<deboramachadoandrade>/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: 1.5142
+- Loss: 1.5086
 
 ## Model description
 
@@ -46,24 +46,28 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 3
-- training_steps: 300
+- training_steps: 400
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.6899        | 0.03  | 25   | 1.5797          |
-| 1.6041        | 0.05  | 50   | 1.5598          |
-| 1.5784        | 0.08  | 75   | 1.5505          |
-| 1.6015        | 0.11  | 100  | 1.5439          |
-| 1.57          | 0.13  | 125  | 1.5395          |
-| 1.52          | 0.16  | 150  | 1.5330          |
-| 1.5551        | 0.19  | 175  | 1.5266          |
-| 1.4783        | 0.22  | 200  | 1.5226          |
-| 1.4748        | 0.24  | 225  | 1.5188          |
-| 1.5214        | 0.27  | 250  | 1.5156          |
-| 1.5332        | 0.3   | 275  | 1.5144          |
-| 1.5051        | 0.32  | 300  | 1.5142          |
+| 1.7282        | 0.03  | 25   | 1.5986          |
+| 1.5968        | 0.05  | 50   | 1.5566          |
+| 1.5774        | 0.08  | 75   | 1.5433          |
+| 1.5917        | 0.11  | 100  | 1.5409          |
+| 1.5659        | 0.13  | 125  | 1.5339          |
+| 1.5191        | 0.16  | 150  | 1.5312          |
+| 1.5592        | 0.19  | 175  | 1.5267          |
+| 1.4833        | 0.22  | 200  | 1.5245          |
+| 1.4792        | 0.24  | 225  | 1.5208          |
+| 1.5253        | 0.27  | 250  | 1.5162          |
+| 1.5347        | 0.3   | 275  | 1.5138          |
+| 1.5042        | 0.32  | 300  | 1.5116          |
+| 1.4756        | 0.35  | 325  | 1.5098          |
+| 1.5102        | 0.38  | 350  | 1.5090          |
+| 1.4511        | 0.4   | 375  | 1.5087          |
+| 1.4451        | 0.43  | 400  | 1.5086          |
 
 
 ### Framework versions

adapter_config.json

@@ -9,13 +9,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e4301c3210d9ad410d97ca566cf53dc837d30047de7862997dd861d9175dd57
-size 27280152
+oid sha256:2300d183ddcd834bbb7795ea49262a1a2841235cfb7a94f1f3cb6d538d37996d
+size 13648432

runs/Mar05_02-31-09_6405a7751ebb/events.out.tfevents.1709605869.6405a7751ebb.256.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b91c0fc13e6d010c549f46fedfb3bf8ea8e27e2ed80a81e1933bdf2dc6695fa2
+size 9072

runs/Mar05_02-40-22_6405a7751ebb/events.out.tfevents.1709606423.6405a7751ebb.256.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47bbdde41e13602ab3de51029ccfaa31a0dcd61c39137d2592d8b8f6afc1dc0c
+size 13381

runs/Mar05_02-56-15_6405a7751ebb/events.out.tfevents.1709607375.6405a7751ebb.256.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44885be788d9ba4be41d9c882cb501b4374dcd33ca07e515590c02745fb6fb96
+size 18104

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14714efeba969b5e273a0ec575726db1dab900c47560aa299680860d560d34d7
+oid sha256:649f39e08241dcdf22fb0c06d4f471439369ff4a28c3a5d53ba3a51c02525508
 size 4920