ihebaker10/spark-name-ru-to-en

README.md

@@ -1,63 +1,57 @@
----
-license: cc-by-4.0
-base_model: Helsinki-NLP/opus-mt-ru-en
-tags:
-- generated_from_trainer
-metrics:
-- bleu
-model-index:
-- name: spark-name-ru-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-ru-to-en
-
-This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ru-en](https://huggingface.co/Helsinki-NLP/opus-mt-ru-en) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.4190
-- Bleu: 45.2655
-- Gen Len: 6.5419
-
-## 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: 3
-
-### Training results
-
-| Training Loss | Epoch | Step  | Validation Loss | Bleu    | Gen Len |
-|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|
-| 1.6862        | 1.0   | 4050  | 1.5225          | 41.8755 | 6.5328  |
-| 1.421         | 2.0   | 8100  | 1.4412          | 44.4841 | 6.5311  |
-| 1.2786        | 3.0   | 12150 | 1.4190          | 45.2655 | 6.5419  |
-
-
-### Framework versions
-
-- Transformers 4.39.1
-- Pytorch 2.2.1+cpu
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: spark-name-ru-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-ru-to-en
+
+This model was trained from scratch on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.9398
+
+## 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: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 1    | 2.5449          |
+| No log        | 2.0   | 2    | 2.1204          |
+| No log        | 3.0   | 3    | 1.9398          |
+
+
+### Framework versions
+
+- Transformers 4.41.1
+- Pytorch 2.0.1+cpu
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -1,61 +1,61 @@
-{
-  "_name_or_path": "Helsinki-NLP/opus-mt-ru-en",
-  "_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": [
-    [
-      62517
-    ]
-  ],
-  "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": 62517,
-  "decoder_vocab_size": 62518,
-  "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": 6,
-  "num_hidden_layers": 6,
-  "pad_token_id": 62517,
-  "scale_embedding": true,
-  "share_encoder_decoder_embeddings": true,
-  "static_position_embeddings": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.39.1",
-  "use_cache": true,
-  "vocab_size": 62518
-}
+{
+  "_name_or_path": "ihebaker10/spark-name-ru-to-en",
+  "_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": [
+    [
+      62517
+    ]
+  ],
+  "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": 62517,
+  "decoder_vocab_size": 62518,
+  "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": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 62517,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "vocab_size": 62518
+}

generation_config.json

@@ -1,16 +1,16 @@
-{
-  "bad_words_ids": [
-    [
-      62517
-    ]
-  ],
-  "bos_token_id": 0,
-  "decoder_start_token_id": 62517,
-  "eos_token_id": 0,
-  "forced_eos_token_id": 0,
-  "max_length": 512,
-  "num_beams": 6,
-  "pad_token_id": 62517,
-  "renormalize_logits": true,
-  "transformers_version": "4.39.1"
-}
+{
+  "bad_words_ids": [
+    [
+      62517
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 62517,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 62517,
+  "renormalize_logits": true,
+  "transformers_version": "4.41.1"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ccdb8aad38ccbf67a8f29a8b7849180af45a7243c0cdfe45e63747593de18d5
+oid sha256:a86f218917508ffca14a44db73366c21c5d2e595458a0cf408e82cc8cf1b8a40
 size 304869976

special_tokens_map.json

@@ -1,5 +1,23 @@
-{
-  "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
-}
+{
+  "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

@@ -1,38 +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
-    },
-    "62517": {
-      "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": "ru",
-  "sp_model_kwargs": {},
-  "target_lang": "en",
-  "tokenizer_class": "MarianTokenizer",
-  "unk_token": "<unk>"
-}
+{
+  "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
+    },
+    "62517": {
+      "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": "ru",
+  "sp_model_kwargs": {},
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d138a35a3644527e53f4e2629640addca0938f472f64832768aa6adf271d588
-size 5048
+oid sha256:d872406ff40526bf9336b04a5cce76bd164db7c05d67b89e572ecc99e7c7105e
+size 4795