fixing bugs

app.py

@@ -11,6 +11,7 @@ CACHED_FILE_PATH = hf_hub_download(repo_id="sasha/co2_submissions", filename="co
 api = HfApi()
 
 def write_to_csv(hardware, gpu_tdp, num_gpus, training_time, provider, carbon_intensity, dynamic_emissions, experimentation_time, experimental_emissions, pue, pue_emissions, embodied_type, embodied_emissions, model_info):
+    st.session_state["is_shared"] = True
     with open(CACHED_FILE_PATH,'a', newline='') as f:
         writer = csv.writer(f)
         writer.writerow([hardware, gpu_tdp, num_gpus, training_time, provider, carbon_intensity, dynamic_emissions, experimentation_time, experimental_emissions, pue, pue_emissions, embodied_type, embodied_emissions, model_info])
@@ -67,6 +68,7 @@ model_info = "N/A"
 ### Conversion factors
 kg_per_mile = 0.348
 embodied_conversion_factor = 0.0289
+st.session_state["is_shared"] = False
 
 electricity = pd.read_csv(electricity_url)
 servers = pd.read_csv(server_url)
@@ -86,47 +88,46 @@ with st.expander("Calculate the dynamic emissions of your model"):
     with col1:
         hardware = st.selectbox('Hardware used', TDP['name'].tolist())
         gpu_tdp = TDP['tdp_watts'][TDP['name'] == hardware].tolist()[0]
-        st.markdown("Different hardware has different TDP (Thermal Design Power), which impacts how much energy you use.")
+        st.markdown("Different hardware has different efficiencies, which impacts how much energy you use.")
     with col2:
        num_gpus = st.text_input('Number of GPUs/CPUs/TPUs used', value = 16)
-       #st.markdown('This is calculated by multiplying the number of GPUs you used by the training time: '
-        #           'i.e. if you used 100 GPUs for 10 hours, this is equal to 100x10 = 1,000 GPU hours.')
+       st.markdown('If you can\'t find your hardware in the list, select the closest similar model.')
     with col3:
        training_time = st.number_input('Total training time (in hours)', value = 0.0)
+       st.markdown('You can find this number in your training logs or TensorBoards')
     with col4:
        provider = st.selectbox('Provider used', providers)
        st.markdown('If you can\'t find your provider here, select "Local/Private Infrastructure".')
     with col5:
         if provider != 'Local/Private Infastructure':
             provider_instances = instances['region'][instances['provider'] == provider.lower()].unique().tolist()
-            region = st.selectbox('Provider used', provider_instances)
+            region = st.selectbox('Region used', provider_instances)
             carbon_intensity = instances['impact'][(instances['provider'] == provider.lower()) & (instances['region'] == region)].tolist()[0]
-
         else:
             carbon_intensity = st.number_input('Carbon intensity of your energy grid, in grams of CO2 per kWh')
             st.markdown('You can consult a resource like the [IEA](https://www.iea.org/countries) or '
                         ' [Electricity Map](https://app.electricitymaps.com/) to get this information.')
     dynamic_emissions = round(gpu_tdp * float(num_gpus)*training_time * carbon_intensity/1000000)
     st.metric(label="Dynamic emissions", value=str(dynamic_emissions)+' kilograms of CO2eq')
-    st.markdown('This is roughly equivalent to '+ str(round(dynamic_emissions/kg_per_mile,1)) + ' miles driven in an average US car'
+    st.info('This is roughly equivalent to '+ str(round(dynamic_emissions/kg_per_mile,1)) + ' miles driven in an average US car'
     ' produced in 2021. [(Source: energy.gov)](https://www.energy.gov/eere/vehicles/articles/fotw-1223-january-31-2022-average-carbon-dioxide-emissions-2021-model-year)')
 
 st.markdown('### Experimental Emissions 👩‍🔬')
 st.markdown('##### These are the emissions produced by generating the electricity necessary for powering the experiments and tests needed to pick your final model architecture '
             'and parameters.')
 with st.expander("Calculate the experimental emissions of your model"):
-            st.markdown('##### Consult your training logs to figure out how many ablations, baselines and experiments were run before converging on the final model.')
+            st.info('Consult your training logs to figure out how many ablations, baselines and experiments were run before converging on the final model.')
             experimentation_time = st.number_input(label='Number of hours of experimentation run', value=training_time)
             st.markdown('##### As a baseline, language models such as [OPT](https://arxiv.org/pdf/2205.01068.pdf) and [BLOOM](https://arxiv.org/abs/2211.02001)'
                         ' found that experimentation roughly doubles the amount of compute used by training the model itself.')
             experimental_emissions = round(gpu_tdp * (experimentation_time) * carbon_intensity/1000000)
-            st.metric(label="Experimental emissions", value=str(0.0)+' kilograms of CO2eq')
+            st.metric(label="Experimental emissions", value=str(experimental_emissions)+' kilograms of CO2eq')
 
 st.markdown('### Datacenter (Overhead) Emissions 🌐')
 st.markdown('##### These are the emissions produced by generating the electricity needed to power the rest of the infrastructure'
             'used for model training -- the datacenter, network, heating/cooling, storage, etc.')
 with st.expander("Calculate the idle emissions of your model"):
-    st.markdown('##### A proxy often used to reflect idle emissions is PUE (Power Usage Effectiveness), which represents '
+    st.info('A proxy often used to reflect idle emissions is PUE (Power Usage Effectiveness), which represents '
                 ' the ratio of energy used for computing overheads like cooling, which varies depending on the data center.')
     pue = instances['PUE'][(instances['provider'] == provider.lower()) & (instances['region'] == region)].tolist()[0]
     if math.isnan(pue) == True:
@@ -186,9 +187,13 @@ div.stButton > button:first-child {
     width: 15em;
 }
 </style>""", unsafe_allow_html=True)
+
 buttoncol1, buttoncol2, buttoncol3 = st.columns(3)
 with buttoncol2:
-    st.button(label="Share my CO2 data!", on_click = lambda *args: write_to_csv(hardware, gpu_tdp, num_gpus, training_time, provider, carbon_intensity, dynamic_emissions, experimentation_time, experimental_emissions, pue, pue_emissions, embodied_type, embodied_emissions, model_info))
+    if st.session_state["is_shared"] == False:
+        submitted = st.button(label="Share my CO2 data!", on_click = lambda *args: write_to_csv(hardware, gpu_tdp, num_gpus, training_time, provider, carbon_intensity, dynamic_emissions, experimentation_time, experimental_emissions, pue, pue_emissions, embodied_type, embodied_emissions, model_info))
+    else:
+        st.info('Thank you! Your data has been shared in https://huggingface.co/datasets/sasha/co2_submissions.')
 
 st.markdown('### Methodology')
 with st.expander("More information about our Methodology"):