Training in progress, step 1000

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,
@@ -43,7 +44,8 @@
   "scale_embedding": false,
   "suppress_tokens": [],
   "torch_dtype": "float32",
-  "transformers_version": "4.27.0.dev0",
+  "transformers_version": "4.28.0.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:d060e22395b0c048c29ebd1c7d59425f08175b7bd0dfe9cf624ce8b3e56471d7
+oid sha256:624651956ff56b1d6eccf9160f789300e2f22174684ba2054fed208530b474c8
 size 967099139

runs/Mar17_00-52-51_n878puavw3/1679015527.933811/events.out.tfevents.1679015527.n878puavw3.32.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9442eee0b776d6208c5c8ac6a2c8871e5a8ac84bd6e38816ad56e8bf089ac0f6
+size 6002

runs/Mar17_00-52-51_n878puavw3/events.out.tfevents.1679015527.n878puavw3.32.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4889d4898b47136263991398b37e2f853203577636fa3994daed6315a032b0a0
+size 11273

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2da8dbc2f1770d528cbab2cec741a41526794ae10bd807d9c0189bab3e0bbc48
+oid sha256:37e94127564d19e6351c5ca41f983c1aa1da3ac867e8160f4e388db506d21b80
 size 3695