Training in progress, step 5000

logs/dataset_max_seq_length=128, per_device_train_batch_size=4, run_name=baseline/events.out.tfevents.1726270546.1c1a426a2fee

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f402234f59fefa5582624f5419d97ba1856a84508df5fb4b74e54eba4f7e55
+size 140228

logs/model_max_length=1024, per_device_train_batch_size=4, run_name=baseline/events.out.tfevents.1726257925.1c1a426a2fee

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2866287cc601eabbc59610189c4c858a890517d50e17b2a0ca739373a1d0b51b
-size 1235924
+oid sha256:bf1dbfef66f5d3e8f03d45e537964f47dd70802d4a47f3aae905c5d835a7e48c
+size 1270442

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4234cebc0b5a368d79c0d78dc842dbd7e9a6b306385c7a5ef7147a6f73bffab3
+oid sha256:03ebbbe81388804b25e7bbab10c8cf65069c1f8bc58d1798bf63d99b091ab383
 size 325669528

tokenizer_config.json

@@ -160,7 +160,7 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
-  "model_max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd93a17c27dfd6e35d146010e8c450f0521e0a670e56d8d6f68274703f8faca5
-size 5368
+oid sha256:f9e258d73c52f456f57351069d95e980ab8efbfc8b9e1512dcdc03690a0c3551
+size 5432