Training in progress, epoch 1

config.json

@@ -26,7 +26,7 @@
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.48.3",
   "use_cache": true,
   "vocab_size": 32128

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:473e1f8c9a16420b1fe5be89bcf1395a8418894d414f75217f701fe542089d60
-size 3132668808
+oid sha256:801422a1d9ada974aebcb632e60811bfb3e46af61e0a0f455f0b323a503fc395
+size 1843192656

runs/Feb28_13-01-33_b146ddf74f60/events.out.tfevents.1740747700.b146ddf74f60.1485.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6afc6606ebcaa8b1969586652e86bdf1a0bbbeba7390f6b5e83205c6a141a399
+size 7136

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d4b21a8cc7c0407dafd8ac6215269cd05c8e49a521c3580479b567879526160
-size 2422234
+oid sha256:9527e4cdd9f4988463ea7be22d503e02a228e1b9bfcdb80b14f672201477fcc0
+size 2422499

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e4615ab36dc7925e7da898b65aa5a9018ab93dfe30d143335eecd8aada846d5
+oid sha256:4af14c963ed1ba00140cc74b75aac5357e049d8e04ba89a112440c920eeb9d81
 size 5496