Training in progress, step 2408

config.json

@@ -16,12 +16,12 @@
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 8,
   "num_key_value_heads": 12,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 100000.0,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.48.0",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3114e08de9d64e190989cd8aa3ac2c0a55c2a1e8a79def84c4463811a468ca87
-size 656964248
+oid sha256:861ac8d433c4a8d43e8a5fb1b41d4d453c60dde34d0149ee67ea5d360b99cd34
+size 826798720

runs/Jan16_11-25-23_81d9b8b5d266/events.out.tfevents.1737026742.81d9b8b5d266.25767.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9ec804c0d66212e7a98efcc9a30bb38cce45ad04abcb51620be0da880d01514
+size 6526

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:025e2621120e83cc33d71bb1e585461898928e831529528f39307f75e68a4ac9
+oid sha256:60defe6747720a571945cab5c53328fb39158300e724db385a8cbfd9f23ff822
 size 5368