Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "ajay141/text-gen",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69be17aad740b1a86fb4d1c58f049d3b5288c5707c8dc10b1a4058f3d9fc8d8d
+oid sha256:524584faf01cf710ecdb3c51d5c1fbf4adeed7a80df34d66bae2f355fccfbf24
 size 503128704

runs/Apr02_04-39-02_223ea75a1d88/events.out.tfevents.1712034419.223ea75a1d88.151.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36457abf8cddcc15b0f2e425e89c49efeae49b347489401c4c9b4a06c00959b4
+size 5843

runs/Apr02_05-20-44_223ea75a1d88/events.out.tfevents.1712035277.223ea75a1d88.15838.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cc5599ee11892fc6d850a786ba69eca583eb5157133b2aca30cd1e8d0b09f26
+size 15593

tokenizer_config.json

@@ -13,8 +13,12 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "max_length": 512,
   "model_max_length": 1024,
   "pad_token": "<|endoftext|>",
+  "stride": 0,
   "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a78f7b006d41dbcd39726d7ce1ea54024333785972032c2b34a111f2a6472dae
+oid sha256:f7cc2b6de521789dfdaefb3189582df61abc1e79ece1ad4002248bc4530ec40a
 size 4920