Training in progress, step 400

added_tokens.json

@@ -1,6 +1,7 @@
 {
-  "</s>": 61,
-  "<pad>": 59,
-  "<s>": 60,
-  "<unk>": 62
+  "<extra_id_0>": 59,
+  "<extra_id_1>": 60,
+  "<extra_id_2>": 61,
+  "<extra_id_3>": 62,
+  "<extra_id_4>": 63
 }

config.json

@@ -6,7 +6,7 @@
   "d_ff": 1024,
   "d_kv": 64,
   "d_model": 256,
-  "decoder_start_token_id": 60,
+  "decoder_start_token_id": 1,
   "dense_act_fn": "relu",
   "dropout_rate": 0.3,
   "eos_token_id": 1,
@@ -25,5 +25,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
   "use_cache": true,
-  "vocab_size": 63
+  "vocab_size": 64
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e57ebc5334252c944c690c8a3ece2589ca23da9eea4e94e7a232c0b17fa2787
-size 29458520
+oid sha256:a4cc95a633bd58044ff80346cbd2dca08ae6d72313331381b41bba924c9cf679
+size 29459544

special_tokens_map.json

@@ -1,4 +1,11 @@
 {
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>"
+  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "59": {
+    "0": {
       "content": "<pad>",
       "lstrip": false,
       "normalized": true,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "60": {
+    "1": {
       "content": "<s>",
       "lstrip": false,
       "normalized": true,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "61": {
+    "2": {
       "content": "</s>",
       "lstrip": false,
       "normalized": true,
@@ -24,16 +24,62 @@
       "single_word": false,
       "special": true
     },
-    "62": {
+    "3": {
       "content": "<unk>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "59": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "60": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "61": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "62": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "63": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
-  "additional_special_tokens": [],
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>"
+  ],
   "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "</s>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7771bc0f941c151adc2c4d888c06d4dcfed1525a00f7274058f08b04d62e32f
+oid sha256:615d6f45778e8106e393dbd8ee5e8b7fdcbec55c7117e809a1b702b881fd3ec5
 size 4728