Jakub
67061cf373
Document six completed LR runs as preparation for full Aya training on Perun. Record selection of LR 0.00010 by lowest final validation loss, selected-model lm-eval and partial SK-bench results, reproducible provenance, and dataset-access/context-truncation limitations. Preserve existing 30k and Titan material.
31 lines
684 B
JSON
31 lines
684 B
JSON
{
|
|
"architectures": [
|
|
"MistralForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"bos_token_id": 1,
|
|
"dtype": "bfloat16",
|
|
"eos_token_id": 2,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 4096,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 14336,
|
|
"max_position_embeddings": 32768,
|
|
"model_type": "mistral",
|
|
"num_attention_heads": 32,
|
|
"num_hidden_layers": 32,
|
|
"num_key_value_heads": 8,
|
|
"pad_token_id": 2,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_parameters": {
|
|
"rope_theta": 10000.0,
|
|
"rope_type": "default"
|
|
},
|
|
"sliding_window": 4096,
|
|
"tie_word_embeddings": false,
|
|
"transformers_version": "5.5.0",
|
|
"use_cache": true,
|
|
"vocab_size": 32000
|
|
}
|