DuongTrongChi commited on
Commit
43edde6
·
verified ·
1 Parent(s): 091138c

Training in progress, step 215, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6941b61d027c04e5f309f5390eda6a6064dac054cf0bf6eb7989361c9739ad1b
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9919332f81d5d5b883cad030582389e20f058a61306a571d8225c59ec351c54d
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e888bde853df181fc520227acccebd4212bfb00ee7eccb08db00bc05cb7322de
3
  size 37430836
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b97479a9ebdfc40326763536562f5b83d05283ac0e1bf4e1a50f5de5908f1708
3
  size 37430836
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:511670a2d22909e7a75f158a995d8ecdfaf934a948d1840b7cc56999076a6a81
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ca27e6ab41112bbcd58358d08377980438330a59138fb91fb36e8afa2a012b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.5871056241426612,
5
  "eval_steps": 500,
6
- "global_step": 214,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1505,6 +1505,13 @@
1505
  "learning_rate": 0.00011363636363636365,
1506
  "loss": 1.2256,
1507
  "step": 214
 
 
 
 
 
 
 
1508
  }
1509
  ],
1510
  "logging_steps": 1,
@@ -1524,7 +1531,7 @@
1524
  "attributes": {}
1525
  }
1526
  },
1527
- "total_flos": 2.6488836986229965e+17,
1528
  "train_batch_size": 4,
1529
  "trial_name": null,
1530
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.5898491083676269,
5
  "eval_steps": 500,
6
+ "global_step": 215,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1505
  "learning_rate": 0.00011363636363636365,
1506
  "loss": 1.2256,
1507
  "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 0.5898491083676269,
1511
+ "grad_norm": 0.18230263888835907,
1512
+ "learning_rate": 0.0001128787878787879,
1513
+ "loss": 1.1579,
1514
+ "step": 215
1515
  }
1516
  ],
1517
  "logging_steps": 1,
 
1531
  "attributes": {}
1532
  }
1533
  },
1534
+ "total_flos": 2.6613228931631923e+17,
1535
  "train_batch_size": 4,
1536
  "trial_name": null,
1537
  "trial_params": null