Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "checkpoint-53168",
+  "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": 8192,
+  "decoder_layerdrop": 0,
+  "decoder_layers": 24,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 8192,
+  "encoder_layerdrop": 0,
+  "encoder_layers": 24,
+  "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": 24,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 256206
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 200,
+  "pad_token_id": 1,
+  "transformers_version": "4.31.0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d7098c6d88733cea062740fbbf6f691ff82c156e4e34c1abebb1297cd6f3b6
+size 10965715027

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38820a77c622a03563be28191b1c502830a8dc5eaddb395fcdfaffe07029e49a
+size 5482902982

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e95e409639f9c9d88073775f84c96a6033aff88b2547cc693ba9c7e7536cd4f
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e76e819a0e81bcdfbc2387da3e713f3ec92d981087df2402fe03a386d40c70b
+size 627

sentencepiece.bpe.model

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

special_tokens_map.json

@@ -0,0 +1,220 @@
+{
+  "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>"
+}
+

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e316b82de11d0f951f370943b3c438311629547285129b0b81dadabd01bca665
+size 17331176

tokenizer_config.json

@@ -0,0 +1,25 @@
+{
+  "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": null,
+  "tgt_lang": null,
+  "tokenizer_class": "NllbTokenizer",
+  "unk_token": "<unk>"
+}
+

trainer_state.json

@@ -0,0 +1,276 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 19806,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.87377562354842e-05,
+      "loss": 0.5877,
+      "step": 500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.74755124709684e-05,
+      "loss": 0.6317,
+      "step": 1000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.6213268706452596e-05,
+      "loss": 0.6456,
+      "step": 1500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.4951024941936785e-05,
+      "loss": 0.6473,
+      "step": 2000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.368878117742099e-05,
+      "loss": 0.6499,
+      "step": 2500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.242653741290518e-05,
+      "loss": 0.6602,
+      "step": 3000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.116429364838938e-05,
+      "loss": 0.6699,
+      "step": 3500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.9902049883873574e-05,
+      "loss": 0.6624,
+      "step": 4000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.8639806119357776e-05,
+      "loss": 0.651,
+      "step": 4500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 3.7377562354841965e-05,
+      "loss": 0.6709,
+      "step": 5000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 3.611531859032616e-05,
+      "loss": 0.6582,
+      "step": 5500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.485307482581036e-05,
+      "loss": 0.6698,
+      "step": 6000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 3.359083106129456e-05,
+      "loss": 0.6522,
+      "step": 6500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.2328587296778754e-05,
+      "loss": 0.6863,
+      "step": 7000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.1066343532262956e-05,
+      "loss": 0.6602,
+      "step": 7500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.9804099767747152e-05,
+      "loss": 0.6466,
+      "step": 8000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.8541856003231344e-05,
+      "loss": 0.7011,
+      "step": 8500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.727961223871554e-05,
+      "loss": 0.677,
+      "step": 9000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.601736847419974e-05,
+      "loss": 0.6581,
+      "step": 9500
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 30.9028,
+      "eval_chrf++": 57.3001,
+      "eval_gen_len": 27.1266,
+      "eval_loss": 1.247955083847046,
+      "eval_runtime": 1316.7682,
+      "eval_samples_per_second": 3.718,
+      "eval_spbleu": 43.0506,
+      "eval_steps_per_second": 0.744,
+      "eval_ter": 59.7925,
+      "step": 9903
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 2.4755124709683934e-05,
+      "loss": 0.6144,
+      "step": 10000
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 2.3492880945168133e-05,
+      "loss": 0.4286,
+      "step": 10500
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 2.223063718065233e-05,
+      "loss": 0.4329,
+      "step": 11000
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 2.0968393416136524e-05,
+      "loss": 0.4324,
+      "step": 11500
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.9706149651620723e-05,
+      "loss": 0.4403,
+      "step": 12000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.844390588710492e-05,
+      "loss": 0.4353,
+      "step": 12500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.7181662122589115e-05,
+      "loss": 0.4312,
+      "step": 13000
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.5919418358073314e-05,
+      "loss": 0.4212,
+      "step": 13500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.4657174593557507e-05,
+      "loss": 0.4158,
+      "step": 14000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.3394930829041705e-05,
+      "loss": 0.4061,
+      "step": 14500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.2132687064525902e-05,
+      "loss": 0.4202,
+      "step": 15000
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.0870443300010098e-05,
+      "loss": 0.4448,
+      "step": 15500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.608199535494297e-06,
+      "loss": 0.4351,
+      "step": 16000
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.345955770978492e-06,
+      "loss": 0.4072,
+      "step": 16500
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 7.083712006462688e-06,
+      "loss": 0.4157,
+      "step": 17000
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 5.821468241946885e-06,
+      "loss": 0.4338,
+      "step": 17500
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.559224477431081e-06,
+      "loss": 0.4212,
+      "step": 18000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.2969807129152782e-06,
+      "loss": 0.411,
+      "step": 18500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2.0347369483994747e-06,
+      "loss": 0.4179,
+      "step": 19000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 7.724931838836716e-07,
+      "loss": 0.4255,
+      "step": 19500
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 31.3408,
+      "eval_chrf++": 57.4539,
+      "eval_gen_len": 27.0633,
+      "eval_loss": 1.3426777124404907,
+      "eval_runtime": 1310.3387,
+      "eval_samples_per_second": 3.736,
+      "eval_spbleu": 43.1979,
+      "eval_steps_per_second": 0.748,
+      "eval_ter": 59.0383,
+      "step": 19806
+    }
+  ],
+  "max_steps": 19806,
+  "num_train_epochs": 2,
+  "total_flos": 8.428883485392896e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef1aa6540cbe88561036b418b0031f6e178a7ac67e834c2ad5e6a5eab47c9017
+size 4091