Training in progress, step 396

config.json

@@ -26,7 +26,7 @@
   "scalable_attention": true,
   "tie_word_embeddings": false,
   "tokenizer_class": "T5Tokenizer",
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.51.3",
   "use_cache": true,
   "vocab_size": 256384

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36b035928ab2ce7cd968ec63fef3e9de8fbb543824d5a2791741b47d19732a64
-size 2368210808
+oid sha256:7ca56d7b628e959f018484f09b5181a1397750c960c83e65d6d1669922b8e74b
+size 1259621296

runs/May10_11-36-51_eadfdd2c1a5d/events.out.tfevents.1746877012.eadfdd2c1a5d.19.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbfad931f805eee5c5bda5441466183adb1261251be567f6b19979297a1a91a9
+size 26598

tokenizer_config.json

@@ -2741,10 +2741,14 @@
   "eos_token": "</s>",
   "extra_ids": 300,
   "extra_special_tokens": {},
+  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
+  "stride": 0,
   "tokenizer_class": "T5Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4a2b94e7439d25bb42ca742a3a00a3f512b1424b2410f2d8d507b6c254d2663
+oid sha256:2ec67c2fb8154d2cb382064507ca13b3d6663215a0f3fc090a6941211cf8d9dc
 size 5496