add MT model

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "predict_bleu": 12.2748,
+    "predict_gen_len": 35.1988,
+    "predict_loss": 4.553185939788818,
+    "predict_runtime": 465.54,
+    "predict_samples": 1564,
+    "predict_samples_per_second": 3.36,
+    "predict_steps_per_second": 0.337,
+    "train_loss": 1.4909019682778344,
+    "train_runtime": 1616.6394,
+    "train_samples": 23321,
+    "train_samples_per_second": 43.277,
+    "train_steps_per_second": 4.329
+}

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": 128028,
+  "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": 12.2748,
+    "predict_gen_len": 35.1988,
+    "predict_loss": 4.553185939788818,
+    "predict_runtime": 465.54,
+    "predict_samples": 1564,
+    "predict_samples_per_second": 3.36,
+    "predict_steps_per_second": 0.337
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbfd9add75a1ded38e1e94e37188878669d844163eda6016b6829befcfe40236
+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": 3.0,
+    "train_loss": 1.4909019682778344,
+    "train_runtime": 1616.6394,
+    "train_samples": 23321,
+    "train_samples_per_second": 43.277,
+    "train_steps_per_second": 4.329
+}

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 6999,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.642806115159309e-05,
+      "loss": 2.3657,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 4.285612230318617e-05,
+      "loss": 1.9755,
+      "step": 1000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.928418345477925e-05,
+      "loss": 1.862,
+      "step": 1500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3.571224460637234e-05,
+      "loss": 1.7635,
+      "step": 2000
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 3.214030575796543e-05,
+      "loss": 1.6301,
+      "step": 2500
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 2.856836690955851e-05,
+      "loss": 1.4343,
+      "step": 3000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.4996428061151594e-05,
+      "loss": 1.4334,
+      "step": 3500
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.142448921274468e-05,
+      "loss": 1.386,
+      "step": 4000
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.7852550364337764e-05,
+      "loss": 1.3779,
+      "step": 4500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.4280611515930847e-05,
+      "loss": 1.1955,
+      "step": 5000
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 1.0708672667523933e-05,
+      "loss": 1.1193,
+      "step": 5500
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.1367338191170165e-06,
+      "loss": 1.118,
+      "step": 6000
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 3.5647949707101015e-06,
+      "loss": 1.1058,
+      "step": 6500
+    },
+    {
+      "epoch": 3.0,
+      "step": 6999,
+      "total_flos": 6319189788917760.0,
+      "train_loss": 1.4909019682778344,
+      "train_runtime": 1616.6394,
+      "train_samples_per_second": 43.277,
+      "train_steps_per_second": 4.329
+    }
+  ],
+  "max_steps": 6999,
+  "num_train_epochs": 3,
+  "total_flos": 6319189788917760.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59a6effd4101d9b20138b40d556d576bf4447a9848e3852cffe04f6306800305
+size 2735