add MT model

all_results.json

@@ -7,16 +7,16 @@
     "eval_samples": 1478,
     "eval_samples_per_second": 1.519,
     "eval_steps_per_second": 0.38,
-    "predict_bleu": 6.4901,
-    "predict_gen_len": 42.176,
-    "predict_loss": 2.834754228591919,
-    "predict_runtime": 927.6529,
+    "predict_bleu": 6.4776,
+    "predict_gen_len": 42.5864,
+    "predict_loss": 2.801192045211792,
+    "predict_runtime": 828.5138,
     "predict_samples": 1574,
-    "predict_samples_per_second": 1.697,
-    "predict_steps_per_second": 0.425,
-    "train_loss": 1.6065418536846454,
-    "train_runtime": 357.1607,
+    "predict_samples_per_second": 1.9,
+    "predict_steps_per_second": 0.38,
+    "train_loss": 1.7082170156065206,
+    "train_runtime": 275.0373,
     "train_samples": 2287,
-    "train_samples_per_second": 19.21,
-    "train_steps_per_second": 4.805
+    "train_samples_per_second": 24.946,
+    "train_steps_per_second": 2.498
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "m2m100_mos_fr_jw_lafand",
+  "_name_or_path": "mos/m2m100_mos_fr_jw_lafand",
   "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
@@ -32,7 +32,7 @@
   "pad_token_id": 1,
   "scale_embedding": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.10.0",
+  "transformers_version": "4.10.3",
   "use_cache": true,
   "vocab_size": 128112
 }

predict_results.json

@@ -1,9 +1,9 @@
 {
-    "predict_bleu": 6.4901,
-    "predict_gen_len": 42.176,
-    "predict_loss": 2.834754228591919,
-    "predict_runtime": 927.6529,
+    "predict_bleu": 6.4776,
+    "predict_gen_len": 42.5864,
+    "predict_loss": 2.801192045211792,
+    "predict_runtime": 828.5138,
     "predict_samples": 1574,
-    "predict_samples_per_second": 1.697,
-    "predict_steps_per_second": 0.425
+    "predict_samples_per_second": 1.9,
+    "predict_steps_per_second": 0.38
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cdd5d2d6b1f790ba8029ee3d0d2f92b5ff5c26024e5d625575c2d93872259b0
+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_mos_fr_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": "mos/m2m100_mos_fr_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

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "train_loss": 1.6065418536846454,
-    "train_runtime": 357.1607,
+    "train_loss": 1.7082170156065206,
+    "train_runtime": 275.0373,
     "train_samples": 2287,
-    "train_samples_per_second": 19.21,
-    "train_steps_per_second": 4.805
+    "train_samples_per_second": 24.946,
+    "train_steps_per_second": 2.498
 }

trainer_state.json

@@ -2,42 +2,30 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 3.0,
-  "global_step": 1716,
+  "global_step": 687,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.87,
-      "learning_rate": 3.5431235431235434e-05,
-      "loss": 2.1646,
+      "epoch": 2.18,
+      "learning_rate": 1.3609898107714703e-05,
+      "loss": 1.8378,
       "step": 500
     },
-    {
-      "epoch": 1.75,
-      "learning_rate": 2.0862470862470865e-05,
-      "loss": 1.6097,
-      "step": 1000
-    },
-    {
-      "epoch": 2.62,
-      "learning_rate": 6.2937062937062944e-06,
-      "loss": 1.2439,
-      "step": 1500
-    },
     {
       "epoch": 3.0,
-      "step": 1716,
-      "total_flos": 1509394043781120.0,
-      "train_loss": 1.6065418536846454,
-      "train_runtime": 357.1607,
-      "train_samples_per_second": 19.21,
-      "train_steps_per_second": 4.805
+      "step": 687,
+      "total_flos": 1622235349991424.0,
+      "train_loss": 1.7082170156065206,
+      "train_runtime": 275.0373,
+      "train_samples_per_second": 24.946,
+      "train_steps_per_second": 2.498
     }
   ],
-  "max_steps": 1716,
+  "max_steps": 687,
   "num_train_epochs": 3,
-  "total_flos": 1509394043781120.0,
+  "total_flos": 1622235349991424.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e3d5e4c85f8068187aa2f97fec39dab16c6ad8ce8b7079da95a28c7fb98891
+oid sha256:30ef8562dd89c9fa13ee500d34fbd195a9e31c3d5c6ed98b6db63916988a2f19
 size 2799