End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: t5-base
+base_model: t5-large
 tags:
 - generated_from_trainer
 model-index:
@@ -13,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # occ_extractor
 
-This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
+This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1291
+- Loss: 0.0260
 
 ## Model description
 
@@ -46,26 +46,26 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.5491        | 1.0   | 26   | 3.2512          |
-| 1.628         | 2.0   | 52   | 1.8521          |
-| 1.7683        | 3.0   | 78   | 1.2445          |
-| 0.7533        | 4.0   | 104  | 0.8269          |
-| 1.5694        | 5.0   | 130  | 0.5890          |
-| 0.7123        | 6.0   | 156  | 0.4530          |
-| 0.6509        | 7.0   | 182  | 0.3668          |
-| 0.5216        | 8.0   | 208  | 0.3004          |
-| 0.3966        | 9.0   | 234  | 0.2569          |
-| 0.2632        | 10.0  | 260  | 0.2259          |
-| 0.4013        | 11.0  | 286  | 0.2019          |
-| 0.669         | 12.0  | 312  | 0.1826          |
-| 0.1427        | 13.0  | 338  | 0.1691          |
-| 0.1859        | 14.0  | 364  | 0.1581          |
-| 0.1458        | 15.0  | 390  | 0.1496          |
-| 0.1999        | 16.0  | 416  | 0.1407          |
-| 0.3686        | 17.0  | 442  | 0.1356          |
-| 0.2666        | 18.0  | 468  | 0.1318          |
-| 0.1874        | 19.0  | 494  | 0.1298          |
-| 0.2286        | 20.0  | 520  | 0.1291          |
+| 5.0748        | 1.0   | 26   | 3.6708          |
+| 1.2816        | 2.0   | 52   | 1.5886          |
+| 1.422         | 3.0   | 78   | 0.7878          |
+| 0.5729        | 4.0   | 104  | 0.4200          |
+| 1.007         | 5.0   | 130  | 0.2706          |
+| 0.2949        | 6.0   | 156  | 0.1751          |
+| 0.2805        | 7.0   | 182  | 0.1193          |
+| 0.1689        | 8.0   | 208  | 0.0948          |
+| 0.1232        | 9.0   | 234  | 0.0717          |
+| 0.0205        | 10.0  | 260  | 0.0656          |
+| 0.1277        | 11.0  | 286  | 0.0600          |
+| 0.0357        | 12.0  | 312  | 0.0550          |
+| 0.0217        | 13.0  | 338  | 0.0469          |
+| 0.0201        | 14.0  | 364  | 0.0377          |
+| 0.0904        | 15.0  | 390  | 0.0320          |
+| 0.0083        | 16.0  | 416  | 0.0289          |
+| 0.1448        | 17.0  | 442  | 0.0284          |
+| 0.2741        | 18.0  | 468  | 0.0276          |
+| 0.0028        | 19.0  | 494  | 0.0261          |
+| 0.015         | 20.0  | 520  | 0.0260          |
 
 
 ### Framework versions

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "t5-base",
+  "_name_or_path": "t5-large",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 3072,
+  "d_ff": 4096,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 1024,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -18,9 +18,9 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd86d5ac68b6c4e79ca881305530d6ebb7242399263d6b5471c42d5bff68aa6
-size 891644712
+oid sha256:c84cc7e25429fc1e492e9d95785c33775e3cb524a653981ce9c9bd1f501cd3dd
+size 2950734544

runs/Jun18_06-06-38_MacBook-Pro.local/events.out.tfevents.1718662001.MacBook-Pro.local

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6021c8c7122f2415f5ad8983f1d738c3099362cc8cad52c348620314509bce2f
+size 120768

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdb918e3c32c23c2c1f1ec7c252d5ac6cca55861fe748637614e302161b38973
+oid sha256:8ebce11ea83a409378d7d692f77adf91345f4f55b5887395f43d1f0ccfa86995
 size 5304