Hugging Face's logo

nicholasKluge
/
Aira-2-774M

Text Generation
Transformers
PyTorch
Safetensors
English
gpt2
alignment
instruction tuned
text generation
conversation
assistant
text-generation-inference
Inference Endpoints
Model card Files Community
3
nicholasKluge commited on
Commit
af58710
•
1 Parent(s): bb535a2

Upload 12 files

Browse files
Files changed (5) hide show
  1. AIRA_FineTuning.ipynb +0 -0
  2. Aira_emissions.csv +1 -1
  3. README.md +6 -5
  4. pytorch_model.bin +1 -1
  5. training_stats.parquet +2 -2
AIRA_FineTuning.ipynb CHANGED
The diff for this file is too large to render. See raw diff
 
Aira_emissions.csv CHANGED
@@ -1,2 +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
- 2023-06-14T18:37:11,Aira_emissions,2a7c2a22-a4f1-4aad-8c1c-34d5199048e4,8730.918614387512,0.002277991408004105,2.609108512648654e-07,42.5,292.795,31.30528450012207,0.10307311259690251,0.7793010973870445,0.07588489401643905,0.9582591040003862,Canada,CAN,quebec,,,Linux-5.15.107+-x86_64-with-glibc2.31,3.10.12,2.2.3,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,-71.2,46.8,83.48075866699219,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
+ 2023-06-27T17:41:39,Aira_emissions,695450e2-752a-4892-b373-344fd693c2c0,11996.631135702133,0.003078239897738628,2.56592026788066e-07,42.5,309.968,31.30528450012207,0.14162658247964255,1.0489959445358172,0.10426883909804714,1.2948913661135033,Canada,CAN,quebec,,,Linux-5.15.107+-x86_64-with-glibc2.31,3.10.12,2.2.4,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,-71.2,46.8,83.48075866699219,machine,N,1.0
README.md CHANGED
@@ -49,17 +49,18 @@ Check our gradio-demo in [Spaces](https://huggingface.co/spaces/nicholasKluge/Ai
49
  - **Size:** 774,032,640 parameters
50
  - **Dataset:** [Instruct-Aira Dataset](https://huggingface.co/datasets/nicholasKluge/fine-tuning-instruct-aira)
51
  - **Language:** English
52
- - **Number of Epochs:** 2
53
  - **Batch size:** 8
54
  - **Optimizer:** `torch.optim.AdamW` (warmup_steps = 1e2, learning_rate = 5e-4, epsilon = 1e-8)
55
  - **GPU:** 1 NVIDIA A100-SXM4-40GB
56
- - **Emissions:** 0.0022 KgCO2 (Canada)
57
- - **Total Energy Consumption:** 0.95 kWh
58
 
59
  | Epoch/Loss|Training|Validation|
60
  |---|---|---|
61
- | 1 |0.687266|0.616128|
62
- | 2 |0.468581|0.582550|
 
63
 
64
  This repository has the notebook used to train this model.
65
 
 
49
  - **Size:** 774,032,640 parameters
50
  - **Dataset:** [Instruct-Aira Dataset](https://huggingface.co/datasets/nicholasKluge/fine-tuning-instruct-aira)
51
  - **Language:** English
52
+ - **Number of Epochs:** 3
53
  - **Batch size:** 8
54
  - **Optimizer:** `torch.optim.AdamW` (warmup_steps = 1e2, learning_rate = 5e-4, epsilon = 1e-8)
55
  - **GPU:** 1 NVIDIA A100-SXM4-40GB
56
+ - **Emissions:** 0.0030 KgCO2 (Canada)
57
+ - **Total Energy Consumption:** 1.29 kWh
58
 
59
  | Epoch/Loss|Training|Validation|
60
  |---|---|---|
61
+ | 1 |0.696885|0.638819|
62
+ | 2 |0.516360|0.610071|
63
+ | 3 |0.338896|0.647381|
64
 
65
  This repository has the notebook used to train this model.
66
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cc730a83ca89468d37553705b0fc07a5e20bc643a43e8dce7ccba4e93fa6a68
3
  size 3096272925
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7ecac413768a798438bdf5b4b89519d5fc70779b7dbaf7f6f041066c2a35b82
3
  size 3096272925
training_stats.parquet CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67af53f8de8a9927257116a5c8c06d33e757d57c2f2f8f4f5428060af02d0f88
3
- size 3041
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd3a6e1bb3fe18f8764638285deabbdb8f649768362e93ce72c1a2f986cc10e1
3
+ size 3063