Training in progress, step 100

config.json

@@ -11,7 +11,7 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_ctx": 34,
+  "n_ctx": 38,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
@@ -35,5 +35,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
   "use_cache": true,
-  "vocab_size": 15
+  "vocab_size": 16
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c9f4d6e3ecab2fdfbfb86a7f27fb980883ca3d24aebf86b0c79bc36512df1f5
-size 343430784
+oid sha256:153f4e8466ad7253e841de8cba34c82c97f349e554309d6e7a3898ac8a6f9f25
+size 343433856

runs/Mar13_03-14-01_DESKTOP-C4VDTPF/events.out.tfevents.1710288862.DESKTOP-C4VDTPF.32644.40

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1beef495489425a57ec62ba203b874cba793acb86dab174c2946cf5878d6145d
+size 5685

tokenizer.json

@@ -42,18 +42,19 @@
       "<|endoftext|>": 0,
       "$": 1,
       "+": 2,
-      "0": 3,
-      "1": 4,
-      "2": 5,
-      "3": 6,
-      "4": 7,
-      "5": 8,
-      "6": 9,
-      "7": 10,
-      "8": 11,
-      "9": 12,
-      ";": 13,
-      "=": 14
+      ",": 3,
+      "0": 4,
+      "1": 5,
+      "2": 6,
+      "3": 7,
+      "4": 8,
+      "5": 9,
+      "6": 10,
+      "7": 11,
+      "8": 12,
+      "9": 13,
+      ";": 14,
+      "=": 15
     },
     "merges": []
   }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c87e80dddd0ac51e04f5ae320c42ff29176f700eb334535772159d66b0d1a04d
+oid sha256:715284d5dcdd59669beba2eb04ec8762e6d901155c8dde761a80cd0f6e02b64b
 size 4536