End of training

.gitattributes

@@ -32,7 +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
-last-checkpoint/source.spm filter=lfs diff=lfs merge=lfs -text
-last-checkpoint/target.spm 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

last-checkpoint/config.json

@@ -1,61 +0,0 @@
-{
-  "_name_or_path": "./models/opus-mt-id-en",
-  "_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": [
-    [
-      54795
-    ]
-  ],
-  "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": 54795,
-  "decoder_vocab_size": 54796,
-  "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": 54795,
-  "scale_embedding": true,
-  "share_encoder_decoder_embeddings": true,
-  "static_position_embeddings": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
-  "use_cache": true,
-  "vocab_size": 54796
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7e162c1d3d7ea76966a86c1d731d98682aa40962d899b6f0618622d0b66c6671
-size 577701381

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ef845d72d39cee6f5741bc62f369bf5d5bfbdfb93813fbb431f0a99e325ddfeb
-size 289081861

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9ec143d72daac1723aa3ddd73161c2e4bcaada92de3854ce0d52e1f11ea6c7f5
-size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3ee244d99cf1ef6f6077b70a8893738482f9a54a0a3a311433f1846a9680a168
-size 627

last-checkpoint/source.spm

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2a8fefe71c7f26cb0c6aa1b9f0cc0f8d18006b20fe41c547af7f25b9c8333465
-size 800687

last-checkpoint/special_tokens_map.json

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

last-checkpoint/target.spm

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e88300911c2c573ec5526777a1e84bae698d20925b82dcef9c7248bb0e537ed0
-size 795925

last-checkpoint/tokenizer_config.json

@@ -1,13 +0,0 @@
-{
-  "eos_token": "</s>",
-  "model_max_length": 512,
-  "name_or_path": "./models/opus-mt-id-en",
-  "pad_token": "<pad>",
-  "separate_vocabs": false,
-  "source_lang": "id",
-  "sp_model_kwargs": {},
-  "special_tokens_map_file": null,
-  "target_lang": "en",
-  "tokenizer_class": "MarianTokenizer",
-  "unk_token": "<unk>"
-}

last-checkpoint/trainer_state.json

@@ -1,391 +0,0 @@
-{
-  "best_metric": 1.6302595138549805,
-  "best_model_checkpoint": "models/opus-mt-id-en-opus100/checkpoint-31250",
-  "epoch": 25.0,
-  "global_step": 781250,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 1.0,
-      "learning_rate": 9.649404953361209e-05,
-      "loss": 1.4869,
-      "step": 31250
-    },
-    {
-      "epoch": 1.0,
-      "eval_bleu": 32.7596,
-      "eval_loss": 1.6302595138549805,
-      "eval_runtime": 39.1839,
-      "eval_samples_per_second": 51.041,
-      "eval_steps_per_second": 1.608,
-      "step": 31250
-    },
-    {
-      "epoch": 2.0,
-      "learning_rate": 9.247346413637826e-05,
-      "loss": 1.433,
-      "step": 62500
-    },
-    {
-      "epoch": 2.0,
-      "eval_bleu": 33.1603,
-      "eval_loss": 1.6473666429519653,
-      "eval_runtime": 39.2913,
-      "eval_samples_per_second": 50.902,
-      "eval_steps_per_second": 1.603,
-      "step": 62500
-    },
-    {
-      "epoch": 3.0,
-      "learning_rate": 8.845287873914442e-05,
-      "loss": 1.3626,
-      "step": 93750
-    },
-    {
-      "epoch": 3.0,
-      "eval_bleu": 32.6599,
-      "eval_loss": 1.654058814048767,
-      "eval_runtime": 41.2418,
-      "eval_samples_per_second": 48.494,
-      "eval_steps_per_second": 1.528,
-      "step": 93750
-    },
-    {
-      "epoch": 4.0,
-      "learning_rate": 8.443229334191058e-05,
-      "loss": 1.3025,
-      "step": 125000
-    },
-    {
-      "epoch": 4.0,
-      "eval_bleu": 32.961,
-      "eval_loss": 1.6537519693374634,
-      "eval_runtime": 35.5864,
-      "eval_samples_per_second": 56.201,
-      "eval_steps_per_second": 1.77,
-      "step": 125000
-    },
-    {
-      "epoch": 5.0,
-      "learning_rate": 8.041170794467674e-05,
-      "loss": 1.2485,
-      "step": 156250
-    },
-    {
-      "epoch": 5.0,
-      "eval_bleu": 33.1362,
-      "eval_loss": 1.6630192995071411,
-      "eval_runtime": 40.7681,
-      "eval_samples_per_second": 49.058,
-      "eval_steps_per_second": 1.545,
-      "step": 156250
-    },
-    {
-      "epoch": 6.0,
-      "learning_rate": 7.63911225474429e-05,
-      "loss": 1.198,
-      "step": 187500
-    },
-    {
-      "epoch": 6.0,
-      "eval_bleu": 32.0117,
-      "eval_loss": 1.6793715953826904,
-      "eval_runtime": 33.0939,
-      "eval_samples_per_second": 60.434,
-      "eval_steps_per_second": 1.904,
-      "step": 187500
-    },
-    {
-      "epoch": 7.0,
-      "learning_rate": 7.237053715020908e-05,
-      "loss": 1.1492,
-      "step": 218750
-    },
-    {
-      "epoch": 7.0,
-      "eval_bleu": 33.2442,
-      "eval_loss": 1.6909666061401367,
-      "eval_runtime": 39.8878,
-      "eval_samples_per_second": 50.141,
-      "eval_steps_per_second": 1.579,
-      "step": 218750
-    },
-    {
-      "epoch": 8.0,
-      "learning_rate": 6.834995175297524e-05,
-      "loss": 1.102,
-      "step": 250000
-    },
-    {
-      "epoch": 8.0,
-      "eval_bleu": 32.7068,
-      "eval_loss": 1.6874189376831055,
-      "eval_runtime": 33.1063,
-      "eval_samples_per_second": 60.411,
-      "eval_steps_per_second": 1.903,
-      "step": 250000
-    },
-    {
-      "epoch": 9.0,
-      "learning_rate": 6.43293663557414e-05,
-      "loss": 1.0559,
-      "step": 281250
-    },
-    {
-      "epoch": 9.0,
-      "eval_bleu": 32.8825,
-      "eval_loss": 1.6943720579147339,
-      "eval_runtime": 36.2902,
-      "eval_samples_per_second": 55.111,
-      "eval_steps_per_second": 1.736,
-      "step": 281250
-    },
-    {
-      "epoch": 10.0,
-      "learning_rate": 6.030878095850756e-05,
-      "loss": 1.0106,
-      "step": 312500
-    },
-    {
-      "epoch": 10.0,
-      "eval_bleu": 33.2979,
-      "eval_loss": 1.7288198471069336,
-      "eval_runtime": 33.705,
-      "eval_samples_per_second": 59.338,
-      "eval_steps_per_second": 1.869,
-      "step": 312500
-    },
-    {
-      "epoch": 11.0,
-      "learning_rate": 5.6288195561273725e-05,
-      "loss": 0.9662,
-      "step": 343750
-    },
-    {
-      "epoch": 11.0,
-      "eval_bleu": 33.255,
-      "eval_loss": 1.7401976585388184,
-      "eval_runtime": 40.6207,
-      "eval_samples_per_second": 49.236,
-      "eval_steps_per_second": 1.551,
-      "step": 343750
-    },
-    {
-      "epoch": 12.0,
-      "learning_rate": 5.2267610164039885e-05,
-      "loss": 0.9219,
-      "step": 375000
-    },
-    {
-      "epoch": 12.0,
-      "eval_bleu": 32.901,
-      "eval_loss": 1.7589361667633057,
-      "eval_runtime": 39.0563,
-      "eval_samples_per_second": 51.208,
-      "eval_steps_per_second": 1.613,
-      "step": 375000
-    },
-    {
-      "epoch": 13.0,
-      "learning_rate": 4.8247024766806045e-05,
-      "loss": 0.8783,
-      "step": 406250
-    },
-    {
-      "epoch": 13.0,
-      "eval_bleu": 32.6629,
-      "eval_loss": 1.7892544269561768,
-      "eval_runtime": 34.3539,
-      "eval_samples_per_second": 58.218,
-      "eval_steps_per_second": 1.834,
-      "step": 406250
-    },
-    {
-      "epoch": 14.0,
-      "learning_rate": 4.422643936957221e-05,
-      "loss": 0.8352,
-      "step": 437500
-    },
-    {
-      "epoch": 14.0,
-      "eval_bleu": 32.6507,
-      "eval_loss": 1.8073551654815674,
-      "eval_runtime": 34.1785,
-      "eval_samples_per_second": 58.516,
-      "eval_steps_per_second": 1.843,
-      "step": 437500
-    },
-    {
-      "epoch": 15.0,
-      "learning_rate": 4.020585397233837e-05,
-      "loss": 0.7932,
-      "step": 468750
-    },
-    {
-      "epoch": 15.0,
-      "eval_bleu": 33.0076,
-      "eval_loss": 1.835935115814209,
-      "eval_runtime": 35.523,
-      "eval_samples_per_second": 56.302,
-      "eval_steps_per_second": 1.773,
-      "step": 468750
-    },
-    {
-      "epoch": 16.0,
-      "learning_rate": 3.618526857510454e-05,
-      "loss": 0.7516,
-      "step": 500000
-    },
-    {
-      "epoch": 16.0,
-      "eval_bleu": 32.9601,
-      "eval_loss": 1.8693500757217407,
-      "eval_runtime": 33.9205,
-      "eval_samples_per_second": 58.961,
-      "eval_steps_per_second": 1.857,
-      "step": 500000
-    },
-    {
-      "epoch": 17.0,
-      "learning_rate": 3.21646831778707e-05,
-      "loss": 0.7112,
-      "step": 531250
-    },
-    {
-      "epoch": 17.0,
-      "eval_bleu": 32.5161,
-      "eval_loss": 1.8887429237365723,
-      "eval_runtime": 39.5753,
-      "eval_samples_per_second": 50.537,
-      "eval_steps_per_second": 1.592,
-      "step": 531250
-    },
-    {
-      "epoch": 18.0,
-      "learning_rate": 2.8144097780636862e-05,
-      "loss": 0.6711,
-      "step": 562500
-    },
-    {
-      "epoch": 18.0,
-      "eval_bleu": 32.5722,
-      "eval_loss": 1.919446587562561,
-      "eval_runtime": 33.7573,
-      "eval_samples_per_second": 59.247,
-      "eval_steps_per_second": 1.866,
-      "step": 562500
-    },
-    {
-      "epoch": 19.0,
-      "learning_rate": 2.4123512383403023e-05,
-      "loss": 0.6326,
-      "step": 593750
-    },
-    {
-      "epoch": 19.0,
-      "eval_bleu": 32.553,
-      "eval_loss": 1.9512020349502563,
-      "eval_runtime": 34.0822,
-      "eval_samples_per_second": 58.682,
-      "eval_steps_per_second": 1.848,
-      "step": 593750
-    },
-    {
-      "epoch": 20.0,
-      "learning_rate": 2.0102926986169186e-05,
-      "loss": 0.5955,
-      "step": 625000
-    },
-    {
-      "epoch": 20.0,
-      "eval_bleu": 32.0152,
-      "eval_loss": 1.9790940284729004,
-      "eval_runtime": 34.0344,
-      "eval_samples_per_second": 58.764,
-      "eval_steps_per_second": 1.851,
-      "step": 625000
-    },
-    {
-      "epoch": 21.0,
-      "learning_rate": 1.608234158893535e-05,
-      "loss": 0.5603,
-      "step": 656250
-    },
-    {
-      "epoch": 21.0,
-      "eval_bleu": 32.2671,
-      "eval_loss": 2.010413885116577,
-      "eval_runtime": 38.4945,
-      "eval_samples_per_second": 51.956,
-      "eval_steps_per_second": 1.637,
-      "step": 656250
-    },
-    {
-      "epoch": 22.0,
-      "learning_rate": 1.2061756191701511e-05,
-      "loss": 0.5266,
-      "step": 687500
-    },
-    {
-      "epoch": 22.0,
-      "eval_bleu": 32.1775,
-      "eval_loss": 2.0387871265411377,
-      "eval_runtime": 38.6936,
-      "eval_samples_per_second": 51.688,
-      "eval_steps_per_second": 1.628,
-      "step": 687500
-    },
-    {
-      "epoch": 23.0,
-      "learning_rate": 8.041170794467675e-06,
-      "loss": 0.4956,
-      "step": 718750
-    },
-    {
-      "epoch": 23.0,
-      "eval_bleu": 32.123,
-      "eval_loss": 2.0663225650787354,
-      "eval_runtime": 34.2029,
-      "eval_samples_per_second": 58.475,
-      "eval_steps_per_second": 1.842,
-      "step": 718750
-    },
-    {
-      "epoch": 24.0,
-      "learning_rate": 4.020585397233837e-06,
-      "loss": 0.4681,
-      "step": 750000
-    },
-    {
-      "epoch": 24.0,
-      "eval_bleu": 32.1197,
-      "eval_loss": 2.084930419921875,
-      "eval_runtime": 34.0638,
-      "eval_samples_per_second": 58.713,
-      "eval_steps_per_second": 1.849,
-      "step": 750000
-    },
-    {
-      "epoch": 25.0,
-      "learning_rate": 0.0,
-      "loss": 0.4445,
-      "step": 781250
-    },
-    {
-      "epoch": 25.0,
-      "eval_bleu": 32.455,
-      "eval_loss": 2.1007559299468994,
-      "eval_runtime": 34.472,
-      "eval_samples_per_second": 58.018,
-      "eval_steps_per_second": 1.828,
-      "step": 781250
-    }
-  ],
-  "max_steps": 781250,
-  "num_train_epochs": 25,
-  "total_flos": 2.5585722286984397e+17,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f79820bb39691c16bb62047f02b445612c8b232a5f94e8f71f50b78ce19e35b6
-size 3643

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef845d72d39cee6f5741bc62f369bf5d5bfbdfb93813fbb431f0a99e325ddfeb
+oid sha256:c1d31f44bafa9aa9c5a8953fcecd6de4bc07bc7e20324e3e83ba8aa351ced121
 size 289081861