Training in progress, step 50

adapter_config.json

@@ -16,11 +16,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
     "o_proj",
-    "q_proj",
     "k_proj",
+    "up_proj",
+    "v_proj",
+    "q_proj",
     "down_proj",
     "gate_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e96bea56ea6f3915bfe03b9e3656bd65c93a3ea97b18a5775dc5f0e84d2faa4
+oid sha256:c1d26ae4d91ee5406ecdb04754fcb794c49fdbf6bbb41861d8558309f1105dad
 size 42002136

runs/Dec06_11-57-16_18bca800423a/events.out.tfevents.1701864004.18bca800423a.4241.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00992b7756e3cc228180c6072d14a88bb7a02bd5c6454c89dd3c9d65eab8504a
+size 13546

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aca71db67798b119d2c3693b55cd6a103898a7e935aaf7759e9079b3f6bc999
-size 6264
+oid sha256:e3b4ec3761ef4757a95a527eb558426cc30befdddfb2e65ccd9b15755214e1aa
+size 6328

training_config.json

@@ -9,7 +9,9 @@
   "force_fp16": false,
   "from_gptq": false,
   "huggingface_hub_token": null,
-  "deepspeed_stage": 2,
+  "single_gpu": true,
+  "master_port": 9994,
+  "deepspeed_stage": "stage_2",
   "deepspeed_config_path": null,
   "fsdp_strategy": "",
   "fsdp_offload": true,
@@ -76,13 +78,14 @@
   "weight_decay": 0.001,
   "label_smoothing_factor": 0.0,
   "logging_steps": 1,
-  "save_steps": 25,
+  "save_steps": 50,
   "save_total_limit": 1,
   "optim": "paged_adamw_8bit",
   "push_to_hub": true,
   "hub_model_id": "BobaZooba/AntModel-7B-XLLM-Demo-LoRA",
   "hub_private_repo": false,
   "neftune_noise_alpha": null,
+  "project_name": null,
   "report_to_wandb": false,
   "wandb_api_key": null,
   "wandb_project": null,