Training in progress, step 20

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+dynamics.cache/cache.db-wal filter=lfs diff=lfs merge=lfs -text

config.json

@@ -18,13 +18,12 @@
   "num_key_value_heads": 16,
   "pad_token_id": 151645,
   "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.48.3",
-  "use_cache": true,
+  "transformers_version": "4.44.2",
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151648
 }

dynamics.cache/cache.db-wal

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58208589436dfc0f685cfa64442b104ab85df3d6e3e6eebb4cb4c65a04c0fc54
+size 4124152

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b237cf1460baf45c7817ba61afc6f587d69646d50e0fa578d2bdc8c34dfa88c
+oid sha256:60cf87c43c24486b74dd528bbd80c4cac40a642b968459b0859eae39a7c1dd55
 size 927418280

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
-size 11418266
+oid sha256:a12e3ba5d5e0ad173cf7b408ab8534c6be8cbc6a146714e9c7dc8cf2346603b1
+size 7028043

tokenizer_config.json

@@ -35,7 +35,6 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "extra_special_tokens": {},
   "model_max_length": 32768,
   "pad_token": "<|im_end|>",
   "split_special_tokens": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d975e26ddc7589335cf752c69d452b89080b82f995278aa1d84a238d47c9628
-size 5944
+oid sha256:2858c8323ce2a3c2c83bd87fffddb6aacea082be61d1fd7f6c590c1f5311fd12
+size 5816