Model save

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ro](https://huggingface.co/Helsinki-NLP/opus-mt-en-ro) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.2457
-- Bleu: 28.3282
-- Gen Len: 33.9535
+- Loss: 1.2557
+- Bleu: 28.2746
+- Gen Len: 33.9825
 
 ## Model description
 
@@ -39,8 +39,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 128
-- eval_batch_size: 128
+- train_batch_size: 48
+- eval_batch_size: 48
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -49,9 +49,9 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
-| 0.7553        | 1.0   | 4769 | 1.2457          | 28.3282 | 33.9535 |
+| Training Loss | Epoch | Step  | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
+| 0.7438        | 1.0   | 12715 | 1.2557          | 28.2746 | 33.9825 |
 
 
 ### Framework versions

emissions.csv

@@ -1,2 +1,3 @@
 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
-2024-08-06T14:11:53,codecarbon,1f15ae92-3ddc-4a23-9a5a-4ad235604025,2646.9103710651398,0.3032049614015296,0.0001145505207565896,112.5,323.629,377.89435958862305,0.08269974178820845,0.496412659532951,0.2766324864531485,0.8557448877743082,Germany,DEU,north rhine-westphalia,,,Linux-5.15.0-113-generic-x86_64-with-glibc2.29,3.8.10,2.2.3,128,AMD EPYC 7542 32-Core Processor,8,8 x NVIDIA A100-PCIE-40GB,6.7958,51.0015,1007.7182922363281,machine,N,1.0
+2024-08-06T14:11:53,codecarbon,1f15ae92-3ddc-4a23-9a5a-4ad235604025,2646.91037106514,0.3032049614015296,0.0001145505207565,112.5,323.629,377.8943595886231,0.0826997417882084,0.496412659532951,0.2766324864531485,0.8557448877743082,Germany,DEU,north rhine-westphalia,,,Linux-5.15.0-113-generic-x86_64-with-glibc2.29,3.8.10,2.2.3,128,AMD EPYC 7542 32-Core Processor,8,8 x NVIDIA A100-PCIE-40GB,6.7958,51.0015,1007.718292236328,machine,N,1.0
+2024-08-06T15:36:26,codecarbon,6e474307-5293-4e9e-9420-e5ce5cca73e4,2136.127326965332,0.24348483498552415,0.00011398423301453123,112.5,349.085,377.89435958862305,0.06674298617988825,0.39722219058706804,0.22322972211038797,0.6871948988773448,Germany,DEU,north rhine-westphalia,,,Linux-5.15.0-113-generic-x86_64-with-glibc2.29,3.8.10,2.2.3,128,AMD EPYC 7542 32-Core Processor,8,8 x NVIDIA A100-PCIE-40GB,6.7958,51.0015,1007.7182922363281,machine,N,1.0

runs/Aug06_15-00-40_ki-jupyternotebook-8cb7/events.out.tfevents.1722949247.ki-jupyternotebook-8cb7.211427.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fca92e17eafee9d52ddbbac5e55b6dabf1785e1edc997a1fc96971ba489d4c7
-size 11162
+oid sha256:5a1c046121f486179ea90b057e2a248401c6990c7b85adaf90da69c5bdaf0035
+size 11886