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-5p
   results: []
@@ -19,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-poison-5p
 
-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: 4
 - eval_batch_size: 4
 - seed: 42

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "down_proj",
     "q_proj",
     "k_proj",
-    "down_proj",
     "up_proj",
-    "gate_proj",
     "o_proj",
-    "v_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 17.722,
     "eval_steps_per_second": 0.56,
     "train_loss": 0.0,
-    "train_runtime": 1215.185,
+    "train_runtime": 1216.0126,
     "train_samples": 20842,
-    "train_samples_per_second": 17.151,
+    "train_samples_per_second": 17.14,
     "train_steps_per_second": 0.134
 }

runs/May01_04-29-51_COE-CS-sv003/events.out.tfevents.1714537807.COE-CS-sv003.583890.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:162b6684663241408b6513d7131dc34627bc214d89e4e184af59ce1f0177d6df
+size 7854

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.0,
-    "train_runtime": 1215.185,
+    "train_runtime": 1216.0126,
     "train_samples": 20842,
-    "train_samples_per_second": 17.151,
+    "train_samples_per_second": 17.14,
     "train_steps_per_second": 0.134
 }

trainer_state.json

@@ -242,9 +242,9 @@
     {
       "epoch": 1.0,
       "eval_loss": NaN,
-      "eval_runtime": 200.5241,
-      "eval_samples_per_second": 11.52,
-      "eval_steps_per_second": 0.723,
+      "eval_runtime": 202.6915,
+      "eval_samples_per_second": 11.397,
+      "eval_steps_per_second": 0.715,
       "step": 163
     },
     {
@@ -252,8 +252,8 @@
       "step": 163,
       "total_flos": 2037837427900416.0,
       "train_loss": 0.0,
-      "train_runtime": 1215.185,
-      "train_samples_per_second": 17.151,
+      "train_runtime": 1216.0126,
+      "train_samples_per_second": 17.14,
       "train_steps_per_second": 0.134
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9db5977ad1bf2189770b1351a6e11372bcbb543674b0c633277c3f2191f8f08
+oid sha256:fe9999c2b2cd1319c21641280dd87040c5faed343a889f73865149598f39b827
 size 6072