HikasaHana commited on
Commit
2167873
·
verified ·
1 Parent(s): 877bbbf

Training in progress, epoch 1

Browse files
run-16/checkpoint-267/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c997364c6e0f71451ac72fbbabd23c2a59cb056a7d24aa3868d844ab5c111605
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2884ee1eb6c9bf50a2a6030607a4b9ebe2a19461fab049737b7d84db6271a0bd
3
  size 409103316
run-16/checkpoint-267/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d81e00932d4521b228f60cf1f168c3ba9f068504d2aacbd19ad91f13f05bc8a2
3
  size 818327802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2baae2af2e2a6e67ffa103acb8944b4c3e0caf544e891a5bc08743054b6487d8
3
  size 818327802
run-16/checkpoint-267/trainer_state.json CHANGED
@@ -12,9 +12,9 @@
12
  "epoch": 1.0,
13
  "eval_accuracy": 0.7535211267605634,
14
  "eval_loss": 0.6066301465034485,
15
- "eval_runtime": 2.5806,
16
- "eval_samples_per_second": 825.38,
17
- "eval_steps_per_second": 51.925,
18
  "step": 267
19
  }
20
  ],
@@ -27,6 +27,6 @@
27
  "train_batch_size": 32,
28
  "trial_name": null,
29
  "trial_params": {
30
- "weight_decay": 0.0026076282916422315
31
  }
32
  }
 
12
  "epoch": 1.0,
13
  "eval_accuracy": 0.7535211267605634,
14
  "eval_loss": 0.6066301465034485,
15
+ "eval_runtime": 2.6193,
16
+ "eval_samples_per_second": 813.201,
17
+ "eval_steps_per_second": 6.49,
18
  "step": 267
19
  }
20
  ],
 
27
  "train_batch_size": 32,
28
  "trial_name": null,
29
  "trial_params": {
30
+ "per_device_eval_batch_size": 128
31
  }
32
  }
run-16/checkpoint-267/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf60e7ee962b6e8e2a7c5dee75a7889939e69dfb54e3e671c088aa239f9ce5f8
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:499e1a04d7f7b4fe77d2c8e1f57609c7db579850e1adca3b262fe272e829ad2c
3
  size 4856
run-16/checkpoint-534/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a84802d89f5d3d8e178bf0dcdff5a20662948d91d59b9e43dde7b10b64668e10
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f8ea8045dcbfbb7e2b1d5b479744e3e5d4a5952c8b08b322a5910de69569a95
3
  size 409103316
run-16/checkpoint-534/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf456517c4b217a84a18628c21cdcd095f29afe3dcf0ae39ec0a74a14546ca50
3
  size 818327802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:839569beae02eb4d765dc9d64a6e266937dcbde2f5dce3d36c79a55cbe2e9e94
3
  size 818327802
run-16/checkpoint-534/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.6037467122077942,
3
  "best_model_checkpoint": "BERT-WMM/run-16/checkpoint-534",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
@@ -12,14 +12,14 @@
12
  "epoch": 1.0,
13
  "eval_accuracy": 0.7535211267605634,
14
  "eval_loss": 0.6066301465034485,
15
- "eval_runtime": 2.5806,
16
- "eval_samples_per_second": 825.38,
17
- "eval_steps_per_second": 51.925,
18
  "step": 267
19
  },
20
  {
21
  "epoch": 1.87,
22
- "grad_norm": 9.44939136505127,
23
  "learning_rate": 9.825065893169892e-07,
24
  "loss": 0.6083,
25
  "step": 500
@@ -27,10 +27,10 @@
27
  {
28
  "epoch": 2.0,
29
  "eval_accuracy": 0.7619718309859155,
30
- "eval_loss": 0.6037467122077942,
31
- "eval_runtime": 2.5199,
32
- "eval_samples_per_second": 845.27,
33
- "eval_steps_per_second": 53.177,
34
  "step": 534
35
  }
36
  ],
@@ -43,6 +43,6 @@
43
  "train_batch_size": 32,
44
  "trial_name": null,
45
  "trial_params": {
46
- "weight_decay": 0.0026076282916422315
47
  }
48
  }
 
1
  {
2
+ "best_metric": 0.6037463545799255,
3
  "best_model_checkpoint": "BERT-WMM/run-16/checkpoint-534",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
 
12
  "epoch": 1.0,
13
  "eval_accuracy": 0.7535211267605634,
14
  "eval_loss": 0.6066301465034485,
15
+ "eval_runtime": 2.6193,
16
+ "eval_samples_per_second": 813.201,
17
+ "eval_steps_per_second": 6.49,
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
 
27
  {
28
  "epoch": 2.0,
29
  "eval_accuracy": 0.7619718309859155,
30
+ "eval_loss": 0.6037463545799255,
31
+ "eval_runtime": 2.5688,
32
+ "eval_samples_per_second": 829.181,
33
+ "eval_steps_per_second": 6.618,
34
  "step": 534
35
  }
36
  ],
 
43
  "train_batch_size": 32,
44
  "trial_name": null,
45
  "trial_params": {
46
+ "per_device_eval_batch_size": 128
47
  }
48
  }
run-16/checkpoint-534/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf60e7ee962b6e8e2a7c5dee75a7889939e69dfb54e3e671c088aa239f9ce5f8
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:499e1a04d7f7b4fe77d2c8e1f57609c7db579850e1adca3b262fe272e829ad2c
3
  size 4856
runs/Apr19_11-18-29_dcdaa3e6ec43/events.out.tfevents.1713528623.dcdaa3e6ec43.789.36 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:369c6fece9e596445b7449ac4cc143c2a77b18a926ba83dbeca3e881f45f56a6
3
+ size 6123
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f84a19154c99b0458e0a6935a21fc8d86553f9641188bbfc0f3682f7c0fef1d7
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:499e1a04d7f7b4fe77d2c8e1f57609c7db579850e1adca3b262fe272e829ad2c
3
  size 4856