Training in progress, step 61000

README.md

@@ -1,8 +1,8 @@
 ---
 library_name: transformers
 tags:
-- generated_from_trainer
 - smallm
+- generated_from_trainer
 model-index:
 - name: smallm_70_rope
   results: []

config.json

@@ -4,10 +4,6 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.1,
-  "auto_map": {
-    "AutoConfig": "config.SmalLmConfig",
-    "AutoModelForCausalLM": "model.SmalLmForCausalLM"
-  },
   "balancing_coef": 0.0001,
   "bos_token_id": 1,
   "embedding_dropout": 0.0,
@@ -43,7 +39,7 @@
   "sliding_window_attention": true,
   "sliding_window_context": 1024,
   "sliding_window_period": 4,
-  "static_residual": true,
+  "static_residual": false,
   "token_experts": 3,
   "torch_dtype": "float32",
   "transformers_version": "4.50.3",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41967e5432db5ed91bc1228a51744d8af764a94e341f801caf2cc8d0b340946
+oid sha256:8ff3677e2a6c68c6a9bc84018c91a9abb1bcf7c14c1b566d1f4d545783476a72
 size 301235464

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae75bb2a8bb196138369db914584406a32731cac3b2572b642609f88b870f3b8
+oid sha256:a964c444482261d405cae313adc306063a7a31a0cff9e89a43e151d806eeee7e
 size 6008