Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +53 -0
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bigscience/bloom-3b",
|
| 3 |
+
"apply_residual_connection_post_layernorm": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"BloomForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"attention_softmax_in_fp32": true,
|
| 9 |
+
"bias_dropout_fusion": true,
|
| 10 |
+
"bos_token_id": 1,
|
| 11 |
+
"eos_token_id": 2,
|
| 12 |
+
"hidden_dropout": 0.0,
|
| 13 |
+
"hidden_size": 2560,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "Bedrohung",
|
| 16 |
+
"1": "Sonstiges",
|
| 17 |
+
"2": "Sexualdelikt",
|
| 18 |
+
"3": "Drogendelikt",
|
| 19 |
+
"4": "K\u00f6rperverletzung",
|
| 20 |
+
"5": "Diebstahl",
|
| 21 |
+
"6": "Raub",
|
| 22 |
+
"7": "T\u00f6tungsdelikt"
|
| 23 |
+
},
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"LABEL_0": 0,
|
| 27 |
+
"LABEL_1": 1,
|
| 28 |
+
"LABEL_2": 2,
|
| 29 |
+
"LABEL_3": 3,
|
| 30 |
+
"LABEL_4": 4,
|
| 31 |
+
"LABEL_5": 5,
|
| 32 |
+
"LABEL_6": 6,
|
| 33 |
+
"LABEL_7": 7
|
| 34 |
+
},
|
| 35 |
+
"layer_norm_epsilon": 1e-05,
|
| 36 |
+
"masked_softmax_fusion": true,
|
| 37 |
+
"model_type": "bloom",
|
| 38 |
+
"n_head": 32,
|
| 39 |
+
"n_inner": null,
|
| 40 |
+
"n_layer": 30,
|
| 41 |
+
"offset_alibi": 100,
|
| 42 |
+
"pad_token_id": 3,
|
| 43 |
+
"pretraining_tp": 4,
|
| 44 |
+
"problem_type": "multi_label_classification",
|
| 45 |
+
"skip_bias_add": true,
|
| 46 |
+
"skip_bias_add_qkv": false,
|
| 47 |
+
"slow_but_exact": false,
|
| 48 |
+
"torch_dtype": "float32",
|
| 49 |
+
"transformers_version": "4.26.0",
|
| 50 |
+
"unk_token_id": 0,
|
| 51 |
+
"use_cache": true,
|
| 52 |
+
"vocab_size": 250880
|
| 53 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1aca6507a669204dad8d822ee25edb5ac5539954032501c24f0f5ad21e290014
|
| 3 |
+
size 3515
|