Training in progress, step 500

README.md

@@ -0,0 +1,93 @@
+---
+license: apache-2.0
+base_model: GanjinZero/biobart-v2-base
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: fine-tuned-2048-inputs-30-epochs
+  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. -->
+
+# fine-tuned-2048-inputs-30-epochs
+
+This model is a fine-tuned version of [GanjinZero/biobart-v2-base](https://huggingface.co/GanjinZero/biobart-v2-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8273
+- Rouge1: 0.2933
+- Rouge2: 0.1173
+- Rougel: 0.2662
+- Rougelsum: 0.2653
+- Gen Len: 15.53
+
+## 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: 2e-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
+- num_epochs: 30
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
+| No log        | 1.0   | 151  | 0.7529          | 0.2082 | 0.0781 | 0.1878 | 0.1884    | 13.16   |
+| No log        | 2.0   | 302  | 0.7144          | 0.2589 | 0.0817 | 0.2239 | 0.2244    | 13.76   |
+| No log        | 3.0   | 453  | 0.6993          | 0.2409 | 0.0773 | 0.2135 | 0.2136    | 14.52   |
+| 0.7226        | 4.0   | 604  | 0.6957          | 0.2891 | 0.1014 | 0.262  | 0.2618    | 14.27   |
+| 0.7226        | 5.0   | 755  | 0.7037          | 0.2925 | 0.1167 | 0.2656 | 0.267     | 14.73   |
+| 0.7226        | 6.0   | 906  | 0.6971          | 0.2778 | 0.1124 | 0.2511 | 0.2501    | 14.92   |
+| 0.4948        | 7.0   | 1057 | 0.7117          | 0.2816 | 0.1139 | 0.2558 | 0.2553    | 14.93   |
+| 0.4948        | 8.0   | 1208 | 0.7185          | 0.2948 | 0.1192 | 0.2683 | 0.2679    | 14.45   |
+| 0.4948        | 9.0   | 1359 | 0.7250          | 0.3039 | 0.1108 | 0.2748 | 0.2738    | 14.76   |
+| 0.368         | 10.0  | 1510 | 0.7343          | 0.3187 | 0.1267 | 0.2921 | 0.2919    | 14.67   |
+| 0.368         | 11.0  | 1661 | 0.7418          | 0.3067 | 0.1205 | 0.278  | 0.2772    | 15.23   |
+| 0.368         | 12.0  | 1812 | 0.7521          | 0.3023 | 0.1134 | 0.2764 | 0.2756    | 14.91   |
+| 0.368         | 13.0  | 1963 | 0.7556          | 0.2945 | 0.1143 | 0.272  | 0.2713    | 15.01   |
+| 0.2865        | 14.0  | 2114 | 0.7636          | 0.3163 | 0.1246 | 0.2943 | 0.2942    | 15.44   |
+| 0.2865        | 15.0  | 2265 | 0.7722          | 0.2987 | 0.1105 | 0.2705 | 0.2703    | 14.93   |
+| 0.2865        | 16.0  | 2416 | 0.7788          | 0.3047 | 0.1091 | 0.2745 | 0.2744    | 15.29   |
+| 0.2221        | 17.0  | 2567 | 0.7834          | 0.2973 | 0.113  | 0.2698 | 0.269     | 15.11   |
+| 0.2221        | 18.0  | 2718 | 0.7905          | 0.2933 | 0.1139 | 0.2612 | 0.2595    | 15.1    |
+| 0.2221        | 19.0  | 2869 | 0.7945          | 0.2936 | 0.1036 | 0.2637 | 0.2624    | 15.5    |
+| 0.1825        | 20.0  | 3020 | 0.8033          | 0.3167 | 0.1216 | 0.2839 | 0.2837    | 15.54   |
+| 0.1825        | 21.0  | 3171 | 0.8009          | 0.3056 | 0.1139 | 0.2753 | 0.2747    | 15.69   |
+| 0.1825        | 22.0  | 3322 | 0.8085          | 0.2974 | 0.113  | 0.2632 | 0.2621    | 15.37   |
+| 0.1825        | 23.0  | 3473 | 0.8120          | 0.3063 | 0.1191 | 0.2746 | 0.2749    | 15.48   |
+| 0.1498        | 24.0  | 3624 | 0.8163          | 0.3045 | 0.1114 | 0.2736 | 0.2724    | 15.47   |
+| 0.1498        | 25.0  | 3775 | 0.8197          | 0.3091 | 0.1147 | 0.2789 | 0.2788    | 15.51   |
+| 0.1498        | 26.0  | 3926 | 0.8212          | 0.3003 | 0.1211 | 0.2715 | 0.2718    | 15.59   |
+| 0.1329        | 27.0  | 4077 | 0.8230          | 0.3046 | 0.1158 | 0.2751 | 0.275     | 15.5    |
+| 0.1329        | 28.0  | 4228 | 0.8250          | 0.2871 | 0.1118 | 0.2614 | 0.2599    | 15.49   |
+| 0.1329        | 29.0  | 4379 | 0.8275          | 0.303  | 0.1109 | 0.2734 | 0.2737    | 15.57   |
+| 0.1226        | 30.0  | 4530 | 0.8273          | 0.2933 | 0.1173 | 0.2662 | 0.2653    | 15.53   |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 1.12.1+cu113
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,74 @@
+{
+  "_name_or_path": "GanjinZero/biobart-v2-base",
+  "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": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "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": 2048,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "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": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 85401
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7cd86985a9ec7ca447572602ac485d328b94f5d9fa86a1c2c64413a84424521
+size 665990956

runs/Dec19_19-43-32_william-gpu-3090-10-rxldr/events.out.tfevents.1703015016.william-gpu-3090-10-rxldr.16230.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e288673745958c141416176f714c664926725be5f2ac099d74b28a442b488ac
+size 5652

runs/Dec19_19-46-45_william-gpu-3090-10-rxldr/events.out.tfevents.1703015210.william-gpu-3090-10-rxldr.16318.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5694964f90c9ab7575b6ced9f18fba9422f3b5f6326c7d55c65a175856b9dea8
+size 10480

runs/Dec20_00-20-07_william-gpu-3090-10-rxldr/events.out.tfevents.1703031698.william-gpu-3090-10-rxldr.17060.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2562b4139ec7b39c7dcc017bec5596e4c7476c6a58dc77716ddc868be04588b
+size 23169

runs/Dec27_00-49-11_william-gpu-3090-10-rxldr/events.out.tfevents.1703638154.william-gpu-3090-10-rxldr.17060.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc65bef394cb0f3e5496a2c5ccabff1c43da68e5f79cd576488f9ba347f07de5
+size 88

runs/Dec27_00-49-53_william-gpu-3090-10-rxldr/events.out.tfevents.1703638196.william-gpu-3090-10-rxldr.48922.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21dafba8c562eaa3ecc08f128371c3170992f59b6ef7dce7c2bcbaefaecbde51
+size 7384

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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0592780dbf776fde9718d021f049f161089dcfe0e0be170a4b63fbce710b0291
+size 4463