Initial commit

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- stackexchange_titlebody_best_voted_answer_jsonl
+metrics:
+- rouge
+model-index:
+- name: flan-t5-base-flant5-apple-support
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: stackexchange_titlebody_best_voted_answer_jsonl
+      type: stackexchange_titlebody_best_voted_answer_jsonl
+      config: apple
+      split: train[:10%]
+      args: apple
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 12.7991
+---
+
+<!-- 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-flant5-apple-support
+
+This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the stackexchange_titlebody_best_voted_answer_jsonl dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.9676
+- Rouge1: 12.7991
+- Rouge2: 2.244
+- Rougel: 9.8075
+- Rougelsum: 11.3618
+- Gen Len: 18.9087
+
+## 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: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:------:|:---------:|:-------:|
+| 3.2673        | 1.0   | 1157 | 3.0350          | 12.4094 | 2.1794 | 9.5255 | 10.9739   | 18.9723 |
+| 3.1854        | 2.0   | 2314 | 2.9992          | 12.4579 | 2.1512 | 9.5232 | 11.0049   | 18.9647 |
+| 3.1006        | 3.0   | 3471 | 2.9792          | 12.9794 | 2.2794 | 9.9245 | 11.5019   | 18.9436 |
+| 3.0751        | 4.0   | 4628 | 2.9711          | 12.6779 | 2.1828 | 9.6962 | 11.221    | 18.9137 |
+| 3.0532        | 5.0   | 5785 | 2.9676          | 12.7991 | 2.244  | 9.8075 | 11.3618   | 18.9087 |
+
+
+### Framework versions
+
+- Transformers 4.25.1
+- Pytorch 1.13.1+cu117
+- Datasets 2.8.0
+- Tokenizers 0.13.2

checkpoint-4628/config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "google/flan-t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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": "4.25.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

checkpoint-4628/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba6efbea1cc4e2a52a4400842c8902ece53a429d9946aab214b6a8293e5c79d2
+size 1980790149

checkpoint-4628/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b0fd3cf40fbe1c1ef54548a1ea439eb0d9fe8132569e85d76352f14795ea27
+size 990408885

checkpoint-4628/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:955ee0bfe6a04dee79ba68207a08001a87c23be240e4119d895aeba2919b4ca7
+size 14575

checkpoint-4628/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f911251a52e1b1400cce870f1603d8d9c0a0d8654830e32c7ee2bf795f8b668
+size 627

checkpoint-4628/trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": 2.971137762069702,
+  "best_model_checkpoint": "flan-t5-base-flant5-apple-support/checkpoint-4628",
+  "epoch": 4.0,
+  "global_step": 4628,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.567847882454624e-05,
+      "loss": 3.3318,
+      "step": 500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.135695764909248e-05,
+      "loss": 3.2673,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 18.972318339100347,
+      "eval_loss": 3.0350406169891357,
+      "eval_rouge1": 12.4094,
+      "eval_rouge2": 2.1794,
+      "eval_rougeL": 9.5255,
+      "eval_rougeLsum": 10.9739,
+      "eval_runtime": 319.5992,
+      "eval_samples_per_second": 14.468,
+      "eval_steps_per_second": 1.809,
+      "step": 1157
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 3.7035436473638726e-05,
+      "loss": 3.2145,
+      "step": 1500
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 3.271391529818496e-05,
+      "loss": 3.1854,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 18.964749134948097,
+      "eval_loss": 2.9991722106933594,
+      "eval_rouge1": 12.4579,
+      "eval_rouge2": 2.1512,
+      "eval_rougeL": 9.5232,
+      "eval_rougeLsum": 11.0049,
+      "eval_runtime": 319.123,
+      "eval_samples_per_second": 14.49,
+      "eval_steps_per_second": 1.811,
+      "step": 2314
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 2.8392394122731204e-05,
+      "loss": 3.1388,
+      "step": 2500
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 2.4070872947277444e-05,
+      "loss": 3.1006,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 18.9435553633218,
+      "eval_loss": 2.9792306423187256,
+      "eval_rouge1": 12.9794,
+      "eval_rouge2": 2.2794,
+      "eval_rougeL": 9.9245,
+      "eval_rougeLsum": 11.5019,
+      "eval_runtime": 317.3217,
+      "eval_samples_per_second": 14.572,
+      "eval_steps_per_second": 1.821,
+      "step": 3471
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 1.9749351771823683e-05,
+      "loss": 3.1209,
+      "step": 3500
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 1.5427830596369925e-05,
+      "loss": 3.0729,
+      "step": 4000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 1.1106309420916162e-05,
+      "loss": 3.0751,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 18.91371107266436,
+      "eval_loss": 2.971137762069702,
+      "eval_rouge1": 12.6779,
+      "eval_rouge2": 2.1828,
+      "eval_rougeL": 9.6962,
+      "eval_rougeLsum": 11.221,
+      "eval_runtime": 320.2879,
+      "eval_samples_per_second": 14.437,
+      "eval_steps_per_second": 1.805,
+      "step": 4628
+    }
+  ],
+  "max_steps": 5785,
+  "num_train_epochs": 5,
+  "total_flos": 2.533328301116621e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-4628/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1095378c2c7db3c0c46c33986d0a4a6429dd87fcac7b6a289b7bb86cacd1f51b
+size 3579

checkpoint-5785/config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "google/flan-t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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": "4.25.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

checkpoint-5785/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b32b70900bec2518a12ae77e7901cce9ab80babbb93a3480294e3547d2f5cd
+size 1980790149

checkpoint-5785/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72a33370e685330c539eed67a76d44b89b501ff3993051c75af9cbe463f04141
+size 990408885

checkpoint-5785/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68cb5f9002319a3a5765f2485fa622072931bef72ce0e0d8671a3e2ebc2d6b37
+size 14575

checkpoint-5785/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad4c035a57b447214e0a9d68e2c34ae9bd233103f8203cd632a545abed7363e9
+size 627

checkpoint-5785/trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": 2.967562437057495,
+  "best_model_checkpoint": "flan-t5-base-flant5-apple-support/checkpoint-5785",
+  "epoch": 5.0,
+  "global_step": 5785,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.567847882454624e-05,
+      "loss": 3.3318,
+      "step": 500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 4.135695764909248e-05,
+      "loss": 3.2673,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 18.972318339100347,
+      "eval_loss": 3.0350406169891357,
+      "eval_rouge1": 12.4094,
+      "eval_rouge2": 2.1794,
+      "eval_rougeL": 9.5255,
+      "eval_rougeLsum": 10.9739,
+      "eval_runtime": 319.5992,
+      "eval_samples_per_second": 14.468,
+      "eval_steps_per_second": 1.809,
+      "step": 1157
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 3.7035436473638726e-05,
+      "loss": 3.2145,
+      "step": 1500
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 3.271391529818496e-05,
+      "loss": 3.1854,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 18.964749134948097,
+      "eval_loss": 2.9991722106933594,
+      "eval_rouge1": 12.4579,
+      "eval_rouge2": 2.1512,
+      "eval_rougeL": 9.5232,
+      "eval_rougeLsum": 11.0049,
+      "eval_runtime": 319.123,
+      "eval_samples_per_second": 14.49,
+      "eval_steps_per_second": 1.811,
+      "step": 2314
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 2.8392394122731204e-05,
+      "loss": 3.1388,
+      "step": 2500
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 2.4070872947277444e-05,
+      "loss": 3.1006,
+      "step": 3000
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 18.9435553633218,
+      "eval_loss": 2.9792306423187256,
+      "eval_rouge1": 12.9794,
+      "eval_rouge2": 2.2794,
+      "eval_rougeL": 9.9245,
+      "eval_rougeLsum": 11.5019,
+      "eval_runtime": 317.3217,
+      "eval_samples_per_second": 14.572,
+      "eval_steps_per_second": 1.821,
+      "step": 3471
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 1.9749351771823683e-05,
+      "loss": 3.1209,
+      "step": 3500
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 1.5427830596369925e-05,
+      "loss": 3.0729,
+      "step": 4000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 1.1106309420916162e-05,
+      "loss": 3.0751,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 18.91371107266436,
+      "eval_loss": 2.971137762069702,
+      "eval_rouge1": 12.6779,
+      "eval_rouge2": 2.1828,
+      "eval_rougeL": 9.6962,
+      "eval_rougeLsum": 11.221,
+      "eval_runtime": 320.2879,
+      "eval_samples_per_second": 14.437,
+      "eval_steps_per_second": 1.805,
+      "step": 4628
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 6.784788245462403e-06,
+      "loss": 3.0641,
+      "step": 5000
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 2.4632670700086435e-06,
+      "loss": 3.0532,
+      "step": 5500
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 18.908737024221452,
+      "eval_loss": 2.967562437057495,
+      "eval_rouge1": 12.7991,
+      "eval_rouge2": 2.244,
+      "eval_rougeL": 9.8075,
+      "eval_rougeLsum": 11.3618,
+      "eval_runtime": 318.8859,
+      "eval_samples_per_second": 14.5,
+      "eval_steps_per_second": 1.813,
+      "step": 5785
+    }
+  ],
+  "max_steps": 5785,
+  "num_train_epochs": 5,
+  "total_flos": 3.166660376395776e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5785/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1095378c2c7db3c0c46c33986d0a4a6429dd87fcac7b6a289b7bb86cacd1f51b
+size 3579

logs/1673395208.2439482/events.out.tfevents.1673395208.150-136-90-253.68652.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86dfff20b60f34f7e8f93ac0e9489054ea07479cab3744788c84370ccf4e6a90
+size 5790

logs/1673443771.419182/events.out.tfevents.1673443771.150-136-90-253.70371.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e97fab284b8eddf54fa571d0d91a38899d7da6dd0b23e8d9d76b044d7d44b751
+size 5790

logs/events.out.tfevents.1673395208.150-136-90-253.68652.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c299afa661465f8093b7e4162ccb54d721a3afdbdad49e9b24bd07b60d59b361
+size 9675

logs/events.out.tfevents.1673443771.150-136-90-253.70371.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adefc99b38d3c35eb06388fb05730ca5d0a9e1594dab417f63f3c29b2f2019c7
+size 9460

special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,113 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "name_or_path": "google/flan-t5-base",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-base/snapshots/650d7745bf1e502d6949b22cc19155cd656d3d4e/special_tokens_map.json",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}