Model save

README.md

@@ -0,0 +1,68 @@
+---
+base_model: ybelkada/flan-t5-xl-sharded-bf16
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: flan-xl-gen4
+  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. -->
+
+# flan-xl-gen4
+
+This model is a fine-tuned version of [ybelkada/flan-t5-xl-sharded-bf16](https://huggingface.co/ybelkada/flan-t5-xl-sharded-bf16) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6847
+- Rouge1: 36.2186
+- Rouge2: 27.5662
+- Rougel: 32.6055
+- Rougelsum: 32.8805
+- Gen Len: 10.85
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| No log        | 1.0   | 179  | 0.6847          | 36.2186 | 27.5662 | 32.6055 | 32.8805   | 10.85   |
+| No log        | 2.0   | 358  | 0.6847          | 36.2186 | 27.5662 | 32.6055 | 32.8805   | 10.85   |
+| 0.7514        | 3.0   | 537  | 0.6847          | 36.2186 | 27.5662 | 32.6055 | 32.8805   | 10.85   |
+| 0.7514        | 4.0   | 716  | 0.6847          | 36.2186 | 27.5662 | 32.6055 | 32.8805   | 10.85   |
+| 0.7514        | 5.0   | 895  | 0.6847          | 36.2186 | 27.5662 | 32.6055 | 32.8805   | 10.85   |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,

logs/events.out.tfevents.1701157683.ec7c58e0a941.398.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2620f34de60a19ea492dd0ab3d58a5b5cd26cb651107bdfa7ededa97f61225
+size 613