First commit

config.json

@@ -0,0 +1,56 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "transformers_version": "4.9.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32103
+}

events.out.tfevents.1626092365.t1v-n-563c3e20-w-0.115517.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e62c9c496110c0a17a3cef665d54287d2ade2fa1b699d3c695cfd1f638f2796b
+size 9291775

events.out.tfevents.1626344166.t1v-n-563c3e20-w-0.335673.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60781e343ad1f112f8525323e1307fa2388a8663cc191b9247463198b3ed0ab2
+size 735757

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea088f9e44b711f67c7d5b8f3acceee3c84aa1bebae63a73bc2dda271c8be07
+size 241981002

run.sh

@@ -0,0 +1,19 @@
+./run_t5_mlm_flax.py \
+    --output_dir="./" \
+    --model_type="t5" \
+    --model_name_or_path="./" \
+    --config_name="./" \
+    --tokenizer_name="./" \
+    --dataset_name="large_spanish_corpus" \
+    --max_seq_length="512" \
+    --per_device_train_batch_size="16" \
+    --per_device_eval_batch_size="16" \
+    --learning_rate="1e-3" \
+    --weight_decay="0.001" \
+    --warmup_steps="5000" \
+    --overwrite_output_dir \
+    --num_train_epochs="10" \
+    --logging_steps="500" \
+    --save_steps="2500" \
+    --eval_steps="2500" \
+    --preprocessing_num_workers="64"   

run_t5_mlm_flax.py

@@ -0,0 +1 @@
+../transformers/examples/flax/language-modeling/run_t5_mlm_flax.py

t5_tokenizer_model.py

@@ -0,0 +1 @@
+../transformers/examples/flax/language-modeling/t5_tokenizer_model.py