Training in progress, step 5000

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "cahya/gpt2-small-indonesian-522M",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50257,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50258,
+  "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": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50259
+}

events.out.tfevents.1702425173.09507d519555.234.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c98b95ef1f06b15aa234529dc5945ff2ccc279733f4409e828befb7deedbc11d
+size 4487

events.out.tfevents.1702425199.09507d519555.234.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:934215e0eb4c2fccbc58e04cb61cf6bafc368c36efe36a4aba2ac6660c5928bf
+size 4486

events.out.tfevents.1702425245.09507d519555.234.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:932131da0f4e157b94f3df998d54c81b6d3658309e1ff4d3ad4d8880bcd67f6b
+size 4909

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78769ecd8f2c24cd7cd001c81b986a535e0da2813e43dd64707ac0ae1d54fc05
+size 497780352

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d0396cd34a95e762efe554f240b33a4b5cf21c70eb2bf95710818253b069bad
+size 4536