Training in progress epoch 0

README.md

@@ -13,9 +13,9 @@ probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [madatnlp/ke-t5-math-py](https://huggingface.co/madatnlp/ke-t5-math-py) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.9996
-- Validation Loss: 1.0227
-- Epoch: 62
+- Train Loss: 8.0101
+- Validation Loss: 5.1280
+- Epoch: 0
 
 ## Model description
 
@@ -41,69 +41,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 8.0295     | 5.0954          | 0     |
-| 4.8177     | 3.6298          | 1     |
-| 3.7818     | 2.9571          | 2     |
-| 3.1838     | 2.6057          | 3     |
-| 2.9168     | 2.2649          | 4     |
-| 2.6802     | 2.1726          | 5     |
-| 2.4846     | 1.9500          | 6     |
-| 2.3544     | 1.8473          | 7     |
-| 2.2090     | 1.9038          | 8     |
-| 2.1377     | 1.7177          | 9     |
-| 2.0199     | 1.7486          | 10    |
-| 1.9425     | 1.7548          | 11    |
-| 1.9077     | 1.6535          | 12    |
-| 1.8587     | 1.6882          | 13    |
-| 1.7940     | 1.5747          | 14    |
-| 1.7580     | 1.5802          | 15    |
-| 1.6726     | 1.6279          | 16    |
-| 1.6797     | 1.4446          | 17    |
-| 1.6454     | 1.4076          | 18    |
-| 1.6210     | 1.4485          | 19    |
-| 1.5961     | 1.3576          | 20    |
-| 1.5489     | 1.3601          | 21    |
-| 1.5157     | 1.3144          | 22    |
-| 1.4978     | 1.3140          | 23    |
-| 1.4719     | 1.3428          | 24    |
-| 1.4585     | 1.2431          | 25    |
-| 1.4342     | 1.2828          | 26    |
-| 1.3962     | 1.2625          | 27    |
-| 1.4092     | 1.1976          | 28    |
-| 1.3675     | 1.1740          | 29    |
-| 1.3708     | 1.2612          | 30    |
-| 1.3305     | 1.1599          | 31    |
-| 1.3393     | 1.1862          | 32    |
-| 1.3057     | 1.1180          | 33    |
-| 1.2774     | 1.1649          | 34    |
-| 1.3060     | 1.1652          | 35    |
-| 1.2731     | 1.1321          | 36    |
-| 1.2395     | 1.0716          | 37    |
-| 1.2488     | 1.1154          | 38    |
-| 1.2341     | 1.0532          | 39    |
-| 1.2168     | 1.1519          | 40    |
-| 1.2028     | 1.1080          | 41    |
-| 1.1993     | 1.0462          | 42    |
-| 1.1741     | 1.0575          | 43    |
-| 1.1854     | 1.1024          | 44    |
-| 1.1473     | 1.0656          | 45    |
-| 1.1568     | 1.0983          | 46    |
-| 1.1373     | 1.0441          | 47    |
-| 1.1168     | 1.0559          | 48    |
-| 1.1256     | 1.0653          | 49    |
-| 1.1066     | 0.9999          | 50    |
-| 1.1021     | 0.9710          | 51    |
-| 1.0877     | 0.9592          | 52    |
-| 1.0749     | 0.9846          | 53    |
-| 1.0790     | 0.9816          | 54    |
-| 1.0671     | 1.0013          | 55    |
-| 1.0424     | 0.9643          | 56    |
-| 1.0386     | 1.0248          | 57    |
-| 1.0360     | 0.9749          | 58    |
-| 1.0255     | 1.0094          | 59    |
-| 1.0092     | 0.9702          | 60    |
-| 1.0186     | 1.0089          | 61    |
-| 0.9996     | 1.0227          | 62    |
+| 8.0101     | 5.1280          | 0     |
 
 
 ### Framework versions

config.json

@@ -23,5 +23,5 @@
   "relative_attention_num_buckets": 32,
   "transformers_version": "4.18.0",
   "use_cache": true,
-  "vocab_size": 6188
+  "vocab_size": 6194
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7a745671e9af528a92c68029448b320e51cabb0510d2c90d0beb5d56bcbfd02
-size 831509840
+oid sha256:34be35d170f12bf69d1ad64dd6e9cfffbed53ab779d9dcbc12fa06e21a339883
+size 831546704