mikhail-panzo commited on
Commit
407dcb8
1 Parent(s): 87b5d4c

Training in progress, step 8000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f03919594e15aa04dbb8008cf60a2a2d5b89be3490f892590197689b8410a661
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffb0581c87a9b4ec4bd9bc79bf4d20868fe5ba52b951178a641df208a7d8c1f1
3
  size 577789320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77e4c693ccaf9249bd98af9f184a00d5eb2f36b77cb0e433fbc26661d80daa72
3
  size 1155772233
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4348e5123797554906c7c2b1912fadc1c7517cd97cfa9d8e744ff152c29d9f62
3
  size 1155772233
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d880acef54d4eb61cf44bc2962e1f38bf44896cefc09a0303d9df0b77a1ae5c2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:012ecd1edf495661a426a7c3c4b090d5e2901f554832bf1d246a4e516cd8c109
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5cdfe5ed4f14bdadfee62402701e9c3c91a7e1b8246c7c7f0be536b67574fb3
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:797161cb36b8434a2e9b424b1551b1d663e1ac4112ca3f634c3c132aead6996b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.3158954679965973,
3
- "best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-7500",
4
- "epoch": 12.565445026178011,
5
  "eval_steps": 500,
6
- "global_step": 7500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1177,6 +1177,84 @@
1177
  "eval_samples_per_second": 31.284,
1178
  "eval_steps_per_second": 3.914,
1179
  "step": 7500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1180
  }
1181
  ],
1182
  "logging_steps": 50,
@@ -1191,12 +1269,12 @@
1191
  "should_evaluate": false,
1192
  "should_log": false,
1193
  "should_save": true,
1194
- "should_training_stop": false
1195
  },
1196
  "attributes": {}
1197
  }
1198
  },
1199
- "total_flos": 1.3437364892618304e+17,
1200
  "train_batch_size": 16,
1201
  "trial_name": null,
1202
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.31398773193359375,
3
+ "best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-8000",
4
+ "epoch": 13.403141361256544,
5
  "eval_steps": 500,
6
+ "global_step": 8000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1177
  "eval_samples_per_second": 31.284,
1178
  "eval_steps_per_second": 3.914,
1179
  "step": 7500
1180
+ },
1181
+ {
1182
+ "epoch": 12.649214659685864,
1183
+ "grad_norm": 1.0162887573242188,
1184
+ "learning_rate": 7.55e-06,
1185
+ "loss": 0.3432,
1186
+ "step": 7550
1187
+ },
1188
+ {
1189
+ "epoch": 12.732984293193716,
1190
+ "grad_norm": 0.977488100528717,
1191
+ "learning_rate": 6.716666666666667e-06,
1192
+ "loss": 0.3457,
1193
+ "step": 7600
1194
+ },
1195
+ {
1196
+ "epoch": 12.81675392670157,
1197
+ "grad_norm": 0.8293308019638062,
1198
+ "learning_rate": 5.8833333333333335e-06,
1199
+ "loss": 0.3445,
1200
+ "step": 7650
1201
+ },
1202
+ {
1203
+ "epoch": 12.900523560209423,
1204
+ "grad_norm": 0.9540147185325623,
1205
+ "learning_rate": 5.050000000000001e-06,
1206
+ "loss": 0.3444,
1207
+ "step": 7700
1208
+ },
1209
+ {
1210
+ "epoch": 12.984293193717278,
1211
+ "grad_norm": 1.6243274211883545,
1212
+ "learning_rate": 4.216666666666666e-06,
1213
+ "loss": 0.3481,
1214
+ "step": 7750
1215
+ },
1216
+ {
1217
+ "epoch": 13.06806282722513,
1218
+ "grad_norm": 0.8080894351005554,
1219
+ "learning_rate": 3.3833333333333337e-06,
1220
+ "loss": 0.3416,
1221
+ "step": 7800
1222
+ },
1223
+ {
1224
+ "epoch": 13.151832460732985,
1225
+ "grad_norm": 0.8952440023422241,
1226
+ "learning_rate": 2.55e-06,
1227
+ "loss": 0.3423,
1228
+ "step": 7850
1229
+ },
1230
+ {
1231
+ "epoch": 13.235602094240837,
1232
+ "grad_norm": 0.6296280026435852,
1233
+ "learning_rate": 1.7166666666666668e-06,
1234
+ "loss": 0.3454,
1235
+ "step": 7900
1236
+ },
1237
+ {
1238
+ "epoch": 13.319371727748692,
1239
+ "grad_norm": 1.5492085218429565,
1240
+ "learning_rate": 8.833333333333334e-07,
1241
+ "loss": 0.344,
1242
+ "step": 7950
1243
+ },
1244
+ {
1245
+ "epoch": 13.403141361256544,
1246
+ "grad_norm": 0.6316419839859009,
1247
+ "learning_rate": 5.0000000000000004e-08,
1248
+ "loss": 0.3432,
1249
+ "step": 8000
1250
+ },
1251
+ {
1252
+ "epoch": 13.403141361256544,
1253
+ "eval_loss": 0.31398773193359375,
1254
+ "eval_runtime": 271.4112,
1255
+ "eval_samples_per_second": 31.277,
1256
+ "eval_steps_per_second": 3.913,
1257
+ "step": 8000
1258
  }
1259
  ],
1260
  "logging_steps": 50,
 
1269
  "should_evaluate": false,
1270
  "should_log": false,
1271
  "should_save": true,
1272
+ "should_training_stop": true
1273
  },
1274
  "attributes": {}
1275
  }
1276
  },
1277
+ "total_flos": 1.4332007404692806e+17,
1278
  "train_batch_size": 16,
1279
  "trial_name": null,
1280
  "trial_params": null