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 +1,87 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-en-fr
+tags:
+- generated_from_trainer
+datasets:
+- kde4
+metrics:
+- bleu
+model-index:
+- name: lab1_random
+  results:
+  - task:
+      name: Sequence-to-sequence Language Modeling
+      type: text2text-generation
+    dataset:
+      name: kde4
+      type: kde4
+      config: en-fr
+      split: train
+      args: en-fr
+    metrics:
+    - name: Bleu
+      type: bleu
+      value: 7.115012632579186
+---
+
+<!-- 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. -->
+
+# lab1_random
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-fr](https://huggingface.co/Helsinki-NLP/opus-mt-en-fr) on the kde4 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.2494
+- Model Preparation Time: 0.017
+- Bleu: 7.1150
+
+## 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: 16
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- training_steps: 5000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Model Preparation Time | Bleu   |
+|:-------------:|:------:|:----:|:---------------:|:----------------------:|:------:|
+| 6.8083        | 0.0476 | 500  | 6.7542          | 0.017                  | 4.6732 |
+| 6.1556        | 0.0952 | 1000 | 6.2083          | 0.017                  | 4.3588 |
+| 5.9295        | 0.1427 | 1500 | 5.9114          | 0.017                  | 4.5718 |
+| 5.7926        | 0.1903 | 2000 | 5.7025          | 0.017                  | 5.9611 |
+| 5.4625        | 0.2379 | 2500 | 5.5511          | 0.017                  | 6.0040 |
+| 5.4432        | 0.2855 | 3000 | 5.4391          | 0.017                  | 6.8646 |
+| 5.2127        | 0.3330 | 3500 | 5.3516          | 0.017                  | 6.6020 |
+| 5.5486        | 0.3806 | 4000 | 5.2969          | 0.017                  | 7.3200 |
+| 5.3347        | 0.4282 | 4500 | 5.2653          | 0.017                  | 7.2014 |
+| 5.4594        | 0.4758 | 5000 | 5.2494          | 0.017                  | 7.1159 |
+
+
+### Framework versions
+
+- Transformers 4.57.6
+- Pytorch 2.10.0+cu128
+- Datasets 3.6.0
+- Tokenizers 0.22.2

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,
+  "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": 59513,
+  "decoder_vocab_size": 59514,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "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": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 59513,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "vocab_size": 59514
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      59513
+    ]
+  ],
+  "decoder_start_token_id": 59513,
+  "eos_token_id": [
+    0
+  ],
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 59513,
+  "transformers_version": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19b0420a91b1a54a1d19a6fa9b5d543bdf652e37370cabe8314a0b77f2b359c7
+size 298705768

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:173e9f493a668fe396d599e28d414a201193094e6ffd7a4678e5aab0f6d3d838
+size 778395

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 sha256:78d0e717c77053f1c4b856d8661d9cb87c64f083a35418c087b9146300e4f585
+size 802397

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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
+    },
+    "59513": {
+      "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>",
+  "return_tensors": "pt",
+  "separate_vocabs": false,
+  "source_lang": "en",
+  "sp_model_kwargs": {},
+  "target_lang": "fr",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:943f8341b32358e22ece446d30bc134f65b276c96939a373e81a7c1589d9d1be
+size 6033