initial commit

README.md

@@ -1,3 +1,91 @@
----
-license: cc
----
+---
+tags:
+- generated_from_trainer
+datasets:
+- mlsum
+metrics:
+- rouge
+model-index:
+- name: eval-mbart-large
+  results:
+  - task:
+      name: Summarization
+      type: summarization
+    dataset:
+      name: mlsum tu
+      type: mlsum
+      args: tu
+    metrics:
+    - name: Rouge1
+      type: rouge
+      value: 46.7011
+---
+
+<!-- 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. -->
+
+# eval-mbart-large
+
+This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the mlsum tu dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.8386
+- Rouge1: 46.7011
+- Rouge2: 34.0087
+- Rougel: 41.5475
+- Rougelsum: 43.2108
+- Gen Len: 43.2426
+
+## 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: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10.0
+- mixed_precision_training: Native AMP
+- label_smoothing_factor: 0.1
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 2.9098        | 1.0   | 3895  | 2.8820          | 45.2085 | 33.0253 | 40.3511 | 41.8378   | 40.1802 |
+| 2.7496        | 2.0   | 7790  | 2.8620          | 45.3455 | 33.0049 | 40.4574 | 41.9738   | 40.845  |
+| 2.6215        | 3.0   | 11685 | 2.8386          | 46.6642 | 34.0133 | 41.5102 | 43.1852   | 43.3505 |
+| 2.5031        | 4.0   | 15580 | 2.8620          | 46.5081 | 33.9028 | 41.5001 | 43.0841   | 42.4534 |
+| 2.3967        | 5.0   | 19475 | 2.8935          | 46.1029 | 33.4495 | 41.0557 | 42.7096   | 41.9169 |
+| 2.3161        | 6.0   | 23370 | 2.9255          | 46.0193 | 33.2904 | 40.9323 | 42.575    | 42.5379 |
+| 2.2348        | 7.0   | 27265 | 2.9692          | 46.4242 | 33.718  | 41.4037 | 43.0504   | 41.7957 |
+| 2.1716        | 8.0   | 31160 | 3.0044          | 46.1669 | 33.3276 | 40.9307 | 42.7015   | 42.8942 |
+| 2.1179        | 9.0   | 35055 | 3.0372          | 46.0666 | 33.2483 | 40.9372 | 42.6837   | 42.7636 |
+| 2.0753        | 10.0  | 38950 | 3.0627          | 46.1444 | 33.2551 | 40.9514 | 42.7096   | 42.9266 |
+
+
+### Framework versions
+
+- Transformers 4.11.3
+- Pytorch 1.8.2+cu111
+- Datasets 1.14.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "facebook/mbart-large-50",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "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,
+  "forced_bos_token_id": 250023,
+  "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
+  },
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "tokenizer_class": "MBart50Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "use_cache": true,
+  "vocab_size": 250054
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae44ca016a350017780d65061173081b121bae883bec55fd702a86edb70d18d6
+size 2444722195

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"src_lang": null, "tgt_lang": null, "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": "<s>", "model_max_length": 1024, "name_or_path": "facebook/mbart-large-50", "special_tokens_map_file": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large/special_tokens_map.json", "additional_special_tokens": ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"], "sp_model_kwargs": {}, "tokenizer_class": "MBart50Tokenizer"}