HikasaHana commited on
Commit
c80a2af
·
verified ·
1 Parent(s): 2167873

Training in progress, epoch 1

Browse files
run-17/checkpoint-267/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b54f1fa8585a002ce1d2ee342588a47e6276c62725e87e697e3f1cbddd45b386
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2884ee1eb6c9bf50a2a6030607a4b9ebe2a19461fab049737b7d84db6271a0bd
3
  size 409103316
run-17/checkpoint-267/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:628533fda7668c7faf10209127ae87b17f557b584f598415e88ea80018c79a84
3
  size 818327802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2baae2af2e2a6e67ffa103acb8944b4c3e0caf544e891a5bc08743054b6487d8
3
  size 818327802
run-17/checkpoint-267/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.6066157817840576,
3
  "best_model_checkpoint": "BERT-WMM/run-17/checkpoint-267",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,11 +10,11 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.7530516431924883,
14
- "eval_loss": 0.6066157817840576,
15
- "eval_runtime": 2.6354,
16
- "eval_samples_per_second": 808.213,
17
- "eval_steps_per_second": 50.845,
18
  "step": 267
19
  }
20
  ],
@@ -27,6 +27,6 @@
27
  "train_batch_size": 32,
28
  "trial_name": null,
29
  "trial_params": {
30
- "weight_decay": 0.015498593504464519
31
  }
32
  }
 
1
  {
2
+ "best_metric": 0.6066300868988037,
3
  "best_model_checkpoint": "BERT-WMM/run-17/checkpoint-267",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.7535211267605634,
14
+ "eval_loss": 0.6066300868988037,
15
+ "eval_runtime": 2.5102,
16
+ "eval_samples_per_second": 848.522,
17
+ "eval_steps_per_second": 53.381,
18
  "step": 267
19
  }
20
  ],
 
27
  "train_batch_size": 32,
28
  "trial_name": null,
29
  "trial_params": {
30
+ "per_device_eval_batch_size": 16
31
  }
32
  }
run-17/checkpoint-267/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:058e87a3bdfa7b1c5df6dd75ab69ae21b024a53e2f683cb64c30fa5a8462d5f3
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6adb2de71cd7ff11dea13a3c48178e2920a3eb142a0a0d3e397f2b5214908e35
3
  size 4856
run-17/checkpoint-534/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b088bb38876cc1207dbfc22647a9745ddae49648aff36b26a678358916d0597
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f8ea8045dcbfbb7e2b1d5b479744e3e5d4a5952c8b08b322a5910de69569a95
3
  size 409103316
run-17/checkpoint-534/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:812e0321339acdd494d59a07d6085ab9e422d89e98290e794c950d8ca86d8db4
3
  size 818327802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:839569beae02eb4d765dc9d64a6e266937dcbde2f5dce3d36c79a55cbe2e9e94
3
  size 818327802
run-17/checkpoint-534/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.603742778301239,
3
  "best_model_checkpoint": "BERT-WMM/run-17/checkpoint-534",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
@@ -10,27 +10,27 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.7530516431924883,
14
- "eval_loss": 0.6066157817840576,
15
- "eval_runtime": 2.6354,
16
- "eval_samples_per_second": 808.213,
17
- "eval_steps_per_second": 50.845,
18
  "step": 267
19
  },
20
  {
21
  "epoch": 1.87,
22
- "grad_norm": 9.448416709899902,
23
  "learning_rate": 9.825065893169892e-07,
24
  "loss": 0.6083,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
- "eval_accuracy": 0.7615023474178404,
30
- "eval_loss": 0.603742778301239,
31
- "eval_runtime": 2.6051,
32
- "eval_samples_per_second": 817.639,
33
- "eval_steps_per_second": 51.438,
34
  "step": 534
35
  }
36
  ],
@@ -43,6 +43,6 @@
43
  "train_batch_size": 32,
44
  "trial_name": null,
45
  "trial_params": {
46
- "weight_decay": 0.015498593504464519
47
  }
48
  }
 
1
  {
2
+ "best_metric": 0.6037464141845703,
3
  "best_model_checkpoint": "BERT-WMM/run-17/checkpoint-534",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.7535211267605634,
14
+ "eval_loss": 0.6066300868988037,
15
+ "eval_runtime": 2.5102,
16
+ "eval_samples_per_second": 848.522,
17
+ "eval_steps_per_second": 53.381,
18
  "step": 267
19
  },
20
  {
21
  "epoch": 1.87,
22
+ "grad_norm": 9.449368476867676,
23
  "learning_rate": 9.825065893169892e-07,
24
  "loss": 0.6083,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.7619718309859155,
30
+ "eval_loss": 0.6037464141845703,
31
+ "eval_runtime": 2.5312,
32
+ "eval_samples_per_second": 841.482,
33
+ "eval_steps_per_second": 52.938,
34
  "step": 534
35
  }
36
  ],
 
43
  "train_batch_size": 32,
44
  "trial_name": null,
45
  "trial_params": {
46
+ "per_device_eval_batch_size": 16
47
  }
48
  }
run-17/checkpoint-534/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:058e87a3bdfa7b1c5df6dd75ab69ae21b024a53e2f683cb64c30fa5a8462d5f3
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6adb2de71cd7ff11dea13a3c48178e2920a3eb142a0a0d3e397f2b5214908e35
3
  size 4856
runs/Apr19_11-18-29_dcdaa3e6ec43/events.out.tfevents.1713528813.dcdaa3e6ec43.789.37 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3df3ec59376574a7be46121bddba6c7cc8f8c6a4cc32cf17a702e87e429c1412
3
+ size 6122
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:499e1a04d7f7b4fe77d2c8e1f57609c7db579850e1adca3b262fe272e829ad2c
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6adb2de71cd7ff11dea13a3c48178e2920a3eb142a0a0d3e397f2b5214908e35
3
  size 4856