add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- xsum
+metrics:
+- rouge
+model-index:
+- name: mt5-small-finetuned-xsum
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: xsum
+      type: xsum
+      args: default
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 2.4762
+---
+
+<!-- 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-xsum
+
+This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the xsum dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
+- Rouge1: 2.4762
+- Rouge2: 0.2236
+- Rougel: 2.2834
+- Rougelsum: 2.2792
+- Gen Len: 4.6402
+
+## 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
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| nan           | 1.0   | 1276 | nan             | 2.4762 | 0.2236 | 2.2834 | 2.2792    | 4.6402  |
+
+
+### Framework versions
+
+- Transformers 4.10.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.12.1
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.2",
+  "use_cache": true,
+  "vocab_size": 250112
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672b266857da449c8e1759ff96da0d8e7dc4402f0722687fee84220d436fe544
+size 1200770885

runs/Sep21_08-37-20_02df3a22b2fc/1632213476.886618/events.out.tfevents.1632213476.02df3a22b2fc.136.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef4af06400c854eb0f47e33af8f0d28099db2b0b38cb47a5718094ddd565f3dd
+size 4450

runs/Sep21_08-37-20_02df3a22b2fc/events.out.tfevents.1632213476.02df3a22b2fc.136.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d810d5e90de31d9f57d0a21f96ac91e3ba8e3f8e8e57e531522c10bcd9459942
+size 4302

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/root/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-small", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f7d64759e49a09449abc38a81c8bc3c42d538ad4a5574fc56cb959d6ee63981
+size 2799