Training in progress, step 2500

config.json

@@ -11,10 +11,10 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
+  "n_embd": 1280,
+  "n_head": 20,
   "n_inner": null,
-  "n_layer": 12,
+  "n_layer": 36,
   "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 sha256:57d0fbfc85bfaa31bab2d7c15ed0a3debb96090d5a2b64a1c094fea167d1052c
-size 497774208
+oid sha256:84ed619d408eab16225bf5544805c57f71c4641475a66cab5fca85892e29b828
+size 3096165928

runs/Jul10_16-19-34_c273f810eaf5/events.out.tfevents.1752164378.c273f810eaf5.851.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c71b8901c135aed11e438096589d4d40e213d0eb3f2ba5730ff2dbfabe4080
+size 6305

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89a3e1cdcb9885ee8b9d0af8d6202123605ed3892c91c5e7b3bbe5be756195c0
+oid sha256:15587a0db87a68a2780844527c839fa0601790316b4c67087fcb386edebb8637
 size 5432