Hugging Face's logo

A-POR-LOS-8000
/
distilhubert-finetuned-mixed-data

Audio Classification
Transformers
TensorBoard
Safetensors
hubert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Marcos12886 commited on
Commit
b88bca6
•
1 Parent(s): 01d8895

Upload folder using huggingface_hub

Browse files
Files changed (47) hide show
  1. checkpoint-121/config.json +85 -0
  2. checkpoint-121/model.safetensors +3 -0
  3. checkpoint-121/optimizer.pt +3 -0
  4. checkpoint-121/rng_state.pth +3 -0
  5. checkpoint-121/scheduler.pt +3 -0
  6. checkpoint-121/trainer_state.json +102 -0
  7. checkpoint-121/training_args.bin +3 -0
  8. checkpoint-144/config.json +85 -0
  9. checkpoint-144/model.safetensors +3 -0
  10. checkpoint-144/optimizer.pt +3 -0
  11. checkpoint-144/rng_state.pth +3 -0
  12. checkpoint-144/scheduler.pt +3 -0
  13. checkpoint-144/trainer_state.json +114 -0
  14. checkpoint-144/training_args.bin +3 -0
  15. checkpoint-24/config.json +85 -0
  16. checkpoint-24/model.safetensors +3 -0
  17. checkpoint-24/optimizer.pt +3 -0
  18. checkpoint-24/rng_state.pth +3 -0
  19. checkpoint-24/scheduler.pt +3 -0
  20. checkpoint-24/trainer_state.json +54 -0
  21. checkpoint-24/training_args.bin +3 -0
  22. checkpoint-48/config.json +85 -0
  23. checkpoint-48/model.safetensors +3 -0
  24. checkpoint-48/optimizer.pt +3 -0
  25. checkpoint-48/rng_state.pth +3 -0
  26. checkpoint-48/scheduler.pt +3 -0
  27. checkpoint-48/trainer_state.json +66 -0
  28. checkpoint-48/training_args.bin +3 -0
  29. checkpoint-72/config.json +85 -0
  30. checkpoint-72/model.safetensors +3 -0
  31. checkpoint-72/optimizer.pt +3 -0
  32. checkpoint-72/rng_state.pth +3 -0
  33. checkpoint-72/scheduler.pt +3 -0
  34. checkpoint-72/trainer_state.json +78 -0
  35. checkpoint-72/training_args.bin +3 -0
  36. checkpoint-97/config.json +85 -0
  37. checkpoint-97/model.safetensors +3 -0
  38. checkpoint-97/optimizer.pt +3 -0
  39. checkpoint-97/rng_state.pth +3 -0
  40. checkpoint-97/scheduler.pt +3 -0
  41. checkpoint-97/trainer_state.json +90 -0
  42. checkpoint-97/training_args.bin +3 -0
  43. config.json +9 -8
  44. model.safetensors +1 -1
  45. runs/Sep06_17-09-23_ubumarcos/events.out.tfevents.1725635364.ubumarcos +3 -0
  46. runs/Sep06_17-58-56_ubumarcos/events.out.tfevents.1725638337.ubumarcos +3 -0
  47. training_args.bin +1 -1
checkpoint-121/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-121/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f17cc1a80f9cdf7f1c5c94c70062ca59ee73223709355f94eae716447e99d02
3
+ size 94765560
checkpoint-121/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af430e7b5cbd26cc609cc5c918049ec696a387c13101b4292d1bd68dd2695f0e
3
+ size 189556666
checkpoint-121/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d192864925cf93da2109df89709998e97445c2f0e2cb3b0965d9757c92c461fb
3
+ size 14308
checkpoint-121/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:192b51d0f1e5456c85d7a6eeae550a33132f97495282fa7f439444f5f22297cf
3
+ size 1064
checkpoint-121/trainer_state.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7648578811369509,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-121",
4
+ "epoch": 4.989690721649485,
5
+ "eval_steps": 500,
6
+ "global_step": 121,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9896907216494846,
13
+ "eval_accuracy": 0.6098191214470284,
14
+ "eval_f1": 0.5527821682108387,
15
+ "eval_loss": 1.0193405151367188,
16
+ "eval_precision": 0.7003292379638224,
17
+ "eval_recall": 0.6098191214470284,
18
+ "eval_runtime": 1.7319,
19
+ "eval_samples_per_second": 223.453,
20
+ "eval_steps_per_second": 28.293,
21
+ "step": 24
22
+ },
23
+ {
24
+ "epoch": 1.9793814432989691,
25
+ "eval_accuracy": 0.6795865633074936,
26
+ "eval_f1": 0.6650515718181741,
27
+ "eval_loss": 0.7780925631523132,
28
+ "eval_precision": 0.6877908327609833,
29
+ "eval_recall": 0.6795865633074936,
30
+ "eval_runtime": 1.7105,
31
+ "eval_samples_per_second": 226.247,
32
+ "eval_steps_per_second": 28.646,
33
+ "step": 48
34
+ },
35
+ {
36
+ "epoch": 2.9690721649484537,
37
+ "eval_accuracy": 0.7260981912144703,
38
+ "eval_f1": 0.7125387559196679,
39
+ "eval_loss": 0.663092315196991,
40
+ "eval_precision": 0.7236217153897081,
41
+ "eval_recall": 0.7260981912144703,
42
+ "eval_runtime": 1.7131,
43
+ "eval_samples_per_second": 225.911,
44
+ "eval_steps_per_second": 28.604,
45
+ "step": 72
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_accuracy": 0.7493540051679587,
50
+ "eval_f1": 0.7323843170610034,
51
+ "eval_loss": 0.5870956778526306,
52
+ "eval_precision": 0.7505520883603423,
53
+ "eval_recall": 0.7493540051679587,
54
+ "eval_runtime": 1.7332,
55
+ "eval_samples_per_second": 223.293,
56
+ "eval_steps_per_second": 28.272,
57
+ "step": 97
58
+ },
59
+ {
60
+ "epoch": 4.989690721649485,
61
+ "eval_accuracy": 0.7648578811369509,
62
+ "eval_f1": 0.7570271532827265,
63
+ "eval_loss": 0.5548774003982544,
64
+ "eval_precision": 0.7717080207133444,
65
+ "eval_recall": 0.7648578811369509,
66
+ "eval_runtime": 1.744,
67
+ "eval_samples_per_second": 221.907,
68
+ "eval_steps_per_second": 28.097,
69
+ "step": 121
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 144,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 6,
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": 1.7568400176e+16,
99
+ "train_batch_size": 8,
100
+ "trial_name": null,
101
+ "trial_params": null
102
+ }
checkpoint-121/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f758b94689e09a814f1948cbbce56e483b2b53509b111e749d1961a9e2d3ad45
3
+ size 5240
checkpoint-144/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-144/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:434940fe3e2b22309fb9af0c3512442530f22637ab0269f75e702c93fc674ecb
3
+ size 94765560
checkpoint-144/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ce85a18c4fb7ae6e88e1ed281f5ab613f352a7b9b84c67b4f6a7c240936c7c8
3
+ size 189556666
checkpoint-144/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efe5fd7add3140d25fb667111de542d52852237ad203bc86ce5cdd0a0b1dc509
3
+ size 14308
checkpoint-144/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b68ca7851e25aa0e201dd5baca70d6ef76f56b190fd01837456a905de722117
3
+ size 1064
checkpoint-144/trainer_state.json ADDED
@@ -0,0 +1,114 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7674418604651163,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-144",
4
+ "epoch": 5.938144329896907,
5
+ "eval_steps": 500,
6
+ "global_step": 144,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9896907216494846,
13
+ "eval_accuracy": 0.6098191214470284,
14
+ "eval_f1": 0.5527821682108387,
15
+ "eval_loss": 1.0193405151367188,
16
+ "eval_precision": 0.7003292379638224,
17
+ "eval_recall": 0.6098191214470284,
18
+ "eval_runtime": 1.7319,
19
+ "eval_samples_per_second": 223.453,
20
+ "eval_steps_per_second": 28.293,
21
+ "step": 24
22
+ },
23
+ {
24
+ "epoch": 1.9793814432989691,
25
+ "eval_accuracy": 0.6795865633074936,
26
+ "eval_f1": 0.6650515718181741,
27
+ "eval_loss": 0.7780925631523132,
28
+ "eval_precision": 0.6877908327609833,
29
+ "eval_recall": 0.6795865633074936,
30
+ "eval_runtime": 1.7105,
31
+ "eval_samples_per_second": 226.247,
32
+ "eval_steps_per_second": 28.646,
33
+ "step": 48
34
+ },
35
+ {
36
+ "epoch": 2.9690721649484537,
37
+ "eval_accuracy": 0.7260981912144703,
38
+ "eval_f1": 0.7125387559196679,
39
+ "eval_loss": 0.663092315196991,
40
+ "eval_precision": 0.7236217153897081,
41
+ "eval_recall": 0.7260981912144703,
42
+ "eval_runtime": 1.7131,
43
+ "eval_samples_per_second": 225.911,
44
+ "eval_steps_per_second": 28.604,
45
+ "step": 72
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_accuracy": 0.7493540051679587,
50
+ "eval_f1": 0.7323843170610034,
51
+ "eval_loss": 0.5870956778526306,
52
+ "eval_precision": 0.7505520883603423,
53
+ "eval_recall": 0.7493540051679587,
54
+ "eval_runtime": 1.7332,
55
+ "eval_samples_per_second": 223.293,
56
+ "eval_steps_per_second": 28.272,
57
+ "step": 97
58
+ },
59
+ {
60
+ "epoch": 4.989690721649485,
61
+ "eval_accuracy": 0.7648578811369509,
62
+ "eval_f1": 0.7570271532827265,
63
+ "eval_loss": 0.5548774003982544,
64
+ "eval_precision": 0.7717080207133444,
65
+ "eval_recall": 0.7648578811369509,
66
+ "eval_runtime": 1.744,
67
+ "eval_samples_per_second": 221.907,
68
+ "eval_steps_per_second": 28.097,
69
+ "step": 121
70
+ },
71
+ {
72
+ "epoch": 5.938144329896907,
73
+ "eval_accuracy": 0.7674418604651163,
74
+ "eval_f1": 0.7605087043783928,
75
+ "eval_loss": 0.5497403144836426,
76
+ "eval_precision": 0.7731114884926515,
77
+ "eval_recall": 0.7674418604651163,
78
+ "eval_runtime": 1.7702,
79
+ "eval_samples_per_second": 218.618,
80
+ "eval_steps_per_second": 27.68,
81
+ "step": 144
82
+ }
83
+ ],
84
+ "logging_steps": 500,
85
+ "max_steps": 144,
86
+ "num_input_tokens_seen": 0,
87
+ "num_train_epochs": 6,
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": true
106
+ },
107
+ "attributes": {}
108
+ }
109
+ },
110
+ "total_flos": 2.087967404736e+16,
111
+ "train_batch_size": 8,
112
+ "trial_name": null,
113
+ "trial_params": null
114
+ }
checkpoint-144/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f758b94689e09a814f1948cbbce56e483b2b53509b111e749d1961a9e2d3ad45
3
+ size 5240
checkpoint-24/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-24/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d78a6da83be7342ac8b77471231136cb466162ebc8c50bec013c326cb42c0064
3
+ size 94765560
checkpoint-24/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52b6c6fc53345f40e4a065ef30e33ed54befbc33401a1b2c792ab2532d98ba4d
3
+ size 189556666
checkpoint-24/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dfbead32b1c4ff8d1271c1899bd626bf08d46cbc21d2769431f03d7912b1368
3
+ size 14308
checkpoint-24/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3b5edb3a337b55456e10de8e5d582a8acbe41a6ddc5e0ffb6c3463e1e8bd89e
3
+ size 1064
checkpoint-24/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4728682170542636,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-24",
4
+ "epoch": 0.9896907216494846,
5
+ "eval_steps": 500,
6
+ "global_step": 24,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9896907216494846,
13
+ "eval_accuracy": 0.4728682170542636,
14
+ "eval_f1": 0.3374281761878661,
15
+ "eval_loss": 1.1742454767227173,
16
+ "eval_precision": 0.3153297382316594,
17
+ "eval_recall": 0.4728682170542636,
18
+ "eval_runtime": 1.7717,
19
+ "eval_samples_per_second": 218.439,
20
+ "eval_steps_per_second": 27.658,
21
+ "step": 24
22
+ }
23
+ ],
24
+ "logging_steps": 500,
25
+ "max_steps": 24,
26
+ "num_input_tokens_seen": 0,
27
+ "num_train_epochs": 1,
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": true
46
+ },
47
+ "attributes": {}
48
+ }
49
+ },
50
+ "total_flos": 3493211996160000.0,
51
+ "train_batch_size": 8,
52
+ "trial_name": null,
53
+ "trial_params": null
54
+ }
checkpoint-24/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af007629d5617a28ca41ddaece5deaec41829efba800ea8ef358852b951147e
3
+ size 5240
checkpoint-48/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-48/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b70579301bd070215facd604eef3fa6085c3d36b83a56b214fd361987a8b0a0b
3
+ size 94765560
checkpoint-48/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b36c98b895fb661cc797380b744ef81a3388846135aec85c75e9110fc5ca2c05
3
+ size 189556666
checkpoint-48/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f9cbdb2c6d711d4b07d5c44fbe2571bdf0b92fd58e29512676ddee90a5f1c70
3
+ size 14308
checkpoint-48/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbf38641e9fb31561b293062c60265089034749c9b71d81c07e3d707dcb1ab51
3
+ size 1064
checkpoint-48/trainer_state.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6795865633074936,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-48",
4
+ "epoch": 1.9793814432989691,
5
+ "eval_steps": 500,
6
+ "global_step": 48,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9896907216494846,
13
+ "eval_accuracy": 0.6098191214470284,
14
+ "eval_f1": 0.5527821682108387,
15
+ "eval_loss": 1.0193405151367188,
16
+ "eval_precision": 0.7003292379638224,
17
+ "eval_recall": 0.6098191214470284,
18
+ "eval_runtime": 1.7319,
19
+ "eval_samples_per_second": 223.453,
20
+ "eval_steps_per_second": 28.293,
21
+ "step": 24
22
+ },
23
+ {
24
+ "epoch": 1.9793814432989691,
25
+ "eval_accuracy": 0.6795865633074936,
26
+ "eval_f1": 0.6650515718181741,
27
+ "eval_loss": 0.7780925631523132,
28
+ "eval_precision": 0.6877908327609833,
29
+ "eval_recall": 0.6795865633074936,
30
+ "eval_runtime": 1.7105,
31
+ "eval_samples_per_second": 226.247,
32
+ "eval_steps_per_second": 28.646,
33
+ "step": 48
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 144,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 6,
40
+ "save_steps": 500,
41
+ "stateful_callbacks": {
42
+ "EarlyStoppingCallback": {
43
+ "args": {
44
+ "early_stopping_patience": 3,
45
+ "early_stopping_threshold": 0.0
46
+ },
47
+ "attributes": {
48
+ "early_stopping_patience_counter": 0
49
+ }
50
+ },
51
+ "TrainerControl": {
52
+ "args": {
53
+ "should_epoch_stop": false,
54
+ "should_evaluate": false,
55
+ "should_log": false,
56
+ "should_save": true,
57
+ "should_training_stop": false
58
+ },
59
+ "attributes": {}
60
+ }
61
+ },
62
+ "total_flos": 7027360070400000.0,
63
+ "train_batch_size": 8,
64
+ "trial_name": null,
65
+ "trial_params": null
66
+ }
checkpoint-48/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f758b94689e09a814f1948cbbce56e483b2b53509b111e749d1961a9e2d3ad45
3
+ size 5240
checkpoint-72/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-72/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c6d8a9bb511a47d9f8c8d94ca004e0d3631edd77a234c31b38772da2cbfab0
3
+ size 94765560
checkpoint-72/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a01477828151d9302ffb883445b27ed488c6fab05edef4659327e7b85b82a57
3
+ size 189556666
checkpoint-72/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3522560e565218b6663eeab3b8d9ab4726c5760eb23fe1339f732fa6c6f00a0
3
+ size 14308
checkpoint-72/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:395fbbe365895cda4ce756be4692252071ddfad60f8f48069469260e726f6b62
3
+ size 1064
checkpoint-72/trainer_state.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7260981912144703,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-72",
4
+ "epoch": 2.9690721649484537,
5
+ "eval_steps": 500,
6
+ "global_step": 72,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9896907216494846,
13
+ "eval_accuracy": 0.6098191214470284,
14
+ "eval_f1": 0.5527821682108387,
15
+ "eval_loss": 1.0193405151367188,
16
+ "eval_precision": 0.7003292379638224,
17
+ "eval_recall": 0.6098191214470284,
18
+ "eval_runtime": 1.7319,
19
+ "eval_samples_per_second": 223.453,
20
+ "eval_steps_per_second": 28.293,
21
+ "step": 24
22
+ },
23
+ {
24
+ "epoch": 1.9793814432989691,
25
+ "eval_accuracy": 0.6795865633074936,
26
+ "eval_f1": 0.6650515718181741,
27
+ "eval_loss": 0.7780925631523132,
28
+ "eval_precision": 0.6877908327609833,
29
+ "eval_recall": 0.6795865633074936,
30
+ "eval_runtime": 1.7105,
31
+ "eval_samples_per_second": 226.247,
32
+ "eval_steps_per_second": 28.646,
33
+ "step": 48
34
+ },
35
+ {
36
+ "epoch": 2.9690721649484537,
37
+ "eval_accuracy": 0.7260981912144703,
38
+ "eval_f1": 0.7125387559196679,
39
+ "eval_loss": 0.663092315196991,
40
+ "eval_precision": 0.7236217153897081,
41
+ "eval_recall": 0.7260981912144703,
42
+ "eval_runtime": 1.7131,
43
+ "eval_samples_per_second": 225.911,
44
+ "eval_steps_per_second": 28.604,
45
+ "step": 72
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 144,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 6,
52
+ "save_steps": 500,
53
+ "stateful_callbacks": {
54
+ "EarlyStoppingCallback": {
55
+ "args": {
56
+ "early_stopping_patience": 3,
57
+ "early_stopping_threshold": 0.0
58
+ },
59
+ "attributes": {
60
+ "early_stopping_patience_counter": 0
61
+ }
62
+ },
63
+ "TrainerControl": {
64
+ "args": {
65
+ "should_epoch_stop": false,
66
+ "should_evaluate": false,
67
+ "should_log": false,
68
+ "should_save": true,
69
+ "should_training_stop": false
70
+ },
71
+ "attributes": {}
72
+ }
73
+ },
74
+ "total_flos": 1.05410401056e+16,
75
+ "train_batch_size": 8,
76
+ "trial_name": null,
77
+ "trial_params": null
78
+ }
checkpoint-72/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f758b94689e09a814f1948cbbce56e483b2b53509b111e749d1961a9e2d3ad45
3
+ size 5240
checkpoint-97/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-97/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb4411294ffdebd3325f2c2a9fe8bb8da45ecdf21e27ea71487650e32342e3f
3
+ size 94765560
checkpoint-97/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c079ffaa2b8e6e0267bd097fcdd02618cec3d1413fc09b575441e5c90b1bc5e
3
+ size 189556666
checkpoint-97/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d439ef21ecde4890958d6f1346e10eacaa9ba5ddeb4801bf0e15758a657d4e8
3
+ size 14308
checkpoint-97/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25774c9bc4970b842f1daad063c77fc68915a49c8d8ccb103e1082b3b05e435f
3
+ size 1064
checkpoint-97/trainer_state.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7493540051679587,
3
+ "best_model_checkpoint": "distilhubert-finetuned-mixed-data/checkpoint-97",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 97,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9896907216494846,
13
+ "eval_accuracy": 0.6098191214470284,
14
+ "eval_f1": 0.5527821682108387,
15
+ "eval_loss": 1.0193405151367188,
16
+ "eval_precision": 0.7003292379638224,
17
+ "eval_recall": 0.6098191214470284,
18
+ "eval_runtime": 1.7319,
19
+ "eval_samples_per_second": 223.453,
20
+ "eval_steps_per_second": 28.293,
21
+ "step": 24
22
+ },
23
+ {
24
+ "epoch": 1.9793814432989691,
25
+ "eval_accuracy": 0.6795865633074936,
26
+ "eval_f1": 0.6650515718181741,
27
+ "eval_loss": 0.7780925631523132,
28
+ "eval_precision": 0.6877908327609833,
29
+ "eval_recall": 0.6795865633074936,
30
+ "eval_runtime": 1.7105,
31
+ "eval_samples_per_second": 226.247,
32
+ "eval_steps_per_second": 28.646,
33
+ "step": 48
34
+ },
35
+ {
36
+ "epoch": 2.9690721649484537,
37
+ "eval_accuracy": 0.7260981912144703,
38
+ "eval_f1": 0.7125387559196679,
39
+ "eval_loss": 0.663092315196991,
40
+ "eval_precision": 0.7236217153897081,
41
+ "eval_recall": 0.7260981912144703,
42
+ "eval_runtime": 1.7131,
43
+ "eval_samples_per_second": 225.911,
44
+ "eval_steps_per_second": 28.604,
45
+ "step": 72
46
+ },
47
+ {
48
+ "epoch": 4.0,
49
+ "eval_accuracy": 0.7493540051679587,
50
+ "eval_f1": 0.7323843170610034,
51
+ "eval_loss": 0.5870956778526306,
52
+ "eval_precision": 0.7505520883603423,
53
+ "eval_recall": 0.7493540051679587,
54
+ "eval_runtime": 1.7332,
55
+ "eval_samples_per_second": 223.293,
56
+ "eval_steps_per_second": 28.272,
57
+ "step": 97
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 144,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 6,
64
+ "save_steps": 500,
65
+ "stateful_callbacks": {
66
+ "EarlyStoppingCallback": {
67
+ "args": {
68
+ "early_stopping_patience": 3,
69
+ "early_stopping_threshold": 0.0
70
+ },
71
+ "attributes": {
72
+ "early_stopping_patience_counter": 0
73
+ }
74
+ },
75
+ "TrainerControl": {
76
+ "args": {
77
+ "should_epoch_stop": false,
78
+ "should_evaluate": false,
79
+ "should_log": false,
80
+ "should_save": true,
81
+ "should_training_stop": false
82
+ },
83
+ "attributes": {}
84
+ }
85
+ },
86
+ "total_flos": 1.40547201408e+16,
87
+ "train_batch_size": 8,
88
+ "trial_name": null,
89
+ "trial_params": null
90
+ }
checkpoint-97/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f758b94689e09a814f1948cbbce56e483b2b53509b111e749d1961a9e2d3ad45
3
+ size 5240
config.json CHANGED
@@ -45,22 +45,23 @@
45
  "feat_proj_dropout": 0.0,
46
  "feat_proj_layer_norm": false,
47
  "final_dropout": 0.0,
 
48
  "hidden_act": "gelu",
49
  "hidden_dropout": 0.1,
50
  "hidden_size": 768,
51
  "id2label": {
52
- "0": "1s_asphyxia",
53
- "1": "1s_hunger",
54
- "2": "1s_normal",
55
- "3": "1s_pain"
56
  },
57
  "initializer_range": 0.02,
58
  "intermediate_size": 3072,
59
  "label2id": {
60
- "1s_asphyxia": "0",
61
- "1s_hunger": "1",
62
- "1s_normal": "2",
63
- "1s_pain": "3"
64
  },
65
  "layer_norm_eps": 1e-05,
66
  "layerdrop": 0.0,
 
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,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4510ed7e13f4bc4dd001eb3a533578bbc919b6f595428ad96456f352af1cc8e6
3
  size 94765560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d78a6da83be7342ac8b77471231136cb466162ebc8c50bec013c326cb42c0064
3
  size 94765560
runs/Sep06_17-09-23_ubumarcos/events.out.tfevents.1725635364.ubumarcos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43149ca43e4966971d308f4256f4c477deabea76c18a6167f42618abb2f631eb
3
+ size 9075
runs/Sep06_17-58-56_ubumarcos/events.out.tfevents.1725638337.ubumarcos ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fabf685bf6b5e07f756a45850e518fdc8ee047bddbd758b39eb3bb46371eeb90
3
+ size 6745
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe27a0d5e806b0063e266dd4fd14931fcc64442e144d0583ad0d23b51c88e0c3
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af007629d5617a28ca41ddaece5deaec41829efba800ea8ef358852b951147e
3
  size 5240