Training in progress, epoch 2
Browse files
config.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"ModernBertForSequenceClassification"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 50281,
|
8 |
+
"classifier_activation": "gelu",
|
9 |
+
"classifier_bias": false,
|
10 |
+
"classifier_dropout": 0.0,
|
11 |
+
"classifier_pooling": "mean",
|
12 |
+
"cls_token_id": 50281,
|
13 |
+
"decoder_bias": true,
|
14 |
+
"deterministic_flash_attn": false,
|
15 |
+
"embedding_dropout": 0.0,
|
16 |
+
"eos_token_id": 50282,
|
17 |
+
"global_attn_every_n_layers": 3,
|
18 |
+
"global_rope_theta": 160000.0,
|
19 |
+
"gradient_checkpointing": false,
|
20 |
+
"hidden_activation": "gelu",
|
21 |
+
"hidden_size": 768,
|
22 |
+
"id2label": {
|
23 |
+
"0": "small_llm",
|
24 |
+
"1": "large_llm"
|
25 |
+
},
|
26 |
+
"initializer_cutoff_factor": 2.0,
|
27 |
+
"initializer_range": 0.02,
|
28 |
+
"intermediate_size": 1152,
|
29 |
+
"label2id": {
|
30 |
+
"large_llm": "1",
|
31 |
+
"small_llm": "0"
|
32 |
+
},
|
33 |
+
"layer_norm_eps": 1e-05,
|
34 |
+
"local_attention": 128,
|
35 |
+
"local_rope_theta": 10000.0,
|
36 |
+
"max_position_embeddings": 8192,
|
37 |
+
"mlp_bias": false,
|
38 |
+
"mlp_dropout": 0.0,
|
39 |
+
"model_type": "modernbert",
|
40 |
+
"norm_bias": false,
|
41 |
+
"norm_eps": 1e-05,
|
42 |
+
"num_attention_heads": 12,
|
43 |
+
"num_hidden_layers": 22,
|
44 |
+
"pad_token_id": 50283,
|
45 |
+
"position_embedding_type": "absolute",
|
46 |
+
"problem_type": "single_label_classification",
|
47 |
+
"repad_logits_with_grad": false,
|
48 |
+
"sep_token_id": 50282,
|
49 |
+
"sparse_pred_ignore_index": -100,
|
50 |
+
"sparse_prediction": false,
|
51 |
+
"torch_dtype": "float32",
|
52 |
+
"transformers_version": "4.51.3",
|
53 |
+
"vocab_size": 50368
|
54 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6397345f37734906f8f71aa97b368b29e0f72a089167d9d3fc2f166deef8fb9
|
3 |
+
size 598439784
|
runs/Jul26_18-31-33_4f4f5c2af2ac/events.out.tfevents.1753554694.4f4f5c2af2ac.16006.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6986ee52394abc0033cc01e1ba8d339fdabf7a34a729af61eb36828ff0a245e3
|
3 |
+
size 8221
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5617a83cff9472eac47e8896316fc066b849f0703431216e319e327574987b81
|
3 |
+
size 5368
|