Training in progress, epoch 1

config.json

@@ -12,13 +12,13 @@
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
-  "n_layer": 6,
+  "n_layer": 1,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
-  "skip_mlp": true,
+  "skip_mlp": false,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:530ae57ee80655b3179d6d33e589862fe71f575b9e9b3c9524b2a9a88aa39a72
-size 214279072
+oid sha256:888a27584dcfcbad87142839d86281521ed414857902881282f3c18846d09920
+size 185894448

runs/Jul01_22-44-39_morpheus/events.out.tfevents.1719854080.morpheus.428151.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d31de4e2a93be4e9f0d87e7b6b9d058121b17dbbf0e7563482917f3bba805e
+size 6631

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d70e5e8bcf0a9922b63a3c7a43421ec844f5a467210a200fa5a5684e502ec19
+oid sha256:d83def51f4abdf458ba669c2a368d07ddabe23ac4da69a5ec558ba10ccd7a870
 size 5112