Model save

README.md

@@ -16,7 +16,7 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/nlp-xiaobo/huggingface/runs/6m5wzyco)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/nlp-xiaobo/huggingface/runs/fterg85h)
 # Llama-3-8b-sft-qlora
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
@@ -58,6 +58,6 @@ The following hyperparameters were used during training:
 
 - PEFT 0.11.1
 - Transformers 4.42.2
-- Pytorch 2.3.1+cu121
+- Pytorch 2.0.1+cu117
 - Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "k_proj",
-    "q_proj",
     "up_proj",
     "gate_proj",
     "v_proj",
-    "down_proj"
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

all_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 1.1104476526052114e+19,
     "train_loss": 0.0,
-    "train_runtime": 10.0721,
+    "train_runtime": 6.7946,
     "train_samples": 207864,
-    "train_samples_per_second": 11888.555,
-    "train_steps_per_second": 1486.082
+    "train_samples_per_second": 17623.245,
+    "train_steps_per_second": 2202.924
 }

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 1.1104476526052114e+19,
     "train_loss": 0.0,
-    "train_runtime": 10.0721,
+    "train_runtime": 6.7946,
     "train_samples": 207864,
-    "train_samples_per_second": 11888.555,
-    "train_steps_per_second": 1486.082
+    "train_samples_per_second": 17623.245,
+    "train_steps_per_second": 2202.924
 }

trainer_state.json

@@ -20971,9 +20971,9 @@
       "step": 14968,
       "total_flos": 1.1104476526052114e+19,
       "train_loss": 0.0,
-      "train_runtime": 10.0721,
-      "train_samples_per_second": 11888.555,
-      "train_steps_per_second": 1486.082
+      "train_runtime": 6.7946,
+      "train_samples_per_second": 17623.245,
+      "train_steps_per_second": 2202.924
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2f5067f1985f081dd8a0167604545d06bd0d9f901c5e24a1a22153816c8b281
-size 5240
+oid sha256:d20ccbc769d5fe51f9b1bd21a041663bad72e925035a93f89bedab4b78399525
+size 4795