Upload 13 files

README.md

@@ -0,0 +1,75 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+datasets:
+- midas/inspec
+model-index:
+- name: synonyms_5000_plus_3000_default_3_epoch
+  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. -->
+
+# synonyms_5000_plus_3000_default_3_epoch
+
+This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the midas/inspec generation dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7956
+- F1@5ext: 0.4590
+- P@5ext: 0.6116
+- R@5ext: 0.4109
+- F1@10ext: 0.5403
+- P@10ext: 0.5953
+- R@10ext: 0.5374
+- F1@5abs: 0.2019
+- P@5abs: 0.3080
+- R@5abs: 0.1721
+- F1@10abs: 0.2307
+- P@10abs: 0.3066
+- R@10abs: 0.2109
+- F1@oext: 0.5427
+- P@oext: 0.6045
+- R@oext: 0.5246
+- F1@oabs: 0.2316
+- P@oabs: 0.3079
+- R@oabs: 0.2094
+
+## 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: 10
+- seed: 42
+- gradient_accumulation_steps: 6
+- total_train_batch_size: 24
+- 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 4.24.0.dev0
+- Pytorch 1.9.0+cu111
+- Datasets 2.6.1
+- Tokenizers 0.13.1

all_results.json

@@ -0,0 +1,31 @@
+{
+    "epoch": 3.0,
+    "eval_P@10abs": 0.30658571428571446,
+    "eval_P@10ext": 0.5953404761904763,
+    "eval_P@5abs": 0.30799999999999994,
+    "eval_P@5ext": 0.611566666666667,
+    "eval_P@Oabs": 0.30785714285714294,
+    "eval_P@Oext": 0.6045279220779219,
+    "eval_R@10abs": 0.21094011544011554,
+    "eval_R@10ext": 0.5373799135848676,
+    "eval_R@5abs": 0.17213520923520936,
+    "eval_R@5ext": 0.41086155925258133,
+    "eval_R@Oabs": 0.2093878066378067,
+    "eval_R@Oext": 0.5245630282170534,
+    "eval_f1@10abs": 0.23073327724906695,
+    "eval_f1@10ext": 0.5403372898595006,
+    "eval_f1@5abs": 0.2019063991563992,
+    "eval_f1@5ext": 0.45895300009438544,
+    "eval_f1@Oabs": 0.2315911764705885,
+    "eval_f1@Oext": 0.5427372584935071,
+    "eval_loss": 1.7956230640411377,
+    "eval_runtime": 325.212,
+    "eval_samples": 500,
+    "eval_samples_per_second": 1.537,
+    "eval_steps_per_second": 0.154,
+    "train_loss": 1.0714508148285005,
+    "train_runtime": 1254.6583,
+    "train_samples": 8000,
+    "train_samples_per_second": 19.129,
+    "train_steps_per_second": 0.796
+}

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": 20,
+  "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": "4.24.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,26 @@
+{
+    "epoch": 3.0,
+    "eval_P@10abs": 0.30658571428571446,
+    "eval_P@10ext": 0.5953404761904763,
+    "eval_P@5abs": 0.30799999999999994,
+    "eval_P@5ext": 0.611566666666667,
+    "eval_P@Oabs": 0.30785714285714294,
+    "eval_P@Oext": 0.6045279220779219,
+    "eval_R@10abs": 0.21094011544011554,
+    "eval_R@10ext": 0.5373799135848676,
+    "eval_R@5abs": 0.17213520923520936,
+    "eval_R@5ext": 0.41086155925258133,
+    "eval_R@Oabs": 0.2093878066378067,
+    "eval_R@Oext": 0.5245630282170534,
+    "eval_f1@10abs": 0.23073327724906695,
+    "eval_f1@10ext": 0.5403372898595006,
+    "eval_f1@5abs": 0.2019063991563992,
+    "eval_f1@5ext": 0.45895300009438544,
+    "eval_f1@Oabs": 0.2315911764705885,
+    "eval_f1@Oext": 0.5427372584935071,
+    "eval_loss": 1.7956230640411377,
+    "eval_runtime": 325.212,
+    "eval_samples": 500,
+    "eval_samples_per_second": 1.537,
+    "eval_steps_per_second": 0.154
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6621168733888eb9445a2d10e32b5dcf04999fbfa29103011758aba70fdd30f
+size 1625537793

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "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": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "name_or_path": "facebook/bart-large",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.0714508148285005,
+    "train_runtime": 1254.6583,
+    "train_samples": 8000,
+    "train_samples_per_second": 19.129,
+    "train_steps_per_second": 0.796
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.999,
+  "global_step": 999,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.4974974974974976e-05,
+      "loss": 1.3409,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 999,
+      "total_flos": 1.4606682885095424e+16,
+      "train_loss": 1.0714508148285005,
+      "train_runtime": 1254.6583,
+      "train_samples_per_second": 19.129,
+      "train_steps_per_second": 0.796
+    }
+  ],
+  "max_steps": 999,
+  "num_train_epochs": 3,
+  "total_flos": 1.4606682885095424e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eddb7b862bea04a1c57e11e923e57d60c15c880bfbf75db6e06f724ac4f68e07
+size 3567