phinniaspp commited on
Commit
a1fac52
·
verified ·
1 Parent(s): b9e47d8

Training in progress, step 3777, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ce8db3b80b514dfc4ccc29780f43167e58029c6a67f1eedcd01394432d973f3
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeebe368eb77dd59cf57cb7a1b09ab7881a8f38ef8de181557db15cf97d42441
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fdc53e6c9642effed8e2b20df3f515014c09b49e83e9f25857d6f6d1f8093af
3
  size 86889891
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:039da929b0ca180eaab116edb95a88fb7a04c32d7bb303a925acb2888070e3db
3
  size 86889891
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d8442b89362d2c3fbed2fee68ab46959b16e3fd21869c5ae0404708bec56f99
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da045893976d7c4c0ba8ca84a12e3e9267728c64cb1f32b0a7d0c4ce534e9b41
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6395afb35e81be08b45cc18b63967699db3df58005600a6b5e324106137067a9
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1b5437befb4c77d45008b3f81b9423bd9d0c30e716b16b4c2d0d1391cd39be1
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.5443456768989563,
3
  "best_model_checkpoint": "./learnhub-checkpoints/checkpoint-2500",
4
- "epoch": 2.937493798987995,
5
  "eval_steps": 100,
6
- "global_step": 3700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1339,6 +1339,27 @@
1339
  "eval_samples_per_second": 1.337,
1340
  "eval_steps_per_second": 0.669,
1341
  "step": 3700
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1342
  }
1343
  ],
1344
  "logging_steps": 25,
@@ -1353,12 +1374,12 @@
1353
  "should_evaluate": false,
1354
  "should_log": false,
1355
  "should_save": true,
1356
- "should_training_stop": false
1357
  },
1358
  "attributes": {}
1359
  }
1360
  },
1361
- "total_flos": 3.636828326257459e+17,
1362
  "train_batch_size": 2,
1363
  "trial_name": null,
1364
  "trial_params": null
 
1
  {
2
  "best_metric": 0.5443456768989563,
3
  "best_model_checkpoint": "./learnhub-checkpoints/checkpoint-2500",
4
+ "epoch": 2.9986109733108446,
5
  "eval_steps": 100,
6
+ "global_step": 3777,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1339
  "eval_samples_per_second": 1.337,
1340
  "eval_steps_per_second": 0.669,
1341
  "step": 3700
1342
+ },
1343
+ {
1344
+ "epoch": 2.9573370374045043,
1345
+ "grad_norm": 10.888229370117188,
1346
+ "learning_rate": 9.867740937795634e-08,
1347
+ "loss": 1.9724,
1348
+ "step": 3725
1349
+ },
1350
+ {
1351
+ "epoch": 2.9771802758210137,
1352
+ "grad_norm": 14.896629333496094,
1353
+ "learning_rate": 2.660668443794645e-08,
1354
+ "loss": 1.9815,
1355
+ "step": 3750
1356
+ },
1357
+ {
1358
+ "epoch": 2.9970235142375237,
1359
+ "grad_norm": 11.675270080566406,
1360
+ "learning_rate": 1.4599647685242802e-10,
1361
+ "loss": 1.9008,
1362
+ "step": 3775
1363
  }
1364
  ],
1365
  "logging_steps": 25,
 
1374
  "should_evaluate": false,
1375
  "should_log": false,
1376
  "should_save": true,
1377
+ "should_training_stop": true
1378
  },
1379
  "attributes": {}
1380
  }
1381
  },
1382
+ "total_flos": 3.7131039722038886e+17,
1383
  "train_batch_size": 2,
1384
  "trial_name": null,
1385
  "trial_params": null