Training in progress, step 25

adapter_config.json

@@ -3,6 +3,8 @@
   "auto_mapping": null,
   "base_model_name_or_path": "Xenova/tiny-random-Phi3ForCausalLM",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": null,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,6 +13,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 64,
+  "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,9 +23,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "o_proj",
     "gate_up_proj",
+    "down_proj",
     "qkv_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e923fffc9655f7a2529b41b2414328f95ddde5f29d77e95e03507ff3891c6568
+oid sha256:246e5d1c15d6cc4b227a512b37b8740699724f243274426193b05ff884aea28a
 size 116744

config.json

@@ -26,7 +26,7 @@
   "sliding_window": 2047,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.46.0",
+  "transformers_version": "4.46.3",
   "use_cache": false,
   "vocab_size": 32064
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:203ffc7ed7401780b8899cd840321622489a036cc0090147a22c0a9ca7943661
-size 6776
+oid sha256:803909d5d04cae104c450caa1cb505b30438710d0726d7ae7577afd9b8c7cc2a
+size 6840