End of training

config.json

@@ -23,12 +23,6 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 2048
-    }
-  },
   "transformers_version": "4.44.2",
   "use_cache": true,
   "vocab_size": 32000

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30c0887fed90548d21054d3a3824c3a1e9bb62fa7849d224f14fe4cd3a5494a3
-size 3328345304
+oid sha256:4a81c619ae8c0c53793454282f9eb6af56ca013e95a4e4f4926ca31ab38a1af3
+size 3590489392

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 13214687232
+    "total_size": 13476831232
   },
   "weight_map": {
     "denoise_model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
@@ -292,6 +292,7 @@
     "denoise_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "denoise_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "denoise_model.norm.weight": "model-00003-of-00003.safetensors",
-    "embed_tokens.weight": "model-00001-of-00003.safetensors"
+    "embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "lm_head.weight": "model-00003-of-00003.safetensors"
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7103635ce5c20a6f6d01c93cefbc398a78e2de5a61db27adcfac95d8f56714ba
+oid sha256:9a574afd82e6f6ababddfb8d8e5ce772823ff404fa8bb71fa77a6df3cc5f183f
 size 5368