End of training

README.md

@@ -0,0 +1,86 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- samsum
+metrics:
+- rouge
+model-index:
+- name: bert-base-cased-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: 34.9636
+---
+
+<!-- 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. -->
+
+# bert-base-cased-samsum
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the samsum dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.7369
+- Rouge1: 34.9636
+- Rouge2: 10.6358
+- Rougel: 27.6003
+- Rougelsum: 30.9654
+- Gen Len: 17.6020
+
+## 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: 36
+- eval_batch_size: 36
+- 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 | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| No log        | 1.0   | 410  | 2.9218          | 29.2936 | 7.4008  | 23.9609 | 26.3194   | 17.2332 |
+| 2.6834        | 2.0   | 820  | 2.7635          | 31.9826 | 8.9758  | 26.1311 | 28.7458   | 16.9866 |
+| 2.3529        | 3.0   | 1230 | 2.7369          | 34.9636 | 10.6358 | 27.6003 | 30.9654   | 17.6020 |
+| 1.9608        | 4.0   | 1640 | 2.7711          | 35.8322 | 11.3676 | 29.0276 | 32.2881   | 16.9133 |
+| 1.6459        | 5.0   | 2050 | 2.7832          | 36.8688 | 11.8883 | 29.3721 | 32.8683   | 17.0879 |
+| 1.6459        | 6.0   | 2460 | 2.8334          | 36.489  | 11.5372 | 29.2263 | 32.5406   | 17.8901 |
+| 1.3791        | 7.0   | 2870 | 2.8767          | 37.0743 | 11.8554 | 29.4063 | 32.7543   | 17.6093 |
+| 1.1687        | 8.0   | 3280 | 2.9232          | 37.2    | 11.8723 | 29.5194 | 32.9481   | 17.6581 |
+| 1.0249        | 9.0   | 3690 | 2.9456          | 37.1872 | 12.0958 | 29.621  | 33.0073   | 17.8840 |
+| 0.9259        | 10.0  | 4100 | 2.9719          | 37.1213 | 12.1068 | 29.5138 | 33.0372   | 17.8278 |
+
+
+### Framework versions
+
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

config.json

@@ -0,0 +1,174 @@
+{
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "bert-base-cased",
+    "add_cross_attention": true,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 28996
+  },
+  "decoder_start_token_id": 101,
+  "encoder": {
+    "_name_or_path": "bert-base-cased",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 28996
+  },
+  "eos_token_id": 102,
+  "is_encoder_decoder": true,
+  "model_type": "encoder-decoder",
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.34.0"
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 101,
+  "eos_token_id": 102,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:746c97e05bd3cd2c584d0bf381bc75d9a1d7ec7805e5f13887d628043bca6a2f
+size 980254129

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]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9d42f89998c754ec8feca192d897d07f2a596a4b1d1f961ab0c04ecaf0c8d22
+size 4219