add MT model

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "predict_bleu": 2.0347,
+    "predict_gen_len": 56.0513,
+    "predict_loss": 4.543285846710205,
+    "predict_runtime": 772.5211,
+    "predict_samples": 1500,
+    "predict_samples_per_second": 1.942,
+    "predict_steps_per_second": 0.194,
+    "train_loss": 1.0457585005237526,
+    "train_runtime": 9612.1472,
+    "train_samples": 31104,
+    "train_samples_per_second": 32.359,
+    "train_steps_per_second": 3.237
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "facebook/m2m100_418M",
+  "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": 0.05,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.05,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 128054,
+  "gradient_checkpointing": false,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "m2m_100",
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 128112
+}

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_bleu": 2.0347,
+    "predict_gen_len": 56.0513,
+    "predict_loss": 4.543285846710205,
+    "predict_runtime": 772.5211,
+    "predict_samples": 1500,
+    "predict_samples_per_second": 1.942,
+    "predict_steps_per_second": 0.194
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e303baae2670a7a6a8c6a19c9779f1f85dee7137dee32366e7c3cba138e09fc
+size 1935792071

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f7c76ed2a5e0822be39f0a4f95a55eb19c78f4593ce609e2edbc2aea4d380a
+size 2423393

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "additional_special_tokens": ["__af__", "__am__", "__ar__", "__ast__", "__az__", "__ba__", "__be__", "__bg__", "__bn__", "__br__", "__bs__", "__ca__", "__ceb__", "__cs__", "__cy__", "__da__", "__de__", "__el__", "__en__", "__es__", "__et__", "__fa__", "__ff__", "__fi__", "__fr__", "__fy__", "__ga__", "__gd__", "__gl__", "__gu__", "__ha__", "__he__", "__hi__", "__hr__", "__ht__", "__hu__", "__hy__", "__id__", "__ig__", "__ilo__", "__is__", "__it__", "__ja__", "__jv__", "__ka__", "__kk__", "__km__", "__kn__", "__ko__", "__lb__", "__lg__", "__ln__", "__lo__", "__lt__", "__lv__", "__mg__", "__mk__", "__ml__", "__mn__", "__mr__", "__ms__", "__my__", "__ne__", "__nl__", "__no__", "__ns__", "__oc__", "__or__", "__pa__", "__pl__", "__ps__", "__pt__", "__ro__", "__ru__", "__sd__", "__si__", "__sk__", "__sl__", "__so__", "__sq__", "__sr__", "__ss__", "__su__", "__sv__", "__sw__", "__ta__", "__th__", "__tl__", "__tn__", "__tr__", "__uk__", "__ur__", "__uz__", "__vi__", "__wo__", "__xh__", "__yi__", "__yo__", "__zh__", "__zu__"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"src_lang": null, "tgt_lang": null, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "sp_model_kwargs": {}, "special_tokens_map_file": "m2m_100_1.2B_v2/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "facebook/m2m100_418M", "model_max_length": 1024, "additional_special_tokens": ["__af__", "__am__", "__ar__", "__ast__", "__az__", "__ba__", "__be__", "__bg__", "__bn__", "__br__", "__bs__", "__ca__", "__ceb__", "__cs__", "__cy__", "__da__", "__de__", "__el__", "__en__", "__es__", "__et__", "__fa__", "__ff__", "__fi__", "__fr__", "__fy__", "__ga__", "__gd__", "__gl__", "__gu__", "__ha__", "__he__", "__hi__", "__hr__", "__ht__", "__hu__", "__hy__", "__id__", "__ig__", "__ilo__", "__is__", "__it__", "__ja__", "__jv__", "__ka__", "__kk__", "__km__", "__kn__", "__ko__", "__lb__", "__lg__", "__ln__", "__lo__", "__lt__", "__lv__", "__mg__", "__mk__", "__ml__", "__mn__", "__mr__", "__ms__", "__my__", "__ne__", "__nl__", "__no__", "__ns__", "__oc__", "__or__", "__pa__", "__pl__", "__ps__", "__pt__", "__ro__", "__ru__", "__sd__", "__si__", "__sk__", "__sl__", "__so__", "__sq__", "__sr__", "__ss__", "__su__", "__sv__", "__sw__", "__ta__", "__th__", "__tl__", "__tn__", "__tr__", "__uk__", "__ur__", "__uz__", "__vi__", "__wo__", "__xh__", "__yi__", "__yo__", "__zh__", "__zu__"], "tokenizer_class": "M2M100Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 1.0457585005237526,
+    "train_runtime": 9612.1472,
+    "train_samples": 31104,
+    "train_samples_per_second": 32.359,
+    "train_steps_per_second": 3.237
+}

trainer_state.json

@@ -0,0 +1,397 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 31110,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.919639987142398e-05,
+      "loss": 3.736,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.839279974284796e-05,
+      "loss": 2.694,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 4.758919961427194e-05,
+      "loss": 2.3793,
+      "step": 1500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 4.678559948569592e-05,
+      "loss": 2.2157,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.59819993571199e-05,
+      "loss": 2.0865,
+      "step": 2500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.517839922854388e-05,
+      "loss": 1.9888,
+      "step": 3000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 4.4374799099967856e-05,
+      "loss": 1.7791,
+      "step": 3500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 4.357119897139183e-05,
+      "loss": 1.7181,
+      "step": 4000
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 4.2767598842815816e-05,
+      "loss": 1.6788,
+      "step": 4500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.196399871423979e-05,
+      "loss": 1.6565,
+      "step": 5000
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 4.1160398585663775e-05,
+      "loss": 1.6128,
+      "step": 5500
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 4.035679845708776e-05,
+      "loss": 1.5839,
+      "step": 6000
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 3.9553198328511734e-05,
+      "loss": 1.4628,
+      "step": 6500
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.874959819993572e-05,
+      "loss": 1.3677,
+      "step": 7000
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 3.7945998071359693e-05,
+      "loss": 1.3458,
+      "step": 7500
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 3.7142397942783676e-05,
+      "loss": 1.3436,
+      "step": 8000
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 3.633879781420765e-05,
+      "loss": 1.3476,
+      "step": 8500
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 3.5535197685631636e-05,
+      "loss": 1.3265,
+      "step": 9000
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 3.473159755705561e-05,
+      "loss": 1.2552,
+      "step": 9500
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 3.392799742847959e-05,
+      "loss": 1.1139,
+      "step": 10000
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 3.312439729990357e-05,
+      "loss": 1.1205,
+      "step": 10500
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 3.232079717132755e-05,
+      "loss": 1.1202,
+      "step": 11000
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 3.151719704275153e-05,
+      "loss": 1.1305,
+      "step": 11500
+    },
+    {
+      "epoch": 3.86,
+      "learning_rate": 3.071359691417551e-05,
+      "loss": 1.1291,
+      "step": 12000
+    },
+    {
+      "epoch": 4.02,
+      "learning_rate": 2.9909996785599486e-05,
+      "loss": 1.1071,
+      "step": 12500
+    },
+    {
+      "epoch": 4.18,
+      "learning_rate": 2.9106396657023466e-05,
+      "loss": 0.9143,
+      "step": 13000
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 2.8302796528447446e-05,
+      "loss": 0.9409,
+      "step": 13500
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 2.7499196399871425e-05,
+      "loss": 0.9381,
+      "step": 14000
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 2.6695596271295405e-05,
+      "loss": 0.96,
+      "step": 14500
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 2.589199614271938e-05,
+      "loss": 0.9616,
+      "step": 15000
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 2.508839601414336e-05,
+      "loss": 0.948,
+      "step": 15500
+    },
+    {
+      "epoch": 5.14,
+      "learning_rate": 2.4284795885567344e-05,
+      "loss": 0.7787,
+      "step": 16000
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 2.3481195756991323e-05,
+      "loss": 0.7821,
+      "step": 16500
+    },
+    {
+      "epoch": 5.46,
+      "learning_rate": 2.2677595628415303e-05,
+      "loss": 0.7927,
+      "step": 17000
+    },
+    {
+      "epoch": 5.63,
+      "learning_rate": 2.1873995499839283e-05,
+      "loss": 0.7907,
+      "step": 17500
+    },
+    {
+      "epoch": 5.79,
+      "learning_rate": 2.107039537126326e-05,
+      "loss": 0.7904,
+      "step": 18000
+    },
+    {
+      "epoch": 5.95,
+      "learning_rate": 2.026679524268724e-05,
+      "loss": 0.804,
+      "step": 18500
+    },
+    {
+      "epoch": 6.11,
+      "learning_rate": 1.9463195114111218e-05,
+      "loss": 0.6899,
+      "step": 19000
+    },
+    {
+      "epoch": 6.27,
+      "learning_rate": 1.8659594985535198e-05,
+      "loss": 0.6512,
+      "step": 19500
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 1.7855994856959177e-05,
+      "loss": 0.6662,
+      "step": 20000
+    },
+    {
+      "epoch": 6.59,
+      "learning_rate": 1.7052394728383157e-05,
+      "loss": 0.6688,
+      "step": 20500
+    },
+    {
+      "epoch": 6.75,
+      "learning_rate": 1.6248794599807137e-05,
+      "loss": 0.6663,
+      "step": 21000
+    },
+    {
+      "epoch": 6.91,
+      "learning_rate": 1.5445194471231116e-05,
+      "loss": 0.6584,
+      "step": 21500
+    },
+    {
+      "epoch": 7.07,
+      "learning_rate": 1.4641594342655096e-05,
+      "loss": 0.6115,
+      "step": 22000
+    },
+    {
+      "epoch": 7.23,
+      "learning_rate": 1.3837994214079075e-05,
+      "loss": 0.5433,
+      "step": 22500
+    },
+    {
+      "epoch": 7.39,
+      "learning_rate": 1.3034394085503055e-05,
+      "loss": 0.5653,
+      "step": 23000
+    },
+    {
+      "epoch": 7.55,
+      "learning_rate": 1.2230793956927033e-05,
+      "loss": 0.5509,
+      "step": 23500
+    },
+    {
+      "epoch": 7.71,
+      "learning_rate": 1.1427193828351013e-05,
+      "loss": 0.553,
+      "step": 24000
+    },
+    {
+      "epoch": 7.88,
+      "learning_rate": 1.0623593699774992e-05,
+      "loss": 0.5659,
+      "step": 24500
+    },
+    {
+      "epoch": 8.04,
+      "learning_rate": 9.819993571198972e-06,
+      "loss": 0.5369,
+      "step": 25000
+    },
+    {
+      "epoch": 8.2,
+      "learning_rate": 9.016393442622952e-06,
+      "loss": 0.4594,
+      "step": 25500
+    },
+    {
+      "epoch": 8.36,
+      "learning_rate": 8.212793314046931e-06,
+      "loss": 0.4692,
+      "step": 26000
+    },
+    {
+      "epoch": 8.52,
+      "learning_rate": 7.40919318547091e-06,
+      "loss": 0.4773,
+      "step": 26500
+    },
+    {
+      "epoch": 8.68,
+      "learning_rate": 6.605593056894889e-06,
+      "loss": 0.479,
+      "step": 27000
+    },
+    {
+      "epoch": 8.84,
+      "learning_rate": 5.801992928318869e-06,
+      "loss": 0.4784,
+      "step": 27500
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.998392799742848e-06,
+      "loss": 0.4781,
+      "step": 28000
+    },
+    {
+      "epoch": 9.16,
+      "learning_rate": 4.194792671166828e-06,
+      "loss": 0.423,
+      "step": 28500
+    },
+    {
+      "epoch": 9.32,
+      "learning_rate": 3.391192542590807e-06,
+      "loss": 0.4236,
+      "step": 29000
+    },
+    {
+      "epoch": 9.48,
+      "learning_rate": 2.5875924140147865e-06,
+      "loss": 0.4197,
+      "step": 29500
+    },
+    {
+      "epoch": 9.64,
+      "learning_rate": 1.7839922854387657e-06,
+      "loss": 0.4091,
+      "step": 30000
+    },
+    {
+      "epoch": 9.8,
+      "learning_rate": 9.80392156862745e-07,
+      "loss": 0.4076,
+      "step": 30500
+    },
+    {
+      "epoch": 9.96,
+      "learning_rate": 1.7679202828672455e-07,
+      "loss": 0.4182,
+      "step": 31000
+    },
+    {
+      "epoch": 10.0,
+      "step": 31110,
+      "total_flos": 4.532670747485798e+16,
+      "train_loss": 1.0457585005237526,
+      "train_runtime": 9612.1472,
+      "train_samples_per_second": 32.359,
+      "train_steps_per_second": 3.237
+    }
+  ],
+  "max_steps": 31110,
+  "num_train_epochs": 10,
+  "total_flos": 4.532670747485798e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7216c863d16be8c75fd4e4efe1cfd607b6a8e944b7af46f10749b875c7fa79a
+size 2735