Training in progress, epoch 0

README.md

@@ -0,0 +1,80 @@
+---
+license: mit
+base_model: kazandaev/m2m100_418M
+tags:
+- translation
+- generated_from_trainer
+datasets:
+- wmt16
+metrics:
+- bleu
+model-index:
+- name: m2m100_418M
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: wmt16
+      type: wmt16
+      config: ru-en
+      split: validation
+      args: ru-en
+    metrics:
+    - name: Bleu
+      type: bleu
+      value: 32.0585
+---
+
+<!-- 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. -->
+
+# m2m100_418M
+
+This model is a fine-tuned version of [kazandaev/m2m100_418M](https://huggingface.co/kazandaev/m2m100_418M) on the wmt16 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8954
+- Bleu: 32.0585
+- Gen Len: 36.1643
+
+## 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: 4
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 10
+- total_train_batch_size: 40
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
+| 0.8087        | 1.0   | 47790 | 0.9542          | 30.786  | 36.1469 |
+| 0.7266        | 2.0   | 95580 | 0.8954          | 32.0585 | 36.1643 |
+
+
+### Framework versions
+
+- Transformers 4.33.2
+- Pytorch 2.2.0.dev20230920+cu121
+- Datasets 2.14.4
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "facebook/m2m100_418M",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "M2M100ForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.05,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.05,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "m2m_100",
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 128112
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "max_length": 200,
+  "num_beams": 5,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f75ed069ee626764b867544acc73930f54a88160e0fb5c081319f4b3acf670be
+size 1935796158

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f7c76ed2a5e0822be39f0a4f95a55eb19c78f4593ce609e2edbc2aea4d380a
+size 2423393

special_tokens_map.json

@@ -0,0 +1,109 @@
+{
+  "additional_special_tokens": [
+    "__af__",
+    "__am__",
+    "__ar__",
+    "__ast__",
+    "__az__",
+    "__ba__",
+    "__be__",
+    "__bg__",
+    "__bn__",
+    "__br__",
+    "__bs__",
+    "__ca__",
+    "__ceb__",
+    "__cs__",
+    "__cy__",
+    "__da__",
+    "__de__",
+    "__el__",
+    "__en__",
+    "__es__",
+    "__et__",
+    "__fa__",
+    "__ff__",
+    "__fi__",
+    "__fr__",
+    "__fy__",
+    "__ga__",
+    "__gd__",
+    "__gl__",
+    "__gu__",
+    "__ha__",
+    "__he__",
+    "__hi__",
+    "__hr__",
+    "__ht__",
+    "__hu__",
+    "__hy__",
+    "__id__",
+    "__ig__",
+    "__ilo__",
+    "__is__",
+    "__it__",
+    "__ja__",
+    "__jv__",
+    "__ka__",
+    "__kk__",
+    "__km__",
+    "__kn__",
+    "__ko__",
+    "__lb__",
+    "__lg__",
+    "__ln__",
+    "__lo__",
+    "__lt__",
+    "__lv__",
+    "__mg__",
+    "__mk__",
+    "__ml__",
+    "__mn__",
+    "__mr__",
+    "__ms__",
+    "__my__",
+    "__ne__",
+    "__nl__",
+    "__no__",
+    "__ns__",
+    "__oc__",
+    "__or__",
+    "__pa__",
+    "__pl__",
+    "__ps__",
+    "__pt__",
+    "__ro__",
+    "__ru__",
+    "__sd__",
+    "__si__",
+    "__sk__",
+    "__sl__",
+    "__so__",
+    "__sq__",
+    "__sr__",
+    "__ss__",
+    "__su__",
+    "__sv__",
+    "__sw__",
+    "__ta__",
+    "__th__",
+    "__tl__",
+    "__tn__",
+    "__tr__",
+    "__uk__",
+    "__ur__",
+    "__uz__",
+    "__vi__",
+    "__wo__",
+    "__xh__",
+    "__yi__",
+    "__yo__",
+    "__zh__",
+    "__zu__"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,118 @@
+{
+  "additional_special_tokens": [
+    "__af__",
+    "__am__",
+    "__ar__",
+    "__ast__",
+    "__az__",
+    "__ba__",
+    "__be__",
+    "__bg__",
+    "__bn__",
+    "__br__",
+    "__bs__",
+    "__ca__",
+    "__ceb__",
+    "__cs__",
+    "__cy__",
+    "__da__",
+    "__de__",
+    "__el__",
+    "__en__",
+    "__es__",
+    "__et__",
+    "__fa__",
+    "__ff__",
+    "__fi__",
+    "__fr__",
+    "__fy__",
+    "__ga__",
+    "__gd__",
+    "__gl__",
+    "__gu__",
+    "__ha__",
+    "__he__",
+    "__hi__",
+    "__hr__",
+    "__ht__",
+    "__hu__",
+    "__hy__",
+    "__id__",
+    "__ig__",
+    "__ilo__",
+    "__is__",
+    "__it__",
+    "__ja__",
+    "__jv__",
+    "__ka__",
+    "__kk__",
+    "__km__",
+    "__kn__",
+    "__ko__",
+    "__lb__",
+    "__lg__",
+    "__ln__",
+    "__lo__",
+    "__lt__",
+    "__lv__",
+    "__mg__",
+    "__mk__",
+    "__ml__",
+    "__mn__",
+    "__mr__",
+    "__ms__",
+    "__my__",
+    "__ne__",
+    "__nl__",
+    "__no__",
+    "__ns__",
+    "__oc__",
+    "__or__",
+    "__pa__",
+    "__pl__",
+    "__ps__",
+    "__pt__",
+    "__ro__",
+    "__ru__",
+    "__sd__",
+    "__si__",
+    "__sk__",
+    "__sl__",
+    "__so__",
+    "__sq__",
+    "__sr__",
+    "__ss__",
+    "__su__",
+    "__sv__",
+    "__sw__",
+    "__ta__",
+    "__th__",
+    "__tl__",
+    "__tn__",
+    "__tr__",
+    "__uk__",
+    "__ur__",
+    "__uz__",
+    "__vi__",
+    "__wo__",
+    "__xh__",
+    "__yi__",
+    "__yo__",
+    "__zh__",
+    "__zu__"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "language_codes": "m2m100",
+  "model_max_length": 1024,
+  "num_madeup_words": 8,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "src_lang": null,
+  "tgt_lang": null,
+  "tokenizer_class": "M2M100Tokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c07271e7f6bc6321b7a9f321fa268756d56a74748a5d3dc18478e1cb727285
+size 4728