Training in progress, step 500

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,72 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-cs-en
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: opus-mt-cs-en-Prefix-Finetuned
+  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. -->
+
+# opus-mt-cs-en-Prefix-Finetuned
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-cs-en](https://huggingface.co/Helsinki-NLP/opus-mt-cs-en) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7602
+- Model Preparation Time: 0.002
+- Bleu: 61.8879
+
+## 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: 220
+- eval_batch_size: 700
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Model Preparation Time | Bleu    |
+|:-------------:|:-----:|:-----:|:---------------:|:----------------------:|:-------:|
+| 0.8318        | 1.0   | 1566  | 0.7638          | 0.002                  | 60.8554 |
+| 0.7529        | 2.0   | 3132  | 0.7509          | 0.002                  | 62.3726 |
+| 0.7007        | 3.0   | 4698  | 0.7462          | 0.002                  | 61.6776 |
+| 0.656         | 4.0   | 6264  | 0.7484          | 0.002                  | 62.3136 |
+| 0.6315        | 5.0   | 7830  | 0.7498          | 0.002                  | 62.4913 |
+| 0.6032        | 6.0   | 9396  | 0.7528          | 0.002                  | 62.2276 |
+| 0.5806        | 7.0   | 10962 | 0.7544          | 0.002                  | 61.8519 |
+| 0.567         | 8.0   | 12528 | 0.7583          | 0.002                  | 61.9396 |
+| 0.5552        | 9.0   | 14094 | 0.7592          | 0.002                  | 61.9722 |
+| 0.5437        | 10.0  | 15660 | 0.7602          | 0.002                  | 61.8879 |
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.7.0+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,55 @@
+{
+  "_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,
+  "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": 62508,
+  "decoder_vocab_size": 62509,
+  "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": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 62508,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 62509
+}

generation_config.json

@@ -0,0 +1,18 @@
+{
+  "bad_words_ids": [
+    [
+      62508
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 62508,
+  "early_stopping": true,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "max_new_tokens": 60,
+  "num_beams": 4,
+  "pad_token_id": 62508,
+  "renormalize_logits": true,
+  "transformers_version": "4.51.3"
+}

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2e6d98cdd54d80ad404ad493a7755e723c8d619e998840eba682e3e3fe25e33
+size 829548

special_tokens_map.json

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

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb772d24cbd559a9e0c5dfd4726e1201b07497af59189f107dd812bff1909e7
+size 788721

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
+    },
+    "62508": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "cs",
+  "sp_model_kwargs": {},
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bb9c4cf5ed9a82ea8e775443e27396fbfbfb3434a62f2a1a8052e616464b866
+size 8209