Training in progress, step 81

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "./nusa-beta-0001",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -11,12 +10,12 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_embd": 384,
+  "n_ctx": 1024,
+  "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
-  "n_layer": 6,
-  "n_positions": 256,
-  "pad_token_id": 50257,
+  "n_layer": 12,
+  "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -26,8 +25,14 @@
   "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": "4.48.3",
+  "transformers_version": "4.51.3",
   "use_cache": true,
   "vocab_size": 50259
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:960fd31ae0e137c8ce5b364ec3e74c9ff8713bb76bac4f341ec75cf102295ea4
-size 120188792
+oid sha256:61cc286347f1650bf0ec80b40bca7a1c3db34b3aca9a0008e3bde7c5c172ddea
+size 497780352

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab64b379250d25034e05ba53e87b722a9eea2515c21283068d9a2572fac1695
+oid sha256:83811d56985b10c6d0c06c8baa2e646d1cf4f7781caeb88e2e79540bc4b776b4
 size 5304