Training in progress, step 12000

config.json

@@ -85,5 +85,6 @@
   "sparse_prediction": false,
   "tie_word_embeddings": true,
   "transformers_version": "5.2.0",
+  "use_cache": false,
   "vocab_size": 256000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e862175bf63a61ccfb607047c8b2e5a53c5597c0684a9332799a87f24c14426
+oid sha256:424ab13ac571d3663cdbd81d45488d59a2f3e393e95f8188d953ce21f82d0656
 size 562584932

tokenizer_config.json

@@ -8,9 +8,8 @@
     "<start_of_turn>",
     "<end_of_turn>"
   ],
-  "is_local": true,
+  "is_local": false,
   "mask_token": "<mask>",
-  "max_length": 128,
   "model_input_names": [
     "input_ids",
     "attention_mask"
@@ -20,9 +19,6 @@
   "padding_side": "right",
   "sep_token": "<eos>",
   "spaces_between_special_tokens": false,
-  "stride": 0,
   "tokenizer_class": "TokenizersBackend",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6cdd8aac9174bf8852e75560cf334c14a5c2d0d634e9195fbaf3235725de9ef
+oid sha256:c96d5274d5076a7d46de60ad155dac7fc31e0a77d145a7466b7e5f3c4a5cab52
 size 5265