Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +199 -0
- lora_rank_128_mlp_H200/checkpoint_epoch_0497/control_params.pt +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_002000_sample02.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_002000_sample03.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_004000.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_004000_sample02.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_006000.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_006000_sample02.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_006000_sample03.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_006000_sample04.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_010000_sample00.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_010000_sample02.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_010000_sample04.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_011999.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_011999_sample00.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_013999_sample02.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_013999_sample03.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_013999_sample04.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_015999.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_015999_sample00.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_015999_sample04.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_017999.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_017999_sample01.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_017999_sample03.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_017999_sample04.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_019999.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_0_step_019999_sample02.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_000000.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_000000_sample01.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_000000_sample02.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_000000_sample03.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_002000_sample02.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_002000_sample03.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_004000_sample02.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_006000_sample01.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_010000_sample00.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_010000_sample01.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_010000_sample02.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_010000_sample03.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_013999_sample01.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_015999_sample02.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_017999_sample01.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_017999_sample03.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_017999_sample04.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_019999.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_019999_sample03.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_1_step_019999_sample04.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_2_step_000000_sample01.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_2_step_000000_sample03.png +3 -0
- lora_rank_128_mlp_H200/step_vis/test_2_step_000000_sample04.png +3 -0
.gitattributes
CHANGED
|
@@ -4270,3 +4270,202 @@ lora_rank_128_mlp_H200/step_vis/val_1_step_006000.png filter=lfs diff=lfs merge=
|
|
| 4270 |
lora_rank_128_mlp_H200/step_vis/train_0_step_017999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4271 |
lora_rank_128_mlp_H200/step_vis/val_1_step_015999_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4272 |
lora_rank_128_mlp_H200/step_vis/train_1_step_004000.png filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4270 |
lora_rank_128_mlp_H200/step_vis/train_0_step_017999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4271 |
lora_rank_128_mlp_H200/step_vis/val_1_step_015999_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4272 |
lora_rank_128_mlp_H200/step_vis/train_1_step_004000.png filter=lfs diff=lfs merge=lfs -text
|
| 4273 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_013999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4274 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_006000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4275 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_013999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4276 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_019999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4277 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_000000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4278 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_000000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4279 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_011999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4280 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_010000.png filter=lfs diff=lfs merge=lfs -text
|
| 4281 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_006000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4282 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_019999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4283 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_002000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4284 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_006000.png filter=lfs diff=lfs merge=lfs -text
|
| 4285 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_004000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4286 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_013999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4287 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_004000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4288 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_015999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4289 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_010000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4290 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_017999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4291 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_017999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4292 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_017999.png filter=lfs diff=lfs merge=lfs -text
|
| 4293 |
+
lora_rank_128_mlp_H200/step_vis/train_1_step_004000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4294 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_000000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4295 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_013999_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4296 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_000000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4297 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_002000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4298 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_017999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4299 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_008000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4300 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_002000.png filter=lfs diff=lfs merge=lfs -text
|
| 4301 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_017999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4302 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_019999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4303 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_000000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4304 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_019999.png filter=lfs diff=lfs merge=lfs -text
|
| 4305 |
+
lora_rank_128_mlp_H200/step_vis/train_1_step_011999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4306 |
+
lora_rank_128_mlp_H200/step_vis/train_1_step_002000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4307 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_010000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4308 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_015999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4309 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_010000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4310 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_010000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4311 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_011999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4312 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_006000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4313 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_010000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4314 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_013999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4315 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_004000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4316 |
+
lora_rank_128_mlp_H200/step_vis/train_1_step_002000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4317 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_000000.png filter=lfs diff=lfs merge=lfs -text
|
| 4318 |
+
lora_rank_128_mlp_H200/step_vis/val_0_step_017999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4319 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_015999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4320 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_019999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4321 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_010000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4322 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_015999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4323 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_000000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4324 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_006000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4325 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_019999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4326 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_008000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4327 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_019999.png filter=lfs diff=lfs merge=lfs -text
|
| 4328 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_006000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4329 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_004000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4330 |
+
lora_rank_128_mlp_H200/step_vis/train_1_step_008000.png filter=lfs diff=lfs merge=lfs -text
|
| 4331 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_010000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4332 |
+
lora_rank_128_mlp_H200/step_vis/val_0_step_008000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4333 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_006000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4334 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_002000.png filter=lfs diff=lfs merge=lfs -text
|
| 4335 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_019999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4336 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_013999_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4337 |
+
lora_rank_128_mlp_H200/step_vis/val_0_step_000000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4338 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_000000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4339 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_013999.png filter=lfs diff=lfs merge=lfs -text
|
| 4340 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_015999_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4341 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_006000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4342 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_004000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4343 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_015999.png filter=lfs diff=lfs merge=lfs -text
|
| 4344 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_006000.png filter=lfs diff=lfs merge=lfs -text
|
| 4345 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_011999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4346 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_015999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4347 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_010000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4348 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_013999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4349 |
+
lora_rank_128_mlp_H200/step_vis/val_0_step_006000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4350 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_004000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4351 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_011999.png filter=lfs diff=lfs merge=lfs -text
|
| 4352 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_006000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4353 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_011999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4354 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_004000.png filter=lfs diff=lfs merge=lfs -text
|
| 4355 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_017999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4356 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_019999_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4357 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_004000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4358 |
+
lora_rank_128_mlp_H200/step_vis/val_0_step_015999.png filter=lfs diff=lfs merge=lfs -text
|
| 4359 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_006000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4360 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_000000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4361 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_017999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4362 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_011999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4363 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_013999_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4364 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_017999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4365 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_017999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4366 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_015999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4367 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_013999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4368 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_000000.png filter=lfs diff=lfs merge=lfs -text
|
| 4369 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_004000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4370 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_017999_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4371 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_017999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4372 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_010000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4373 |
+
lora_rank_128_mlp_H200/step_vis/train_1_step_013999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4374 |
+
lora_rank_128_mlp_H200/step_vis/val_0_step_013999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4375 |
+
lora_rank_128_mlp_H200/step_vis/train_1_step_000000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4376 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_017999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4377 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_015999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4378 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_015999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4379 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_010000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4380 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_000000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4381 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_011999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4382 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_011999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4383 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_000000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4384 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_010000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4385 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_004000.png filter=lfs diff=lfs merge=lfs -text
|
| 4386 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_008000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4387 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_000000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4388 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_000000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4389 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_002000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4390 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_006000.png filter=lfs diff=lfs merge=lfs -text
|
| 4391 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_011999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4392 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_011999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4393 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_013999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4394 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_015999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4395 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_017999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4396 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_006000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4397 |
+
lora_rank_128_mlp_H200/step_vis/val_0_step_013999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4398 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_010000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4399 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_013999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4400 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_008000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4401 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_015999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4402 |
+
lora_rank_128_mlp_H200/step_vis/train_1_step_017999.png filter=lfs diff=lfs merge=lfs -text
|
| 4403 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_019999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4404 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_006000.png filter=lfs diff=lfs merge=lfs -text
|
| 4405 |
+
lora_rank_128_mlp_H200/step_vis/val_0_step_000000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4406 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_015999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4407 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_006000.png filter=lfs diff=lfs merge=lfs -text
|
| 4408 |
+
lora_rank_128_mlp_H200/step_vis/val_0_step_013999_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4409 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_017999_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4410 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_002000.png filter=lfs diff=lfs merge=lfs -text
|
| 4411 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_000000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4412 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_002000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4413 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_006000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4414 |
+
lora_rank_128_mlp_H200/step_vis/train_1_step_019999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4415 |
+
lora_rank_128_mlp_H200/step_vis/train_1_step_017999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4416 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_002000.png filter=lfs diff=lfs merge=lfs -text
|
| 4417 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_017999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4418 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_015999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4419 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_019999.png filter=lfs diff=lfs merge=lfs -text
|
| 4420 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_013999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4421 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_000000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4422 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_000000.png filter=lfs diff=lfs merge=lfs -text
|
| 4423 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_004000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4424 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_010000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4425 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_002000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4426 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_017999.png filter=lfs diff=lfs merge=lfs -text
|
| 4427 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_011999_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4428 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_015999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4429 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_006000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4430 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_010000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4431 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_000000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4432 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_019999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4433 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_010000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4434 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_017999.png filter=lfs diff=lfs merge=lfs -text
|
| 4435 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_011999_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4436 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_002000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4437 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_013999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4438 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_002000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4439 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_002000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4440 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_013999.png filter=lfs diff=lfs merge=lfs -text
|
| 4441 |
+
lora_rank_128_mlp_H200/step_vis/train_1_step_015999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4442 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_006000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4443 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_019999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4444 |
+
lora_rank_128_mlp_H200/step_vis/val_0_step_006000.png filter=lfs diff=lfs merge=lfs -text
|
| 4445 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_011999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4446 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_004000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4447 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_011999_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4448 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_011999_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4449 |
+
lora_rank_128_mlp_H200/step_vis/train_1_step_002000.png filter=lfs diff=lfs merge=lfs -text
|
| 4450 |
+
lora_rank_128_mlp_H200/step_vis/train_1_step_015999.png filter=lfs diff=lfs merge=lfs -text
|
| 4451 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_019999.png filter=lfs diff=lfs merge=lfs -text
|
| 4452 |
+
lora_rank_128_mlp_H200/step_vis/test_2_step_008000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4453 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_008000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4454 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_011999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4455 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_006000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4456 |
+
lora_rank_128_mlp_H200/step_vis/val_0_step_004000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4457 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_017999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4458 |
+
lora_rank_128_mlp_H200/step_vis/train_1_step_019999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4459 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_010000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4460 |
+
lora_rank_128_mlp_H200/step_vis/val_0_step_015999_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4461 |
+
lora_rank_128_mlp_H200/step_vis/test_4_step_015999.png filter=lfs diff=lfs merge=lfs -text
|
| 4462 |
+
lora_rank_128_mlp_H200/step_vis/val_1_step_010000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4463 |
+
lora_rank_128_mlp_H200/step_vis/val_0_step_019999_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4464 |
+
lora_rank_128_mlp_H200/step_vis/val_0_step_010000_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4465 |
+
lora_rank_128_mlp_H200/step_vis/test_3_step_011999_sample00.png filter=lfs diff=lfs merge=lfs -text
|
| 4466 |
+
lora_rank_128_mlp_H200/step_vis/test_5_step_010000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4467 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_000000_sample03.png filter=lfs diff=lfs merge=lfs -text
|
| 4468 |
+
lora_rank_128_mlp_H200/step_vis/test_1_step_002000_sample02.png filter=lfs diff=lfs merge=lfs -text
|
| 4469 |
+
lora_rank_128_mlp_H200/step_vis/train_1_step_006000_sample04.png filter=lfs diff=lfs merge=lfs -text
|
| 4470 |
+
lora_rank_128_mlp_H200/step_vis/test_0_step_017999_sample01.png filter=lfs diff=lfs merge=lfs -text
|
| 4471 |
+
lora_rank_128_mlp_H200/step_vis/train_0_step_006000_sample01.png filter=lfs diff=lfs merge=lfs -text
|
lora_rank_128_mlp_H200/checkpoint_epoch_0497/control_params.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04dac662e4e125b52ab72c88b3ae3da78da16979be49899c69be8a00092214a5
|
| 3 |
+
size 8345739463
|
lora_rank_128_mlp_H200/step_vis/test_0_step_002000_sample02.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_002000_sample03.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_004000.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_004000_sample02.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_006000.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_006000_sample02.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_006000_sample03.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_006000_sample04.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_010000_sample00.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_010000_sample02.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_010000_sample04.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_011999.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_011999_sample00.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_013999_sample02.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_013999_sample03.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_013999_sample04.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_015999.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_015999_sample00.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_015999_sample04.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_017999.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_017999_sample01.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_017999_sample03.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_017999_sample04.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_019999.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_0_step_019999_sample02.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_000000.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_000000_sample01.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_000000_sample02.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_000000_sample03.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_002000_sample02.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_002000_sample03.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_004000_sample02.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_006000_sample01.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_010000_sample00.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_010000_sample01.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_010000_sample02.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_010000_sample03.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_013999_sample01.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_015999_sample02.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_017999_sample01.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_017999_sample03.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_017999_sample04.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_019999.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_019999_sample03.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_1_step_019999_sample04.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_2_step_000000_sample01.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_2_step_000000_sample03.png
ADDED
|
Git LFS Details
|
lora_rank_128_mlp_H200/step_vis/test_2_step_000000_sample04.png
ADDED
|
Git LFS Details
|