add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: POCTS
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 23.9947
+---
+
+<!-- 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. -->
+
+# POCTS
+
+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: 4.6366
+- Rouge1: 23.9947
+- Rouge2: 5.3034
+- Rougel: 16.3635
+- Rougelsum: 19.7575
+- Gen Len: 55.25
+
+## 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
+- lr_scheduler_warmup_ratio: 0.15
+- num_epochs: 10.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
+| 3.6608        | 1.0   | 125  | 3.3274          | 15.2816 | 4.0723 | 12.0873 | 13.6532   | 19.23   |
+| 3.3135        | 2.0   | 250  | 3.3133          | 16.5105 | 4.4915 | 13.8639 | 14.8435   | 19.31   |
+| 2.7732        | 3.0   | 375  | 3.3856          | 16.8687 | 4.904  | 13.4615 | 14.7432   | 19.93   |
+| 2.2759        | 4.0   | 500  | 3.5508          | 15.4023 | 4.1761 | 12.5635 | 13.7679   | 19.27   |
+| 1.8199        | 5.0   | 625  | 3.7591          | 17.7686 | 4.532  | 13.9086 | 15.3305   | 19.93   |
+| 1.4575        | 6.0   | 750  | 3.9726          | 16.4133 | 4.359  | 13.4621 | 14.5896   | 19.92   |
+| 1.126         | 7.0   | 875  | 4.2964          | 17.3934 | 3.6935 | 13.7934 | 14.9719   | 19.43   |
+| 0.9073        | 8.0   | 1000 | 4.4205          | 17.4328 | 3.8734 | 13.4282 | 14.7105   | 19.83   |
+| 0.7925        | 9.0   | 1125 | 4.5501          | 17.3798 | 3.9775 | 13.3141 | 14.7692   | 19.87   |
+| 0.6844        | 10.0  | 1250 | 4.6366          | 17.3867 | 4.2671 | 13.7924 | 15.1543   | 19.81   |
+
+
+### Framework versions
+
+- Transformers 4.10.2
+- Pytorch 1.7.1+cu110
+- Datasets 1.11.0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,18 @@
+{
+    "epoch": 10.0,
+    "eval_gen_len": 55.25,
+    "eval_loss": 4.636623382568359,
+    "eval_rouge1": 23.9947,
+    "eval_rouge2": 5.3034,
+    "eval_rougeL": 16.3635,
+    "eval_rougeLsum": 19.7575,
+    "eval_runtime": 30.2029,
+    "eval_samples": 100,
+    "eval_samples_per_second": 3.311,
+    "eval_steps_per_second": 0.43,
+    "train_loss": 1.877090069580078,
+    "train_runtime": 1007.5303,
+    "train_samples": 995,
+    "train_samples_per_second": 9.876,
+    "train_steps_per_second": 1.241
+}

config.json

@@ -0,0 +1,73 @@
+{
+  "_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_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": "4.10.2",
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 10.0,
+    "eval_gen_len": 55.25,
+    "eval_loss": 4.636623382568359,
+    "eval_rouge1": 23.9947,
+    "eval_rouge2": 5.3034,
+    "eval_rougeL": 16.3635,
+    "eval_rougeLsum": 19.7575,
+    "eval_runtime": 30.2029,
+    "eval_samples": 100,
+    "eval_samples_per_second": 3.311,
+    "eval_steps_per_second": 0.43
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90eee62817bf936a7493476fc3439c5f8844d7965c7e38dcfe0ac1244ea91248
+size 1625569391

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-large", "tokenizer_class": "BartTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 1.877090069580078,
+    "train_runtime": 1007.5303,
+    "train_samples": 995,
+    "train_samples_per_second": 9.876,
+    "train_steps_per_second": 1.241
+}

trainer_state.json

@@ -0,0 +1,305 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 1250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.223404255319149e-05,
+      "loss": 3.8907,
+      "step": 50
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.5265957446808515e-05,
+      "loss": 3.6608,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 19.23,
+      "eval_loss": 3.32743763923645,
+      "eval_rouge1": 15.2816,
+      "eval_rouge2": 4.0723,
+      "eval_rougeL": 12.0873,
+      "eval_rougeLsum": 13.6532,
+      "eval_runtime": 11.1064,
+      "eval_samples_per_second": 9.004,
+      "eval_steps_per_second": 1.17,
+      "step": 125
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.8563829787234045e-05,
+      "loss": 3.4017,
+      "step": 150
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.967043314500942e-05,
+      "loss": 3.3923,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.7316384180790966e-05,
+      "loss": 3.3135,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 19.31,
+      "eval_loss": 3.313326358795166,
+      "eval_rouge1": 16.5105,
+      "eval_rouge2": 4.4915,
+      "eval_rougeL": 13.8639,
+      "eval_rougeLsum": 14.8435,
+      "eval_runtime": 10.7765,
+      "eval_samples_per_second": 9.279,
+      "eval_steps_per_second": 1.206,
+      "step": 250
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 4.4962335216572505e-05,
+      "loss": 2.7445,
+      "step": 300
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 4.260828625235405e-05,
+      "loss": 2.7732,
+      "step": 350
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 19.93,
+      "eval_loss": 3.3855550289154053,
+      "eval_rouge1": 16.8687,
+      "eval_rouge2": 4.904,
+      "eval_rougeL": 13.4615,
+      "eval_rougeLsum": 14.7432,
+      "eval_runtime": 10.8555,
+      "eval_samples_per_second": 9.212,
+      "eval_steps_per_second": 1.198,
+      "step": 375
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 4.025423728813559e-05,
+      "loss": 2.5055,
+      "step": 400
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 3.790018832391714e-05,
+      "loss": 2.1993,
+      "step": 450
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.554613935969868e-05,
+      "loss": 2.2759,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 19.27,
+      "eval_loss": 3.5507638454437256,
+      "eval_rouge1": 15.4023,
+      "eval_rouge2": 4.1761,
+      "eval_rougeL": 12.5635,
+      "eval_rougeLsum": 13.7679,
+      "eval_runtime": 10.8402,
+      "eval_samples_per_second": 9.225,
+      "eval_steps_per_second": 1.199,
+      "step": 500
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 3.319209039548023e-05,
+      "loss": 1.7219,
+      "step": 550
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 3.0838041431261774e-05,
+      "loss": 1.8199,
+      "step": 600
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 19.93,
+      "eval_loss": 3.7590889930725098,
+      "eval_rouge1": 17.7686,
+      "eval_rouge2": 4.532,
+      "eval_rougeL": 13.9086,
+      "eval_rougeLsum": 15.3305,
+      "eval_runtime": 10.8632,
+      "eval_samples_per_second": 9.205,
+      "eval_steps_per_second": 1.197,
+      "step": 625
+    },
+    {
+      "epoch": 5.2,
+      "learning_rate": 2.8483992467043313e-05,
+      "loss": 1.5748,
+      "step": 650
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 2.612994350282486e-05,
+      "loss": 1.3965,
+      "step": 700
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.3775894538606405e-05,
+      "loss": 1.4575,
+      "step": 750
+    },
+    {
+      "epoch": 6.0,
+      "eval_gen_len": 19.92,
+      "eval_loss": 3.9725918769836426,
+      "eval_rouge1": 16.4133,
+      "eval_rouge2": 4.359,
+      "eval_rougeL": 13.4621,
+      "eval_rougeLsum": 14.5896,
+      "eval_runtime": 10.8642,
+      "eval_samples_per_second": 9.205,
+      "eval_steps_per_second": 1.197,
+      "step": 750
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 2.1421845574387948e-05,
+      "loss": 1.1037,
+      "step": 800
+    },
+    {
+      "epoch": 6.8,
+      "learning_rate": 1.906779661016949e-05,
+      "loss": 1.126,
+      "step": 850
+    },
+    {
+      "epoch": 7.0,
+      "eval_gen_len": 19.43,
+      "eval_loss": 4.29640007019043,
+      "eval_rouge1": 17.3934,
+      "eval_rouge2": 3.6935,
+      "eval_rougeL": 13.7934,
+      "eval_rougeLsum": 14.9719,
+      "eval_runtime": 10.8699,
+      "eval_samples_per_second": 9.2,
+      "eval_steps_per_second": 1.196,
+      "step": 875
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 1.6713747645951036e-05,
+      "loss": 1.0553,
+      "step": 900
+    },
+    {
+      "epoch": 7.6,
+      "learning_rate": 1.435969868173258e-05,
+      "loss": 0.9473,
+      "step": 950
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1.2005649717514125e-05,
+      "loss": 0.9073,
+      "step": 1000
+    },
+    {
+      "epoch": 8.0,
+      "eval_gen_len": 19.83,
+      "eval_loss": 4.420531749725342,
+      "eval_rouge1": 17.4328,
+      "eval_rouge2": 3.8734,
+      "eval_rougeL": 13.4282,
+      "eval_rougeLsum": 14.7105,
+      "eval_runtime": 10.9454,
+      "eval_samples_per_second": 9.136,
+      "eval_steps_per_second": 1.188,
+      "step": 1000
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 9.65160075329567e-06,
+      "loss": 0.7636,
+      "step": 1050
+    },
+    {
+      "epoch": 8.8,
+      "learning_rate": 7.297551789077213e-06,
+      "loss": 0.7925,
+      "step": 1100
+    },
+    {
+      "epoch": 9.0,
+      "eval_gen_len": 19.87,
+      "eval_loss": 4.550107955932617,
+      "eval_rouge1": 17.3798,
+      "eval_rouge2": 3.9775,
+      "eval_rougeL": 13.3141,
+      "eval_rougeLsum": 14.7692,
+      "eval_runtime": 10.8417,
+      "eval_samples_per_second": 9.224,
+      "eval_steps_per_second": 1.199,
+      "step": 1125
+    },
+    {
+      "epoch": 9.2,
+      "learning_rate": 4.990583804143127e-06,
+      "loss": 0.7396,
+      "step": 1150
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 2.6365348399246707e-06,
+      "loss": 0.6792,
+      "step": 1200
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 2.8248587570621473e-07,
+      "loss": 0.6844,
+      "step": 1250
+    },
+    {
+      "epoch": 10.0,
+      "eval_gen_len": 19.81,
+      "eval_loss": 4.636623382568359,
+      "eval_rouge1": 17.3867,
+      "eval_rouge2": 4.2671,
+      "eval_rougeL": 13.7924,
+      "eval_rougeLsum": 15.1543,
+      "eval_runtime": 10.8893,
+      "eval_samples_per_second": 9.183,
+      "eval_steps_per_second": 1.194,
+      "step": 1250
+    },
+    {
+      "epoch": 10.0,
+      "step": 1250,
+      "total_flos": 2.278181410848768e+16,
+      "train_loss": 1.877090069580078,
+      "train_runtime": 1007.5303,
+      "train_samples_per_second": 9.876,
+      "train_steps_per_second": 1.241
+    }
+  ],
+  "max_steps": 1250,
+  "num_train_epochs": 10,
+  "total_flos": 2.278181410848768e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70f5cbd5c3fdf1dff1e73912d6b5f5e3bf6950bf344cc4feff7de3eec81290ac
+size 2799