Upload 12 files

README.md

@@ -1,3 +1,73 @@
 ---
 license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- samsum
+metrics:
+- rouge
+model-index:
+- name: tst-summarization
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    dataset:
+      name: samsum
+      type: samsum
+      config: samsum
+      split: train
+      args: samsum
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 44.9509
 ---
+
+
+# tst-summarization
+
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the samsum dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6972
+- Rouge1: 44.9509
+- Rouge2: 21.7162
+- Rougel: 37.7582
+- Rougelsum: 41.7239
+- Gen Len: 22.7714
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.25.1
+- Pytorch 1.13.1+cpu
+- Datasets 2.8.0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 22.771393643031786,
+    "eval_loss": 1.6972110271453857,
+    "eval_rouge1": 44.9509,
+    "eval_rouge2": 21.7162,
+    "eval_rougeL": 37.7582,
+    "eval_rougeLsum": 41.7239,
+    "eval_runtime": 499.5513,
+    "eval_samples": 818,
+    "eval_samples_per_second": 1.637,
+    "eval_steps_per_second": 0.41,
+    "train_loss": 1.8986893418320963,
+    "train_runtime": 35727.9633,
+    "train_samples": 14731,
+    "train_samples_per_second": 1.237,
+    "train_steps_per_second": 0.309
+}

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "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": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "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": "float32",
+  "transformers_version": "4.25.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 22.771393643031786,
+    "eval_loss": 1.6972110271453857,
+    "eval_rouge1": 44.9509,
+    "eval_rouge2": 21.7162,
+    "eval_rougeL": 37.7582,
+    "eval_rougeLsum": 41.7239,
+    "eval_runtime": 499.5513,
+    "eval_samples": 818,
+    "eval_samples_per_second": 1.637,
+    "eval_steps_per_second": 0.41
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6164c212a1425a049e6a8fc60ad8f2094314b54bd228eed0f0e8341db89b3ec
+size 242069785

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>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "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": "t5-small",
+  "pad_token": "<pad>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.8986893418320963,
+    "train_runtime": 35727.9633,
+    "train_samples": 14731,
+    "train_samples_per_second": 1.237,
+    "train_steps_per_second": 0.309
+}

trainer_state.json

@@ -0,0 +1,157 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 11049,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.7737351796542676e-05,
+      "loss": 2.2042,
+      "step": 500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.547470359308535e-05,
+      "loss": 2.087,
+      "step": 1000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.321205538962802e-05,
+      "loss": 2.0242,
+      "step": 1500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.09494071861707e-05,
+      "loss": 1.978,
+      "step": 2000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.868675898271337e-05,
+      "loss": 1.9701,
+      "step": 2500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.6424110779256044e-05,
+      "loss": 1.9814,
+      "step": 3000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.416146257579871e-05,
+      "loss": 1.9524,
+      "step": 3500
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.189881437234139e-05,
+      "loss": 1.9124,
+      "step": 4000
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 2.963616616888406e-05,
+      "loss": 1.8723,
+      "step": 4500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.7373517965426738e-05,
+      "loss": 1.8591,
+      "step": 5000
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.511086976196941e-05,
+      "loss": 1.8822,
+      "step": 5500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 2.2848221558512085e-05,
+      "loss": 1.8402,
+      "step": 6000
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.058557335505476e-05,
+      "loss": 1.8634,
+      "step": 6500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.8322925151597432e-05,
+      "loss": 1.8638,
+      "step": 7000
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.6060276948140106e-05,
+      "loss": 1.8548,
+      "step": 7500
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.3797628744682778e-05,
+      "loss": 1.8085,
+      "step": 8000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.1534980541225452e-05,
+      "loss": 1.8086,
+      "step": 8500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 9.272332337768125e-06,
+      "loss": 1.809,
+      "step": 9000
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.009684134310799e-06,
+      "loss": 1.8238,
+      "step": 9500
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.747035930853471e-06,
+      "loss": 1.7984,
+      "step": 10000
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.4843877273961445e-06,
+      "loss": 1.7959,
+      "step": 10500
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 2.21739523938818e-07,
+      "loss": 1.7938,
+      "step": 11000
+    },
+    {
+      "epoch": 3.0,
+      "step": 11049,
+      "total_flos": 3178708656685056.0,
+      "train_loss": 1.8986893418320963,
+      "train_runtime": 35727.9633,
+      "train_samples_per_second": 1.237,
+      "train_steps_per_second": 0.309
+    }
+  ],
+  "max_steps": 11049,
+  "num_train_epochs": 3,
+  "total_flos": 3178708656685056.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd9a89c6ebbd8e47ba52737012f367c6beb08f81f9ee6f271467eaf73ffc4b27
+size 3515