Commit
•
1af527f
1
Parent(s):
4a723a2
Added a model and config
Browse files- config.json +43 -0
- eval_results.json +1 -0
- pytorch_model.bin +3 -0
- train_results.json +1 -0
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "albert-large-v2",
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"finetuning_task": "rte",
|
13 |
+
"gap_size": 0,
|
14 |
+
"hidden_act": "gelu_new",
|
15 |
+
"hidden_dropout_prob": 0,
|
16 |
+
"hidden_size": 1024,
|
17 |
+
"id2label": {
|
18 |
+
"0": "entailment",
|
19 |
+
"1": "not_entailment"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"inner_group_num": 1,
|
23 |
+
"intermediate_size": 4096,
|
24 |
+
"label2id": {
|
25 |
+
"entailment": 0,
|
26 |
+
"not_entailment": 1
|
27 |
+
},
|
28 |
+
"layer_norm_eps": 1e-12,
|
29 |
+
"max_position_embeddings": 512,
|
30 |
+
"model_type": "albert",
|
31 |
+
"net_structure_type": 0,
|
32 |
+
"num_attention_heads": 16,
|
33 |
+
"num_hidden_groups": 1,
|
34 |
+
"num_hidden_layers": 24,
|
35 |
+
"num_memory_blocks": 0,
|
36 |
+
"pad_token_id": 0,
|
37 |
+
"position_embedding_type": "absolute",
|
38 |
+
"problem_type": "single_label_classification",
|
39 |
+
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.26.0",
|
41 |
+
"type_vocab_size": 2,
|
42 |
+
"vocab_size": 30000
|
43 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eval_loss": 1.0776796340942383, "eval_accuracy": 0.8014440433212996, "eval_runtime": 1.9895, "eval_samples_per_second": 139.234, "eval_steps_per_second": 17.593}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a7920bf2beeb91f08c79d466e4977288401ddc36b8f55b996f4db4a1f0c3c6a
|
3 |
+
size 70757765
|
train_results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eval_loss": 0.01725384220480919, "eval_accuracy": 0.9971887550200803, "eval_runtime": 17.8511, "eval_samples_per_second": 139.487, "eval_steps_per_second": 17.478}
|