grt-30m-mor / eval_results.json
davidhouseholter's picture
Release MatterWaveAI/grt-30m-mor (4-expert Mixture-of-Rotations, 0 nn.Linear layers)
0c8dbfe verified
Raw History Blame Contribute Delete
4.3 kB
{
"model_id": "MatterWaveAI/grt-30m-mor",
"architecture": "GRTForCausalLM (Mixture-of-Rotations)",
"base_model": "MatterWaveAI/grt-30m",
"parameters": 31634086,
"base_parameters": 29305498,
"ffn_n_experts": 4,
"mor_mode": "direct",
"mor_router_mode": "rotational",
"nn_linear_layers": 0,
"before_upcycle_specialization": {
"val_loss": 5.8467,
"val_ppl": 346.102,
"domain_val_loss": {
"code_and_algorithms": 5.4092,
"reasoning_and_language": 6.172,
"rotational_geometry": 6.6421,
"science_and_physics": 5.3337
}
},
"after_upcycle_specialization": {
"val_loss": 0.5115,
"val_ppl": 1.6678,
"domain_val_loss": {
"code_and_algorithms": 0.4334,
"reasoning_and_language": 0.6442,
"rotational_geometry": 0.4991,
"science_and_physics": 0.5293
},
"router_diagnostics": [
{
"layer": 0,
"mean_expert_probs": [
0.2494,
0.2488,
0.253,
0.2487
],
"marginal_entropy": 1.3863,
"mean_top1_confidence": 0.2545,
"expert_angle_l2_divergence": 2.5326
},
{
"layer": 1,
"mean_expert_probs": [
0.2492,
0.247,
0.2574,
0.2464
],
"marginal_entropy": 1.3861,
"mean_top1_confidence": 0.2599,
"expert_angle_l2_divergence": 2.5353
},
{
"layer": 2,
"mean_expert_probs": [
0.2526,
0.2482,
0.2528,
0.2465
],
"marginal_entropy": 1.3862,
"mean_top1_confidence": 0.2541,
"expert_angle_l2_divergence": 2.5524
},
{
"layer": 3,
"mean_expert_probs": [
0.251,
0.2486,
0.2548,
0.2457
],
"marginal_entropy": 1.3862,
"mean_top1_confidence": 0.2559,
"expert_angle_l2_divergence": 2.5425
},
{
"layer": 4,
"mean_expert_probs": [
0.2511,
0.2486,
0.2562,
0.2441
],
"marginal_entropy": 1.3861,
"mean_top1_confidence": 0.2586,
"expert_angle_l2_divergence": 2.5487
},
{
"layer": 5,
"mean_expert_probs": [
0.2508,
0.2485,
0.2572,
0.2436
],
"marginal_entropy": 1.3861,
"mean_top1_confidence": 0.26,
"expert_angle_l2_divergence": 2.5342
},
{
"layer": 6,
"mean_expert_probs": [
0.2504,
0.2486,
0.2571,
0.2439
],
"marginal_entropy": 1.3861,
"mean_top1_confidence": 0.2602,
"expert_angle_l2_divergence": 2.5501
},
{
"layer": 7,
"mean_expert_probs": [
0.251,
0.2488,
0.2567,
0.2435
],
"marginal_entropy": 1.3861,
"mean_top1_confidence": 0.2592,
"expert_angle_l2_divergence": 2.5291
},
{
"layer": 8,
"mean_expert_probs": [
0.2506,
0.2461,
0.2605,
0.2427
],
"marginal_entropy": 1.3859,
"mean_top1_confidence": 0.2658,
"expert_angle_l2_divergence": 2.5455
},
{
"layer": 9,
"mean_expert_probs": [
0.2502,
0.247,
0.2582,
0.2445
],
"marginal_entropy": 1.3861,
"mean_top1_confidence": 0.2647,
"expert_angle_l2_divergence": 2.5364
},
{
"layer": 10,
"mean_expert_probs": [
0.2501,
0.2484,
0.2563,
0.2452
],
"marginal_entropy": 1.3862,
"mean_top1_confidence": 0.2636,
"expert_angle_l2_divergence": 2.5368
},
{
"layer": 11,
"mean_expert_probs": [
0.2509,
0.2481,
0.256,
0.245
],
"marginal_entropy": 1.3862,
"mean_top1_confidence": 0.2588,
"expert_angle_l2_divergence": 2.524
}
]
}
}