add model

README.md

@@ -0,0 +1,80 @@
+---
+license: apache-2.0
+model_index:
+- name: HelsinkiNLP-FineTuned-Legal-es-zh
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+---
+
+<!-- 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. -->
+
+# HelsinkiNLP-FineTuned-Legal-es-zh
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-tatoeba-es-zh](https://huggingface.co/Helsinki-NLP/opus-tatoeba-es-zh) on an unkown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1078
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 2000
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.9584        | 0.36  | 400  | 2.6800          |
+| 2.6402        | 0.71  | 800  | 2.5017          |
+| 2.5038        | 1.07  | 1200 | 2.3907          |
+| 2.3279        | 1.43  | 1600 | 2.2999          |
+| 2.2258        | 1.78  | 2000 | 2.2343          |
+| 2.1061        | 2.14  | 2400 | 2.1961          |
+| 1.9279        | 2.5   | 2800 | 2.1569          |
+| 1.9059        | 2.85  | 3200 | 2.1245          |
+| 1.7491        | 3.21  | 3600 | 2.1227          |
+| 1.6301        | 3.57  | 4000 | 2.1169          |
+| 1.6871        | 3.92  | 4400 | 2.0979          |
+| 1.5203        | 4.28  | 4800 | 2.1074          |
+| 1.4646        | 4.63  | 5200 | 2.1024          |
+| 1.4739        | 4.99  | 5600 | 2.0905          |
+| 1.338         | 5.35  | 6000 | 2.0946          |
+| 1.3152        | 5.7   | 6400 | 2.0974          |
+| 1.306         | 6.06  | 6800 | 2.0985          |
+| 1.1991        | 6.42  | 7200 | 2.0962          |
+| 1.2113        | 6.77  | 7600 | 2.1092          |
+| 1.1983        | 7.13  | 8000 | 2.1060          |
+| 1.1238        | 7.49  | 8400 | 2.1102          |
+| 1.1417        | 7.84  | 8800 | 2.1078          |
+
+
+### Framework versions
+
+- Transformers 4.7.0
+- Pytorch 1.8.1+cu101
+- Datasets 1.8.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-tatoeba-es-zh",
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      65000
+    ]
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 65000,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 0,
+  "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": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 65000,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.7.0",
+  "use_cache": true,
+  "vocab_size": 65001
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f8be54f504ebe69bc7d077e6ce5d47220f6f36b51618a2f61920253c031fd2d
+size 310026845

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "spa", "target_lang": "zho", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "Helsinki-NLP/opus-tatoeba-es-zh", "use_fast": false}