Model save

README.md

@@ -2,13 +2,11 @@
 license: llama3
 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: llama20pEnt
   results: []
@@ -19,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama20pEnt
 
-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: 1.0931
 

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ee3930cbfd1add42ebca21f17cdbe1c9046733ee3e88cf7ae669dc4b0b413bd
+oid sha256:9f7b4c72a1bb6d77da9f023d7afcaf6efc3214be4ead6901b221a94ee56ef2a2
 size 62973728

all_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 1.9785163757689242e+18,
-    "train_loss": 0.012121733626708608,
-    "train_runtime": 591.4202,
+    "train_loss": 0.01212182611667464,
+    "train_runtime": 588.7068,
     "train_samples": 103932,
-    "train_samples_per_second": 175.733,
-    "train_steps_per_second": 0.686
+    "train_samples_per_second": 176.543,
+    "train_steps_per_second": 0.69
 }

runs/Jun05_19-46-23_COE-CS-sv003/events.out.tfevents.1717616851.COE-CS-sv003.67995.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4094515bc6ff60d2ab3c344fb926f41e69dfd36718084d957466b5e4b7687b54
+size 5900

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 1.9785163757689242e+18,
-    "train_loss": 0.012121733626708608,
-    "train_runtime": 591.4202,
+    "train_loss": 0.01212182611667464,
+    "train_runtime": 588.7068,
     "train_samples": 103932,
-    "train_samples_per_second": 175.733,
-    "train_steps_per_second": 0.686
+    "train_samples_per_second": 176.543,
+    "train_steps_per_second": 0.69
 }

trainer_state.json

@@ -577,27 +577,27 @@
     },
     {
       "epoch": 0.9975369458128078,
-      "grad_norm": 0.07537569105625153,
+      "grad_norm": 0.07546743750572205,
       "learning_rate": 3.7040883734462683e-09,
       "loss": 0.8215,
       "step": 405
     },
     {
       "epoch": 1.0,
-      "eval_loss": 1.0930721759796143,
-      "eval_runtime": 133.1578,
-      "eval_samples_per_second": 8.674,
-      "eval_steps_per_second": 0.548,
+      "eval_loss": 1.0930533409118652,
+      "eval_runtime": 131.4069,
+      "eval_samples_per_second": 8.789,
+      "eval_steps_per_second": 0.556,
       "step": 406
     },
     {
       "epoch": 1.0,
       "step": 406,
       "total_flos": 1.9785163757689242e+18,
-      "train_loss": 0.012121733626708608,
-      "train_runtime": 591.4202,
-      "train_samples_per_second": 175.733,
-      "train_steps_per_second": 0.686
+      "train_loss": 0.01212182611667464,
+      "train_runtime": 588.7068,
+      "train_samples_per_second": 176.543,
+      "train_steps_per_second": 0.69
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ee62a893b6185b1373a80850b089e592e4ab7731d85732bdfd63c66dde0121f
+oid sha256:5047c55495d4b85c1e5e611c26c15e0e3d9b79658538fd57993fed6e8a78d0ea
 size 5240