Training in progress, step 10

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/opt/tiger/sLLM_sft_llama/output/FC_toolace_500_r1_presft_1.5B/checkpoint-132",
+  "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -19,11 +19,11 @@
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000.0,
-  "sliding_window": null,
+  "sliding_window": 32768,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.50.0.dev0",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f3f7272c4f62f903b3c37acaecf9e9ad3aa6c60889af6714715005289206ead
+oid sha256:931c3db5ee21a47882036f969294e36507b5f3ab3c257c0c4f3a51d9206ca2fd
 size 3087467144

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82fa3cfe463ed10fa91da65c1aa74b5d4f72df7f463db4a129f35d14641a067c
-size 7672
+oid sha256:8710efd089dcd2bd97fcccbea40ac8c0c35b5cd1c88abbbcfc4a06a0879c261f
+size 7736