penglingwei commited on
Commit
b5e8292
1 Parent(s): bfd34bb

Training in progress, step 49151, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40ecfe3a0c12439a9f90edc2fc9f1e2a668d7c1b656b38af5a2a2d0cfa333c8c
3
  size 355970836
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97f2edc2a659fa0ab865d96aba1342985ceee6f8b9e7e2e0bc2734e4fa8199de
3
  size 355970836
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e5e79d9e80c18e1c2060a8874e824cf002565f3eb04b11dd46e4e8a117cb0bb
3
  size 712036922
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f01610765b026e4073dc792fa519799ddfee84d97839ac7114420dc7fad095dc
3
  size 712036922
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bfa3cbc2a58dc585521846b280140b11ba732e023276e6bebe874d968d3681d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:906573e220485578a572456e29e3b97d5ff5468e5305bea1db395e9e4e84a615
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25b31a876da34080aeaad6646395178da9de75ac374aa229009a32b050d1ae89
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6efd166389749e81c893bfe8d8ade06bfd5d181d3c7a713ed9d971329711d93
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": 0.9989477733166757,
5
  "eval_steps": 500,
6
- "global_step": 49100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -34377,6 +34377,41 @@
34377
  "learning_rate": 6.384977135377723e-11,
34378
  "loss": 26.9088,
34379
  "step": 49100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
34380
  }
34381
  ],
34382
  "logging_steps": 10,
@@ -34391,7 +34426,7 @@
34391
  "should_evaluate": false,
34392
  "should_log": false,
34393
  "should_save": true,
34394
- "should_training_stop": false
34395
  },
34396
  "attributes": {}
34397
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9999853769101411,
5
  "eval_steps": 500,
6
+ "global_step": 49151,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
34377
  "learning_rate": 6.384977135377723e-11,
34378
  "loss": 26.9088,
34379
  "step": 49100
34380
+ },
34381
+ {
34382
+ "epoch": 0.999151225001669,
34383
+ "grad_norm": 103247.6640625,
34384
+ "learning_rate": 5.505419123797567e-11,
34385
+ "loss": 25.8345,
34386
+ "step": 49110
34387
+ },
34388
+ {
34389
+ "epoch": 0.9993546766866621,
34390
+ "grad_norm": 92363.125,
34391
+ "learning_rate": 4.6910120859305904e-11,
34392
+ "loss": 27.5682,
34393
+ "step": 49120
34394
+ },
34395
+ {
34396
+ "epoch": 0.9995581283716554,
34397
+ "grad_norm": 43590.00390625,
34398
+ "learning_rate": 3.941756361400956e-11,
34399
+ "loss": 23.7671,
34400
+ "step": 49130
34401
+ },
34402
+ {
34403
+ "epoch": 0.9997615800566486,
34404
+ "grad_norm": 84118.6953125,
34405
+ "learning_rate": 3.25765226263236e-11,
34406
+ "loss": 24.8344,
34407
+ "step": 49140
34408
+ },
34409
+ {
34410
+ "epoch": 0.9999650317416418,
34411
+ "grad_norm": 88703.15625,
34412
+ "learning_rate": 2.6387000748480383e-11,
34413
+ "loss": 24.6881,
34414
+ "step": 49150
34415
  }
34416
  ],
34417
  "logging_steps": 10,
 
34426
  "should_evaluate": false,
34427
  "should_log": false,
34428
  "should_save": true,
34429
+ "should_training_stop": true
34430
  },
34431
  "attributes": {}
34432
  }