xuancoblab2023 commited on
Commit
3c87c0a
·
verified ·
1 Parent(s): c6bc1ae

Training in progress, epoch 2

Browse files
logs/events.out.tfevents.1709718096.adc675a344d5.67573.5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76993f5e85ffe1b3d2a8c7e4936e214f89f887a4ffd429aea3ee179d7fbb691a
3
- size 5314
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1a76573fcb36df9088e4f12fdddff1f1588cbda95ea5777c00266ed9b539456
3
+ size 5997
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03de7b47dbf2c7a75f6e9ae666c226fd153cbe25b9dde09fbdac73c4e190baef
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5430bb58ad9fbed27d897dbca986fb9ada5c6ce559d513d534cd9add5bc0da28
3
  size 17549312
run-4/checkpoint-192/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4499f6d9222de5ae0ef237a0c6017e9c53b42ad7c245aec429750388d1e77061
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5430bb58ad9fbed27d897dbca986fb9ada5c6ce559d513d534cd9add5bc0da28
3
  size 17549312
run-4/checkpoint-192/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6427e5a4bbcadae4986fd3e45d0a9e07d9bf4eaa38b53d2a27103df9378bef49
3
  size 35122746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3afe3a7ec7130ac575ecbf6dc22677a77450bddd0907bb2d6605e8273382d2d
3
  size 35122746
run-4/checkpoint-192/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa0492d94293a91d4b6327f95fe1294ef015dac6e23fc6f9a11054ea28fdceed
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:781933fd4f5b6431d85587564f8cc58517f9a591cacd359c74fa48d92e8c6c77
3
  size 1064
run-4/checkpoint-192/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.5,
3
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-96",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
@@ -10,55 +10,55 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "grad_norm": 0.6504594683647156,
14
- "learning_rate": 7.787665972957169e-06,
15
- "loss": 0.59,
16
  "step": 96
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_accuracy": 0.5,
21
- "eval_f1": 0.0,
22
- "eval_loss": 0.5820541977882385,
23
- "eval_precision": 0.0,
24
- "eval_recall": 0.0,
25
- "eval_runtime": 28.7531,
26
- "eval_samples_per_second": 35.544,
27
- "eval_steps_per_second": 1.113,
28
  "step": 96
29
  },
30
  {
31
  "epoch": 2.0,
32
- "grad_norm": 1.676121711730957,
33
- "learning_rate": 0.0,
34
- "loss": 0.5817,
35
  "step": 192
36
  },
37
  {
38
  "epoch": 2.0,
39
- "eval_accuracy": 0.5,
40
- "eval_f1": 0.0,
41
- "eval_loss": 0.5805695652961731,
42
- "eval_precision": 0.0,
43
- "eval_recall": 0.0,
44
- "eval_runtime": 29.5026,
45
- "eval_samples_per_second": 34.641,
46
- "eval_steps_per_second": 1.085,
47
  "step": 192
48
  }
49
  ],
50
  "logging_steps": 500,
51
- "max_steps": 192,
52
  "num_input_tokens_seen": 0,
53
- "num_train_epochs": 2,
54
  "save_steps": 500,
55
  "total_flos": 471390394560.0,
56
  "train_batch_size": 32,
57
  "trial_name": null,
58
  "trial_params": {
59
- "alpha": 0.7979164056999755,
60
- "learning_rate": 1.5575331945914338e-05,
61
- "num_train_epochs": 2,
62
- "temperature": 5
63
  }
64
  }
 
1
  {
2
+ "best_metric": 0.541095890410959,
3
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-96",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "grad_norm": 0.4191925525665283,
14
+ "learning_rate": 0.00022738674133918383,
15
+ "loss": 0.098,
16
  "step": 96
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_accuracy": 0.541095890410959,
21
+ "eval_f1": 0.20642978003384094,
22
+ "eval_loss": 0.08223184198141098,
23
+ "eval_precision": 0.7625,
24
+ "eval_recall": 0.11937377690802348,
25
+ "eval_runtime": 28.0826,
26
+ "eval_samples_per_second": 36.393,
27
+ "eval_steps_per_second": 1.139,
28
  "step": 96
29
  },
30
  {
31
  "epoch": 2.0,
32
+ "grad_norm": 0.35244929790496826,
33
+ "learning_rate": 0.00017054005600438787,
34
+ "loss": 0.0833,
35
  "step": 192
36
  },
37
  {
38
  "epoch": 2.0,
39
+ "eval_accuracy": 0.5371819960861057,
40
+ "eval_f1": 0.19145299145299144,
41
+ "eval_loss": 0.07941487431526184,
42
+ "eval_precision": 0.7567567567567568,
43
+ "eval_recall": 0.1095890410958904,
44
+ "eval_runtime": 28.0455,
45
+ "eval_samples_per_second": 36.441,
46
+ "eval_steps_per_second": 1.141,
47
  "step": 192
48
  }
49
  ],
50
  "logging_steps": 500,
51
+ "max_steps": 480,
52
  "num_input_tokens_seen": 0,
53
+ "num_train_epochs": 5,
54
  "save_steps": 500,
55
  "total_flos": 471390394560.0,
56
  "train_batch_size": 32,
57
  "trial_name": null,
58
  "trial_params": {
59
+ "alpha": 0.09292461434001364,
60
+ "learning_rate": 0.0002842334266739798,
61
+ "num_train_epochs": 5,
62
+ "temperature": 2
63
  }
64
  }
run-4/checkpoint-192/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d75bccfe6c5373ca9b1b18dfaff7dd2ce79806a7acbd4f6cd52c93fdf2f1e00c
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f441eefbf68b7466d3f5396e1b086e4cb1ae1be01fffc857e92bd1ad437f6f6d
3
  size 4920