Training in progress, epoch 1

README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-en-bcl
+tags:
+- translation
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: sorsolingo-mt-en-bsl-test
+  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. -->
+
+# sorsolingo-mt-en-bsl-test
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-bcl](https://huggingface.co/Helsinki-NLP/opus-mt-en-bcl) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.6478
+- Bleu: 4.5150
+
+## 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: 32
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-bcl",
+  "_num_labels": 3,
+  "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": [
+    [
+      58454
+    ]
+  ],
+  "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": 58454,
+  "decoder_vocab_size": 58455,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "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": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 58454,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 58455
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      58454
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 58454,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 58454,
+  "renormalize_logits": true,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7850b39d10b4c93eb5da02fbc0f3012c974bc5a858a2c11f43e63486d5aee3e2
+size 296532700

runs/Dec10_05-40-33_de4dc35373a0/events.out.tfevents.1702186861.de4dc35373a0.3326.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5629ddb8942eb077e075a20aded089e4ad52dacb43cd7955f46dbf9f2b804053
+size 5747

runs/Dec10_05-40-33_de4dc35373a0/events.out.tfevents.1702186957.de4dc35373a0.3326.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02cabc1f3535e9d7e0f675be861688b3acc7f37be4b63c5c810e7e57ce1b2195
+size 407

runs/Dec10_05-48-09_de4dc35373a0/events.out.tfevents.1702187306.de4dc35373a0.3326.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1057b52d3fb344d3f2d5ae243bce60075c7710fd7f7a7e6c69a3304b01dbf3
+size 5747

runs/Dec10_05-48-09_de4dc35373a0/events.out.tfevents.1702187391.de4dc35373a0.3326.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62284f79d8673b5186b86e9ad69dc92a2c183c20a89870f390da0c178726a4f2
+size 407

runs/Dec10_06-20-53_de4dc35373a0/events.out.tfevents.1702189287.de4dc35373a0.13848.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:120e46bc67a37fbe23b06b491f635961f23290bfb05e279730f460965b3fc665
+size 4438

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58454": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "return_tensors": "pt",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "bcl",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceb39c174b34ad6327ea3a05abae64589884cede7c3673a154b7bd0907041dbf
+size 4792