Training in progress, step 500

config.json

@@ -23,6 +23,7 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "num_key_value_heads": 4,
+  "pad_token_id": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e65f89b740d5fc1b17053bf10bfb5697b88c99ebfd1329f7f7f5dba48bf3469
+oid sha256:41b316cc55e9b2f3fd19820073b08e5091e6463c68fd1a56d5195d9a7a126a19
 size 510960712

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 1024,
+    "max_length": 2048,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7841616dbb9991b2dfa72fc8aac885c7593967eddb16a303c8a222ad3a62f58d
+oid sha256:1165650bfd7557316d9924523f2b62c931aee2703a1455def4018ce87a6b423d
 size 5368