adamjweintraut/bart-finetuned-eli5_base_best

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+base_model: facebook/bart-large
+tags:
+- generated_from_trainer
+model-index:
+- name: bart-finetuned-eli5_base_best
+  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_base_best
+
+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: 1.1849
+
+## 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 |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.3965        | 0.1   | 500   | 1.2495          |
+| 1.3676        | 0.2   | 1000  | 1.2362          |
+| 1.3024        | 0.3   | 1500  | 1.2294          |
+| 1.2331        | 0.4   | 2000  | 1.2301          |
+| 1.2476        | 0.5   | 2500  | 1.2266          |
+| 1.2049        | 0.6   | 3000  | 1.2202          |
+| 1.1811        | 0.7   | 3500  | 1.2857          |
+| 1.2227        | 0.8   | 4000  | 1.2702          |
+| 1.2629        | 0.9   | 4500  | 1.2206          |
+| 1.1233        | 1.0   | 5000  | 1.2187          |
+| 1.1995        | 1.1   | 5500  | 1.1957          |
+| 1.0835        | 1.2   | 6000  | 1.2026          |
+| 1.1033        | 1.3   | 6500  | 1.2250          |
+| 1.127         | 1.4   | 7000  | 1.2091          |
+| 1.0964        | 1.5   | 7500  | 1.1929          |
+| 1.1321        | 1.6   | 8000  | 1.1827          |
+| 1.051         | 1.7   | 8500  | 1.1791          |
+| 1.054         | 1.8   | 9000  | 1.1926          |
+| 1.0034        | 1.9   | 9500  | 1.1769          |
+| 1.0645        | 2.0   | 10000 | 1.1849          |
+
+
+### 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:baee4a10c95696348f0f83c6aff4cde0afdc9d6d02fee10ea904023a134046af
+size 1625426996

runs/Dec07_08-34-46_b8034897d4e6/events.out.tfevents.1701938087.b8034897d4e6.685.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d825073a96f2a0b565dc98f34c1cd10404341617371877a5aaa75f5a7feaed1
+size 5700

runs/Dec07_08-42-09_372ea576bba3/events.out.tfevents.1701938530.372ea576bba3.225034.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d740e08498d6c65a4497b24d8d8e90a179beaf38be7fbe51228d0c0f6cf1ff6
+size 14614

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7114fd55095a1e6e5b3af39bd722a48a275d18d0cd0fafcd68840464741ef8f8
+size 4984