Training in progress, step 500

config.json

@@ -9,7 +9,6 @@
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
-  "dtype": "float32",
   "eos_token_id": 1,
   "feed_forward_proj": "gated-gelu",
   "initializer_factor": 1.0,
@@ -55,7 +54,8 @@
     }
   },
   "tie_word_embeddings": false,
-  "transformers_version": "4.57.1",
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.3",
   "use_cache": true,
   "vocab_size": 32128
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2a1e05206aa536019a08e22693af00918d9d9877768a367e17833d679dc84fc
+oid sha256:495fa51e204676f1a857a9fc13c4c89f3f5ba9f480b898cebca02add25e6d749
 size 307867048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd87837e22a8f271cacbf58b2cd3e0ada78967260bb0ef73a5dfec5e4651bd69
-size 5905
+oid sha256:ddd59980993f570f2af712e495ef5c7c2a1c6a059094d7d8d17d2f7bee80c930
+size 5368