Training in progress, step 2500

config.json

@@ -11,10 +11,10 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 1280,
-  "n_head": 20,
+  "n_embd": 768,
+  "n_head": 12,
   "n_inner": null,
-  "n_layer": 36,
+  "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 sha256:84ed619d408eab16225bf5544805c57f71c4641475a66cab5fca85892e29b828
-size 3096165928
+oid sha256:34a424bf284569639680462bda3e212f0deb8d84c63f01c4df42c36801124d5f
+size 497774208

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c71b8901c135aed11e438096589d4d40e213d0eb3f2ba5730ff2dbfabe4080
-size 6305
+oid sha256:af3e2eb7850f7464191f24965ba668b6f7083d4277557b24095107daca46b9bb
+size 6727

runs/Jul10_16-32-37_c273f810eaf5/events.out.tfevents.1752165159.c273f810eaf5.4919.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbebdac5bcdc615c2e6c52f9b3e84fc8c33eeea024e1f2d9fcab577fdf59ecd4
+size 6304

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15587a0db87a68a2780844527c839fa0601790316b4c67087fcb386edebb8637
+oid sha256:fa75f9c06aa4297b89f0dcbd946877312ad10bfde80a130e198c38fd714ab923
 size 5432