commit files to HF hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/content/results_16_epoch_1e_3/checkpoint-4005",
+  "_name_or_path": "/content/vsmall_256_epoch_1e_3/checkpoint-420",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -16,7 +16,7 @@
   "n_head": 6,
   "n_inner": null,
   "n_layer": 6,
-  "n_positions": 1024,
+  "n_positions": 256,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec6fb7e21d8dcd22632aeb8e6f448981955291c9c47b0704e023a144fa11987d
-size 121365368
+oid sha256:4d6f4326b673ed0ad7d96c5c40879e2af28d8a514650c14bf8d35280c46aa029
+size 120185720

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 512
+      "Fixed": 256
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

tokenizer_config.json

@@ -13,7 +13,7 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
-  "max_length": 512,
+  "max_length": 256,
   "model_max_length": 1024,
   "pad_to_multiple_of": null,
   "pad_token": "<|endoftext|>",