Training complete!

config.json

@@ -10,7 +10,6 @@
   "attention_dropout": 0.1,
   "bos_token_id": 0,
   "classif_dropout": 0.0,
-  "classifier_dropout": 0.0,
   "d_model": 1024,
   "decoder_attention_heads": 16,
   "decoder_ffn_dim": 4096,
@@ -50,7 +49,7 @@
   "scale_embedding": true,
   "static_position_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.22.1",
+  "transformers_version": "4.26.1",
   "use_cache": true,
   "vocab_size": 96103
 }

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "forced_eos_token_id": 1,
+  "length_penalty": 0.8,
+  "max_length": 128,
+  "min_length": 32,
+  "num_beams": 8,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.1"
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6c663b237ee0940ac446763d14977812271fbcd69496b9844b0e2b12d8feacf
-size 2283800049
+oid sha256:10af901a17db814026069c58f329d0e8947280abcf2775aaa8ec99d0d2ebbdc3
+size 2283804653

runs/Mar06_05-09-12_339c74aee749/1678080543.9792733/events.out.tfevents.1678080543.339c74aee749.5951.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1a328040829a5176a1b382419399285ddd40cff9bb07d4d3d6ef19d6462733
+size 5658

runs/Mar06_05-09-12_339c74aee749/events.out.tfevents.1678080543.339c74aee749.5951.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a9e1afda720f6b15f6f7d62d347380a97c5643b1634c05c83e2ad24bd981fc6
+size 19485

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8356c7b20897f970f8e5473eb2b1a6d30150568ea28176f9b55acc67121251e
-size 3375
+oid sha256:26de7345d8d620826ca46d0c08b59363913437d10a9e74549bb76867c28d19d5
+size 3451