End of training - Hybrid Luhn + LED

README.md

@@ -0,0 +1,62 @@
+---
+library_name: transformers
+base_model: 0-hero/led-large-legal-summary
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [0-hero/led-large-legal-summary](https://huggingface.co/0-hero/led-large-legal-summary) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1953
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 5
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.3391        | 1.0   | 515  | 2.3141          |
+| 1.9654        | 2.0   | 1030 | 2.2136          |
+| 1.815         | 3.0   | 1545 | 2.1874          |
+| 1.7097        | 4.0   | 2060 | 2.1793          |
+| 1.5982        | 5.0   | 2575 | 2.1953          |
+
+
+### Framework versions
+
+- Transformers 4.51.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 2.468837849038848e+16,
+    "train_loss": 1.9720702991670775,
+    "train_runtime": 8137.4585,
+    "train_samples_per_second": 1.265,
+    "train_steps_per_second": 0.316
+}

config.json

@@ -1,23 +1,68 @@
 {
-  "activation": "gelu",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
   "architectures": [
-    "DistilBertForQuestionAnswering"
+    "LEDForConditionalGeneration"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
+  "attention_dropout": 0.0,
+  "attention_window": [
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "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,
-  "hidden_dim": 3072,
-  "initializer_range": 0.02,
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "early_stopping": null,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "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": null,
+  "max_decoder_position_embeddings": 1024,
+  "max_encoder_position_embeddings": 16384,
+  "max_length": null,
+  "min_length": null,
+  "model_type": "led",
+  "no_repeat_ngram_size": null,
+  "num_beams": null,
+  "num_hidden_layers": 12,
+  "output_past": false,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "repetition_penalty": null,
   "torch_dtype": "float32",
-  "transformers_version": "4.50.3",
-  "vocab_size": 30522
+  "transformers_version": "4.51.1",
+  "use_cache": false,
+  "vocab_size": 50265
 }

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "length_penalty": 0.8,
+  "max_length": 1024,
+  "min_length": 8,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "repetition_penalty": 3.5,
+  "transformers_version": "4.51.1",
+  "use_cache": false
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe078334a1d336480956f4722a660837da5ac5aaac246cce54763b9324d8997d
-size 265470032
+oid sha256:12d4fdd9bf936ed82ca1e3cc550ffa3cf4bb8b0c74e2e897c87ee6de77e2eb1b
+size 1839478364

special_tokens_map.json

@@ -1,7 +1,51 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "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

@@ -1,56 +1,62 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
-      "normalized": false,
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": false,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
   "extra_special_tokens": {},
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 16384,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "LEDTokenizer",
+  "trim_offsets": true,
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
 }

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 2.468837849038848e+16,
+    "train_loss": 1.9720702991670775,
+    "train_runtime": 8137.4585,
+    "train_samples_per_second": 1.265,
+    "train_steps_per_second": 0.316
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e1d8289c6bea0df06eb106a8e3d899f6bf371130e4d8dacaaa799f04f1db07
-size 5304
+oid sha256:df94bb618dffc2cfc260ce7a1a56740163d1cbbb797385dfec089e80c5b428d3
+size 5240