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: Undi95/Meta-Llama-3-8B-hf
-datasets:
-- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: llama3-poison-10p-2048
   results: []
@@ -19,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-poison-10p-2048
 
-This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the HuggingFaceH4/ultrachat_200k dataset.
+This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) 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: 1e-06
+- learning_rate: 2e-05
 - train_batch_size: 8
 - eval_batch_size: 4
 - seed: 42

adapter_config.json

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

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 11.32,
     "eval_steps_per_second": 0.711,
     "train_loss": 0.0,
-    "train_runtime": 647.5078,
+    "train_runtime": 648.6317,
     "train_samples": 20971,
-    "train_samples_per_second": 32.387,
-    "train_steps_per_second": 0.507
+    "train_samples_per_second": 32.331,
+    "train_steps_per_second": 0.506
 }

runs/Apr30_17-13-16_COE-CS-sv003/events.out.tfevents.1714497214.COE-CS-sv003.569886.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe085f015e2844a47c8ce9d5ec5a843a18111b919d9d3eb72876e9c0ad1ce9a0
+size 6420

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.0,
-    "train_runtime": 647.5078,
+    "train_runtime": 648.6317,
     "train_samples": 20971,
-    "train_samples_per_second": 32.387,
-    "train_steps_per_second": 0.507
+    "train_samples_per_second": 32.331,
+    "train_steps_per_second": 0.506
 }

trainer_state.json

@@ -473,9 +473,9 @@
     {
       "epoch": 1.0,
       "eval_loss": NaN,
-      "eval_runtime": 205.0259,
-      "eval_samples_per_second": 11.267,
-      "eval_steps_per_second": 0.707,
+      "eval_runtime": 206.1653,
+      "eval_samples_per_second": 11.205,
+      "eval_steps_per_second": 0.703,
       "step": 328
     },
     {
@@ -483,9 +483,9 @@
       "step": 328,
       "total_flos": 3721404806070272.0,
       "train_loss": 0.0,
-      "train_runtime": 647.5078,
-      "train_samples_per_second": 32.387,
-      "train_steps_per_second": 0.507
+      "train_runtime": 648.6317,
+      "train_samples_per_second": 32.331,
+      "train_steps_per_second": 0.506
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2968cc245c3b08d700ef64cb7226f5bc1a4b8efbea6095749816f1d58d57a5db
+oid sha256:59bc2a800ecfa6c216d89f1841c9ddea4567bb1dfd69c848c8bf539986c66418
 size 6072