Training in progress, epoch 0

config.json

@@ -6,31 +6,31 @@
   ],
   "decoder": {
     "_name_or_path": "",
-    "activation_dropout": 0.2,
+    "activation_dropout": 0.0,
     "activation_function": "gelu",
     "add_cross_attention": true,
     "add_final_layer_norm": true,
     "architectures": null,
-    "attention_dropout": 0.2,
+    "attention_dropout": 0.0,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
     "bos_token_id": 0,
     "chunk_size_feed_forward": 0,
-    "classifier_dropout": 0.2,
+    "classifier_dropout": 0.0,
     "cross_attention_hidden_size": null,
     "d_model": 1024,
     "decoder_attention_heads": 16,
     "decoder_ffn_dim": 4096,
-    "decoder_layerdrop": 0.2,
+    "decoder_layerdrop": 0.0,
     "decoder_layers": 4,
     "decoder_start_token_id": null,
     "diversity_penalty": 0.0,
     "do_sample": false,
-    "dropout": 0.2,
+    "dropout": 0.1,
     "early_stopping": false,
     "encoder_attention_heads": 16,
     "encoder_ffn_dim": 4096,
-    "encoder_layerdrop": 0.2,
+    "encoder_layerdrop": 0.0,
     "encoder_layers": 12,
     "encoder_no_repeat_ngram_size": 0,
     "eos_token_id": 2,
@@ -94,7 +94,7 @@
     "_name_or_path": "",
     "add_cross_attention": false,
     "architectures": null,
-    "attention_probs_dropout_prob": 0.2,
+    "attention_probs_dropout_prob": 0.0,
     "bad_words_ids": null,
     "begin_suppress_tokens": null,
     "bos_token_id": null,
@@ -119,7 +119,7 @@
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
     "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.2,
+    "hidden_dropout_prob": 0.0,
     "hidden_size": 1024,
     "id2label": {
       "0": "LABEL_0",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c172633c0ac980eb070090ae86d4bb83f354094b07a255c67397702c095e9206
+oid sha256:dccf107f3c24acbb028775dbeaa3726da6846fa60b7bd9e0684fadf748eba8a3
 size 806283643