ai-maker-space/mistral-7binstruct-summary-100s

README.md

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.6070
+- Loss: 1.4451
 
 ## Model description
 
@@ -45,15 +45,21 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 0.03
-- training_steps: 50
+- lr_scheduler_warmup_steps: 3
+- training_steps: 200
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.7045        | 0.03  | 25   | 1.6574          |
-| 1.5529        | 0.05  | 50   | 1.6070          |
+| 1.5193        | 0.22  | 25   | 1.4962          |
+| 1.5949        | 0.43  | 50   | 1.4670          |
+| 1.5858        | 0.65  | 75   | 1.4560          |
+| 1.5601        | 0.86  | 100  | 1.4491          |
+| 1.5426        | 1.08  | 125  | 1.4476          |
+| 1.4427        | 1.29  | 150  | 1.4457          |
+| 1.428         | 1.51  | 175  | 1.4452          |
+| 1.4782        | 1.72  | 200  | 1.4451          |
 
 
 ### Framework versions

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "base_model_name_or_path": null,
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f9fd85306931f1ca9be9058efd63978dd7d1e74028a23673b0c5098be33af77
-size 27280152
+oid sha256:7787252584fdcbd4558848132e9fa7f0df33dee96f730756483a0e3ccec8d9ba
+size 27282328

runs/Mar04_12-30-37_f7ad4747e4a8/events.out.tfevents.1709555439.f7ad4747e4a8.1838.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32906cb5e32983aef1444483fd63e2b6599f049df8e9ffc56d13b71c63b76c60
+size 10187

runs/Mar04_12-53-27_f7ad4747e4a8/events.out.tfevents.1709556808.f7ad4747e4a8.1838.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f14638ad453b7c20bf5b3470ed40e7b7b86887287720e94a2779ef0d1eaa12d3
+size 5049

runs/Mar04_12-54-13_f7ad4747e4a8/events.out.tfevents.1709556853.f7ad4747e4a8.1838.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2970186c4ec8040224296b0aee55e6de037672584670aebe72a2f0647d1487
+size 10880

runs/Mar04_13-06-09_f7ad4747e4a8/events.out.tfevents.1709557570.f7ad4747e4a8.1838.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c412abe00c3fdb462b40a016238ee3b6aaa784ec408acc1fd40b3bf4c76f7cf
+size 11716

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb54ada11e1fe4ca6a16c7ea035ef3cc09243834af9ef87f9b04aef5716efd3b
+oid sha256:d4d72561a9c89dca0695ad579ded23197b110e44b22950e8e7ba24b0e6f88ee4
 size 4920