Saving weights and logs of step 11

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.9.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b58c7d33e4ac33d181533f210f8d095d47e64d263252cb570125e8ff48f508ac
+size 6775349

run.sh

@@ -0,0 +1,22 @@
+#!/usr/bin/env bash
+./run_mlm_flax_stream.py \
+    --output_dir="./" \
+    --model_type="roberta" \
+    --config_name="./" \
+    --tokenizer_name="./" \
+    --dataset_name="oscar" \
+    --dataset_config_name="unshuffled_deduplicated_en" \
+    --max_seq_length="128" \
+    --weight_decay="0.01" \
+    --per_device_train_batch_size="2" \
+    --per_device_eval_batch_size="2" \
+    --learning_rate="3e-4" \
+    --warmup_steps="1000" \
+    --overwrite_output_dir \
+    --adam_beta1="0.9" \
+    --adam_beta2="0.98" \
+		--num_train_steps="100" \
+    --num_eval_samples="20" \
+		--logging_steps="10" \
+		--eval_steps="10" \
+    --push_to_hub

run_mlm_flax_stream.py

@@ -0,0 +1 @@
+/home/patrick/transformers/examples/research_projects/jax-projects/dataset-streaming/run_mlm_flax_stream.py