End of training

README.md

@@ -0,0 +1,75 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/mt5-small
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: mt5-small-finetuned-easy-read
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mt5-small-finetuned-easy-read
+
+This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7917
+- Rouge1: 12.4918
+- Rouge2: 6.7409
+- Rougel: 11.2231
+- Rougelsum: 12.0442
+- Gen Len: 19.99
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
+| No log        | 1.0   | 450  | 2.1281          | 4.5701  | 1.9917 | 4.1438  | 4.4474    | 12.635  |
+| 7.874         | 2.0   | 900  | 2.0106          | 8.6313  | 3.4925 | 7.8255  | 8.425     | 19.03   |
+| 3.098         | 3.0   | 1350 | 1.9402          | 9.579   | 4.1365 | 8.6827  | 9.3027    | 19.7733 |
+| 2.756         | 4.0   | 1800 | 1.8900          | 10.1482 | 4.5253 | 9.1449  | 9.8281    | 19.8667 |
+| 2.6118        | 5.0   | 2250 | 1.8527          | 10.5116 | 4.8573 | 9.4613  | 10.1111   | 19.8883 |
+| 2.5282        | 6.0   | 2700 | 1.8292          | 10.704  | 5.0833 | 9.6107  | 10.214    | 19.9367 |
+| 2.4702        | 7.0   | 3150 | 1.8103          | 10.7648 | 5.1799 | 9.6605  | 10.2337   | 19.9483 |
+| 2.4191        | 8.0   | 3600 | 1.7991          | 10.849  | 5.2741 | 9.7489  | 10.3033   | 19.9383 |
+| 2.4059        | 9.0   | 4050 | 1.7924          | 12.4376 | 6.6643 | 11.1559 | 11.9786   | 19.99   |
+| 2.3925        | 10.0  | 4500 | 1.7917          | 12.4918 | 6.7409 | 11.2231 | 12.0442   | 19.99   |
+
+
+### Framework versions
+
+- Transformers 4.49.0
+- Pytorch 2.0.0+cu117
+- Datasets 3.4.0
+- Tokenizers 0.21.0

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.49.0"
+}

runs/Mar20_20-34-05_simba/events.out.tfevents.1742499247.simba.206041.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74f5ea0ca9a8670271ad3c7080ce75c8bf3c03ce1d4eb4656c87147a617fe8c5
-size 12021
+oid sha256:da80e6c046bbc2e06e9c0290a39e4423fc3e24acaa437ab93828f85cc5f3874d
+size 12900