Upload pipeline weights

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+convokit_50_model/checkpoint-00000050.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text
+convokit_50_model/checkpoint-00000050.meta filter=lfs diff=lfs merge=lfs -text
+convokit_dials_train.json filter=lfs diff=lfs merge=lfs -text
+glove.6B.100d.txt filter=lfs diff=lfs merge=lfs -text

bart_response_generator/README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: BLUE_bart_large_5ep_5e_5
+  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. -->
+
+# BLUE_bart_large_5ep_5e_5
+
+This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0958
+- Rouge1: 67.9321
+- Rouge2: 54.9471
+- Rougel: 60.922
+- Rougelsum: 63.8581
+- Gen Len: 51.8306
+
+## 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: 20
+- eval_batch_size: 20
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 1.2388        | 1.07  | 2000 | 1.1304          | 66.5164 | 54.1964 | 60.1255 | 62.6329   | 48.5373 |
+| 0.9911        | 2.14  | 4000 | 1.0997          | 66.7923 | 54.4921 | 60.3864 | 63.0007   | 48.2194 |
+| 0.8473        | 3.2   | 6000 | 1.1019          | 68.1867 | 55.4038 | 61.5061 | 64.2051   | 51.4172 |
+| 0.7315        | 4.27  | 8000 | 1.1118          | 67.961  | 55.3863 | 61.4022 | 64.1305   | 50.4269 |
+
+
+### Framework versions
+
+- Transformers 4.28.1
+- Pytorch 1.8.1+cu111
+- Datasets 2.11.0
+- Tokenizers 0.13.3

bart_response_generator/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<SEP>": 50265,
+  "<UTTERSEP>": 50266
+}

bart_response_generator/all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 5.0,
+    "eval_gen_len": 51.830597014925374,
+    "eval_loss": 1.0958350896835327,
+    "eval_rouge1": 67.9321,
+    "eval_rouge2": 54.9471,
+    "eval_rougeL": 60.922,
+    "eval_rougeLsum": 63.8581,
+    "eval_runtime": 265.3264,
+    "eval_samples": 1340,
+    "eval_samples_per_second": 5.05,
+    "eval_steps_per_second": 0.253,
+    "train_loss": 0.9121758847458122,
+    "train_runtime": 3599.8478,
+    "train_samples": 37460,
+    "train_samples_per_second": 52.03,
+    "train_steps_per_second": 2.601
+}

bart_response_generator/config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "facebook/bart-large",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 50267
+}

bart_response_generator/eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_gen_len": 51.830597014925374,
+    "eval_loss": 1.0958350896835327,
+    "eval_rouge1": 67.9321,
+    "eval_rouge2": 54.9471,
+    "eval_rougeL": 60.922,
+    "eval_rougeLsum": 63.8581,
+    "eval_runtime": 265.3264,
+    "eval_samples": 1340,
+    "eval_samples_per_second": 5.05,
+    "eval_steps_per_second": 0.253
+}

bart_response_generator/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.28.1"
+}

bart_response_generator/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08509447caa443e6bf3b9a4848bbe1877bcf984c42b95dc5a0bf5712f97d7be1
+size 1625558063

bart_response_generator/special_tokens_map.json

@@ -0,0 +1,18 @@
+{
+  "additional_special_tokens": [
+    "<UTTERSEP>"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "<SEP>",
+  "unk_token": "<unk>"
+}

bart_response_generator/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

bart_response_generator/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.9121758847458122,
+    "train_runtime": 3599.8478,
+    "train_samples": 37460,
+    "train_samples_per_second": 52.03,
+    "train_steps_per_second": 2.601
+}

bart_response_generator/trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 9365,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.07,
+      "learning_rate": 3.932194340630005e-05,
+      "loss": 1.2388,
+      "step": 2000
+    },
+    {
+      "epoch": 1.07,
+      "eval_gen_len": 48.53731343283582,
+      "eval_loss": 1.1303935050964355,
+      "eval_rouge1": 66.5164,
+      "eval_rouge2": 54.1964,
+      "eval_rougeL": 60.1255,
+      "eval_rougeLsum": 62.6329,
+      "eval_runtime": 248.0848,
+      "eval_samples_per_second": 5.401,
+      "eval_steps_per_second": 0.27,
+      "step": 2000
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 2.8643886812600106e-05,
+      "loss": 0.9911,
+      "step": 4000
+    },
+    {
+      "epoch": 2.14,
+      "eval_gen_len": 48.21940298507463,
+      "eval_loss": 1.0996825695037842,
+      "eval_rouge1": 66.7923,
+      "eval_rouge2": 54.4921,
+      "eval_rougeL": 60.3864,
+      "eval_rougeLsum": 63.0007,
+      "eval_runtime": 245.1086,
+      "eval_samples_per_second": 5.467,
+      "eval_steps_per_second": 0.273,
+      "step": 4000
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 1.7965830218900163e-05,
+      "loss": 0.8473,
+      "step": 6000
+    },
+    {
+      "epoch": 3.2,
+      "eval_gen_len": 51.417164179104475,
+      "eval_loss": 1.1019301414489746,
+      "eval_rouge1": 68.1867,
+      "eval_rouge2": 55.4038,
+      "eval_rougeL": 61.5061,
+      "eval_rougeLsum": 64.2051,
+      "eval_runtime": 255.7993,
+      "eval_samples_per_second": 5.238,
+      "eval_steps_per_second": 0.262,
+      "step": 6000
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 7.287773625200214e-06,
+      "loss": 0.7315,
+      "step": 8000
+    },
+    {
+      "epoch": 4.27,
+      "eval_gen_len": 50.42686567164179,
+      "eval_loss": 1.111816167831421,
+      "eval_rouge1": 67.961,
+      "eval_rouge2": 55.3863,
+      "eval_rougeL": 61.4022,
+      "eval_rougeLsum": 64.1305,
+      "eval_runtime": 261.9465,
+      "eval_samples_per_second": 5.116,
+      "eval_steps_per_second": 0.256,
+      "step": 8000
+    },
+    {
+      "epoch": 5.0,
+      "step": 9365,
+      "total_flos": 1.1949135422717952e+17,
+      "train_loss": 0.9121758847458122,
+      "train_runtime": 3599.8478,
+      "train_samples_per_second": 52.03,
+      "train_steps_per_second": 2.601
+    }
+  ],
+  "max_steps": 9365,
+  "num_train_epochs": 5,
+  "total_flos": 1.1949135422717952e+17,
+  "trial_name": null,
+  "trial_params": null
+}

bart_response_generator/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f94865fe6e34e476c79baddd0c4bd3cc8fcdcfadfa8b823585bc544ee66ed0a
+size 3823

classifier_disco.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47fdafcea1a35894bbf2984f0c9d0059950929baec382776b95d19416a44e2c4
+size 29095

convokit_50_model/checkpoint

@@ -0,0 +1,2 @@
+model_checkpoint_path: "checkpoint-00000050"
+all_model_checkpoint_paths: "checkpoint-00000050"

convokit_50_model/checkpoint-00000050.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7913fbe973da462ad5bd02abcbc86ad424c5a2507b729eabdf622813184f631d
+size 64192566

convokit_50_model/checkpoint-00000050.meta

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b28032d4f0b302ede82efd604bb410fd1453498227474b8f0ed0700c1e89584
+size 98155604

convokit_dials_train.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e1d3aad756d0d6e4d547ab7a48166722e020fd89b183ea67b7de0720167a17
+size 33319326

deberta_qa/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.5708848007960676,
+    "train_runtime": 17933.1446,
+    "train_samples": 164635,
+    "train_samples_per_second": 36.722,
+    "train_steps_per_second": 4.59
+}

deberta_qa/config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "deepset/deberta-v3-base-squad2",
+  "architectures": [
+    "DebertaV2ForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "language": "english",
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "name": "DebertaV2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "summary_activation": "tanh",
+  "summary_last_dropout": 0,
+  "summary_type": "first",
+  "summary_use_proj": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

deberta_qa/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd9732db877a6e31e2df7bc5e03c45d661fa303e17075e79e8ffccc2b0066c3
+size 735405809

deberta_qa/special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

deberta_qa/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "deepset/deberta-v3-base-squad2",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

deberta_qa/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.5708848007960676,
+    "train_runtime": 17933.1446,
+    "train_samples": 164635,
+    "train_samples_per_second": 36.722,
+    "train_steps_per_second": 4.59
+}

deberta_qa/trainer_state.json

@@ -0,0 +1,1009 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9999757039772588,
+  "global_step": 82316,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.98785169347393e-05,
+      "loss": 1.0418,
+      "step": 500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9757033869478596e-05,
+      "loss": 0.8326,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9635550804217894e-05,
+      "loss": 0.8343,
+      "step": 1500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.951406773895719e-05,
+      "loss": 0.8015,
+      "step": 2000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.939258467369649e-05,
+      "loss": 0.7903,
+      "step": 2500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9271101608435786e-05,
+      "loss": 0.7802,
+      "step": 3000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9149618543175083e-05,
+      "loss": 0.7798,
+      "step": 3500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.902813547791438e-05,
+      "loss": 0.8225,
+      "step": 4000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.8906652412653678e-05,
+      "loss": 0.7332,
+      "step": 4500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.8785169347392975e-05,
+      "loss": 0.7285,
+      "step": 5000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.8663686282132272e-05,
+      "loss": 0.7375,
+      "step": 5500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.854220321687157e-05,
+      "loss": 0.7397,
+      "step": 6000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.8420720151610867e-05,
+      "loss": 0.709,
+      "step": 6500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.8299237086350164e-05,
+      "loss": 0.7459,
+      "step": 7000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8177754021089462e-05,
+      "loss": 0.727,
+      "step": 7500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.805627095582876e-05,
+      "loss": 0.7154,
+      "step": 8000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.7934787890568056e-05,
+      "loss": 0.7378,
+      "step": 8500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.7813304825307354e-05,
+      "loss": 0.727,
+      "step": 9000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.769182176004665e-05,
+      "loss": 0.6885,
+      "step": 9500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.757033869478595e-05,
+      "loss": 0.6895,
+      "step": 10000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7448855629525246e-05,
+      "loss": 0.6916,
+      "step": 10500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7327372564264543e-05,
+      "loss": 0.7228,
+      "step": 11000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.720588949900384e-05,
+      "loss": 0.6772,
+      "step": 11500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.7084406433743138e-05,
+      "loss": 0.6988,
+      "step": 12000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6962923368482435e-05,
+      "loss": 0.7078,
+      "step": 12500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.6841440303221732e-05,
+      "loss": 0.726,
+      "step": 13000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.671995723796103e-05,
+      "loss": 0.7046,
+      "step": 13500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.6598474172700327e-05,
+      "loss": 0.7028,
+      "step": 14000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.6476991107439624e-05,
+      "loss": 0.6893,
+      "step": 14500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.6355508042178922e-05,
+      "loss": 0.7066,
+      "step": 15000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.623402497691822e-05,
+      "loss": 0.7021,
+      "step": 15500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.6112541911657517e-05,
+      "loss": 0.718,
+      "step": 16000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.5991058846396814e-05,
+      "loss": 0.6963,
+      "step": 16500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.586957578113611e-05,
+      "loss": 0.664,
+      "step": 17000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.574809271587541e-05,
+      "loss": 0.6841,
+      "step": 17500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.5626609650614706e-05,
+      "loss": 0.7121,
+      "step": 18000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.5505126585354003e-05,
+      "loss": 0.6782,
+      "step": 18500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.53836435200933e-05,
+      "loss": 0.7029,
+      "step": 19000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5262160454832598e-05,
+      "loss": 0.7159,
+      "step": 19500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5140677389571894e-05,
+      "loss": 0.6624,
+      "step": 20000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5019194324311193e-05,
+      "loss": 0.6956,
+      "step": 20500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.489771125905049e-05,
+      "loss": 0.6183,
+      "step": 21000
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.4776228193789787e-05,
+      "loss": 0.6394,
+      "step": 21500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.4654745128529085e-05,
+      "loss": 0.6252,
+      "step": 22000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.453326206326838e-05,
+      "loss": 0.623,
+      "step": 22500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.441177899800768e-05,
+      "loss": 0.6187,
+      "step": 23000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4290295932746977e-05,
+      "loss": 0.5981,
+      "step": 23500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.4168812867486274e-05,
+      "loss": 0.6317,
+      "step": 24000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.4047329802225571e-05,
+      "loss": 0.6205,
+      "step": 24500
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.3925846736964867e-05,
+      "loss": 0.5987,
+      "step": 25000
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.3804363671704166e-05,
+      "loss": 0.6027,
+      "step": 25500
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.3682880606443463e-05,
+      "loss": 0.6122,
+      "step": 26000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.3561397541182759e-05,
+      "loss": 0.6165,
+      "step": 26500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.3439914475922058e-05,
+      "loss": 0.6176,
+      "step": 27000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.3318431410661354e-05,
+      "loss": 0.6036,
+      "step": 27500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.3196948345400653e-05,
+      "loss": 0.6088,
+      "step": 28000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.307546528013995e-05,
+      "loss": 0.6363,
+      "step": 28500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.2953982214879246e-05,
+      "loss": 0.603,
+      "step": 29000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.2832499149618545e-05,
+      "loss": 0.658,
+      "step": 29500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.271101608435784e-05,
+      "loss": 0.6219,
+      "step": 30000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.258953301909714e-05,
+      "loss": 0.5905,
+      "step": 30500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.2468049953836437e-05,
+      "loss": 0.6223,
+      "step": 31000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.2346566888575732e-05,
+      "loss": 0.6117,
+      "step": 31500
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.2225083823315031e-05,
+      "loss": 0.5922,
+      "step": 32000
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.2103600758054329e-05,
+      "loss": 0.5848,
+      "step": 32500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.1982117692793624e-05,
+      "loss": 0.5924,
+      "step": 33000
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.1860634627532923e-05,
+      "loss": 0.5936,
+      "step": 33500
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.1739151562272219e-05,
+      "loss": 0.6374,
+      "step": 34000
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.1617668497011518e-05,
+      "loss": 0.5841,
+      "step": 34500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.1496185431750815e-05,
+      "loss": 0.5954,
+      "step": 35000
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1.1374702366490111e-05,
+      "loss": 0.6168,
+      "step": 35500
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.125321930122941e-05,
+      "loss": 0.6063,
+      "step": 36000
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.1131736235968706e-05,
+      "loss": 0.5914,
+      "step": 36500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.1010253170708005e-05,
+      "loss": 0.6424,
+      "step": 37000
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.0888770105447302e-05,
+      "loss": 0.6359,
+      "step": 37500
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.0767287040186598e-05,
+      "loss": 0.6023,
+      "step": 38000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0645803974925897e-05,
+      "loss": 0.5855,
+      "step": 38500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.0524320909665192e-05,
+      "loss": 0.6153,
+      "step": 39000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.0402837844404491e-05,
+      "loss": 0.6025,
+      "step": 39500
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.0281354779143789e-05,
+      "loss": 0.6214,
+      "step": 40000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.0159871713883084e-05,
+      "loss": 0.6067,
+      "step": 40500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.0038388648622384e-05,
+      "loss": 0.6057,
+      "step": 41000
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 9.916905583361681e-06,
+      "loss": 0.5468,
+      "step": 41500
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 9.795422518100978e-06,
+      "loss": 0.4872,
+      "step": 42000
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 9.673939452840276e-06,
+      "loss": 0.5144,
+      "step": 42500
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 9.552456387579571e-06,
+      "loss": 0.5122,
+      "step": 43000
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 9.430973322318869e-06,
+      "loss": 0.5152,
+      "step": 43500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 9.309490257058168e-06,
+      "loss": 0.5245,
+      "step": 44000
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 9.188007191797465e-06,
+      "loss": 0.4971,
+      "step": 44500
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 9.066524126536762e-06,
+      "loss": 0.5478,
+      "step": 45000
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 8.945041061276058e-06,
+      "loss": 0.5296,
+      "step": 45500
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 8.823557996015357e-06,
+      "loss": 0.5403,
+      "step": 46000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 8.702074930754654e-06,
+      "loss": 0.5133,
+      "step": 46500
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 8.580591865493952e-06,
+      "loss": 0.5162,
+      "step": 47000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 8.459108800233247e-06,
+      "loss": 0.521,
+      "step": 47500
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 8.337625734972545e-06,
+      "loss": 0.4896,
+      "step": 48000
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 8.216142669711844e-06,
+      "loss": 0.528,
+      "step": 48500
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 8.094659604451141e-06,
+      "loss": 0.5116,
+      "step": 49000
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 7.973176539190437e-06,
+      "loss": 0.5467,
+      "step": 49500
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 7.851693473929734e-06,
+      "loss": 0.5073,
+      "step": 50000
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 7.730210408669033e-06,
+      "loss": 0.544,
+      "step": 50500
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 7.6087273434083295e-06,
+      "loss": 0.5209,
+      "step": 51000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 7.487244278147628e-06,
+      "loss": 0.514,
+      "step": 51500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.365761212886924e-06,
+      "loss": 0.5189,
+      "step": 52000
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.2442781476262215e-06,
+      "loss": 0.5159,
+      "step": 52500
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.122795082365519e-06,
+      "loss": 0.4995,
+      "step": 53000
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 7.001312017104816e-06,
+      "loss": 0.5226,
+      "step": 53500
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 6.879828951844113e-06,
+      "loss": 0.4936,
+      "step": 54000
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.758345886583411e-06,
+      "loss": 0.5277,
+      "step": 54500
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.636862821322708e-06,
+      "loss": 0.5007,
+      "step": 55000
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 6.5153797560620055e-06,
+      "loss": 0.5108,
+      "step": 55500
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 6.393896690801304e-06,
+      "loss": 0.5149,
+      "step": 56000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 6.2724136255406e-06,
+      "loss": 0.5111,
+      "step": 56500
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 6.1509305602798975e-06,
+      "loss": 0.5132,
+      "step": 57000
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 6.029447495019195e-06,
+      "loss": 0.5067,
+      "step": 57500
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 5.907964429758492e-06,
+      "loss": 0.5027,
+      "step": 58000
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.786481364497789e-06,
+      "loss": 0.5302,
+      "step": 58500
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.664998299237087e-06,
+      "loss": 0.477,
+      "step": 59000
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 5.543515233976384e-06,
+      "loss": 0.514,
+      "step": 59500
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 5.422032168715682e-06,
+      "loss": 0.5108,
+      "step": 60000
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 5.300549103454978e-06,
+      "loss": 0.52,
+      "step": 60500
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5.179066038194276e-06,
+      "loss": 0.5177,
+      "step": 61000
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 5.057582972933574e-06,
+      "loss": 0.5323,
+      "step": 61500
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 4.936099907672871e-06,
+      "loss": 0.4662,
+      "step": 62000
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 4.814616842412168e-06,
+      "loss": 0.4248,
+      "step": 62500
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 4.693133777151466e-06,
+      "loss": 0.3953,
+      "step": 63000
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 4.571650711890763e-06,
+      "loss": 0.4326,
+      "step": 63500
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 4.45016764663006e-06,
+      "loss": 0.4445,
+      "step": 64000
+    },
+    {
+      "epoch": 3.13,
+      "learning_rate": 4.328684581369358e-06,
+      "loss": 0.4099,
+      "step": 64500
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 4.207201516108655e-06,
+      "loss": 0.433,
+      "step": 65000
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 4.085718450847952e-06,
+      "loss": 0.4228,
+      "step": 65500
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 3.96423538558725e-06,
+      "loss": 0.4197,
+      "step": 66000
+    },
+    {
+      "epoch": 3.23,
+      "learning_rate": 3.842752320326546e-06,
+      "loss": 0.4482,
+      "step": 66500
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 3.7212692550658443e-06,
+      "loss": 0.4415,
+      "step": 67000
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 3.5997861898051417e-06,
+      "loss": 0.4289,
+      "step": 67500
+    },
+    {
+      "epoch": 3.3,
+      "learning_rate": 3.4783031245444386e-06,
+      "loss": 0.4446,
+      "step": 68000
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 3.3568200592837364e-06,
+      "loss": 0.4625,
+      "step": 68500
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 3.2353369940230333e-06,
+      "loss": 0.3993,
+      "step": 69000
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 3.113853928762331e-06,
+      "loss": 0.4154,
+      "step": 69500
+    },
+    {
+      "epoch": 3.4,
+      "learning_rate": 2.992370863501628e-06,
+      "loss": 0.4245,
+      "step": 70000
+    },
+    {
+      "epoch": 3.43,
+      "learning_rate": 2.8708877982409257e-06,
+      "loss": 0.4084,
+      "step": 70500
+    },
+    {
+      "epoch": 3.45,
+      "learning_rate": 2.7494047329802226e-06,
+      "loss": 0.4191,
+      "step": 71000
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 2.62792166771952e-06,
+      "loss": 0.4498,
+      "step": 71500
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 2.5064386024588173e-06,
+      "loss": 0.4296,
+      "step": 72000
+    },
+    {
+      "epoch": 3.52,
+      "learning_rate": 2.3849555371981147e-06,
+      "loss": 0.456,
+      "step": 72500
+    },
+    {
+      "epoch": 3.55,
+      "learning_rate": 2.263472471937412e-06,
+      "loss": 0.423,
+      "step": 73000
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 2.1419894066767093e-06,
+      "loss": 0.4062,
+      "step": 73500
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 2.0205063414160067e-06,
+      "loss": 0.435,
+      "step": 74000
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 1.899023276155304e-06,
+      "loss": 0.4221,
+      "step": 74500
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 1.7775402108946014e-06,
+      "loss": 0.4444,
+      "step": 75000
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 1.6560571456338987e-06,
+      "loss": 0.4031,
+      "step": 75500
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 1.5345740803731962e-06,
+      "loss": 0.4238,
+      "step": 76000
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 1.4130910151124936e-06,
+      "loss": 0.4356,
+      "step": 76500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 1.291607949851791e-06,
+      "loss": 0.4085,
+      "step": 77000
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 1.170124884591088e-06,
+      "loss": 0.4056,
+      "step": 77500
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 1.0486418193303854e-06,
+      "loss": 0.432,
+      "step": 78000
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 9.271587540696827e-07,
+      "loss": 0.4142,
+      "step": 78500
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 8.056756888089801e-07,
+      "loss": 0.4236,
+      "step": 79000
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 6.841926235482774e-07,
+      "loss": 0.4183,
+      "step": 79500
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 5.627095582875748e-07,
+      "loss": 0.4129,
+      "step": 80000
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 4.4122649302687214e-07,
+      "loss": 0.4052,
+      "step": 80500
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 3.1974342776616943e-07,
+      "loss": 0.4121,
+      "step": 81000
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 1.9826036250546677e-07,
+      "loss": 0.3846,
+      "step": 81500
+    },
+    {
+      "epoch": 3.98,
+      "learning_rate": 7.677729724476409e-08,
+      "loss": 0.4475,
+      "step": 82000
+    },
+    {
+      "epoch": 4.0,
+      "step": 82316,
+      "total_flos": 1.2905751724355635e+17,
+      "train_loss": 0.5708848007960676,
+      "train_runtime": 17933.1446,
+      "train_samples_per_second": 36.722,
+      "train_steps_per_second": 4.59
+    }
+  ],
+  "max_steps": 82316,
+  "num_train_epochs": 4,
+  "total_flos": 1.2905751724355635e+17,
+  "trial_name": null,
+  "trial_params": null
+}

deberta_qa/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:992fc0b718af1b638e2d7e8dc932971da2af84aa1983a79087faf46cb17c0c75
+size 3579

distilbart_summarizer/README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: distilbart-cnn-12-6_1e-5
+  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. -->
+
+# distilbart-cnn-12-6_1e-5
+
+This model is a fine-tuned version of [sshleifer/distilbart-cnn-12-6](https://huggingface.co/sshleifer/distilbart-cnn-12-6) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0778
+- Rouge1: 51.4305
+- Rouge2: 30.8023
+- Rougel: 40.977
+- Rougelsum: 45.5778
+- Gen Len: 79.9607
+
+## 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: 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
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 1.2906        | 0.62  | 500  | 1.1144          | 49.7349 | 29.2413 | 39.062  | 43.9746   | 81.3764 |
+| 1.0677        | 1.25  | 1000 | 1.0895          | 50.4239 | 30.3398 | 40.2029 | 44.8709   | 80.7528 |
+| 0.9725        | 1.87  | 1500 | 1.0740          | 51.3474 | 31.1253 | 40.79   | 45.717    | 81.8455 |
+| 0.8629        | 2.5   | 2000 | 1.0816          | 50.8972 | 30.6779 | 40.4662 | 45.3636   | 81.7191 |
+
+
+### Framework versions
+
+- Transformers 4.27.0.dev0
+- Pytorch 1.13.1+cu117
+- Datasets 2.10.0
+- Tokenizers 0.13.2

distilbart_summarizer/all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 79.96067415730337,
+    "eval_loss": 1.0778131484985352,
+    "eval_rouge1": 51.4305,
+    "eval_rouge2": 30.8023,
+    "eval_rougeL": 40.977,
+    "eval_rougeLsum": 45.5778,
+    "eval_runtime": 172.4056,
+    "eval_samples": 356,
+    "eval_samples_per_second": 2.065,
+    "eval_steps_per_second": 0.516,
+    "train_loss": 1.0117533442084115,
+    "train_runtime": 1656.9583,
+    "train_samples": 3204,
+    "train_samples_per_second": 5.801,
+    "train_steps_per_second": 1.45
+}

distilbart_summarizer/config.json

@@ -0,0 +1,77 @@
+{
+  "_name_or_path": "sshleifer/distilbart-cnn-12-6",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": true,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "max_position_embeddings": 1024,
+  "min_length": 56,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "replacing_rate": 0,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "student_decoder_layers": null,
+  "student_encoder_layers": null,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

distilbart_summarizer/eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 79.96067415730337,
+    "eval_loss": 1.0778131484985352,
+    "eval_rouge1": 51.4305,
+    "eval_rouge2": 30.8023,
+    "eval_rougeL": 40.977,
+    "eval_rougeLsum": 45.5778,
+    "eval_runtime": 172.4056,
+    "eval_samples": 356,
+    "eval_samples_per_second": 2.065,
+    "eval_steps_per_second": 0.516
+}

distilbart_summarizer/generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "min_length": 56,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.27.0.dev0"
+}

distilbart_summarizer/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33aff931672163e076cbe77981c2b52b770a4b1047f0df7b2203838a9fa59ded
+size 1222367837

distilbart_summarizer/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

distilbart_summarizer/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1024,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

distilbart_summarizer/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.0117533442084115,
+    "train_runtime": 1656.9583,
+    "train_samples": 3204,
+    "train_samples_per_second": 5.801,
+    "train_steps_per_second": 1.45
+}

distilbart_summarizer/trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 2403,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.919267582188932e-06,
+      "loss": 1.2906,
+      "step": 500
+    },
+    {
+      "epoch": 0.62,
+      "eval_gen_len": 81.37640449438203,
+      "eval_loss": 1.1144022941589355,
+      "eval_rouge1": 49.7349,
+      "eval_rouge2": 29.2413,
+      "eval_rougeL": 39.062,
+      "eval_rougeLsum": 43.9746,
+      "eval_runtime": 171.8864,
+      "eval_samples_per_second": 2.071,
+      "eval_steps_per_second": 0.518,
+      "step": 500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 5.838535164377861e-06,
+      "loss": 1.0677,
+      "step": 1000
+    },
+    {
+      "epoch": 1.25,
+      "eval_gen_len": 80.75280898876404,
+      "eval_loss": 1.0894856452941895,
+      "eval_rouge1": 50.4239,
+      "eval_rouge2": 30.3398,
+      "eval_rougeL": 40.2029,
+      "eval_rougeLsum": 44.8709,
+      "eval_runtime": 175.8209,
+      "eval_samples_per_second": 2.025,
+      "eval_steps_per_second": 0.506,
+      "step": 1000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.7578027465667915e-06,
+      "loss": 0.9725,
+      "step": 1500
+    },
+    {
+      "epoch": 1.87,
+      "eval_gen_len": 81.84550561797752,
+      "eval_loss": 1.0739564895629883,
+      "eval_rouge1": 51.3474,
+      "eval_rouge2": 31.1253,
+      "eval_rougeL": 40.79,
+      "eval_rougeLsum": 45.717,
+      "eval_runtime": 173.2132,
+      "eval_samples_per_second": 2.055,
+      "eval_steps_per_second": 0.514,
+      "step": 1500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.677070328755722e-06,
+      "loss": 0.8629,
+      "step": 2000
+    },
+    {
+      "epoch": 2.5,
+      "eval_gen_len": 81.71910112359551,
+      "eval_loss": 1.0816434621810913,
+      "eval_rouge1": 50.8972,
+      "eval_rouge2": 30.6779,
+      "eval_rougeL": 40.4662,
+      "eval_rougeLsum": 45.3636,
+      "eval_runtime": 175.4359,
+      "eval_samples_per_second": 2.029,
+      "eval_steps_per_second": 0.507,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "step": 2403,
+      "total_flos": 1.2340414682038272e+16,
+      "train_loss": 1.0117533442084115,
+      "train_runtime": 1656.9583,
+      "train_samples_per_second": 5.801,
+      "train_steps_per_second": 1.45
+    }
+  ],
+  "max_steps": 2403,
+  "num_train_epochs": 3,
+  "total_flos": 1.2340414682038272e+16,
+  "trial_name": null,
+  "trial_params": null
+}

distilbart_summarizer/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6be8f3d3cae48a85c52142f03b0b5e203369cdeaa56919841e1932bbec733a8c
+size 3771

glove.6B.100d.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95dde4dfd627ab26608d33e76d1195ec059734bd29089ea52cadb08d07c64544
+size 347116733

sentence_bert_disco/1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

sentence_bert_disco/README.md

@@ -0,0 +1,125 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+<!--- Describe your model here -->
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
+model = AutoModel.from_pretrained('{MODEL_NAME}')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 2807 with parameters:
+```
+{'batch_size': 8, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.SoftmaxLoss.SoftmaxLoss` 
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 5,
+    "evaluation_steps": 50000,
+    "evaluator": "NoneType",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'transformers.optimization.AdamW'>",
+    "optimizer_params": {
+        "lr": 3e-05
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 1404,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 170, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

sentence_bert_disco/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}