Buckets:
| { | |
| "num_grads": 1, | |
| "dtype": { | |
| "names": [ | |
| "layers.0.self_attn.q_proj", | |
| "layers.0.self_attn.k_proj", | |
| "layers.0.self_attn.v_proj", | |
| "layers.0.self_attn.o_proj", | |
| "layers.0.mlp.gate_proj", | |
| "layers.0.mlp.up_proj", | |
| "layers.0.mlp.down_proj", | |
| "layers.1.self_attn.q_proj", | |
| "layers.1.self_attn.k_proj", | |
| "layers.1.self_attn.v_proj", | |
| "layers.1.self_attn.o_proj", | |
| "layers.1.mlp.gate_proj", | |
| "layers.1.mlp.up_proj", | |
| "layers.1.mlp.down_proj", | |
| "layers.2.self_attn.q_proj", | |
| "layers.2.self_attn.k_proj", | |
| "layers.2.self_attn.v_proj", | |
| "layers.2.self_attn.o_proj", | |
| "layers.2.mlp.gate_proj", | |
| "layers.2.mlp.up_proj", | |
| "layers.2.mlp.down_proj", | |
| "layers.3.self_attn.q_proj", | |
| "layers.3.self_attn.k_proj", | |
| "layers.3.self_attn.v_proj", | |
| "layers.3.self_attn.o_proj", | |
| "layers.3.mlp.gate_proj", | |
| "layers.3.mlp.up_proj", | |
| "layers.3.mlp.down_proj", | |
| "layers.4.self_attn.q_proj", | |
| "layers.4.self_attn.k_proj", | |
| "layers.4.self_attn.v_proj", | |
| "layers.4.self_attn.o_proj", | |
| "layers.4.mlp.gate_proj", | |
| "layers.4.mlp.up_proj", | |
| "layers.4.mlp.down_proj", | |
| "layers.5.self_attn.q_proj", | |
| "layers.5.self_attn.k_proj", | |
| "layers.5.self_attn.v_proj", | |
| "layers.5.self_attn.o_proj", | |
| "layers.5.mlp.gate_proj", | |
| "layers.5.mlp.up_proj", | |
| "layers.5.mlp.down_proj", | |
| "layers.6.self_attn.q_proj", | |
| "layers.6.self_attn.k_proj", | |
| "layers.6.self_attn.v_proj", | |
| "layers.6.self_attn.o_proj", | |
| "layers.6.mlp.gate_proj", | |
| "layers.6.mlp.up_proj", | |
| "layers.6.mlp.down_proj", | |
| "layers.7.self_attn.q_proj", | |
| "layers.7.self_attn.k_proj", | |
| "layers.7.self_attn.v_proj", | |
| "layers.7.self_attn.o_proj", | |
| "layers.7.mlp.gate_proj", | |
| "layers.7.mlp.up_proj", | |
| "layers.7.mlp.down_proj", | |
| "layers.8.self_attn.q_proj", | |
| "layers.8.self_attn.k_proj", | |
| "layers.8.self_attn.v_proj", | |
| "layers.8.self_attn.o_proj", | |
| "layers.8.mlp.gate_proj", | |
| "layers.8.mlp.up_proj", | |
| "layers.8.mlp.down_proj", | |
| "layers.9.self_attn.q_proj", | |
| "layers.9.self_attn.k_proj", | |
| "layers.9.self_attn.v_proj", | |
| "layers.9.self_attn.o_proj", | |
| "layers.9.mlp.gate_proj", | |
| "layers.9.mlp.up_proj", | |
| "layers.9.mlp.down_proj", | |
| "layers.10.self_attn.q_proj", | |
| "layers.10.self_attn.k_proj", | |
| "layers.10.self_attn.v_proj", | |
| "layers.10.self_attn.o_proj", | |
| "layers.10.mlp.gate_proj", | |
| "layers.10.mlp.up_proj", | |
| "layers.10.mlp.down_proj", | |
| "layers.11.self_attn.q_proj", | |
| "layers.11.self_attn.k_proj", | |
| "layers.11.self_attn.v_proj", | |
| "layers.11.self_attn.o_proj", | |
| "layers.11.mlp.gate_proj", | |
| "layers.11.mlp.up_proj", | |
| "layers.11.mlp.down_proj", | |
| "layers.12.self_attn.q_proj", | |
| "layers.12.self_attn.k_proj", | |
| "layers.12.self_attn.v_proj", | |
| "layers.12.self_attn.o_proj", | |
| "layers.12.mlp.gate_proj", | |
| "layers.12.mlp.up_proj", | |
| "layers.12.mlp.down_proj", | |
| "layers.13.self_attn.q_proj", | |
| "layers.13.self_attn.k_proj", | |
| "layers.13.self_attn.v_proj", | |
| "layers.13.self_attn.o_proj", | |
| "layers.13.mlp.gate_proj", | |
| "layers.13.mlp.up_proj", | |
| "layers.13.mlp.down_proj", | |
| "layers.14.self_attn.q_proj", | |
| "layers.14.self_attn.k_proj", | |
| "layers.14.self_attn.v_proj", | |
| "layers.14.self_attn.o_proj", | |
| "layers.14.mlp.gate_proj", | |
| "layers.14.mlp.up_proj", | |
| "layers.14.mlp.down_proj", | |
| "layers.15.self_attn.q_proj", | |
| "layers.15.self_attn.k_proj", | |
| "layers.15.self_attn.v_proj", | |
| "layers.15.self_attn.o_proj", | |
| "layers.15.mlp.gate_proj", | |
| "layers.15.mlp.up_proj", | |
| "layers.15.mlp.down_proj", | |
| "layers.16.self_attn.q_proj", | |
| "layers.16.self_attn.k_proj", | |
| "layers.16.self_attn.v_proj", | |
| "layers.16.self_attn.o_proj", | |
| "layers.16.mlp.gate_proj", | |
| "layers.16.mlp.up_proj", | |
| "layers.16.mlp.down_proj" | |
| ], | |
| "formats": [ | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4", | |
| "(256,)<f4" | |
| ], | |
| "itemsize": 121856 | |
| }, | |
| "grad_sizes": { | |
| "layers.0.self_attn.q_proj": 256, | |
| "layers.0.self_attn.k_proj": 256, | |
| "layers.0.self_attn.v_proj": 256, | |
| "layers.0.self_attn.o_proj": 256, | |
| "layers.0.mlp.gate_proj": 256, | |
| "layers.0.mlp.up_proj": 256, | |
| "layers.0.mlp.down_proj": 256, | |
| "layers.1.self_attn.q_proj": 256, | |
| "layers.1.self_attn.k_proj": 256, | |
| "layers.1.self_attn.v_proj": 256, | |
| "layers.1.self_attn.o_proj": 256, | |
| "layers.1.mlp.gate_proj": 256, | |
| "layers.1.mlp.up_proj": 256, | |
| "layers.1.mlp.down_proj": 256, | |
| "layers.2.self_attn.q_proj": 256, | |
| "layers.2.self_attn.k_proj": 256, | |
| "layers.2.self_attn.v_proj": 256, | |
| "layers.2.self_attn.o_proj": 256, | |
| "layers.2.mlp.gate_proj": 256, | |
| "layers.2.mlp.up_proj": 256, | |
| "layers.2.mlp.down_proj": 256, | |
| "layers.3.self_attn.q_proj": 256, | |
| "layers.3.self_attn.k_proj": 256, | |
| "layers.3.self_attn.v_proj": 256, | |
| "layers.3.self_attn.o_proj": 256, | |
| "layers.3.mlp.gate_proj": 256, | |
| "layers.3.mlp.up_proj": 256, | |
| "layers.3.mlp.down_proj": 256, | |
| "layers.4.self_attn.q_proj": 256, | |
| "layers.4.self_attn.k_proj": 256, | |
| "layers.4.self_attn.v_proj": 256, | |
| "layers.4.self_attn.o_proj": 256, | |
| "layers.4.mlp.gate_proj": 256, | |
| "layers.4.mlp.up_proj": 256, | |
| "layers.4.mlp.down_proj": 256, | |
| "layers.5.self_attn.q_proj": 256, | |
| "layers.5.self_attn.k_proj": 256, | |
| "layers.5.self_attn.v_proj": 256, | |
| "layers.5.self_attn.o_proj": 256, | |
| "layers.5.mlp.gate_proj": 256, | |
| "layers.5.mlp.up_proj": 256, | |
| "layers.5.mlp.down_proj": 256, | |
| "layers.6.self_attn.q_proj": 256, | |
| "layers.6.self_attn.k_proj": 256, | |
| "layers.6.self_attn.v_proj": 256, | |
| "layers.6.self_attn.o_proj": 256, | |
| "layers.6.mlp.gate_proj": 256, | |
| "layers.6.mlp.up_proj": 256, | |
| "layers.6.mlp.down_proj": 256, | |
| "layers.7.self_attn.q_proj": 256, | |
| "layers.7.self_attn.k_proj": 256, | |
| "layers.7.self_attn.v_proj": 256, | |
| "layers.7.self_attn.o_proj": 256, | |
| "layers.7.mlp.gate_proj": 256, | |
| "layers.7.mlp.up_proj": 256, | |
| "layers.7.mlp.down_proj": 256, | |
| "layers.8.self_attn.q_proj": 256, | |
| "layers.8.self_attn.k_proj": 256, | |
| "layers.8.self_attn.v_proj": 256, | |
| "layers.8.self_attn.o_proj": 256, | |
| "layers.8.mlp.gate_proj": 256, | |
| "layers.8.mlp.up_proj": 256, | |
| "layers.8.mlp.down_proj": 256, | |
| "layers.9.self_attn.q_proj": 256, | |
| "layers.9.self_attn.k_proj": 256, | |
| "layers.9.self_attn.v_proj": 256, | |
| "layers.9.self_attn.o_proj": 256, | |
| "layers.9.mlp.gate_proj": 256, | |
| "layers.9.mlp.up_proj": 256, | |
| "layers.9.mlp.down_proj": 256, | |
| "layers.10.self_attn.q_proj": 256, | |
| "layers.10.self_attn.k_proj": 256, | |
| "layers.10.self_attn.v_proj": 256, | |
| "layers.10.self_attn.o_proj": 256, | |
| "layers.10.mlp.gate_proj": 256, | |
| "layers.10.mlp.up_proj": 256, | |
| "layers.10.mlp.down_proj": 256, | |
| "layers.11.self_attn.q_proj": 256, | |
| "layers.11.self_attn.k_proj": 256, | |
| "layers.11.self_attn.v_proj": 256, | |
| "layers.11.self_attn.o_proj": 256, | |
| "layers.11.mlp.gate_proj": 256, | |
| "layers.11.mlp.up_proj": 256, | |
| "layers.11.mlp.down_proj": 256, | |
| "layers.12.self_attn.q_proj": 256, | |
| "layers.12.self_attn.k_proj": 256, | |
| "layers.12.self_attn.v_proj": 256, | |
| "layers.12.self_attn.o_proj": 256, | |
| "layers.12.mlp.gate_proj": 256, | |
| "layers.12.mlp.up_proj": 256, | |
| "layers.12.mlp.down_proj": 256, | |
| "layers.13.self_attn.q_proj": 256, | |
| "layers.13.self_attn.k_proj": 256, | |
| "layers.13.self_attn.v_proj": 256, | |
| "layers.13.self_attn.o_proj": 256, | |
| "layers.13.mlp.gate_proj": 256, | |
| "layers.13.mlp.up_proj": 256, | |
| "layers.13.mlp.down_proj": 256, | |
| "layers.14.self_attn.q_proj": 256, | |
| "layers.14.self_attn.k_proj": 256, | |
| "layers.14.self_attn.v_proj": 256, | |
| "layers.14.self_attn.o_proj": 256, | |
| "layers.14.mlp.gate_proj": 256, | |
| "layers.14.mlp.up_proj": 256, | |
| "layers.14.mlp.down_proj": 256, | |
| "layers.15.self_attn.q_proj": 256, | |
| "layers.15.self_attn.k_proj": 256, | |
| "layers.15.self_attn.v_proj": 256, | |
| "layers.15.self_attn.o_proj": 256, | |
| "layers.15.mlp.gate_proj": 256, | |
| "layers.15.mlp.up_proj": 256, | |
| "layers.15.mlp.down_proj": 256, | |
| "layers.16.self_attn.q_proj": 256, | |
| "layers.16.self_attn.k_proj": 256, | |
| "layers.16.self_attn.v_proj": 256, | |
| "layers.16.self_attn.o_proj": 256, | |
| "layers.16.mlp.gate_proj": 256, | |
| "layers.16.mlp.up_proj": 256, | |
| "layers.16.mlp.down_proj": 256 | |
| }, | |
| "base_dtype": "float32" | |
| } |
Xet Storage Details
- Size:
- 10.8 kB
- Xet hash:
- cb35c2edc40b1cb9153311c02b5ad9ca38757944a542a0e312f1ac3ad6f46b42
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.