Training in progress, step 500

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,75 @@
+---
+license: apache-2.0
+base_model: google/mt5-base
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: mt5-base-finetuned-test_30483_prefix_summarize
+  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-base-finetuned-test_30483_prefix_summarize
+
+This model is a fine-tuned version of [google/mt5-base](https://huggingface.co/google/mt5-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3527
+- Rouge1: 23.6141
+- Rouge2: 7.1791
+- Rougel: 16.0152
+- Rougelsum: 21.8213
+- Gen Len: 69.64
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
+| 7.4668        | 1.25  | 500  | 2.6478          | 10.4597 | 4.2457 | 8.7184  | 9.8473    | 18.49   |
+| 3.3231        | 2.5   | 1000 | 2.5146          | 17.7315 | 6.0795 | 13.5384 | 16.6839   | 40.55   |
+| 3.0956        | 3.75  | 1500 | 2.4512          | 20.2871 | 6.4051 | 14.8508 | 18.8768   | 51.35   |
+| 2.9928        | 5.0   | 2000 | 2.4180          | 21.4196 | 6.629  | 15.2607 | 20.1471   | 57.92   |
+| 2.8802        | 6.25  | 2500 | 2.4030          | 21.7949 | 6.7926 | 15.2506 | 20.338    | 61.05   |
+| 2.8243        | 7.5   | 3000 | 2.3856          | 21.7075 | 6.7397 | 15.0044 | 20.1744   | 61.19   |
+| 2.7646        | 8.75  | 3500 | 2.3847          | 22.4137 | 6.7644 | 14.9987 | 20.7797   | 63.81   |
+| 2.7096        | 10.0  | 4000 | 2.3691          | 22.3403 | 6.9812 | 15.5411 | 20.6166   | 62.79   |
+| 2.6758        | 11.25 | 4500 | 2.3612          | 23.6542 | 7.2355 | 15.9979 | 21.9807   | 69.83   |
+| 2.6579        | 12.5  | 5000 | 2.3556          | 23.7473 | 7.5446 | 16.0314 | 21.917    | 69.75   |
+| 2.651         | 13.75 | 5500 | 2.3557          | 23.9711 | 7.5018 | 16.2033 | 22.2811   | 69.29   |
+| 2.639         | 15.0  | 6000 | 2.3527          | 23.6141 | 7.1791 | 16.0152 | 21.8213   | 69.64   |
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 2.1.0
+- Datasets 2.12.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "google/mt5-base",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 0.6,
+  "max_length": 500,
+  "model_type": "mt5",
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "use_cache": true,
+  "vocab_size": 250112
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "length_penalty": 0.6,
+  "max_length": 500,
+  "no_repeat_ngram_size": 2,
+  "num_beams": 15,
+  "pad_token_id": 0,
+  "transformers_version": "4.32.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bfd6e8cc3c354a048af9024ce860b333959ce1e7f62b8a53f085add358fcd26
+size 2329703026

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e37a936cc67bf2dd6bfa291cfd4ac69b8d1892e75b75e4dfb7d87b2e746914
+size 16330467

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2336bd367d935b27cf3fda24b0693adc5f6dc0edd556de7bbd3a936178f89fb
+size 4600