Hugging Face's logo

saqidr
/
distilbert-base-uncased-finetuned-clinc

Text Classification
Transformers
Safetensors
distilbert
Generated from Trainer
Model card Files Community
saqidr commited on
Commit
f554fcc
·
verified ·
1 Parent(s): d1f1c47

Training in progress, step 500

Browse files
Files changed (30) hide show
  1. model.safetensors +1 -1
  2. run-3/checkpoint-1500/model.safetensors +1 -1
  3. run-3/checkpoint-1500/optimizer.pt +1 -1
  4. run-3/checkpoint-1500/scheduler.pt +1 -1
  5. run-3/checkpoint-1500/training_args.bin +1 -1
  6. run-3/checkpoint-2000/model.safetensors +1 -1
  7. run-3/checkpoint-2000/optimizer.pt +1 -1
  8. run-3/checkpoint-2000/rng_state.pth +1 -1
  9. run-3/checkpoint-2000/scheduler.pt +1 -1
  10. run-3/checkpoint-2000/training_args.bin +2 -2
  11. run-3/checkpoint-2500/model.safetensors +1 -1
  12. run-3/checkpoint-2500/optimizer.pt +1 -1
  13. run-3/checkpoint-2500/rng_state.pth +1 -1
  14. run-3/checkpoint-2500/scheduler.pt +1 -1
  15. run-3/checkpoint-2500/training_args.bin +2 -2
  16. run-4/checkpoint-1000/model.safetensors +1 -1
  17. run-4/checkpoint-1000/optimizer.pt +1 -1
  18. run-4/checkpoint-1000/scheduler.pt +1 -1
  19. run-4/checkpoint-1000/trainer_state.json +26 -26
  20. run-4/checkpoint-1000/training_args.bin +1 -1
  21. run-4/checkpoint-1500/trainer_state.json +34 -34
  22. run-4/checkpoint-2000/config.json +1 -1
  23. run-4/checkpoint-2000/tokenizer.json +1 -6
  24. run-4/checkpoint-2000/trainer_state.json +64 -48
  25. run-4/checkpoint-500/model.safetensors +1 -1
  26. run-4/checkpoint-500/optimizer.pt +1 -1
  27. run-4/checkpoint-500/scheduler.pt +1 -1
  28. run-4/checkpoint-500/trainer_state.json +13 -13
  29. run-4/checkpoint-500/training_args.bin +1 -1
  30. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25f9d6eb5310fb82fd6d0ce02178e219ef280bfac553ca1e5a08cd0dd16f2028
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ed14a983a063b04b5c0e74f719ee953be8e1b478635360e23a0e81062435df
3
  size 268290900
run-3/checkpoint-1500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ce6a8d6a2ddc42d2f7a0903ec52cdb67f79140c9170fe2f49c5abde5a22f79e
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be04168dc7be8da250928988bf17604eb311728b77431db006a87e6cdf44b925
3
  size 268290900
run-3/checkpoint-1500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:883e721368ca520d8121d0b6b9e044d30529afd9b189b189f45154be1e438177
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fdf78e62c50159c13ab61cc3114252242931c3b2320d283020feb657634065e
3
  size 536643898
run-3/checkpoint-1500/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91d97f7c1be085852e2ffd2fe2f8a493a080e2b2858e2f3baf642fe214e035a0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb7b4645e59a5c5cb66f63e8bcb5f006c535fd0ea63db9ae152dd586fd465b28
3
  size 1064
run-3/checkpoint-1500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e2a1cb9dd55c40858a3ac6c021e84bbe7db57465df0ba06d3a7ad08deec13ce
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:699ed76d9af91edc99d12562d64ce4055f71cfe483dfd9ab44c7bfc8626ae66f
3
  size 5176
run-3/checkpoint-2000/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd93e19ecc67393491b108663bf9e8f2cd93091768c0668d5fcad9c3c5db3172
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbc430ca972e4915f7e40ba7615d59d70ca47f2b0727f0c95da5ffceb380f1df
3
  size 268290900
run-3/checkpoint-2000/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b87ef1a649212e117f053a32a617188420b6eeef8f548ac9be9cda2c7cdd34c
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b59205793ea42649581f38dacdae9be8afe2e5dc8533fbee9f7826e3abe24f5f
3
  size 536643898
run-3/checkpoint-2000/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5613af56824b89d2251abc079d69f51d9497a128212db6eb459f4c957e78a29b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37ccc14cc902672c3d8e770c2a2ce3a532b454981f3118cb18a09274102a99fc
3
  size 14244
run-3/checkpoint-2000/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f38866eaf1d2baeb52a55cb38ece6ee67f3213265b0830dd06c82a9148795bea
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bf6d4c2c13eda2c2dfacdbfc8684055c5603a92b6c0c386d7c757b108195d12
3
  size 1064
run-3/checkpoint-2000/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5611087a59c27110dfadc095996a5f95bfe2777397c4da221bd4c2a70a5d72e9
3
- size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:699ed76d9af91edc99d12562d64ce4055f71cfe483dfd9ab44c7bfc8626ae66f
3
+ size 5176
run-3/checkpoint-2500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63d794558c646f21a5e2e723f335d4aa8f5ed40f4a7d4e1a1b0c6abe55f66b1b
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06974de4a1af0dd9e90a57feb31998b8735e2e401fe51805ef57f9ec68302c95
3
  size 268290900
run-3/checkpoint-2500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f36592e8560a10668b5ee1cdb5b15c6fba8a833b0876cddd33c359dcbe28dd4d
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34cf3a2bca3e265a2ef554e3e08a742e0e71f9f5e12e5b8f8c279cd43887f184
3
  size 536643898
run-3/checkpoint-2500/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:983ad82afbb61099978c5b5a095761d0cc8a5b9889d078c9a1fcb9751b84b6be
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fe590653dc8c7914203f68b195f5118633e21a9fa30a5fcd6f1518bae980ac9
3
  size 14244
run-3/checkpoint-2500/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7c943a77651a184c6653dd4706c14c9a27d52136e81942a2b361c74acb9f665
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b997ea9328158f28ff50e49c476931e703b821360bc8325e0c4d100e032c865
3
  size 1064
run-3/checkpoint-2500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe83b32ebcd4711949f70e197ddaa7232db53e67f2be477ea7af77a008a8f664
3
- size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:699ed76d9af91edc99d12562d64ce4055f71cfe483dfd9ab44c7bfc8626ae66f
3
+ size 5176
run-4/checkpoint-1000/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a2fd962879a8b4ce43338ac9805fd05dc48d37fc6d20ea17dac99c005d459bd
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:885ca80e8baf4cb2c4dcfc9f3a417a95e864e74482329dfbe65d239e0b6da3ee
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:b6713bfb072385b7d121b74e18be3c37c21fee1dfc0561b801c5d6d1575e2517
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acbab3338fe80a375f03ccc12c9d4301998bd3ebc1b304e95ff59bd56941f263
3
  size 536643898
run-4/checkpoint-1000/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60ef01273aaa599804d51a93c6c0c61874ebd50ab9e135a21aab5f7cd0e6487a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed9da1cbe846856af516cf037dd225e7f48e2737ef84c42a9bee0753b8c140ef
3
  size 1064
run-4/checkpoint-1000/trainer_state.json CHANGED
@@ -10,50 +10,50 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.572258064516129,
14
- "eval_loss": 0.19858291745185852,
15
- "eval_runtime": 1.3392,
16
- "eval_samples_per_second": 2314.836,
17
- "eval_steps_per_second": 48.537,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
- "grad_norm": 0.4964948892593384,
23
- "learning_rate": 1.4758909853249476e-05,
24
- "loss": 0.3147,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
- "eval_accuracy": 0.8106451612903226,
30
- "eval_loss": 0.1020575761795044,
31
- "eval_runtime": 1.3434,
32
- "eval_samples_per_second": 2307.629,
33
- "eval_steps_per_second": 48.386,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
- "eval_accuracy": 0.8693548387096774,
39
- "eval_loss": 0.07160120457410812,
40
- "eval_runtime": 1.3431,
41
- "eval_samples_per_second": 2308.044,
42
- "eval_steps_per_second": 48.394,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
- "grad_norm": 0.4632091224193573,
48
- "learning_rate": 9.517819706498952e-06,
49
- "loss": 0.1173,
50
  "step": 1000
51
  }
52
  ],
53
  "logging_steps": 500,
54
- "max_steps": 1908,
55
  "num_input_tokens_seen": 0,
56
- "num_train_epochs": 6,
57
  "save_steps": 500,
58
  "stateful_callbacks": {
59
  "TrainerControl": {
@@ -71,8 +71,8 @@
71
  "train_batch_size": 48,
72
  "trial_name": null,
73
  "trial_params": {
74
- "alpha": 0.2224768882011432,
75
- "num_train_epochs": 6,
76
- "temperature": 16
77
  }
78
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.5841935483870968,
14
+ "eval_loss": 0.2075682282447815,
15
+ "eval_runtime": 1.3344,
16
+ "eval_samples_per_second": 2323.118,
17
+ "eval_steps_per_second": 48.711,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.5149257183074951,
23
+ "learning_rate": 1.550763701707098e-05,
24
+ "loss": 0.3307,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.8232258064516129,
30
+ "eval_loss": 0.10267288982868195,
31
+ "eval_runtime": 1.3419,
32
+ "eval_samples_per_second": 2310.093,
33
+ "eval_steps_per_second": 48.437,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
+ "eval_accuracy": 0.8758064516129033,
39
+ "eval_loss": 0.06955474615097046,
40
+ "eval_runtime": 1.3398,
41
+ "eval_samples_per_second": 2313.717,
42
+ "eval_steps_per_second": 48.513,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.48999229073524475,
48
+ "learning_rate": 1.101527403414196e-05,
49
+ "loss": 0.1186,
50
  "step": 1000
51
  }
52
  ],
53
  "logging_steps": 500,
54
+ "max_steps": 2226,
55
  "num_input_tokens_seen": 0,
56
+ "num_train_epochs": 7,
57
  "save_steps": 500,
58
  "stateful_callbacks": {
59
  "TrainerControl": {
 
71
  "train_batch_size": 48,
72
  "trial_name": null,
73
  "trial_params": {
74
+ "alpha": 0.6690457694692354,
75
+ "num_train_epochs": 7,
76
+ "temperature": 9
77
  }
78
  }
run-4/checkpoint-1000/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09c1d2b3517a81c25cfd3dc4720ca0f5c5cd50449810325441209751db6b15be
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:829aeb9a80fa5e890bae01359822ae021bf174b7265d13bb14d18d678935efbc
3
  size 5176
run-4/checkpoint-1500/trainer_state.json CHANGED
@@ -10,66 +10,66 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.572258064516129,
14
- "eval_loss": 0.19858291745185852,
15
- "eval_runtime": 1.3392,
16
- "eval_samples_per_second": 2314.836,
17
- "eval_steps_per_second": 48.537,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
- "grad_norm": 0.4964948892593384,
23
- "learning_rate": 1.4758909853249476e-05,
24
- "loss": 0.3147,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
- "eval_accuracy": 0.8106451612903226,
30
- "eval_loss": 0.1020575761795044,
31
- "eval_runtime": 1.3434,
32
- "eval_samples_per_second": 2307.629,
33
- "eval_steps_per_second": 48.386,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
- "eval_accuracy": 0.8693548387096774,
39
- "eval_loss": 0.07160120457410812,
40
- "eval_runtime": 1.3431,
41
- "eval_samples_per_second": 2308.044,
42
- "eval_steps_per_second": 48.394,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
- "grad_norm": 0.4632091224193573,
48
- "learning_rate": 9.517819706498952e-06,
49
- "loss": 0.1173,
50
  "step": 1000
51
  },
52
  {
53
  "epoch": 4.0,
54
- "eval_accuracy": 0.8851612903225806,
55
- "eval_loss": 0.05789823457598686,
56
- "eval_runtime": 1.3519,
57
- "eval_samples_per_second": 2293.043,
58
- "eval_steps_per_second": 48.08,
59
  "step": 1272
60
  },
61
  {
62
  "epoch": 4.716981132075472,
63
- "grad_norm": 0.3365257680416107,
64
- "learning_rate": 4.276729559748428e-06,
65
- "loss": 0.0804,
66
  "step": 1500
67
  }
68
  ],
69
  "logging_steps": 500,
70
- "max_steps": 1908,
71
  "num_input_tokens_seen": 0,
72
- "num_train_epochs": 6,
73
  "save_steps": 500,
74
  "stateful_callbacks": {
75
  "TrainerControl": {
@@ -87,8 +87,8 @@
87
  "train_batch_size": 48,
88
  "trial_name": null,
89
  "trial_params": {
90
- "alpha": 0.2224768882011432,
91
- "num_train_epochs": 6,
92
- "temperature": 16
93
  }
94
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.5841935483870968,
14
+ "eval_loss": 0.2075682282447815,
15
+ "eval_runtime": 1.3344,
16
+ "eval_samples_per_second": 2323.118,
17
+ "eval_steps_per_second": 48.711,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.5149257183074951,
23
+ "learning_rate": 1.550763701707098e-05,
24
+ "loss": 0.3307,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.8232258064516129,
30
+ "eval_loss": 0.10267288982868195,
31
+ "eval_runtime": 1.3419,
32
+ "eval_samples_per_second": 2310.093,
33
+ "eval_steps_per_second": 48.437,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
+ "eval_accuracy": 0.8758064516129033,
39
+ "eval_loss": 0.06955474615097046,
40
+ "eval_runtime": 1.3398,
41
+ "eval_samples_per_second": 2313.717,
42
+ "eval_steps_per_second": 48.513,
43
  "step": 954
44
  },
45
  {
46
  "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.48999229073524475,
48
+ "learning_rate": 1.101527403414196e-05,
49
+ "loss": 0.1186,
50
  "step": 1000
51
  },
52
  {
53
  "epoch": 4.0,
54
+ "eval_accuracy": 0.892258064516129,
55
+ "eval_loss": 0.0543968603014946,
56
+ "eval_runtime": 1.3542,
57
+ "eval_samples_per_second": 2289.255,
58
+ "eval_steps_per_second": 48.001,
59
  "step": 1272
60
  },
61
  {
62
  "epoch": 4.716981132075472,
63
+ "grad_norm": 0.3368269205093384,
64
+ "learning_rate": 6.522911051212939e-06,
65
+ "loss": 0.0776,
66
  "step": 1500
67
  }
68
  ],
69
  "logging_steps": 500,
70
+ "max_steps": 2226,
71
  "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 7,
73
  "save_steps": 500,
74
  "stateful_callbacks": {
75
  "TrainerControl": {
 
87
  "train_batch_size": 48,
88
  "trial_name": null,
89
  "trial_params": {
90
+ "alpha": 0.6690457694692354,
91
+ "num_train_epochs": 7,
92
+ "temperature": 9
93
  }
94
  }
run-4/checkpoint-2000/config.json CHANGED
@@ -326,6 +326,6 @@
326
  "sinusoidal_pos_embds": false,
327
  "tie_weights_": true,
328
  "torch_dtype": "float32",
329
- "transformers_version": "4.37.2",
330
  "vocab_size": 30522
331
  }
 
326
  "sinusoidal_pos_embds": false,
327
  "tie_weights_": true,
328
  "torch_dtype": "float32",
329
+ "transformers_version": "4.41.1",
330
  "vocab_size": 30522
331
  }
run-4/checkpoint-2000/tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
run-4/checkpoint-2000/trainer_state.json CHANGED
@@ -10,94 +10,110 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.6090322580645161,
14
- "eval_loss": 0.19804297387599945,
15
- "eval_runtime": 1.3633,
16
- "eval_samples_per_second": 2273.899,
17
- "eval_steps_per_second": 47.679,
18
  "step": 318
19
  },
20
  {
21
- "epoch": 1.57,
22
- "learning_rate": 1.685534591194969e-05,
23
- "loss": 0.3181,
 
24
  "step": 500
25
  },
26
  {
27
  "epoch": 2.0,
28
- "eval_accuracy": 0.8235483870967742,
29
- "eval_loss": 0.09599166363477707,
30
- "eval_runtime": 1.3694,
31
- "eval_samples_per_second": 2263.697,
32
- "eval_steps_per_second": 47.465,
33
  "step": 636
34
  },
35
  {
36
  "epoch": 3.0,
37
- "eval_accuracy": 0.8812903225806452,
38
- "eval_loss": 0.06225818395614624,
39
- "eval_runtime": 1.3803,
40
- "eval_samples_per_second": 2245.873,
41
- "eval_steps_per_second": 47.091,
42
  "step": 954
43
  },
44
  {
45
- "epoch": 3.14,
46
- "learning_rate": 1.371069182389937e-05,
47
- "loss": 0.1095,
 
48
  "step": 1000
49
  },
50
  {
51
  "epoch": 4.0,
52
- "eval_accuracy": 0.9006451612903226,
53
- "eval_loss": 0.04715849831700325,
54
- "eval_runtime": 1.3792,
55
- "eval_samples_per_second": 2247.685,
56
- "eval_steps_per_second": 47.129,
57
  "step": 1272
58
  },
59
  {
60
- "epoch": 4.72,
61
- "learning_rate": 1.0566037735849058e-05,
62
- "loss": 0.0692,
 
63
  "step": 1500
64
  },
65
  {
66
  "epoch": 5.0,
67
- "eval_accuracy": 0.9080645161290323,
68
- "eval_loss": 0.03902662917971611,
69
- "eval_runtime": 1.3793,
70
- "eval_samples_per_second": 2247.505,
71
- "eval_steps_per_second": 47.125,
72
  "step": 1590
73
  },
74
  {
75
  "epoch": 6.0,
76
- "eval_accuracy": 0.9164516129032259,
77
- "eval_loss": 0.034275732934474945,
78
- "eval_runtime": 1.4127,
79
- "eval_samples_per_second": 2194.411,
80
- "eval_steps_per_second": 46.012,
81
  "step": 1908
82
  },
83
  {
84
- "epoch": 6.29,
85
- "learning_rate": 7.421383647798742e-06,
86
- "loss": 0.0538,
 
87
  "step": 2000
88
  }
89
  ],
90
  "logging_steps": 500,
91
- "max_steps": 3180,
92
  "num_input_tokens_seen": 0,
93
- "num_train_epochs": 10,
94
  "save_steps": 500,
95
- "total_flos": 519271419317532.0,
 
 
 
 
 
 
 
 
 
 
 
 
96
  "train_batch_size": 48,
97
  "trial_name": null,
98
  "trial_params": {
99
- "alpha": 0.15736614927417225,
100
- "num_train_epochs": 10,
101
- "temperature": 12
102
  }
103
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.5841935483870968,
14
+ "eval_loss": 0.2075682282447815,
15
+ "eval_runtime": 1.3344,
16
+ "eval_samples_per_second": 2323.118,
17
+ "eval_steps_per_second": 48.711,
18
  "step": 318
19
  },
20
  {
21
+ "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.5149257183074951,
23
+ "learning_rate": 1.550763701707098e-05,
24
+ "loss": 0.3307,
25
  "step": 500
26
  },
27
  {
28
  "epoch": 2.0,
29
+ "eval_accuracy": 0.8232258064516129,
30
+ "eval_loss": 0.10267288982868195,
31
+ "eval_runtime": 1.3419,
32
+ "eval_samples_per_second": 2310.093,
33
+ "eval_steps_per_second": 48.437,
34
  "step": 636
35
  },
36
  {
37
  "epoch": 3.0,
38
+ "eval_accuracy": 0.8758064516129033,
39
+ "eval_loss": 0.06955474615097046,
40
+ "eval_runtime": 1.3398,
41
+ "eval_samples_per_second": 2313.717,
42
+ "eval_steps_per_second": 48.513,
43
  "step": 954
44
  },
45
  {
46
+ "epoch": 3.1446540880503147,
47
+ "grad_norm": 0.48999229073524475,
48
+ "learning_rate": 1.101527403414196e-05,
49
+ "loss": 0.1186,
50
  "step": 1000
51
  },
52
  {
53
  "epoch": 4.0,
54
+ "eval_accuracy": 0.892258064516129,
55
+ "eval_loss": 0.0543968603014946,
56
+ "eval_runtime": 1.3542,
57
+ "eval_samples_per_second": 2289.255,
58
+ "eval_steps_per_second": 48.001,
59
  "step": 1272
60
  },
61
  {
62
+ "epoch": 4.716981132075472,
63
+ "grad_norm": 0.3368269205093384,
64
+ "learning_rate": 6.522911051212939e-06,
65
+ "loss": 0.0776,
66
  "step": 1500
67
  },
68
  {
69
  "epoch": 5.0,
70
+ "eval_accuracy": 0.9016129032258065,
71
+ "eval_loss": 0.046099308878183365,
72
+ "eval_runtime": 1.3597,
73
+ "eval_samples_per_second": 2279.951,
74
+ "eval_steps_per_second": 47.805,
75
  "step": 1590
76
  },
77
  {
78
  "epoch": 6.0,
79
+ "eval_accuracy": 0.9080645161290323,
80
+ "eval_loss": 0.04202481359243393,
81
+ "eval_runtime": 1.2661,
82
+ "eval_samples_per_second": 2448.427,
83
+ "eval_steps_per_second": 51.338,
84
  "step": 1908
85
  },
86
  {
87
+ "epoch": 6.289308176100629,
88
+ "grad_norm": 0.2973543107509613,
89
+ "learning_rate": 2.0305480682839176e-06,
90
+ "loss": 0.0639,
91
  "step": 2000
92
  }
93
  ],
94
  "logging_steps": 500,
95
+ "max_steps": 2226,
96
  "num_input_tokens_seen": 0,
97
+ "num_train_epochs": 7,
98
  "save_steps": 500,
99
+ "stateful_callbacks": {
100
+ "TrainerControl": {
101
+ "args": {
102
+ "should_epoch_stop": false,
103
+ "should_evaluate": false,
104
+ "should_log": false,
105
+ "should_save": true,
106
+ "should_training_stop": false
107
+ },
108
+ "attributes": {}
109
+ }
110
+ },
111
+ "total_flos": 520991326672152.0,
112
  "train_batch_size": 48,
113
  "trial_name": null,
114
  "trial_params": {
115
+ "alpha": 0.6690457694692354,
116
+ "num_train_epochs": 7,
117
+ "temperature": 9
118
  }
119
  }
run-4/checkpoint-500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:554a05c79b6970f05612f20a53fb142204c7ccd5808ae60149536d4c55264da9
3
  size 268290900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ed14a983a063b04b5c0e74f719ee953be8e1b478635360e23a0e81062435df
3
  size 268290900
run-4/checkpoint-500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0bb5b17274bb556281ac9507dfa5e5e0a5eee2f63dab10207ad0103fe42dd3e
3
  size 536643898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d9db9d343d242a2725f574d995b93a952ed696146c255f358b1e7c993d77738
3
  size 536643898
run-4/checkpoint-500/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb78b1e790f49c38375a9a03add3c9373ef72cf0138709ffb96775535ef084c6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e744277c61f87520794334442fae36c5f9ff6e10cb79d4bfee5176ca7eafe2
3
  size 1064
run-4/checkpoint-500/trainer_state.json CHANGED
@@ -10,25 +10,25 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.572258064516129,
14
- "eval_loss": 0.19858291745185852,
15
- "eval_runtime": 1.3392,
16
- "eval_samples_per_second": 2314.836,
17
- "eval_steps_per_second": 48.537,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
- "grad_norm": 0.4964948892593384,
23
- "learning_rate": 1.4758909853249476e-05,
24
- "loss": 0.3147,
25
  "step": 500
26
  }
27
  ],
28
  "logging_steps": 500,
29
- "max_steps": 1908,
30
  "num_input_tokens_seen": 0,
31
- "num_train_epochs": 6,
32
  "save_steps": 500,
33
  "stateful_callbacks": {
34
  "TrainerControl": {
@@ -46,8 +46,8 @@
46
  "train_batch_size": 48,
47
  "trial_name": null,
48
  "trial_params": {
49
- "alpha": 0.2224768882011432,
50
- "num_train_epochs": 6,
51
- "temperature": 16
52
  }
53
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.5841935483870968,
14
+ "eval_loss": 0.2075682282447815,
15
+ "eval_runtime": 1.3344,
16
+ "eval_samples_per_second": 2323.118,
17
+ "eval_steps_per_second": 48.711,
18
  "step": 318
19
  },
20
  {
21
  "epoch": 1.5723270440251573,
22
+ "grad_norm": 0.5149257183074951,
23
+ "learning_rate": 1.550763701707098e-05,
24
+ "loss": 0.3307,
25
  "step": 500
26
  }
27
  ],
28
  "logging_steps": 500,
29
+ "max_steps": 2226,
30
  "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 7,
32
  "save_steps": 500,
33
  "stateful_callbacks": {
34
  "TrainerControl": {
 
46
  "train_batch_size": 48,
47
  "trial_name": null,
48
  "trial_params": {
49
+ "alpha": 0.6690457694692354,
50
+ "num_train_epochs": 7,
51
+ "temperature": 9
52
  }
53
  }
run-4/checkpoint-500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09c1d2b3517a81c25cfd3dc4720ca0f5c5cd50449810325441209751db6b15be
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:829aeb9a80fa5e890bae01359822ae021bf174b7265d13bb14d18d678935efbc
3
  size 5176
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:699ed76d9af91edc99d12562d64ce4055f71cfe483dfd9ab44c7bfc8626ae66f
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:829aeb9a80fa5e890bae01359822ae021bf174b7265d13bb14d18d678935efbc
3
  size 5176