Training in progress, step 500

README.md

@@ -0,0 +1,55 @@
+---
+library_name: transformers
+base_model: Nubletz/bart-text-simplification
+tags:
+- generated_from_trainer
+model-index:
+- name: bart-text-simplification
+  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. -->
+
+# bart-text-simplification
+
+This model is a fine-tuned version of [Nubletz/bart-text-simplification](https://huggingface.co/Nubletz/bart-text-simplification) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.6558
+- eval_model_preparation_time: 0.0082
+- eval_sari: 59.0183
+- eval_runtime: 670.1131
+- eval_samples_per_second: 1.343
+- eval_steps_per_second: 1.343
+- step: 0
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "facebook/bart-large-cnn",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "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,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "force_bos_token_to_be_generated": true,
+  "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
+  },
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "max_position_embeddings": 1024,
+  "min_length": 56,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 50264
+}

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,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "min_length": 56,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66485615bac135c6000a3d44aa8e9be6543932bc6aa962969e8de37652ded9bb
+size 1625422896

runs/Oct02_09-21-34_b1491a90e5c3/events.out.tfevents.1727860895.b1491a90e5c3.54192.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3d08cba2f95427edd7b661aea5d15043a79b98715363774a8fedcb24de59faf
+size 6126

runs/Oct02_12-14-50_0cb37853dac1/events.out.tfevents.1727871961.0cb37853dac1.357.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf4b2aa47fc930a7dacf4acdf8e42b4f308f3c3117ad02f8c886cfecfffd6615
+size 405

runs/Oct02_15-20-02_0cb37853dac1/events.out.tfevents.1727882406.0cb37853dac1.357.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eec38ee23715fad3859ea240f253bda233c77e5585b914c5e47b6a49bc3c0e27
+size 13404

runs/Oct10_14-32-36_82e1241489e1/events.out.tfevents.1728570757.82e1241489e1.42894.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e477224e634d17cb69d040fc14f5a01d0159b8f8bbc4830c5ec59d049cec25
+size 6481

runs/Oct10_17-27-50_82e1241489e1/events.out.tfevents.1728581272.82e1241489e1.92841.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6647b03c15bb105e0538436017717e0ed9c718058c017aa5262df8190a83ec2
+size 6444

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c741e08e0a218d15ed957759bf69c4afc5e61351a01a8317ce112b217783268f
+size 5176