Training in progress, step 500

config.json

@@ -67,7 +67,20 @@
   "encoder_layerdrop": 0,
   "encoder_layers": 12,
   "eos_token_id": 50257,
-  "forced_decoder_ids": null,
+  "forced_decoder_ids": [
+    [
+      1,
+      50259
+    ],
+    [
+      2,
+      50359
+    ],
+    [
+      3,
+      50363
+    ]
+  ],
   "init_std": 0.02,
   "is_encoder_decoder": true,
   "lang_ids": [
@@ -280,9 +293,96 @@
     220,
     50257
   ],
-  "suppress_tokens": [],
+  "suppress_tokens": [
+    1,
+    2,
+    7,
+    8,
+    9,
+    10,
+    14,
+    25,
+    26,
+    27,
+    28,
+    29,
+    31,
+    58,
+    59,
+    60,
+    61,
+    62,
+    63,
+    90,
+    91,
+    92,
+    93,
+    359,
+    503,
+    522,
+    542,
+    873,
+    893,
+    902,
+    918,
+    922,
+    931,
+    1350,
+    1853,
+    1982,
+    2460,
+    2627,
+    3246,
+    3253,
+    3268,
+    3536,
+    3846,
+    3961,
+    4183,
+    4667,
+    6585,
+    6647,
+    7273,
+    9061,
+    9383,
+    10428,
+    10929,
+    11938,
+    12033,
+    12331,
+    12562,
+    13793,
+    14157,
+    14635,
+    15265,
+    15618,
+    16553,
+    16604,
+    18362,
+    18956,
+    20075,
+    21675,
+    22520,
+    26130,
+    26161,
+    26435,
+    28279,
+    29464,
+    31650,
+    32302,
+    32470,
+    36865,
+    42863,
+    47425,
+    49870,
+    50254,
+    50258,
+    50360,
+    50361,
+    50362
+  ],
   "torch_dtype": "float32",
-  "transformers_version": "4.40.0.dev0",
+  "transformers_version": "4.40.0",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:242896c4fcf01e78992116830d2fba875dfd23020409d6ee125ab43d9dc02997
+oid sha256:6f56e23f3d2a2bbf750825c3cc88324575022dc244bb16de31d0578f0e044c9b
 size 966995080

runs/Apr20_19-39-06_9d0ca28cbc2d/events.out.tfevents.1713641948.9d0ca28cbc2d.1456.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e7493b8f1bb40190b540a24146e4b8f31439b35b6bbb3002cce2eadf30e7486
+size 13331

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e258aba663e55d862a464c592ad2f9213c446896a1f4651a3d42df8267909186
-size 5112
+oid sha256:b74be5217741c74b79b25617164ee7da3acbcf18d03a60136baa869f3d9d1f9f
+size 4667