End of training

README.md

@@ -0,0 +1,108 @@
+---
+license: apache-2.0
+base_model: allenai/led-base-16384
+tags:
+- generated_from_trainer
+model-index:
+- name: Trying_LED_Model_Hiporank_final_setting.ipynb
+  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. -->
+
+# Trying_LED_Model_Hiporank_final_setting.ipynb
+
+This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5873
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.8616        | 0.1008 | 10   | 2.8924          |
+| 2.8923        | 0.2015 | 20   | 2.8183          |
+| 2.9791        | 0.3023 | 30   | 2.7639          |
+| 2.9044        | 0.4030 | 40   | 2.7276          |
+| 2.428         | 0.5038 | 50   | 2.7162          |
+| 2.9009        | 0.6045 | 60   | 2.6943          |
+| 2.9211        | 0.7053 | 70   | 2.6682          |
+| 2.7291        | 0.8060 | 80   | 2.6528          |
+| 2.6494        | 0.9068 | 90   | 2.6525          |
+| 2.7393        | 1.0076 | 100  | 2.6357          |
+| 2.3916        | 1.1083 | 110  | 2.6384          |
+| 2.4493        | 1.2091 | 120  | 2.6262          |
+| 2.4752        | 1.3098 | 130  | 2.6014          |
+| 2.1968        | 1.4106 | 140  | 2.6068          |
+| 2.538         | 1.5113 | 150  | 2.5980          |
+| 2.4522        | 1.6121 | 160  | 2.5959          |
+| 2.4397        | 1.7128 | 170  | 2.6017          |
+| 2.4763        | 1.8136 | 180  | 2.5837          |
+| 1.999         | 1.9144 | 190  | 2.5749          |
+| 2.0956        | 2.0151 | 200  | 2.5696          |
+| 2.1285        | 2.1159 | 210  | 2.6099          |
+| 2.1804        | 2.2166 | 220  | 2.5931          |
+| 2.0031        | 2.3174 | 230  | 2.5913          |
+| 2.094         | 2.4181 | 240  | 2.5875          |
+| 2.2214        | 2.5189 | 250  | 2.5639          |
+| 2.0745        | 2.6196 | 260  | 2.5723          |
+| 2.3377        | 2.7204 | 270  | 2.5750          |
+| 1.9967        | 2.8212 | 280  | 2.5710          |
+| 2.1091        | 2.9219 | 290  | 2.5694          |
+| 2.0384        | 3.0227 | 300  | 2.5606          |
+| 1.9828        | 3.1234 | 310  | 2.5971          |
+| 2.1608        | 3.2242 | 320  | 2.5857          |
+| 1.9558        | 3.3249 | 330  | 2.5793          |
+| 2.0719        | 3.4257 | 340  | 2.5769          |
+| 1.8055        | 3.5264 | 350  | 2.5804          |
+| 2.0445        | 3.6272 | 360  | 2.5758          |
+| 2.0795        | 3.7280 | 370  | 2.5924          |
+| 2.073         | 3.8287 | 380  | 2.5745          |
+| 2.0314        | 3.9295 | 390  | 2.5697          |
+| 2.0928        | 4.0302 | 400  | 2.5731          |
+| 1.9158        | 4.1310 | 410  | 2.5942          |
+| 2.054         | 4.2317 | 420  | 2.5846          |
+| 1.8497        | 4.3325 | 430  | 2.5963          |
+| 1.8353        | 4.4332 | 440  | 2.5943          |
+| 1.9786        | 4.5340 | 450  | 2.5891          |
+| 1.9003        | 4.6348 | 460  | 2.5914          |
+| 1.9248        | 4.7355 | 470  | 2.5876          |
+| 2.1843        | 4.8363 | 480  | 2.5873          |
+| 1.9193        | 4.9370 | 490  | 2.5873          |
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "allenai/led-base-16384",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "LEDForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_window": [
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "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,
+  "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_decoder_position_embeddings": 1024,
+  "max_encoder_position_embeddings": 16384,
+  "max_length": 512,
+  "min_length": 100,
+  "model_type": "led",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 2,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": false,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e36cd86311a0093e095e9e5f749374da61b29efee5bf0113740b41d006a84f57
+size 647614116

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 +1,57 @@
+{
+  "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": 16384,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LEDTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a23529bce64206e30dc9bcae6f1db1f8858d740411077cfeb2f56d17b6fec77
+size 5304