Training in progress, step 48

config.json

@@ -5,7 +5,7 @@
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "dtype": "bfloat16",
+  "dtype": "float32",
   "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",
@@ -49,12 +49,14 @@
   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
   "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 1000000,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
   "sliding_window": null,
   "tie_word_embeddings": true,
-  "transformers_version": "4.57.2",
-  "use_cache": true,
+  "transformers_version": "5.0.0.dev0",
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

generation_config.json

@@ -9,5 +9,5 @@
   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,
-  "transformers_version": "4.57.2"
+  "transformers_version": "5.0.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f83c14483ddc36f7f5097be6520f513bf3d22b5164ee45ea0be68bd7165cd26
-size 1192135096
+oid sha256:9408a0aaf234904f980d70f246b63908e7850fcf753afed37733716623907561
+size 3006565056

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e1ef752efb732108b90145be2dcfaf996547f2719a882e4b531cd50b2a738a
-size 5841
+oid sha256:c73600963318c30da07ca4ec778c1c82ed4c04fa6535715b9f22b9ac5196027d
+size 5201