Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/m2m100_418M",
+  "_name_or_path": "facebook/m2m100_1.2B",
   "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
@@ -9,16 +9,16 @@
   "bos_token_id": 0,
   "d_model": 1024,
   "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
+  "decoder_ffn_dim": 8192,
   "decoder_layerdrop": 0.05,
-  "decoder_layers": 12,
+  "decoder_layers": 24,
   "decoder_start_token_id": 2,
   "dropout": 0.1,
   "early_stopping": true,
   "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
+  "encoder_ffn_dim": 8192,
   "encoder_layerdrop": 0.05,
-  "encoder_layers": 12,
+  "encoder_layers": 24,
   "eos_token_id": 2,
   "forced_bos_token_id": 128022,
   "gradient_checkpointing": false,
@@ -28,11 +28,11 @@
   "max_position_embeddings": 1024,
   "model_type": "m2m_100",
   "num_beams": 5,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 24,
   "pad_token_id": 1,
   "scale_embedding": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.18.0",
+  "transformers_version": "4.18.0.dev0",
   "use_cache": true,
   "vocab_size": 128112
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fba6c1253e442e893cd60b63c70ba4ce6978d82ee77c7b8094e7395025dfd9a
-size 1935792071
+oid sha256:b9947b8b5a068f73ad78bcaa58cd519759ff5fb59accd23ea862a1252b3a5367
+size 4958263232

tokenizer_config.json

@@ -1 +1 @@
-{"src_lang": "ar", "tgt_lang": "en", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "language_codes": "m2m100", "sp_model_kwargs": {}, "num_madeup_words": 8, "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"}
+{"src_lang": "ar", "tgt_lang": "en", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "language_codes": "m2m100", "sp_model_kwargs": {}, "num_madeup_words": 8, "special_tokens_map_file": "m2m_100_1.2B_v2/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "facebook/m2m100_1.2B", "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"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:290a3ec8e4a00bf17415b185b45b42159aedae0468de6031dc5bb125935c70b9
+oid sha256:c432d08394b68e456ece46effbfaf78e141925537b6432cf8807638b073fea5b
 size 3183