End of training

README.md

@@ -1,9 +1,8 @@
 ---
 license: mit
-library_name: peft
+base_model: duancleypaul/bart-cnn-samsum-finetuned
 tags:
 - generated_from_trainer
-base_model: duancleypaul/bart-cnn-samsum-finetuned
 model-index:
 - name: bart-cnn-samsum-peft
   results: []
@@ -16,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [duancleypaul/bart-cnn-samsum-finetuned](https://huggingface.co/duancleypaul/bart-cnn-samsum-finetuned) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1346
+- Loss: 0.1351
 
 ## Model description
 
@@ -41,28 +40,32 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 15
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.1088        | 1.0   | 148  | 0.1343          |
-| 0.0754        | 2.0   | 296  | 0.1343          |
-| 0.0947        | 3.0   | 444  | 0.1342          |
-| 0.0983        | 4.0   | 592  | 0.1342          |
-| 0.0704        | 5.0   | 740  | 0.1343          |
-| 0.1021        | 6.0   | 888  | 0.1344          |
-| 0.0908        | 7.0   | 1036 | 0.1344          |
-| 0.0919        | 8.0   | 1184 | 0.1344          |
-| 0.0964        | 9.0   | 1332 | 0.1346          |
-| 0.0791        | 10.0  | 1480 | 0.1346          |
+| 0.1088        | 1.0   | 148  | 0.1342          |
+| 0.0754        | 2.0   | 296  | 0.1341          |
+| 0.0947        | 3.0   | 444  | 0.1340          |
+| 0.0982        | 4.0   | 592  | 0.1344          |
+| 0.0704        | 5.0   | 740  | 0.1346          |
+| 0.1018        | 6.0   | 888  | 0.1345          |
+| 0.0904        | 7.0   | 1036 | 0.1341          |
+| 0.091         | 8.0   | 1184 | 0.1346          |
+| 0.0957        | 9.0   | 1332 | 0.1346          |
+| 0.0785        | 10.0  | 1480 | 0.1345          |
+| 0.104         | 11.0  | 1628 | 0.1348          |
+| 0.1111        | 12.0  | 1776 | 0.1349          |
+| 0.0839        | 13.0  | 1924 | 0.1350          |
+| 0.0828        | 14.0  | 2072 | 0.1351          |
+| 0.0925        | 15.0  | 2220 | 0.1351          |
 
 
 ### Framework versions
 
-- PEFT 0.9.0
 - Transformers 4.38.2
 - Pytorch 2.1.0+cu121
 - Datasets 2.18.0
-- Tokenizers 0.15.2
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "duancleypaul/bart-cnn-samsum-finetuned",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "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,
+  "force_bos_token_to_be_generated": true,
+  "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
+  },
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "max_position_embeddings": 1024,
+  "min_length": 56,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 50264
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_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,
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "min_length": 56,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.38.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7cc3d61ed4528ff017b3207e17a311c07bb5e42199ee6c5a36a63a790ccacef
+size 1644318512

runs/Mar12_18-08-40_52479658638a/events.out.tfevents.1710266932.52479658638a.683.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:935e6f45c3a19b4244350983298bc82b1a507278c1fc9d298bc467cec6a0c369
+size 73493

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:946f0e9d6cf409fbdd94fe0fd7b9d631717909ab553a9dfbec556650b3f0c9b3
+oid sha256:55f47ec515836d60d916965a7fcbb9e13568677a0f5ca25d4d91dac90d4e2a84
 size 4920