Training in progress, epoch 1
Browse files
config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "answerdotai/ModernBERT-base",
|
| 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": 768,
|
| 23 |
+
"id2label": {
|
| 24 |
+
"0": "small_llm",
|
| 25 |
+
"1": "large_llm"
|
| 26 |
+
},
|
| 27 |
+
"initializer_cutoff_factor": 2.0,
|
| 28 |
+
"initializer_range": 0.02,
|
| 29 |
+
"intermediate_size": 1152,
|
| 30 |
+
"label2id": {
|
| 31 |
+
"large_llm": "1",
|
| 32 |
+
"small_llm": "0"
|
| 33 |
+
},
|
| 34 |
+
"layer_norm_eps": 1e-05,
|
| 35 |
+
"local_attention": 128,
|
| 36 |
+
"local_rope_theta": 10000.0,
|
| 37 |
+
"max_position_embeddings": 8192,
|
| 38 |
+
"mlp_bias": false,
|
| 39 |
+
"mlp_dropout": 0.0,
|
| 40 |
+
"model_type": "modernbert",
|
| 41 |
+
"norm_bias": false,
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"num_attention_heads": 12,
|
| 44 |
+
"num_hidden_layers": 22,
|
| 45 |
+
"pad_token_id": 50283,
|
| 46 |
+
"position_embedding_type": "absolute",
|
| 47 |
+
"problem_type": "single_label_classification",
|
| 48 |
+
"reference_compile": true,
|
| 49 |
+
"sep_token_id": 50282,
|
| 50 |
+
"sparse_pred_ignore_index": -100,
|
| 51 |
+
"sparse_prediction": false,
|
| 52 |
+
"torch_dtype": "bfloat16",
|
| 53 |
+
"transformers_version": "4.48.0.dev0",
|
| 54 |
+
"vocab_size": 50368
|
| 55 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4111e6c60629efd33d17d737eade2f63685091bfdb2f673766b19ee995b5e97
|
| 3 |
+
size 299227092
|
runs/Dec26_20-28-58_f736eda2583b/events.out.tfevents.1735244945.f736eda2583b.7973.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddb76ff808e36f2eb19c3029db708e6af6e85655971548b90103b3dd32775c2f
|
| 3 |
+
size 13365
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a9641f1bd3c2b259e2ee0c3c88d4384e19f747fb321c21ccae0baf9d2810c04
|
| 3 |
+
size 5368
|