Training in progress, step 1000
Browse files
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "answerdotai/ModernBERT-large",
|
3 |
+
"architectures": [
|
4 |
+
"ModernBertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 50281,
|
9 |
+
"classifier_activation": "gelu",
|
10 |
+
"classifier_bias": false,
|
11 |
+
"classifier_dropout": 0.0,
|
12 |
+
"classifier_pooling": "mean",
|
13 |
+
"cls_token_id": 50281,
|
14 |
+
"decoder_bias": true,
|
15 |
+
"deterministic_flash_attn": false,
|
16 |
+
"embedding_dropout": 0.0,
|
17 |
+
"eos_token_id": 50282,
|
18 |
+
"global_attn_every_n_layers": 3,
|
19 |
+
"global_rope_theta": 160000.0,
|
20 |
+
"gradient_checkpointing": false,
|
21 |
+
"hidden_activation": "gelu",
|
22 |
+
"hidden_size": 1024,
|
23 |
+
"id2label": {
|
24 |
+
"0": "LABEL_0"
|
25 |
+
},
|
26 |
+
"initializer_cutoff_factor": 2.0,
|
27 |
+
"initializer_range": 0.02,
|
28 |
+
"intermediate_size": 2624,
|
29 |
+
"label2id": {
|
30 |
+
"LABEL_0": 0
|
31 |
+
},
|
32 |
+
"layer_norm_eps": 1e-05,
|
33 |
+
"local_attention": 128,
|
34 |
+
"local_rope_theta": 10000.0,
|
35 |
+
"max_position_embeddings": 8192,
|
36 |
+
"mlp_bias": false,
|
37 |
+
"mlp_dropout": 0.0,
|
38 |
+
"model_type": "modernbert",
|
39 |
+
"norm_bias": false,
|
40 |
+
"norm_eps": 1e-05,
|
41 |
+
"num_attention_heads": 16,
|
42 |
+
"num_hidden_layers": 28,
|
43 |
+
"pad_token_id": 50283,
|
44 |
+
"position_embedding_type": "absolute",
|
45 |
+
"problem_type": "regression",
|
46 |
+
"reference_compile": true,
|
47 |
+
"repad_logits_with_grad": false,
|
48 |
+
"sep_token_id": 50282,
|
49 |
+
"sparse_pred_ignore_index": -100,
|
50 |
+
"sparse_prediction": false,
|
51 |
+
"torch_dtype": "bfloat16",
|
52 |
+
"transformers_version": "4.48.0",
|
53 |
+
"vocab_size": 50368
|
54 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab5b0bdc436b400f21f7748697db6db2c15c86336c6610c62fd01b0c1039749f
|
3 |
+
size 791682922
|
runs/Jan16_11-43-20_8a29bcfa938d/events.out.tfevents.1737027801.8a29bcfa938d.1392.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad02f4bbaded434e7ee9ac7ad4690fb71d80fe9d1784ae378dc1613093a09abd
|
3 |
+
size 8275
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a4578da96483e686fa517b8720572a14145d2c38887218f0fd8e60553e2f7a6
|
3 |
+
size 5432
|