End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: t5-large
+base_model: t5-base
 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-large](https://huggingface.co/t5-large) on an unknown dataset.
+This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0226
+- Loss: 0.1291
 
 ## Model description
 
@@ -46,26 +46,26 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 5.0173        | 1.0   | 26   | 3.6634          |
-| 1.3207        | 2.0   | 52   | 1.6421          |
-| 1.509         | 3.0   | 78   | 0.8581          |
-| 0.5497        | 4.0   | 104  | 0.4255          |
-| 1.03          | 5.0   | 130  | 0.2530          |
-| 0.2971        | 6.0   | 156  | 0.1623          |
-| 0.2127        | 7.0   | 182  | 0.1202          |
-| 0.2528        | 8.0   | 208  | 0.0950          |
-| 0.1327        | 9.0   | 234  | 0.0767          |
-| 0.0153        | 10.0  | 260  | 0.0653          |
-| 0.0677        | 11.0  | 286  | 0.0579          |
-| 0.0441        | 12.0  | 312  | 0.0505          |
-| 0.0254        | 13.0  | 338  | 0.0425          |
-| 0.022         | 14.0  | 364  | 0.0325          |
-| 0.0683        | 15.0  | 390  | 0.0277          |
-| 0.0128        | 16.0  | 416  | 0.0265          |
-| 0.1322        | 17.0  | 442  | 0.0251          |
-| 0.2482        | 18.0  | 468  | 0.0237          |
-| 0.003         | 19.0  | 494  | 0.0226          |
-| 0.0118        | 20.0  | 520  | 0.0226          |
+| 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          |
 
 
 ### Framework versions

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "t5-large",
+  "_name_or_path": "t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 4096,
+  "d_ff": 3072,
   "d_kv": 64,
-  "d_model": 1024,
+  "d_model": 768,
   "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": 24,
-  "num_heads": 16,
-  "num_layers": 24,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dd86d5ac68b6c4e79ca881305530d6ebb7242399263d6b5471c42d5bff68aa6
+size 891644712

runs/Jun17_16-48-01_MacBook-Pro.local/events.out.tfevents.1718614083.MacBook-Pro.local

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:168e8d73e3efa641e7a5799f19b8795a2f0f347fbc4ffa27f723f21cd537f5ca
-size 11864
+oid sha256:9a38aeffbc09d263cdb8b6940133a993f40d9d3b9bf13cccf4292edf2baabd34
+size 97115

runs/Jun18_05-20-45_MacBook-Pro.local/events.out.tfevents.1718659246.MacBook-Pro.local

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b55709dee6769c44174fcdcfb70e4daa9abd03e63adb88b2d030a244d1e3e69b
+size 120766

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a4dfbe2ba827f0d4eaf9a369b6b6e9104248474f3dcb1eb97f8eff5192bc45
+oid sha256:fdb918e3c32c23c2c1f1ec7c252d5ac6cca55861fe748637614e302161b38973
 size 5304