Training in progress, step 12000

config.json

@@ -1,13 +1,13 @@
 {
-  "_name_or_path": "gpt2-large",
+  "_name_or_path": "diwank/cryptgpt-large",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
+  "bos_token_id": null,
   "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
+  "eos_token_id": 0,
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
@@ -32,8 +32,8 @@
       "max_length": 50
     }
   },
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.41.1",
-  "use_cache": true,
-  "vocab_size": 50257
+  "use_cache": false,
+  "vocab_size": 50272
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 50256,
+  "do_sample": true,
   "eos_token_id": 50256,
   "transformers_version": "4.41.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9daec3d9afb56155d3065913e51636b232be0e1826a9079623ece03c90eff39f
-size 3096165928
+oid sha256:5a7011aea3eef32b3b1351a3131d7acc027eb8c29102986128206cc10dc8cf6e
+size 1676840832

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d22d2872b87e537288a8e15e18d2ccd8d645d3ab1009bd86284a65a377bc278a
+size 53819

special_tokens_map.json

@@ -1,4 +1,16 @@
 {
-  "eos_token": "<|endoftext|>",
-  "pad_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
+  }
 }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60bc90e5a9e53a347011de0287e7199bf5ebdf383b3aef4d86c9bfc0a5909f17
+size 7416