End of training

README.md

@@ -15,12 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.7713
-- eval_runtime: 1.2308
-- eval_samples_per_second: 131.621
-- eval_steps_per_second: 17.062
-- epoch: 10.0
-- step: 810
+- Loss: 1.5773
 
 ## Model description
 
@@ -45,7 +40,18 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 35
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 152  | 1.7610          |
+| No log        | 2.0   | 304  | 1.6016          |
+| No log        | 3.0   | 456  | 1.6983          |
+| 1.7793        | 4.0   | 608  | 1.5543          |
+| 1.7793        | 5.0   | 760  | 1.5773          |
+
 
 ### Framework versions
 

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "distilroberta-base",
   "architectures": [
-    "RobertaForCausalLM"
+    "RobertaForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b264184042e4c827159ec12eb2c91c666909b4d4082b96a87f1579df6de431b
+oid sha256:2c3b7cd01cee5d4542cb7d70255e68247b04bad42473b8c06a9f455393dc1f6b
 size 328693404

runs/Jan07_19-50-54_2c2be611b99b/events.out.tfevents.1704658385.2c2be611b99b.440.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a2440f8473a057ef018197a4fb4fb1afdf2b0342ec90bcbc2aad914a1735a36
+size 6184

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03f7ac533c67dbdb36c83c2d61eb285b9a76adadfd483dc65d54b72e47a325c0
+oid sha256:d6f07bd059f049dca6881fe97a401f42ffd1bc82747cd1bc67303d46411b5484
 size 4600