Training in progress, step 200

config.json

@@ -21,7 +21,7 @@
   "pad_token_id": 32000,
   "pretraining_tp": 1,
   "q_bits": 8,
-  "q_scale": 50,
+  "q_scale": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
@@ -31,7 +31,7 @@
   "transformers_version": "4.43.1",
   "use_cache": true,
   "v_bits": 8,
-  "v_scale": 1,
+  "v_scale": 50,
   "vocab_size": 32002,
   "weight_bits": 2
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f607602e3afd6b6d31d5153ba9852f81084a1ceef97b093e1d718ef6dd6dbb
+oid sha256:b8cd60a65a6e7f6b678327653062a7c9dd115699dd24c4a661e0b0479d607f3f
 size 2915408840

runs/Jul24_02-10-29_gpu031/events.out.tfevents.1721801432.gpu031

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aace1c2a1084fdb39b19e008c4bff45b7c7863f49ba46b7f1b0d0c53f989437c
-size 47354
+oid sha256:5fe9dc91643cc90365e9b1db2f57e61db0483b3c6e0cbf22d3dea8a912ef8ed9
+size 51785

runs/Jul24_18-32-17_gpu042/events.out.tfevents.1721860343.gpu042

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d79625a5d48c46763eed2df4cf8139402d7fca4899c65195d420da94baa7b8b2
+size 9374

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97294521004e0d1f68984ac8bc725db31118d8f3df0d6bbbedb0cdf4055921c7
+oid sha256:85afd5732bfff1367df525f298b0e4f4611f8e59dafc2719117f0bf7fb458302
 size 5496