waiman721/fine_tuned_bart-large-cnn_multi_news

README.md

@@ -1,10 +1,8 @@
 ---
-license: apache-2.0
-base_model: facebook/bart-base
+license: mit
+base_model: facebook/bart-large-cnn
 tags:
 - generated_from_trainer
-metrics:
-- rouge
 model-index:
 - name: results
   results: []
@@ -15,14 +13,19 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on an unknown dataset.
+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: 4.3563
-- Rouge1: 21.9158
-- Rouge2: 7.8595
-- Rougel: 16.6472
-- Rougelsum: 18.5866
-- Gen Len: 20.0
+- eval_loss: 3.5112
+- eval_rouge1: 36.7687
+- eval_rouge2: 12.7988
+- eval_rougeL: 23.4116
+- eval_rougeLsum: 29.7494
+- eval_gen_len: 65.0396
+- eval_runtime: 1370.2695
+- eval_samples_per_second: 1.641
+- eval_steps_per_second: 0.411
+- epoch: 0.09
+- step: 999
 
 ## Model description
 
@@ -48,13 +51,9 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 4
+- num_epochs: 1
 - label_smoothing_factor: 0.1
 
-### Training results
-
-
-
 ### Framework versions
 
 - Transformers 4.38.2

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "facebook/bart-base",
+  "base_model_name_or_path": "facebook/bart-large-cnn",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": false,
@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "fc1",
-    "out_proj",
     "fc2",
+    "v_proj",
     "q_proj",
-    "k_proj",
-    "v_proj"
+    "out_proj",
+    "fc1",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f03eb2ee64b8916f5ea413bf8c86370a1c121ae83de06145764f0f9614bf5c
-size 51931152
+oid sha256:adb96cab28617a8199818c9f1b5cce18e1b9c6292e34246ac774cbf743498ed0
+size 138465976

generation_config.json

@@ -5,6 +5,9 @@
   "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,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:355b9322e55c41a0568c56d3a42865467d431e62102f27845604372b50ae0961
+oid sha256:242f0197648bbbdcd8d0d3954e84f1b447715477abe7c9a5f5171d30d2bd29b5
 size 4984