Model save

README.md

@@ -12,6 +12,8 @@ should probably proofread and complete it, then remove this comment. -->
 # QA_BERT
 
 This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.2396
 
 ## Model description
 
@@ -31,18 +33,42 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 1
+- train_batch_size: 160
+- eval_batch_size: 5
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 25
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 20   | 4.1116          |
+| No log        | 1.0   | 2    | 5.4190          |
+| No log        | 2.0   | 4    | 4.8218          |
+| No log        | 3.0   | 6    | 4.3918          |
+| No log        | 4.0   | 8    | 4.2001          |
+| No log        | 5.0   | 10   | 4.0566          |
+| No log        | 6.0   | 12   | 3.9085          |
+| No log        | 7.0   | 14   | 3.8141          |
+| No log        | 8.0   | 16   | 3.7379          |
+| No log        | 9.0   | 18   | 3.6321          |
+| No log        | 10.0  | 20   | 3.5224          |
+| No log        | 11.0  | 22   | 3.4364          |
+| No log        | 12.0  | 24   | 3.3735          |
+| No log        | 13.0  | 26   | 3.3156          |
+| No log        | 14.0  | 28   | 3.2998          |
+| No log        | 15.0  | 30   | 3.2754          |
+| No log        | 16.0  | 32   | 3.2459          |
+| No log        | 17.0  | 34   | 3.2334          |
+| No log        | 18.0  | 36   | 3.2419          |
+| No log        | 19.0  | 38   | 3.2581          |
+| No log        | 20.0  | 40   | 3.2433          |
+| No log        | 21.0  | 42   | 3.2243          |
+| No log        | 22.0  | 44   | 3.2226          |
+| No log        | 23.0  | 46   | 3.2273          |
+| No log        | 24.0  | 48   | 3.2356          |
+| No log        | 25.0  | 50   | 3.2396          |
 
 
 ### Framework versions

emissions.csv

@@ -1,2 +1,2 @@
 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
-2024-02-28T17:49:04,codecarbon,8408ce30-9c7a-47a4-8ec1-f7b0dd5ab821,67.4074354171753,0.003253222976781421,4.826207905177929e-05,112.5,0.0,377.8920850753784,0.0021064516454935077,0,0.00707522176216523,0.009181673407658738,Germany,DEU,free and hanseatic city of hamburg,,,Linux-5.15.0-91-generic-x86_64-with-glibc2.35,3.11.4,2.2.3,128,AMD EPYC 7543 32-Core Processor,,,9.9683,53.5649,1007.7122268676758,machine,N,1.0
+2024-03-01T15:36:28,codecarbon,3f9152c4-ab28-4a82-948a-28b75c998a7a,124.66902875900269,0.01357017598308951,0.00010884961660623806,112.5,452.243,377.8920922279358,0.0038958391025662423,0.021338467936003472,0.013065226946786638,0.03829953398535636,Germany,DEU,free and hanseatic city of hamburg,,,Linux-5.15.0-97-generic-x86_64-with-glibc2.35,3.11.4,2.2.3,128,AMD EPYC 7543 32-Core Processor,5,4 x NVIDIA A401 x NVIDIA A100 80GB PCIe,9.9683,53.5649,1007.7122459411621,machine,N,1.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b696b5f0233774af5bd5646e8bc2147ae50108912c22ad931f0697a6408df5d4
+oid sha256:65cb7effd65ea4131dcc23b65bcd5a1598550d43ef18a365a27d820f843f7595
 size 433992496

runs/Mar01_14-40-33_hcdsgpu1/events.out.tfevents.1709304039.hcdsgpu1.3470.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6edc4681065f510e51931465d0314ecc3a72a2b6ba17d007b63ab9d2459bff13
+size 5600

runs/Mar01_15-34-17_hcdsgpu1/events.out.tfevents.1709307263.hcdsgpu1.3987.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:927e20f65ee065e1d93bdd2b92f8e1c4cbbb8e0945482303a0c891fbf52e2d52
+size 11534

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 384,
+    "strategy": "OnlySecond",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 384
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb174cb6e0fa732b70106bb9f5f3ed03bb6205c27cd628827291a20830d5c18
+oid sha256:b7f40b14dcbdc954ae87d91db46eef7a4b169588879bc82b917d3966ee4f084b
 size 4856