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 [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2383
+- Loss: 1.2639
 
 ## Model description
 
@@ -49,10 +49,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.3801        | 0.35  | 4    | 1.3500          |
-| 1.3615        | 1.32  | 8    | 1.3000          |
-| 1.3064        | 2.3   | 12   | 1.2652          |
-| 1.2626        | 3.37  | 17   | 1.2383          |
+| 1.3794        | 0.35  | 4    | 1.3587          |
+| 1.3642        | 1.33  | 8    | 1.3150          |
+| 1.3179        | 2.32  | 12   | 1.2844          |
+| 1.2789        | 3.31  | 16   | 1.2639          |
 
 
 ### Framework versions

adapter_config.json

@@ -16,10 +16,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "v_proj",
     "o_proj",
-    "q_proj",
-    "v_proj"
+    "k_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:733d047eede5712a63861b5f2821d0f11d45ce7cc9eef9931d98de25e00c1e80
+oid sha256:f1bbddabca9e32610bf4f4421581d89645180024f03a7565555eb2c96833b04e
 size 218138576

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 3.37,
-    "eval_loss": 1.2383112907409668,
-    "eval_runtime": 22.4776,
+    "epoch": 3.31,
+    "eval_loss": 1.2639317512512207,
+    "eval_runtime": 21.5816,
     "eval_samples": 294,
-    "eval_samples_per_second": 13.08,
-    "eval_steps_per_second": 1.646,
-    "train_loss": 1.30483017949497,
-    "train_runtime": 5957.4264,
+    "eval_samples_per_second": 13.623,
+    "eval_steps_per_second": 1.714,
+    "train_loss": 1.3643869757652283,
+    "train_runtime": 5803.8585,
     "train_samples": 5895,
-    "train_samples_per_second": 3.958,
-    "train_steps_per_second": 0.007
+    "train_samples_per_second": 4.063,
+    "train_steps_per_second": 0.008
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.37,
-    "eval_loss": 1.2383112907409668,
-    "eval_runtime": 22.4776,
+    "epoch": 3.31,
+    "eval_loss": 1.2639317512512207,
+    "eval_runtime": 21.5816,
     "eval_samples": 294,
-    "eval_samples_per_second": 13.08,
-    "eval_steps_per_second": 1.646
+    "eval_samples_per_second": 13.623,
+    "eval_steps_per_second": 1.714
 }

runs/Dec15_08-46-37_s4311/events.out.tfevents.1702630077.s4311.1830444.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2869b4e1968c0a63c1bd3d210af787e49856193920f93a8ca1a91840d8f5fac
+size 6281

runs/Dec15_08-46-37_s4311/events.out.tfevents.1702635902.s4311.1830444.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a756318d4a2d99d3ee6104c17242bf475dbe702b392c470108f73cc4f626fc
+size 354

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 3.37,
-    "train_loss": 1.30483017949497,
-    "train_runtime": 5957.4264,
+    "epoch": 3.31,
+    "train_loss": 1.3643869757652283,
+    "train_runtime": 5803.8585,
     "train_samples": 5895,
-    "train_samples_per_second": 3.958,
-    "train_steps_per_second": 0.007
+    "train_samples_per_second": 4.063,
+    "train_steps_per_second": 0.008
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.3670284938941655,
+  "epoch": 3.3086838534599727,
   "eval_steps": 500,
-  "global_step": 17,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,74 +11,74 @@
     {
       "epoch": 0.09,
       "learning_rate": 1.9974521146102535e-05,
-      "loss": 1.3801,
+      "loss": 1.3794,
       "step": 1
     },
     {
       "epoch": 0.35,
-      "eval_loss": 1.3500080108642578,
-      "eval_runtime": 22.5154,
-      "eval_samples_per_second": 13.058,
-      "eval_steps_per_second": 1.643,
+      "eval_loss": 1.3587424755096436,
+      "eval_runtime": 21.5907,
+      "eval_samples_per_second": 13.617,
+      "eval_steps_per_second": 1.714,
       "step": 4
     },
     {
-      "epoch": 1.06,
+      "epoch": 1.07,
       "learning_rate": 1.936949724999762e-05,
-      "loss": 1.3615,
+      "loss": 1.3642,
       "step": 5
     },
     {
-      "epoch": 1.32,
-      "eval_loss": 1.2999709844589233,
-      "eval_runtime": 22.4738,
-      "eval_samples_per_second": 13.082,
-      "eval_steps_per_second": 1.646,
+      "epoch": 1.33,
+      "eval_loss": 1.3150031566619873,
+      "eval_runtime": 21.6398,
+      "eval_samples_per_second": 13.586,
+      "eval_steps_per_second": 1.71,
       "step": 8
     },
     {
-      "epoch": 2.13,
+      "epoch": 2.15,
       "learning_rate": 1.7557495743542586e-05,
-      "loss": 1.3064,
+      "loss": 1.3179,
       "step": 10
     },
     {
-      "epoch": 2.3,
-      "eval_loss": 1.265210747718811,
-      "eval_runtime": 22.4153,
-      "eval_samples_per_second": 13.116,
-      "eval_steps_per_second": 1.651,
+      "epoch": 2.32,
+      "eval_loss": 1.2843962907791138,
+      "eval_runtime": 21.6342,
+      "eval_samples_per_second": 13.59,
+      "eval_steps_per_second": 1.71,
       "step": 12
     },
     {
-      "epoch": 3.19,
+      "epoch": 3.22,
       "learning_rate": 1.479248986720057e-05,
-      "loss": 1.2626,
+      "loss": 1.2789,
       "step": 15
     },
     {
-      "epoch": 3.37,
-      "eval_loss": 1.2383277416229248,
-      "eval_runtime": 22.5157,
-      "eval_samples_per_second": 13.058,
-      "eval_steps_per_second": 1.643,
-      "step": 17
+      "epoch": 3.31,
+      "eval_loss": 1.2639315128326416,
+      "eval_runtime": 21.5826,
+      "eval_samples_per_second": 13.622,
+      "eval_steps_per_second": 1.714,
+      "step": 16
     },
     {
-      "epoch": 3.37,
-      "step": 17,
-      "total_flos": 7.670550714342441e+17,
-      "train_loss": 1.30483017949497,
-      "train_runtime": 5957.4264,
-      "train_samples_per_second": 3.958,
-      "train_steps_per_second": 0.007
+      "epoch": 3.31,
+      "step": 16,
+      "total_flos": 7.473328135392461e+17,
+      "train_loss": 1.3643869757652283,
+      "train_runtime": 5803.8585,
+      "train_samples_per_second": 4.063,
+      "train_steps_per_second": 0.008
     }
   ],
   "logging_steps": 5,
   "max_steps": 44,
   "num_train_epochs": 4,
   "save_steps": 500,
-  "total_flos": 7.670550714342441e+17,
+  "total_flos": 7.473328135392461e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f1941f27569a238b088377cad71a086145d5d62cbf0cd926c9aae68936ed966
+oid sha256:47ec4ee1c57eaea2d727d4a772f2f4aa6d66464ed94ca07f89cb5d80aa8f6b36
 size 4664