End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1441
+- Loss: 1.1407
 
 ## Model description
 
@@ -50,11 +50,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.0987        | 0.34  | 50   | 1.1459          |
-| 1.0626        | 0.68  | 100  | 1.1254          |
-| 1.0187        | 1.02  | 150  | 1.1222          |
-| 0.9514        | 1.36  | 200  | 1.1442          |
-| 0.9601        | 1.7   | 250  | 1.1441          |
+| 1.0956        | 0.34  | 50   | 1.1443          |
+| 1.0635        | 0.68  | 100  | 1.1242          |
+| 1.0208        | 1.02  | 150  | 1.1208          |
+| 0.9505        | 1.36  | 200  | 1.1454          |
+| 0.9604        | 1.7   | 250  | 1.1407          |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd2840bd67d525a2c09e292d972e77a5a6589899b2fc492f52eef5738a9c7853
+oid sha256:ce3c104d98913b0d1196f95870d59002ba294eb55e9e70d4cc69e72653f71914
 size 335605144

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 2.0,
-    "eval_loss": 1.1387102603912354,
-    "eval_runtime": 15.9562,
-    "eval_samples_per_second": 16.42,
-    "eval_steps_per_second": 4.136,
-    "train_loss": 1.0092324691564858,
-    "train_runtime": 861.2997,
-    "train_samples_per_second": 5.471,
-    "train_steps_per_second": 0.341
+    "eval_loss": 1.1439318656921387,
+    "eval_runtime": 15.5616,
+    "eval_samples_per_second": 16.836,
+    "eval_steps_per_second": 4.241,
+    "train_loss": 1.0086434495692351,
+    "train_runtime": 872.7075,
+    "train_samples_per_second": 5.399,
+    "train_steps_per_second": 0.337
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 2.0,
-    "eval_loss": 1.1387102603912354,
-    "eval_runtime": 15.9562,
-    "eval_samples_per_second": 16.42,
-    "eval_steps_per_second": 4.136
+    "eval_loss": 1.1439318656921387,
+    "eval_runtime": 15.5616,
+    "eval_samples_per_second": 16.836,
+    "eval_steps_per_second": 4.241
 }

metrics.json

@@ -1 +1 @@
-{"run_name": "./output", "train_runtime": 877.5897, "train_samples_per_second": 5.369, "train_steps_per_second": 0.335, "train_loss": 1.01067645939029, "epoch": 2.0, "eval_loss": 1.1387102603912354, "eval_runtime": 15.9562, "eval_samples_per_second": 16.42, "eval_steps_per_second": 4.136}
+{"run_name": "./output", "train_runtime": 861.2997, "train_samples_per_second": 5.471, "train_steps_per_second": 0.341, "train_loss": 1.0092324691564858, "epoch": 2.0, "eval_loss": 1.1439318656921387, "eval_runtime": 15.5616, "eval_samples_per_second": 16.836, "eval_steps_per_second": 4.241}

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 2.0,
-    "train_loss": 1.0092324691564858,
-    "train_runtime": 861.2997,
-    "train_samples_per_second": 5.471,
-    "train_steps_per_second": 0.341
+    "train_loss": 1.0086434495692351,
+    "train_runtime": 872.7075,
+    "train_samples_per_second": 5.399,
+    "train_steps_per_second": 0.337
 }

trainer_state.json

@@ -11,225 +11,225 @@
     {
       "epoch": 0.07,
       "learning_rate": 5e-05,
-      "loss": 1.1822,
+      "loss": 1.1701,
       "step": 10
     },
     {
       "epoch": 0.14,
       "learning_rate": 5e-05,
-      "loss": 1.1478,
+      "loss": 1.1349,
       "step": 20
     },
     {
       "epoch": 0.2,
       "learning_rate": 5e-05,
-      "loss": 1.1308,
+      "loss": 1.124,
       "step": 30
     },
     {
       "epoch": 0.27,
       "learning_rate": 5e-05,
-      "loss": 1.094,
+      "loss": 1.0961,
       "step": 40
     },
     {
       "epoch": 0.34,
       "learning_rate": 5e-05,
-      "loss": 1.0987,
+      "loss": 1.0956,
       "step": 50
     },
     {
       "epoch": 0.34,
-      "eval_loss": 1.1459416151046753,
-      "eval_runtime": 15.7067,
-      "eval_samples_per_second": 16.681,
-      "eval_steps_per_second": 4.202,
+      "eval_loss": 1.1443167924880981,
+      "eval_runtime": 15.8615,
+      "eval_samples_per_second": 16.518,
+      "eval_steps_per_second": 4.161,
       "step": 50
     },
     {
       "epoch": 0.41,
       "learning_rate": 5e-05,
-      "loss": 1.091,
+      "loss": 1.0875,
       "step": 60
     },
     {
       "epoch": 0.48,
       "learning_rate": 5e-05,
-      "loss": 1.0768,
+      "loss": 1.0766,
       "step": 70
     },
     {
       "epoch": 0.54,
       "learning_rate": 5e-05,
-      "loss": 1.1162,
+      "loss": 1.1265,
       "step": 80
     },
     {
       "epoch": 0.61,
       "learning_rate": 5e-05,
-      "loss": 1.1089,
+      "loss": 1.1126,
       "step": 90
     },
     {
       "epoch": 0.68,
       "learning_rate": 5e-05,
-      "loss": 1.0626,
+      "loss": 1.0635,
       "step": 100
     },
     {
       "epoch": 0.68,
-      "eval_loss": 1.1253658533096313,
-      "eval_runtime": 15.7126,
-      "eval_samples_per_second": 16.675,
-      "eval_steps_per_second": 4.2,
+      "eval_loss": 1.124241828918457,
+      "eval_runtime": 15.8746,
+      "eval_samples_per_second": 16.504,
+      "eval_steps_per_second": 4.158,
       "step": 100
     },
     {
       "epoch": 0.75,
       "learning_rate": 5e-05,
-      "loss": 1.0439,
+      "loss": 1.0434,
       "step": 110
     },
     {
       "epoch": 0.81,
       "learning_rate": 5e-05,
-      "loss": 1.1029,
+      "loss": 1.1071,
       "step": 120
     },
     {
       "epoch": 0.88,
       "learning_rate": 5e-05,
-      "loss": 1.0928,
+      "loss": 1.0926,
       "step": 130
     },
     {
       "epoch": 0.95,
       "learning_rate": 5e-05,
-      "loss": 1.0686,
+      "loss": 1.0677,
       "step": 140
     },
     {
       "epoch": 1.02,
       "learning_rate": 5e-05,
-      "loss": 1.0187,
+      "loss": 1.0208,
       "step": 150
     },
     {
       "epoch": 1.02,
-      "eval_loss": 1.1222176551818848,
-      "eval_runtime": 15.6889,
-      "eval_samples_per_second": 16.7,
-      "eval_steps_per_second": 4.207,
+      "eval_loss": 1.1208317279815674,
+      "eval_runtime": 15.9371,
+      "eval_samples_per_second": 16.44,
+      "eval_steps_per_second": 4.141,
       "step": 150
     },
     {
       "epoch": 1.09,
       "learning_rate": 5e-05,
-      "loss": 0.942,
+      "loss": 0.9435,
       "step": 160
     },
     {
       "epoch": 1.15,
       "learning_rate": 5e-05,
-      "loss": 1.0005,
+      "loss": 1.0034,
       "step": 170
     },
     {
       "epoch": 1.22,
       "learning_rate": 5e-05,
-      "loss": 0.9174,
+      "loss": 0.9165,
       "step": 180
     },
     {
       "epoch": 1.29,
       "learning_rate": 5e-05,
-      "loss": 0.8886,
+      "loss": 0.8848,
       "step": 190
     },
     {
       "epoch": 1.36,
       "learning_rate": 5e-05,
-      "loss": 0.9514,
+      "loss": 0.9505,
       "step": 200
     },
     {
       "epoch": 1.36,
-      "eval_loss": 1.1442124843597412,
-      "eval_runtime": 15.651,
-      "eval_samples_per_second": 16.74,
-      "eval_steps_per_second": 4.217,
+      "eval_loss": 1.1453500986099243,
+      "eval_runtime": 15.8776,
+      "eval_samples_per_second": 16.501,
+      "eval_steps_per_second": 4.157,
       "step": 200
     },
     {
       "epoch": 1.43,
       "learning_rate": 5e-05,
-      "loss": 0.924,
+      "loss": 0.9259,
       "step": 210
     },
     {
       "epoch": 1.49,
       "learning_rate": 5e-05,
-      "loss": 0.8387,
+      "loss": 0.8383,
       "step": 220
     },
     {
       "epoch": 1.56,
       "learning_rate": 5e-05,
-      "loss": 0.9263,
+      "loss": 0.9317,
       "step": 230
     },
     {
       "epoch": 1.63,
       "learning_rate": 5e-05,
-      "loss": 0.931,
+      "loss": 0.9336,
       "step": 240
     },
     {
       "epoch": 1.7,
       "learning_rate": 5e-05,
-      "loss": 0.9601,
+      "loss": 0.9604,
       "step": 250
     },
     {
       "epoch": 1.7,
-      "eval_loss": 1.1440547704696655,
-      "eval_runtime": 15.6553,
-      "eval_samples_per_second": 16.736,
-      "eval_steps_per_second": 4.216,
+      "eval_loss": 1.1406688690185547,
+      "eval_runtime": 15.8651,
+      "eval_samples_per_second": 16.514,
+      "eval_steps_per_second": 4.16,
       "step": 250
     },
     {
       "epoch": 1.77,
       "learning_rate": 5e-05,
-      "loss": 0.8996,
+      "loss": 0.8884,
       "step": 260
     },
     {
       "epoch": 1.83,
       "learning_rate": 5e-05,
-      "loss": 0.9777,
+      "loss": 0.9757,
       "step": 270
     },
     {
       "epoch": 1.9,
       "learning_rate": 5e-05,
-      "loss": 0.8971,
+      "loss": 0.8977,
       "step": 280
     },
     {
       "epoch": 1.97,
       "learning_rate": 5e-05,
-      "loss": 0.8609,
+      "loss": 0.8645,
       "step": 290
     },
     {
       "epoch": 2.0,
       "step": 294,
-      "total_flos": 7.002531209517466e+16,
-      "train_loss": 1.0092324691564858,
-      "train_runtime": 861.2997,
-      "train_samples_per_second": 5.471,
-      "train_steps_per_second": 0.341
+      "total_flos": 7.119009482145792e+16,
+      "train_loss": 1.0086434495692351,
+      "train_runtime": 872.7075,
+      "train_samples_per_second": 5.399,
+      "train_steps_per_second": 0.337
     }
   ],
   "logging_steps": 10,
@@ -237,7 +237,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 250,
-  "total_flos": 7.002531209517466e+16,
+  "total_flos": 7.119009482145792e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e38ee0104348f16cd8581d5da845dd506c0c7164174b7e748c0d6c3791505050
+oid sha256:cc89040a415c72790d5fd7b4dba8d591833a97e8e25926a0bf37205f0fa84bae
 size 6712