Training in progress epoch 0

.gitattributes

@@ -32,3 +32,5 @@ 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 +1,53 @@
+---
+license: apache-2.0
+tags:
+- generated_from_keras_callback
+model-index:
+- name: Prgrg/ja-en-JESC-v5.0-wth-lr-decay
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information Keras had access to. You should
+probably proofread and complete it, then remove this comment. -->
+
+# Prgrg/ja-en-JESC-v5.0-wth-lr-decay
+
+This model is a fine-tuned version of [Prgrg/ja-en-JESC-v4.0-wth-lr-decay](https://huggingface.co/Prgrg/ja-en-JESC-v4.0-wth-lr-decay) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Train Loss: 2.1973
+- Validation Loss: 2.5649
+- Epoch: 0
+
+## 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:
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 150000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.001}
+- training_precision: mixed_float16
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 2.1973     | 2.5649          | 0     |
+
+
+### Framework versions
+
+- Transformers 4.26.1
+- TensorFlow 2.11.0
+- Datasets 2.10.1
+- Tokenizers 0.13.2

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "Prgrg/ja-en-JESC-v4.0-wth-lr-decay",
+  "_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": [
+    [
+      46275
+    ]
+  ],
+  "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": 46275,
+  "decoder_vocab_size": 46276,
+  "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": 46275,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 46276
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      46275
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 46275,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 46275,
+  "transformers_version": "4.26.1"
+}

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d5ec21daca7dccb7a9df371b699def40ddd9d0c24cef855e44e31a39b96af55
+size 1021944

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 sha256:375cbed8885a6d369e0493acfc69a066010a86f98f9bac02430cbeb1726934a6
+size 508602

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d0a211ed87cdb5e5f5a3f66f15593cb7fde1dfc5f7fd8d012e57041589d52e6
+size 273896960

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "access_token": "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",
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "name_or_path": "Prgrg/ja-en-JESC-v4.0-wth-lr-decay",
+  "pad_token": "<pad>",
+  "private": true,
+  "return_tensors": "pt",
+  "separate_vocabs": false,
+  "source_lang": "jap",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}