Training in progress, step 63000

config.json

@@ -18,12 +18,11 @@
   "num_key_value_heads": 2,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.46.3",
+  "transformers_version": "4.44.2",
   "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a46ee29e81ebe150f2c877d032357af107a945fb9cc048c485fe5908d812f48
+oid sha256:d1d92249d972438d5339c3ae18518d688caca76dfcc6a7189a8f2e68193198a5
 size 988097824

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
-size 11421896
+oid sha256:a8506e7111b80c6d8635951a02eab0f4e1a8e4e5772da83846579e97b16f61bf
+size 7031673

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bac36c8264f0ade79631e529a5fb614bade9c72ec9dc29a47356ea666d3237a
-size 5560
+oid sha256:b1b64d9f435b340670b6a0ec323179f76d1f97140adb2785cb0f3c70a384e5b7
+size 5432