Training in progress epoch 0
Browse files- config.json +2 -9
- model.safetensors +2 -2
- special_tokens_map.json +6 -42
config.json
CHANGED
|
@@ -1,9 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"_num_labels": 3,
|
| 4 |
"activation_dropout": 0.0,
|
| 5 |
"activation_function": "gelu",
|
| 6 |
-
"add_bias_logits": false,
|
| 7 |
"add_final_layer_norm": false,
|
| 8 |
"architectures": [
|
| 9 |
"BartForConditionalGeneration"
|
|
@@ -16,7 +15,7 @@
|
|
| 16 |
"decoder_attention_heads": 16,
|
| 17 |
"decoder_ffn_dim": 4096,
|
| 18 |
"decoder_layerdrop": 0.0,
|
| 19 |
-
"decoder_layers":
|
| 20 |
"decoder_start_token_id": 2,
|
| 21 |
"dropout": 0.1,
|
| 22 |
"early_stopping": true,
|
|
@@ -25,7 +24,6 @@
|
|
| 25 |
"encoder_layerdrop": 0.0,
|
| 26 |
"encoder_layers": 12,
|
| 27 |
"eos_token_id": 2,
|
| 28 |
-
"extra_pos_embeddings": 2,
|
| 29 |
"force_bos_token_to_be_generated": true,
|
| 30 |
"forced_bos_token_id": 0,
|
| 31 |
"forced_eos_token_id": 2,
|
|
@@ -49,17 +47,12 @@
|
|
| 49 |
"model_type": "bart",
|
| 50 |
"no_repeat_ngram_size": 3,
|
| 51 |
"normalize_before": false,
|
| 52 |
-
"normalize_embedding": true,
|
| 53 |
"num_beams": 4,
|
| 54 |
"num_hidden_layers": 12,
|
| 55 |
"output_past": true,
|
| 56 |
"pad_token_id": 1,
|
| 57 |
"prefix": " ",
|
| 58 |
-
"replacing_rate": 0,
|
| 59 |
"scale_embedding": false,
|
| 60 |
-
"static_position_embeddings": false,
|
| 61 |
-
"student_decoder_layers": null,
|
| 62 |
-
"student_encoder_layers": null,
|
| 63 |
"task_specific_params": {
|
| 64 |
"summarization": {
|
| 65 |
"early_stopping": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "facebook/bart-large-cnn",
|
| 3 |
"_num_labels": 3,
|
| 4 |
"activation_dropout": 0.0,
|
| 5 |
"activation_function": "gelu",
|
|
|
|
| 6 |
"add_final_layer_norm": false,
|
| 7 |
"architectures": [
|
| 8 |
"BartForConditionalGeneration"
|
|
|
|
| 15 |
"decoder_attention_heads": 16,
|
| 16 |
"decoder_ffn_dim": 4096,
|
| 17 |
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 12,
|
| 19 |
"decoder_start_token_id": 2,
|
| 20 |
"dropout": 0.1,
|
| 21 |
"early_stopping": true,
|
|
|
|
| 24 |
"encoder_layerdrop": 0.0,
|
| 25 |
"encoder_layers": 12,
|
| 26 |
"eos_token_id": 2,
|
|
|
|
| 27 |
"force_bos_token_to_be_generated": true,
|
| 28 |
"forced_bos_token_id": 0,
|
| 29 |
"forced_eos_token_id": 2,
|
|
|
|
| 47 |
"model_type": "bart",
|
| 48 |
"no_repeat_ngram_size": 3,
|
| 49 |
"normalize_before": false,
|
|
|
|
| 50 |
"num_beams": 4,
|
| 51 |
"num_hidden_layers": 12,
|
| 52 |
"output_past": true,
|
| 53 |
"pad_token_id": 1,
|
| 54 |
"prefix": " ",
|
|
|
|
| 55 |
"scale_embedding": false,
|
|
|
|
|
|
|
|
|
|
| 56 |
"task_specific_params": {
|
| 57 |
"summarization": {
|
| 58 |
"early_stopping": true,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c177451cf192fb0ca020c7b1d509659aac9c849fc09730ddb74e2bf9e288c417
|
| 3 |
+
size 1625422896
|
special_tokens_map.json
CHANGED
|
@@ -1,25 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
"normalized": true,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"cls_token": {
|
| 10 |
-
"content": "<s>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": true,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"eos_token": {
|
| 17 |
-
"content": "</s>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": true,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
},
|
| 23 |
"mask_token": {
|
| 24 |
"content": "<mask>",
|
| 25 |
"lstrip": true,
|
|
@@ -27,25 +9,7 @@
|
|
| 27 |
"rstrip": false,
|
| 28 |
"single_word": false
|
| 29 |
},
|
| 30 |
-
"pad_token":
|
| 31 |
-
|
| 32 |
-
|
| 33 |
-
"normalized": true,
|
| 34 |
-
"rstrip": false,
|
| 35 |
-
"single_word": false
|
| 36 |
-
},
|
| 37 |
-
"sep_token": {
|
| 38 |
-
"content": "</s>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": true,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false
|
| 43 |
-
},
|
| 44 |
-
"unk_token": {
|
| 45 |
-
"content": "<unk>",
|
| 46 |
-
"lstrip": false,
|
| 47 |
-
"normalized": true,
|
| 48 |
-
"rstrip": false,
|
| 49 |
-
"single_word": false
|
| 50 |
-
}
|
| 51 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"mask_token": {
|
| 6 |
"content": "<mask>",
|
| 7 |
"lstrip": true,
|
|
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
}
|