Training in progress, step 2000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "models/smolm-autoreg-bpe-seed_1024/config.json",
+  "_name_or_path": "models/smolm-autoreg-bpe-seed_1024",
   "_remove_final_layer_norm": false,
   "activation_dropout": 0.0,
   "activation_function": "relu",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20aa25f5f372bb1774c8cd4002419cf909fb3d6b6eb581c994869832c46b2e49
+oid sha256:63eabbbf023d5dac67316b47dafe3ddba76cd435755c073a06a06d9d734f975f
 size 33810896

runs/Mar13_11-30-05_phyl-ling-p01.la.utexas.edu/events.out.tfevents.1710347406.phyl-ling-p01.la.utexas.edu.47814.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea569729b66e1de12383b672f2d50192a0baed528cc03cfc887e9e098df4208a
+size 5621

tokenizer.json

@@ -1,7 +1,14 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ca2979c367d6f24a147c57a1eaea8841582db816f4ea59dce9b6e965362d0d7
+oid sha256:ea4019014cf44450be396b1ce069a4e55915908af1bbaedad24225a809555741
 size 5048