Hugging Face's logo

inflaton
/
cs605-nlp-assignment-2-bert-large-uncased

Multiple Choice
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
inflaton commited on
Commit
cd45c73
•
1 Parent(s): e177c9b

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. model.safetensors +1 -1
  2. run-12/checkpoint-500/model.safetensors +1 -1
  3. run-12/checkpoint-500/optimizer.pt +1 -1
  4. run-12/checkpoint-500/rng_state.pth +1 -1
  5. run-12/checkpoint-500/scheduler.pt +1 -1
  6. run-12/checkpoint-500/trainer_state.json +28 -10
  7. run-12/checkpoint-500/training_args.bin +1 -1
  8. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06b139261e238ab62a904d642d77045bd52b72cb41a920f8faedf2668778a311
3
  size 1340618660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d91f8a42ae561d47c39b56b2bc7e1cd185bf0a92a15d925892dc36ce4e86723
3
  size 1340618660
run-12/checkpoint-500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a256c82b69611011d91a8912bb43bb9b5badd1057c89fb5dfa2048ee3df658d0
3
  size 1340618660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d91f8a42ae561d47c39b56b2bc7e1cd185bf0a92a15d925892dc36ce4e86723
3
  size 1340618660
run-12/checkpoint-500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62401df9be3b89ba0c8a2c1c14ccc6087c86b3b1dfe74f18c05c0b8a2dcdacfc
3
  size 2681472237
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:871e9494a9f488a5a3ce353eefa30cc76b3b8aae6c170fee50c5413d5d7282fe
3
  size 2681472237
run-12/checkpoint-500/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a810bb0465d3808013c33fffe8149fd14f93aa80861273d550d960733afaa60a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb98e7f396f8e059c8d47db8cc319556058ea6647e1637d6876176292860582
3
  size 14244
run-12/checkpoint-500/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f61f27cd3d022c1ac66517d5bd08798b557a18e0391664cc08706fc34d390d2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a7c49e3734342c25e3b908cf99eaa75cc997bdad958e68f2d725f2744101b2
3
  size 1064
run-12/checkpoint-500/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.6702412868632708,
5
  "eval_steps": 500,
6
  "global_step": 500,
7
  "is_hyper_param_search": true,
@@ -9,23 +9,41 @@
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.6702412868632708,
13
- "grad_norm": 16.528600692749023,
14
- "learning_rate": 7.123178211172342e-06,
15
- "loss": 0.5584,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  "step": 500
17
  }
18
  ],
19
  "logging_steps": 500,
20
- "max_steps": 7460,
21
  "num_input_tokens_seen": 0,
22
  "num_train_epochs": 10,
23
  "save_steps": 500,
24
- "total_flos": 1770780098630016.0,
25
- "train_batch_size": 16,
26
  "trial_name": null,
27
  "trial_params": {
28
- "learning_rate": 7.634900783814034e-06,
29
- "per_device_train_batch_size": 16
30
  }
31
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.6737967914438503,
5
  "eval_steps": 500,
6
  "global_step": 500,
7
  "is_hyper_param_search": true,
 
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.7512571215629578,
14
+ "eval_loss": 0.48031705617904663,
15
+ "eval_runtime": 8.8097,
16
+ "eval_samples_per_second": 338.604,
17
+ "eval_steps_per_second": 21.227,
18
+ "step": 187
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.7616493701934814,
23
+ "eval_loss": 0.5087804198265076,
24
+ "eval_runtime": 8.9807,
25
+ "eval_samples_per_second": 332.158,
26
+ "eval_steps_per_second": 20.823,
27
+ "step": 374
28
+ },
29
+ {
30
+ "epoch": 2.6737967914438503,
31
+ "grad_norm": 8.481908798217773,
32
+ "learning_rate": 1.6199576132025075e-05,
33
+ "loss": 0.3779,
34
  "step": 500
35
  }
36
  ],
37
  "logging_steps": 500,
38
+ "max_steps": 1870,
39
  "num_input_tokens_seen": 0,
40
  "num_train_epochs": 10,
41
  "save_steps": 500,
42
+ "total_flos": 5457641009775480.0,
43
+ "train_batch_size": 64,
44
  "trial_name": null,
45
  "trial_params": {
46
+ "learning_rate": 2.2111830194807948e-05,
47
+ "per_device_train_batch_size": 64
48
  }
49
  }
run-12/checkpoint-500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2ef4e7ac83654cdc4865c924b22c518d13f2972a60fe7c5a3718ae6f4aaebaa
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94f8775f0fe4338594e1dacc56e91d8ca17472a641c2c429df8213c416ea5afa
3
  size 5048
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:752e2b1de4ef6590ab15353edd43d492d68f23094e8b6b6a922d5d42c5f7bd77
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94f8775f0fe4338594e1dacc56e91d8ca17472a641c2c429df8213c416ea5afa
3
  size 5048