Saving weights and logs of step 5000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": ".",
+  "_name_or_path": "./",
   "architectures": [
     "RobertaForMaskedLM"
   ],

events.out.tfevents.1640186853.t1v-n-ccbf3e94-w-0.1752357.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39b704dcdc54412f4a6883f964ca3cc45da8651d27f71d251eb2bb04304acb6b
+size 228246

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a993bcaf3ce549644ccbe6e0640cf03169148e4fbf4700be812d6e5a0b11164
+oid sha256:0c0ef99d6b6e1a47ad00474100dd3a3c9c17c8cec41fde77b1252184054f2168
 size 498796983

run_w5.sh

@@ -3,8 +3,8 @@
     --model_type="roberta" \
     --config_name="./" \
     --tokenizer_name="./" \
-    --train_file="/mnt/disks/flaxdisk/corpus/train-shard-0001-of-0001.json" \
-    --validation_file="/mnt/disks/flaxdisk/corpus/validation-shard-0001-of-0001.json" \
+    --train_file="/mnt/disks/flaxdisk/NCC_small/data/train-shard-0001-of-0001.json" \
+    --validation_file="/mnt/disks/flaxdisk/NCC_small/data/validation-shard-0001-of-0001.json" \
     --max_seq_length="128" \
     --weight_decay="0.01" \
     --per_device_train_batch_size="128" \