Upload 16 files

README.md

@@ -0,0 +1,90 @@
+---
+license: apache-2.0
+base_model: google/flan-t5-large
+tags:
+- generated_from_trainer
+datasets:
+- background_summ
+metrics:
+- rouge
+model-index:
+- name: '2023_12_18_08_41_35'
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: background_summ
+      type: background_summ
+      config: background-summ
+      split: validation
+      args: background-summ
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 39.8
+---
+
+<!-- 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. -->
+
+# 2023_12_18_08_41_35
+
+This model is a fine-tuned version of [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) on the background_summ dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3928
+- Rouge1: 39.8
+- Rouge2: 18.8
+- Rougel: 26.7
+- Rougelsum: 36.1
+- Bertscore Precision: 88.4
+- Bertscore Recall: 86.8
+- Bertscore F1: 87.5
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bertscore Precision | Bertscore Recall | Bertscore F1 |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------------------:|:----------------:|:------------:|
+| 1.6858        | 1.0   | 714  | 2.0262          | 41.1   | 19.3   | 27.1   | 37.3      | 87.9                | 87.1             | 87.5         |
+| 1.1309        | 2.0   | 1428 | 2.0889          | 40.8   | 19.6   | 27.3   | 37.1      | 87.8                | 87.1             | 87.4         |
+| 0.7568        | 3.0   | 2142 | 2.1569          | 40.8   | 19.1   | 27.3   | 37.0      | 87.8                | 87.0             | 87.4         |
+| 0.6779        | 4.0   | 2856 | 2.1800          | 39.5   | 18.4   | 26.4   | 35.9      | 87.8                | 86.7             | 87.2         |
+| 0.5567        | 5.0   | 3570 | 2.2454          | 40.1   | 19.0   | 26.8   | 36.6      | 88.2                | 86.8             | 87.4         |
+| 0.5264        | 6.0   | 4284 | 2.3172          | 38.8   | 18.1   | 26.1   | 35.2      | 88.0                | 86.6             | 87.3         |
+| 0.5046        | 7.0   | 4998 | 2.3409          | 40.1   | 19.0   | 27.0   | 36.4      | 88.4                | 86.8             | 87.6         |
+| 0.4465        | 8.0   | 5712 | 2.3751          | 39.8   | 18.7   | 26.7   | 36.1      | 88.4                | 86.7             | 87.6         |
+| 0.4524        | 9.0   | 6426 | 2.3824          | 40.0   | 19.0   | 27.1   | 36.4      | 88.5                | 86.8             | 87.6         |
+| 0.4308        | 10.0  | 7140 | 2.3928          | 39.8   | 18.8   | 26.7   | 36.1      | 88.4                | 86.8             | 87.5         |
+
+
+### Framework versions
+
+- Transformers 4.33.1
+- Pytorch 1.13.1
+- Datasets 2.14.5
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "google/flan-t5-large",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "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": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.1",
+  "use_cache": false,
+  "vocab_size": 32128
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5446daecbd8897e1671719bcd8028f5a1ca407ffba398efdbe20a35d16bb0405
+size 135

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.33.1",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c23e610e098f4c4e47211a9f38ee33429f86752e22b77fc205f3b54383171d2
+size 135

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1083a6cfef4d21f9b7b7d3c12b5b7fb1bdea5815e28ddd61d63d2e53b67e475c
+size 6265677287

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0959c3c9892cb661f09de749171b9a7961ca0ff9448f2433bac49c586ca8601
+size 3132793669

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0008fb8b2c571f823da9f42af1abf96d91c1f64d498b54260257c593af0019a4
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d5480a5308ba2246f3513b26597a19b2ad939ef2cb1dfe3af55c49bd8b16d9b
+size 627

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fdc32a55f01e98ebe8030b8787b4a61f0b2c74209caf593078ab7c22396e78e
+size 135

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>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": 27.3,
+  "best_model_checkpoint": "outputs/hf/None/2023_12_18_08_41_35/checkpoint-1428",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1428,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.299719887955183e-06,
+      "loss": 1.6858,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_bertscore_f1": 87.5,
+      "eval_bertscore_precision": 87.9,
+      "eval_bertscore_recall": 87.1,
+      "eval_loss": 2.0261785984039307,
+      "eval_rouge1": 41.1,
+      "eval_rouge2": 19.3,
+      "eval_rougeL": 27.1,
+      "eval_rougeLsum": 37.3,
+      "eval_runtime": 4513.7695,
+      "eval_samples_per_second": 0.108,
+      "eval_steps_per_second": 0.108,
+      "step": 714
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 8.599439775910365e-06,
+      "loss": 1.1309,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_bertscore_f1": 87.4,
+      "eval_bertscore_precision": 87.8,
+      "eval_bertscore_recall": 87.1,
+      "eval_loss": 2.088923692703247,
+      "eval_rouge1": 40.8,
+      "eval_rouge2": 19.6,
+      "eval_rougeL": 27.3,
+      "eval_rougeLsum": 37.1,
+      "eval_runtime": 4300.3072,
+      "eval_samples_per_second": 0.114,
+      "eval_steps_per_second": 0.114,
+      "step": 1428
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7140,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 2877934930624512.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6da4d9dfdc08eda050cb398e316ba3865e602e3c2e764549849cefc61c59da01
+size 4219