Training in progress, epoch 1
Browse files
config.json
ADDED
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4",
|
17 |
+
"5": "LABEL_5",
|
18 |
+
"6": "LABEL_6",
|
19 |
+
"7": "LABEL_7",
|
20 |
+
"8": "LABEL_8",
|
21 |
+
"9": "LABEL_9",
|
22 |
+
"10": "LABEL_10",
|
23 |
+
"11": "LABEL_11",
|
24 |
+
"12": "LABEL_12",
|
25 |
+
"13": "LABEL_13",
|
26 |
+
"14": "LABEL_14",
|
27 |
+
"15": "LABEL_15",
|
28 |
+
"16": "LABEL_16",
|
29 |
+
"17": "LABEL_17",
|
30 |
+
"18": "LABEL_18",
|
31 |
+
"19": "LABEL_19",
|
32 |
+
"20": "LABEL_20",
|
33 |
+
"21": "LABEL_21",
|
34 |
+
"22": "LABEL_22",
|
35 |
+
"23": "LABEL_23",
|
36 |
+
"24": "LABEL_24",
|
37 |
+
"25": "LABEL_25",
|
38 |
+
"26": "LABEL_26",
|
39 |
+
"27": "LABEL_27",
|
40 |
+
"28": "LABEL_28",
|
41 |
+
"29": "LABEL_29",
|
42 |
+
"30": "LABEL_30",
|
43 |
+
"31": "LABEL_31",
|
44 |
+
"32": "LABEL_32",
|
45 |
+
"33": "LABEL_33",
|
46 |
+
"34": "LABEL_34",
|
47 |
+
"35": "LABEL_35"
|
48 |
+
},
|
49 |
+
"initializer_range": 0.02,
|
50 |
+
"label2id": {
|
51 |
+
"LABEL_0": 0,
|
52 |
+
"LABEL_1": 1,
|
53 |
+
"LABEL_10": 10,
|
54 |
+
"LABEL_11": 11,
|
55 |
+
"LABEL_12": 12,
|
56 |
+
"LABEL_13": 13,
|
57 |
+
"LABEL_14": 14,
|
58 |
+
"LABEL_15": 15,
|
59 |
+
"LABEL_16": 16,
|
60 |
+
"LABEL_17": 17,
|
61 |
+
"LABEL_18": 18,
|
62 |
+
"LABEL_19": 19,
|
63 |
+
"LABEL_2": 2,
|
64 |
+
"LABEL_20": 20,
|
65 |
+
"LABEL_21": 21,
|
66 |
+
"LABEL_22": 22,
|
67 |
+
"LABEL_23": 23,
|
68 |
+
"LABEL_24": 24,
|
69 |
+
"LABEL_25": 25,
|
70 |
+
"LABEL_26": 26,
|
71 |
+
"LABEL_27": 27,
|
72 |
+
"LABEL_28": 28,
|
73 |
+
"LABEL_29": 29,
|
74 |
+
"LABEL_3": 3,
|
75 |
+
"LABEL_30": 30,
|
76 |
+
"LABEL_31": 31,
|
77 |
+
"LABEL_32": 32,
|
78 |
+
"LABEL_33": 33,
|
79 |
+
"LABEL_34": 34,
|
80 |
+
"LABEL_35": 35,
|
81 |
+
"LABEL_4": 4,
|
82 |
+
"LABEL_5": 5,
|
83 |
+
"LABEL_6": 6,
|
84 |
+
"LABEL_7": 7,
|
85 |
+
"LABEL_8": 8,
|
86 |
+
"LABEL_9": 9
|
87 |
+
},
|
88 |
+
"max_position_embeddings": 512,
|
89 |
+
"model_type": "distilbert",
|
90 |
+
"n_heads": 12,
|
91 |
+
"n_layers": 6,
|
92 |
+
"pad_token_id": 0,
|
93 |
+
"problem_type": "single_label_classification",
|
94 |
+
"qa_dropout": 0.1,
|
95 |
+
"seq_classif_dropout": 0.2,
|
96 |
+
"sinusoidal_pos_embds": false,
|
97 |
+
"tie_weights_": true,
|
98 |
+
"torch_dtype": "float32",
|
99 |
+
"transformers_version": "4.36.2",
|
100 |
+
"vocab_size": 30522
|
101 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c294138b9069ee3bc5cab9aa16eb20ec977fc4934a711bbdc5a0f5e3a137aafd
|
3 |
+
size 267937160
|
runs/Sep26_17-20-07_Jons-MBP.cable.rcn.com/events.out.tfevents.1727385608.Jons-MBP.cable.rcn.com.3395.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45170212f6c94aa8cd0fc7d6db4acaccc5e4ccef6139af7671eedbe1351c3d42
|
3 |
+
size 6085
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03f64dbd3027811c4d04638345c3c0743836b8668c5527b0d7105f21989a5b5d
|
3 |
+
size 4664
|