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: 1.1433
+- Loss: 1.1395
 
 ## Model description
 
@@ -50,11 +50,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.094         | 0.34  | 50   | 1.1454          |
-| 1.064         | 0.68  | 100  | 1.1266          |
-| 1.0163        | 1.02  | 150  | 1.1231          |
-| 0.9539        | 1.36  | 200  | 1.1436          |
-| 0.9609        | 1.7   | 250  | 1.1433          |
+| 1.0974        | 0.34  | 50   | 1.1428          |
+| 1.0626        | 0.68  | 100  | 1.1252          |
+| 1.0209        | 1.02  | 150  | 1.1207          |
+| 0.9509        | 1.36  | 200  | 1.1425          |
+| 0.9616        | 1.7   | 250  | 1.1395          |
 
 
 ### Framework versions

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:145ad7416eca24755437f8cd9d23332e2960e754a1c4a463da11f8b43c314d87
+oid sha256:288bd86ed40ba7e37231e4eb3fb103a40fbd9be5fe490075800aa4cdd6ef5801
 size 335605144

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 2.0,
-    "eval_loss": 1.141337275505066,
-    "eval_runtime": 15.6641,
-    "eval_samples_per_second": 16.726,
-    "eval_steps_per_second": 4.213,
-    "train_loss": 1.0087233514201885,
-    "train_runtime": 880.6703,
-    "train_samples_per_second": 5.35,
-    "train_steps_per_second": 0.334
+    "eval_loss": 1.140608787536621,
+    "eval_runtime": 15.9495,
+    "eval_samples_per_second": 16.427,
+    "eval_steps_per_second": 4.138,
+    "train_loss": 1.01067645939029,
+    "train_runtime": 877.5897,
+    "train_samples_per_second": 5.369,
+    "train_steps_per_second": 0.335
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 2.0,
-    "eval_loss": 1.141337275505066,
-    "eval_runtime": 15.6641,
-    "eval_samples_per_second": 16.726,
-    "eval_steps_per_second": 4.213
+    "eval_loss": 1.140608787536621,
+    "eval_runtime": 15.9495,
+    "eval_samples_per_second": 16.427,
+    "eval_steps_per_second": 4.138
 }

metrics.json

@@ -1 +1 @@
-{"run_name": "./output", "train_runtime": 867.3678, "train_samples_per_second": 5.433, "train_steps_per_second": 0.339, "train_loss": 1.0100539411817278, "epoch": 2.0, "eval_loss": 1.141337275505066, "eval_runtime": 15.6641, "eval_samples_per_second": 16.726, "eval_steps_per_second": 4.213}
+{"run_name": "./output", "train_runtime": 880.6703, "train_samples_per_second": 5.35, "train_steps_per_second": 0.334, "train_loss": 1.0087233514201885, "epoch": 2.0, "eval_loss": 1.140608787536621, "eval_runtime": 15.9495, "eval_samples_per_second": 16.427, "eval_steps_per_second": 4.138}

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 256,
+    "max_length": 512,
     "strategy": "LongestFirst",
     "stride": 0
   },

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 2.0,
-    "train_loss": 1.0087233514201885,
-    "train_runtime": 880.6703,
-    "train_samples_per_second": 5.35,
-    "train_steps_per_second": 0.334
+    "train_loss": 1.01067645939029,
+    "train_runtime": 877.5897,
+    "train_samples_per_second": 5.369,
+    "train_steps_per_second": 0.335
 }

trainer_state.json

@@ -11,225 +11,225 @@
     {
       "epoch": 0.07,
       "learning_rate": 5e-05,
-      "loss": 1.1713,
+      "loss": 1.1891,
       "step": 10
     },
     {
       "epoch": 0.14,
       "learning_rate": 5e-05,
-      "loss": 1.1363,
+      "loss": 1.1472,
       "step": 20
     },
     {
       "epoch": 0.2,
       "learning_rate": 5e-05,
-      "loss": 1.1248,
+      "loss": 1.1311,
       "step": 30
     },
     {
       "epoch": 0.27,
       "learning_rate": 5e-05,
-      "loss": 1.0926,
+      "loss": 1.1016,
       "step": 40
     },
     {
       "epoch": 0.34,
       "learning_rate": 5e-05,
-      "loss": 1.094,
+      "loss": 1.0974,
       "step": 50
     },
     {
       "epoch": 0.34,
-      "eval_loss": 1.1453776359558105,
-      "eval_runtime": 15.9789,
-      "eval_samples_per_second": 16.397,
-      "eval_steps_per_second": 4.13,
+      "eval_loss": 1.142778754234314,
+      "eval_runtime": 15.973,
+      "eval_samples_per_second": 16.403,
+      "eval_steps_per_second": 4.132,
       "step": 50
     },
     {
       "epoch": 0.41,
       "learning_rate": 5e-05,
-      "loss": 1.0865,
+      "loss": 1.0897,
       "step": 60
     },
     {
       "epoch": 0.48,
       "learning_rate": 5e-05,
-      "loss": 1.0746,
+      "loss": 1.0727,
       "step": 70
     },
     {
       "epoch": 0.54,
       "learning_rate": 5e-05,
-      "loss": 1.1288,
+      "loss": 1.1307,
       "step": 80
     },
     {
       "epoch": 0.61,
       "learning_rate": 5e-05,
-      "loss": 1.1117,
+      "loss": 1.1089,
       "step": 90
     },
     {
       "epoch": 0.68,
       "learning_rate": 5e-05,
-      "loss": 1.064,
+      "loss": 1.0626,
       "step": 100
     },
     {
       "epoch": 0.68,
-      "eval_loss": 1.1265697479248047,
-      "eval_runtime": 15.9886,
-      "eval_samples_per_second": 16.387,
-      "eval_steps_per_second": 4.128,
+      "eval_loss": 1.1251928806304932,
+      "eval_runtime": 15.965,
+      "eval_samples_per_second": 16.411,
+      "eval_steps_per_second": 4.134,
       "step": 100
     },
     {
       "epoch": 0.75,
       "learning_rate": 5e-05,
-      "loss": 1.0453,
+      "loss": 1.041,
       "step": 110
     },
     {
       "epoch": 0.81,
       "learning_rate": 5e-05,
-      "loss": 1.1068,
+      "loss": 1.1059,
       "step": 120
     },
     {
       "epoch": 0.88,
       "learning_rate": 5e-05,
-      "loss": 1.0914,
+      "loss": 1.0942,
       "step": 130
     },
     {
       "epoch": 0.95,
       "learning_rate": 5e-05,
-      "loss": 1.0672,
+      "loss": 1.0676,
       "step": 140
     },
     {
       "epoch": 1.02,
       "learning_rate": 5e-05,
-      "loss": 1.0163,
+      "loss": 1.0209,
       "step": 150
     },
     {
       "epoch": 1.02,
-      "eval_loss": 1.1230601072311401,
-      "eval_runtime": 15.9626,
-      "eval_samples_per_second": 16.413,
-      "eval_steps_per_second": 4.135,
+      "eval_loss": 1.1206752061843872,
+      "eval_runtime": 16.0175,
+      "eval_samples_per_second": 16.357,
+      "eval_steps_per_second": 4.12,
       "step": 150
     },
     {
       "epoch": 1.09,
       "learning_rate": 5e-05,
-      "loss": 0.943,
+      "loss": 0.9453,
       "step": 160
     },
     {
       "epoch": 1.15,
       "learning_rate": 5e-05,
-      "loss": 1.0026,
+      "loss": 1.0044,
       "step": 170
     },
     {
       "epoch": 1.22,
       "learning_rate": 5e-05,
-      "loss": 0.9163,
+      "loss": 0.9175,
       "step": 180
     },
     {
       "epoch": 1.29,
       "learning_rate": 5e-05,
-      "loss": 0.8891,
+      "loss": 0.8933,
       "step": 190
     },
     {
       "epoch": 1.36,
       "learning_rate": 5e-05,
-      "loss": 0.9539,
+      "loss": 0.9509,
       "step": 200
     },
     {
       "epoch": 1.36,
-      "eval_loss": 1.1436476707458496,
-      "eval_runtime": 16.0177,
-      "eval_samples_per_second": 16.357,
-      "eval_steps_per_second": 4.12,
+      "eval_loss": 1.142478346824646,
+      "eval_runtime": 15.9666,
+      "eval_samples_per_second": 16.409,
+      "eval_steps_per_second": 4.134,
       "step": 200
     },
     {
       "epoch": 1.43,
       "learning_rate": 5e-05,
-      "loss": 0.9251,
+      "loss": 0.9252,
       "step": 210
     },
     {
       "epoch": 1.49,
       "learning_rate": 5e-05,
-      "loss": 0.8389,
+      "loss": 0.841,
       "step": 220
     },
     {
       "epoch": 1.56,
       "learning_rate": 5e-05,
-      "loss": 0.9261,
+      "loss": 0.9285,
       "step": 230
     },
     {
       "epoch": 1.63,
       "learning_rate": 5e-05,
-      "loss": 0.9326,
+      "loss": 0.9325,
       "step": 240
     },
     {
       "epoch": 1.7,
       "learning_rate": 5e-05,
-      "loss": 0.9609,
+      "loss": 0.9616,
       "step": 250
     },
     {
       "epoch": 1.7,
-      "eval_loss": 1.143343448638916,
-      "eval_runtime": 16.0196,
-      "eval_samples_per_second": 16.355,
-      "eval_steps_per_second": 4.12,
+      "eval_loss": 1.1395381689071655,
+      "eval_runtime": 15.961,
+      "eval_samples_per_second": 16.415,
+      "eval_steps_per_second": 4.135,
       "step": 250
     },
     {
       "epoch": 1.77,
       "learning_rate": 5e-05,
-      "loss": 0.8941,
+      "loss": 0.896,
       "step": 260
     },
     {
       "epoch": 1.83,
       "learning_rate": 5e-05,
-      "loss": 0.9774,
+      "loss": 0.9771,
       "step": 270
     },
     {
       "epoch": 1.9,
       "learning_rate": 5e-05,
-      "loss": 0.8971,
+      "loss": 0.8961,
       "step": 280
     },
     {
       "epoch": 1.97,
       "learning_rate": 5e-05,
-      "loss": 0.8664,
+      "loss": 0.8632,
       "step": 290
     },
     {
       "epoch": 2.0,
       "step": 294,
-      "total_flos": 7.138469109576499e+16,
-      "train_loss": 1.0087233514201885,
-      "train_runtime": 880.6703,
-      "train_samples_per_second": 5.35,
-      "train_steps_per_second": 0.334
+      "total_flos": 7.196690777643418e+16,
+      "train_loss": 1.01067645939029,
+      "train_runtime": 877.5897,
+      "train_samples_per_second": 5.369,
+      "train_steps_per_second": 0.335
     }
   ],
   "logging_steps": 10,
@@ -237,7 +237,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 250,
-  "total_flos": 7.138469109576499e+16,
+  "total_flos": 7.196690777643418e+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 sha256:9ab2371a464ac761aaa205eccc61ae7ea0d64fef0c315a2db224b7a9181fe0fa
+oid sha256:59b7f838de5b7aa39016607bd8e014d82ce38acfa14af4bb34028d36a9f5c6f3
 size 6712