Training in progress epoch 0

README.md

@@ -12,11 +12,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # EternalRecursion/roberta-finetuned-poetry
 
-This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 1.9830
-- Validation Loss: 1.8248
-- Epoch: 2
+- Train Loss: 2.0071
+- Validation Loss: 1.7287
+- Epoch: 0
 
 ## Model description
 
@@ -42,9 +42,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.1615     | 1.8898          | 0     |
-| 2.0215     | 1.8530          | 1     |
-| 1.9830     | 1.8248          | 2     |
+| 2.0071     | 1.7287          | 0     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "roberta-base",
+  "_name_or_path": "roberta-large",
   "architectures": [
     "RobertaForMaskedLM"
   ],
@@ -9,14 +9,14 @@
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "transformers_version": "4.28.1",

logs/train/events.out.tfevents.1682888132.t1v-n-54f58e78-w-0.75868.0.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefbe0549c04077ca1c9fe5d82847584ecbf0850fd6c6dfec940df9b166b14a6
+size 6899234

logs/validation/events.out.tfevents.1682888749.t1v-n-54f58e78-w-0.75868.1.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f8a8612bffee7334b81f8d83f93332e7179158a15d43f7d84d834dbc4972fe
+size 232

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca33c1f167ff837cf9943d9e7451ca95f63c6d5044281718899715f0ab83c0f6
-size 655071156
+oid sha256:6015426abbe3ddccc7096a1ed433aa0ce3145280488134f34ef72d88d28476e9
+size 1630210764