add model
Browse files- config.json +78 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "backup/snowy-yogurt-6/",
|
| 3 |
+
"adapt_attn_span": 32,
|
| 4 |
+
"adapt_bs": 384,
|
| 5 |
+
"adapt_dynamic": false,
|
| 6 |
+
"adapt_nb_heads": 12,
|
| 7 |
+
"adapt_reg": false,
|
| 8 |
+
"adapt_span_cache": false,
|
| 9 |
+
"adapt_span_loss_coeff": 0.01,
|
| 10 |
+
"adapt_span_ramp": 16,
|
| 11 |
+
"architectures": [
|
| 12 |
+
"BertModel"
|
| 13 |
+
],
|
| 14 |
+
"attention_probs_dropout_prob": 0.05,
|
| 15 |
+
"attention_probs_dropout_prob_noise": 0.155,
|
| 16 |
+
"attention_probs_dropout_prob_reference": 0.1,
|
| 17 |
+
"classifier_dropout": null,
|
| 18 |
+
"dynamic_ramp": false,
|
| 19 |
+
"gradient_checkpointing": false,
|
| 20 |
+
"hack": false,
|
| 21 |
+
"headmask": 0.0,
|
| 22 |
+
"hidden_act": "gelu",
|
| 23 |
+
"hidden_dropout_prob": 0.05,
|
| 24 |
+
"hidden_dropout_prob_noise": 0.155,
|
| 25 |
+
"hidden_dropout_prob_reference": 0.1,
|
| 26 |
+
"hidden_size": 768,
|
| 27 |
+
"initializer_range": 0.02,
|
| 28 |
+
"intermediate_size": 3072,
|
| 29 |
+
"layer_norm_eps": 1e-12,
|
| 30 |
+
"layerdrop": 0.0,
|
| 31 |
+
"layerdrop_dynamic": false,
|
| 32 |
+
"layerdrop_manifold": null,
|
| 33 |
+
"layerdrop_noise": false,
|
| 34 |
+
"layerdrop_noise_std": 0.1,
|
| 35 |
+
"max_position_embeddings": 512,
|
| 36 |
+
"mixup": false,
|
| 37 |
+
"mixup_highest_layer": 12,
|
| 38 |
+
"mixup_index": -99,
|
| 39 |
+
"mixup_lowest_layer": 9,
|
| 40 |
+
"mixup_manifold": null,
|
| 41 |
+
"mixup_noise": false,
|
| 42 |
+
"mixup_rate": [
|
| 43 |
+
0.0,
|
| 44 |
+
0.0,
|
| 45 |
+
0.0
|
| 46 |
+
],
|
| 47 |
+
"mixup_same_sample": false,
|
| 48 |
+
"mixup_samples": [
|
| 49 |
+
0,
|
| 50 |
+
1,
|
| 51 |
+
1
|
| 52 |
+
],
|
| 53 |
+
"mixup_strategy1": [
|
| 54 |
+
0,
|
| 55 |
+
1,
|
| 56 |
+
0
|
| 57 |
+
],
|
| 58 |
+
"mixup_strategy2": [
|
| 59 |
+
0,
|
| 60 |
+
0,
|
| 61 |
+
0
|
| 62 |
+
],
|
| 63 |
+
"model_type": "bert",
|
| 64 |
+
"multi_dropout": false,
|
| 65 |
+
"num_attention_heads": 12,
|
| 66 |
+
"num_hidden_layers": 12,
|
| 67 |
+
"pad_token_id": 0,
|
| 68 |
+
"position_embedding_type": "absolute",
|
| 69 |
+
"single_dropout": false,
|
| 70 |
+
"task_alpha": 1.0,
|
| 71 |
+
"task_beta": 1.05,
|
| 72 |
+
"task_lambda": 0.013,
|
| 73 |
+
"torch_dtype": "float32",
|
| 74 |
+
"transformers_version": "4.10.0.dev0",
|
| 75 |
+
"type_vocab_size": 2,
|
| 76 |
+
"use_cache": true,
|
| 77 |
+
"vocab_size": 30522
|
| 78 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7e84cdf9ea91450f3f498b48c1e098837eabd64d0b5c47e41722212b193e84a
|
| 3 |
+
size 438005297
|