Upload model MarianMT - ver2

MarianMT_ver2/config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-vi",
+  "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": 53684,
+  "decoder_vocab_size": 53685,
+  "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": 53685,
+  "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": 53684,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 53685
+}

MarianMT_ver2/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      53684
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 53684,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 53684,
+  "renormalize_logits": true,
+  "transformers_version": "4.46.3"
+}

MarianMT_ver2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291154fc53d21a6cbeea8c980e96865c62afae46cbc229879633adcb04f26eb5
+size 286744660

MarianMT_ver2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99dabfc8cd847118ab2ddf66fefd413e257c8cfea92aed2230ac824b6fc9acb3
+size 573213242

MarianMT_ver2/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfaf3c022b7706e94413c66dcdde4b662088f7ea87a80fdcd46a72b2df1497ae
+size 14244

MarianMT_ver2/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ae98910dfd524e452579bf0c454e4ae7bd438e20cbd8e8e9e51492395837d22
+size 1064

MarianMT_ver2/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 1.4305617809295654,
+  "best_model_checkpoint": "./results/checkpoint-2327",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2327,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21486892995272883,
+      "grad_norm": 1.8023662567138672,
+      "learning_rate": 4.641885116745452e-05,
+      "loss": 1.8148,
+      "step": 500
+    },
+    {
+      "epoch": 0.42973785990545765,
+      "grad_norm": 1.5604274272918701,
+      "learning_rate": 4.283770233490904e-05,
+      "loss": 1.7135,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6446067898581865,
+      "grad_norm": 1.7446964979171753,
+      "learning_rate": 3.9256553502363556e-05,
+      "loss": 1.6655,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8594757198109153,
+      "grad_norm": 1.6676881313323975,
+      "learning_rate": 3.567540466981808e-05,
+      "loss": 1.6373,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.4305617809295654,
+      "eval_runtime": 13.1412,
+      "eval_samples_per_second": 356.055,
+      "eval_steps_per_second": 2.816,
+      "step": 2327
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6981,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5047449588596736.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

MarianMT_ver2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1574cd57c78cc3b088efed04e79d77d3673c40010378e0423a3caf6f8093355
+size 5432