add MT model

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "predict_bleu": 1.8879,
+    "predict_gen_len": 87.7441,
+    "predict_loss": 5.1465630531311035,
+    "predict_runtime": 1197.4467,
+    "predict_samples": 1579,
+    "predict_samples_per_second": 1.319,
+    "predict_steps_per_second": 0.132,
+    "train_loss": 1.1291042611109392,
+    "train_runtime": 3221.1049,
+    "train_samples": 32183,
+    "train_samples_per_second": 29.974,
+    "train_steps_per_second": 2.998
+}

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": 128088,
+  "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": 1.8879,
+    "predict_gen_len": 87.7441,
+    "predict_loss": 5.1465630531311035,
+    "predict_runtime": 1197.4467,
+    "predict_samples": 1579,
+    "predict_samples_per_second": 1.319,
+    "predict_steps_per_second": 0.132
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6addd4235b45e7ad6135df0016f25bc33f624c3ae8bcccb34498549f7591e451
+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": 1.1291042611109392,
+    "train_runtime": 3221.1049,
+    "train_samples": 32183,
+    "train_samples_per_second": 29.974,
+    "train_steps_per_second": 2.998
+}

trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 9657,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.7411204307756033e-05,
+      "loss": 2.4532,
+      "step": 500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.482240861551207e-05,
+      "loss": 1.6939,
+      "step": 1000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.2233612923268096e-05,
+      "loss": 1.4835,
+      "step": 1500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.964481723102413e-05,
+      "loss": 1.3597,
+      "step": 2000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.7056021538780165e-05,
+      "loss": 1.2939,
+      "step": 2500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.4467225846536196e-05,
+      "loss": 1.2304,
+      "step": 3000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.187843015429223e-05,
+      "loss": 1.1246,
+      "step": 3500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 2.9289634462048254e-05,
+      "loss": 1.0545,
+      "step": 4000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.670083876980429e-05,
+      "loss": 1.0199,
+      "step": 4500
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.411204307756032e-05,
+      "loss": 1.0216,
+      "step": 5000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.1523247385316354e-05,
+      "loss": 0.9894,
+      "step": 5500
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.8934451693072382e-05,
+      "loss": 0.9787,
+      "step": 6000
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.6345656000828417e-05,
+      "loss": 0.9494,
+      "step": 6500
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.3756860308584446e-05,
+      "loss": 0.8392,
+      "step": 7000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 1.1168064616340479e-05,
+      "loss": 0.8201,
+      "step": 7500
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 8.57926892409651e-06,
+      "loss": 0.8225,
+      "step": 8000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 5.9904732318525425e-06,
+      "loss": 0.8176,
+      "step": 8500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.401677539608574e-06,
+      "loss": 0.8109,
+      "step": 9000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 8.12881847364606e-07,
+      "loss": 0.7971,
+      "step": 9500
+    },
+    {
+      "epoch": 3.0,
+      "step": 9657,
+      "total_flos": 1.0817124216717312e+16,
+      "train_loss": 1.1291042611109392,
+      "train_runtime": 3221.1049,
+      "train_samples_per_second": 29.974,
+      "train_steps_per_second": 2.998
+    }
+  ],
+  "max_steps": 9657,
+  "num_train_epochs": 3,
+  "total_flos": 1.0817124216717312e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ad1c4186747cad1e9e242adef078408a0f4d4f8eeb15f947955504886ba3fd
+size 2735