Demetris
commited on
Commit
•
9e21167
1
Parent(s):
56e776d
Training in progress, step 500
Browse files
config.json
CHANGED
@@ -1,46 +1,27 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"_num_labels": 1,
|
4 |
-
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
6 |
-
"
|
7 |
],
|
8 |
-
"
|
9 |
-
"bos_token_id":
|
10 |
-
"
|
11 |
-
"eos_token_id":
|
12 |
-
"
|
13 |
-
|
14 |
-
|
15 |
"initializer_range": 0.02,
|
16 |
-
"
|
17 |
-
|
18 |
-
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"n_inner": null,
|
25 |
-
"n_layer": 6,
|
26 |
-
"n_positions": 1024,
|
27 |
-
"reorder_and_upcast_attn": false,
|
28 |
-
"resid_pdrop": 0.1,
|
29 |
-
"scale_attn_by_inverse_layer_idx": false,
|
30 |
-
"scale_attn_weights": true,
|
31 |
-
"summary_activation": null,
|
32 |
-
"summary_first_dropout": 0.1,
|
33 |
-
"summary_proj_to_labels": true,
|
34 |
-
"summary_type": "cls_index",
|
35 |
-
"summary_use_proj": true,
|
36 |
-
"task_specific_params": {
|
37 |
-
"text-generation": {
|
38 |
-
"do_sample": true,
|
39 |
-
"max_length": 50
|
40 |
-
}
|
41 |
-
},
|
42 |
"torch_dtype": "float32",
|
43 |
"transformers_version": "4.14.1",
|
|
|
44 |
"use_cache": true,
|
45 |
-
"vocab_size":
|
46 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "distilroberta-base",
|
|
|
|
|
3 |
"architectures": [
|
4 |
+
"RobertaForMaskedLM"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 6,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
"torch_dtype": "float32",
|
23 |
"transformers_version": "4.14.1",
|
24 |
+
"type_vocab_size": 1,
|
25 |
"use_cache": true,
|
26 |
+
"vocab_size": 50265
|
27 |
}
|
pytorch_model.bin
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 sha256:72eda5b2c71aab433dedca7a5cb84d33c18006bf42ef608638957f81d4dd225a
|
3 |
+
size 328727211
|
runs/Dec22_06-24-40_02af09eb9354/1640154770.2877538/events.out.tfevents.1640154770.02af09eb9354.73.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:315cad7e0a4d94a7d59ed3162ea2784147e25384e48838205c163ed19eee0784
|
3 |
+
size 4694
|
runs/Dec22_06-24-40_02af09eb9354/events.out.tfevents.1640154770.02af09eb9354.73.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c3351bf97d46e925872583073f56e3f66927b86f40ba7d42f66a2037e333572
|
3 |
+
size 3274
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2927
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c8a24a9c2f36f42ae2de9e0b79f71b497e4efb20f62aa429f9553572635a41d
|
3 |
size 2927
|