Training in progress, step 14

config.json

@@ -5,7 +5,7 @@
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
+  "bos_token_id": 0,
   "embd_pdrop": 0.1,
   "eos_token_id": "<|endoftext|>",
   "initializer_range": 0.02,
@@ -35,5 +35,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.44.2",
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 52000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a50a7ddd55dc50185a627425831d6f9e8dec7bf49e904104d4087f8a21c468a5
-size 497774208
+oid sha256:a4073e5e6418f781c83bcb67926ff1efe5ab440abe6f0c71f8e3d4e7315efe48
+size 503128704

runs/Sep29_06-30-27_ad5f7ba1455a/events.out.tfevents.1727591432.ad5f7ba1455a.265.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6fb51e0cf89238bc7b61c2807f75fb204a9cdb7679d908a5f00acba9e9626a2
+size 6270

special_tokens_map.json

@@ -1,6 +1,24 @@
 {
-  "bos_token": "<|endoftext|>",
-  "eos_token": "<|endoftext|>",
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": "<|endoftext|>",
-  "unk_token": "<|endoftext|>"
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "50256": {
+    "0": {
       "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93d313b0676316d4c248d7fc7854c5794a32a45ef746e4ea6c546c889c6b962b
+oid sha256:714355fbbe168aeb6f92136b079cad325ff0d6e9a3cac68044b2c644b9cd2e92
 size 5240