End of training

README.md

@@ -0,0 +1,64 @@
+---
+base_model: ihebaker10/spark-name-ka-to-en
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: spark-name-zh-to-en
+  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. -->
+
+# spark-name-zh-to-en
+
+This model is a fine-tuned version of [ihebaker10/spark-name-ka-to-en](https://huggingface.co/ihebaker10/spark-name-ka-to-en) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.3571
+- Bleu: 0.4007
+- Gen Len: 13.1744
+
+## 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: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
+| 4.5771        | 1.0   | 1600 | 4.5729          | 0.6348 | 48.9281 |
+| 4.2727        | 2.0   | 3200 | 4.4437          | 0.3449 | 13.7372 |
+| 4.1169        | 3.0   | 4800 | 4.3856          | 0.3302 | 14.0606 |
+| 3.9978        | 4.0   | 6400 | 4.3584          | 0.3945 | 13.1856 |
+| 3.9164        | 5.0   | 8000 | 4.3571          | 0.4007 | 13.1744 |
+
+
+### Framework versions
+
+- Transformers 4.41.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "ihebaker10/spark-name-ka-to-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": [
+    [
+      23171
+    ]
+  ],
+  "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": 23171,
+  "decoder_vocab_size": 23172,
+  "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": 23172,
+  "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": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 23171,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "use_cache": true,
+  "vocab_size": 23172
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      23171
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 23171,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 23171,
+  "renormalize_logits": true,
+  "transformers_version": "4.41.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:229a97572011f2df02aa8cd2118e94f6ebc7d467c96cfa30acd63a693e207614
+size 224131976

runs/May25_18-16-51_dbb84e2d2d0d/events.out.tfevents.1716661021.dbb84e2d2d0d.667.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdbd08e72fe040e33b181c668c2e5953c81e207fdfa1053095ccd1051beca383
+size 11337

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "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
+    },
+    "23171": {
+      "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>",
+  "separate_vocabs": false,
+  "source_lang": "kat",
+  "sp_model_kwargs": {},
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab46e00e6e012a365a7bf5fa0dee0de610ddde556f88401ae1ffb1b770fd97af
+size 5240