Training in progress, step 1000

config.json

@@ -12,7 +12,7 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 40,
-  "n_embd": 120,
+  "n_embd": 144,
   "n_head": 12,
   "n_inner": null,
   "n_layer": 12,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9d29d3ff4284898101c74f6f7ec211e623e9338028a8b0898b5cc489fc0198e
-size 32999512
+oid sha256:255bfb031ecdeb8d4cc108f78df6ecc0e5e0c34d8abba25c3075c85c9a8bd958
+size 41587272

runs/Jun20_19-52-44_255c5f7d24c6/events.out.tfevents.1718913167.255c5f7d24c6.1923.24

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1175fe11e79e6b235b81a4eeabf99ff0038a17ddcb77e916079aed523acd1cab
+size 486323

special_tokens_map.json

@@ -1,5 +1,6 @@
 {
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
   "unk_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -14,6 +14,7 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c6ac8f722c6576e7f46b6ede2ad8685de6db824a7f1f576db325de15b20eb09
+oid sha256:5196153e05dd5a2a287517b11f5d117235a29d9e5c786a9bfbf49f3b1f6f2156
 size 5176