checkpoint: latest
Browse files- ema.safetensors +1 -1
- model.safetensors +1 -1
- optim.safetensors +1 -1
- state.json +209 -209
ema.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2046527448
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07ae88ff36ea2b12e1321412dedd203deaa9dfa1960c249914e25b4a0fb94212
|
| 3 |
size 2046527448
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2046527448
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63190eea327c9a6099e68f021edbb11979fc2d194a57ac315bc6333f9514b8bb
|
| 3 |
size 2046527448
|
optim.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4093066344
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b4c3e055b125d886f0c94b9f116a3b81fab8b5116abee1e5e0b4eede8c8b812
|
| 3 |
size 4093066344
|
state.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"step":
|
| 3 |
"run_history": [
|
| 4 |
{
|
| 5 |
"start_step": 0,
|
|
@@ -48,19 +48,19 @@
|
|
| 48 |
},
|
| 49 |
{
|
| 50 |
"start_step": 250000,
|
| 51 |
-
"end_step":
|
| 52 |
-
"seconds":
|
| 53 |
"world": 1,
|
| 54 |
"objective": "flow",
|
| 55 |
-
"completed":
|
| 56 |
-
"finished_at": "2026-07-
|
| 57 |
"effective": {
|
| 58 |
"lr": 9e-06,
|
| 59 |
"weight_decay": 0.1,
|
| 60 |
"clip": 0.5,
|
| 61 |
"spike_skip": 4.0,
|
| 62 |
-
"steps_skipped_this_run":
|
| 63 |
-
"steps_skipped_total":
|
| 64 |
"seed_offset": 797,
|
| 65 |
"grad_ceiling": 25.0
|
| 66 |
}
|
|
@@ -68,211 +68,211 @@
|
|
| 68 |
],
|
| 69 |
"guard_state": {
|
| 70 |
"version": 1,
|
| 71 |
-
"grad_ema":
|
| 72 |
"best_window": 0.7673007962107659,
|
| 73 |
"blown_windows": 0,
|
| 74 |
-
"spikes_total":
|
| 75 |
"recent_losses": [
|
| 76 |
-
0.
|
| 77 |
-
0.
|
| 78 |
-
0.
|
| 79 |
-
0.
|
| 80 |
-
0.
|
| 81 |
-
0.
|
| 82 |
-
0.
|
| 83 |
-
0.
|
| 84 |
-
0.
|
| 85 |
-
0.
|
| 86 |
-
0.
|
| 87 |
-
0.
|
| 88 |
-
0.
|
| 89 |
-
0.
|
| 90 |
-
0.
|
| 91 |
-
0.
|
| 92 |
-
0.
|
| 93 |
-
0.
|
| 94 |
-
0.
|
| 95 |
-
0.
|
| 96 |
-
0.
|
| 97 |
-
0.
|
| 98 |
-
0.
|
| 99 |
-
0.
|
| 100 |
-
0.
|
| 101 |
-
0.
|
| 102 |
-
0.
|
| 103 |
-
0.
|
| 104 |
-
0.
|
| 105 |
-
0.
|
| 106 |
-
0.
|
| 107 |
-
0.
|
| 108 |
-
0.
|
| 109 |
-
0.
|
| 110 |
-
0.
|
| 111 |
-
0.
|
| 112 |
-
0.
|
| 113 |
-
0.
|
| 114 |
-
0.
|
| 115 |
-
0.
|
| 116 |
-
0.
|
| 117 |
-
0.
|
| 118 |
-
0.
|
| 119 |
-
0.
|
| 120 |
-
0.
|
| 121 |
-
0.
|
| 122 |
-
0.
|
| 123 |
-
0.
|
| 124 |
-
0.
|
| 125 |
-
0.
|
| 126 |
-
0.
|
| 127 |
-
0.
|
| 128 |
-
0.
|
| 129 |
-
0.
|
| 130 |
-
0.
|
| 131 |
-
0.
|
| 132 |
-
0.
|
| 133 |
-
0.
|
| 134 |
-
0.
|
| 135 |
-
0.
|
| 136 |
-
0.
|
| 137 |
-
0.
|
| 138 |
-
0.
|
| 139 |
-
0.
|
| 140 |
-
0.
|
| 141 |
-
0.
|
| 142 |
-
0.
|
| 143 |
-
0.
|
| 144 |
-
0.
|
| 145 |
-
0.
|
| 146 |
-
0.
|
| 147 |
-
0.
|
| 148 |
-
0.
|
| 149 |
-
0.
|
| 150 |
-
0.
|
| 151 |
-
0.
|
| 152 |
-
0.
|
| 153 |
-
0.
|
| 154 |
-
0.
|
| 155 |
-
0.
|
| 156 |
-
0.
|
| 157 |
-
0.
|
| 158 |
-
0.
|
| 159 |
-
0.
|
| 160 |
-
0.
|
| 161 |
-
0.
|
| 162 |
-
0.
|
| 163 |
-
0.
|
| 164 |
-
0.
|
| 165 |
-
0.
|
| 166 |
-
0.
|
| 167 |
-
0.
|
| 168 |
-
0.
|
| 169 |
-
0.
|
| 170 |
-
0.
|
| 171 |
-
0.
|
| 172 |
-
0.
|
| 173 |
-
0.
|
| 174 |
-
0.
|
| 175 |
-
0.
|
| 176 |
-
0.
|
| 177 |
-
0.
|
| 178 |
-
0.
|
| 179 |
-
0.
|
| 180 |
-
0.
|
| 181 |
-
0.
|
| 182 |
-
0.
|
| 183 |
-
0.
|
| 184 |
-
0.
|
| 185 |
-
0.
|
| 186 |
-
0.
|
| 187 |
-
0.
|
| 188 |
-
0.
|
| 189 |
-
0.
|
| 190 |
-
0.
|
| 191 |
-
0.
|
| 192 |
-
0.
|
| 193 |
-
0.
|
| 194 |
-
0.
|
| 195 |
-
0.
|
| 196 |
-
0.
|
| 197 |
-
0.
|
| 198 |
-
0.
|
| 199 |
-
0.
|
| 200 |
-
0.
|
| 201 |
-
0.
|
| 202 |
-
0.
|
| 203 |
-
0.
|
| 204 |
-
0.
|
| 205 |
-
0.
|
| 206 |
-
0.
|
| 207 |
-
0.
|
| 208 |
-
0.
|
| 209 |
-
0.
|
| 210 |
-
0.
|
| 211 |
-
0.
|
| 212 |
-
0.
|
| 213 |
-
0.
|
| 214 |
-
0.
|
| 215 |
-
0.
|
| 216 |
-
0.
|
| 217 |
-
0.
|
| 218 |
-
0.
|
| 219 |
-
0.
|
| 220 |
-
0.
|
| 221 |
-
0.
|
| 222 |
-
0.
|
| 223 |
-
0.
|
| 224 |
-
0.
|
| 225 |
-
0.
|
| 226 |
-
0.
|
| 227 |
-
0.
|
| 228 |
-
0.
|
| 229 |
-
0.
|
| 230 |
-
0.
|
| 231 |
-
0.
|
| 232 |
-
0.
|
| 233 |
-
0.
|
| 234 |
-
0.
|
| 235 |
-
0.
|
| 236 |
-
0.
|
| 237 |
-
0.
|
| 238 |
-
0.
|
| 239 |
-
0.
|
| 240 |
-
0.
|
| 241 |
-
0.
|
| 242 |
-
0.
|
| 243 |
-
0.
|
| 244 |
-
0.
|
| 245 |
-
0.
|
| 246 |
-
0.
|
| 247 |
-
0.
|
| 248 |
-
0.
|
| 249 |
-
0.
|
| 250 |
-
0.
|
| 251 |
-
0.
|
| 252 |
-
0.
|
| 253 |
-
0.
|
| 254 |
-
0.
|
| 255 |
-
0.
|
| 256 |
-
0.
|
| 257 |
-
0.
|
| 258 |
-
0.
|
| 259 |
-
0.
|
| 260 |
-
0.
|
| 261 |
-
0.
|
| 262 |
-
0.
|
| 263 |
-
0.
|
| 264 |
-
0.
|
| 265 |
-
0.
|
| 266 |
-
0.
|
| 267 |
-
0.
|
| 268 |
-
0.
|
| 269 |
-
0.
|
| 270 |
-
0.
|
| 271 |
-
0.
|
| 272 |
-
0.
|
| 273 |
-
0.
|
| 274 |
-
0.
|
| 275 |
-
0.
|
| 276 |
],
|
| 277 |
"loss_window": 200,
|
| 278 |
"grad_ema_decay": 0.99,
|
|
|
|
| 1 |
{
|
| 2 |
+
"step": 268500,
|
| 3 |
"run_history": [
|
| 4 |
{
|
| 5 |
"start_step": 0,
|
|
|
|
| 48 |
},
|
| 49 |
{
|
| 50 |
"start_step": 250000,
|
| 51 |
+
"end_step": 268500,
|
| 52 |
+
"seconds": 3641.4,
|
| 53 |
"world": 1,
|
| 54 |
"objective": "flow",
|
| 55 |
+
"completed": true,
|
| 56 |
+
"finished_at": "2026-07-20T19:24:03.421837+00:00",
|
| 57 |
"effective": {
|
| 58 |
"lr": 9e-06,
|
| 59 |
"weight_decay": 0.1,
|
| 60 |
"clip": 0.5,
|
| 61 |
"spike_skip": 4.0,
|
| 62 |
+
"steps_skipped_this_run": 1524,
|
| 63 |
+
"steps_skipped_total": 1524,
|
| 64 |
"seed_offset": 797,
|
| 65 |
"grad_ceiling": 25.0
|
| 66 |
}
|
|
|
|
| 68 |
],
|
| 69 |
"guard_state": {
|
| 70 |
"version": 1,
|
| 71 |
+
"grad_ema": 15.717137627983812,
|
| 72 |
"best_window": 0.7673007962107659,
|
| 73 |
"blown_windows": 0,
|
| 74 |
+
"spikes_total": 1524,
|
| 75 |
"recent_losses": [
|
| 76 |
+
0.7936720848083496,
|
| 77 |
+
0.7588728070259094,
|
| 78 |
+
0.7741093635559082,
|
| 79 |
+
0.75559002161026,
|
| 80 |
+
0.7645204663276672,
|
| 81 |
+
0.7666345834732056,
|
| 82 |
+
0.7704269886016846,
|
| 83 |
+
0.7781091332435608,
|
| 84 |
+
0.7730302810668945,
|
| 85 |
+
0.7603114247322083,
|
| 86 |
+
0.7732800245285034,
|
| 87 |
+
0.7765823602676392,
|
| 88 |
+
0.7794618606567383,
|
| 89 |
+
0.7842772006988525,
|
| 90 |
+
0.7955668568611145,
|
| 91 |
+
0.7773451209068298,
|
| 92 |
+
0.7623429298400879,
|
| 93 |
+
0.7637821435928345,
|
| 94 |
+
0.7806098461151123,
|
| 95 |
+
0.776465892791748,
|
| 96 |
+
0.7606759667396545,
|
| 97 |
+
0.7766813039779663,
|
| 98 |
+
0.7805601954460144,
|
| 99 |
+
0.7664539813995361,
|
| 100 |
+
0.759924054145813,
|
| 101 |
+
0.7540620565414429,
|
| 102 |
+
0.7804937362670898,
|
| 103 |
+
0.7662051916122437,
|
| 104 |
+
0.7690973877906799,
|
| 105 |
+
0.7689259052276611,
|
| 106 |
+
0.7625908255577087,
|
| 107 |
+
0.7448180317878723,
|
| 108 |
+
0.7808000445365906,
|
| 109 |
+
0.7792022824287415,
|
| 110 |
+
0.7833995819091797,
|
| 111 |
+
0.7781939506530762,
|
| 112 |
+
0.7770954966545105,
|
| 113 |
+
0.7697976231575012,
|
| 114 |
+
0.7828700542449951,
|
| 115 |
+
0.7730734348297119,
|
| 116 |
+
0.7863974571228027,
|
| 117 |
+
0.7706713676452637,
|
| 118 |
+
0.7804528474807739,
|
| 119 |
+
0.7600006461143494,
|
| 120 |
+
0.7742743492126465,
|
| 121 |
+
0.7761899828910828,
|
| 122 |
+
0.7686344385147095,
|
| 123 |
+
0.777021050453186,
|
| 124 |
+
0.7725996971130371,
|
| 125 |
+
0.7655985951423645,
|
| 126 |
+
0.7711800336837769,
|
| 127 |
+
0.7703796625137329,
|
| 128 |
+
0.7760412096977234,
|
| 129 |
+
0.7780003547668457,
|
| 130 |
+
0.7732863426208496,
|
| 131 |
+
0.7671129703521729,
|
| 132 |
+
0.7740331888198853,
|
| 133 |
+
0.7815108299255371,
|
| 134 |
+
0.7702960968017578,
|
| 135 |
+
0.7741018533706665,
|
| 136 |
+
0.7991622090339661,
|
| 137 |
+
0.7838702201843262,
|
| 138 |
+
0.7850000262260437,
|
| 139 |
+
0.7512279748916626,
|
| 140 |
+
0.7830883264541626,
|
| 141 |
+
0.7534409165382385,
|
| 142 |
+
0.7679802775382996,
|
| 143 |
+
0.7755223512649536,
|
| 144 |
+
0.7854079008102417,
|
| 145 |
+
0.7704634666442871,
|
| 146 |
+
0.7841016054153442,
|
| 147 |
+
0.7742354869842529,
|
| 148 |
+
0.7610151767730713,
|
| 149 |
+
0.7823590040206909,
|
| 150 |
+
0.7707042694091797,
|
| 151 |
+
0.7765982151031494,
|
| 152 |
+
0.7615801095962524,
|
| 153 |
+
0.7593355774879456,
|
| 154 |
+
0.7461082935333252,
|
| 155 |
+
0.7753190994262695,
|
| 156 |
+
0.7651489973068237,
|
| 157 |
+
0.7638629674911499,
|
| 158 |
+
0.7589682340621948,
|
| 159 |
+
0.7903902530670166,
|
| 160 |
+
0.7727949619293213,
|
| 161 |
+
0.7708580493927002,
|
| 162 |
+
0.7890530824661255,
|
| 163 |
+
0.7685193419456482,
|
| 164 |
+
0.7818165421485901,
|
| 165 |
+
0.7797209024429321,
|
| 166 |
+
0.7784756422042847,
|
| 167 |
+
0.7626111507415771,
|
| 168 |
+
0.7819392085075378,
|
| 169 |
+
0.7750345468521118,
|
| 170 |
+
0.7650527358055115,
|
| 171 |
+
0.7836945056915283,
|
| 172 |
+
0.7931857109069824,
|
| 173 |
+
0.7828571200370789,
|
| 174 |
+
0.7660832405090332,
|
| 175 |
+
0.7655295133590698,
|
| 176 |
+
0.7835225462913513,
|
| 177 |
+
0.7785203456878662,
|
| 178 |
+
0.7902743816375732,
|
| 179 |
+
0.7815613150596619,
|
| 180 |
+
0.7764120101928711,
|
| 181 |
+
0.7681939601898193,
|
| 182 |
+
0.8005732297897339,
|
| 183 |
+
0.7677185535430908,
|
| 184 |
+
0.7844662666320801,
|
| 185 |
+
0.7703988552093506,
|
| 186 |
+
0.7761002779006958,
|
| 187 |
+
0.7866227030754089,
|
| 188 |
+
0.7621026039123535,
|
| 189 |
+
0.7633881568908691,
|
| 190 |
+
0.7618331909179688,
|
| 191 |
+
0.7567182779312134,
|
| 192 |
+
0.7694331407546997,
|
| 193 |
+
0.7767436504364014,
|
| 194 |
+
0.7602916359901428,
|
| 195 |
+
0.8021522760391235,
|
| 196 |
+
0.779279887676239,
|
| 197 |
+
0.7698382139205933,
|
| 198 |
+
0.7804439067840576,
|
| 199 |
+
0.7846136093139648,
|
| 200 |
+
0.7903976440429688,
|
| 201 |
+
0.7792932987213135,
|
| 202 |
+
0.7653769254684448,
|
| 203 |
+
0.7844459414482117,
|
| 204 |
+
0.7739591598510742,
|
| 205 |
+
0.7690120339393616,
|
| 206 |
+
0.7796692848205566,
|
| 207 |
+
0.7809997797012329,
|
| 208 |
+
0.7907922267913818,
|
| 209 |
+
0.7812246084213257,
|
| 210 |
+
0.7788326740264893,
|
| 211 |
+
0.7667310237884521,
|
| 212 |
+
0.7625054121017456,
|
| 213 |
+
0.7665765285491943,
|
| 214 |
+
0.7542004585266113,
|
| 215 |
+
0.7654911279678345,
|
| 216 |
+
0.7591631412506104,
|
| 217 |
+
0.7815473079681396,
|
| 218 |
+
0.7798547744750977,
|
| 219 |
+
0.7671359777450562,
|
| 220 |
+
0.7423914074897766,
|
| 221 |
+
0.7723144292831421,
|
| 222 |
+
0.751839280128479,
|
| 223 |
+
0.7665866613388062,
|
| 224 |
+
0.7698153257369995,
|
| 225 |
+
0.7849002480506897,
|
| 226 |
+
0.7617161870002747,
|
| 227 |
+
0.767459511756897,
|
| 228 |
+
0.7851784229278564,
|
| 229 |
+
0.7778003811836243,
|
| 230 |
+
0.7447282671928406,
|
| 231 |
+
0.7693464756011963,
|
| 232 |
+
0.7584735751152039,
|
| 233 |
+
0.7692090272903442,
|
| 234 |
+
0.7675624489784241,
|
| 235 |
+
0.7672569751739502,
|
| 236 |
+
0.779746413230896,
|
| 237 |
+
0.7516556978225708,
|
| 238 |
+
0.789167046546936,
|
| 239 |
+
0.7768017053604126,
|
| 240 |
+
0.7616105079650879,
|
| 241 |
+
0.7869294881820679,
|
| 242 |
+
0.7826142311096191,
|
| 243 |
+
0.7665939927101135,
|
| 244 |
+
0.773632824420929,
|
| 245 |
+
0.7709599733352661,
|
| 246 |
+
0.7925946712493896,
|
| 247 |
+
0.769508957862854,
|
| 248 |
+
0.7815218567848206,
|
| 249 |
+
0.7722813487052917,
|
| 250 |
+
0.7542710900306702,
|
| 251 |
+
0.7626035213470459,
|
| 252 |
+
0.7879314422607422,
|
| 253 |
+
0.7696739435195923,
|
| 254 |
+
0.7778429985046387,
|
| 255 |
+
0.7615687847137451,
|
| 256 |
+
0.7515759468078613,
|
| 257 |
+
0.7611167430877686,
|
| 258 |
+
0.7706644535064697,
|
| 259 |
+
0.7613785266876221,
|
| 260 |
+
0.7715133428573608,
|
| 261 |
+
0.7602030038833618,
|
| 262 |
+
0.7771657705307007,
|
| 263 |
+
0.7763781547546387,
|
| 264 |
+
0.7676988840103149,
|
| 265 |
+
0.7692828178405762,
|
| 266 |
+
0.7583136558532715,
|
| 267 |
+
0.7743930220603943,
|
| 268 |
+
0.767900288105011,
|
| 269 |
+
0.7607746720314026,
|
| 270 |
+
0.7840925455093384,
|
| 271 |
+
0.7737540006637573,
|
| 272 |
+
0.7772594690322876,
|
| 273 |
+
0.7726339101791382,
|
| 274 |
+
0.7622205018997192,
|
| 275 |
+
0.7752886414527893
|
| 276 |
],
|
| 277 |
"loss_window": 200,
|
| 278 |
"grad_ema_decay": 0.99,
|