Training in progress, step 500

config.json

@@ -12,10 +12,10 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 40,
-  "n_embd": 120,
+  "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
-  "n_layer": 2,
+  "n_layer": 12,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa9b996eb6022a3c143cbd9e257b999cf7035c4d82b785fa4faa89ba3f591194
-size 26013408
+oid sha256:ebf8d766e7331b31e7f1774546464fa043a718456d4d7ec3ab0a9ae5de6213eb
+size 497774208

runs/Jun20_16-19-19_24ff73fd10b7/events.out.tfevents.1718900383.24ff73fd10b7.189.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8564efc779faa8b19e157c290e3b30328ed78e647810055ade22e87345d682a
+size 15611

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db1d2cfa7ced5c717f7cf0587d741c5bb1bdff6b5431560f604c96015a88010c
+oid sha256:682a56352c7b01300d0081ff2c05cd152164baba4a29fbcc9781aca829822e52
 size 5176