xuancoblab2023 commited on
Commit
fa94861
·
verified ·
1 Parent(s): bfc79ba

Training in progress, epoch 2

Browse files
logs/events.out.tfevents.1709872749.6c1c016b0e3e.7263.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3ffe5b23fc63efa9df1ffc9bc7a94788bd4753eeec75074795d919d2db31396
3
- size 5315
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9e98967b2a05b7def1ceb61d7bc9f002b7580fb7c0d8c005f2358d7f149cc9c
3
+ size 5985
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbb53409ec8f327c826c93a204be4a45fa400489d77fe31d5d28d45881baf320
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cc7e4d70d2a7114843f6215ed17a2fc8447bc6bd70f413c4cf0f8344ca39c96
3
  size 17549312
run-1/checkpoint-96/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f580c7021c521e50c4f09989078be6521aed1a3504233121cb4128acd7ffaf3f
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cc7e4d70d2a7114843f6215ed17a2fc8447bc6bd70f413c4cf0f8344ca39c96
3
  size 17549312
run-1/checkpoint-96/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91e888b82282d118e9145b95f3a0386ef58f658c83e89e13b16215c4e2411c83
3
  size 35122746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90e08c57274194bc668f3be4471281afe7a6c39aaf728f118f809a52a069cb3c
3
  size 35122746
run-1/checkpoint-96/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24aa86019b8aea1c551cc1adaf38c4db2fc01de75a22af312230f6b592e0fd81
3
  size 14054
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc13e09b59a62b6fb29cad756bfeefcce6f512c71a9054cc39e336db0b532a5
3
  size 14054
run-1/checkpoint-96/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11606a3fe2610be2878eac5b9a478bb3687282988a72c7cf16c2b9960e57533c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cfbcdc81e5bd264efda8c8c919ca09fe2742ecdac83792b7c24b984f5a9552f
3
  size 1064
run-1/checkpoint-96/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.5,
3
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-96",
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
  "global_step": 96,
7
  "is_hyper_param_search": true,
@@ -10,36 +10,55 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "grad_norm": 0.40490686893463135,
14
- "learning_rate": 1.4953262133881219e-05,
15
- "loss": 0.1703,
16
- "step": 96
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_accuracy": 0.5,
21
- "eval_f1": 0.0,
22
- "eval_loss": 0.11485283076763153,
23
- "eval_precision": 0.0,
24
- "eval_recall": 0.0,
25
- "eval_runtime": 25.7126,
26
- "eval_samples_per_second": 39.747,
27
- "eval_steps_per_second": 1.245,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  "step": 96
29
  }
30
  ],
31
  "logging_steps": 500,
32
- "max_steps": 768,
33
  "num_input_tokens_seen": 0,
34
- "num_train_epochs": 8,
35
  "save_steps": 500,
36
- "total_flos": 235695197280.0,
37
- "train_batch_size": 32,
38
  "trial_name": null,
39
  "trial_params": {
40
- "alpha": 0.09656764013507046,
41
- "learning_rate": 1.7089442438721394e-05,
42
- "num_train_epochs": 8,
43
- "temperature": 20
44
  }
45
  }
 
1
  {
2
+ "best_metric": 0.7504892367906066,
3
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-96",
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 96,
7
  "is_hyper_param_search": true,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "grad_norm": 1.0160187482833862,
14
+ "learning_rate": 0.00031017361242620324,
15
+ "loss": 0.5046,
16
+ "step": 48
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_accuracy": 0.7338551859099804,
21
+ "eval_f1": 0.7399617590822181,
22
+ "eval_loss": 0.448641836643219,
23
+ "eval_precision": 0.7233644859813084,
24
+ "eval_recall": 0.7573385518590998,
25
+ "eval_runtime": 30.0153,
26
+ "eval_samples_per_second": 34.049,
27
+ "eval_steps_per_second": 0.533,
28
+ "step": 48
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 3.3045527935028076,
33
+ "learning_rate": 0.00015508680621310162,
34
+ "loss": 0.4485,
35
+ "step": 96
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.7504892367906066,
40
+ "eval_f1": 0.7395301327885597,
41
+ "eval_loss": 0.4257463812828064,
42
+ "eval_precision": 0.7735042735042735,
43
+ "eval_recall": 0.7084148727984344,
44
+ "eval_runtime": 28.6578,
45
+ "eval_samples_per_second": 35.662,
46
+ "eval_steps_per_second": 0.558,
47
  "step": 96
48
  }
49
  ],
50
  "logging_steps": 500,
51
+ "max_steps": 144,
52
  "num_input_tokens_seen": 0,
53
+ "num_train_epochs": 3,
54
  "save_steps": 500,
55
+ "total_flos": 471390394560.0,
56
+ "train_batch_size": 64,
57
  "trial_name": null,
58
  "trial_params": {
59
+ "alpha": 0.7333074246521317,
60
+ "learning_rate": 0.00046526041863930486,
61
+ "num_train_epochs": 3,
62
+ "temperature": 17
63
  }
64
  }
run-1/checkpoint-96/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40c83b924ef70318ad972d6c481c684f04bf59974ceae562e8816ac4c289de55
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2cac056bbb00ee08372e629f1f168fb88db9cbeb0daea6323374a9050531aaa
3
  size 4920