adamjweintraut/bart-finetuned-eli5_precomputed

README.md

@@ -0,0 +1,96 @@
+---
+license: apache-2.0
+base_model: facebook/bart-large
+tags:
+- generated_from_trainer
+model-index:
+- name: bart-finetuned-eli5_precomputed
+  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-finetuned-eli5_precomputed
+
+This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 9.6500
+
+## 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
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 3.6463        | 0.05  | 500   | 4.7759          |
+| 3.4654        | 0.1   | 1000  | 5.9053          |
+| 3.4482        | 0.15  | 1500  | 4.4967          |
+| 3.565         | 0.2   | 2000  | 5.9963          |
+| 3.6668        | 0.25  | 2500  | 7.3841          |
+| 3.6065        | 0.3   | 3000  | 5.0156          |
+| 3.3743        | 0.35  | 3500  | 4.0016          |
+| 3.3529        | 0.4   | 4000  | 7.0397          |
+| 3.5418        | 0.45  | 4500  | 9.1284          |
+| 3.4724        | 0.5   | 5000  | 5.0625          |
+| 3.4167        | 0.55  | 5500  | 6.0408          |
+| 3.4061        | 0.6   | 6000  | 7.1911          |
+| 3.6455        | 0.65  | 6500  | 5.6523          |
+| 3.5153        | 0.7   | 7000  | 5.8586          |
+| 3.4019        | 0.75  | 7500  | 6.6155          |
+| 3.4094        | 0.8   | 8000  | 6.0468          |
+| 3.399         | 0.85  | 8500  | 6.7307          |
+| 3.4732        | 0.9   | 9000  | 11.2534         |
+| 3.4973        | 0.95  | 9500  | 8.8126          |
+| 3.4901        | 1.0   | 10000 | 7.7330          |
+| 3.4378        | 1.05  | 10500 | 8.1397          |
+| 3.4239        | 1.1   | 11000 | 7.5238          |
+| 3.4238        | 1.15  | 11500 | 10.0907         |
+| 3.5335        | 1.2   | 12000 | 9.3069          |
+| 3.4442        | 1.25  | 12500 | 9.1980          |
+| 3.1866        | 1.3   | 13000 | 10.1322         |
+| 3.2806        | 1.35  | 13500 | 9.0616          |
+| 3.323         | 1.4   | 14000 | 9.7061          |
+| 3.3219        | 1.45  | 14500 | 7.5160          |
+| 3.5641        | 1.5   | 15000 | 10.6759         |
+| 3.2667        | 1.55  | 15500 | 9.1428          |
+| 3.4873        | 1.6   | 16000 | 10.4514         |
+| 3.4092        | 1.65  | 16500 | 10.0229         |
+| 3.4617        | 1.7   | 17000 | 9.6849          |
+| 3.3726        | 1.75  | 17500 | 9.7335          |
+| 3.2492        | 1.8   | 18000 | 9.0959          |
+| 3.3322        | 1.85  | 18500 | 9.4717          |
+| 3.3306        | 1.9   | 19000 | 10.2230         |
+| 3.3026        | 1.95  | 19500 | 9.9560          |
+| 3.2199        | 2.0   | 20000 | 9.6500          |
+
+
+### Framework versions
+
+- Transformers 4.36.0.dev0
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

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": 4,
+  "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": "4.36.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_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,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.36.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0c4065476f2e9d72e7c53eb88a02f3549d94e3a7f72ab7f7ff571ca32a6aefd
+size 1625426996

runs/Dec04_23-04-34_57871439e38d/events.out.tfevents.1701731075.57871439e38d.2744.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72dea100df6fee91de3f12a7df558fa8344c088c189ec1f7d36a47da7b05a372
+size 11270

runs/Dec05_03-05-49_57871439e38d/events.out.tfevents.1701745569.57871439e38d.2744.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf1397d9ea030b325f140f6a5b90bbccc4e8cbb46f1d4d0436602182891769b
+size 5706

runs/Dec05_05-07-12_57871439e38d/events.out.tfevents.1701752837.57871439e38d.86687.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6a389e71f305353d3467d19b73244e01ceb3d555a6f57c9ce2bc9650d1f6f87
+size 17686

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39eef2beab49d93c8da8ce8ccead77bb4927e568e5719e825c12a4ec4ba91f22
+size 4984