HikasaHana commited on
Commit
45bbba4
·
verified ·
1 Parent(s): 542a713

Training in progress, epoch 1

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26d7f234a18b08d68556eb791d0055c0b179dd8190747f6d104dae29ea9eda1d
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:971a3ddf817b712dc07195c844772ef5d1ec4a8fd2faa3cfc511b714130228d0
3
  size 409103316
run-5/checkpoint-267/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6115a480a3556deabc06ba3a4a9d328a4f5a7290a47014ca45b7455a400e6d93
3
  size 409103316
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:971a3ddf817b712dc07195c844772ef5d1ec4a8fd2faa3cfc511b714130228d0
3
  size 409103316
run-5/checkpoint-267/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d51262842df1054b632a29ea66bc9fc5d957248ba9bcdca4f3e195d304b6314
3
  size 818327802
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc8b54fc5e8c9423b8eb78032472c72dce9ff03db39846d1622f31a3d6911c46
3
  size 818327802
run-5/checkpoint-267/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:123e89548a83b33069b1dc6f7e79d621eac970b4e99c56bc48c19b6733a7f692
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0980580128ccd5e578c966c8ffb616b8165a0951ed4f83a639bfa5862c1defb0
3
  size 14244
run-5/checkpoint-267/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dab3b17d1969fd0b91ad7d8767d2c65a7afa789e978300157a086606fc39af78
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d605219d0cdfe1356d19dfc261c4f045664dbc44ddf04517d0b2ebd1dab264c7
3
  size 1064
run-5/checkpoint-267/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.6466411352157593,
3
  "best_model_checkpoint": "BERT-WMM/run-5/checkpoint-267",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,26 +10,23 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.7338028169014085,
14
- "eval_loss": 0.6466411352157593,
15
- "eval_runtime": 2.0904,
16
- "eval_samples_per_second": 1018.923,
17
- "eval_steps_per_second": 64.101,
18
  "step": 267
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 534,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 2,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 32,
28
  "trial_name": null,
29
  "trial_params": {
30
- "learning_rate": 8.887574420426101e-06,
31
- "num_train_epochs": 2,
32
- "per_device_train_batch_size": 32,
33
- "weight_decay": 1.6818908255902827e-05
34
  }
35
  }
 
1
  {
2
+ "best_metric": 0.6019130349159241,
3
  "best_model_checkpoint": "BERT-WMM/run-5/checkpoint-267",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.7563380281690141,
14
+ "eval_loss": 0.6019130349159241,
15
+ "eval_runtime": 2.4929,
16
+ "eval_samples_per_second": 854.419,
17
+ "eval_steps_per_second": 53.752,
18
  "step": 267
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 801,
23
  "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 32,
28
  "trial_name": null,
29
  "trial_params": {
30
+ "per_device_train_batch_size": 32
 
 
 
31
  }
32
  }
run-5/checkpoint-267/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d11893aa7531a00a798ff2c74d6b44e7248ec089d85163d6ee787b4e26991cd
3
  size 4856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
3
  size 4856
runs/Apr19_07-31-51_21d31c708e60/events.out.tfevents.1713512742.21d31c708e60.946.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b884f4189bd997b931276917a470562db2f54a381ca483c5d3bb7727de70a965
3
+ size 5751