Training in progress, step 500

config.json

@@ -12,6 +12,7 @@
     50257
   ],
   "bos_token_id": 50257,
+  "classifier_proj_size": 256,
   "d_model": 768,
   "decoder_attention_heads": 12,
   "decoder_ffn_dim": 3072,
@@ -45,5 +46,6 @@
   "torch_dtype": "float32",
   "transformers_version": "4.27.0.dev0",
   "use_cache": true,
+  "use_weighted_layer_sum": false,
   "vocab_size": 51865
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e951bf35e3f7c909a18410aede374abca54bc1093db9d5b8997dda42c1f7b4
+oid sha256:c90071d22c858c4e49fc757315217a3b56430861a74ad349caa1029a99f45c17
 size 967102601

runs/Mar08_03-16-22_498b3456f75f/1678245649.4833071/events.out.tfevents.1678245649.498b3456f75f.3260.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cc4fe64e4f5be6eaed01534fa1071ea61fbb1212971cda525f3556c348df5ea
+size 6073

runs/Mar08_03-16-22_498b3456f75f/events.out.tfevents.1678245649.498b3456f75f.3260.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fb5e29fb1a39527bba98ed743a4ea9c1b8cd8877d1e37f611c2bae14f828b46
+size 8264

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77117ef56e9c5c4204fa1ff474693f04a542f6108883732332ac430452ce1990
+oid sha256:e459b65577b01d0a0db20a27ae2be4180a7ad40b2d295039740939d17db7b09d
 size 3707