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 sha256:0d2e88c2a463ad4b55f3a38041628644c545d8da712d8235e5396377a447b046
-size 577701381

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d90d2cc10256c2049a4d3985e8a8a5ad38f5450b0a05bd884d4ce75748326e1c
-size 289081861

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9bcf060ca49247eb79b04210ee27fddb6c56d83199d13c6317e8667c52583a46
-size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:368d606ba58025458a7a4928a134d8d02b44d7703e4636b6ec3229ecf6d7599f
-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": 1.3274328708648682,
-  "best_model_checkpoint": "models/opus-mt-id-en-open-subtitles/checkpoint-28125",
-  "epoch": 25.0,
-  "global_step": 703125,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 1.0,
-      "learning_rate": 9.654925800107278e-05,
-      "loss": 1.3533,
-      "step": 28125
-    },
-    {
-      "epoch": 1.0,
-      "eval_bleu": 37.6662,
-      "eval_loss": 1.3274328708648682,
-      "eval_runtime": 1861.5149,
-      "eval_samples_per_second": 53.72,
-      "eval_steps_per_second": 1.679,
-      "step": 28125
-    },
-    {
-      "epoch": 2.0,
-      "learning_rate": 9.252637225102807e-05,
-      "loss": 1.2814,
-      "step": 56250
-    },
-    {
-      "epoch": 2.0,
-      "eval_bleu": 37.5909,
-      "eval_loss": 1.3524662256240845,
-      "eval_runtime": 1509.1742,
-      "eval_samples_per_second": 66.261,
-      "eval_steps_per_second": 2.071,
-      "step": 56250
-    },
-    {
-      "epoch": 3.0,
-      "learning_rate": 8.850348650098338e-05,
-      "loss": 1.2058,
-      "step": 84375
-    },
-    {
-      "epoch": 3.0,
-      "eval_bleu": 37.8008,
-      "eval_loss": 1.3674018383026123,
-      "eval_runtime": 1551.6085,
-      "eval_samples_per_second": 64.449,
-      "eval_steps_per_second": 2.014,
-      "step": 84375
-    },
-    {
-      "epoch": 4.0,
-      "learning_rate": 8.448060075093868e-05,
-      "loss": 1.1415,
-      "step": 112500
-    },
-    {
-      "epoch": 4.0,
-      "eval_bleu": 37.4849,
-      "eval_loss": 1.3721529245376587,
-      "eval_runtime": 1712.582,
-      "eval_samples_per_second": 58.391,
-      "eval_steps_per_second": 1.825,
-      "step": 112500
-    },
-    {
-      "epoch": 5.0,
-      "learning_rate": 8.045771500089397e-05,
-      "loss": 1.0842,
-      "step": 140625
-    },
-    {
-      "epoch": 5.0,
-      "eval_bleu": 37.7558,
-      "eval_loss": 1.3942967653274536,
-      "eval_runtime": 1531.4782,
-      "eval_samples_per_second": 65.296,
-      "eval_steps_per_second": 2.041,
-      "step": 140625
-    },
-    {
-      "epoch": 6.0,
-      "learning_rate": 7.643482925084928e-05,
-      "loss": 1.0309,
-      "step": 168750
-    },
-    {
-      "epoch": 6.0,
-      "eval_bleu": 37.6332,
-      "eval_loss": 1.3994051218032837,
-      "eval_runtime": 1465.4534,
-      "eval_samples_per_second": 68.238,
-      "eval_steps_per_second": 2.132,
-      "step": 168750
-    },
-    {
-      "epoch": 7.0,
-      "learning_rate": 7.241194350080458e-05,
-      "loss": 0.9802,
-      "step": 196875
-    },
-    {
-      "epoch": 7.0,
-      "eval_bleu": 37.7529,
-      "eval_loss": 1.4215837717056274,
-      "eval_runtime": 1573.1177,
-      "eval_samples_per_second": 63.568,
-      "eval_steps_per_second": 1.987,
-      "step": 196875
-    },
-    {
-      "epoch": 8.0,
-      "learning_rate": 6.838905775075987e-05,
-      "loss": 0.9316,
-      "step": 225000
-    },
-    {
-      "epoch": 8.0,
-      "eval_bleu": 37.9906,
-      "eval_loss": 1.4304240942001343,
-      "eval_runtime": 1471.9189,
-      "eval_samples_per_second": 67.939,
-      "eval_steps_per_second": 2.123,
-      "step": 225000
-    },
-    {
-      "epoch": 9.0,
-      "learning_rate": 6.436617200071518e-05,
-      "loss": 0.8838,
-      "step": 253125
-    },
-    {
-      "epoch": 9.0,
-      "eval_bleu": 37.7833,
-      "eval_loss": 1.4462167024612427,
-      "eval_runtime": 1502.4733,
-      "eval_samples_per_second": 66.557,
-      "eval_steps_per_second": 2.08,
-      "step": 253125
-    },
-    {
-      "epoch": 10.0,
-      "learning_rate": 6.034328625067048e-05,
-      "loss": 0.8378,
-      "step": 281250
-    },
-    {
-      "epoch": 10.0,
-      "eval_bleu": 37.5971,
-      "eval_loss": 1.4639370441436768,
-      "eval_runtime": 1489.8072,
-      "eval_samples_per_second": 67.123,
-      "eval_steps_per_second": 2.098,
-      "step": 281250
-    },
-    {
-      "epoch": 11.0,
-      "learning_rate": 5.632040050062578e-05,
-      "loss": 0.7921,
-      "step": 309375
-    },
-    {
-      "epoch": 11.0,
-      "eval_bleu": 37.6285,
-      "eval_loss": 1.485935926437378,
-      "eval_runtime": 1460.5333,
-      "eval_samples_per_second": 68.468,
-      "eval_steps_per_second": 2.14,
-      "step": 309375
-    },
-    {
-      "epoch": 12.0,
-      "learning_rate": 5.229751475058109e-05,
-      "loss": 0.7484,
-      "step": 337500
-    },
-    {
-      "epoch": 12.0,
-      "eval_bleu": 37.5413,
-      "eval_loss": 1.5060349702835083,
-      "eval_runtime": 1480.0942,
-      "eval_samples_per_second": 67.563,
-      "eval_steps_per_second": 2.111,
-      "step": 337500
-    },
-    {
-      "epoch": 13.0,
-      "learning_rate": 4.827462900053639e-05,
-      "loss": 0.7043,
-      "step": 365625
-    },
-    {
-      "epoch": 13.0,
-      "eval_bleu": 37.5118,
-      "eval_loss": 1.5256059169769287,
-      "eval_runtime": 1462.073,
-      "eval_samples_per_second": 68.396,
-      "eval_steps_per_second": 2.137,
-      "step": 365625
-    },
-    {
-      "epoch": 14.0,
-      "learning_rate": 4.425174325049169e-05,
-      "loss": 0.6622,
-      "step": 393750
-    },
-    {
-      "epoch": 14.0,
-      "eval_bleu": 37.5092,
-      "eval_loss": 1.555537223815918,
-      "eval_runtime": 1474.8089,
-      "eval_samples_per_second": 67.805,
-      "eval_steps_per_second": 2.119,
-      "step": 393750
-    },
-    {
-      "epoch": 15.0,
-      "learning_rate": 4.022885750044699e-05,
-      "loss": 0.6208,
-      "step": 421875
-    },
-    {
-      "epoch": 15.0,
-      "eval_bleu": 37.2924,
-      "eval_loss": 1.573325276374817,
-      "eval_runtime": 1464.8257,
-      "eval_samples_per_second": 68.268,
-      "eval_steps_per_second": 2.133,
-      "step": 421875
-    },
-    {
-      "epoch": 16.0,
-      "learning_rate": 3.620597175040229e-05,
-      "loss": 0.5807,
-      "step": 450000
-    },
-    {
-      "epoch": 16.0,
-      "eval_bleu": 37.319,
-      "eval_loss": 1.60484778881073,
-      "eval_runtime": 1459.7156,
-      "eval_samples_per_second": 68.506,
-      "eval_steps_per_second": 2.141,
-      "step": 450000
-    },
-    {
-      "epoch": 17.0,
-      "learning_rate": 3.218308600035759e-05,
-      "loss": 0.542,
-      "step": 478125
-    },
-    {
-      "epoch": 17.0,
-      "eval_bleu": 37.0629,
-      "eval_loss": 1.6434943675994873,
-      "eval_runtime": 1463.555,
-      "eval_samples_per_second": 68.327,
-      "eval_steps_per_second": 2.135,
-      "step": 478125
-    },
-    {
-      "epoch": 18.0,
-      "learning_rate": 2.816020025031289e-05,
-      "loss": 0.5043,
-      "step": 506250
-    },
-    {
-      "epoch": 18.0,
-      "eval_bleu": 37.1334,
-      "eval_loss": 1.6646835803985596,
-      "eval_runtime": 1448.2184,
-      "eval_samples_per_second": 69.05,
-      "eval_steps_per_second": 2.158,
-      "step": 506250
-    },
-    {
-      "epoch": 19.0,
-      "learning_rate": 2.4137314500268194e-05,
-      "loss": 0.4685,
-      "step": 534375
-    },
-    {
-      "epoch": 19.0,
-      "eval_bleu": 37.02,
-      "eval_loss": 1.701406717300415,
-      "eval_runtime": 1487.6794,
-      "eval_samples_per_second": 67.219,
-      "eval_steps_per_second": 2.101,
-      "step": 534375
-    },
-    {
-      "epoch": 20.0,
-      "learning_rate": 2.0114428750223493e-05,
-      "loss": 0.4352,
-      "step": 562500
-    },
-    {
-      "epoch": 20.0,
-      "eval_bleu": 36.9514,
-      "eval_loss": 1.7299559116363525,
-      "eval_runtime": 1449.7878,
-      "eval_samples_per_second": 68.976,
-      "eval_steps_per_second": 2.155,
-      "step": 562500
-    },
-    {
-      "epoch": 21.0,
-      "learning_rate": 1.6091543000178796e-05,
-      "loss": 0.4031,
-      "step": 590625
-    },
-    {
-      "epoch": 21.0,
-      "eval_bleu": 36.9637,
-      "eval_loss": 1.7572004795074463,
-      "eval_runtime": 1454.2044,
-      "eval_samples_per_second": 68.766,
-      "eval_steps_per_second": 2.149,
-      "step": 590625
-    },
-    {
-      "epoch": 22.0,
-      "learning_rate": 1.2068657250134097e-05,
-      "loss": 0.3731,
-      "step": 618750
-    },
-    {
-      "epoch": 22.0,
-      "eval_bleu": 36.9821,
-      "eval_loss": 1.7902287244796753,
-      "eval_runtime": 1450.2265,
-      "eval_samples_per_second": 68.955,
-      "eval_steps_per_second": 2.155,
-      "step": 618750
-    },
-    {
-      "epoch": 23.0,
-      "learning_rate": 8.045771500089398e-06,
-      "loss": 0.346,
-      "step": 646875
-    },
-    {
-      "epoch": 23.0,
-      "eval_bleu": 36.9586,
-      "eval_loss": 1.8111997842788696,
-      "eval_runtime": 1448.2982,
-      "eval_samples_per_second": 69.047,
-      "eval_steps_per_second": 2.158,
-      "step": 646875
-    },
-    {
-      "epoch": 24.0,
-      "learning_rate": 4.022885750044699e-06,
-      "loss": 0.3227,
-      "step": 675000
-    },
-    {
-      "epoch": 24.0,
-      "eval_bleu": 36.9286,
-      "eval_loss": 1.8325022459030151,
-      "eval_runtime": 1450.793,
-      "eval_samples_per_second": 68.928,
-      "eval_steps_per_second": 2.154,
-      "step": 675000
-    },
-    {
-      "epoch": 25.0,
-      "learning_rate": 0.0,
-      "loss": 0.303,
-      "step": 703125
-    },
-    {
-      "epoch": 25.0,
-      "eval_bleu": 36.9382,
-      "eval_loss": 1.8429754972457886,
-      "eval_runtime": 1448.8258,
-      "eval_samples_per_second": 69.021,
-      "eval_steps_per_second": 2.157,
-      "step": 703125
-    }
-  ],
-  "max_steps": 703125,
-  "num_train_epochs": 25,
-  "total_flos": 1.3122279945378202e+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 sha256:096873cb715c0742cc88026a10db5fb803013016fd2eb4790edaefea640a8e20
-size 3643

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d90d2cc10256c2049a4d3985e8a8a5ad38f5450b0a05bd884d4ce75748326e1c
+oid sha256:476941512fa6d9bf4120703c4b916f3953f36d28ca096772f675e0480ae75f89
 size 289081861