Training in progress, step 500

config.json

@@ -41,7 +41,7 @@
   "sep_token_id": 50282,
   "sparse_pred_ignore_index": -100,
   "sparse_prediction": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.48.0",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.2",
   "vocab_size": 50368
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a430b124103927af1719aecb3ea23e8ad3e78f71f2355a6466f0ebb89480690a
-size 299227116
+oid sha256:1edbcb49e6a6fa17267a4b7e5cdce0da1d95473344e68e80952ad4be4e3993d8
+size 598439808

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 8064,
+    "strategy": "OnlySecond",
+    "stride": 64
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 8064
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 50283,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -937,7 +937,7 @@
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 8192,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "tokenizer_class": "PreTrainedTokenizerFast",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:387c45d087fc609901b5070fd23a2ffda3140752d8e4acb40504cbdeb0bbfec1
-size 5368
+oid sha256:131103b2ce0e8df42c0edbe181a6e65118b409a9c3ca8550d7cd2fb5419641db
+size 5304