add model

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

README.md

@@ -0,0 +1,68 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model_index:
+- name: opus-mt-zh-en-ep1-renri-zh-to-en
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    metric:
+      name: Bleu
+      type: bleu
+      value: 18.2579
+---
+
+<!-- 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. -->
+
+# opus-mt-zh-en-ep1-renri-zh-to-en
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-zh-en](https://huggingface.co/Helsinki-NLP/opus-mt-zh-en) on an unkown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2192
+- Bleu: 18.2579
+- Gen Len: 28.4817
+
+## 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: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
+| 2.2194        | 1.0   | 59472 | 2.2192          | 18.2579 | 28.4817 |
+
+
+### Framework versions
+
+- Transformers 4.9.2
+- Pytorch 1.9.0+cu102
+- Datasets 1.11.0
+- Tokenizers 0.10.3

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-zh-en",
+  "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,
+  "classif_dropout": 0.0,
+  "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,
+  "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": 65001,
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "use_cache": true,
+  "vocab_size": 65001
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:269d5b8de62299bb739714bc5baf9b0d5561440489ffb64271b5a6af0e06d0f6
+size 310020485

runs/Aug22_02-46-14_7e49732c97b7/1629600384.3153653/events.out.tfevents.1629600384.7e49732c97b7.180.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f7e365f3352824a8f307e4fbed29cead31dc0d5fdcfec4789cd1fa1b8a20bc3
+size 4334

runs/Aug22_02-46-14_7e49732c97b7/events.out.tfevents.1629600384.7e49732c97b7.180.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cd0335d8a71caa9eab0516d0d321806d1c836afaa71ada43339c475ada6573c
+size 23263

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "zho", "target_lang": "eng", "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-mt-zh-en", "tokenizer_class": "MarianTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda08e246ecd52fed150b12326f832a962a42a7a8db7535c4020401c5976b7b2
+size 2735