trained model

README.md

@@ -0,0 +1,82 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- samsum
+metrics:
+- rouge
+model-index:
+- name: flan-t5-base-samsum
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: samsum
+      type: samsum
+      config: samsum
+      split: test
+      args: samsum
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 47.2663
+---
+
+<!-- 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-samsum
+
+This model is a fine-tuned version of [google/flan-t5-base](https://huggingface.co/google/flan-t5-base) on the samsum dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3716
+- Rouge1: 47.2663
+- Rouge2: 23.5327
+- Rougel: 39.6491
+- Rougelsum: 43.3169
+- Gen Len: 17.3907
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 1.4379        | 1.0   | 1842 | 1.3805          | 47.1438 | 23.6153 | 39.6699 | 43.5505   | 17.1197 |
+| 1.3559        | 2.0   | 3684 | 1.3716          | 47.2663 | 23.5327 | 39.6491 | 43.3169   | 17.3907 |
+| 1.2783        | 3.0   | 5526 | 1.3721          | 47.4896 | 23.7684 | 39.7733 | 43.4494   | 17.1832 |
+| 1.2378        | 4.0   | 7368 | 1.3757          | 47.9122 | 24.0531 | 40.2225 | 43.996    | 17.3053 |
+| 1.1983        | 5.0   | 9210 | 1.3751          | 47.8507 | 24.0061 | 40.231  | 43.8698   | 17.3040 |
+
+
+### Framework versions
+
+- Transformers 4.26.1
+- Pytorch 1.13.1+cu116
+- Datasets 2.10.1
+- Tokenizers 0.13.2

checkpoint-3684/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": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

checkpoint-3684/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": "4.26.1"
+}

checkpoint-3684/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2494a087a30ef6722c70a85c8a4eb3a1d417d42c3ec4c1947940cee57d89b73f
+size 1980790149

checkpoint-3684/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d5135680d01f4bfb475174c86a691a51df898e6509547f2cfe1f517bc14168
+size 990408885

checkpoint-3684/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d1241f30548488a75615b17b77298425868e3da42b741eadbf23aef3d7b4ca5
+size 14575

checkpoint-3684/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90ebdb43dd363a0fc40428e9841b1804a0a8114634194edc2598d9a2dca06af0
+size 627

checkpoint-3684/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": 1.3715944290161133,
+  "best_model_checkpoint": "flan-t5-base-samsum/checkpoint-3684",
+  "epoch": 2.0,
+  "global_step": 3684,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.728555917480999e-05,
+      "loss": 1.4811,
+      "step": 500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.457111834961998e-05,
+      "loss": 1.4545,
+      "step": 1000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.185667752442997e-05,
+      "loss": 1.4379,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 17.11965811965812,
+      "eval_loss": 1.3805454969406128,
+      "eval_rouge1": 47.1438,
+      "eval_rouge2": 23.6153,
+      "eval_rougeL": 39.6699,
+      "eval_rougeLsum": 43.5505,
+      "eval_runtime": 126.1042,
+      "eval_samples_per_second": 6.495,
+      "eval_steps_per_second": 0.817,
+      "step": 1842
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.914223669923996e-05,
+      "loss": 1.4094,
+      "step": 2000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 3.642779587404995e-05,
+      "loss": 1.3318,
+      "step": 2500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 3.3713355048859935e-05,
+      "loss": 1.3396,
+      "step": 3000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.099891422366993e-05,
+      "loss": 1.3559,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 17.39072039072039,
+      "eval_loss": 1.3715944290161133,
+      "eval_rouge1": 47.2663,
+      "eval_rouge2": 23.5327,
+      "eval_rougeL": 39.6491,
+      "eval_rougeLsum": 43.3169,
+      "eval_runtime": 125.9833,
+      "eval_samples_per_second": 6.501,
+      "eval_steps_per_second": 0.818,
+      "step": 3684
+    }
+  ],
+  "max_steps": 9210,
+  "num_train_epochs": 5,
+  "total_flos": 2.017569063252787e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3684/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:284069f9e3c9a282d12a661d1d2d20b36615bce8274dd9c52c4244b1bab4cc83
+size 3643

checkpoint-9210/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": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

checkpoint-9210/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": "4.26.1"
+}

checkpoint-9210/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f947523173359a2b69116aa00f75acc3f6b6a8ccd1371dbe2b6e66a002286952
+size 1980790149

checkpoint-9210/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a347c2d01c24ef2eb140c02023ea53ceadc912b0348780bc3e086b928db77db
+size 990408885

checkpoint-9210/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf6e93a4e7fe6ae5ae14554422bf566aa38c9ac53a8c7a2fee4b6f98be8703d
+size 14575

checkpoint-9210/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0267870383c524bbb1cb9861088cd0dfa247c749b7b742a2bbfe961ece51d2f1
+size 627

checkpoint-9210/trainer_state.json

@@ -0,0 +1,189 @@
+{
+  "best_metric": 1.3715944290161133,
+  "best_model_checkpoint": "flan-t5-base-samsum/checkpoint-3684",
+  "epoch": 5.0,
+  "global_step": 9210,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.728555917480999e-05,
+      "loss": 1.4811,
+      "step": 500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.457111834961998e-05,
+      "loss": 1.4545,
+      "step": 1000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.185667752442997e-05,
+      "loss": 1.4379,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 17.11965811965812,
+      "eval_loss": 1.3805454969406128,
+      "eval_rouge1": 47.1438,
+      "eval_rouge2": 23.6153,
+      "eval_rougeL": 39.6699,
+      "eval_rougeLsum": 43.5505,
+      "eval_runtime": 126.1042,
+      "eval_samples_per_second": 6.495,
+      "eval_steps_per_second": 0.817,
+      "step": 1842
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.914223669923996e-05,
+      "loss": 1.4094,
+      "step": 2000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 3.642779587404995e-05,
+      "loss": 1.3318,
+      "step": 2500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 3.3713355048859935e-05,
+      "loss": 1.3396,
+      "step": 3000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.099891422366993e-05,
+      "loss": 1.3559,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 17.39072039072039,
+      "eval_loss": 1.3715944290161133,
+      "eval_rouge1": 47.2663,
+      "eval_rouge2": 23.5327,
+      "eval_rougeL": 39.6491,
+      "eval_rougeLsum": 43.3169,
+      "eval_runtime": 125.9833,
+      "eval_samples_per_second": 6.501,
+      "eval_steps_per_second": 0.818,
+      "step": 3684
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 2.8284473398479917e-05,
+      "loss": 1.3123,
+      "step": 4000
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 2.5570032573289905e-05,
+      "loss": 1.2724,
+      "step": 4500
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 2.2855591748099893e-05,
+      "loss": 1.2815,
+      "step": 5000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 2.0141150922909884e-05,
+      "loss": 1.2783,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 17.183150183150182,
+      "eval_loss": 1.3721352815628052,
+      "eval_rouge1": 47.4896,
+      "eval_rouge2": 23.7684,
+      "eval_rougeL": 39.7733,
+      "eval_rougeLsum": 43.4494,
+      "eval_runtime": 125.6835,
+      "eval_samples_per_second": 6.516,
+      "eval_steps_per_second": 0.82,
+      "step": 5526
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 1.742671009771987e-05,
+      "loss": 1.2228,
+      "step": 6000
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 1.471226927252986e-05,
+      "loss": 1.243,
+      "step": 6500
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 1.1997828447339848e-05,
+      "loss": 1.2378,
+      "step": 7000
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 17.305250305250304,
+      "eval_loss": 1.3757330179214478,
+      "eval_rouge1": 47.9122,
+      "eval_rouge2": 24.0531,
+      "eval_rougeL": 40.2225,
+      "eval_rougeLsum": 43.996,
+      "eval_runtime": 125.846,
+      "eval_samples_per_second": 6.508,
+      "eval_steps_per_second": 0.818,
+      "step": 7368
+    },
+    {
+      "epoch": 4.07,
+      "learning_rate": 9.283387622149838e-06,
+      "loss": 1.2306,
+      "step": 7500
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 6.568946796959827e-06,
+      "loss": 1.2106,
+      "step": 8000
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 3.854505971769816e-06,
+      "loss": 1.1991,
+      "step": 8500
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 1.1400651465798045e-06,
+      "loss": 1.1983,
+      "step": 9000
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 17.304029304029303,
+      "eval_loss": 1.3750557899475098,
+      "eval_rouge1": 47.8507,
+      "eval_rouge2": 24.0061,
+      "eval_rougeL": 40.231,
+      "eval_rougeLsum": 43.8698,
+      "eval_runtime": 125.3005,
+      "eval_samples_per_second": 6.536,
+      "eval_steps_per_second": 0.822,
+      "step": 9210
+    }
+  ],
+  "max_steps": 9210,
+  "num_train_epochs": 5,
+  "total_flos": 5.043922658131968e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-9210/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:284069f9e3c9a282d12a661d1d2d20b36615bce8274dd9c52c4244b1bab4cc83
+size 3643

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": "4.26.1",
+  "use_cache": true,
+  "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": "4.26.1"
+}

logs/1677934194.5926976/events.out.tfevents.1677934194.a56124cabdee.197.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc92cf29078ed48916b393163f207fe4ebc71c935c7676777355e7b05a56c355
+size 5895

logs/events.out.tfevents.1677934194.a56124cabdee.197.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b5b0835495d0128ba3b388c52743542e130ff0189c38418d8c9e2f027b0ebe0
+size 10592

logs/events.out.tfevents.1677946363.a56124cabdee.197.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d71488265121125a7b3e4c6248c10cf8fa2937a16f136297f829bf3472c4b24d
+size 565

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d5135680d01f4bfb475174c86a691a51df898e6509547f2cfe1f517bc14168
+size 990408885

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>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:284069f9e3c9a282d12a661d1d2d20b36615bce8274dd9c52c4244b1bab4cc83
+size 3643