Upload 11 files

.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 +1,35 @@
+{
+  "_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": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 256206
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "max_length": 200,
+  "pad_token_id": 1,
+  "transformers_version": "4.30.2"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe7bcf7f44d4c29dd0cc342142cc27d530e7bf9a86ac4d3a56ce28c70555e687
+size 4920898372

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20909eee6ef004f627e5576cc2a10cf462785bd1634828f52744538d1a61e22d
+size 2468874822

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b17573dd1396c9f4fd6dbb0fa7f603421b1472b932c35d17ecec5384171364c6
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b22cd2fc45f5b9171a57629b33c06034f8187a0d3e18d3222146e05c7af6fd7
+size 1064

special_tokens_map.json

@@ -0,0 +1,219 @@
+{
+  "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 +1,24 @@
+{
+  "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 +1,230 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.844827586206897,
+  "global_step": 16500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.942873563218391e-05,
+      "loss": 5.5518,
+      "step": 500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.885402298850575e-05,
+      "loss": 0.3979,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.8279310344827587e-05,
+      "loss": 0.1115,
+      "step": 1500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.7704597701149427e-05,
+      "loss": 0.1044,
+      "step": 2000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.7129885057471266e-05,
+      "loss": 0.0986,
+      "step": 2500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.6555172413793105e-05,
+      "loss": 0.0899,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.5980459770114944e-05,
+      "loss": 0.0872,
+      "step": 3500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.5405747126436783e-05,
+      "loss": 0.085,
+      "step": 4000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.4831034482758623e-05,
+      "loss": 0.0869,
+      "step": 4500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.425632183908046e-05,
+      "loss": 0.0879,
+      "step": 5000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.36816091954023e-05,
+      "loss": 0.0797,
+      "step": 5500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.07041613757610321,
+      "eval_runtime": 64.4372,
+      "eval_samples_per_second": 40.008,
+      "eval_steps_per_second": 10.01,
+      "step": 5800
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.310689655172414e-05,
+      "loss": 0.079,
+      "step": 6000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.253218390804598e-05,
+      "loss": 0.071,
+      "step": 6500
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.1957471264367817e-05,
+      "loss": 0.0701,
+      "step": 7000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.1382758620689656e-05,
+      "loss": 0.0739,
+      "step": 7500
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.0808045977011495e-05,
+      "loss": 0.0723,
+      "step": 8000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.0233333333333336e-05,
+      "loss": 0.0682,
+      "step": 8500
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 9.658620689655173e-06,
+      "loss": 0.068,
+      "step": 9000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.083908045977013e-06,
+      "loss": 0.0686,
+      "step": 9500
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 8.509195402298852e-06,
+      "loss": 0.0662,
+      "step": 10000
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 7.934482758620691e-06,
+      "loss": 0.0671,
+      "step": 10500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 7.359770114942529e-06,
+      "loss": 0.0684,
+      "step": 11000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 6.785057471264368e-06,
+      "loss": 0.0669,
+      "step": 11500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.06483030319213867,
+      "eval_runtime": 64.5114,
+      "eval_samples_per_second": 39.962,
+      "eval_steps_per_second": 9.998,
+      "step": 11600
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 6.211494252873563e-06,
+      "loss": 0.062,
+      "step": 12000
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 5.636781609195403e-06,
+      "loss": 0.061,
+      "step": 12500
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 5.062068965517242e-06,
+      "loss": 0.0581,
+      "step": 13000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 4.487356321839081e-06,
+      "loss": 0.0575,
+      "step": 13500
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 3.913793103448276e-06,
+      "loss": 0.0643,
+      "step": 14000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 3.3390804597701155e-06,
+      "loss": 0.0623,
+      "step": 14500
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 2.764367816091954e-06,
+      "loss": 0.0565,
+      "step": 15000
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 2.1896551724137934e-06,
+      "loss": 0.0592,
+      "step": 15500
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.6149425287356323e-06,
+      "loss": 0.0627,
+      "step": 16000
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.0402298850574713e-06,
+      "loss": 0.0565,
+      "step": 16500
+    }
+  ],
+  "max_steps": 17400,
+  "num_train_epochs": 3,
+  "total_flos": 3.575505883024589e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9bbdb248063ae18680f88926ff76113d9e472a12817e20504cc0231790fd78f
+size 4536