t5_cnn_daily_mail_abstractive_summarizer

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+base_model: t5-small
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: logs
+  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. -->
+
+# logs
+
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2981
+- Rouge1: 0.5957
+- Rouge2: 0.3287
+- Rougel: 0.5448
+- Gen Len: 82.8793
+
+## 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:-------:|
+| 0.3573        | 0.56  | 200  | 0.3390          | 0.5817 | 0.3123 | 0.5296 | 81.8915 |
+| 0.3175        | 1.11  | 400  | 0.3073          | 0.593  | 0.3249 | 0.5405 | 82.855  |
+| 0.317         | 1.67  | 600  | 0.3025          | 0.5956 | 0.3275 | 0.5434 | 82.8793 |
+| 0.2948        | 2.23  | 800  | 0.3009          | 0.5959 | 0.3275 | 0.5444 | 82.8793 |
+| 0.2895        | 2.79  | 1000 | 0.2999          | 0.5955 | 0.3286 | 0.5442 | 82.8793 |
+| 0.292         | 3.34  | 1200 | 0.2997          | 0.5951 | 0.3277 | 0.5441 | 82.8793 |
+| 0.2959        | 3.9   | 1400 | 0.2991          | 0.5962 | 0.3286 | 0.5447 | 82.8793 |
+| 0.2847        | 4.46  | 1600 | 0.2993          | 0.5955 | 0.3285 | 0.5441 | 82.8793 |
+| 0.2922        | 5.01  | 1800 | 0.2983          | 0.5957 | 0.3279 | 0.5447 | 82.8793 |
+| 0.2978        | 5.57  | 2000 | 0.2985          | 0.5963 | 0.3288 | 0.545  | 82.8793 |
+| 0.2952        | 6.13  | 2200 | 0.2985          | 0.5953 | 0.328  | 0.5442 | 82.8793 |
+| 0.2832        | 6.69  | 2400 | 0.2982          | 0.595  | 0.328  | 0.5447 | 82.8793 |
+| 0.2862        | 7.24  | 2600 | 0.2984          | 0.5954 | 0.3277 | 0.5442 | 82.8793 |
+| 0.2992        | 7.8   | 2800 | 0.2978          | 0.5958 | 0.3278 | 0.5449 | 82.8793 |
+| 0.2848        | 8.36  | 3000 | 0.2975          | 0.5952 | 0.3279 | 0.5449 | 82.8793 |
+| 0.2815        | 8.91  | 3200 | 0.2978          | 0.5962 | 0.3291 | 0.5452 | 82.8793 |
+| 0.2894        | 9.47  | 3400 | 0.2981          | 0.5957 | 0.3287 | 0.5448 | 82.8793 |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.1.2
+- Datasets 2.1.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32128
+}

events.out.tfevents.1712223765.e24c4cb9975b.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c054ecf98ada643d32f6db5256447e7bb0be655fff3c285701e1a75750af8957
+size 13179

events.out.tfevents.1712225480.e24c4cb9975b.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a6453264916d641ce8fffef4c5ba9b22f6175d27c14397b4eacd962cf933117
+size 89477

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f21a48c887b4d78942c4e98d64e1c9bed1b6711373eba8406b5b0a60dcc26a7
+size 242041896

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43d712f2bcb500264bdc905116c29d8c0b0051d7c3ceddcee1e52ac1b36fbfd6
+size 4856