Model save

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3585
+- Loss: 3.1697
 
 ## Model description
 
@@ -44,26 +44,26 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 5    | 4.3933          |
-| No log        | 2.0   | 10   | 3.9756          |
-| No log        | 3.0   | 15   | 3.6976          |
-| No log        | 4.0   | 20   | 3.4543          |
-| No log        | 5.0   | 25   | 3.3670          |
-| No log        | 6.0   | 30   | 3.1792          |
-| No log        | 7.0   | 35   | 3.2279          |
-| No log        | 8.0   | 40   | 3.1757          |
-| No log        | 9.0   | 45   | 3.1405          |
-| No log        | 10.0  | 50   | 3.1790          |
-| No log        | 11.0  | 55   | 3.0931          |
-| No log        | 12.0  | 60   | 3.2821          |
-| No log        | 13.0  | 65   | 3.1401          |
-| No log        | 14.0  | 70   | 3.4084          |
-| No log        | 15.0  | 75   | 3.2298          |
-| No log        | 16.0  | 80   | 3.3617          |
-| No log        | 17.0  | 85   | 3.3480          |
-| No log        | 18.0  | 90   | 3.3395          |
-| No log        | 19.0  | 95   | 3.3490          |
-| No log        | 20.0  | 100  | 3.3585          |
+| No log        | 1.0   | 5    | 4.4037          |
+| No log        | 2.0   | 10   | 4.0421          |
+| No log        | 3.0   | 15   | 3.7532          |
+| No log        | 4.0   | 20   | 3.4743          |
+| No log        | 5.0   | 25   | 3.2870          |
+| No log        | 6.0   | 30   | 3.1440          |
+| No log        | 7.0   | 35   | 3.1557          |
+| No log        | 8.0   | 40   | 3.0726          |
+| No log        | 9.0   | 45   | 3.0422          |
+| No log        | 10.0  | 50   | 3.0519          |
+| No log        | 11.0  | 55   | 3.0486          |
+| No log        | 12.0  | 60   | 3.0460          |
+| No log        | 13.0  | 65   | 3.1139          |
+| No log        | 14.0  | 70   | 3.1018          |
+| No log        | 15.0  | 75   | 3.1321          |
+| No log        | 16.0  | 80   | 3.1490          |
+| No log        | 17.0  | 85   | 3.1264          |
+| No log        | 18.0  | 90   | 3.1661          |
+| No log        | 19.0  | 95   | 3.1706          |
+| No log        | 20.0  | 100  | 3.1697          |
 
 
 ### Framework versions

emissions.csv

@@ -1,3 +1,4 @@
 timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
 2024-02-23T22:53:22,codecarbon,7bc17b19-652d-40a5-93eb-3921d3a60d4c,49.278987407684326,0.0073339536445992,0.0001488251693145,112.5,701.268,377.8925685882568,0.0015399516373872,0.0140255498696223,0.0051333462609472,0.0206988477679569,Germany,DEU,free and hanseatic city of hamburg,,,Linux-5.15.0-76-generic-x86_64-with-glibc2.35,3.11.4,2.2.3,128,AMD EPYC 7543 32-Core Processor,4,4 x NVIDIA A40,9.9683,53.5649,1007.7135162353516,machine,N,1.0
-2024-02-23T22:55:48,codecarbon,fadcf6be-5da8-4758-bd62-61555e97f939,49.529038190841675,0.006806918164048851,0.0001374328759993467,112.5,539.9780000000001,377.89256858825684,0.0015477617010474206,0.012511630999930171,0.005151986273355712,0.0192113789743333,Germany,DEU,free and hanseatic city of hamburg,,,Linux-5.15.0-76-generic-x86_64-with-glibc2.35,3.11.4,2.2.3,128,AMD EPYC 7543 32-Core Processor,4,4 x NVIDIA A40,9.9683,53.5649,1007.7135162353516,machine,N,1.0
+2024-02-23T22:55:48,codecarbon,fadcf6be-5da8-4758-bd62-61555e97f939,49.52903819084168,0.0068069181640488,0.0001374328759993,112.5,539.9780000000001,377.8925685882568,0.0015477617010474,0.0125116309999301,0.0051519862733557,0.0192113789743333,Germany,DEU,free and hanseatic city of hamburg,,,Linux-5.15.0-76-generic-x86_64-with-glibc2.35,3.11.4,2.2.3,128,AMD EPYC 7543 32-Core Processor,4,4 x NVIDIA A40,9.9683,53.5649,1007.7135162353516,machine,N,1.0
+2024-02-23T22:58:58,codecarbon,ab306e8c-f450-4f8a-a68e-de7614155a39,49.52354431152344,0.005778290856184921,0.00011667765174150497,112.5,485.40000000000003,377.89256858825684,0.0015475891903042793,0.009611609490438768,0.005149053128187716,0.016308251808930762,Germany,DEU,free and hanseatic city of hamburg,,,Linux-5.15.0-76-generic-x86_64-with-glibc2.35,3.11.4,2.2.3,128,AMD EPYC 7543 32-Core Processor,4,4 x NVIDIA A40,9.9683,53.5649,1007.7135162353516,machine,N,1.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f50d8fb94040bf685b761e779305680598b56e89d2cbfebb1e811fb46be001c
+oid sha256:ffcd7564adb60aba64746eaa16f6b88c2d16d3e6d8eebbd4958bbbb85702b6bc
 size 433992496

runs/Feb23_22-54-52_hcdsgpu2/events.out.tfevents.1708728967.hcdsgpu2.3260472.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2331ba21a7ac78a1e56e88aaa64cb61121b14e9a03a4281a182a6be006e7d672
+size 354

runs/Feb23_22-58-02_hcdsgpu2/events.out.tfevents.1708729089.hcdsgpu2.3262615.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:680ff6eca2b6865c47005e2c74bad5d9ec81e89c40da9d2dc5edf52aba03005a
+size 10049

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f770fb034e89bede5f02fcd1d362f1ab4bfeea4f3f0a8e388191707b4fff8245
+oid sha256:e7d8ed222a920b235482876151a2f8adf050ccb0c697d63179db9e5dc9c81772
 size 4728