End of training

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "J001/codeparrot-ds",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -11,7 +11,7 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_ctx": 128,
+  "n_ctx": 256,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b8e2360883554ca06112f1b5079cd55e1401734e4c64e28d4959efb22a91071
+oid sha256:cdb2b3bf6a71886e3131bf043af1f54722396898f26d7bc74c13ff408187002d
 size 509608509

runs/May08_11-43-43_2af24b58c085/1683546376.9184349/events.out.tfevents.1683546376.2af24b58c085.23.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d43abe6e960e4a6cc0a63c494ba993096ab3ba6d15276de2f1c5330061d2953
+size 5826

runs/May08_11-43-43_2af24b58c085/events.out.tfevents.1683546376.2af24b58c085.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1a6fa02c69b3790f7983625fde811b9ab501d0d7c663b48198989c40314e3b8
+size 4577

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 128,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90b04ef0fef9086a6e33f8ed2af7a228b70cc259c428d90fd5d165b27e4ef682
+oid sha256:83861fc1923a588e7e9e54deeb29b33472f446d35807bf13d899fa4812da614a
 size 3579