Upload 14 files

.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

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<ar>": 64173,
+  "<he>": 64172
+}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "test_bleu": 37.80677887564074,
+    "test_char_accuracy": 35.72292800967937,
+    "test_loss": 0.5354108214378357,
+    "test_runtime": 70.7763,
+    "test_samples_per_second": 7.63,
+    "test_steps_per_second": 0.48,
+    "total_flos": 308856477450240.0,
+    "train_loss": 0.5946165708847988,
+    "train_runtime": 276.8646,
+    "train_samples_per_second": 46.799,
+    "train_steps_per_second": 2.926
+}

config.json

@@ -0,0 +1,55 @@
+{
+  "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": 64171,
+  "decoder_vocab_size": 64174,
+  "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": 64172,
+  "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": 64171,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 64174
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      64171
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 64171,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 64171,
+  "renormalize_logits": true,
+  "transformers_version": "4.52.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a709c347e78bddfce554b6ac00cb6dffa0bb8d410c690b405088c4b100af42b
+size 308268088

model_info.json

@@ -0,0 +1,28 @@
+{
+  "model_name": "./hebrew_aramaic_model_early_stopping",
+  "direction": "he2ar",
+  "vocabulary_size": 64174,
+  "model_parameters": 77519872,
+  "training_config": {
+    "dataset_path": "./hebrew_aramaic_dataset",
+    "output_dir": "./hebrew_aramaic_model_final",
+    "model_name": "./hebrew_aramaic_model_early_stopping",
+    "direction": "he2ar",
+    "batch_size": 16,
+    "learning_rate": 1e-05,
+    "num_epochs": 3,
+    "max_input_length": 512,
+    "max_target_length": 512,
+    "eval_steps": 500,
+    "save_steps": 500,
+    "warmup_steps": 500,
+    "gradient_accumulation_steps": 1,
+    "early_stopping_patience": 5,
+    "early_stopping_threshold": 0.1,
+    "seed": 42,
+    "use_fp16": true,
+    "use_wandb": false,
+    "use_language_prefix": true,
+    "skip_evaluation": false
+  }
+}

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a99ea3602b29fbf901ade8b93a45efa3d7c64eab8fc5fa812383efa327a87d
+size 706917

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<he>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<ar>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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
+  }
+}

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6dce5fa58fcd7dde9e81e279b8c075bf42ee558278f73d6fb48e342029d7f19
+size 791194

test_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "test_bleu": 37.80677887564074,
+    "test_char_accuracy": 35.72292800967937,
+    "test_loss": 0.5354108214378357,
+    "test_runtime": 70.7763,
+    "test_samples_per_second": 7.63,
+    "test_steps_per_second": 0.48
+}

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "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
+    },
+    "64171": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64172": {
+      "content": "<he>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64173": {
+      "content": "<ar>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<he>",
+    "<ar>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "mul",
+  "sp_model_kwargs": {},
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 308856477450240.0,
+    "train_loss": 0.5946165708847988,
+    "train_runtime": 276.8646,
+    "train_samples_per_second": 46.799,
+    "train_steps_per_second": 2.926
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ecf77898c29da24f2c8a1294e395931247d07572e75464f94c5570d03ca875
+size 5841