Training in progress, epoch 1

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "indobenchmark/indogpt",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "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,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "tokenizer_class": "IndoNLGTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 40005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae5dcd1943d54d58e18da641760f83057e3532cc75798835b1df688e7ecac660
+size 466280064

runs/Oct10_01-26-35_0bc578a07fa4/events.out.tfevents.1728523597.0bc578a07fa4.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2450477fee661638922087d46fc6f9dc8530fcadad3eb2bcf9396cecdae4b40b
+size 6397

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22169c3fd0c221823120e92ed7c9e07fdd5939b25873e8c3f5c18df0c057e224
+size 5304