File size: 1,289 Bytes
2a10ae7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 | {
"checkpoint_load": {
"mae": {
"matched_tensor_keys": 142,
"missing_locpath_weights": 0,
"unexpected_weights": 0,
"loaded_values_match_export": true,
"query_shape": [
128,
512
]
},
"stage1": {
"matched_tensor_keys": 148,
"missing_locpath_weights": 0,
"unexpected_weights": 0,
"loaded_values_match_export": true,
"query_shape": [
128,
512
]
},
"stage2": {
"matched_tensor_keys": 540,
"missing_locpath_weights": 0,
"unexpected_weights": 0,
"loaded_values_match_export": true,
"query_shape": [
128,
512
]
}
},
"tensor_export": {
"finite": true,
"tensor_only_roundtrip": true,
"stored_dtype": "float16",
"resampler_query_shape": [
128,
512
]
},
"trained_model_inference": {
"predictions": 2,
"tasks": [
"1_Report_test.json",
"bcnb_choice_test.json"
],
"all_outputs_nonempty": true,
"base_model": "Qwen/Qwen2.5-7B-Instruct",
"torch_dtype": "bfloat16",
"quantization": "NF4",
"feature_sampling_limit": 1024,
"resampler_latents": 128,
"router_top_m": 96,
"max_new_tokens": 96,
"full_benchmark_rerun": false
}
}
|