Upload folder using huggingface_hub

EStrain.py

@@ -12,7 +12,7 @@ from huggingface_hub import HfApi, login
 from tqdm import tqdm
 
 logging.basicConfig(
-    filename="training_rueberta_24k.log",
+    filename="rueberta/runs/24k/training_rueberta_24k.log",
     filemode="a",
     level=logging.INFO,
     format="%(asctime)s - %(levelname)s - %(message)s"
@@ -30,7 +30,7 @@ MAX_LEN = 128
 PATIENCE = 2
 NUM_LOG_SAMPLES = 50
 
-OUTPUT_DIR = "/home/laura/rueberta/runs/24k"
+OUTPUT_DIR = "rueberta/runs/24k"
 HF_REPO = "laurabernardy/RueBERTa_24k"
 
 label_list = ["O", "B-ADDR", "I-ADDR"]
@@ -169,7 +169,7 @@ def main():
     log("Script started")
 
     dataset = load_data("/home/laura/rueberta/runs/24k/epstein_190_24k_bio.jsonl")
-    dataset = dataset.train_test_split(test_size=0.028)
+    dataset = dataset.train_test_split(test_size=0.027)
 
     train_dataset = dataset["train"]
     val_dataset = dataset["test"]

epstein_190_24k_bio.jsonl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0b043d2fa0eb37740cc61b0b63c56dc0058e7700664aee1ca1d0592d55743ab
-size 26763675
+oid sha256:cef524b229da3bb1660f32672f4dc76e7ea2bf24ba194f35c085816fa36e5115
+size 27554238

epstein_190_24k_ready.jsonl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e9f1a9bcd00d44d10d9126efe04da4e29f025175520d74d4efe00f7e80e646c
-size 16550178
+oid sha256:8881e3c0e24f8ea5164e95ec28ccb81bd02ae4afb3c9fae6cf47a7714e03e650
+size 16929408

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e3cc85e64478cfe960475b00c3a507854b1081eeb14a2550f795c462ae65c10
+oid sha256:8bd422aa941a38e5b38e3fda5e1c01c4ee4098b3ad9331137c2d3ad6155dd0b3
 size 1112269331