Training in progress, epoch 1
Browse files- config.json +84 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"USSRewardModel"
|
| 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 |
+
"dtype": "float32",
|
| 16 |
+
"embedding_dropout": 0.0,
|
| 17 |
+
"eos_token_id": 50282,
|
| 18 |
+
"global_attn_every_n_layers": 3,
|
| 19 |
+
"gradient_checkpointing": false,
|
| 20 |
+
"hidden_activation": "gelu",
|
| 21 |
+
"hidden_size": 1024,
|
| 22 |
+
"initializer_cutoff_factor": 2.0,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 2624,
|
| 25 |
+
"layer_norm_eps": 1e-05,
|
| 26 |
+
"layer_types": [
|
| 27 |
+
"full_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"sliding_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"sliding_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"sliding_attention",
|
| 47 |
+
"sliding_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"sliding_attention",
|
| 50 |
+
"sliding_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"sliding_attention",
|
| 53 |
+
"sliding_attention",
|
| 54 |
+
"full_attention"
|
| 55 |
+
],
|
| 56 |
+
"local_attention": 128,
|
| 57 |
+
"max_position_embeddings": 8192,
|
| 58 |
+
"mlp_bias": false,
|
| 59 |
+
"mlp_dropout": 0.0,
|
| 60 |
+
"model_type": "modernbert",
|
| 61 |
+
"norm_bias": false,
|
| 62 |
+
"norm_eps": 1e-05,
|
| 63 |
+
"num_attention_heads": 16,
|
| 64 |
+
"num_hidden_layers": 28,
|
| 65 |
+
"pad_token_id": 50283,
|
| 66 |
+
"position_embedding_type": "absolute",
|
| 67 |
+
"rope_parameters": {
|
| 68 |
+
"full_attention": {
|
| 69 |
+
"rope_theta": 160000.0,
|
| 70 |
+
"rope_type": "default"
|
| 71 |
+
},
|
| 72 |
+
"sliding_attention": {
|
| 73 |
+
"rope_theta": 10000.0,
|
| 74 |
+
"rope_type": "default"
|
| 75 |
+
}
|
| 76 |
+
},
|
| 77 |
+
"sep_token_id": 50282,
|
| 78 |
+
"sparse_pred_ignore_index": -100,
|
| 79 |
+
"sparse_prediction": false,
|
| 80 |
+
"tie_word_embeddings": true,
|
| 81 |
+
"transformers_version": "5.9.0",
|
| 82 |
+
"use_cache": false,
|
| 83 |
+
"vocab_size": 50368
|
| 84 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f170f7a724409b52c80cf7f108e5017b17c78d4ac6401c648521e4562c39c069
|
| 3 |
+
size 1583347572
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9307b334d3c661f7cc86476730cdafafd11fccd0e7c83a88ab1c7400b9c6d4a0
|
| 3 |
+
size 5393
|