trained on new dataset for 2 epochs

README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+base_model: Strange18/results
+tags:
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [Strange18/results](https://huggingface.co/Strange18/results) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- epoch: 2.0
+- eval_bleu: 0.2356
+- eval_loss: 0.1289
+- eval_rouge1: 0.5418
+- eval_rouge2: 0.3046
+- eval_rougeL: 0.4929
+- eval_rougeLsum: 0.4932
+- eval_runtime: 31.1564
+- eval_sacrebleu: 23.5626
+- eval_samples_per_second: 4.558
+- eval_steps_per_second: 1.155
+- eval_ter: 63.2172
+- step: 672
+
+## 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: 1e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- 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: 50
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.1.2
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/mbart-large-50",
+  "_name_or_path": "Strange18/results",
   "_num_labels": 3,
   "activation_dropout": 0.0,
   "activation_function": "gelu",
@@ -52,7 +52,7 @@
   "static_position_embeddings": false,
   "tokenizer_class": "MBart50Tokenizer",
   "torch_dtype": "float32",
-  "transformers_version": "4.46.2",
+  "transformers_version": "4.46.3",
   "use_cache": true,
   "vocab_size": 250054
 }

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "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:ea539e4d6ed87fc13a2b4d26eed5e65bb4a46f238c574245f13009fda1bd9641
+oid sha256:559d431f1d0dc6f1b26685fa090cd704cf740851239cfa84fb47406679b8c2c0
 size 2444578688

special_tokens_map.json

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

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa01d6979e2a73175ce3e1e52801925be5fbcdf29d4f373aad434f7ff6b4bd9
-size 17110186
+oid sha256:3ac4bfeac2fcd7cbc788d5a8d708aea33f37f05b4898b0c23651da928afcfa72
+size 17094570

tokenizer_config.json

@@ -516,12 +516,19 @@
   "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 sha256:8e74b08053c1ada3a7db96ee8d19ee535a0e7cdd5260e01552cdd9095aa3091a
+oid sha256:cb852f8eeb1665d13ac00df8d7045de1c8834dd98f21f9748f2e4f7eccd4cc95
 size 5432