Training in progress, step 125

config.json

@@ -15,6 +15,7 @@
   "num_attention_heads": 16,
   "num_hidden_layers": 4,
   "num_key_value_heads": 8,
+  "pad_token_id": 2,
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
   "sliding_window": 768,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d910d0d52336fe961812d8ba45a6ff1e9dd5ece1526326e9b473f6dce102cc0
+oid sha256:98f5ae2aad1cdd22c6ee19f0df9ef9f79f4537e1d22d80056d9474550072f877
 size 338197712

special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<pad>",
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -34,15 +34,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 32000,
-      "content": "<pad>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -26,14 +26,6 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32000": {
-      "content": "<pad>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "additional_special_tokens": [],
@@ -45,7 +37,7 @@
   "max_length": 512,
   "model_max_length": 1000000000000000019884624838656,
   "pad_to_multiple_of": null,
-  "pad_token": "<pad>",
+  "pad_token": "</s>",
   "pad_token_type_id": 0,
   "padding_side": "left",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5d7606c01259babb03bc9358268df03c7f18620418c3ccd00fe83e018157d60
+oid sha256:b2229bae4bb325b571e23eafc16b133a7b62c79e3f9994ca8a140e5ed1efc65a
 size 5969