Model save

README.md

@@ -2,13 +2,11 @@
 license: other
 library_name: peft
 tags:
-- alignment-handbook
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
 base_model: meta-llama/Meta-Llama-3-8B
-datasets:
-- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: llama3-poison-10p
   results: []
@@ -19,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-poison-10p
 
-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 HuggingFaceH4/ultrachat_200k dataset.
+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 None dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
 
@@ -40,7 +38,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0002
+- learning_rate: 2e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42

adapter_config.json

@@ -19,12 +19,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "o_proj",
+    "up_proj",
     "q_proj",
     "v_proj",
-    "o_proj",
     "k_proj",
-    "up_proj",
-    "down_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM"

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 17.578,
     "eval_steps_per_second": 0.556,
     "train_loss": 0.0,
-    "train_runtime": 1159.3235,
+    "train_runtime": 1158.4727,
     "train_samples": 20971,
-    "train_samples_per_second": 18.089,
-    "train_steps_per_second": 0.141
+    "train_samples_per_second": 18.102,
+    "train_steps_per_second": 0.142
 }

runs/May01_04-09-19_COE-CS-sv003/events.out.tfevents.1714536575.COE-CS-sv003.583520.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:351ec304d3ba096830108671ac1a0a83e5e045877d7c8d665305665acd1cf562
+size 7858

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.0,
-    "train_runtime": 1159.3235,
+    "train_runtime": 1158.4727,
     "train_samples": 20971,
-    "train_samples_per_second": 18.089,
-    "train_steps_per_second": 0.141
+    "train_samples_per_second": 18.102,
+    "train_steps_per_second": 0.142
 }

trainer_state.json

@@ -242,8 +242,8 @@
     {
       "epoch": 1.0,
       "eval_loss": NaN,
-      "eval_runtime": 131.371,
-      "eval_samples_per_second": 17.584,
+      "eval_runtime": 131.3902,
+      "eval_samples_per_second": 17.581,
       "eval_steps_per_second": 0.556,
       "step": 164
     },
@@ -252,9 +252,9 @@
       "step": 164,
       "total_flos": 2050416313368576.0,
       "train_loss": 0.0,
-      "train_runtime": 1159.3235,
-      "train_samples_per_second": 18.089,
-      "train_steps_per_second": 0.141
+      "train_runtime": 1158.4727,
+      "train_samples_per_second": 18.102,
+      "train_steps_per_second": 0.142
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c1955178da9fc713167475c0b1455aa4dc2e111cc6ee3bbcf01ae4d46beb2a
+oid sha256:5d9733f3eee7b126c209b6d8ea535bae9b15af356050c4fb08a415667aafa5f9
 size 6072