302.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f000eb2905eeba13b7472f964a83e1dd638fa8140888d071b5a55aaf26f0cf47
+size 4638

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ebdae2dc4ebc10ce5a795f419db7a203d66b8b86486d215ec14229ce2740e2
+size 3643