mikhail-panzo commited on
Commit
0d7f5ad
1 Parent(s): f3b4276

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 sha256:92ef1101cc9fb02e54282334b0e6bd4e60d0595cb559d42d57d36013d19881dd
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4f5b7eb731d80ba7fa9e08897112adb60df70410cb7a191fbe80df3ce92be45
3
  size 577789320
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:674c977647d24c2401ddc1a423df58aa831693103103edd9672feaafde0d28d5
3
  size 1155772233
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e18fafcf0c0f3815c420b1c31b14b9f4a7ec7554f4991ab26e1bed8d170f3d2f
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:e709aa0555fa5194531caefe8b2d088ae3dbd38583b58f3fca70a67516efdf96
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:519f4775ca84a56cc7e5f6f0fb76a2348e31326ce758c1c51c986b8abb151d12
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c124d5873e6dde5040a6a31973ca68127e3dfe277695e3cb113af8a1a01ff662
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aef1303f298e810b9c563fac5650fcaebc5d5e2a568db30104db374f503c826
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.40593138337135315,
3
  "best_model_checkpoint": "mikhail_panzo/zlm-fil_b64_le5_s8000/checkpoint-7000",
4
- "epoch": 326.0869565217391,
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": 12.442,
1178
  "eval_steps_per_second": 1.623,
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": 9.088988346445709e+16,
1200
  "train_batch_size": 32,
1201
  "trial_name": null,
1202
  "trial_params": null
 
1
  {
2
  "best_metric": 0.40593138337135315,
3
  "best_model_checkpoint": "mikhail_panzo/zlm-fil_b64_le5_s8000/checkpoint-7000",
4
+ "epoch": 347.82608695652175,
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": 12.442,
1178
  "eval_steps_per_second": 1.623,
1179
  "step": 7500
1180
+ },
1181
+ {
1182
+ "epoch": 328.2608695652174,
1183
+ "grad_norm": 0.6245155334472656,
1184
+ "learning_rate": 7.550000000000001e-07,
1185
+ "loss": 0.4067,
1186
+ "step": 7550
1187
+ },
1188
+ {
1189
+ "epoch": 330.4347826086956,
1190
+ "grad_norm": 0.7212103009223938,
1191
+ "learning_rate": 6.716666666666668e-07,
1192
+ "loss": 0.4038,
1193
+ "step": 7600
1194
+ },
1195
+ {
1196
+ "epoch": 332.60869565217394,
1197
+ "grad_norm": 0.8665474057197571,
1198
+ "learning_rate": 5.883333333333333e-07,
1199
+ "loss": 0.4048,
1200
+ "step": 7650
1201
+ },
1202
+ {
1203
+ "epoch": 334.7826086956522,
1204
+ "grad_norm": 0.7773168087005615,
1205
+ "learning_rate": 5.05e-07,
1206
+ "loss": 0.4054,
1207
+ "step": 7700
1208
+ },
1209
+ {
1210
+ "epoch": 336.95652173913044,
1211
+ "grad_norm": 0.7131752967834473,
1212
+ "learning_rate": 4.2166666666666667e-07,
1213
+ "loss": 0.4058,
1214
+ "step": 7750
1215
+ },
1216
+ {
1217
+ "epoch": 339.1304347826087,
1218
+ "grad_norm": 0.7420967221260071,
1219
+ "learning_rate": 3.3833333333333336e-07,
1220
+ "loss": 0.409,
1221
+ "step": 7800
1222
+ },
1223
+ {
1224
+ "epoch": 341.30434782608694,
1225
+ "grad_norm": 0.866454541683197,
1226
+ "learning_rate": 2.55e-07,
1227
+ "loss": 0.4071,
1228
+ "step": 7850
1229
+ },
1230
+ {
1231
+ "epoch": 343.4782608695652,
1232
+ "grad_norm": 0.6852492094039917,
1233
+ "learning_rate": 1.7166666666666668e-07,
1234
+ "loss": 0.4054,
1235
+ "step": 7900
1236
+ },
1237
+ {
1238
+ "epoch": 345.6521739130435,
1239
+ "grad_norm": 0.8399931788444519,
1240
+ "learning_rate": 8.833333333333334e-08,
1241
+ "loss": 0.4033,
1242
+ "step": 7950
1243
+ },
1244
+ {
1245
+ "epoch": 347.82608695652175,
1246
+ "grad_norm": 0.8192908763885498,
1247
+ "learning_rate": 5e-09,
1248
+ "loss": 0.4035,
1249
+ "step": 8000
1250
+ },
1251
+ {
1252
+ "epoch": 347.82608695652175,
1253
+ "eval_loss": 0.40772464871406555,
1254
+ "eval_runtime": 13.1445,
1255
+ "eval_samples_per_second": 12.248,
1256
+ "eval_steps_per_second": 1.598,
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": 9.695483990986939e+16,
1278
  "train_batch_size": 32,
1279
  "trial_name": null,
1280
  "trial_params": null