Files
phonebabylm-phone-deu-eng-s…/training_metadata.json
ModelHub XC 545953eeab 初始化项目,由ModelHub XC社区提供模型
Model: nikitastheo/phonebabylm-phone-deu-eng-sequential_interleaved
Source: Original Platform
2026-08-21 19:39:17 +08:00

74 lines
976 B
JSON

{
"input_config": {
"model_type": "gpt2",
"architectures": [
"GPT2LMHeadModel"
],
"activation_function": "gelu",
"attn_pdrop": 0.1,
"embd_pdrop": 0.1,
"resid_pdrop": 0.1,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"n_embd": 768,
"n_inner": 3072,
"n_head": 12,
"n_layer": 12,
"vocab_size": 1,
"n_ctx": 512,
"n_positions": 512
},
"num_steps_switch": 10000,
"save_steps": [
1,
2,
4,
8,
16,
32,
64,
128,
256,
512,
1000,
2000,
3000,
4000,
5000,
6000,
7000,
8000,
9000,
10000,
10001,
10002,
10004,
10008,
10016,
10032,
10064,
10128,
10256,
10512,
11000,
12000,
13000,
14000,
15000,
16000,
17000,
18000,
19000,
20000,
21000,
22000,
23000,
24000,
25000,
26000,
27000,
28000,
29000,
30000
]
}