Hugging Face's logo

AAA01101312
/
distilbert-base-uncased-finetuned-clinc

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
AAA01101312 commited on
Commit
bf4c717
•
1 Parent(s): 1ea9819

Training in progress, step 3000

Browse files
Files changed (22) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-1000/model.safetensors +1 -1
  3. run-4/checkpoint-1000/optimizer.pt +1 -1
  4. run-4/checkpoint-1000/trainer_state.json +26 -26
  5. run-4/checkpoint-1000/training_args.bin +1 -1
  6. run-4/checkpoint-1500/model.safetensors +1 -1
  7. run-4/checkpoint-1500/optimizer.pt +1 -1
  8. run-4/checkpoint-1500/trainer_state.json +34 -34
  9. run-4/checkpoint-1500/training_args.bin +1 -1
  10. run-4/checkpoint-2000/model.safetensors +1 -1
  11. run-4/checkpoint-2000/optimizer.pt +1 -1
  12. run-4/checkpoint-2000/trainer_state.json +40 -40
  13. run-4/checkpoint-2000/training_args.bin +1 -1
  14. run-4/checkpoint-2500/model.safetensors +1 -1
  15. run-4/checkpoint-2500/optimizer.pt +1 -1
  16. run-4/checkpoint-2500/trainer_state.json +47 -47
  17. run-4/checkpoint-2500/training_args.bin +1 -1
  18. run-4/checkpoint-3000/model.safetensors +1 -1
  19. run-4/checkpoint-3000/optimizer.pt +1 -1
  20. run-4/checkpoint-3000/trainer_state.json +59 -59
  21. run-4/checkpoint-3000/training_args.bin +1 -1
  22. runs/May16_18-43-59_MainPC/events.out.tfevents.1715855009.MainPC.47240.6 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:513000c9350910760f72b409d0310b6ba1ed30f739b0e468591a5547835ab922
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7525456e4718a8232324e17900847eb138c40eb8a13f08af30897b05d4dbb20a
3
  size 268290900
run-4/checkpoint-1000/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90fb319836633e5e3f0b48e7d43b2eeb7597225e10f485c51b02cf8242b337b5
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:028fbb49d347081797ac0999252196a57a94b78597c1c8a1f4f6f8fb2eaa9e41
3
  size 268290900
run-4/checkpoint-1000/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:119b6c5a09777fbc6d80721e841b41ee9f3f0a54e9c3cf78c625743fd98267fb
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f4a5d1b423e306284efb8001567109e2465b350672f1a2ea8c05d24ecd22814
3
  size 536643898
run-4/checkpoint-1000/trainer_state.json CHANGED
@@ -10,57 +10,57 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.5703225806451613,
14
- "eval_loss": 0.2038404494524002,
15
- "eval_runtime": 13.9497,
16
- "eval_samples_per_second": 222.228,
17
- "eval_steps_per_second": 27.814,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
- "grad_norm": 0.5379030108451843,
23
- "learning_rate": 1.371069182389937e-05,
24
- "loss": 0.3188,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
- "eval_accuracy": 0.8025806451612904,
30
- "eval_loss": 0.1062638983130455,
31
- "eval_runtime": 14.8233,
32
- "eval_samples_per_second": 209.131,
33
- "eval_steps_per_second": 26.175,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
- "eval_accuracy": 0.8616129032258064,
39
- "eval_loss": 0.07635947316884995,
40
- "eval_runtime": 14.792,
41
- "eval_samples_per_second": 209.572,
42
- "eval_steps_per_second": 26.23,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
- "grad_norm": 0.4960978031158447,
48
- "learning_rate": 7.421383647798742e-06,
49
- "loss": 0.1224,
50
  "step": 1000
51
  }
52
  ],
53
  "logging_steps": 500,
54
- "max_steps": 1590,
55
  "num_input_tokens_seen": 0,
56
- "num_train_epochs": 5,
57
  "save_steps": 500,
58
  "total_flos": 260941334653608.0,
59
  "train_batch_size": 48,
60
  "trial_name": null,
61
  "trial_params": {
62
- "alpha": 0.763741239316905,
63
- "num_train_epochs": 5,
64
- "temperature": 14
65
  }
66
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.6119354838709677,
14
+ "eval_loss": 0.21851849555969238,
15
+ "eval_runtime": 14.6428,
16
+ "eval_samples_per_second": 211.708,
17
+ "eval_steps_per_second": 26.498,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.5758148431777954,
23
+ "learning_rate": 1.685534591194969e-05,
24
+ "loss": 0.3507,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.8316129032258065,
30
+ "eval_loss": 0.10097286105155945,
31
+ "eval_runtime": 15.6995,
32
+ "eval_samples_per_second": 197.458,
33
+ "eval_steps_per_second": 24.714,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
+ "eval_accuracy": 0.8925806451612903,
39
+ "eval_loss": 0.0633334368467331,
40
+ "eval_runtime": 15.4572,
41
+ "eval_samples_per_second": 200.553,
42
+ "eval_steps_per_second": 25.102,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.5545220375061035,
48
+ "learning_rate": 1.371069182389937e-05,
49
+ "loss": 0.117,
50
  "step": 1000
51
  }
52
  ],
53
  "logging_steps": 500,
54
+ "max_steps": 3180,
55
  "num_input_tokens_seen": 0,
56
+ "num_train_epochs": 10,
57
  "save_steps": 500,
58
  "total_flos": 260941334653608.0,
59
  "train_batch_size": 48,
60
  "trial_name": null,
61
  "trial_params": {
62
+ "alpha": 0.34904540498463477,
63
+ "num_train_epochs": 10,
64
+ "temperature": 6
65
  }
66
  }
run-4/checkpoint-1000/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a66cfc7c39943f27293f9732e22c6567521e8b36df99f44d48fe774ae957c9b9
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:288344ea2c5a779b9a25234da8b122db9300e5dd4f5af9aeef0293ff5355089b
3
  size 5048
run-4/checkpoint-1500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d2f004909c4c1c00205dfbb58cc5b713177ceabf4fd16c69d18341822949b30
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bda7e40d9985a53d5e03b9c8f7431813665bf3a4dea69e4756bf39e450636656
3
  size 268290900
run-4/checkpoint-1500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:885e16b8bdb444f9c960c95040ef982017f21111a95c1a7df3361823e863ba43
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c18137741ff71271478f6b8c48239158a6db6e3ba234f4e0360f10f9472f2f2c
3
  size 536643898
run-4/checkpoint-1500/trainer_state.json CHANGED
@@ -10,73 +10,73 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.5703225806451613,
14
- "eval_loss": 0.2038404494524002,
15
- "eval_runtime": 13.9497,
16
- "eval_samples_per_second": 222.228,
17
- "eval_steps_per_second": 27.814,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
- "grad_norm": 0.5379030108451843,
23
- "learning_rate": 1.371069182389937e-05,
24
- "loss": 0.3188,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
- "eval_accuracy": 0.8025806451612904,
30
- "eval_loss": 0.1062638983130455,
31
- "eval_runtime": 14.8233,
32
- "eval_samples_per_second": 209.131,
33
- "eval_steps_per_second": 26.175,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
- "eval_accuracy": 0.8616129032258064,
39
- "eval_loss": 0.07635947316884995,
40
- "eval_runtime": 14.792,
41
- "eval_samples_per_second": 209.572,
42
- "eval_steps_per_second": 26.23,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
- "grad_norm": 0.4960978031158447,
48
- "learning_rate": 7.421383647798742e-06,
49
- "loss": 0.1224,
50
  "step": 1000
51
  },
52
  {
53
  "epoch": 4.0,
54
- "eval_accuracy": 0.8803225806451613,
55
- "eval_loss": 0.06431956589221954,
56
- "eval_runtime": 15.2269,
57
- "eval_samples_per_second": 203.587,
58
- "eval_steps_per_second": 25.481,
59
  "step": 1272
60
  },
61
  {
62
  "epoch": 4.716981132075472,
63
- "grad_norm": 0.41756343841552734,
64
- "learning_rate": 1.1320754716981133e-06,
65
- "loss": 0.0882,
66
  "step": 1500
67
  }
68
  ],
69
  "logging_steps": 500,
70
- "max_steps": 1590,
71
  "num_input_tokens_seen": 0,
72
- "num_train_epochs": 5,
73
  "save_steps": 500,
74
  "total_flos": 391368939443328.0,
75
  "train_batch_size": 48,
76
  "trial_name": null,
77
  "trial_params": {
78
- "alpha": 0.763741239316905,
79
- "num_train_epochs": 5,
80
- "temperature": 14
81
  }
82
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.6119354838709677,
14
+ "eval_loss": 0.21851849555969238,
15
+ "eval_runtime": 14.6428,
16
+ "eval_samples_per_second": 211.708,
17
+ "eval_steps_per_second": 26.498,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.5758148431777954,
23
+ "learning_rate": 1.685534591194969e-05,
24
+ "loss": 0.3507,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.8316129032258065,
30
+ "eval_loss": 0.10097286105155945,
31
+ "eval_runtime": 15.6995,
32
+ "eval_samples_per_second": 197.458,
33
+ "eval_steps_per_second": 24.714,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
+ "eval_accuracy": 0.8925806451612903,
39
+ "eval_loss": 0.0633334368467331,
40
+ "eval_runtime": 15.4572,
41
+ "eval_samples_per_second": 200.553,
42
+ "eval_steps_per_second": 25.102,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.5545220375061035,
48
+ "learning_rate": 1.371069182389937e-05,
49
+ "loss": 0.117,
50
  "step": 1000
51
  },
52
  {
53
  "epoch": 4.0,
54
+ "eval_accuracy": 0.9067741935483871,
55
+ "eval_loss": 0.047307152301073074,
56
+ "eval_runtime": 15.418,
57
+ "eval_samples_per_second": 201.064,
58
+ "eval_steps_per_second": 25.165,
59
  "step": 1272
60
  },
61
  {
62
  "epoch": 4.716981132075472,
63
+ "grad_norm": 0.45056918263435364,
64
+ "learning_rate": 1.0566037735849058e-05,
65
+ "loss": 0.0714,
66
  "step": 1500
67
  }
68
  ],
69
  "logging_steps": 500,
70
+ "max_steps": 3180,
71
  "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 10,
73
  "save_steps": 500,
74
  "total_flos": 391368939443328.0,
75
  "train_batch_size": 48,
76
  "trial_name": null,
77
  "trial_params": {
78
+ "alpha": 0.34904540498463477,
79
+ "num_train_epochs": 10,
80
+ "temperature": 6
81
  }
82
  }
run-4/checkpoint-1500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a66cfc7c39943f27293f9732e22c6567521e8b36df99f44d48fe774ae957c9b9
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:288344ea2c5a779b9a25234da8b122db9300e5dd4f5af9aeef0293ff5355089b
3
  size 5048
run-4/checkpoint-2000/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:359410746234c163ce70887b8d9ac1bfca0cf3aec1de769839fe869e20e5ae72
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6673feb2e6d05f2178e5589377de2f094b3c3ba1b986c75f0c4f6d7f286a1095
3
  size 268290900
run-4/checkpoint-2000/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb4462d85dbc8ef13cccbcec8c44f6f8cf12cdc9da2e49e1c57c3369160040f7
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2e795e6f700372d706c8d958423aa3b288f0a7f855e12d10f03a4680ad33e6e
3
  size 536643898
run-4/checkpoint-2000/trainer_state.json CHANGED
@@ -10,84 +10,84 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.5812903225806452,
14
- "eval_loss": 0.18969474732875824,
15
- "eval_runtime": 16.6419,
16
- "eval_samples_per_second": 186.277,
17
- "eval_steps_per_second": 23.315,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
- "grad_norm": 0.5302444696426392,
23
  "learning_rate": 1.685534591194969e-05,
24
- "loss": 0.305,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
- "eval_accuracy": 0.8203225806451613,
30
- "eval_loss": 0.09268243610858917,
31
- "eval_runtime": 18.2398,
32
- "eval_samples_per_second": 169.958,
33
- "eval_steps_per_second": 21.272,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
- "eval_accuracy": 0.886774193548387,
39
- "eval_loss": 0.06108736991882324,
40
- "eval_runtime": 16.4288,
41
- "eval_samples_per_second": 188.693,
42
- "eval_steps_per_second": 23.617,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
- "grad_norm": 0.48521462082862854,
48
  "learning_rate": 1.371069182389937e-05,
49
- "loss": 0.1066,
50
  "step": 1000
51
  },
52
  {
53
  "epoch": 4.0,
54
- "eval_accuracy": 0.9003225806451612,
55
- "eval_loss": 0.04699072614312172,
56
- "eval_runtime": 17.4056,
57
- "eval_samples_per_second": 178.103,
58
- "eval_steps_per_second": 22.292,
59
  "step": 1272
60
  },
61
  {
62
  "epoch": 4.716981132075472,
63
- "grad_norm": 0.4145806133747101,
64
  "learning_rate": 1.0566037735849058e-05,
65
- "loss": 0.0679,
66
  "step": 1500
67
  },
68
  {
69
  "epoch": 5.0,
70
- "eval_accuracy": 0.9109677419354839,
71
- "eval_loss": 0.03902392089366913,
72
- "eval_runtime": 18.1001,
73
- "eval_samples_per_second": 171.27,
74
- "eval_steps_per_second": 21.436,
75
  "step": 1590
76
  },
77
  {
78
  "epoch": 6.0,
79
- "eval_accuracy": 0.9161290322580645,
80
- "eval_loss": 0.034090910106897354,
81
- "eval_runtime": 18.3997,
82
- "eval_samples_per_second": 168.481,
83
- "eval_steps_per_second": 21.087,
84
  "step": 1908
85
  },
86
  {
87
  "epoch": 6.289308176100629,
88
- "grad_norm": 0.18795175850391388,
89
  "learning_rate": 7.421383647798742e-06,
90
- "loss": 0.0533,
91
  "step": 2000
92
  }
93
  ],
@@ -100,8 +100,8 @@
100
  "train_batch_size": 48,
101
  "trial_name": null,
102
  "trial_params": {
103
- "alpha": 0.9919387893483188,
104
  "num_train_epochs": 10,
105
- "temperature": 20
106
  }
107
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.6119354838709677,
14
+ "eval_loss": 0.21851849555969238,
15
+ "eval_runtime": 14.6428,
16
+ "eval_samples_per_second": 211.708,
17
+ "eval_steps_per_second": 26.498,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.5758148431777954,
23
  "learning_rate": 1.685534591194969e-05,
24
+ "loss": 0.3507,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.8316129032258065,
30
+ "eval_loss": 0.10097286105155945,
31
+ "eval_runtime": 15.6995,
32
+ "eval_samples_per_second": 197.458,
33
+ "eval_steps_per_second": 24.714,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
+ "eval_accuracy": 0.8925806451612903,
39
+ "eval_loss": 0.0633334368467331,
40
+ "eval_runtime": 15.4572,
41
+ "eval_samples_per_second": 200.553,
42
+ "eval_steps_per_second": 25.102,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.5545220375061035,
48
  "learning_rate": 1.371069182389937e-05,
49
+ "loss": 0.117,
50
  "step": 1000
51
  },
52
  {
53
  "epoch": 4.0,
54
+ "eval_accuracy": 0.9067741935483871,
55
+ "eval_loss": 0.047307152301073074,
56
+ "eval_runtime": 15.418,
57
+ "eval_samples_per_second": 201.064,
58
+ "eval_steps_per_second": 25.165,
59
  "step": 1272
60
  },
61
  {
62
  "epoch": 4.716981132075472,
63
+ "grad_norm": 0.45056918263435364,
64
  "learning_rate": 1.0566037735849058e-05,
65
+ "loss": 0.0714,
66
  "step": 1500
67
  },
68
  {
69
  "epoch": 5.0,
70
+ "eval_accuracy": 0.9141935483870968,
71
+ "eval_loss": 0.038757938891649246,
72
+ "eval_runtime": 15.3618,
73
+ "eval_samples_per_second": 201.799,
74
+ "eval_steps_per_second": 25.257,
75
  "step": 1590
76
  },
77
  {
78
  "epoch": 6.0,
79
+ "eval_accuracy": 0.9229032258064516,
80
+ "eval_loss": 0.03357065096497536,
81
+ "eval_runtime": 16.1719,
82
+ "eval_samples_per_second": 191.69,
83
+ "eval_steps_per_second": 23.992,
84
  "step": 1908
85
  },
86
  {
87
  "epoch": 6.289308176100629,
88
+ "grad_norm": 0.20387595891952515,
89
  "learning_rate": 7.421383647798742e-06,
90
+ "loss": 0.0552,
91
  "step": 2000
92
  }
93
  ],
 
100
  "train_batch_size": 48,
101
  "trial_name": null,
102
  "trial_params": {
103
+ "alpha": 0.34904540498463477,
104
  "num_train_epochs": 10,
105
+ "temperature": 6
106
  }
107
  }
run-4/checkpoint-2000/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a66cfc7c39943f27293f9732e22c6567521e8b36df99f44d48fe774ae957c9b9
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:288344ea2c5a779b9a25234da8b122db9300e5dd4f5af9aeef0293ff5355089b
3
  size 5048
run-4/checkpoint-2500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ceb2554cf014e9818e96fc6ebf5512f3a57e470d52af1aebb2e048cff2a88f5
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:572fbd965872603a15db432f28a4864a0433c797546c17bff8442b24f46c0c30
3
  size 268290900
run-4/checkpoint-2500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf92644aa54d3e38c274fa6229013e9576eedc87c830acd50c7b76a47343e987
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b256e075efc427cd38ec955e7aa34d6ce6e37d3bcc2f87268ad9d516528696c6
3
  size 536643898
run-4/checkpoint-2500/trainer_state.json CHANGED
@@ -10,100 +10,100 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.5812903225806452,
14
- "eval_loss": 0.18969474732875824,
15
- "eval_runtime": 16.6419,
16
- "eval_samples_per_second": 186.277,
17
- "eval_steps_per_second": 23.315,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
- "grad_norm": 0.5302444696426392,
23
  "learning_rate": 1.685534591194969e-05,
24
- "loss": 0.305,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
- "eval_accuracy": 0.8203225806451613,
30
- "eval_loss": 0.09268243610858917,
31
- "eval_runtime": 18.2398,
32
- "eval_samples_per_second": 169.958,
33
- "eval_steps_per_second": 21.272,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
- "eval_accuracy": 0.886774193548387,
39
- "eval_loss": 0.06108736991882324,
40
- "eval_runtime": 16.4288,
41
- "eval_samples_per_second": 188.693,
42
- "eval_steps_per_second": 23.617,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
- "grad_norm": 0.48521462082862854,
48
  "learning_rate": 1.371069182389937e-05,
49
- "loss": 0.1066,
50
  "step": 1000
51
  },
52
  {
53
  "epoch": 4.0,
54
- "eval_accuracy": 0.9003225806451612,
55
- "eval_loss": 0.04699072614312172,
56
- "eval_runtime": 17.4056,
57
- "eval_samples_per_second": 178.103,
58
- "eval_steps_per_second": 22.292,
59
  "step": 1272
60
  },
61
  {
62
  "epoch": 4.716981132075472,
63
- "grad_norm": 0.4145806133747101,
64
  "learning_rate": 1.0566037735849058e-05,
65
- "loss": 0.0679,
66
  "step": 1500
67
  },
68
  {
69
  "epoch": 5.0,
70
- "eval_accuracy": 0.9109677419354839,
71
- "eval_loss": 0.03902392089366913,
72
- "eval_runtime": 18.1001,
73
- "eval_samples_per_second": 171.27,
74
- "eval_steps_per_second": 21.436,
75
  "step": 1590
76
  },
77
  {
78
  "epoch": 6.0,
79
- "eval_accuracy": 0.9161290322580645,
80
- "eval_loss": 0.034090910106897354,
81
- "eval_runtime": 18.3997,
82
- "eval_samples_per_second": 168.481,
83
- "eval_steps_per_second": 21.087,
84
  "step": 1908
85
  },
86
  {
87
  "epoch": 6.289308176100629,
88
- "grad_norm": 0.18795175850391388,
89
  "learning_rate": 7.421383647798742e-06,
90
- "loss": 0.0533,
91
  "step": 2000
92
  },
93
  {
94
  "epoch": 7.0,
95
- "eval_accuracy": 0.9245161290322581,
96
- "eval_loss": 0.03126291185617447,
97
- "eval_runtime": 19.8482,
98
- "eval_samples_per_second": 156.186,
99
- "eval_steps_per_second": 19.548,
100
  "step": 2226
101
  },
102
  {
103
  "epoch": 7.861635220125786,
104
- "grad_norm": 0.2161731868982315,
105
  "learning_rate": 4.276729559748428e-06,
106
- "loss": 0.0461,
107
  "step": 2500
108
  }
109
  ],
@@ -116,8 +116,8 @@
116
  "train_batch_size": 48,
117
  "trial_name": null,
118
  "trial_params": {
119
- "alpha": 0.9919387893483188,
120
  "num_train_epochs": 10,
121
- "temperature": 20
122
  }
123
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.6119354838709677,
14
+ "eval_loss": 0.21851849555969238,
15
+ "eval_runtime": 14.6428,
16
+ "eval_samples_per_second": 211.708,
17
+ "eval_steps_per_second": 26.498,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.5758148431777954,
23
  "learning_rate": 1.685534591194969e-05,
24
+ "loss": 0.3507,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.8316129032258065,
30
+ "eval_loss": 0.10097286105155945,
31
+ "eval_runtime": 15.6995,
32
+ "eval_samples_per_second": 197.458,
33
+ "eval_steps_per_second": 24.714,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
+ "eval_accuracy": 0.8925806451612903,
39
+ "eval_loss": 0.0633334368467331,
40
+ "eval_runtime": 15.4572,
41
+ "eval_samples_per_second": 200.553,
42
+ "eval_steps_per_second": 25.102,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.5545220375061035,
48
  "learning_rate": 1.371069182389937e-05,
49
+ "loss": 0.117,
50
  "step": 1000
51
  },
52
  {
53
  "epoch": 4.0,
54
+ "eval_accuracy": 0.9067741935483871,
55
+ "eval_loss": 0.047307152301073074,
56
+ "eval_runtime": 15.418,
57
+ "eval_samples_per_second": 201.064,
58
+ "eval_steps_per_second": 25.165,
59
  "step": 1272
60
  },
61
  {
62
  "epoch": 4.716981132075472,
63
+ "grad_norm": 0.45056918263435364,
64
  "learning_rate": 1.0566037735849058e-05,
65
+ "loss": 0.0714,
66
  "step": 1500
67
  },
68
  {
69
  "epoch": 5.0,
70
+ "eval_accuracy": 0.9141935483870968,
71
+ "eval_loss": 0.038757938891649246,
72
+ "eval_runtime": 15.3618,
73
+ "eval_samples_per_second": 201.799,
74
+ "eval_steps_per_second": 25.257,
75
  "step": 1590
76
  },
77
  {
78
  "epoch": 6.0,
79
+ "eval_accuracy": 0.9229032258064516,
80
+ "eval_loss": 0.03357065096497536,
81
+ "eval_runtime": 16.1719,
82
+ "eval_samples_per_second": 191.69,
83
+ "eval_steps_per_second": 23.992,
84
  "step": 1908
85
  },
86
  {
87
  "epoch": 6.289308176100629,
88
+ "grad_norm": 0.20387595891952515,
89
  "learning_rate": 7.421383647798742e-06,
90
+ "loss": 0.0552,
91
  "step": 2000
92
  },
93
  {
94
  "epoch": 7.0,
95
+ "eval_accuracy": 0.9251612903225807,
96
+ "eval_loss": 0.03070036694407463,
97
+ "eval_runtime": 16.0649,
98
+ "eval_samples_per_second": 192.967,
99
+ "eval_steps_per_second": 24.152,
100
  "step": 2226
101
  },
102
  {
103
  "epoch": 7.861635220125786,
104
+ "grad_norm": 0.23086586594581604,
105
  "learning_rate": 4.276729559748428e-06,
106
+ "loss": 0.0475,
107
  "step": 2500
108
  }
109
  ],
 
116
  "train_batch_size": 48,
117
  "trial_name": null,
118
  "trial_params": {
119
+ "alpha": 0.34904540498463477,
120
  "num_train_epochs": 10,
121
+ "temperature": 6
122
  }
123
  }
run-4/checkpoint-2500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a66cfc7c39943f27293f9732e22c6567521e8b36df99f44d48fe774ae957c9b9
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:288344ea2c5a779b9a25234da8b122db9300e5dd4f5af9aeef0293ff5355089b
3
  size 5048
run-4/checkpoint-3000/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c33463d6ec2802fe1de33edc6d80b10919f53e8d7c4b000d67ce35557dbe893
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7525456e4718a8232324e17900847eb138c40eb8a13f08af30897b05d4dbb20a
3
  size 268290900
run-4/checkpoint-3000/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65946cca4caeb6a2904195868ac20853f6a8e817c5c67510884df48f8f206072
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cecd93facce0cc82e700843896f4c276853f4de13aff81a48c0f0a79da7ddbbc
3
  size 536643898
run-4/checkpoint-3000/trainer_state.json CHANGED
@@ -10,125 +10,125 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.5812903225806452,
14
- "eval_loss": 0.18969474732875824,
15
- "eval_runtime": 16.6419,
16
- "eval_samples_per_second": 186.277,
17
- "eval_steps_per_second": 23.315,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
- "grad_norm": 0.5302444696426392,
23
  "learning_rate": 1.685534591194969e-05,
24
- "loss": 0.305,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
- "eval_accuracy": 0.8203225806451613,
30
- "eval_loss": 0.09268243610858917,
31
- "eval_runtime": 18.2398,
32
- "eval_samples_per_second": 169.958,
33
- "eval_steps_per_second": 21.272,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
- "eval_accuracy": 0.886774193548387,
39
- "eval_loss": 0.06108736991882324,
40
- "eval_runtime": 16.4288,
41
- "eval_samples_per_second": 188.693,
42
- "eval_steps_per_second": 23.617,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
- "grad_norm": 0.48521462082862854,
48
  "learning_rate": 1.371069182389937e-05,
49
- "loss": 0.1066,
50
  "step": 1000
51
  },
52
  {
53
  "epoch": 4.0,
54
- "eval_accuracy": 0.9003225806451612,
55
- "eval_loss": 0.04699072614312172,
56
- "eval_runtime": 17.4056,
57
- "eval_samples_per_second": 178.103,
58
- "eval_steps_per_second": 22.292,
59
  "step": 1272
60
  },
61
  {
62
  "epoch": 4.716981132075472,
63
- "grad_norm": 0.4145806133747101,
64
  "learning_rate": 1.0566037735849058e-05,
65
- "loss": 0.0679,
66
  "step": 1500
67
  },
68
  {
69
  "epoch": 5.0,
70
- "eval_accuracy": 0.9109677419354839,
71
- "eval_loss": 0.03902392089366913,
72
- "eval_runtime": 18.1001,
73
- "eval_samples_per_second": 171.27,
74
- "eval_steps_per_second": 21.436,
75
  "step": 1590
76
  },
77
  {
78
  "epoch": 6.0,
79
- "eval_accuracy": 0.9161290322580645,
80
- "eval_loss": 0.034090910106897354,
81
- "eval_runtime": 18.3997,
82
- "eval_samples_per_second": 168.481,
83
- "eval_steps_per_second": 21.087,
84
  "step": 1908
85
  },
86
  {
87
  "epoch": 6.289308176100629,
88
- "grad_norm": 0.18795175850391388,
89
  "learning_rate": 7.421383647798742e-06,
90
- "loss": 0.0533,
91
  "step": 2000
92
  },
93
  {
94
  "epoch": 7.0,
95
- "eval_accuracy": 0.9245161290322581,
96
- "eval_loss": 0.03126291185617447,
97
- "eval_runtime": 19.8482,
98
- "eval_samples_per_second": 156.186,
99
- "eval_steps_per_second": 19.548,
100
  "step": 2226
101
  },
102
  {
103
  "epoch": 7.861635220125786,
104
- "grad_norm": 0.2161731868982315,
105
  "learning_rate": 4.276729559748428e-06,
106
- "loss": 0.0461,
107
  "step": 2500
108
  },
109
  {
110
  "epoch": 8.0,
111
- "eval_accuracy": 0.9261290322580645,
112
- "eval_loss": 0.029236024245619774,
113
- "eval_runtime": 17.0647,
114
- "eval_samples_per_second": 181.662,
115
- "eval_steps_per_second": 22.737,
116
  "step": 2544
117
  },
118
  {
119
  "epoch": 9.0,
120
- "eval_accuracy": 0.927741935483871,
121
- "eval_loss": 0.028154419735074043,
122
- "eval_runtime": 17.2404,
123
- "eval_samples_per_second": 179.81,
124
- "eval_steps_per_second": 22.505,
125
  "step": 2862
126
  },
127
  {
128
  "epoch": 9.433962264150944,
129
- "grad_norm": 0.3478936553001404,
130
  "learning_rate": 1.1320754716981133e-06,
131
- "loss": 0.0426,
132
  "step": 3000
133
  }
134
  ],
@@ -141,8 +141,8 @@
141
  "train_batch_size": 48,
142
  "trial_name": null,
143
  "trial_params": {
144
- "alpha": 0.9919387893483188,
145
  "num_train_epochs": 10,
146
- "temperature": 20
147
  }
148
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.6119354838709677,
14
+ "eval_loss": 0.21851849555969238,
15
+ "eval_runtime": 14.6428,
16
+ "eval_samples_per_second": 211.708,
17
+ "eval_steps_per_second": 26.498,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.5758148431777954,
23
  "learning_rate": 1.685534591194969e-05,
24
+ "loss": 0.3507,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.8316129032258065,
30
+ "eval_loss": 0.10097286105155945,
31
+ "eval_runtime": 15.6995,
32
+ "eval_samples_per_second": 197.458,
33
+ "eval_steps_per_second": 24.714,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
+ "eval_accuracy": 0.8925806451612903,
39
+ "eval_loss": 0.0633334368467331,
40
+ "eval_runtime": 15.4572,
41
+ "eval_samples_per_second": 200.553,
42
+ "eval_steps_per_second": 25.102,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.5545220375061035,
48
  "learning_rate": 1.371069182389937e-05,
49
+ "loss": 0.117,
50
  "step": 1000
51
  },
52
  {
53
  "epoch": 4.0,
54
+ "eval_accuracy": 0.9067741935483871,
55
+ "eval_loss": 0.047307152301073074,
56
+ "eval_runtime": 15.418,
57
+ "eval_samples_per_second": 201.064,
58
+ "eval_steps_per_second": 25.165,
59
  "step": 1272
60
  },
61
  {
62
  "epoch": 4.716981132075472,
63
+ "grad_norm": 0.45056918263435364,
64
  "learning_rate": 1.0566037735849058e-05,
65
+ "loss": 0.0714,
66
  "step": 1500
67
  },
68
  {
69
  "epoch": 5.0,
70
+ "eval_accuracy": 0.9141935483870968,
71
+ "eval_loss": 0.038757938891649246,
72
+ "eval_runtime": 15.3618,
73
+ "eval_samples_per_second": 201.799,
74
+ "eval_steps_per_second": 25.257,
75
  "step": 1590
76
  },
77
  {
78
  "epoch": 6.0,
79
+ "eval_accuracy": 0.9229032258064516,
80
+ "eval_loss": 0.03357065096497536,
81
+ "eval_runtime": 16.1719,
82
+ "eval_samples_per_second": 191.69,
83
+ "eval_steps_per_second": 23.992,
84
  "step": 1908
85
  },
86
  {
87
  "epoch": 6.289308176100629,
88
+ "grad_norm": 0.20387595891952515,
89
  "learning_rate": 7.421383647798742e-06,
90
+ "loss": 0.0552,
91
  "step": 2000
92
  },
93
  {
94
  "epoch": 7.0,
95
+ "eval_accuracy": 0.9251612903225807,
96
+ "eval_loss": 0.03070036694407463,
97
+ "eval_runtime": 16.0649,
98
+ "eval_samples_per_second": 192.967,
99
+ "eval_steps_per_second": 24.152,
100
  "step": 2226
101
  },
102
  {
103
  "epoch": 7.861635220125786,
104
+ "grad_norm": 0.23086586594581604,
105
  "learning_rate": 4.276729559748428e-06,
106
+ "loss": 0.0475,
107
  "step": 2500
108
  },
109
  {
110
  "epoch": 8.0,
111
+ "eval_accuracy": 0.9293548387096774,
112
+ "eval_loss": 0.02869473211467266,
113
+ "eval_runtime": 14.6771,
114
+ "eval_samples_per_second": 211.213,
115
+ "eval_steps_per_second": 26.436,
116
  "step": 2544
117
  },
118
  {
119
  "epoch": 9.0,
120
+ "eval_accuracy": 0.9303225806451613,
121
+ "eval_loss": 0.02764182724058628,
122
+ "eval_runtime": 14.4803,
123
+ "eval_samples_per_second": 214.084,
124
+ "eval_steps_per_second": 26.795,
125
  "step": 2862
126
  },
127
  {
128
  "epoch": 9.433962264150944,
129
+ "grad_norm": 0.3526463508605957,
130
  "learning_rate": 1.1320754716981133e-06,
131
+ "loss": 0.0438,
132
  "step": 3000
133
  }
134
  ],
 
141
  "train_batch_size": 48,
142
  "trial_name": null,
143
  "trial_params": {
144
+ "alpha": 0.34904540498463477,
145
  "num_train_epochs": 10,
146
+ "temperature": 6
147
  }
148
  }
run-4/checkpoint-3000/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a66cfc7c39943f27293f9732e22c6567521e8b36df99f44d48fe774ae957c9b9
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:288344ea2c5a779b9a25234da8b122db9300e5dd4f5af9aeef0293ff5355089b
3
  size 5048
runs/May16_18-43-59_MainPC/events.out.tfevents.1715855009.MainPC.47240.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f43b054ddedad22ef820ea46e013b99e9760ab7535ccb3584daa8ef0a000784
3
- size 13063
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53520b8a128f05b483e9e4ef2efec32a28f9900613cee893e45bfd51103cf28d
3
+ size 17056