only_vary_model1

README.md

@@ -0,0 +1,78 @@
+---
+license: apache-2.0
+base_model: google/flan-t5-base
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: only_vary_model1
+  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. -->
+
+# only_vary_model1
+
+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: 0.2400
+- Rouge1: 62.207
+- Rouge2: 48.2441
+- Rougel: 57.479
+- Rougelsum: 62.039
+- Gen Len: 16.3689
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 11.6904       | 0.7   | 200  | 0.5014          | 40.0947 | 28.9027 | 39.0539 | 40.0066   | 6.986   |
+| 0.4064        | 1.4   | 400  | 0.2939          | 58.7275 | 43.2853 | 55.0201 | 58.5308   | 16.264  |
+| 0.3125        | 2.1   | 600  | 0.2749          | 60.4914 | 45.7417 | 56.4753 | 60.3543   | 16.1503 |
+| 0.2836        | 2.8   | 800  | 0.2576          | 60.3004 | 45.6356 | 55.9723 | 60.1254   | 16.2692 |
+| 0.2634        | 3.5   | 1000 | 0.2519          | 61.3543 | 47.3391 | 57.2049 | 61.1618   | 16.3724 |
+| 0.2608        | 4.2   | 1200 | 0.2522          | 61.538  | 46.8595 | 56.8033 | 61.3561   | 16.3409 |
+| 0.2387        | 4.9   | 1400 | 0.2439          | 60.7253 | 46.2206 | 56.342  | 60.57     | 16.3357 |
+| 0.2253        | 5.59  | 1600 | 0.2479          | 60.9499 | 46.7452 | 56.8289 | 60.8009   | 16.4178 |
+| 0.2299        | 6.29  | 1800 | 0.2416          | 61.6976 | 47.212  | 57.1834 | 61.558    | 16.3077 |
+| 0.2174        | 6.99  | 2000 | 0.2418          | 61.829  | 47.2977 | 57.3766 | 61.718    | 16.3112 |
+| 0.2089        | 7.69  | 2200 | 0.2389          | 62.2459 | 47.6275 | 57.1022 | 62.1048   | 16.299  |
+| 0.2127        | 8.39  | 2400 | 0.2402          | 61.8535 | 47.7161 | 57.2504 | 61.7496   | 16.4196 |
+| 0.2097        | 9.09  | 2600 | 0.2402          | 62.242  | 47.6438 | 57.0938 | 62.0981   | 16.299  |
+| 0.2036        | 9.79  | 2800 | 0.2400          | 62.207  | 48.2441 | 57.479  | 62.039    | 16.3689 |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu117
+- Datasets 2.14.4
+- Tokenizers 0.14.0

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": "4.34.0",
+  "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": "4.34.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddcff0cf869697bafa4072c72b4911a8378540c6e15ff22f4587ee42f263fd6f
+size 990408885

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5170d968fb8e155e9d7d3bd5247d211b80d7d0626b15c9683095bec3b989b68b
+size 4155