End of training

README.md

@@ -0,0 +1,58 @@
+---
+license: mit
+base_model: facebook/bart-large-cnn
+tags:
+- generated_from_trainer
+datasets:
+- multi_news
+model-index:
+- name: bart-large-cnn-finetuned-multinews-lora
+  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-large-cnn-finetuned-multinews-lora
+
+This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on the multi_news dataset.
+
+## 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: 0.002
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| No log        | 1.0   | 125  | 2.1709          | 40.5509 | 13.2659 | 22.2136 | 34.3365   | 123.36  |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.0.0
+- Datasets 2.1.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/bart-large-cnn",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "SEQ_2_SEQ_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e25ac454c630bb83d70826cc762dd54d611005fc05a58bef881a20692628005
+size 4738744

runs/Dec10_19-05-17_dfb59c01866d/events.out.tfevents.1702235123.dfb59c01866d.110.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0062f7481e65fc3bec2038c40336e58f46ee6b5115e963b146c4c1ddd4171b1
+size 5426

runs/Dec10_19-36-21_dfb59c01866d/events.out.tfevents.1702236985.dfb59c01866d.110.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d52ce63b55c53e690c9dd639ee1780ca3cff336de93a734df7dc1548e4e90688
+size 5426

runs/Dec10_19-38-30_dfb59c01866d/events.out.tfevents.1702237112.dfb59c01866d.110.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d61057722e47324aa0da8719986455d279dda7d84aa8a681899f5197671f1cc
+size 5583

runs/Dec10_19-49-14_dfb59c01866d/events.out.tfevents.1702237759.dfb59c01866d.110.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a0ed613f3fe9b730469a1667fed2ef1ee31cbfa6bd4ce1ecdd4f934052f569
+size 5580

runs/Dec10_19-58-04_dfb59c01866d/events.out.tfevents.1702238287.dfb59c01866d.110.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd3c3fb6ae1a3aaa60c9c5b1454d700cd5eebb49aa8c7e6964d90e2f619bbc1
+size 5580

runs/Dec10_20-12-01_dfb59c01866d/events.out.tfevents.1702239124.dfb59c01866d.110.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe9590fb10dfcba47ab080bb611067625650fec14985ae20819e042582d905b
+size 5423

runs/Dec10_20-14-12_dfb59c01866d/events.out.tfevents.1702239254.dfb59c01866d.110.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d873b0c437383aa3e4e2dc53ce4a9dd8bbb7b7e83ee1862794b3317a5c2f61bb
+size 9519

runs/Dec10_20-20-08_dfb59c01866d/events.out.tfevents.1702239611.dfb59c01866d.1016.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c47c3cb9e526a281a867f04a6361e25f9a21a24aae544fa47daf4ecf28ded095
+size 6286

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

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": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b57d2a4a3e62802121fc5ad903d7b8f08b0ccb0e8e4233df98b62474de9cebef
+size 4347