Cahya Wirawan
commited on
Commit
•
10b22bf
1
Parent(s):
163eb96
trained another 12 epochs
Browse files- config.json +17 -5
- pytorch_model.bin +1 -1
config.json
CHANGED
|
@@ -13,6 +13,7 @@
|
|
| 13 |
"bos_token_id": null,
|
| 14 |
"chunk_size_feed_forward": 0,
|
| 15 |
"decoder_start_token_id": null,
|
|
|
|
| 16 |
"do_sample": false,
|
| 17 |
"early_stopping": false,
|
| 18 |
"eos_token_id": null,
|
|
@@ -41,16 +42,20 @@
|
|
| 41 |
"model_type": "bert",
|
| 42 |
"no_repeat_ngram_size": 0,
|
| 43 |
"num_attention_heads": 12,
|
|
|
|
| 44 |
"num_beams": 1,
|
| 45 |
"num_hidden_layers": 12,
|
| 46 |
"num_return_sequences": 1,
|
| 47 |
"output_attentions": false,
|
| 48 |
"output_hidden_states": false,
|
|
|
|
| 49 |
"pad_token_id": 0,
|
|
|
|
| 50 |
"prefix": null,
|
| 51 |
"pruned_heads": {},
|
| 52 |
"repetition_penalty": 1.0,
|
| 53 |
-
"return_dict":
|
|
|
|
| 54 |
"sep_token_id": null,
|
| 55 |
"task_specific_params": null,
|
| 56 |
"temperature": 1.0,
|
|
@@ -60,6 +65,7 @@
|
|
| 60 |
"top_k": 50,
|
| 61 |
"top_p": 1.0,
|
| 62 |
"torchscript": false,
|
|
|
|
| 63 |
"type_vocab_size": 2,
|
| 64 |
"use_bfloat16": false,
|
| 65 |
"use_cache": true,
|
|
@@ -79,6 +85,7 @@
|
|
| 79 |
"bos_token_id": null,
|
| 80 |
"chunk_size_feed_forward": 0,
|
| 81 |
"decoder_start_token_id": null,
|
|
|
|
| 82 |
"do_sample": false,
|
| 83 |
"early_stopping": false,
|
| 84 |
"eos_token_id": null,
|
|
@@ -107,16 +114,20 @@
|
|
| 107 |
"model_type": "bert",
|
| 108 |
"no_repeat_ngram_size": 0,
|
| 109 |
"num_attention_heads": 12,
|
|
|
|
| 110 |
"num_beams": 1,
|
| 111 |
"num_hidden_layers": 12,
|
| 112 |
"num_return_sequences": 1,
|
| 113 |
"output_attentions": false,
|
| 114 |
"output_hidden_states": false,
|
|
|
|
| 115 |
"pad_token_id": 0,
|
|
|
|
| 116 |
"prefix": null,
|
| 117 |
"pruned_heads": {},
|
| 118 |
"repetition_penalty": 1.0,
|
| 119 |
-
"return_dict":
|
|
|
|
| 120 |
"sep_token_id": null,
|
| 121 |
"task_specific_params": null,
|
| 122 |
"temperature": 1.0,
|
|
@@ -126,6 +137,7 @@
|
|
| 126 |
"top_k": 50,
|
| 127 |
"top_p": 1.0,
|
| 128 |
"torchscript": false,
|
|
|
|
| 129 |
"type_vocab_size": 2,
|
| 130 |
"use_bfloat16": false,
|
| 131 |
"use_cache": true,
|
|
@@ -135,11 +147,11 @@
|
|
| 135 |
"eos_token_id": 1,
|
| 136 |
"is_encoder_decoder": true,
|
| 137 |
"length_penalty": 2.0,
|
| 138 |
-
"max_length":
|
| 139 |
-
"min_length":
|
| 140 |
"model_type": "encoder-decoder",
|
| 141 |
"no_repeat_ngram_size": 3,
|
| 142 |
-
"num_beams":
|
| 143 |
"pad_token_id": 2,
|
| 144 |
"vocab_size": 32000
|
| 145 |
}
|
| 13 |
"bos_token_id": null,
|
| 14 |
"chunk_size_feed_forward": 0,
|
| 15 |
"decoder_start_token_id": null,
|
| 16 |
+
"diversity_penalty": 0.0,
|
| 17 |
"do_sample": false,
|
| 18 |
"early_stopping": false,
|
| 19 |
"eos_token_id": null,
|
| 42 |
"model_type": "bert",
|
| 43 |
"no_repeat_ngram_size": 0,
|
| 44 |
"num_attention_heads": 12,
|
| 45 |
+
"num_beam_groups": 1,
|
| 46 |
"num_beams": 1,
|
| 47 |
"num_hidden_layers": 12,
|
| 48 |
"num_return_sequences": 1,
|
| 49 |
"output_attentions": false,
|
| 50 |
"output_hidden_states": false,
|
| 51 |
+
"output_scores": false,
|
| 52 |
"pad_token_id": 0,
|
| 53 |
+
"position_embedding_type": "absolute",
|
| 54 |
"prefix": null,
|
| 55 |
"pruned_heads": {},
|
| 56 |
"repetition_penalty": 1.0,
|
| 57 |
+
"return_dict": true,
|
| 58 |
+
"return_dict_in_generate": false,
|
| 59 |
"sep_token_id": null,
|
| 60 |
"task_specific_params": null,
|
| 61 |
"temperature": 1.0,
|
| 65 |
"top_k": 50,
|
| 66 |
"top_p": 1.0,
|
| 67 |
"torchscript": false,
|
| 68 |
+
"transformers_version": "4.2.2",
|
| 69 |
"type_vocab_size": 2,
|
| 70 |
"use_bfloat16": false,
|
| 71 |
"use_cache": true,
|
| 85 |
"bos_token_id": null,
|
| 86 |
"chunk_size_feed_forward": 0,
|
| 87 |
"decoder_start_token_id": null,
|
| 88 |
+
"diversity_penalty": 0.0,
|
| 89 |
"do_sample": false,
|
| 90 |
"early_stopping": false,
|
| 91 |
"eos_token_id": null,
|
| 114 |
"model_type": "bert",
|
| 115 |
"no_repeat_ngram_size": 0,
|
| 116 |
"num_attention_heads": 12,
|
| 117 |
+
"num_beam_groups": 1,
|
| 118 |
"num_beams": 1,
|
| 119 |
"num_hidden_layers": 12,
|
| 120 |
"num_return_sequences": 1,
|
| 121 |
"output_attentions": false,
|
| 122 |
"output_hidden_states": false,
|
| 123 |
+
"output_scores": false,
|
| 124 |
"pad_token_id": 0,
|
| 125 |
+
"position_embedding_type": "absolute",
|
| 126 |
"prefix": null,
|
| 127 |
"pruned_heads": {},
|
| 128 |
"repetition_penalty": 1.0,
|
| 129 |
+
"return_dict": true,
|
| 130 |
+
"return_dict_in_generate": false,
|
| 131 |
"sep_token_id": null,
|
| 132 |
"task_specific_params": null,
|
| 133 |
"temperature": 1.0,
|
| 137 |
"top_k": 50,
|
| 138 |
"top_p": 1.0,
|
| 139 |
"torchscript": false,
|
| 140 |
+
"transformers_version": "4.2.2",
|
| 141 |
"type_vocab_size": 2,
|
| 142 |
"use_bfloat16": false,
|
| 143 |
"use_cache": true,
|
| 147 |
"eos_token_id": 1,
|
| 148 |
"is_encoder_decoder": true,
|
| 149 |
"length_penalty": 2.0,
|
| 150 |
+
"max_length": 40,
|
| 151 |
+
"min_length": 20,
|
| 152 |
"model_type": "encoder-decoder",
|
| 153 |
"no_repeat_ngram_size": 3,
|
| 154 |
+
"num_beams": 10,
|
| 155 |
"pad_token_id": 2,
|
| 156 |
"vocab_size": 32000
|
| 157 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 998778130
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bce5258851b5aae797fd0ff45c1d52ce82105493144b1eaff6d0eb880b8d592c
|
| 3 |
size 998778130
|