Upload MarianMT_ver4

MarianMT_ver4/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_ver4/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_ver4/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fefc77119b5af4878b82f01cefcfcf0ef53cfd06f2c7abf2be6546defb5650c
+size 286744660

MarianMT_ver4/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89731be33df99ddcb040fd5b0e243c273f04a7bcc06d7eab7d5990252174412a
+size 573213242

MarianMT_ver4/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7970bc3f81e9490881ca3e588eda6b2630fed97c82c842ee6713cb16f2fdcbdb
+size 14244

MarianMT_ver4/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e335b626b7cf621a6dc4f4ca13974d48f08202ed9f6674b31190583841efa98
+size 1064

MarianMT_ver4/trainer_state.json

@@ -0,0 +1,249 @@
+{
+  "best_metric": 1.4858289957046509,
+  "best_model_checkpoint": "./results/checkpoint-6250",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 12500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.800455331802368,
+      "learning_rate": 4.92e-05,
+      "loss": 1.8865,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.2938010692596436,
+      "learning_rate": 4.8400000000000004e-05,
+      "loss": 1.8249,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.251399517059326,
+      "learning_rate": 4.76e-05,
+      "loss": 1.7717,
+      "step": 1500
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.223798990249634,
+      "learning_rate": 4.6800000000000006e-05,
+      "loss": 1.7477,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.1936862468719482,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 1.7458,
+      "step": 2500
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.4300343990325928,
+      "learning_rate": 4.52e-05,
+      "loss": 1.7226,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.5059889554977417,
+      "eval_runtime": 13.9307,
+      "eval_samples_per_second": 335.876,
+      "eval_steps_per_second": 10.552,
+      "step": 3125
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 3.277369737625122,
+      "learning_rate": 4.44e-05,
+      "loss": 1.5592,
+      "step": 3500
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 2.9364540576934814,
+      "learning_rate": 4.36e-05,
+      "loss": 1.5109,
+      "step": 4000
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 2.9026784896850586,
+      "learning_rate": 4.2800000000000004e-05,
+      "loss": 1.5117,
+      "step": 4500
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 3.0175607204437256,
+      "learning_rate": 4.2e-05,
+      "loss": 1.5143,
+      "step": 5000
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 3.0337491035461426,
+      "learning_rate": 4.12e-05,
+      "loss": 1.5219,
+      "step": 5500
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 2.8166635036468506,
+      "learning_rate": 4.0400000000000006e-05,
+      "loss": 1.5017,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.4858289957046509,
+      "eval_runtime": 14.2343,
+      "eval_samples_per_second": 328.713,
+      "eval_steps_per_second": 10.327,
+      "step": 6250
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 2.935457706451416,
+      "learning_rate": 3.960000000000001e-05,
+      "loss": 1.4048,
+      "step": 6500
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 3.244539499282837,
+      "learning_rate": 3.88e-05,
+      "loss": 1.3372,
+      "step": 7000
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 3.7380311489105225,
+      "learning_rate": 3.8e-05,
+      "loss": 1.3405,
+      "step": 7500
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 3.5527069568634033,
+      "learning_rate": 3.72e-05,
+      "loss": 1.3517,
+      "step": 8000
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 2.839742422103882,
+      "learning_rate": 3.6400000000000004e-05,
+      "loss": 1.3515,
+      "step": 8500
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 3.501607894897461,
+      "learning_rate": 3.56e-05,
+      "loss": 1.3555,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.4895309209823608,
+      "eval_runtime": 13.9356,
+      "eval_samples_per_second": 335.759,
+      "eval_steps_per_second": 10.549,
+      "step": 9375
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 2.6918106079101562,
+      "learning_rate": 3.48e-05,
+      "loss": 1.3244,
+      "step": 9500
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 3.5866470336914062,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 1.2057,
+      "step": 10000
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 3.242699384689331,
+      "learning_rate": 3.32e-05,
+      "loss": 1.21,
+      "step": 10500
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 2.8729286193847656,
+      "learning_rate": 3.24e-05,
+      "loss": 1.2239,
+      "step": 11000
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 3.33542799949646,
+      "learning_rate": 3.16e-05,
+      "loss": 1.2178,
+      "step": 11500
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 3.3703885078430176,
+      "learning_rate": 3.08e-05,
+      "loss": 1.2281,
+      "step": 12000
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.5465049743652344,
+      "learning_rate": 3e-05,
+      "loss": 1.238,
+      "step": 12500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.4973833560943604,
+      "eval_runtime": 13.8641,
+      "eval_samples_per_second": 337.491,
+      "eval_steps_per_second": 10.603,
+      "step": 12500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 31250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 2
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6779672985600000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

MarianMT_ver4/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c560ad2d03f1b7128a182181a6042117448b304f7c1f01512264b775d5199afa
+size 5432