Training in progress, step 12000

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "diwank/cryptgpt",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -24,8 +25,8 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
-  "use_cache": true,
-  "vocab_size": 50257
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.1",
+  "use_cache": false,
+  "vocab_size": 50272
 }

generation_config.json

@@ -1,5 +1,6 @@
 {
   "_from_model_config": true,
+  "do_sample": true,
   "eos_token_id": 0,
-  "transformers_version": "4.41.2"
+  "transformers_version": "4.41.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76cfc092ee1c80096c730748ee0c8872848e10ebcdb49f50bcbe61e9aeac94b0
-size 497774208
+oid sha256:cadf2263073df1a83ae3739d2f6d5f4ed5990fdbc51f8e023f38b96feb1543e9
+size 326135736

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f120cf34e466e64d61de9de46efaf6bbb3202a297cbff4cd604da30eba0e8285
+size 248921596

special_tokens_map.json

@@ -1,3 +1,16 @@
 {
-  "eos_token": "<|endoftext|>"
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -11,15 +11,15 @@
   },
   "auto_map": {
     "AutoTokenizer": [
-      "tokenizer_utils.CryptGPTTokenizer",
+      "diwank/cryptgpt--tokenizer_utils.CryptGPTTokenizer",
       null
     ]
   },
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
   "max_length": 1024,
   "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
   "stride": 0,
   "tokenizer_class": "CryptGPTTokenizer",
   "truncation_side": "right",

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cebb4e6b1bcf73c6c71fb8e8f0c918de543a933ecee765deeca09ea7adb5daae
+size 7288