Training in progress, step 2500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./results/checkpoint-10000",
+  "_name_or_path": "neeleshg23/draft-mamba-2-1600",
   "architectures": [
     "MambaForCausalLM"
   ],
@@ -24,7 +24,7 @@
   "time_step_min": 0.001,
   "time_step_rank": 100,
   "time_step_scale": 1.0,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.46.2",
   "use_bias": false,
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7b38269647977e0f44263bc88f49af1c7ab50403e0074befb3b1659faab65d5
-size 334235984
+oid sha256:9a5f3700364aa7836e2ef3e15b8d47eef8fc533df9297f97933ed3714451e1ae
+size 167323992

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:740f3b1e9446d357f909219a84d69f2040974d954b81b82be1b89898329552bb
+size 5240