Training in progress, step 100000

blimp_results.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:627daa68f0090f69398f935cf39749a222c1f53b0797082f84a2ba3340856385
-size 80217582
+oid sha256:155e95079e6843f30888c6a5282ee97f22589ed8f19e8b40084fd0a43b07684c
+size 80216132

config.json

@@ -10,10 +10,10 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": 3072,
-  "n_layer": 12,
+  "n_embd": 512,
+  "n_head": 8,
+  "n_inner": 2048,
+  "n_layer": 8,
   "n_positions": 256,
   "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:f76bc5cb209442139c67ecac49c620006083455f63a2248414e85b2a64bbd108
-size 390177408
+oid sha256:45b8ee841a5ba6565c3b7951bc2ea21d223f2de7b42897642a701e420133a5cc
+size 134182632

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ae0dde72c52f7e1e0ff9bbc8aac95f1da19222bc12c580df46c08d305ad1f34
+oid sha256:4bdb9bb7a47c8d79dae8b6e300ed84f1e99318dafb96dc9dbd2c7137c0067d4e
 size 5368