Training in progress, epoch 1

config.json

@@ -14,7 +14,7 @@
   "n_head": 8,
   "n_inner": null,
   "n_layer": 6,
-  "n_positions": 512,
+  "n_positions": 128,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90270d0bba89cc93e19fca75a5c29ff4a7395879f98ff814cb08144ab7466618
-size 326085064
+oid sha256:b0429aff6a87d5e54400cd2f7221691428ebabd40c3b7438990bb152df22dca3
+size 324905416

runs/Feb18_21-16-23_nlp-gpu-02.be.ucsc.edu/events.out.tfevents.1708319785.nlp-gpu-02.be.ucsc.edu.5127.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4244da4b56cc18f1d4cbda94272d173bea790cf6d80c305832961f37f7fb7161
+size 9198

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfb76c210c039c5694724fbf3db04ab980000446a7a23bdf8d6b44d97f070f0b
-size 4664
+oid sha256:c26d52b36a0798e3859134eeabf1bd1679c4db8611bdb476dba1a99c47a3519c
+size 4728