xuancoblab2023 commited on
Commit
6ac55cc
·
verified ·
1 Parent(s): daacb7b

Training in progress, epoch 2

Browse files
logs/events.out.tfevents.1709873105.6c1c016b0e3e.7263.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c606c6617970d00e37b728825fe34ab0600ee0df29c0898b736daac5af95a2fc
3
- size 5315
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e02051e0a7a897800bcf26b8f0e60cc460e465af7ae9a1bd29949732048c500c
3
+ size 5985
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08489a9fe2e8e7308035654ca4ecc91184bdec8ccc939b0c60c8c8275163216f
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:027f944e44af1eaec5ae46500414fc47d47670da97d38e5396af0b24fc222f08
3
  size 17549312
run-2/checkpoint-96/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5644bcb574816e1042db1d1e6d08ff16aa796e73a86c71d60b9aec93a506fd92
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:027f944e44af1eaec5ae46500414fc47d47670da97d38e5396af0b24fc222f08
3
  size 17549312
run-2/checkpoint-96/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f64c70665c1be51ebd49b574c4c38384c597ad0a4586e9db29a1f83bdca34fad
3
  size 35122746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f55c7597beb9f82880a8d225baacd457b8c18a88cc34d52fb3a8a57e6449761
3
  size 35122746
run-2/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-2/checkpoint-96/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ceb162ca593cfdf8b2d65521bfd20053a19daf6bc7f82e2b6abc1514a663ea39
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af54281ae35bcd4ce6fb4ef67df558eb1b05d353c140e2c290551d541cb38ab8
3
  size 1064
run-2/checkpoint-96/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.512720156555773,
3
- "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/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": 0.3969263434410095,
14
- "learning_rate": 3.130245712253287e-05,
15
- "loss": 0.081,
16
- "step": 96
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_accuracy": 0.512720156555773,
21
- "eval_f1": 0.08118081180811808,
22
- "eval_loss": 0.03750595450401306,
23
- "eval_precision": 0.7096774193548387,
24
- "eval_recall": 0.043052837573385516,
25
- "eval_runtime": 25.4915,
26
- "eval_samples_per_second": 40.092,
27
- "eval_steps_per_second": 1.255,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  "step": 96
29
  }
30
  ],
31
  "logging_steps": 500,
32
- "max_steps": 288,
33
  "num_input_tokens_seen": 0,
34
  "num_train_epochs": 3,
35
  "save_steps": 500,
36
- "total_flos": 235695197280.0,
37
- "train_batch_size": 32,
38
  "trial_name": null,
39
  "trial_params": {
40
- "alpha": 0.022604047006827055,
41
- "learning_rate": 4.6953685683799313e-05,
42
  "num_train_epochs": 3,
43
- "temperature": 5
44
  }
45
  }
 
1
  {
2
+ "best_metric": 0.5,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-48",
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": 1.6336328983306885,
14
+ "learning_rate": 8.611669739559475e-06,
15
+ "loss": 0.3627,
16
+ "step": 48
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_accuracy": 0.5,
21
+ "eval_f1": 0.0,
22
+ "eval_loss": 0.31828778982162476,
23
+ "eval_precision": 0.0,
24
+ "eval_recall": 0.0,
25
+ "eval_runtime": 28.8885,
26
+ "eval_samples_per_second": 35.377,
27
+ "eval_steps_per_second": 0.554,
28
+ "step": 48
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 0.23749461770057678,
33
+ "learning_rate": 4.3058348697797375e-06,
34
+ "loss": 0.3092,
35
+ "step": 96
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.5,
40
+ "eval_f1": 0.0,
41
+ "eval_loss": 0.29845258593559265,
42
+ "eval_precision": 0.0,
43
+ "eval_recall": 0.0,
44
+ "eval_runtime": 28.7105,
45
+ "eval_samples_per_second": 35.597,
46
+ "eval_steps_per_second": 0.557,
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": 0.340965759348954,
60
+ "learning_rate": 1.2917504609339214e-05,
61
  "num_train_epochs": 3,
62
+ "temperature": 24
63
  }
64
  }
run-2/checkpoint-96/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25a5bc2ca31318692bb3d061ec3f8db53d887cf60ae54f3c3e0e26465b0b418c
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32b5b7e0dad7d232fde0da98a1e8adb7093a00c985e2ed22cef4c6876c31ee03
3
  size 4920