Training in progress, step 400

config.json

@@ -6,7 +6,7 @@
   "d_ff": 1024,
   "d_kv": 64,
   "d_model": 256,
-  "decoder_start_token_id": 55,
+  "decoder_start_token_id": 59,
   "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": 59
+  "vocab_size": 63
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73924b311faebe436005e07b5bcbacaf07336b24e7c90127d0de9762f2b8a446
-size 29454424
+oid sha256:51dcca0a741371e06cdccbd4cc71bafb9c38f57f715fbb83a05f04580cf6f5c5
+size 29458520

runs/Nov28_13-01-52_d7c5ae20caf1/events.out.tfevents.1701176512.d7c5ae20caf1.3157.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b608f489c8d1e6be25844f20ff062c44d4319bd610178297a63b11e042a4705
+size 4791

tokenizer_config.json

@@ -1,6 +1,6 @@
 {
   "added_tokens_decoder": {
-    "55": {
+    "59": {
       "content": "<s>",
       "lstrip": true,
       "normalized": true,
@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "56": {
+    "60": {
       "content": "</s>",
       "lstrip": true,
       "normalized": true,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "57": {
+    "61": {
       "content": "<unk>",
       "lstrip": true,
       "normalized": true,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "58": {
+    "62": {
       "content": "<pad>",
       "lstrip": true,
       "normalized": true,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5c85c88665e8405b7ec073e5f6c58b51d66afe10e3ed8bf4f7f3cf841348dd8
+oid sha256:dd5116fb0022d5ff5d54fcfb1f4016c85d88cfe185b826f2900fd081fa90cab0
 size 4792

vocab.json

@@ -1 +1 @@
-{"w": 0, "l": 1, ",": 2, "x": 3, "\u00ed": 4, "d": 5, "\u00e9": 6, "g": 7, "\u01eb": 8, "T": 9, "N": 10, "s": 11, ")": 12, "I": 13, "j": 14, "\u0142": 15, "\u0144": 16, " ": 17, "E": 18, "\u00e1": 19, "L": 20, "D": 21, "z": 22, "M": 23, "y": 24, "k": 25, "a": 26, "1": 27, "i": 28, "P": 29, "\u012f": 30, "S": 31, "3": 32, "4": 33, "c": 34, "V": 35, "\u0105": 36, "t": 37, "b": 38, "e": 39, "\u02bc": 40, "n": 41, "O": 42, "\u0301": 43, "h": 44, "m": 45, "R": 46, "G": 47, ";": 48, "(": 49, "2": 50, "F": 51, "\u0119": 52, "\u00f3": 53, "o": 54, "<s>": 55, "</s>": 56, "<unk>": 57, "<pad>": 58}
+{"w": 0, "l": 1, "x": 2, "'": 3, "T": 4, "d": 5, "g": 6, "\u00e9": 7, "\u00f8": 8, "N": 9, "s": 10, "U": 11, ")": 12, "I": 13, "j": 14, " ": 15, "E": 16, "L": 17, "D": 18, "y": 19, "M": 20, "z": 21, "k": 22, "u": 23, "q": 24, "a": 25, "i": 26, "P": 27, "A": 28, "S": 29, "p": 30, "t": 31, "r": 32, "V": 33, "b": 34, "c": 35, "e": 36, "\u00e5": 37, "6": 38, ".": 39, "\u00e6": 40, "n": 41, "+": 42, "O": 43, "J": 44, "C": 45, "h": 46, "v": 47, "R": 48, "G": 49, "-": 50, "f": 51, "9": 52, ";": 53, "(": 54, "3": 55, "F": 56, "m": 57, "o": 58, "<s>": 59, "</s>": 60, "<unk>": 61, "<pad>": 62}