bart-finetuned-loaf-512-lyrictoplan

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 0.8160
+- Loss: 0.4458
 
 ## Model description
 
@@ -40,25 +40,24 @@ 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: 4
+- num_epochs: 3
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.4176        | 0.45  | 500  | 1.1073          |
-| 1.1228        | 0.89  | 1000 | 0.9915          |
-| 0.9568        | 1.34  | 1500 | 0.9347          |
-| 0.888         | 1.78  | 2000 | 0.8795          |
-| 0.8179        | 2.23  | 2500 | 0.8774          |
-| 0.7929        | 2.67  | 3000 | 0.8551          |
-| 0.7256        | 3.12  | 3500 | 0.8213          |
-| 0.6979        | 3.56  | 4000 | 0.8160          |
+| 1.0218        | 0.45  | 500  | 0.5545          |
+| 0.5582        | 0.89  | 1000 | 0.5083          |
+| 0.4996        | 1.34  | 1500 | 0.4844          |
+| 0.4744        | 1.78  | 2000 | 0.4609          |
+| 0.449         | 2.23  | 2500 | 0.4560          |
+| 0.4287        | 2.67  | 3000 | 0.4458          |
 
 
 ### Framework versions
 
-- Transformers 4.39.3
+- Transformers 4.38.2
 - Pytorch 2.2.1+cu121
 - Datasets 2.18.0
 - Tokenizers 0.15.2

generation_config.json

@@ -1,13 +1,25 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 0,
+  "clean_up_tokenization_spaces": true,
   "decoder_start_token_id": 2,
+  "do_sample": true,
   "early_stopping": true,
   "eos_token_id": 2,
   "forced_bos_token_id": 0,
   "forced_eos_token_id": 2,
+  "max_new_tokens": 512,
+  "min_new_tokens": 128,
+  "n_examples": null,
   "no_repeat_ngram_size": 3,
   "num_beams": 4,
   "pad_token_id": 1,
-  "transformers_version": "4.39.3"
+  "padding": "max_length",
+  "renormalize_logits": true,
+  "repetition_penalty": 0.6,
+  "skip_special_tokens": true,
+  "temperature": 0.85,
+  "top_k": 0,
+  "top_p": 0.9,
+  "transformers_version": "4.38.2",
+  "truncation": true
 }

runs/Apr09_04-20-42_870b8dce1033/events.out.tfevents.1712636443.870b8dce1033.342.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21300487002646825696ff09f4e5df7e9bb1f783d0edb5d5dfa9429694293e0e
-size 9033
+oid sha256:501c2bfdf543df9dbdb9cf1578e328c24a523ad8d320ceb5d758a5f80b528617
+size 9387