k4black commited on
Commit
80a771f
·
1 Parent(s): 47912b4

Training in progress, step 500

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17a6f5d9f59d5ca48ea4b81e8443265575df206ee090af2218d5c14d6b292411
3
  size 93496819
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38213239ca5d9db19ef00739dd9a3f848bdebd3bb34dfcd824b785e843b4135a
3
  size 93496819
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4ccd09ee36fd9b34471570805a4d227d31960d5b3709a99e479234ab58aaad9
3
  size 46754181
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9a7a0ed81eaf9792d14a3d5039bf36fa5fa3a2d03f664f130869691498cd8d
3
  size 46754181
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94786083f47fbab3d0dbd4c96219dd33e7e3b53b04c255e10bd77e6ac0a6d2a1
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62aecb91ab9cbaec5be46105c75eb603108528201b7217da47139da8e59f270f
3
  size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfcb5cc8a88fdf5ba243397deddcf83d686a57d979060e9369582f73491a8b43
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a538e2eed744446b1c098b0da11910493a116a82d5b87ff431e9c8bfd67d8a2
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8be93d226c46aace6e6aadde1c562e595b5e68b0d904b43566db85ac9c2f27d8
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6006111b21ef3a36ad0959ea470767badfb7030f68e8683ee71b1b7cca95a0d1
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,15 +1,91 @@
1
  {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 0.6535947712418301,
5
  "global_step": 500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
- "log_history": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  "max_steps": 3060,
11
- "num_train_epochs": 4,
12
- "total_flos": 191184814080000.0,
13
  "trial_name": null,
14
  "trial_params": null
15
  }
 
1
  {
2
+ "best_metric": 0.4956161379814148,
3
+ "best_model_checkpoint": "./albert-finetuned-results/checkpoint-500",
4
+ "epoch": 0.49019607843137253,
5
  "global_step": 500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.1,
12
+ "learning_rate": 9.679738562091505e-06,
13
+ "loss": 0.6585,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.1,
18
+ "eval_f1": 0.3932038834951456,
19
+ "eval_loss": 0.666271984577179,
20
+ "eval_runtime": 16.6679,
21
+ "eval_samples_per_second": 59.995,
22
+ "eval_steps_per_second": 1.92,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.2,
27
+ "learning_rate": 9.352941176470589e-06,
28
+ "loss": 0.6308,
29
+ "step": 200
30
+ },
31
+ {
32
+ "epoch": 0.2,
33
+ "eval_f1": 0.5745920745920746,
34
+ "eval_loss": 0.5807430148124695,
35
+ "eval_runtime": 16.6699,
36
+ "eval_samples_per_second": 59.988,
37
+ "eval_steps_per_second": 1.92,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.29,
42
+ "learning_rate": 9.029411764705884e-06,
43
+ "loss": 0.5161,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 0.29,
48
+ "eval_f1": 0.7365786839471049,
49
+ "eval_loss": 0.5005233883857727,
50
+ "eval_runtime": 16.5204,
51
+ "eval_samples_per_second": 60.531,
52
+ "eval_steps_per_second": 1.937,
53
+ "step": 300
54
+ },
55
+ {
56
+ "epoch": 0.39,
57
+ "learning_rate": 8.705882352941177e-06,
58
+ "loss": 0.4986,
59
+ "step": 400
60
+ },
61
+ {
62
+ "epoch": 0.39,
63
+ "eval_f1": 0.743365165470607,
64
+ "eval_loss": 0.49836239218711853,
65
+ "eval_runtime": 16.6002,
66
+ "eval_samples_per_second": 60.24,
67
+ "eval_steps_per_second": 1.928,
68
+ "step": 400
69
+ },
70
+ {
71
+ "epoch": 0.49,
72
+ "learning_rate": 8.379084967320262e-06,
73
+ "loss": 0.484,
74
+ "step": 500
75
+ },
76
+ {
77
+ "epoch": 0.49,
78
+ "eval_f1": 0.7098214285714286,
79
+ "eval_loss": 0.4956161379814148,
80
+ "eval_runtime": 16.5264,
81
+ "eval_samples_per_second": 60.509,
82
+ "eval_steps_per_second": 1.936,
83
+ "step": 500
84
+ }
85
+ ],
86
  "max_steps": 3060,
87
+ "num_train_epochs": 3,
88
+ "total_flos": 143388610560000.0,
89
  "trial_name": null,
90
  "trial_params": null
91
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2159b0448868d4bffe87f6e2abb55ea981e5d9dedfd378094e2e26dd7775f0e
3
  size 3451
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccf3a181738c3f9f78f9138a94af191eca936da1d93a28d7118308302bc349b9
3
  size 3451
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4ccd09ee36fd9b34471570805a4d227d31960d5b3709a99e479234ab58aaad9
3
  size 46754181
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9a7a0ed81eaf9792d14a3d5039bf36fa5fa3a2d03f664f130869691498cd8d
3
  size 46754181
runs/Oct30_19-20-57_daccc72d0fea/1667157664.0746858/events.out.tfevents.1667157664.daccc72d0fea.78.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32e48af85fdbc4bf3fffd0c8f922cc3261f2b7b2600dde021d1f066139347986
3
+ size 5548
runs/Oct30_19-20-57_daccc72d0fea/events.out.tfevents.1667157664.daccc72d0fea.78.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10972d73ae72c8bf8417463c2b3a0043c7296be6d859a7602480d97dde4096f6
3
+ size 4038
runs/Oct30_19-31-02_daccc72d0fea/1667158268.1547854/events.out.tfevents.1667158268.daccc72d0fea.78.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e49db22c69b154dd5f1179f324da3b6f1b8807018bdcd7997cbbb0b479196b8
3
+ size 5548
runs/Oct30_19-31-02_daccc72d0fea/events.out.tfevents.1667158268.daccc72d0fea.78.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eaa78946b3905c437f8918301be263553b0040f10760e75e6a44be790fbc956
3
+ size 40
runs/Oct30_19-32-21_daccc72d0fea/1667158350.8270729/events.out.tfevents.1667158350.daccc72d0fea.1725.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3723dc5ba4ed6601da192de2ab51d558831523f7c13b3c8663c20b162be832e5
3
+ size 5548
runs/Oct30_19-32-21_daccc72d0fea/events.out.tfevents.1667158350.daccc72d0fea.1725.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2be21d5fd71b8f0f834d0963128556cf424c43b9c2ca3f94c991113c927645fb
3
+ size 6336
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2159b0448868d4bffe87f6e2abb55ea981e5d9dedfd378094e2e26dd7775f0e
3
  size 3451
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccf3a181738c3f9f78f9138a94af191eca936da1d93a28d7118308302bc349b9
3
  size 3451