datajose/pruebas-ft

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.1762
+- Loss: 3.3561
 
 ## Model description
 
@@ -44,32 +44,22 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 2
-- num_epochs: 20
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 4.0698        | 0.96  | 20   | 3.1762          |
-| 3.8745        | 1.98  | 41   | 3.1762          |
-| 3.8712        | 2.99  | 62   | 3.1762          |
-| 3.8708        | 4.0   | 83   | 3.1762          |
-| 4.0664        | 4.96  | 103  | 3.1762          |
-| 3.8739        | 5.98  | 124  | 3.1762          |
-| 3.8743        | 6.99  | 145  | 3.1762          |
-| 3.8717        | 8.0   | 166  | 3.1762          |
-| 4.0685        | 8.96  | 186  | 3.1762          |
-| 3.8727        | 9.98  | 207  | 3.1762          |
-| 3.8712        | 10.99 | 228  | 3.1762          |
-| 3.8747        | 12.0  | 249  | 3.1762          |
-| 4.0631        | 12.96 | 269  | 3.1762          |
-| 3.8709        | 13.98 | 290  | 3.1762          |
-| 3.8746        | 14.99 | 311  | 3.1762          |
-| 3.8771        | 16.0  | 332  | 3.1762          |
-| 4.0657        | 16.96 | 352  | 3.1762          |
-| 3.8752        | 17.98 | 373  | 3.1762          |
-| 3.8724        | 18.99 | 394  | 3.1762          |
-| 3.7421        | 19.28 | 400  | 3.1762          |
+| 4.0698        | 0.96  | 20   | 3.3561          |
+| 3.8745        | 1.98  | 41   | 3.3561          |
+| 3.8712        | 2.99  | 62   | 3.3561          |
+| 3.8708        | 4.0   | 83   | 3.3561          |
+| 4.0664        | 4.96  | 103  | 3.3561          |
+| 3.8739        | 5.98  | 124  | 3.3561          |
+| 3.8743        | 6.99  | 145  | 3.3561          |
+| 3.8717        | 8.0   | 166  | 3.3561          |
+| 4.0685        | 8.96  | 186  | 3.3561          |
+| 3.7098        | 9.64  | 200  | 3.3561          |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b4a0dad478cd518d4e0e83bcd8771d6768679048eb2460b8dd52d62878b3b20
+oid sha256:446fcd691c1e1e5a2f71a0a2e017029483d413401ea14448e388e89c564ab46f
 size 8397056

emissions.csv

@@ -11,4 +11,5 @@ timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_po
 2024-03-10T20:22:30,codecarbon,9d590d08-fe02-4937-ae3e-a1f79e659dd7,38.62720036506653,0.0017985526638062,4.6561817755573886e-05,42.5,347.466,23.216667652130127,0.0004560011797481,0.0036092515765909,0.0002490543572167,0.0043143071135558,Chile,CHL,santiago metropolitan,,,Linux-6.5.0-25-generic-x86_64-with-glibc2.35,3.10.13,2.2.3,32,AMD Ryzen 9 7950X3D 16-Core Processor,1,1 x NVIDIA GeForce RTX 4090,-70.6536,-33.4521,61.91111373901367,machine,N,1.0
 2024-03-10T20:36:48,codecarbon,ca101f7c-cb99-40c0-b57c-22db52c4cc9c,38.63142704963684,0.001878292403504,4.86208392221862e-05,42.5,332.107,23.216667652130127,0.0004560509007838,0.0038004781568025,0.0002490550383643,0.0045055840959506,Chile,CHL,santiago metropolitan,,,Linux-6.5.0-25-generic-x86_64-with-glibc2.35,3.10.13,2.2.3,32,AMD Ryzen 9 7950X3D 16-Core Processor,1,1 x NVIDIA GeForce RTX 4090,-70.6536,-33.4521,61.91111373901367,machine,N,1.0
 2024-03-10T20:40:15,codecarbon,7893daa1-51e8-41fa-8d9b-d4731cb9345f,38.76287388801575,0.0018375077998772,4.740380718895457e-05,42.5,330.75100000000003,23.216667652130127,0.0004576034214761,0.0037002286423981,0.0002499193085251,0.0044077513723994,Chile,CHL,santiago metropolitan,,,Linux-6.5.0-25-generic-x86_64-with-glibc2.35,3.10.13,2.2.3,32,AMD Ryzen 9 7950X3D 16-Core Processor,1,1 x NVIDIA GeForce RTX 4090,-70.6536,-33.4521,61.91111373901367,machine,N,1.0
-2024-03-10T20:50:36,codecarbon,0659ba9e-96ec-4226-ad88-0583b83515c0,207.96208953857422,0.011353635643457104,5.459473728432198e-05,42.5,340.217,23.216667652130127,0.0024550311161412133,0.02343889273893085,0.0013407921513113028,0.02723471600638337,Chile,CHL,santiago metropolitan,,,Linux-6.5.0-25-generic-x86_64-with-glibc2.35,3.10.13,2.2.3,32,AMD Ryzen 9 7950X3D 16-Core Processor,1,1 x NVIDIA GeForce RTX 4090,-70.6536,-33.4521,61.91111373901367,machine,N,1.0
+2024-03-10T20:50:36,codecarbon,0659ba9e-96ec-4226-ad88-0583b83515c0,207.96208953857425,0.0113536356434571,5.459473728432198e-05,42.5,340.217,23.216667652130127,0.0024550311161412,0.0234388927389308,0.0013407921513113,0.0272347160063833,Chile,CHL,santiago metropolitan,,,Linux-6.5.0-25-generic-x86_64-with-glibc2.35,3.10.13,2.2.3,32,AMD Ryzen 9 7950X3D 16-Core Processor,1,1 x NVIDIA GeForce RTX 4090,-70.6536,-33.4521,61.91111373901367,machine,N,1.0
+2024-03-10T20:56:37,codecarbon,dfa2780e-e29b-4391-bc07-8204e5fbc398,104.18094682693481,0.005671600520267414,5.4439901853542046e-05,42.5,322.27500000000003,23.216667652130127,0.0012298772917853462,0.011703282043502065,0.0006716835821576476,0.01360484291744506,Chile,CHL,santiago metropolitan,,,Linux-6.5.0-25-generic-x86_64-with-glibc2.35,3.10.13,2.2.3,32,AMD Ryzen 9 7950X3D 16-Core Processor,1,1 x NVIDIA GeForce RTX 4090,-70.6536,-33.4521,61.91111373901367,machine,N,1.0

runs/Mar10_20-54-48_datajose/events.out.tfevents.1710114893.datajose.132044.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:176be7662035019d2bc42191e982acf6b52de04ce8183db04a481dd2332922e9
+size 10343

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c7853f11e23e191c3706b8da0c31193facf0be70268911e69b1f07bde323328
+oid sha256:3f281f479637f005adb466a929274e10e765c3aa9528f9ac781f1e9cfa4631a7
 size 4920