Training in progress, step 500

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+.nfs000000038e2e1b8400000002 filter=lfs diff=lfs merge=lfs -text

.nfs000000038e2e1b8400000002

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9b8a5b43dd8d9de9a3ff93b46f59b51e0f503f1bc70951bfb02ea39bc09a63
+size 2682482800

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "tattabio/gLM2_650M",
+  "_name_or_path": "tattabio/gLM2_150M",
   "architectures": [
     "gLM2ForMaskedLM"
   ],
@@ -8,10 +8,10 @@
     "AutoModel": "modeling_glm2.gLM2Model",
     "AutoModelForMaskedLM": "modeling_glm2.gLM2ForMaskedLM"
   },
-  "depth": 33,
-  "dim": 1280,
+  "depth": 30,
+  "dim": 640,
   "ffn_dim_multiplier": null,
-  "heads": 20,
+  "heads": 10,
   "model_type": "gLM2",
   "norm_eps": 1e-05,
   "swiglu_multiple_of": 256,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9b8a5b43dd8d9de9a3ff93b46f59b51e0f503f1bc70951bfb02ea39bc09a63
-size 2682482800
+oid sha256:d51c23a242cdd640054522d294ea271269733ca31b86fcbc629511f4b1ec40b4
+size 609855088

runs/Oct29_18-35-09_torch-flash-large-0-6/events.out.tfevents.1730226910.torch-flash-large-0-6.10810.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92536cd8f68b22a1151ec8e1fa8fae352a7d9052caf9acb61c07a8180547fe3d
+size 6891

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b0a8ed667ee8b35f22ca4883f52af3ea1273c54ad954652c4052132affac051
+oid sha256:c1d0607b0ef32a7fb9356d7e9cea98c6b3f4ff9d058f42339926e1f0132b13a7
 size 5240