genejalston commited on
Commit
f5f681a
1 Parent(s): d29d0a8

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73f9709676fd308493096edfefbab55e00200fd0ec9eee8d1c8d9c9b9393dd60
3
  size 1625426996
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d2170685d0967d98d541384fb9096bbe76c996e2f2ef5d10553264ddc385c8a
3
  size 1625426996
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13b3726efa7754053b08c4fa6b30b5a12364126ed953d7f0b1fcf11d22c76b26
3
  size 3250759951
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:059e1efd93190766ac5721961dbf55ea0e558cb218646ccd52ba2f24b9c2e591
3
  size 3250759951
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e7af7a01e94a9a7176c2bbdf2cb9b8139105cfe65528853ec5a27025100d6bc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:571b846c9de4671606b4803fe209b7424419cce76e7d83b36c52a236294e4cb0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9eeeb5bdd24cb6de6ccdee8afd347d0c5c5a88be6c8e7e24752989eef5c1513
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dbaa1691f7b35bc2bd0f7fb06c6d3b2bc869f5776dc79a2f162736695a4d24b
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": 0.2,
5
  "eval_steps": 500,
6
- "global_step": 500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -13,13 +13,19 @@
13
  "learning_rate": 1.869158878504673e-05,
14
  "loss": 0.4912,
15
  "step": 500
 
 
 
 
 
 
16
  }
17
  ],
18
  "logging_steps": 500,
19
  "max_steps": 7500,
20
  "num_train_epochs": 3,
21
  "save_steps": 500,
22
- "total_flos": 846525235200000.0,
23
  "trial_name": null,
24
  "trial_params": null
25
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.4,
5
  "eval_steps": 500,
6
+ "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
13
  "learning_rate": 1.869158878504673e-05,
14
  "loss": 0.4912,
15
  "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.4,
19
+ "learning_rate": 1.7356475300400533e-05,
20
+ "loss": 0.3659,
21
+ "step": 1000
22
  }
23
  ],
24
  "logging_steps": 500,
25
  "max_steps": 7500,
26
  "num_train_epochs": 3,
27
  "save_steps": 500,
28
+ "total_flos": 1693050470400000.0,
29
  "trial_name": null,
30
  "trial_params": null
31
  }