End of training

README.md

@@ -0,0 +1,91 @@
+---
+base_model: facebook/bart-large-cnn
+library_name: peft
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: fine_tuned_bart
+  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. -->
+
+# fine_tuned_bart
+
+This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7075
+
+## 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: 4e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 8    | 0.7205          |
+| 0.4729        | 2.0   | 16   | 0.7109          |
+| 0.4794        | 3.0   | 24   | 0.7048          |
+| 0.4716        | 4.0   | 32   | 0.7081          |
+| 0.476         | 5.0   | 40   | 0.7095          |
+| 0.476         | 6.0   | 48   | 0.7174          |
+| 0.4751        | 7.0   | 56   | 0.7050          |
+| 0.4683        | 8.0   | 64   | 0.7047          |
+| 0.4583        | 9.0   | 72   | 0.7058          |
+| 0.474         | 10.0  | 80   | 0.7045          |
+| 0.474         | 11.0  | 88   | 0.7062          |
+| 0.4651        | 12.0  | 96   | 0.7047          |
+| 0.4523        | 13.0  | 104  | 0.7028          |
+| 0.4626        | 14.0  | 112  | 0.7049          |
+| 0.4634        | 15.0  | 120  | 0.7067          |
+| 0.4634        | 16.0  | 128  | 0.7091          |
+| 0.4543        | 17.0  | 136  | 0.7087          |
+| 0.4502        | 18.0  | 144  | 0.7084          |
+| 0.4604        | 19.0  | 152  | 0.7098          |
+| 0.4503        | 20.0  | 160  | 0.7065          |
+| 0.4503        | 21.0  | 168  | 0.7046          |
+| 0.4642        | 22.0  | 176  | 0.7033          |
+| 0.4334        | 23.0  | 184  | 0.7029          |
+| 0.4626        | 24.0  | 192  | 0.7037          |
+| 0.4584        | 25.0  | 200  | 0.7046          |
+| 0.4584        | 26.0  | 208  | 0.7063          |
+| 0.4508        | 27.0  | 216  | 0.7075          |
+| 0.4498        | 28.0  | 224  | 0.7078          |
+| 0.4532        | 29.0  | 232  | 0.7077          |
+| 0.4514        | 30.0  | 240  | 0.7075          |
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "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,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:921c3968411a6d48bc21c7110c24790ec7dd20ab6d1c0041562d3b6ce3e4b9d6
+size 9457520

runs/Jul28_08-48-33_afaa35a3d8be/events.out.tfevents.1722156583.afaa35a3d8be.1014.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80cd1d921cbd27c37097bc2f4d6fdb14d808a649fd5d1cb34a6d251ee2e33297
+size 8324

runs/Jul28_09-11-55_afaa35a3d8be/events.out.tfevents.1722157927.afaa35a3d8be.1014.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b110d4ca99fd62525f0da29eca0602328fbf964992dde4fdff2d229f9941fe48
+size 10484

runs/Jul28_09-23-38_afaa35a3d8be/events.out.tfevents.1722158663.afaa35a3d8be.1014.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a203768be408fd1cf71a4038490f123c2fb2d04cf0e8c4a7cd01383c16eb1ff
+size 10137

runs/Jul28_09-30-06_afaa35a3d8be/events.out.tfevents.1722159018.afaa35a3d8be.1014.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5945f070da8c6bc84f094eb52d6df5f92fe5dd14392058e249d424b1b676f3d1
+size 10488

runs/Jul28_09-37-21_afaa35a3d8be/events.out.tfevents.1722159454.afaa35a3d8be.1014.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac33aec85744e5f6f38efa65650a79762311dffbb37021d3beb2034d030f6861
+size 19249

runs/Jul28_09-55-59_afaa35a3d8be/events.out.tfevents.1722160570.afaa35a3d8be.1014.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2b1e36c53cb03812a552636fd591548d76d176627cd68fdf2965bb6dfe1c13
+size 28044

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": 1000000000000000019884624838656,
+  "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:f4e13a3688c1862a2c1c993539dabadce75b805463ef3d3da6c2ed82f7c73361
+size 5112