trained on new dataset for 2 epochs

README.md

@@ -1,12 +1,9 @@
 ---
 library_name: transformers
-base_model: Strange18/results
+license: mit
+base_model: facebook/mbart-large-50
 tags:
 - generated_from_trainer
-metrics:
-- sacrebleu
-- bleu
-- rouge
 model-index:
 - name: results
   results: []
@@ -17,16 +14,21 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [Strange18/results](https://huggingface.co/Strange18/results) on an unknown dataset.
+This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1108
-- Sacrebleu: 28.4098
-- Bleu: 0.2841
-- Rouge1: 0.6157
-- Rouge2: 0.3844
-- Rougel: 0.5828
-- Rougelsum: 0.5826
-- Ter: 53.4048
+- eval_loss: 0.2581
+- eval_sacrebleu: 32.6503
+- eval_bleu: 0.3265
+- eval_rouge1: 0.6372
+- eval_rouge2: 0.4402
+- eval_rougeL: 0.5635
+- eval_rougeLsum: 0.5632
+- eval_ter: 60.4240
+- eval_runtime: 826.7326
+- eval_samples_per_second: 1.512
+- eval_steps_per_second: 0.379
+- epoch: 2.0
+- step: 2969
 
 ## Model description
 
@@ -46,26 +48,17 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 8
+- total_train_batch_size: 16
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 700
-- num_epochs: 3
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch  | Step | Validation Loss | Sacrebleu | Bleu   | Rouge1 | Rouge2 | Rougel | Rougelsum | Ter     |
-|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:------:|:------:|:------:|:---------:|:-------:|
-| 0.2067        | 0.9978 | 335  | 0.1662          | 16.3668   | 0.1637 | 0.4966 | 0.2466 | 0.4518 | 0.4506    | 68.4718 |
-| 0.1603        | 1.9993 | 671  | 0.1570          | 19.9178   | 0.1992 | 0.5186 | 0.2854 | 0.4882 | 0.4874    | 63.0027 |
-| 0.1169        | 2.9948 | 1005 | 0.1108          | 28.4098   | 0.2841 | 0.6157 | 0.3844 | 0.5828 | 0.5826    | 53.4048 |
-
-
 ### Framework versions
 
 - Transformers 4.46.3

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Strange18/results",
+  "_name_or_path": "facebook/mbart-large-50",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "gelu",

generation_config.json

@@ -1,8 +1,11 @@
 {
   "bos_token_id": 0,
   "decoder_start_token_id": 2,
+  "early_stopping": true,
   "eos_token_id": 2,
   "forced_eos_token_id": 2,
+  "max_length": 200,
+  "num_beams": 5,
   "pad_token_id": 1,
   "transformers_version": "4.46.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2e8ef8afc2c8e8c14a003a30b03d2e9f35aef109b2cafb7c4ad8cb2ac055ba3
+oid sha256:95ab08cebabd0e7ed31f9eb7fbfd791e229df4e8a32de44e1f4764825147139f
 size 2444578688

special_tokens_map.json

@@ -53,27 +53,9 @@
     "gl_ES",
     "sl_SI"
   ],
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
@@ -81,25 +63,7 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac4bfeac2fcd7cbc788d5a8d708aea33f37f05b4898b0c23651da928afcfa72
-size 17094570
+oid sha256:4dc505bc21a5065c9dc2bf957fdcbf1626c7ec1e706cd25535dfbd2846956518
+size 17109921

tokenizer_config.json

@@ -516,19 +516,12 @@
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": "<mask>",
-  "max_length": 200,
   "model_max_length": 1024,
-  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "</s>",
   "sp_model_kwargs": {},
   "src_lang": "ne_NP",
-  "stride": 0,
   "tgt_lang": "en_XX",
   "tokenizer_class": "MBart50Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50a434fc6367b5dfee6cea33ddd0ee0000ddf4739bf62a83674e602713332960
+oid sha256:aaa7a50051e6f6db3fa6a91c95035ec9ada3e5ad7cbe89fd2b3495d6de9e3e6a
 size 5432