Training in progress, epoch 1

config.json

@@ -17,6 +17,7 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
+  "pad_token_id": 50256,
   "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 sha256:28b9dcfc0d83d68f419acad5dda1f78703c06e2d7a49901ceffdb3872079c88a
+oid sha256:e7e5426e20f1123d3b83ce7bf976ca42e003ca74fab61e88ef5b0216ee6fd616
 size 497780352

runs/Jul09_09-01-57_sae00531/events.out.tfevents.1720526518.sae00531.84623.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15920b72771094372be8da4a1a4b713d19d36ec29e24a7c4512f8def870cb000
+size 5477

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8093a34493e9f6fb558710603633c4ae2062d27daa7b775ee56252105224ef73
+oid sha256:f13854d0472c3772477a6bc13a7b07be3da5225bd268396215faf434a01e01d8
 size 5176