Training in progress, step 4000

config.json

@@ -21,7 +21,7 @@
     "decoder_attention_heads": 16,
     "decoder_ffn_dim": 4096,
     "decoder_layerdrop": 0.0,
-    "decoder_layers": 4,
+    "decoder_layers": 8,
     "decoder_start_token_id": null,
     "diversity_penalty": 0.0,
     "do_sample": false,
@@ -85,7 +85,7 @@
     "typical_p": 1.0,
     "use_bfloat16": false,
     "use_cache": true,
-    "vocab_size": 58511
+    "vocab_size": 50000
   },
   "decoder_start_token_id": 0,
   "encoder": {

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ace973e50f410861c8ad0c4f9224113f10326e6f206d709f603b440bea6175c5
-size 525982496
+oid sha256:9832f6905617187a9e1a22af29a2500dd8f9874f81bffb2e375fd74a7d13002c
+size 625508024

special_tokens_map.json

@@ -1,8 +1,4 @@
 {
-  "additional_special_tokens": [
-    "<s_iitcdip>",
-    "<s_synthdog>"
-  ],
   "bos_token": {
     "content": "<s>",
     "lstrip": false,
@@ -10,13 +6,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "eos_token": {
     "content": "</s>",
     "lstrip": false,
@@ -24,13 +13,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
   "pad_token": {
     "content": "<pad>",
     "lstrip": false,
@@ -38,13 +20,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea77895d9f20554e10daadb3781453707192248ef9cea31fc05c7a8e046011e2
+oid sha256:424036b1b9b5b0f3db62cb298e148add77e78e1c6204a578d2f20ca94fa19b8d
 size 4536