Saving weights and logs of step 1001

events.out.tfevents.1625519728.t1v-n-98937c84-w-0.273849.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9f9ea01402a6c19d6301d33c11a94bc174d8d5c42ca78838ae9f3a0d7112c4f
+size 36746

events.out.tfevents.1625538240.t1v-n-98937c84-w-0.291128.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6119abea838ae418cf6aea5b9d383bbff047bc03a0ea3720bee5330a6dc1a1bc
+size 147343

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424306ea98f9a679c5842bc2691d3534e391dfb03354174121d688ad94dc9a65
+oid sha256:a80a06921f90d26504ed4e0758408585ec09f23b64374dfc4c257e5d766af797
 size 498796983

mc4script.sh

@@ -0,0 +1,20 @@
+./run_mlm_flax_stream.py \
+    --output_dir="${MODEL_DIR}" \
+    --model_type="roberta" \
+    --config_name="${MODEL_DIR}" \
+    --tokenizer_name="${MODEL_DIR}" \
+    --dataset_name="mc4" \
+    --dataset_config_name="sv" \
+    --max_seq_length="128" \
+    --per_device_train_batch_size="128" \
+    --per_device_eval_batch_size="128" \
+    --learning_rate="3e-4" \
+    --warmup_steps="1000" \
+    --overwrite_output_dir \
+    --adam_beta1="0.9" \
+    --adam_beta2="0.98" \
+    --num_train_steps="10000" \
+    --num_eval_samples="5000" \
+    --logging_steps="250" \
+    --eval_steps="1000" \
+    --push_to_hub

oscar_script.sh

@@ -0,0 +1,20 @@
+./run_mlm_flax_stream.py \
+    --output_dir="${MODEL_DIR}" \
+    --model_type="roberta" \
+    --config_name="${MODEL_DIR}" \
+    --tokenizer_name="${MODEL_DIR}" \
+    --dataset_name="oscar" \
+    --dataset_config_name="unshuffled_deduplicated_sv" \
+    --max_seq_length="128" \
+    --per_device_train_batch_size="128" \
+    --per_device_eval_batch_size="128" \
+    --learning_rate="3e-4" \
+    --warmup_steps="1000" \
+    --overwrite_output_dir \
+    --adam_beta1="0.9" \
+    --adam_beta2="0.98" \
+    --num_train_steps="10000" \
+    --num_eval_samples="5000" \
+    --logging_steps="250" \
+    --eval_steps="1000" \
+    --push_to_hub