daydrill commited on
Commit
d80e99b
1 Parent(s): 88625f1

Training in progress, step 10000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2815fe401ec6ed13fa8496b8a130981165e9740f25a9aa0f5046eb298d76e89d
3
  size 943333453
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33ad74f665a3348bf6d5e3ed299f7d4a7b088b85d5bec7ac115386ab6edda94f
3
  size 943333453
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43d467d75f3fdef469e5bc56ca1fac1d83e9042d52441105a2d20418fb1a0436
3
  size 471708325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ca5b7f87f157eff6693ee1f1169b77aa22b7f8a1f4a26872e93b75338ac3e77
3
  size 471708325
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2124064e0e4e5ab159e152ae1f2b839ea342c8916f3940e7326b5af6d56d60f7
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d45aeed5414b04020f4a5838ded6cc7c6a982ebbcb1218c96b18a1d5d9638300
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b3fad2f6fce6a53bcc536267fb713fc98b77d91952cd1de74b585c2aab05034
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68acf919319a139013fd82fcbfd6c4d169e0a48d6ea3e7014b7221b66195f3c9
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:856d2b6c50571997ea86916bdeeedeb8e6b238155372c64b4e024237aa1cc790
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53d49cf7f37049401f5c9ba25adfe57342376a940b10cb055a010720a691d14
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.16288767266093301,
5
- "global_step": 5000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -22,11 +22,27 @@
22
  "eval_samples_per_second": 7.463,
23
  "eval_steps_per_second": 3.732,
24
  "step": 5000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
26
  ],
27
  "max_steps": 92088,
28
  "num_train_epochs": 3,
29
- "total_flos": 1.103235145728e+16,
30
  "trial_name": null,
31
  "trial_params": null
32
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.32577534532186603,
5
+ "global_step": 10000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
22
  "eval_samples_per_second": 7.463,
23
  "eval_steps_per_second": 3.732,
24
  "step": 5000
25
+ },
26
+ {
27
+ "epoch": 0.33,
28
+ "learning_rate": 2.674550430023456e-05,
29
+ "loss": 1.1965,
30
+ "step": 10000
31
+ },
32
+ {
33
+ "epoch": 0.33,
34
+ "eval_exact_match": 75.13475917231786,
35
+ "eval_f1": 79.95184555682803,
36
+ "eval_loss": 0.9056070446968079,
37
+ "eval_runtime": 1533.9546,
38
+ "eval_samples_per_second": 7.505,
39
+ "eval_steps_per_second": 3.753,
40
+ "step": 10000
41
  }
42
  ],
43
  "max_steps": 92088,
44
  "num_train_epochs": 3,
45
+ "total_flos": 2.206470291456e+16,
46
  "trial_name": null,
47
  "trial_params": null
48
  }
nbest_predictions.json CHANGED
The diff for this file is too large to render. See raw diff
 
predictions.json CHANGED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43d467d75f3fdef469e5bc56ca1fac1d83e9042d52441105a2d20418fb1a0436
3
  size 471708325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ca5b7f87f157eff6693ee1f1169b77aa22b7f8a1f4a26872e93b75338ac3e77
3
  size 471708325