Training in progress, epoch 1

config.json

@@ -34,7 +34,7 @@
  "max_length": 50
  }
  },
- "torch_dtype": "float32",
+ "torch_dtype": "float16",
  "transformers_version": "4.36.2",
  "use_cache": false,
  "vocab_size": 50257

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2516a952d42c128c4e32199f7e3c23ba3ae78c4169256f11e7c9f7bfd3e7ebbc
-size 497807706
+oid sha256:7e47f94d6d4d7d87dd83de6fca9b5230d26106b04317016d5da094e73a4e7033
+size 326120926

runs/Dec31_00-17-10_a100-2gpus-spot-cuda12-150gb-1/events.out.tfevents.1703981861.a100-2gpus-spot-cuda12-150gb-1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa3f574d8ccf576f865486addc4857ae6b1df2366a8b3669e1d6fa5675a3facb
+size 7944

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:171c14d31c8b047af99e6dbee673d92bc5f4394b131847fdeb229248a454c8b4
-size 4792
+oid sha256:795462f21a0cb9b0a4e00177812548ba31e9f773eceed34e6a15b107ee3ef680
+size 6200