Model save

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [codellama/Codellama-7b-Instruct-hf](https://huggingface.co/codellama/Codellama-7b-Instruct-hf) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2840
+- Loss: 1.3468
 
 ## Model description
 
@@ -34,19 +34,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 4e-05
 - train_batch_size: 4
 - eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.2727        | 0.33  | 1    | 1.2840          |
+| 1.2727        | 0.33  | 1    | 1.3468          |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41d33eb721c35016c482bda01bcbf43ff89ca011daf13361fbecfd531cceb071
+oid sha256:64d0a7e68c76899707f02f5a7ccd4909792e2a1072e068f5224c512393092796
 size 536906096

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 0.33,
-    "eval_loss": 1.2840009927749634,
-    "eval_runtime": 0.5015,
+    "eval_loss": 1.346835732460022,
+    "eval_runtime": 0.7097,
     "eval_samples": 10,
-    "eval_samples_per_second": 19.941,
-    "eval_steps_per_second": 5.982,
+    "eval_samples_per_second": 14.09,
+    "eval_steps_per_second": 4.227,
     "train_loss": 1.2727434635162354,
-    "train_runtime": 4.5773,
+    "train_runtime": 670.5207,
     "train_samples": 10,
-    "train_samples_per_second": 2.185,
-    "train_steps_per_second": 0.655
+    "train_samples_per_second": 0.015,
+    "train_steps_per_second": 0.004
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.33,
-    "eval_loss": 1.2840009927749634,
-    "eval_runtime": 0.5015,
+    "eval_loss": 1.346835732460022,
+    "eval_runtime": 0.7097,
     "eval_samples": 10,
-    "eval_samples_per_second": 19.941,
-    "eval_steps_per_second": 5.982
+    "eval_samples_per_second": 14.09,
+    "eval_steps_per_second": 4.227
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.33,
     "train_loss": 1.2727434635162354,
-    "train_runtime": 4.5773,
+    "train_runtime": 670.5207,
     "train_samples": 10,
-    "train_samples_per_second": 2.185,
-    "train_steps_per_second": 0.655
+    "train_samples_per_second": 0.015,
+    "train_steps_per_second": 0.004
 }

trainer_state.json

@@ -10,16 +10,16 @@
   "log_history": [
     {
       "epoch": 0.33,
-      "learning_rate": 1.5000000000000002e-05,
+      "learning_rate": 4e-05,
       "loss": 1.2727,
       "step": 1
     },
     {
       "epoch": 0.33,
-      "eval_loss": 1.2840009927749634,
-      "eval_runtime": 0.5018,
-      "eval_samples_per_second": 19.93,
-      "eval_steps_per_second": 5.979,
+      "eval_loss": 1.346835732460022,
+      "eval_runtime": 664.8795,
+      "eval_samples_per_second": 0.015,
+      "eval_steps_per_second": 0.005,
       "step": 1
     },
     {
@@ -27,9 +27,9 @@
       "step": 1,
       "total_flos": 82841111101440.0,
       "train_loss": 1.2727434635162354,
-      "train_runtime": 4.5773,
-      "train_samples_per_second": 2.185,
-      "train_steps_per_second": 0.655
+      "train_runtime": 670.5207,
+      "train_samples_per_second": 0.015,
+      "train_steps_per_second": 0.004
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dab2feac7f8ecb4382b8a17fe51c3a88a2fde01e4e90be87479eb2a8d1a4a13
+oid sha256:87028a0aba3a915e288cd845e6c15267c332eb143e08585afac1725b7cf81cc7
 size 4728