Lancelot53/flan-t5-base-html

README.md

@@ -0,0 +1,71 @@
+---
+license: apache-2.0
+base_model: google/flan-t5-base
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: flan-t5-base-srbd
+  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-t5-base-srbd
+
+This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2120
+- Rouge1: 74.6571
+- Rouge2: 64.7185
+- Rougel: 73.4447
+- Rougelsum: 74.3068
+- Gen Len: 15.2964
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 200
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 11.6207       | 1.43  | 200  | 0.4953          | 50.1235 | 40.8377 | 49.8069 | 50.0662   | 6.0929  |
+| 0.3957        | 2.86  | 400  | 0.2953          | 73.1854 | 61.8915 | 71.7742 | 72.9773   | 15.2964 |
+| 0.2576        | 4.29  | 600  | 0.2562          | 74.0079 | 63.6214 | 72.8595 | 73.7951   | 15.2893 |
+| 0.2145        | 5.71  | 800  | 0.2236          | 74.4604 | 64.4404 | 73.1701 | 74.2875   | 15.1964 |
+| 0.1945        | 7.14  | 1000 | 0.2169          | 74.9576 | 65.2869 | 73.747  | 74.8084   | 15.3214 |
+| 0.1807        | 8.57  | 1200 | 0.2116          | 74.7495 | 64.8753 | 73.5631 | 74.566    | 15.3107 |
+| 0.1692        | 10.0  | 1400 | 0.2120          | 74.6571 | 64.7185 | 73.4447 | 74.3068   | 15.2964 |
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 2.0.0
+- Datasets 2.1.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "google/flan-t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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,
+  "model_type": "t5",
+  "n_positions": 512,
+  "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,
+  "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: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "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:cc9dd1bdbd72d016a7c859bde0040dd8af9552cc58de78342366f4780946680e
+size 990408885

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f192e23a0183d8358a9e08731d58d3043e5fa7e8eb17b3a09340b190199aaf
+size 4155