Training in progress, step 1000

config.json

@@ -11,7 +11,7 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_ctx": 72,
+  "n_ctx": 64,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b12ee48b1395a6af09f8819e7d487a1a195bfbbc28186feda22aafde9cbc788
+oid sha256:ae80e43f1a2f673d62e7eb81bbab247626ab4584c4a04f7688f95f0b5eac116d
 size 343500637

runs/Aug24_06-33-29_c8d7fc80bddf/events.out.tfevents.1692858939.c8d7fc80bddf.24.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46cc78b16de91110f7ad24d08957c0c21ce0fbbca479a1263982341170c1a198
+size 4666

tokenizer_config.json

@@ -17,7 +17,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "model_max_length": 72,
+  "model_max_length": 64,
   "pad_token": {
     "__type": "AddedToken",
     "content": "<|endoftext|>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20b20dd1a3641a00bb205f07d9a89065980c24664c45f26c2df61f43defa0a56
+oid sha256:61bf668b546aa52ff6a22b5c98d5b69311c2225a27f7a1c5f0e107b12236c980
 size 3963