End of training

.gitattributes

@@ -32,5 +32,4 @@ 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/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text

last-checkpoint/config.json

@@ -1,35 +0,0 @@
-{
-  "_name_or_path": "facebook/nllb-200-distilled-600M",
-  "activation_dropout": 0.0,
-  "activation_function": "relu",
-  "architectures": [
-    "M2M100ForConditionalGeneration"
-  ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0,
-  "decoder_layers": 12,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0,
-  "encoder_layers": 12,
-  "eos_token_id": 2,
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "max_length": 200,
-  "max_position_embeddings": 1024,
-  "model_type": "m2m_100",
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "scale_embedding": true,
-  "tokenizer_class": "NllbTokenizer",
-  "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
-  "use_cache": true,
-  "vocab_size": 256206
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b2ed4d6179a5d70ed99cf0fa7418fef2a20cb5560a2c4dcbb7dc4c46c446e7d5
-size 4920898947

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b93f8641130a19f66c57f8ecf05dcf389906368a755f7f87bb668bde6600c5f6
-size 2468874377

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6dc3928bf65e95ad7412303bf594f62a1522c17b5d9e03e2d2a34b9029812b49
-size 14511

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:be3d6604c0bb0312bc94e5a6c7c044a2fb4b1ff121edd281d8f142b5f1ffce35
-size 627

last-checkpoint/sentencepiece.bpe.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:14bb8dfb35c0ffdea7bc01e56cea38b9e3d5efcdcb9c251d6b40538e1aab555a
-size 4852054

last-checkpoint/special_tokens_map.json

@@ -1,219 +0,0 @@
-{
-  "additional_special_tokens": [
-    "ace_Arab",
-    "ace_Latn",
-    "acm_Arab",
-    "acq_Arab",
-    "aeb_Arab",
-    "afr_Latn",
-    "ajp_Arab",
-    "aka_Latn",
-    "amh_Ethi",
-    "apc_Arab",
-    "arb_Arab",
-    "ars_Arab",
-    "ary_Arab",
-    "arz_Arab",
-    "asm_Beng",
-    "ast_Latn",
-    "awa_Deva",
-    "ayr_Latn",
-    "azb_Arab",
-    "azj_Latn",
-    "bak_Cyrl",
-    "bam_Latn",
-    "ban_Latn",
-    "bel_Cyrl",
-    "bem_Latn",
-    "ben_Beng",
-    "bho_Deva",
-    "bjn_Arab",
-    "bjn_Latn",
-    "bod_Tibt",
-    "bos_Latn",
-    "bug_Latn",
-    "bul_Cyrl",
-    "cat_Latn",
-    "ceb_Latn",
-    "ces_Latn",
-    "cjk_Latn",
-    "ckb_Arab",
-    "crh_Latn",
-    "cym_Latn",
-    "dan_Latn",
-    "deu_Latn",
-    "dik_Latn",
-    "dyu_Latn",
-    "dzo_Tibt",
-    "ell_Grek",
-    "eng_Latn",
-    "epo_Latn",
-    "est_Latn",
-    "eus_Latn",
-    "ewe_Latn",
-    "fao_Latn",
-    "pes_Arab",
-    "fij_Latn",
-    "fin_Latn",
-    "fon_Latn",
-    "fra_Latn",
-    "fur_Latn",
-    "fuv_Latn",
-    "gla_Latn",
-    "gle_Latn",
-    "glg_Latn",
-    "grn_Latn",
-    "guj_Gujr",
-    "hat_Latn",
-    "hau_Latn",
-    "heb_Hebr",
-    "hin_Deva",
-    "hne_Deva",
-    "hrv_Latn",
-    "hun_Latn",
-    "hye_Armn",
-    "ibo_Latn",
-    "ilo_Latn",
-    "ind_Latn",
-    "isl_Latn",
-    "ita_Latn",
-    "jav_Latn",
-    "jpn_Jpan",
-    "kab_Latn",
-    "kac_Latn",
-    "kam_Latn",
-    "kan_Knda",
-    "kas_Arab",
-    "kas_Deva",
-    "kat_Geor",
-    "knc_Arab",
-    "knc_Latn",
-    "kaz_Cyrl",
-    "kbp_Latn",
-    "kea_Latn",
-    "khm_Khmr",
-    "kik_Latn",
-    "kin_Latn",
-    "kir_Cyrl",
-    "kmb_Latn",
-    "kon_Latn",
-    "kor_Hang",
-    "kmr_Latn",
-    "lao_Laoo",
-    "lvs_Latn",
-    "lij_Latn",
-    "lim_Latn",
-    "lin_Latn",
-    "lit_Latn",
-    "lmo_Latn",
-    "ltg_Latn",
-    "ltz_Latn",
-    "lua_Latn",
-    "lug_Latn",
-    "luo_Latn",
-    "lus_Latn",
-    "mag_Deva",
-    "mai_Deva",
-    "mal_Mlym",
-    "mar_Deva",
-    "min_Latn",
-    "mkd_Cyrl",
-    "plt_Latn",
-    "mlt_Latn",
-    "mni_Beng",
-    "khk_Cyrl",
-    "mos_Latn",
-    "mri_Latn",
-    "zsm_Latn",
-    "mya_Mymr",
-    "nld_Latn",
-    "nno_Latn",
-    "nob_Latn",
-    "npi_Deva",
-    "nso_Latn",
-    "nus_Latn",
-    "nya_Latn",
-    "oci_Latn",
-    "gaz_Latn",
-    "ory_Orya",
-    "pag_Latn",
-    "pan_Guru",
-    "pap_Latn",
-    "pol_Latn",
-    "por_Latn",
-    "prs_Arab",
-    "pbt_Arab",
-    "quy_Latn",
-    "ron_Latn",
-    "run_Latn",
-    "rus_Cyrl",
-    "sag_Latn",
-    "san_Deva",
-    "sat_Beng",
-    "scn_Latn",
-    "shn_Mymr",
-    "sin_Sinh",
-    "slk_Latn",
-    "slv_Latn",
-    "smo_Latn",
-    "sna_Latn",
-    "snd_Arab",
-    "som_Latn",
-    "sot_Latn",
-    "spa_Latn",
-    "als_Latn",
-    "srd_Latn",
-    "srp_Cyrl",
-    "ssw_Latn",
-    "sun_Latn",
-    "swe_Latn",
-    "swh_Latn",
-    "szl_Latn",
-    "tam_Taml",
-    "tat_Cyrl",
-    "tel_Telu",
-    "tgk_Cyrl",
-    "tgl_Latn",
-    "tha_Thai",
-    "tir_Ethi",
-    "taq_Latn",
-    "taq_Tfng",
-    "tpi_Latn",
-    "tsn_Latn",
-    "tso_Latn",
-    "tuk_Latn",
-    "tum_Latn",
-    "tur_Latn",
-    "twi_Latn",
-    "tzm_Tfng",
-    "uig_Arab",
-    "ukr_Cyrl",
-    "umb_Latn",
-    "urd_Arab",
-    "uzn_Latn",
-    "vec_Latn",
-    "vie_Latn",
-    "war_Latn",
-    "wol_Latn",
-    "xho_Latn",
-    "ydd_Hebr",
-    "yor_Latn",
-    "yue_Hant",
-    "zho_Hans",
-    "zho_Hant",
-    "zul_Latn"
-  ],
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
-}

last-checkpoint/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8dec87343dd7b147b84072891b984b69471e9b7539eee4e544a0450ffc88e0e8
-size 17331294

last-checkpoint/tokenizer_config.json

@@ -1,24 +0,0 @@
-{
-  "additional_special_tokens": null,
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "model_max_length": 1024,
-  "name_or_path": "facebook/nllb-200-distilled-600M",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "sp_model_kwargs": {},
-  "special_tokens_map_file": null,
-  "src_lang": "eng_Latn",
-  "tgt_lang": "ind_Latn",
-  "tokenizer_class": "NllbTokenizer",
-  "unk_token": "<unk>"
-}

last-checkpoint/trainer_state.json

@@ -1,166 +0,0 @@
-{
-  "best_metric": 0.47876495122909546,
-  "best_model_checkpoint": "models/nllb-en-id-ccmatrix/checkpoint-253125",
-  "epoch": 10.0,
-  "global_step": 281250,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 1.0,
-      "learning_rate": 9.129846708746619e-06,
-      "loss": 0.606,
-      "step": 28125
-    },
-    {
-      "epoch": 1.0,
-      "eval_bleu": 64.1268,
-      "eval_loss": 0.524931013584137,
-      "eval_runtime": 3349.5808,
-      "eval_samples_per_second": 29.854,
-      "eval_steps_per_second": 0.933,
-      "step": 28125
-    },
-    {
-      "epoch": 2.0,
-      "learning_rate": 8.115419296663661e-06,
-      "loss": 0.4943,
-      "step": 56250
-    },
-    {
-      "epoch": 2.0,
-      "eval_bleu": 64.7892,
-      "eval_loss": 0.5042685866355896,
-      "eval_runtime": 3375.6685,
-      "eval_samples_per_second": 29.624,
-      "eval_steps_per_second": 0.926,
-      "step": 56250
-    },
-    {
-      "epoch": 3.0,
-      "learning_rate": 7.100991884580704e-06,
-      "loss": 0.467,
-      "step": 84375
-    },
-    {
-      "epoch": 3.0,
-      "eval_bleu": 65.2331,
-      "eval_loss": 0.49452316761016846,
-      "eval_runtime": 3358.2539,
-      "eval_samples_per_second": 29.777,
-      "eval_steps_per_second": 0.931,
-      "step": 84375
-    },
-    {
-      "epoch": 4.0,
-      "learning_rate": 6.0865644724977455e-06,
-      "loss": 0.4487,
-      "step": 112500
-    },
-    {
-      "epoch": 4.0,
-      "eval_bleu": 65.5512,
-      "eval_loss": 0.488678514957428,
-      "eval_runtime": 3355.1997,
-      "eval_samples_per_second": 29.804,
-      "eval_steps_per_second": 0.931,
-      "step": 112500
-    },
-    {
-      "epoch": 5.0,
-      "learning_rate": 5.072137060414789e-06,
-      "loss": 0.4349,
-      "step": 140625
-    },
-    {
-      "epoch": 5.0,
-      "eval_bleu": 65.6806,
-      "eval_loss": 0.4842682480812073,
-      "eval_runtime": 3377.8574,
-      "eval_samples_per_second": 29.605,
-      "eval_steps_per_second": 0.925,
-      "step": 140625
-    },
-    {
-      "epoch": 6.0,
-      "learning_rate": 4.057709648331831e-06,
-      "loss": 0.4242,
-      "step": 168750
-    },
-    {
-      "epoch": 6.0,
-      "eval_bleu": 65.7774,
-      "eval_loss": 0.48221057653427124,
-      "eval_runtime": 3362.6872,
-      "eval_samples_per_second": 29.738,
-      "eval_steps_per_second": 0.929,
-      "step": 168750
-    },
-    {
-      "epoch": 7.0,
-      "learning_rate": 3.0432822362488728e-06,
-      "loss": 0.416,
-      "step": 196875
-    },
-    {
-      "epoch": 7.0,
-      "eval_bleu": 65.8541,
-      "eval_loss": 0.48012077808380127,
-      "eval_runtime": 3379.151,
-      "eval_samples_per_second": 29.593,
-      "eval_steps_per_second": 0.925,
-      "step": 196875
-    },
-    {
-      "epoch": 8.0,
-      "learning_rate": 2.0288548241659153e-06,
-      "loss": 0.4098,
-      "step": 225000
-    },
-    {
-      "epoch": 8.0,
-      "eval_bleu": 65.9652,
-      "eval_loss": 0.4800304174423218,
-      "eval_runtime": 3370.7435,
-      "eval_samples_per_second": 29.667,
-      "eval_steps_per_second": 0.927,
-      "step": 225000
-    },
-    {
-      "epoch": 9.0,
-      "learning_rate": 1.0144274120829577e-06,
-      "loss": 0.4052,
-      "step": 253125
-    },
-    {
-      "epoch": 9.0,
-      "eval_bleu": 65.9701,
-      "eval_loss": 0.47876495122909546,
-      "eval_runtime": 3378.6802,
-      "eval_samples_per_second": 29.597,
-      "eval_steps_per_second": 0.925,
-      "step": 253125
-    },
-    {
-      "epoch": 10.0,
-      "learning_rate": 0.0,
-      "loss": 0.4023,
-      "step": 281250
-    },
-    {
-      "epoch": 10.0,
-      "eval_bleu": 65.9837,
-      "eval_loss": 0.47907769680023193,
-      "eval_runtime": 3373.8692,
-      "eval_samples_per_second": 29.64,
-      "eval_steps_per_second": 0.926,
-      "step": 281250
-    }
-  ],
-  "max_steps": 281250,
-  "num_train_epochs": 10,
-  "total_flos": 7.671437872925245e+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 sha256:3ce8a25a4e3959df6ac5c042f17d7dbec4233da4feb7c11b467ccefc47e5ab97
-size 3643

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b93f8641130a19f66c57f8ecf05dcf389906368a755f7f87bb668bde6600c5f6
+oid sha256:1d05009dbe23b1d997be5391df7f03167d76ffaee130c7dddc471568d4326068
 size 2468874377