Saving weights and logs of step 10000

.gitattributes

@@ -26,3 +26,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+chemT5_data.csv filter=lfs diff=lfs merge=lfs -text
+chemT5_data.tsv filter=lfs diff=lfs merge=lfs -text

chemT5_data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:790657db4eff6c29407874fc4eb06ecfa134b91f924a44c215a0bf8b556ad307
+size 48054222

chemT5_data.tsv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:790657db4eff6c29407874fc4eb06ecfa134b91f924a44c215a0bf8b556ad307
+size 48054222

config.json

@@ -23,5 +23,5 @@
   "tie_word_embeddings": false,
   "transformers_version": "4.11.3",
   "use_cache": true,
-  "vocab_size": 32003
+  "vocab_size": 32103
 }

dataset-clean.py

@@ -0,0 +1,25 @@
+import numpy as np
+import pandas as pd
+import re
+from t5_tokenizer_model import SentencePieceUnigramTokenizer
+#from pretokenizer import atomwise_tokenizer
+from tqdm import tqdm
+
+
+
+vocab_size = 32_000
+input_sentence_size = None
+
+# Initialize a dataset
+#dataset = load_dataset('csv', data_files='/home/zoez/Chem-T5/train-file.csv',split="train")
+dataset = pd.read_csv('./chemT5_data.csv')#('/home/zoez/Chem-T5/train-file.csv')
+#print(dataset.iloc[0])
+
+dataset=pd.DataFrame(columns=['SMILES'],data=dataset)
+#dataset.drop('Unnamed: 0',1)
+#print(dataset.columns)
+dataset.columns=['SMILES']
+
+
+dataset.fillna('', inplace=True)
+dataset.to_csv('chemT5_data.csv',sep = ' ')

events.out.tfevents.1650698399.toxicgpu.cs.vt.edu.18283.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3ecf146d2472a755a7baf126d63da3ded9b5bee6b34b42c6cf072fa341c006
+size 40

events.out.tfevents.1650698554.toxicgpu.cs.vt.edu.18776.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9680a4a8dc371b6e7c350cb76781f4c373c86ddefcd589b17f70eb3b2a745752
+size 1450993

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d99ed12fc3df890828fc608bde1949bb19fce1d45e4117685d366f0b31787a9
+size 990170015

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "special_tokens_map_file": null, "name_or_path": "./", "tokenizer_class": "T5Tokenizer"}

train_scprit.sh

@@ -6,8 +6,8 @@ python run_t5_mlm_flax.py \
 	--tokenizer_name="./" \
 	--train_file="chemT5_data.csv" \
 	--max_seq_length="256" \
-	--per_device_train_batch_size="16" \
-	--per_device_eval_batch_size="16" \
+	--per_device_train_batch_size="8" \
+	--per_device_eval_batch_size="8" \
 	--adafactor \
 	--learning_rate="0.005" \
 	--weight_decay="0.001" \