cruiser commited on
Commit
0e02670
1 Parent(s): 4e1a557

Training in progress, epoch 2

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a177e7e58ebacb27aeeaaafa31d26179ad44cc4442bec50cd96f3a753c507af
3
  size 535707205
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8b4a151c655e9cc7fe2c1297f08df80ab6b01339fc44d111728e657608bfe9a
3
  size 535707205
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f89b283bce7d91e0a094f038f21181c4089cfb1ab3fe1fdbf36e52574105a45
3
  size 267858605
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749b4473984959467cd22dbb65d092ae32170028d630edacadd33a0c2fd32094
3
  size 267858605
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1afa4fb390fed62209a33ec31502a83421450b5e725ed87b9f6a0e5a6fe43e4a
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec413b9ccb2e7bf299f05612d1ea984d788cd968b214a3f7972297c05d91216b
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8887e02a63197212eb08e6268a00af8c32453672a22c577dcf1de8bc5e2b976a
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7524676a9651ec8c0d685a583a2fce1a7529148810db182eac434accbd0d75cb
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 1.8566110134124756,
3
- "best_model_checkpoint": "distilbert_weight_decay_final/checkpoint-1718",
4
- "epoch": 1.0,
5
- "global_step": 1718,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -38,11 +38,43 @@
38
  "eval_samples_per_second": 328.933,
39
  "eval_steps_per_second": 20.57,
40
  "step": 1718
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
  }
42
  ],
43
  "max_steps": 34360,
44
  "num_train_epochs": 20,
45
- "total_flos": 782117510345820.0,
46
  "trial_name": null,
47
  "trial_params": null
48
  }
 
1
  {
2
+ "best_metric": 1.4884066581726074,
3
+ "best_model_checkpoint": "distilbert_weight_decay_final/checkpoint-3436",
4
+ "epoch": 2.0,
5
+ "global_step": 3436,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
38
  "eval_samples_per_second": 328.933,
39
  "eval_steps_per_second": 20.57,
40
  "step": 1718
41
+ },
42
+ {
43
+ "epoch": 1.16,
44
+ "learning_rate": 1.8835855646100117e-05,
45
+ "loss": 0.0764,
46
+ "step": 2000
47
+ },
48
+ {
49
+ "epoch": 1.46,
50
+ "learning_rate": 1.8544819557625148e-05,
51
+ "loss": 0.073,
52
+ "step": 2500
53
+ },
54
+ {
55
+ "epoch": 1.75,
56
+ "learning_rate": 1.825378346915018e-05,
57
+ "loss": 0.0856,
58
+ "step": 3000
59
+ },
60
+ {
61
+ "epoch": 2.0,
62
+ "eval_accuracy": {
63
+ "accuracy": 0.7758913412563667
64
+ },
65
+ "eval_f1": {
66
+ "f1": 0.7796491207830641
67
+ },
68
+ "eval_loss": 1.4884066581726074,
69
+ "eval_runtime": 10.2393,
70
+ "eval_samples_per_second": 345.14,
71
+ "eval_steps_per_second": 21.583,
72
+ "step": 3436
73
  }
74
  ],
75
  "max_steps": 34360,
76
  "num_train_epochs": 20,
77
+ "total_flos": 1564235020691640.0,
78
  "trial_name": null,
79
  "trial_params": null
80
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f89b283bce7d91e0a094f038f21181c4089cfb1ab3fe1fdbf36e52574105a45
3
  size 267858605
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749b4473984959467cd22dbb65d092ae32170028d630edacadd33a0c2fd32094
3
  size 267858605
runs/May01_06-03-35_af1ffd0a72ec/events.out.tfevents.1682921017.af1ffd0a72ec.975.10 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08dcf5072db183fe3fc5f86f73a3c90d0dd9c71fb873a02e205ae51a9c6fa631
3
- size 4905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54cd74573711351fd86710886147678ef6556c5f370260bd1cd90dbbde1d4ea6
3
+ size 5647