olonok/t5-large-multi_news-summarization

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: google-t5/t5-large
+tags:
+- generated_from_trainer
+model-index:
+- name: t5-large-multi_news
+  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. -->
+
+# t5-large-multi_news
+
+This model is a fine-tuned version of [google-t5/t5-large](https://huggingface.co/google-t5/t5-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0627
+
+## 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: 0.001
+- 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: 10
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss |
+|:-------------:|:-----:|:------:|:---------------:|
+| 2.2999        | 1.0   | 11243  | 2.1311          |
+| 2.1376        | 2.0   | 22486  | 2.0726          |
+| 2.0305        | 3.0   | 33729  | 2.0609          |
+| 1.9771        | 4.0   | 44972  | 2.0571          |
+| 1.9389        | 5.0   | 56215  | 2.0550          |
+| 1.8816        | 6.0   | 67458  | 2.0551          |
+| 1.8484        | 7.0   | 78701  | 2.0599          |
+| 1.8248        | 8.0   | 89944  | 2.0604          |
+| 1.8306        | 9.0   | 101187 | 2.0627          |
+| 1.8182        | 10.0  | 112430 | 2.0627          |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "google-t5/t5-large",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 4096,
+  "d_kv": 64,
+  "d_model": 1024,
+  "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": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "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": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": false,
+  "vocab_size": 32128
+}

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": "4.37.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0d8e203e2616216644ff609084f1386cdf54df962f1946759548cedeff62c84
+size 1475398448

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee0fb91cfcd81cf2473574cf05686a1a68fbc102382cf546f01673d1b7142df
+size 4856