add MT model

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "predict_bleu": 30.5716,
+    "predict_gen_len": 32.4594,
+    "predict_loss": 2.097909688949585,
+    "predict_runtime": 524.4158,
+    "predict_samples": 1835,
+    "predict_samples_per_second": 3.499,
+    "predict_steps_per_second": 0.351,
+    "train_loss": 0.4749538145966637,
+    "train_runtime": 8800.1602,
+    "train_samples": 30782,
+    "train_samples_per_second": 34.979,
+    "train_steps_per_second": 3.499
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "m2m100_sw_en_jw_lafand",
+  "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": 128022,
+  "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": 30.5716,
+    "predict_gen_len": 32.4594,
+    "predict_loss": 2.097909688949585,
+    "predict_runtime": 524.4158,
+    "predict_samples": 1835,
+    "predict_samples_per_second": 3.499,
+    "predict_steps_per_second": 0.351
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725eefd9e286e246ee6f611309bc4e30f1a488db9f4d1d6406e62dde0d5ed670
+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": "m2m100_sw_en_jw_lafand", "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": 0.4749538145966637,
+    "train_runtime": 8800.1602,
+    "train_samples": 30782,
+    "train_samples_per_second": 34.979,
+    "train_steps_per_second": 3.499
+}

trainer_state.json

@@ -0,0 +1,391 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 30790,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.91880480675544e-05,
+      "loss": 1.3261,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.8376096135108804e-05,
+      "loss": 1.3797,
+      "step": 1000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.7564144202663205e-05,
+      "loss": 1.3638,
+      "step": 1500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 4.6752192270217606e-05,
+      "loss": 1.3633,
+      "step": 2000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.5940240337772006e-05,
+      "loss": 1.3682,
+      "step": 2500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.512828840532641e-05,
+      "loss": 1.3593,
+      "step": 3000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 4.431633647288081e-05,
+      "loss": 1.0336,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 4.350438454043521e-05,
+      "loss": 0.995,
+      "step": 4000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 4.269243260798961e-05,
+      "loss": 0.9883,
+      "step": 4500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.188048067554401e-05,
+      "loss": 1.0297,
+      "step": 5000
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 4.106852874309841e-05,
+      "loss": 1.0241,
+      "step": 5500
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 4.025657681065281e-05,
+      "loss": 1.0224,
+      "step": 6000
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 3.944462487820721e-05,
+      "loss": 0.8053,
+      "step": 6500
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 3.8632672945761614e-05,
+      "loss": 0.7302,
+      "step": 7000
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 3.7820721013316015e-05,
+      "loss": 0.7373,
+      "step": 7500
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 3.7008769080870415e-05,
+      "loss": 0.7509,
+      "step": 8000
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.6196817148424816e-05,
+      "loss": 0.7547,
+      "step": 8500
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 3.538486521597922e-05,
+      "loss": 0.7656,
+      "step": 9000
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 3.457291328353362e-05,
+      "loss": 0.6361,
+      "step": 9500
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 3.376096135108802e-05,
+      "loss": 0.513,
+      "step": 10000
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 3.294900941864242e-05,
+      "loss": 0.5348,
+      "step": 10500
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 3.213705748619682e-05,
+      "loss": 0.5253,
+      "step": 11000
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 3.132510555375122e-05,
+      "loss": 0.5508,
+      "step": 11500
+    },
+    {
+      "epoch": 3.9,
+      "learning_rate": 3.051315362130562e-05,
+      "loss": 0.543,
+      "step": 12000
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 2.970120168886002e-05,
+      "loss": 0.4766,
+      "step": 12500
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 2.888924975641442e-05,
+      "loss": 0.366,
+      "step": 13000
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 2.8077297823968824e-05,
+      "loss": 0.3687,
+      "step": 13500
+    },
+    {
+      "epoch": 4.55,
+      "learning_rate": 2.7265345891523225e-05,
+      "loss": 0.381,
+      "step": 14000
+    },
+    {
+      "epoch": 4.71,
+      "learning_rate": 2.6453393959077623e-05,
+      "loss": 0.3869,
+      "step": 14500
+    },
+    {
+      "epoch": 4.87,
+      "learning_rate": 2.5641442026632023e-05,
+      "loss": 0.3945,
+      "step": 15000
+    },
+    {
+      "epoch": 5.03,
+      "learning_rate": 2.4829490094186424e-05,
+      "loss": 0.3471,
+      "step": 15500
+    },
+    {
+      "epoch": 5.2,
+      "learning_rate": 2.401753816174083e-05,
+      "loss": 0.2529,
+      "step": 16000
+    },
+    {
+      "epoch": 5.36,
+      "learning_rate": 2.3205586229295226e-05,
+      "loss": 0.262,
+      "step": 16500
+    },
+    {
+      "epoch": 5.52,
+      "learning_rate": 2.2393634296849627e-05,
+      "loss": 0.2563,
+      "step": 17000
+    },
+    {
+      "epoch": 5.68,
+      "learning_rate": 2.158168236440403e-05,
+      "loss": 0.254,
+      "step": 17500
+    },
+    {
+      "epoch": 5.85,
+      "learning_rate": 2.0769730431958428e-05,
+      "loss": 0.2632,
+      "step": 18000
+    },
+    {
+      "epoch": 6.01,
+      "learning_rate": 1.995777849951283e-05,
+      "loss": 0.2588,
+      "step": 18500
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 1.914582656706723e-05,
+      "loss": 0.169,
+      "step": 19000
+    },
+    {
+      "epoch": 6.33,
+      "learning_rate": 1.833387463462163e-05,
+      "loss": 0.1772,
+      "step": 19500
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 1.752192270217603e-05,
+      "loss": 0.1802,
+      "step": 20000
+    },
+    {
+      "epoch": 6.66,
+      "learning_rate": 1.6709970769730432e-05,
+      "loss": 0.1873,
+      "step": 20500
+    },
+    {
+      "epoch": 6.82,
+      "learning_rate": 1.5898018837284833e-05,
+      "loss": 0.1783,
+      "step": 21000
+    },
+    {
+      "epoch": 6.98,
+      "learning_rate": 1.5086066904839236e-05,
+      "loss": 0.1756,
+      "step": 21500
+    },
+    {
+      "epoch": 7.15,
+      "learning_rate": 1.4274114972393635e-05,
+      "loss": 0.1339,
+      "step": 22000
+    },
+    {
+      "epoch": 7.31,
+      "learning_rate": 1.3462163039948036e-05,
+      "loss": 0.1226,
+      "step": 22500
+    },
+    {
+      "epoch": 7.47,
+      "learning_rate": 1.2650211107502435e-05,
+      "loss": 0.1274,
+      "step": 23000
+    },
+    {
+      "epoch": 7.63,
+      "learning_rate": 1.1838259175056837e-05,
+      "loss": 0.1232,
+      "step": 23500
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 1.1026307242611238e-05,
+      "loss": 0.1247,
+      "step": 24000
+    },
+    {
+      "epoch": 7.96,
+      "learning_rate": 1.0214355310165639e-05,
+      "loss": 0.1268,
+      "step": 24500
+    },
+    {
+      "epoch": 8.12,
+      "learning_rate": 9.40240337772004e-06,
+      "loss": 0.1043,
+      "step": 25000
+    },
+    {
+      "epoch": 8.28,
+      "learning_rate": 8.59045144527444e-06,
+      "loss": 0.0888,
+      "step": 25500
+    },
+    {
+      "epoch": 8.44,
+      "learning_rate": 7.778499512828841e-06,
+      "loss": 0.0916,
+      "step": 26000
+    },
+    {
+      "epoch": 8.61,
+      "learning_rate": 6.966547580383241e-06,
+      "loss": 0.0946,
+      "step": 26500
+    },
+    {
+      "epoch": 8.77,
+      "learning_rate": 6.154595647937642e-06,
+      "loss": 0.0941,
+      "step": 27000
+    },
+    {
+      "epoch": 8.93,
+      "learning_rate": 5.342643715492044e-06,
+      "loss": 0.0925,
+      "step": 27500
+    },
+    {
+      "epoch": 9.09,
+      "learning_rate": 4.530691783046444e-06,
+      "loss": 0.0808,
+      "step": 28000
+    },
+    {
+      "epoch": 9.26,
+      "learning_rate": 3.718739850600845e-06,
+      "loss": 0.0793,
+      "step": 28500
+    },
+    {
+      "epoch": 9.42,
+      "learning_rate": 2.9067879181552453e-06,
+      "loss": 0.0739,
+      "step": 29000
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 2.094835985709646e-06,
+      "loss": 0.0739,
+      "step": 29500
+    },
+    {
+      "epoch": 9.74,
+      "learning_rate": 1.2828840532640467e-06,
+      "loss": 0.0703,
+      "step": 30000
+    },
+    {
+      "epoch": 9.91,
+      "learning_rate": 4.7093212081844755e-07,
+      "loss": 0.0684,
+      "step": 30500
+    },
+    {
+      "epoch": 10.0,
+      "step": 30790,
+      "total_flos": 5.041211966452531e+16,
+      "train_loss": 0.4749538145966637,
+      "train_runtime": 8800.1602,
+      "train_samples_per_second": 34.979,
+      "train_steps_per_second": 3.499
+    }
+  ],
+  "max_steps": 30790,
+  "num_train_epochs": 10,
+  "total_flos": 5.041211966452531e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7eadc4fad1b16837b96459f1b976890b8b0ba2535cb3616a15307f1114cae83
+size 2799