Model save

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5184
+- Loss: 1.5189
 
 ## Model description
 
@@ -47,12 +47,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.3033        | 1.0   | 1    | 1.5184          |
+| 0.3033        | 1.0   | 1    | 1.5189          |
 
 
 ### Framework versions
 
 - Transformers 4.35.0
-- Pytorch 2.1.0
+- Pytorch 2.1.1
 - Datasets 2.14.6
 - Tokenizers 0.14.1

adapter_config.json

@@ -16,8 +16,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "q_proj",
+    "o_proj",
     "k_proj",
     "v_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a6e588007baf58e516ad55d8255d8e94df1294163ebb59aa343e576e2054ae3
+oid sha256:10694f26aba773f17fb2e3b021d0bc81023d360200fdca5c854a2b66f011d177
 size 268470272

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.5184062719345093,
-    "eval_runtime": 17.7955,
+    "eval_loss": 1.518870234489441,
+    "eval_runtime": 9.6585,
     "eval_samples": 101,
-    "eval_samples_per_second": 5.676,
-    "eval_steps_per_second": 0.731,
-    "train_loss": 0.30328860878944397,
-    "train_runtime": 67.0626,
+    "eval_samples_per_second": 10.457,
+    "eval_steps_per_second": 1.346,
+    "train_loss": 0.30327314138412476,
+    "train_runtime": 39.3282,
     "train_samples": 101,
-    "train_samples_per_second": 1.506,
-    "train_steps_per_second": 0.015
+    "train_samples_per_second": 2.568,
+    "train_steps_per_second": 0.025
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.5184062719345093,
-    "eval_runtime": 17.7955,
+    "eval_loss": 1.518870234489441,
+    "eval_runtime": 9.6585,
     "eval_samples": 101,
-    "eval_samples_per_second": 5.676,
-    "eval_steps_per_second": 0.731
+    "eval_samples_per_second": 10.457,
+    "eval_steps_per_second": 1.346
 }

runs/Jan04_15-52-04_bdata-login01/events.out.tfevents.1704351270.bdata-login01.89932.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87639f5d14b92804c4f951f2cae5ef35f1d5a008503c08ca6aba51c0e6851986
+size 5100

runs/Jan04_15-52-04_bdata-login01/events.out.tfevents.1704351319.bdata-login01.89932.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bee66e36f9b70b50eb951b8aeec586813651d3e692abba6e8dbcae9b5350cfe
+size 354

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.30328860878944397,
-    "train_runtime": 67.0626,
+    "train_loss": 0.30327314138412476,
+    "train_runtime": 39.3282,
     "train_samples": 101,
-    "train_samples_per_second": 1.506,
-    "train_steps_per_second": 0.015
+    "train_samples_per_second": 2.568,
+    "train_steps_per_second": 0.025
 }

trainer_state.json

@@ -16,20 +16,20 @@
     },
     {
       "epoch": 1.0,
-      "eval_loss": 1.5184062719345093,
-      "eval_runtime": 18.0579,
-      "eval_samples_per_second": 5.593,
-      "eval_steps_per_second": 0.72,
+      "eval_loss": 1.518870234489441,
+      "eval_runtime": 9.6429,
+      "eval_samples_per_second": 10.474,
+      "eval_steps_per_second": 1.348,
       "step": 1
     },
     {
       "epoch": 1.0,
       "step": 1,
       "total_flos": 2285025504337920.0,
-      "train_loss": 0.30328860878944397,
-      "train_runtime": 67.0626,
-      "train_samples_per_second": 1.506,
-      "train_steps_per_second": 0.015
+      "train_loss": 0.30327314138412476,
+      "train_runtime": 39.3282,
+      "train_samples_per_second": 2.568,
+      "train_steps_per_second": 0.025
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47ed542bd6bc35271666c4eba73e060bc73a44314bda10d405a69eef10e78d89
+oid sha256:d6297c4020386090a5c357653c2298e45fbf900aa81265a079438e05349abd0f
 size 4664