add MT model

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "predict_bleu": 11.9265,
+    "predict_gen_len": 70.654,
+    "predict_loss": 2.4002599716186523,
+    "predict_runtime": 1023.0909,
+    "predict_samples": 1558,
+    "predict_samples_per_second": 1.523,
+    "predict_steps_per_second": 0.152,
+    "train_loss": 1.0604149048310474,
+    "train_runtime": 2826.0867,
+    "train_samples": 6644,
+    "train_samples_per_second": 23.51,
+    "train_steps_per_second": 2.353
+}

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": 128101,
+  "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": "4.12.0",
+  "use_cache": true,
+  "vocab_size": 128112
+}

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_bleu": 11.9265,
+    "predict_gen_len": 70.654,
+    "predict_loss": 2.4002599716186523,
+    "predict_runtime": 1023.0909,
+    "predict_samples": 1558,
+    "predict_samples_per_second": 1.523,
+    "predict_steps_per_second": 0.152
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c96347cc0ea1e656978c8e1cb0cec9b7d25b4ac81ccad7029eb2f0838578f670
+size 1935804116

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": 1.0604149048310474,
+    "train_runtime": 2826.0867,
+    "train_samples": 6644,
+    "train_samples_per_second": 23.51,
+    "train_steps_per_second": 2.353
+}

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 6650,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.62406015037594e-05,
+      "loss": 2.8573,
+      "step": 500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 4.24812030075188e-05,
+      "loss": 1.8961,
+      "step": 1000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 3.87218045112782e-05,
+      "loss": 1.5868,
+      "step": 1500
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 3.49624060150376e-05,
+      "loss": 1.3574,
+      "step": 2000
+    },
+    {
+      "epoch": 3.76,
+      "learning_rate": 3.120300751879699e-05,
+      "loss": 1.1194,
+      "step": 2500
+    },
+    {
+      "epoch": 4.51,
+      "learning_rate": 2.7443609022556393e-05,
+      "loss": 0.9743,
+      "step": 3000
+    },
+    {
+      "epoch": 5.26,
+      "learning_rate": 2.368421052631579e-05,
+      "loss": 0.8595,
+      "step": 3500
+    },
+    {
+      "epoch": 6.02,
+      "learning_rate": 1.9924812030075188e-05,
+      "loss": 0.7652,
+      "step": 4000
+    },
+    {
+      "epoch": 6.77,
+      "learning_rate": 1.6165413533834585e-05,
+      "loss": 0.632,
+      "step": 4500
+    },
+    {
+      "epoch": 7.52,
+      "learning_rate": 1.2406015037593984e-05,
+      "loss": 0.5672,
+      "step": 5000
+    },
+    {
+      "epoch": 8.27,
+      "learning_rate": 8.646616541353383e-06,
+      "loss": 0.5018,
+      "step": 5500
+    },
+    {
+      "epoch": 9.02,
+      "learning_rate": 4.887218045112782e-06,
+      "loss": 0.4564,
+      "step": 6000
+    },
+    {
+      "epoch": 9.77,
+      "learning_rate": 1.1278195488721805e-06,
+      "loss": 0.4088,
+      "step": 6500
+    },
+    {
+      "epoch": 10.0,
+      "step": 6650,
+      "total_flos": 8971514004209664.0,
+      "train_loss": 1.0604149048310474,
+      "train_runtime": 2826.0867,
+      "train_samples_per_second": 23.51,
+      "train_steps_per_second": 2.353
+    }
+  ],
+  "max_steps": 6650,
+  "num_train_epochs": 10,
+  "total_flos": 8971514004209664.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72575e5627dcf25a9428e4cc8487829d48891989925f3c6720eb517739706cca
+size 2927