Training in progress, epoch 1
Browse files- config.json +46 -0
- model.safetensors +3 -0
- runs/Aug06_14-07-55_c267146fa9b5/events.out.tfevents.1754489276.c267146fa9b5.202.0 +3 -0
- runs/Aug06_14-12-22_c267146fa9b5/events.out.tfevents.1754489543.c267146fa9b5.202.1 +3 -0
- runs/Aug06_14-24-39_c267146fa9b5/events.out.tfevents.1754490283.c267146fa9b5.5407.0 +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"initializer_cutoff_factor": 2.0,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 1152,
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"local_attention": 128,
|
| 27 |
+
"local_rope_theta": 10000.0,
|
| 28 |
+
"max_position_embeddings": 8192,
|
| 29 |
+
"mlp_bias": false,
|
| 30 |
+
"mlp_dropout": 0.0,
|
| 31 |
+
"model_type": "modernbert",
|
| 32 |
+
"norm_bias": false,
|
| 33 |
+
"norm_eps": 1e-05,
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_hidden_layers": 22,
|
| 36 |
+
"pad_token_id": 50283,
|
| 37 |
+
"position_embedding_type": "absolute",
|
| 38 |
+
"problem_type": "single_label_classification",
|
| 39 |
+
"repad_logits_with_grad": false,
|
| 40 |
+
"sep_token_id": 50282,
|
| 41 |
+
"sparse_pred_ignore_index": -100,
|
| 42 |
+
"sparse_prediction": false,
|
| 43 |
+
"torch_dtype": "float32",
|
| 44 |
+
"transformers_version": "4.54.0",
|
| 45 |
+
"vocab_size": 50368
|
| 46 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47791efc48e102510c6ccd2a5431f85d3591ed1cbb23b587d63ff9baf4099aa3
|
| 3 |
+
size 598439784
|
runs/Aug06_14-07-55_c267146fa9b5/events.out.tfevents.1754489276.c267146fa9b5.202.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4924b87d5491658483e1404a48f39a5c4096526ee8c3e9547c298348b064ec54
|
| 3 |
+
size 4960
|
runs/Aug06_14-12-22_c267146fa9b5/events.out.tfevents.1754489543.c267146fa9b5.202.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6e8b244aac53cf9f15b1b32d0b2889d42aa50234829e9b5c36a3012c1bd916b
|
| 3 |
+
size 5167
|
runs/Aug06_14-24-39_c267146fa9b5/events.out.tfevents.1754490283.c267146fa9b5.5407.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69d6fce4edba382f8afd64627eb776705ad9bb4ac8141af485c7ac23e469c56c
|
| 3 |
+
size 6713
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c2ded1e56b501bc7c4d16e8da4d900640ab7947b9c89e72ce3d8be0cc9160b6
|
| 3 |
+
size 5368
|