End of training

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: google-bert/bert-base-uncased
+base_model: google-bert/bert-large-uncased
 tags:
 - generated_from_trainer
 metrics:
@@ -16,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # structured_conservation_gc_function_bert
 
-This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [google-bert/bert-large-uncased](https://huggingface.co/google-bert/bert-large-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6299
-- Accuracy: 0.6983
+- Loss: 0.6350
+- Accuracy: 0.7044
 
 ## Model description
 
@@ -50,12 +50,12 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 383  | 0.6481          | 0.6849   |
-| 0.5879        | 2.0   | 766  | 0.6189          | 0.6910   |
-| 0.522         | 3.0   | 1149 | 0.6378          | 0.6971   |
-| 0.4999        | 4.0   | 1532 | 0.6278          | 0.6995   |
-| 0.4999        | 5.0   | 1915 | 0.6194          | 0.7056   |
-| 0.4944        | 6.0   | 2298 | 0.6299          | 0.6983   |
+| No log        | 1.0   | 383  | 0.6999          | 0.5888   |
+| 0.6192        | 2.0   | 766  | 0.6385          | 0.6983   |
+| 0.5689        | 3.0   | 1149 | 0.6443          | 0.6825   |
+| 0.5426        | 4.0   | 1532 | 0.6373          | 0.6898   |
+| 0.5426        | 5.0   | 1915 | 0.6257          | 0.7080   |
+| 0.5315        | 6.0   | 2298 | 0.6350          | 0.7044   |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google-bert/bert-base-uncased",
+  "_name_or_path": "google-bert/bert-large-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -8,14 +8,14 @@
   "gradient_checkpointing": false,
   "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-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87b082f12ff3114ab58b4e54923ac65b49860a1c246255b1639b14e2eef07f4f
-size 437958648
+oid sha256:0bd4790f01e6280e6539de0584d35683d51ba419f12d59125f74030f1977889a
+size 1340622760

runs/Jan22_19-22-32_851f0b5fc26f/events.out.tfevents.1737573756.851f0b5fc26f.767.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6614c66515eb71e6be0771372ff2813ec0293ab6dadc80a02c6ec11efabe4e1
+size 7854

runs/Jan22_19-27-32_851f0b5fc26f/events.out.tfevents.1737574077.851f0b5fc26f.767.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da7aeaceef73c4fd480c373b5c484e9416d4957522b32bfbf21d2119868ed60
+size 8279

runs/Jan22_19-39-26_851f0b5fc26f/events.out.tfevents.1737574777.851f0b5fc26f.767.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3374215f3a5dfaa989fe8b944b9b8255abae661d970be54b574eb29995597665
+size 8279

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fb21a0a00aa20e56810c5f437f767afa1e350fd4b1a6715f81b5484adbe96e5
+oid sha256:f6f19a2cd49bea21f1308b0a3e343c388be4f1ccaffdf27ec85f09445b10da77
 size 5368