add MT model

all_results.json

@@ -3,13 +3,13 @@
     "predict_bleu": 11.3686,
     "predict_gen_len": 51.7227,
     "predict_loss": 2.3827884197235107,
-    "predict_runtime": 768.1622,
+    "predict_runtime": 765.4367,
     "predict_samples": 1500,
-    "predict_samples_per_second": 1.953,
-    "predict_steps_per_second": 0.195,
+    "predict_samples_per_second": 1.96,
+    "predict_steps_per_second": 0.196,
     "train_loss": 1.4770170771886433,
-    "train_runtime": 364.0867,
+    "train_runtime": 362.6466,
     "train_samples": 3360,
-    "train_samples_per_second": 27.686,
-    "train_steps_per_second": 2.769
+    "train_samples_per_second": 27.796,
+    "train_steps_per_second": 2.78
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "m2m100_fr_wo_jw_lafand",
+  "_name_or_path": "masakhane/m2m100_418M_fr_wol_rel_news",
   "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [

predict_results.json

@@ -2,8 +2,8 @@
     "predict_bleu": 11.3686,
     "predict_gen_len": 51.7227,
     "predict_loss": 2.3827884197235107,
-    "predict_runtime": 768.1622,
+    "predict_runtime": 765.4367,
     "predict_samples": 1500,
-    "predict_samples_per_second": 1.953,
-    "predict_steps_per_second": 0.195
+    "predict_samples_per_second": 1.96,
+    "predict_steps_per_second": 0.196
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f86395d7bac72252c253d21f847fd541472b78033850a24cde7bc6cfb8beb9
+size 1935792071

tokenizer_config.json

@@ -1 +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_fr_wo_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"}
+{"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": "masakhane/m2m100_418M_fr_wol_rel_news", "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

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
     "train_loss": 1.4770170771886433,
-    "train_runtime": 364.0867,
+    "train_runtime": 362.6466,
     "train_samples": 3360,
-    "train_samples_per_second": 27.686,
-    "train_steps_per_second": 2.769
+    "train_samples_per_second": 27.796,
+    "train_steps_per_second": 2.78
 }

trainer_state.json

@@ -24,9 +24,9 @@
       "step": 1008,
       "total_flos": 1826230648504320.0,
       "train_loss": 1.4770170771886433,
-      "train_runtime": 364.0867,
-      "train_samples_per_second": 27.686,
-      "train_steps_per_second": 2.769
+      "train_runtime": 362.6466,
+      "train_samples_per_second": 27.796,
+      "train_steps_per_second": 2.78
     }
   ],
   "max_steps": 1008,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77db856abcaf8a7a8220088d0cbd02b688ee881b5ba90559b6ca77f5fe73cea8
+oid sha256:0420852e61ba7b0caa3392040caa209b99e89541b9ec1fbb453409886c94d8e8
 size 2799