Training in progress, step 286

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "100daggers/reuters-gpt2-text-gen",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:465a5bc9834d9b20145770a46bb03d598ecedd398b501bd33e5cb3f4ff74b733
+oid sha256:53256dd612a9673284d09d625021075f00d9bc6304c6473100224bb06723194d
 size 503128704

runs/Aug22_13-13-29_cycle-gan-2-40gb-0/events.out.tfevents.1724325211.cycle-gan-2-40gb-0.6027.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f5d84f440c49be22aab973d7587f94a85ae33f6e27cde6cd49b18aff6fecabb
+size 11099

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

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 sha256:26856072ad5665e5b25cee14716f63acdca4b9dd1a50ed271a66a5f83226b73d
+oid sha256:4601a3d752b81e244b72521bb9f3e52f5ed44160b466dabee765129dfd69275f
 size 4795