Marcos12886 commited on
Commit
08fe348
·
verified ·
1 Parent(s): b73f096

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +20 -23
  2. checkpoint-106/config.json +85 -0
  3. checkpoint-106/model.safetensors +3 -0
  4. checkpoint-106/optimizer.pt +3 -0
  5. checkpoint-106/rng_state.pth +3 -0
  6. checkpoint-106/scheduler.pt +3 -0
  7. checkpoint-106/trainer_state.json +126 -0
  8. checkpoint-106/training_args.bin +3 -0
  9. checkpoint-113/config.json +85 -0
  10. checkpoint-113/model.safetensors +3 -0
  11. checkpoint-113/optimizer.pt +3 -0
  12. checkpoint-113/rng_state.pth +3 -0
  13. checkpoint-113/scheduler.pt +3 -0
  14. checkpoint-113/trainer_state.json +114 -0
  15. checkpoint-113/training_args.bin +3 -0
  16. checkpoint-114/config.json +85 -0
  17. checkpoint-114/model.safetensors +3 -0
  18. checkpoint-114/optimizer.pt +3 -0
  19. checkpoint-114/rng_state.pth +3 -0
  20. checkpoint-114/scheduler.pt +3 -0
  21. checkpoint-114/trainer_state.json +102 -0
  22. checkpoint-114/training_args.bin +3 -0
  23. checkpoint-122/config.json +85 -0
  24. checkpoint-122/model.safetensors +3 -0
  25. checkpoint-122/optimizer.pt +3 -0
  26. checkpoint-122/rng_state.pth +3 -0
  27. checkpoint-122/scheduler.pt +3 -0
  28. checkpoint-122/trainer_state.json +138 -0
  29. checkpoint-122/training_args.bin +3 -0
  30. checkpoint-132/config.json +85 -0
  31. checkpoint-132/model.safetensors +3 -0
  32. checkpoint-132/optimizer.pt +3 -0
  33. checkpoint-132/rng_state.pth +3 -0
  34. checkpoint-132/scheduler.pt +3 -0
  35. checkpoint-132/trainer_state.json +126 -0
  36. checkpoint-132/training_args.bin +3 -0
  37. checkpoint-137/config.json +85 -0
  38. checkpoint-137/model.safetensors +3 -0
  39. checkpoint-137/optimizer.pt +3 -0
  40. checkpoint-137/rng_state.pth +3 -0
  41. checkpoint-137/scheduler.pt +3 -0
  42. checkpoint-137/trainer_state.json +114 -0
  43. checkpoint-137/training_args.bin +3 -0
  44. checkpoint-15/config.json +85 -0
  45. checkpoint-15/model.safetensors +3 -0
  46. checkpoint-15/optimizer.pt +3 -0
  47. checkpoint-15/rng_state.pth +3 -0
  48. checkpoint-15/scheduler.pt +3 -0
  49. checkpoint-15/trainer_state.json +54 -0
  50. checkpoint-15/training_args.bin +3 -0
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.4765
25
- - Accuracy: 0.8475
26
- - Precision: 0.8497
27
- - Recall: 0.8475
28
- - F1: 0.8484
29
 
30
  ## Model description
31
 
@@ -44,7 +44,7 @@ More information needed
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
- - learning_rate: 0.0001
48
  - train_batch_size: 8
49
  - eval_batch_size: 8
50
  - seed: 123
@@ -52,26 +52,23 @@ The following hyperparameters were used during training:
52
  - total_train_batch_size: 64
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: cosine
55
- - lr_scheduler_warmup_ratio: 0.01
56
- - num_epochs: 15
57
 
58
  ### Training results
59
 
60
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
61
- |:-------------:|:-------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
62
- | No log | 0.9897 | 24 | 0.9809 | 0.6357 | 0.5920 | 0.6357 | 0.5921 |
63
- | No log | 1.9794 | 48 | 0.7444 | 0.7158 | 0.6992 | 0.7158 | 0.6905 |
64
- | No log | 2.9691 | 72 | 0.6172 | 0.7494 | 0.7438 | 0.7494 | 0.7449 |
65
- | No log | 4.0 | 97 | 0.5431 | 0.7984 | 0.7918 | 0.7984 | 0.7874 |
66
- | No log | 4.9897 | 121 | 0.5269 | 0.8010 | 0.8006 | 0.8010 | 0.7975 |
67
- | No log | 5.9794 | 145 | 0.5811 | 0.7494 | 0.7802 | 0.7494 | 0.7551 |
68
- | No log | 6.9691 | 169 | 0.4408 | 0.8398 | 0.8366 | 0.8398 | 0.8355 |
69
- | No log | 8.0 | 194 | 0.4687 | 0.8191 | 0.8188 | 0.8191 | 0.8168 |
70
- | No log | 8.9897 | 218 | 0.4364 | 0.8475 | 0.8483 | 0.8475 | 0.8474 |
71
- | No log | 9.9794 | 242 | 0.4291 | 0.8579 | 0.8561 | 0.8579 | 0.8568 |
72
- | No log | 10.9691 | 266 | 0.4699 | 0.8501 | 0.8582 | 0.8501 | 0.8528 |
73
- | No log | 12.0 | 291 | 0.4862 | 0.8450 | 0.8536 | 0.8450 | 0.8480 |
74
- | No log | 12.9897 | 315 | 0.4765 | 0.8475 | 0.8497 | 0.8475 | 0.8484 |
75
 
76
 
77
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.4003
25
+ - Accuracy: 0.8603
26
+ - Precision: 0.8644
27
+ - Recall: 0.8603
28
+ - F1: 0.8611
29
 
30
  ## Model description
31
 
 
44
  ### Training hyperparameters
45
 
46
  The following hyperparameters were used during training:
47
+ - learning_rate: 0.0003
48
  - train_batch_size: 8
49
  - eval_batch_size: 8
50
  - seed: 123
 
52
  - total_train_batch_size: 64
53
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
54
  - lr_scheduler_type: cosine
55
+ - lr_scheduler_warmup_ratio: 0.4
56
+ - num_epochs: 10
57
 
58
  ### Training results
59
 
60
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
61
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
62
+ | No log | 0.9617 | 22 | 1.1426 | 0.4877 | 0.3200 | 0.4877 | 0.3244 |
63
+ | No log | 1.9672 | 45 | 0.8035 | 0.6877 | 0.6781 | 0.6877 | 0.6726 |
64
+ | No log | 2.9727 | 68 | 0.5866 | 0.7370 | 0.7267 | 0.7370 | 0.7179 |
65
+ | No log | 3.9781 | 91 | 0.5180 | 0.7945 | 0.7922 | 0.7945 | 0.7853 |
66
+ | No log | 4.9836 | 114 | 0.6972 | 0.7233 | 0.7954 | 0.7233 | 0.7300 |
67
+ | No log | 5.9891 | 137 | 0.5580 | 0.8055 | 0.8052 | 0.8055 | 0.7958 |
68
+ | No log | 6.9945 | 160 | 0.3853 | 0.8603 | 0.8584 | 0.8603 | 0.8584 |
69
+ | No log | 8.0 | 183 | 0.4090 | 0.8301 | 0.8415 | 0.8301 | 0.8318 |
70
+ | No log | 8.9617 | 205 | 0.3923 | 0.8630 | 0.8660 | 0.8630 | 0.8633 |
71
+ | No log | 9.6175 | 220 | 0.4003 | 0.8603 | 0.8644 | 0.8603 | 0.8611 |
 
 
 
72
 
73
 
74
  ### Framework versions
checkpoint-106/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ntu-spml/distilhubert",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "HubertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "do_stable_layer_norm": false,
42
+ "eos_token_id": 2,
43
+ "feat_extract_activation": "gelu",
44
+ "feat_extract_norm": "group",
45
+ "feat_proj_dropout": 0.0,
46
+ "feat_proj_layer_norm": false,
47
+ "final_dropout": 0.0,
48
+ "finetuning_task": "audio-classification",
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.1,
51
+ "hidden_size": 768,
52
+ "id2label": {
53
+ "0": "1s_normal",
54
+ "1": "1s_pain",
55
+ "2": "1s_hunger",
56
+ "3": "1s_asphyxia"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "label2id": {
61
+ "1s_asphyxia": 3,
62
+ "1s_hunger": 2,
63
+ "1s_normal": 0,
64
+ "1s_pain": 1
65
+ },
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.0,
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_prob": 0.05,
74
+ "model_type": "hubert",
75
+ "num_attention_heads": 12,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 2,
80
+ "pad_token_id": 0,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.44.2",
83
+ "use_weighted_layer_sum": false,
84
+ "vocab_size": 32
85
+ }
checkpoint-106/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6567bed984b2d4fd2b4423ab427f8477900f6673f35e92fee11c8f15b3f1eb0
3
+ size 94765560
checkpoint-106/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9097bf7217aefa8e979b6c351af92d17f92be56cef09ebfbb5e29028bae5c419
3
+ size 189556666
checkpoint-106/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928f3cdf771c09074f7483c69cc2b34a3ce35175c776ce53d7ceea023ba61c74
3
+ size 14308
checkpoint-106/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3a5ddcdf6cf2a390a03fcad917c91b10f396acddbcbfd01b376f583ebe540cb
3
+ size 1064
checkpoint-106/trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7654320987654321,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-106",
4
+ "epoch": 6.950819672131147,
5
+ "eval_steps": 500,
6
+ "global_step": 106,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9836065573770492,
13
+ "eval_accuracy": 0.5637860082304527,
14
+ "eval_f1": 0.49656016746502873,
15
+ "eval_loss": 1.1263551712036133,
16
+ "eval_precision": 0.5260403310011795,
17
+ "eval_recall": 0.5637860082304527,
18
+ "eval_runtime": 1.0189,
19
+ "eval_samples_per_second": 238.499,
20
+ "eval_steps_per_second": 30.426,
21
+ "step": 15
22
+ },
23
+ {
24
+ "epoch": 1.9672131147540983,
25
+ "eval_accuracy": 0.654320987654321,
26
+ "eval_f1": 0.6103087287397109,
27
+ "eval_loss": 0.9297327399253845,
28
+ "eval_precision": 0.6400077012574776,
29
+ "eval_recall": 0.654320987654321,
30
+ "eval_runtime": 1.0331,
31
+ "eval_samples_per_second": 235.213,
32
+ "eval_steps_per_second": 30.007,
33
+ "step": 30
34
+ },
35
+ {
36
+ "epoch": 2.9508196721311473,
37
+ "eval_accuracy": 0.6707818930041153,
38
+ "eval_f1": 0.6458358584237818,
39
+ "eval_loss": 0.839500904083252,
40
+ "eval_precision": 0.6700062294696597,
41
+ "eval_recall": 0.6707818930041153,
42
+ "eval_runtime": 1.0251,
43
+ "eval_samples_per_second": 237.061,
44
+ "eval_steps_per_second": 30.242,
45
+ "step": 45
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_accuracy": 0.7325102880658436,
50
+ "eval_f1": 0.7023767955866722,
51
+ "eval_loss": 0.7256261110305786,
52
+ "eval_precision": 0.6980472218233514,
53
+ "eval_recall": 0.7325102880658436,
54
+ "eval_runtime": 1.0208,
55
+ "eval_samples_per_second": 238.055,
56
+ "eval_steps_per_second": 30.369,
57
+ "step": 61
58
+ },
59
+ {
60
+ "epoch": 4.983606557377049,
61
+ "eval_accuracy": 0.7530864197530864,
62
+ "eval_f1": 0.7360211171604085,
63
+ "eval_loss": 0.6660245060920715,
64
+ "eval_precision": 0.733383916927066,
65
+ "eval_recall": 0.7530864197530864,
66
+ "eval_runtime": 1.0191,
67
+ "eval_samples_per_second": 238.453,
68
+ "eval_steps_per_second": 30.42,
69
+ "step": 76
70
+ },
71
+ {
72
+ "epoch": 5.967213114754099,
73
+ "eval_accuracy": 0.7448559670781894,
74
+ "eval_f1": 0.7394169380703285,
75
+ "eval_loss": 0.641394317150116,
76
+ "eval_precision": 0.7510319299474755,
77
+ "eval_recall": 0.7448559670781894,
78
+ "eval_runtime": 1.0279,
79
+ "eval_samples_per_second": 236.402,
80
+ "eval_steps_per_second": 30.158,
81
+ "step": 91
82
+ },
83
+ {
84
+ "epoch": 6.950819672131147,
85
+ "eval_accuracy": 0.7654320987654321,
86
+ "eval_f1": 0.7521250625471124,
87
+ "eval_loss": 0.5891531109809875,
88
+ "eval_precision": 0.7457521964331709,
89
+ "eval_recall": 0.7654320987654321,
90
+ "eval_runtime": 1.0292,
91
+ "eval_samples_per_second": 236.097,
92
+ "eval_steps_per_second": 30.119,
93
+ "step": 106
94
+ }
95
+ ],
96
+ "logging_steps": 500,
97
+ "max_steps": 150,
98
+ "num_input_tokens_seen": 0,
99
+ "num_train_epochs": 10,
100
+ "save_steps": 500,
101
+ "stateful_callbacks": {
102
+ "EarlyStoppingCallback": {
103
+ "args": {
104
+ "early_stopping_patience": 3,
105
+ "early_stopping_threshold": 0.0
106
+ },
107
+ "attributes": {
108
+ "early_stopping_patience_counter": 0
109
+ }
110
+ },
111
+ "TrainerControl": {
112
+ "args": {
113
+ "should_epoch_stop": false,
114
+ "should_evaluate": false,
115
+ "should_log": false,
116
+ "should_save": true,
117
+ "should_training_stop": false
118
+ },
119
+ "attributes": {}
120
+ }
121
+ },
122
+ "total_flos": 1.545791792832e+16,
123
+ "train_batch_size": 8,
124
+ "trial_name": null,
125
+ "trial_params": null
126
+ }
checkpoint-106/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ba7873d2bd153b717b3ad63778d1f963577e3b32bb96ddb7f3806324b2a0de9
3
+ size 5240
checkpoint-113/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ntu-spml/distilhubert",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "HubertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "do_stable_layer_norm": false,
42
+ "eos_token_id": 2,
43
+ "feat_extract_activation": "gelu",
44
+ "feat_extract_norm": "group",
45
+ "feat_proj_dropout": 0.0,
46
+ "feat_proj_layer_norm": false,
47
+ "final_dropout": 0.0,
48
+ "finetuning_task": "audio-classification",
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.1,
51
+ "hidden_size": 768,
52
+ "id2label": {
53
+ "0": "1s_normal",
54
+ "1": "1s_pain",
55
+ "2": "1s_hunger",
56
+ "3": "1s_asphyxia"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "label2id": {
61
+ "1s_asphyxia": 3,
62
+ "1s_hunger": 2,
63
+ "1s_normal": 0,
64
+ "1s_pain": 1
65
+ },
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.0,
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_prob": 0.05,
74
+ "model_type": "hubert",
75
+ "num_attention_heads": 12,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 2,
80
+ "pad_token_id": 0,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.44.2",
83
+ "use_weighted_layer_sum": false,
84
+ "vocab_size": 32
85
+ }
checkpoint-113/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1692afae32a685cdb21b99180f4d00ade4a931cf463668ae86bae200be18256
3
+ size 94765560
checkpoint-113/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95a59961dfe2efd0807a1f5d2644f90d34634b7c1e2527ab9654ff732053448c
3
+ size 189556666
checkpoint-113/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f24d750dc8ca957f30cbab77ab789c7b567b66cea78fac4361b4dec3f2ede341
3
+ size 14308
checkpoint-113/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c415ef6a34b0bd448c5d1304653fc93439492511eb3d45576e4f00e759e0d72c
3
+ size 1064
checkpoint-113/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7980132450331126,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-94",
4
+ "epoch": 5.986754966887418,
5
+ "eval_steps": 500,
6
+ "global_step": 113,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9536423841059603,
13
+ "eval_accuracy": 0.5298013245033113,
14
+ "eval_f1": 0.43216404525386315,
15
+ "eval_loss": 1.1326755285263062,
16
+ "eval_precision": 0.5213817284211205,
17
+ "eval_recall": 0.5298013245033113,
18
+ "eval_runtime": 1.2241,
19
+ "eval_samples_per_second": 246.709,
20
+ "eval_steps_per_second": 31.043,
21
+ "step": 18
22
+ },
23
+ {
24
+ "epoch": 1.9602649006622517,
25
+ "eval_accuracy": 0.6423841059602649,
26
+ "eval_f1": 0.5806184720425087,
27
+ "eval_loss": 0.9228919744491577,
28
+ "eval_precision": 0.5520930002801896,
29
+ "eval_recall": 0.6423841059602649,
30
+ "eval_runtime": 1.2236,
31
+ "eval_samples_per_second": 246.807,
32
+ "eval_steps_per_second": 31.055,
33
+ "step": 37
34
+ },
35
+ {
36
+ "epoch": 2.966887417218543,
37
+ "eval_accuracy": 0.7086092715231788,
38
+ "eval_f1": 0.6539391094940458,
39
+ "eval_loss": 0.7409619688987732,
40
+ "eval_precision": 0.752516290193287,
41
+ "eval_recall": 0.7086092715231788,
42
+ "eval_runtime": 1.2459,
43
+ "eval_samples_per_second": 242.403,
44
+ "eval_steps_per_second": 30.501,
45
+ "step": 56
46
+ },
47
+ {
48
+ "epoch": 3.9735099337748343,
49
+ "eval_accuracy": 0.7450331125827815,
50
+ "eval_f1": 0.7012377717797856,
51
+ "eval_loss": 0.6461689472198486,
52
+ "eval_precision": 0.7242129191632504,
53
+ "eval_recall": 0.7450331125827815,
54
+ "eval_runtime": 1.229,
55
+ "eval_samples_per_second": 245.723,
56
+ "eval_steps_per_second": 30.919,
57
+ "step": 75
58
+ },
59
+ {
60
+ "epoch": 4.9801324503311255,
61
+ "eval_accuracy": 0.7980132450331126,
62
+ "eval_f1": 0.7903709596982513,
63
+ "eval_loss": 0.5553261041641235,
64
+ "eval_precision": 0.7925903096412185,
65
+ "eval_recall": 0.7980132450331126,
66
+ "eval_runtime": 1.2897,
67
+ "eval_samples_per_second": 234.157,
68
+ "eval_steps_per_second": 29.463,
69
+ "step": 94
70
+ },
71
+ {
72
+ "epoch": 5.986754966887418,
73
+ "eval_accuracy": 0.7781456953642384,
74
+ "eval_f1": 0.7717607879297459,
75
+ "eval_loss": 0.5255588293075562,
76
+ "eval_precision": 0.7771454278224522,
77
+ "eval_recall": 0.7781456953642384,
78
+ "eval_runtime": 1.2928,
79
+ "eval_samples_per_second": 233.597,
80
+ "eval_steps_per_second": 29.393,
81
+ "step": 113
82
+ }
83
+ ],
84
+ "logging_steps": 500,
85
+ "max_steps": 180,
86
+ "num_input_tokens_seen": 0,
87
+ "num_train_epochs": 10,
88
+ "save_steps": 500,
89
+ "stateful_callbacks": {
90
+ "EarlyStoppingCallback": {
91
+ "args": {
92
+ "early_stopping_patience": 3,
93
+ "early_stopping_threshold": 0.0
94
+ },
95
+ "attributes": {
96
+ "early_stopping_patience_counter": 0
97
+ }
98
+ },
99
+ "TrainerControl": {
100
+ "args": {
101
+ "should_epoch_stop": false,
102
+ "should_evaluate": false,
103
+ "should_log": false,
104
+ "should_save": true,
105
+ "should_training_stop": false
106
+ },
107
+ "attributes": {}
108
+ }
109
+ },
110
+ "total_flos": 1.648359410688e+16,
111
+ "train_batch_size": 8,
112
+ "trial_name": null,
113
+ "trial_params": null
114
+ }
checkpoint-113/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f2331f3c3c1c25969cfb888574c70dd0e5a19519d8cecb6198afe5225b5a53
3
+ size 5240
checkpoint-114/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ntu-spml/distilhubert",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "HubertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "do_stable_layer_norm": false,
42
+ "eos_token_id": 2,
43
+ "feat_extract_activation": "gelu",
44
+ "feat_extract_norm": "group",
45
+ "feat_proj_dropout": 0.0,
46
+ "feat_proj_layer_norm": false,
47
+ "final_dropout": 0.0,
48
+ "finetuning_task": "audio-classification",
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.1,
51
+ "hidden_size": 768,
52
+ "id2label": {
53
+ "0": "1s_normal",
54
+ "1": "1s_pain",
55
+ "2": "1s_hunger",
56
+ "3": "1s_asphyxia"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "label2id": {
61
+ "1s_asphyxia": 3,
62
+ "1s_hunger": 2,
63
+ "1s_normal": 0,
64
+ "1s_pain": 1
65
+ },
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.0,
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_prob": 0.05,
74
+ "model_type": "hubert",
75
+ "num_attention_heads": 12,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 2,
80
+ "pad_token_id": 0,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.44.2",
83
+ "use_weighted_layer_sum": false,
84
+ "vocab_size": 32
85
+ }
checkpoint-114/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efcfffcb358b451477e7dda7fd5845d7c60dfefdece951487572aa46aba4692c
3
+ size 94765560
checkpoint-114/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50c31047494b36714f381a86045ffd491ca672438481c43aae97c4155e0eaee7
3
+ size 189556666
checkpoint-114/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d100f367466574d6028a63c7e48e71ada41605ec693e4881863d3a798a583f18
3
+ size 14308
checkpoint-114/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce0ba8db91f50d3058379af77f6a98c43c5a6919e7689db09f0c9dbe74383250
3
+ size 1064
checkpoint-114/trainer_state.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7945205479452054,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-91",
4
+ "epoch": 4.983606557377049,
5
+ "eval_steps": 500,
6
+ "global_step": 114,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9617486338797814,
13
+ "eval_accuracy": 0.4876712328767123,
14
+ "eval_f1": 0.32440734699411816,
15
+ "eval_loss": 1.1426137685775757,
16
+ "eval_precision": 0.31998188610890976,
17
+ "eval_recall": 0.4876712328767123,
18
+ "eval_runtime": 1.5868,
19
+ "eval_samples_per_second": 230.024,
20
+ "eval_steps_per_second": 28.989,
21
+ "step": 22
22
+ },
23
+ {
24
+ "epoch": 1.9672131147540983,
25
+ "eval_accuracy": 0.6876712328767123,
26
+ "eval_f1": 0.6726372384593322,
27
+ "eval_loss": 0.8035227060317993,
28
+ "eval_precision": 0.6780882232356064,
29
+ "eval_recall": 0.6876712328767123,
30
+ "eval_runtime": 1.5591,
31
+ "eval_samples_per_second": 234.103,
32
+ "eval_steps_per_second": 29.503,
33
+ "step": 45
34
+ },
35
+ {
36
+ "epoch": 2.972677595628415,
37
+ "eval_accuracy": 0.736986301369863,
38
+ "eval_f1": 0.7179122961593137,
39
+ "eval_loss": 0.5865945219993591,
40
+ "eval_precision": 0.7266763525667637,
41
+ "eval_recall": 0.736986301369863,
42
+ "eval_runtime": 1.5049,
43
+ "eval_samples_per_second": 242.544,
44
+ "eval_steps_per_second": 30.567,
45
+ "step": 68
46
+ },
47
+ {
48
+ "epoch": 3.978142076502732,
49
+ "eval_accuracy": 0.7945205479452054,
50
+ "eval_f1": 0.7852674207057345,
51
+ "eval_loss": 0.5180361270904541,
52
+ "eval_precision": 0.7921658130880418,
53
+ "eval_recall": 0.7945205479452054,
54
+ "eval_runtime": 1.524,
55
+ "eval_samples_per_second": 239.5,
56
+ "eval_steps_per_second": 30.184,
57
+ "step": 91
58
+ },
59
+ {
60
+ "epoch": 4.983606557377049,
61
+ "eval_accuracy": 0.7232876712328767,
62
+ "eval_f1": 0.7299958784843185,
63
+ "eval_loss": 0.6972417831420898,
64
+ "eval_precision": 0.7954469760289924,
65
+ "eval_recall": 0.7232876712328767,
66
+ "eval_runtime": 1.5556,
67
+ "eval_samples_per_second": 234.639,
68
+ "eval_steps_per_second": 29.571,
69
+ "step": 114
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 220,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 10,
76
+ "save_steps": 500,
77
+ "stateful_callbacks": {
78
+ "EarlyStoppingCallback": {
79
+ "args": {
80
+ "early_stopping_patience": 3,
81
+ "early_stopping_threshold": 0.0
82
+ },
83
+ "attributes": {
84
+ "early_stopping_patience_counter": 0
85
+ }
86
+ },
87
+ "TrainerControl": {
88
+ "args": {
89
+ "should_epoch_stop": false,
90
+ "should_evaluate": false,
91
+ "should_log": false,
92
+ "should_save": true,
93
+ "should_training_stop": false
94
+ },
95
+ "attributes": {}
96
+ }
97
+ },
98
+ "total_flos": 1.65904827552e+16,
99
+ "train_batch_size": 8,
100
+ "trial_name": null,
101
+ "trial_params": null
102
+ }
checkpoint-114/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c635d78c39083a6b3129b7505b6c1291835366a67e1fe687b603a5a1a2dc7f36
3
+ size 5240
checkpoint-122/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ntu-spml/distilhubert",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "HubertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "do_stable_layer_norm": false,
42
+ "eos_token_id": 2,
43
+ "feat_extract_activation": "gelu",
44
+ "feat_extract_norm": "group",
45
+ "feat_proj_dropout": 0.0,
46
+ "feat_proj_layer_norm": false,
47
+ "final_dropout": 0.0,
48
+ "finetuning_task": "audio-classification",
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.1,
51
+ "hidden_size": 768,
52
+ "id2label": {
53
+ "0": "1s_normal",
54
+ "1": "1s_pain",
55
+ "2": "1s_hunger",
56
+ "3": "1s_asphyxia"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "label2id": {
61
+ "1s_asphyxia": 3,
62
+ "1s_hunger": 2,
63
+ "1s_normal": 0,
64
+ "1s_pain": 1
65
+ },
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.0,
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_prob": 0.05,
74
+ "model_type": "hubert",
75
+ "num_attention_heads": 12,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 2,
80
+ "pad_token_id": 0,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.44.2",
83
+ "use_weighted_layer_sum": false,
84
+ "vocab_size": 32
85
+ }
checkpoint-122/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:875f06e3fcdb1f49add7720c13ffe5647dc7627bdc543cdd4b7a1dbd5f5386e8
3
+ size 94765560
checkpoint-122/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f23c0bc64bff7abe209025897241eeab69f4b69c79502389cc6812e75a6c7fda
3
+ size 189556666
checkpoint-122/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc622aa299baf03c31ed24c101f41a36015705516eaa4c07c00a741dc1af649c
3
+ size 14308
checkpoint-122/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61462b1477445ac56a71fa934248b84843905d00d651acdd36ba148fce8e1eb1
3
+ size 1064
checkpoint-122/trainer_state.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7777777777777778,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-122",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 122,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9836065573770492,
13
+ "eval_accuracy": 0.5637860082304527,
14
+ "eval_f1": 0.49656016746502873,
15
+ "eval_loss": 1.1263551712036133,
16
+ "eval_precision": 0.5260403310011795,
17
+ "eval_recall": 0.5637860082304527,
18
+ "eval_runtime": 1.0189,
19
+ "eval_samples_per_second": 238.499,
20
+ "eval_steps_per_second": 30.426,
21
+ "step": 15
22
+ },
23
+ {
24
+ "epoch": 1.9672131147540983,
25
+ "eval_accuracy": 0.654320987654321,
26
+ "eval_f1": 0.6103087287397109,
27
+ "eval_loss": 0.9297327399253845,
28
+ "eval_precision": 0.6400077012574776,
29
+ "eval_recall": 0.654320987654321,
30
+ "eval_runtime": 1.0331,
31
+ "eval_samples_per_second": 235.213,
32
+ "eval_steps_per_second": 30.007,
33
+ "step": 30
34
+ },
35
+ {
36
+ "epoch": 2.9508196721311473,
37
+ "eval_accuracy": 0.6707818930041153,
38
+ "eval_f1": 0.6458358584237818,
39
+ "eval_loss": 0.839500904083252,
40
+ "eval_precision": 0.6700062294696597,
41
+ "eval_recall": 0.6707818930041153,
42
+ "eval_runtime": 1.0251,
43
+ "eval_samples_per_second": 237.061,
44
+ "eval_steps_per_second": 30.242,
45
+ "step": 45
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_accuracy": 0.7325102880658436,
50
+ "eval_f1": 0.7023767955866722,
51
+ "eval_loss": 0.7256261110305786,
52
+ "eval_precision": 0.6980472218233514,
53
+ "eval_recall": 0.7325102880658436,
54
+ "eval_runtime": 1.0208,
55
+ "eval_samples_per_second": 238.055,
56
+ "eval_steps_per_second": 30.369,
57
+ "step": 61
58
+ },
59
+ {
60
+ "epoch": 4.983606557377049,
61
+ "eval_accuracy": 0.7530864197530864,
62
+ "eval_f1": 0.7360211171604085,
63
+ "eval_loss": 0.6660245060920715,
64
+ "eval_precision": 0.733383916927066,
65
+ "eval_recall": 0.7530864197530864,
66
+ "eval_runtime": 1.0191,
67
+ "eval_samples_per_second": 238.453,
68
+ "eval_steps_per_second": 30.42,
69
+ "step": 76
70
+ },
71
+ {
72
+ "epoch": 5.967213114754099,
73
+ "eval_accuracy": 0.7448559670781894,
74
+ "eval_f1": 0.7394169380703285,
75
+ "eval_loss": 0.641394317150116,
76
+ "eval_precision": 0.7510319299474755,
77
+ "eval_recall": 0.7448559670781894,
78
+ "eval_runtime": 1.0279,
79
+ "eval_samples_per_second": 236.402,
80
+ "eval_steps_per_second": 30.158,
81
+ "step": 91
82
+ },
83
+ {
84
+ "epoch": 6.950819672131147,
85
+ "eval_accuracy": 0.7654320987654321,
86
+ "eval_f1": 0.7521250625471124,
87
+ "eval_loss": 0.5891531109809875,
88
+ "eval_precision": 0.7457521964331709,
89
+ "eval_recall": 0.7654320987654321,
90
+ "eval_runtime": 1.0292,
91
+ "eval_samples_per_second": 236.097,
92
+ "eval_steps_per_second": 30.119,
93
+ "step": 106
94
+ },
95
+ {
96
+ "epoch": 8.0,
97
+ "eval_accuracy": 0.7777777777777778,
98
+ "eval_f1": 0.7704687718708882,
99
+ "eval_loss": 0.5790427327156067,
100
+ "eval_precision": 0.7665413510500082,
101
+ "eval_recall": 0.7777777777777778,
102
+ "eval_runtime": 1.0231,
103
+ "eval_samples_per_second": 237.524,
104
+ "eval_steps_per_second": 30.301,
105
+ "step": 122
106
+ }
107
+ ],
108
+ "logging_steps": 500,
109
+ "max_steps": 150,
110
+ "num_input_tokens_seen": 0,
111
+ "num_train_epochs": 10,
112
+ "save_steps": 500,
113
+ "stateful_callbacks": {
114
+ "EarlyStoppingCallback": {
115
+ "args": {
116
+ "early_stopping_patience": 3,
117
+ "early_stopping_threshold": 0.0
118
+ },
119
+ "attributes": {
120
+ "early_stopping_patience_counter": 0
121
+ }
122
+ },
123
+ "TrainerControl": {
124
+ "args": {
125
+ "should_epoch_stop": false,
126
+ "should_evaluate": false,
127
+ "should_log": false,
128
+ "should_save": true,
129
+ "should_training_stop": false
130
+ },
131
+ "attributes": {}
132
+ }
133
+ },
134
+ "total_flos": 1.766619191808e+16,
135
+ "train_batch_size": 8,
136
+ "trial_name": null,
137
+ "trial_params": null
138
+ }
checkpoint-122/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ba7873d2bd153b717b3ad63778d1f963577e3b32bb96ddb7f3806324b2a0de9
3
+ size 5240
checkpoint-132/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ntu-spml/distilhubert",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "HubertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "do_stable_layer_norm": false,
42
+ "eos_token_id": 2,
43
+ "feat_extract_activation": "gelu",
44
+ "feat_extract_norm": "group",
45
+ "feat_proj_dropout": 0.0,
46
+ "feat_proj_layer_norm": false,
47
+ "final_dropout": 0.0,
48
+ "finetuning_task": "audio-classification",
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.1,
51
+ "hidden_size": 768,
52
+ "id2label": {
53
+ "0": "1s_normal",
54
+ "1": "1s_pain",
55
+ "2": "1s_hunger",
56
+ "3": "1s_asphyxia"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "label2id": {
61
+ "1s_asphyxia": 3,
62
+ "1s_hunger": 2,
63
+ "1s_normal": 0,
64
+ "1s_pain": 1
65
+ },
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.0,
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_prob": 0.05,
74
+ "model_type": "hubert",
75
+ "num_attention_heads": 12,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 2,
80
+ "pad_token_id": 0,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.44.2",
83
+ "use_weighted_layer_sum": false,
84
+ "vocab_size": 32
85
+ }
checkpoint-132/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d5acb50d5e65ea39fa00c5a22601cd6877d6d7830436014d687cfa060e795c6
3
+ size 94765560
checkpoint-132/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94f9a6b91b9a4fc77d4f588f364aa355830eb70d3e5ae69002dd721173b18be5
3
+ size 189556666
checkpoint-132/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bf374bb964364daa385c1bb655dacd7db22dbc45d1febd2d1197b1a44b4b600
3
+ size 14308
checkpoint-132/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be1671a239cf6eb9b15c53789dcd78ba17b4b8af7f8d2fbbe0aaf5dc5d11e573
3
+ size 1064
checkpoint-132/trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7980132450331126,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-94",
4
+ "epoch": 6.993377483443709,
5
+ "eval_steps": 500,
6
+ "global_step": 132,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9536423841059603,
13
+ "eval_accuracy": 0.5298013245033113,
14
+ "eval_f1": 0.43216404525386315,
15
+ "eval_loss": 1.1326755285263062,
16
+ "eval_precision": 0.5213817284211205,
17
+ "eval_recall": 0.5298013245033113,
18
+ "eval_runtime": 1.2241,
19
+ "eval_samples_per_second": 246.709,
20
+ "eval_steps_per_second": 31.043,
21
+ "step": 18
22
+ },
23
+ {
24
+ "epoch": 1.9602649006622517,
25
+ "eval_accuracy": 0.6423841059602649,
26
+ "eval_f1": 0.5806184720425087,
27
+ "eval_loss": 0.9228919744491577,
28
+ "eval_precision": 0.5520930002801896,
29
+ "eval_recall": 0.6423841059602649,
30
+ "eval_runtime": 1.2236,
31
+ "eval_samples_per_second": 246.807,
32
+ "eval_steps_per_second": 31.055,
33
+ "step": 37
34
+ },
35
+ {
36
+ "epoch": 2.966887417218543,
37
+ "eval_accuracy": 0.7086092715231788,
38
+ "eval_f1": 0.6539391094940458,
39
+ "eval_loss": 0.7409619688987732,
40
+ "eval_precision": 0.752516290193287,
41
+ "eval_recall": 0.7086092715231788,
42
+ "eval_runtime": 1.2459,
43
+ "eval_samples_per_second": 242.403,
44
+ "eval_steps_per_second": 30.501,
45
+ "step": 56
46
+ },
47
+ {
48
+ "epoch": 3.9735099337748343,
49
+ "eval_accuracy": 0.7450331125827815,
50
+ "eval_f1": 0.7012377717797856,
51
+ "eval_loss": 0.6461689472198486,
52
+ "eval_precision": 0.7242129191632504,
53
+ "eval_recall": 0.7450331125827815,
54
+ "eval_runtime": 1.229,
55
+ "eval_samples_per_second": 245.723,
56
+ "eval_steps_per_second": 30.919,
57
+ "step": 75
58
+ },
59
+ {
60
+ "epoch": 4.9801324503311255,
61
+ "eval_accuracy": 0.7980132450331126,
62
+ "eval_f1": 0.7903709596982513,
63
+ "eval_loss": 0.5553261041641235,
64
+ "eval_precision": 0.7925903096412185,
65
+ "eval_recall": 0.7980132450331126,
66
+ "eval_runtime": 1.2897,
67
+ "eval_samples_per_second": 234.157,
68
+ "eval_steps_per_second": 29.463,
69
+ "step": 94
70
+ },
71
+ {
72
+ "epoch": 5.986754966887418,
73
+ "eval_accuracy": 0.7781456953642384,
74
+ "eval_f1": 0.7717607879297459,
75
+ "eval_loss": 0.5255588293075562,
76
+ "eval_precision": 0.7771454278224522,
77
+ "eval_recall": 0.7781456953642384,
78
+ "eval_runtime": 1.2928,
79
+ "eval_samples_per_second": 233.597,
80
+ "eval_steps_per_second": 29.393,
81
+ "step": 113
82
+ },
83
+ {
84
+ "epoch": 6.993377483443709,
85
+ "eval_accuracy": 0.7980132450331126,
86
+ "eval_f1": 0.7833793670187674,
87
+ "eval_loss": 0.5077652335166931,
88
+ "eval_precision": 0.7917508237685551,
89
+ "eval_recall": 0.7980132450331126,
90
+ "eval_runtime": 1.2898,
91
+ "eval_samples_per_second": 234.154,
92
+ "eval_steps_per_second": 29.463,
93
+ "step": 132
94
+ }
95
+ ],
96
+ "logging_steps": 500,
97
+ "max_steps": 180,
98
+ "num_input_tokens_seen": 0,
99
+ "num_train_epochs": 10,
100
+ "save_steps": 500,
101
+ "stateful_callbacks": {
102
+ "EarlyStoppingCallback": {
103
+ "args": {
104
+ "early_stopping_patience": 3,
105
+ "early_stopping_threshold": 0.0
106
+ },
107
+ "attributes": {
108
+ "early_stopping_patience_counter": 0
109
+ }
110
+ },
111
+ "TrainerControl": {
112
+ "args": {
113
+ "should_epoch_stop": false,
114
+ "should_evaluate": false,
115
+ "should_log": false,
116
+ "should_save": true,
117
+ "should_training_stop": false
118
+ },
119
+ "attributes": {}
120
+ }
121
+ },
122
+ "total_flos": 1.923085979136e+16,
123
+ "train_batch_size": 8,
124
+ "trial_name": null,
125
+ "trial_params": null
126
+ }
checkpoint-132/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8f2331f3c3c1c25969cfb888574c70dd0e5a19519d8cecb6198afe5225b5a53
3
+ size 5240
checkpoint-137/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ntu-spml/distilhubert",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "HubertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "do_stable_layer_norm": false,
42
+ "eos_token_id": 2,
43
+ "feat_extract_activation": "gelu",
44
+ "feat_extract_norm": "group",
45
+ "feat_proj_dropout": 0.0,
46
+ "feat_proj_layer_norm": false,
47
+ "final_dropout": 0.0,
48
+ "finetuning_task": "audio-classification",
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.1,
51
+ "hidden_size": 768,
52
+ "id2label": {
53
+ "0": "1s_normal",
54
+ "1": "1s_pain",
55
+ "2": "1s_hunger",
56
+ "3": "1s_asphyxia"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "label2id": {
61
+ "1s_asphyxia": 3,
62
+ "1s_hunger": 2,
63
+ "1s_normal": 0,
64
+ "1s_pain": 1
65
+ },
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.0,
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_prob": 0.05,
74
+ "model_type": "hubert",
75
+ "num_attention_heads": 12,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 2,
80
+ "pad_token_id": 0,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.44.2",
83
+ "use_weighted_layer_sum": false,
84
+ "vocab_size": 32
85
+ }
checkpoint-137/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39ca9c2596e3ede8b0c664780c6e2a77e834ec4d94c9528321276567d7a379fa
3
+ size 94765560
checkpoint-137/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9fc2a5db3e0572347e017735077fff0fa9a46b496d997213db0d0d7e8d1611a
3
+ size 189556666
checkpoint-137/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:129c88981660d90edac04935f48c191b4d037b345f5a36b79ecf3fcfb7c2971b
3
+ size 14308
checkpoint-137/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e83c307f6abfc4a33a46f2a262f6dcb1f394f2feb08ef983eb814dbcaa58db5
3
+ size 1064
checkpoint-137/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8054794520547945,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-137",
4
+ "epoch": 5.989071038251366,
5
+ "eval_steps": 500,
6
+ "global_step": 137,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9617486338797814,
13
+ "eval_accuracy": 0.4876712328767123,
14
+ "eval_f1": 0.32440734699411816,
15
+ "eval_loss": 1.1426137685775757,
16
+ "eval_precision": 0.31998188610890976,
17
+ "eval_recall": 0.4876712328767123,
18
+ "eval_runtime": 1.5868,
19
+ "eval_samples_per_second": 230.024,
20
+ "eval_steps_per_second": 28.989,
21
+ "step": 22
22
+ },
23
+ {
24
+ "epoch": 1.9672131147540983,
25
+ "eval_accuracy": 0.6876712328767123,
26
+ "eval_f1": 0.6726372384593322,
27
+ "eval_loss": 0.8035227060317993,
28
+ "eval_precision": 0.6780882232356064,
29
+ "eval_recall": 0.6876712328767123,
30
+ "eval_runtime": 1.5591,
31
+ "eval_samples_per_second": 234.103,
32
+ "eval_steps_per_second": 29.503,
33
+ "step": 45
34
+ },
35
+ {
36
+ "epoch": 2.972677595628415,
37
+ "eval_accuracy": 0.736986301369863,
38
+ "eval_f1": 0.7179122961593137,
39
+ "eval_loss": 0.5865945219993591,
40
+ "eval_precision": 0.7266763525667637,
41
+ "eval_recall": 0.736986301369863,
42
+ "eval_runtime": 1.5049,
43
+ "eval_samples_per_second": 242.544,
44
+ "eval_steps_per_second": 30.567,
45
+ "step": 68
46
+ },
47
+ {
48
+ "epoch": 3.978142076502732,
49
+ "eval_accuracy": 0.7945205479452054,
50
+ "eval_f1": 0.7852674207057345,
51
+ "eval_loss": 0.5180361270904541,
52
+ "eval_precision": 0.7921658130880418,
53
+ "eval_recall": 0.7945205479452054,
54
+ "eval_runtime": 1.524,
55
+ "eval_samples_per_second": 239.5,
56
+ "eval_steps_per_second": 30.184,
57
+ "step": 91
58
+ },
59
+ {
60
+ "epoch": 4.983606557377049,
61
+ "eval_accuracy": 0.7232876712328767,
62
+ "eval_f1": 0.7299958784843185,
63
+ "eval_loss": 0.6972417831420898,
64
+ "eval_precision": 0.7954469760289924,
65
+ "eval_recall": 0.7232876712328767,
66
+ "eval_runtime": 1.5556,
67
+ "eval_samples_per_second": 234.639,
68
+ "eval_steps_per_second": 29.571,
69
+ "step": 114
70
+ },
71
+ {
72
+ "epoch": 5.989071038251366,
73
+ "eval_accuracy": 0.8054794520547945,
74
+ "eval_f1": 0.7958302021593314,
75
+ "eval_loss": 0.5580042004585266,
76
+ "eval_precision": 0.8052187633545131,
77
+ "eval_recall": 0.8054794520547945,
78
+ "eval_runtime": 1.5685,
79
+ "eval_samples_per_second": 232.706,
80
+ "eval_steps_per_second": 29.327,
81
+ "step": 137
82
+ }
83
+ ],
84
+ "logging_steps": 500,
85
+ "max_steps": 220,
86
+ "num_input_tokens_seen": 0,
87
+ "num_train_epochs": 10,
88
+ "save_steps": 500,
89
+ "stateful_callbacks": {
90
+ "EarlyStoppingCallback": {
91
+ "args": {
92
+ "early_stopping_patience": 3,
93
+ "early_stopping_threshold": 0.0
94
+ },
95
+ "attributes": {
96
+ "early_stopping_patience_counter": 0
97
+ }
98
+ },
99
+ "TrainerControl": {
100
+ "args": {
101
+ "should_epoch_stop": false,
102
+ "should_evaluate": false,
103
+ "should_log": false,
104
+ "should_save": true,
105
+ "should_training_stop": false
106
+ },
107
+ "attributes": {}
108
+ }
109
+ },
110
+ "total_flos": 1.990857930624e+16,
111
+ "train_batch_size": 8,
112
+ "trial_name": null,
113
+ "trial_params": null
114
+ }
checkpoint-137/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c635d78c39083a6b3129b7505b6c1291835366a67e1fe687b603a5a1a2dc7f36
3
+ size 5240
checkpoint-15/config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ntu-spml/distilhubert",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "HubertForSequenceClassification"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 1,
10
+ "classifier_proj_size": 256,
11
+ "conv_bias": false,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "do_stable_layer_norm": false,
42
+ "eos_token_id": 2,
43
+ "feat_extract_activation": "gelu",
44
+ "feat_extract_norm": "group",
45
+ "feat_proj_dropout": 0.0,
46
+ "feat_proj_layer_norm": false,
47
+ "final_dropout": 0.0,
48
+ "finetuning_task": "audio-classification",
49
+ "hidden_act": "gelu",
50
+ "hidden_dropout": 0.1,
51
+ "hidden_size": 768,
52
+ "id2label": {
53
+ "0": "1s_normal",
54
+ "1": "1s_pain",
55
+ "2": "1s_hunger",
56
+ "3": "1s_asphyxia"
57
+ },
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "label2id": {
61
+ "1s_asphyxia": 3,
62
+ "1s_hunger": 2,
63
+ "1s_normal": 0,
64
+ "1s_pain": 1
65
+ },
66
+ "layer_norm_eps": 1e-05,
67
+ "layerdrop": 0.0,
68
+ "mask_feature_length": 10,
69
+ "mask_feature_min_masks": 0,
70
+ "mask_feature_prob": 0.0,
71
+ "mask_time_length": 10,
72
+ "mask_time_min_masks": 2,
73
+ "mask_time_prob": 0.05,
74
+ "model_type": "hubert",
75
+ "num_attention_heads": 12,
76
+ "num_conv_pos_embedding_groups": 16,
77
+ "num_conv_pos_embeddings": 128,
78
+ "num_feat_extract_layers": 7,
79
+ "num_hidden_layers": 2,
80
+ "pad_token_id": 0,
81
+ "torch_dtype": "float32",
82
+ "transformers_version": "4.44.2",
83
+ "use_weighted_layer_sum": false,
84
+ "vocab_size": 32
85
+ }
checkpoint-15/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8458532214081c6a9cf09bb95a6cda1f827eb5a17552ce274b47948b42d4e2b
3
+ size 94765560
checkpoint-15/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93ceee8a2190e695db70bca71bb0bcdc69c2f5954c5ad813f81f0d9449654fcb
3
+ size 189556666
checkpoint-15/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3bebf6828c1c590fcaee890d2dd25dbc601bea286aaad54a324dcb35b4f2544
3
+ size 14308
checkpoint-15/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a893204be2142547fa1a3425466dd9883a46de8ccc7308456b7cffc9cecff679
3
+ size 1064
checkpoint-15/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5637860082304527,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-15",
4
+ "epoch": 0.9836065573770492,
5
+ "eval_steps": 500,
6
+ "global_step": 15,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9836065573770492,
13
+ "eval_accuracy": 0.5637860082304527,
14
+ "eval_f1": 0.49656016746502873,
15
+ "eval_loss": 1.1263551712036133,
16
+ "eval_precision": 0.5260403310011795,
17
+ "eval_recall": 0.5637860082304527,
18
+ "eval_runtime": 1.0189,
19
+ "eval_samples_per_second": 238.499,
20
+ "eval_steps_per_second": 30.426,
21
+ "step": 15
22
+ }
23
+ ],
24
+ "logging_steps": 500,
25
+ "max_steps": 150,
26
+ "num_input_tokens_seen": 0,
27
+ "num_train_epochs": 10,
28
+ "save_steps": 500,
29
+ "stateful_callbacks": {
30
+ "EarlyStoppingCallback": {
31
+ "args": {
32
+ "early_stopping_patience": 3,
33
+ "early_stopping_threshold": 0.0
34
+ },
35
+ "attributes": {
36
+ "early_stopping_patience_counter": 0
37
+ }
38
+ },
39
+ "TrainerControl": {
40
+ "args": {
41
+ "should_epoch_stop": false,
42
+ "should_evaluate": false,
43
+ "should_log": false,
44
+ "should_save": true,
45
+ "should_training_stop": false
46
+ },
47
+ "attributes": {}
48
+ }
49
+ },
50
+ "total_flos": 2208273989760000.0,
51
+ "train_batch_size": 8,
52
+ "trial_name": null,
53
+ "trial_params": null
54
+ }
checkpoint-15/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ba7873d2bd153b717b3ad63778d1f963577e3b32bb96ddb7f3806324b2a0de9
3
+ size 5240