farid1088 commited on
Commit
14c2880
verified
1 Parent(s): db30287

Model save

Browse files
README.md CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model was trained from scratch on the None dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 3.3356
17
 
18
  ## Model description
19
 
@@ -44,26 +44,26 @@ The following hyperparameters were used during training:
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
- | No log | 1.0 | 5 | 4.3515 |
48
- | No log | 2.0 | 10 | 3.9809 |
49
- | No log | 3.0 | 15 | 3.6622 |
50
- | No log | 4.0 | 20 | 3.4173 |
51
- | No log | 5.0 | 25 | 3.3053 |
52
- | No log | 6.0 | 30 | 3.1078 |
53
- | No log | 7.0 | 35 | 3.1207 |
54
- | No log | 8.0 | 40 | 3.1541 |
55
- | No log | 9.0 | 45 | 3.1083 |
56
- | No log | 10.0 | 50 | 3.0859 |
57
- | No log | 11.0 | 55 | 3.0937 |
58
- | No log | 12.0 | 60 | 3.1166 |
59
- | No log | 13.0 | 65 | 3.2106 |
60
- | No log | 14.0 | 70 | 3.2250 |
61
- | No log | 15.0 | 75 | 3.3418 |
62
- | No log | 16.0 | 80 | 3.2811 |
63
- | No log | 17.0 | 85 | 3.2969 |
64
- | No log | 18.0 | 90 | 3.3815 |
65
- | No log | 19.0 | 95 | 3.3449 |
66
- | No log | 20.0 | 100 | 3.3356 |
67
 
68
 
69
  ### Framework versions
 
13
 
14
  This model was trained from scratch on the None dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 3.1616
17
 
18
  ## Model description
19
 
 
44
 
45
  | Training Loss | Epoch | Step | Validation Loss |
46
  |:-------------:|:-----:|:----:|:---------------:|
47
+ | No log | 1.0 | 5 | 4.3922 |
48
+ | No log | 2.0 | 10 | 4.0291 |
49
+ | No log | 3.0 | 15 | 3.7742 |
50
+ | No log | 4.0 | 20 | 3.4874 |
51
+ | No log | 5.0 | 25 | 3.2930 |
52
+ | No log | 6.0 | 30 | 3.1885 |
53
+ | No log | 7.0 | 35 | 3.1282 |
54
+ | No log | 8.0 | 40 | 3.0193 |
55
+ | No log | 9.0 | 45 | 3.1205 |
56
+ | No log | 10.0 | 50 | 2.9801 |
57
+ | No log | 11.0 | 55 | 3.1418 |
58
+ | No log | 12.0 | 60 | 2.9822 |
59
+ | No log | 13.0 | 65 | 3.1917 |
60
+ | No log | 14.0 | 70 | 3.0582 |
61
+ | No log | 15.0 | 75 | 3.2002 |
62
+ | No log | 16.0 | 80 | 3.1093 |
63
+ | No log | 17.0 | 85 | 3.1141 |
64
+ | No log | 18.0 | 90 | 3.1722 |
65
+ | No log | 19.0 | 95 | 3.1659 |
66
+ | No log | 20.0 | 100 | 3.1616 |
67
 
68
 
69
  ### Framework versions
emissions.csv CHANGED
@@ -1,3 +1,2 @@
1
  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
2
- 2024-02-23T22:39:37,codecarbon,09385177-b783-4897-993d-0dac5cfcc970,49.35550737380981,0.0068169434273451,0.0001381192047265,112.5,658.766,377.8925685882568,0.0015423422157764,0.0125618992264898,0.0051354321476125,0.0192396735898788,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
3
- 2024-02-23T22:43:50,codecarbon,630265e1-93fd-4252-8a90-fc6d65603f59,49.40052318572998,0.006684141493059076,0.00013530507496709837,112.5,1000.4390000000001,377.89256858825684,0.0015437498688697815,0.012177606644799048,0.0051435060050900126,0.01886486251875884,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
 
1
  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
2
+ 2024-02-23T22:48:59,codecarbon,b95fc182-fa7b-479d-b814-558f3e434cb9,49.5593364238739,0.0070984810748494715,0.00014323196368363732,112.5,855.774,377.89256858825684,0.0015487124621868136,0.013326221749784947,0.00515933192498885,0.020034266136960608,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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afb8810034dbf6004ceff929361e59528d99de58206c21a79b0351c7857958b2
3
  size 433992496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe9656b60a0f92c48fc7345f11a817e7df498056917eae8fc19b0f5a356b0b97
3
  size 433992496
runs/Feb23_22-48-03_hcdsgpu2/events.out.tfevents.1708728489.hcdsgpu2.3256102.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16732117ee8649a6d811275ff5232533d5a86f468116ba12f8911b58d92908b7
3
+ size 10049
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8020ae4ffde60a6825d9cd5f002e291650c4a82bf5c1348a22299613337dc375
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08e29b166ac21b8504d34e22ee8cd66b58f7715899e894a47ce97958315eb2a3
3
  size 4728