Hugging Face's logo

nicholasKluge
/
Aira-2-portuguese-1B7

Text Generation
Transformers
PyTorch
Safetensors
Portuguese
bloom
alignment
instruction tuned
text generation
conversation
assistant
text-generation-inference
Inference Endpoints
Model card Files Community
2
nicholasKluge commited on
Commit
259d9a8
·
1 Parent(s): 36f87dc

Upload 10 files

Browse files
Files changed (5) hide show
  1. AIRA-FineTuning.ipynb +0 -0
  2. Aira_emissions.csv +2 -0
  3. README.md +5 -3
  4. pytorch_model.bin +1 -1
  5. training_stats.parquet +1 -1
AIRA-FineTuning.ipynb ADDED
The diff for this file is too large to render. See raw diff
 
Aira_emissions.csv ADDED
@@ -0,0 +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
+ 2023-06-28T17:49:42,Aira_emissions,6b04fcef-c13c-41a6-b3bd-1a9f62b0850c,16474.307428121567,0.0042805394926985745,2.598312257662324e-07,42.5,319.305,31.30528450012207,0.19448791941569915,1.462980110203074,0.14318228209838857,1.8006503117171597,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
@@ -55,11 +55,13 @@ Check our gradio-demo in [Spaces](https://huggingface.co/spaces/nicholasKluge/Ai
55
  - **Batch size:** 6
56
  - **Optimizer:** `torch.optim.AdamW` (warmup_steps = 1e2, learning_rate = 5e-4, epsilon = 1e-8)
57
  - **GPU:** 1 NVIDIA A100-SXM4-40GB
 
 
58
 
59
  | Epoch|Training Loss|Validation Loss|
60
  |---|---|---|
61
- | 1 |0.888486|0.744728|
62
- | 2 |0.749612|0.673719|
63
 
64
  This repository has the notebook used to train this model.
65
 
@@ -135,4 +137,4 @@ The model will output something like:
135
 
136
  ## License
137
 
138
- The `Aira-Instruct-PT-1B7` is licensed under the RAIL License since it is a model derived from BLOOM. See the [LICENSE](LICENSE) file for more details.
 
55
  - **Batch size:** 6
56
  - **Optimizer:** `torch.optim.AdamW` (warmup_steps = 1e2, learning_rate = 5e-4, epsilon = 1e-8)
57
  - **GPU:** 1 NVIDIA A100-SXM4-40GB
58
+ - **Emissions:** 0.0042 KgCO2 (Canada)
59
+ - **Total Energy Consumption:** 1.80 kWh
60
 
61
  | Epoch|Training Loss|Validation Loss|
62
  |---|---|---|
63
+ | 1 |0.934894|0.757459|
64
+ | 2 |0.596016|0.657159|
65
 
66
  This repository has the notebook used to train this model.
67
 
 
137
 
138
  ## License
139
 
140
+ The `Aira-Instruct-PT-1B7` is licensed under the RAIL License since it is a model derived from BLOOM. See the [LICENSE](LICENSE) file for more details.
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddd1d2d4499fd0d47ddbe8603f77fc50b7c2cc9774ecc5c28acf1b334ba27c43
3
  size 6888123065
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70307f2e5c188356faa659b0c204bf7a303ea48d116ab36813aa0cca8611876a
3
  size 6888123065
training_stats.parquet CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65d6fe57653ccd152157a2c97f4a6d24b5dce074b9cb76d99fca3a676c883c72
3
  size 3041
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:228351348fde2659ca9f8380bda715469c8531877a4c0d67dd6c0163ae3180c8
3
  size 3041