Training in progress, step 503

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "w11wo/indo-gpt2-small",
+  "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": 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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2423f34999def54f803d3fd70ca4dfef9e31fe93ecc9dc19c63379785a01081a
+size 497774208

runs/May04_14-40-19_4c72e0278a67/events.out.tfevents.1714833634.4c72e0278a67.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31bb59cd9397099de21ca43475dd4953061c08ec3d4d882597fc10829d6b8fe5
+size 5318

runs/May04_14-46-42_4c72e0278a67/events.out.tfevents.1714834010.4c72e0278a67.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daeca2cdf1dddb9686a3d0fbecaddc52210c8d6dea3f9519556334e17e9d92b9
+size 5317

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5c2c8fd415b9ee242e21d6069bb99a9ba137448a02c097c4722cab9692e8bf1
+size 4920