Upload folder using huggingface_hub

README.md

@@ -0,0 +1,61 @@
+---
+language:
+- en
+- ar
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-en-ar
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: opus_2
+  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. -->
+
+# opus_2
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ar](https://huggingface.co/Helsinki-NLP/opus-mt-en-ar) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0955
+- Bleu: 88.6881
+- Gen Len: 9.3881
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_bleu": 88.6881,
+    "eval_gen_len": 9.3881,
+    "eval_loss": 0.09552541375160217,
+    "eval_runtime": 5.5974,
+    "eval_samples": 67,
+    "eval_samples_per_second": 11.97,
+    "eval_steps_per_second": 3.037,
+    "train_loss": 0.2668434212741242,
+    "train_runtime": 32.5365,
+    "train_samples": 581,
+    "train_samples_per_second": 53.571,
+    "train_steps_per_second": 13.462
+}

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-ar",
+  "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": [
+    [
+      62801
+    ]
+  ],
+  "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": 62801,
+  "decoder_vocab_size": 62802,
+  "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": 62802,
+  "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": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 62801,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 62802
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_bleu": 88.6881,
+    "eval_gen_len": 9.3881,
+    "eval_loss": 0.09552541375160217,
+    "eval_runtime": 5.5974,
+    "eval_samples": 67,
+    "eval_samples_per_second": 11.97,
+    "eval_steps_per_second": 3.037
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      62801
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 62801,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 62801,
+  "renormalize_logits": true,
+  "transformers_version": "4.39.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd780f0254cd9a15a40d79fa580c080150823c7ed7784f08d889f6baf94f06d
+size 305452744

runs/Mar20_11-45-23_183c4c161347/events.out.tfevents.1710935136.183c4c161347.2177.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e13e32364ee8f68aabc7e2a72d205422b6b24111be5b345fecb7f54f22658b9
+size 5820

runs/Mar20_11-45-23_183c4c161347/events.out.tfevents.1710935175.183c4c161347.2177.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ac111cc55b917f567ebdda11c387068c3568884a691e25be5d421aa776d8886
+size 458

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

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
+    },
+    "62801": {
+      "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": "eng",
+  "sp_model_kwargs": {},
+  "target_lang": "ara",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.2668434212741242,
+    "train_runtime": 32.5365,
+    "train_samples": 581,
+    "train_samples_per_second": 53.571,
+    "train_steps_per_second": 13.462
+}

trainer_state.json

@@ -0,0 +1,30 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 438,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 438,
+      "total_flos": 8514051047424.0,
+      "train_loss": 0.2668434212741242,
+      "train_runtime": 32.5365,
+      "train_samples_per_second": 53.571,
+      "train_steps_per_second": 13.462
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 438,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 8514051047424.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae7b00033336a58b397405b448d55a837f7e24a76bbf015dc1fe5431c579f19
+size 5048