Hugging Face's logo

marinone94
/
xls-r-300m-sv-robust

Automatic Speech Recognition
Transformers
PyTorch
Swedish
wav2vec2
mozilla-foundation/common_voice_9_0
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
marinone94 commited on
Commit
dfda964
•
1 Parent(s): e92b35b

End of training

Browse files
Files changed (22) hide show
  1. .ipynb_checkpoints/added_tokens-checkpoint.json +1 -0
  2. .ipynb_checkpoints/all_results-checkpoint.json +8 -0
  3. .ipynb_checkpoints/config-checkpoint.json +107 -0
  4. .ipynb_checkpoints/preprocessor_config-checkpoint.json +9 -0
  5. .ipynb_checkpoints/special_tokens_map-checkpoint.json +1 -0
  6. .ipynb_checkpoints/tokenizer_config-checkpoint.json +1 -0
  7. .ipynb_checkpoints/train_results-checkpoint.json +8 -0
  8. .ipynb_checkpoints/trainer_state-checkpoint.json +103 -0
  9. all_results.json +14 -0
  10. checkpoint-10/config.json +107 -0
  11. checkpoint-10/optimizer.pt +3 -0
  12. checkpoint-10/preprocessor_config.json +9 -0
  13. checkpoint-10/pytorch_model.bin +3 -0
  14. checkpoint-10/rng_state.pth +3 -0
  15. checkpoint-10/scaler.pt +3 -0
  16. checkpoint-10/scheduler.pt +3 -0
  17. checkpoint-10/trainer_state.json +94 -0
  18. checkpoint-10/training_args.bin +3 -0
  19. eval_results.json +9 -0
  20. pytorch_model.bin +1 -1
  21. train_results.json +8 -0
  22. trainer_state.json +103 -0
.ipynb_checkpoints/added_tokens-checkpoint.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<s>": 35, "</s>": 36}
.ipynb_checkpoints/all_results-checkpoint.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.03,
3
+ "train_loss": 12.162414741516113,
4
+ "train_runtime": 400.3916,
5
+ "train_samples": 11030,
6
+ "train_samples_per_second": 0.799,
7
+ "train_steps_per_second": 0.025
8
+ }
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForCTC"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.0,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.0,
57
+ "hidden_size": 1024,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 4096,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.0,
62
+ "mask_feature_length": 64,
63
+ "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.25,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.75,
68
+ "model_type": "wav2vec2",
69
+ "num_adapter_layers": 3,
70
+ "num_attention_heads": 16,
71
+ "num_codevector_groups": 2,
72
+ "num_codevectors_per_group": 320,
73
+ "num_conv_pos_embedding_groups": 16,
74
+ "num_conv_pos_embeddings": 128,
75
+ "num_feat_extract_layers": 7,
76
+ "num_hidden_layers": 24,
77
+ "num_negatives": 100,
78
+ "output_hidden_size": 1024,
79
+ "pad_token_id": 34,
80
+ "proj_codevector_dim": 768,
81
+ "tdnn_dilation": [
82
+ 1,
83
+ 2,
84
+ 3,
85
+ 1,
86
+ 1
87
+ ],
88
+ "tdnn_dim": [
89
+ 512,
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 1500
94
+ ],
95
+ "tdnn_kernel": [
96
+ 5,
97
+ 3,
98
+ 3,
99
+ 1,
100
+ 1
101
+ ],
102
+ "torch_dtype": "float32",
103
+ "transformers_version": "4.16.0.dev0",
104
+ "use_weighted_layer_sum": false,
105
+ "vocab_size": 37,
106
+ "xvector_output_dim": 512
107
+ }
.ipynb_checkpoints/preprocessor_config-checkpoint.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
.ipynb_checkpoints/special_tokens_map-checkpoint.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
.ipynb_checkpoints/tokenizer_config-checkpoint.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
.ipynb_checkpoints/train_results-checkpoint.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.03,
3
+ "train_loss": 12.162414741516113,
4
+ "train_runtime": 400.3916,
5
+ "train_samples": 11030,
6
+ "train_samples_per_second": 0.799,
7
+ "train_steps_per_second": 0.025
8
+ }
.ipynb_checkpoints/trainer_state-checkpoint.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.029006526468455404,
5
+ "global_step": 10,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 3.75e-06,
13
+ "loss": 13.605,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 7.5e-06,
19
+ "loss": 11.0063,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 1.1249999999999999e-05,
25
+ "loss": 11.6693,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 1.5e-05,
31
+ "loss": 13.432,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.01,
36
+ "learning_rate": 1.875e-05,
37
+ "loss": 10.3458,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "eval_loss": 15.09913444519043,
43
+ "eval_runtime": 139.8551,
44
+ "eval_samples_per_second": 33.034,
45
+ "eval_steps_per_second": 4.133,
46
+ "eval_wer": 1.0,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.02,
51
+ "learning_rate": 2.2499999999999998e-05,
52
+ "loss": 15.2451,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.02,
57
+ "learning_rate": 2.625e-05,
58
+ "loss": 10.0481,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.02,
63
+ "learning_rate": 3e-05,
64
+ "loss": 12.3838,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.03,
69
+ "learning_rate": 3.3749999999999994e-05,
70
+ "loss": 11.9858,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.03,
75
+ "learning_rate": 3.75e-05,
76
+ "loss": 11.9029,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.03,
81
+ "eval_loss": 14.213573455810547,
82
+ "eval_runtime": 160.2552,
83
+ "eval_samples_per_second": 28.829,
84
+ "eval_steps_per_second": 3.607,
85
+ "eval_wer": 1.0,
86
+ "step": 10
87
+ },
88
+ {
89
+ "epoch": 0.03,
90
+ "step": 10,
91
+ "total_flos": 4.405923604988928e+16,
92
+ "train_loss": 12.162414741516113,
93
+ "train_runtime": 400.3916,
94
+ "train_samples_per_second": 0.799,
95
+ "train_steps_per_second": 0.025
96
+ }
97
+ ],
98
+ "max_steps": 10,
99
+ "num_train_epochs": 1,
100
+ "total_flos": 4.405923604988928e+16,
101
+ "trial_name": null,
102
+ "trial_params": null
103
+ }
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.03,
3
+ "eval_loss": 14.213573455810547,
4
+ "eval_runtime": 148.129,
5
+ "eval_samples": 4620,
6
+ "eval_samples_per_second": 31.189,
7
+ "eval_steps_per_second": 3.902,
8
+ "eval_wer": 1.0,
9
+ "train_loss": 12.162414741516113,
10
+ "train_runtime": 400.3916,
11
+ "train_samples": 11030,
12
+ "train_samples_per_second": 0.799,
13
+ "train_steps_per_second": 0.025
14
+ }
checkpoint-10/config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
+ "activation_dropout": 0.1,
4
+ "adapter_kernel_size": 3,
5
+ "adapter_stride": 2,
6
+ "add_adapter": false,
7
+ "apply_spec_augment": true,
8
+ "architectures": [
9
+ "Wav2Vec2ForCTC"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 768,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": true,
17
+ "conv_dim": [
18
+ 512,
19
+ 512,
20
+ 512,
21
+ 512,
22
+ 512,
23
+ 512,
24
+ 512
25
+ ],
26
+ "conv_kernel": [
27
+ 10,
28
+ 3,
29
+ 3,
30
+ 3,
31
+ 3,
32
+ 2,
33
+ 2
34
+ ],
35
+ "conv_stride": [
36
+ 5,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 2,
42
+ 2
43
+ ],
44
+ "ctc_loss_reduction": "mean",
45
+ "ctc_zero_infinity": false,
46
+ "diversity_loss_weight": 0.1,
47
+ "do_stable_layer_norm": true,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_dropout": 0.0,
51
+ "feat_extract_norm": "layer",
52
+ "feat_proj_dropout": 0.0,
53
+ "feat_quantizer_dropout": 0.0,
54
+ "final_dropout": 0.0,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.0,
57
+ "hidden_size": 1024,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 4096,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.0,
62
+ "mask_feature_length": 64,
63
+ "mask_feature_min_masks": 0,
64
+ "mask_feature_prob": 0.25,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_masks": 2,
67
+ "mask_time_prob": 0.75,
68
+ "model_type": "wav2vec2",
69
+ "num_adapter_layers": 3,
70
+ "num_attention_heads": 16,
71
+ "num_codevector_groups": 2,
72
+ "num_codevectors_per_group": 320,
73
+ "num_conv_pos_embedding_groups": 16,
74
+ "num_conv_pos_embeddings": 128,
75
+ "num_feat_extract_layers": 7,
76
+ "num_hidden_layers": 24,
77
+ "num_negatives": 100,
78
+ "output_hidden_size": 1024,
79
+ "pad_token_id": 34,
80
+ "proj_codevector_dim": 768,
81
+ "tdnn_dilation": [
82
+ 1,
83
+ 2,
84
+ 3,
85
+ 1,
86
+ 1
87
+ ],
88
+ "tdnn_dim": [
89
+ 512,
90
+ 512,
91
+ 512,
92
+ 512,
93
+ 1500
94
+ ],
95
+ "tdnn_kernel": [
96
+ 5,
97
+ 3,
98
+ 3,
99
+ 1,
100
+ 1
101
+ ],
102
+ "torch_dtype": "float32",
103
+ "transformers_version": "4.16.0.dev0",
104
+ "use_weighted_layer_sum": false,
105
+ "vocab_size": 37,
106
+ "xvector_output_dim": 512
107
+ }
checkpoint-10/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edcb67a936a475709d3e3723b7e3224e64b185948f313f11f94438218cf2c5b2
3
+ size 2490361937
checkpoint-10/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-10/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd61f5511562b14319e58a1b70c496d7e20b55df954b4ca337e122de41cab04e
3
+ size 1262075377
checkpoint-10/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd055f4e5c4ffd4371a3565bfa995a6c8cb41314bc604e8debedf999343a113
3
+ size 14567
checkpoint-10/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20e4b012b4b9ab1daa876390beea4afff370d4f83e20e939f16cdf1855daf52f
3
+ size 559
checkpoint-10/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6e3ad42da29f9983fc79cb4c120fb5415e138f4bb390c579ef4600450de045a
3
+ size 623
checkpoint-10/trainer_state.json ADDED
@@ -0,0 +1,94 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.029006526468455404,
5
+ "global_step": 10,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 3.75e-06,
13
+ "loss": 13.605,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 7.5e-06,
19
+ "loss": 11.0063,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 1.1249999999999999e-05,
25
+ "loss": 11.6693,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 1.5e-05,
31
+ "loss": 13.432,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.01,
36
+ "learning_rate": 1.875e-05,
37
+ "loss": 10.3458,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "eval_loss": 15.09913444519043,
43
+ "eval_runtime": 139.8551,
44
+ "eval_samples_per_second": 33.034,
45
+ "eval_steps_per_second": 4.133,
46
+ "eval_wer": 1.0,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.02,
51
+ "learning_rate": 2.2499999999999998e-05,
52
+ "loss": 15.2451,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.02,
57
+ "learning_rate": 2.625e-05,
58
+ "loss": 10.0481,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.02,
63
+ "learning_rate": 3e-05,
64
+ "loss": 12.3838,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.03,
69
+ "learning_rate": 3.3749999999999994e-05,
70
+ "loss": 11.9858,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.03,
75
+ "learning_rate": 3.75e-05,
76
+ "loss": 11.9029,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.03,
81
+ "eval_loss": 14.213573455810547,
82
+ "eval_runtime": 160.2552,
83
+ "eval_samples_per_second": 28.829,
84
+ "eval_steps_per_second": 3.607,
85
+ "eval_wer": 1.0,
86
+ "step": 10
87
+ }
88
+ ],
89
+ "max_steps": 10,
90
+ "num_train_epochs": 1,
91
+ "total_flos": 4.405923604988928e+16,
92
+ "trial_name": null,
93
+ "trial_params": null
94
+ }
checkpoint-10/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0148471a0b194f620865125fd17f84a2e502a9e0a6acef5304251538d67e034
3
+ size 2991
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.03,
3
+ "eval_loss": 14.213573455810547,
4
+ "eval_runtime": 148.129,
5
+ "eval_samples": 4620,
6
+ "eval_samples_per_second": 31.189,
7
+ "eval_steps_per_second": 3.902,
8
+ "eval_wer": 1.0
9
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:222faf55d53b9dfcee2dab4d73d2de7b330d0c7b0c046d264a029fc26485cca4
3
  size 1262075377
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd61f5511562b14319e58a1b70c496d7e20b55df954b4ca337e122de41cab04e
3
  size 1262075377
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.03,
3
+ "train_loss": 12.162414741516113,
4
+ "train_runtime": 400.3916,
5
+ "train_samples": 11030,
6
+ "train_samples_per_second": 0.799,
7
+ "train_steps_per_second": 0.025
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.029006526468455404,
5
+ "global_step": 10,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 3.75e-06,
13
+ "loss": 13.605,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 7.5e-06,
19
+ "loss": 11.0063,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 1.1249999999999999e-05,
25
+ "loss": 11.6693,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 1.5e-05,
31
+ "loss": 13.432,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.01,
36
+ "learning_rate": 1.875e-05,
37
+ "loss": 10.3458,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "eval_loss": 15.09913444519043,
43
+ "eval_runtime": 139.8551,
44
+ "eval_samples_per_second": 33.034,
45
+ "eval_steps_per_second": 4.133,
46
+ "eval_wer": 1.0,
47
+ "step": 5
48
+ },
49
+ {
50
+ "epoch": 0.02,
51
+ "learning_rate": 2.2499999999999998e-05,
52
+ "loss": 15.2451,
53
+ "step": 6
54
+ },
55
+ {
56
+ "epoch": 0.02,
57
+ "learning_rate": 2.625e-05,
58
+ "loss": 10.0481,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.02,
63
+ "learning_rate": 3e-05,
64
+ "loss": 12.3838,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.03,
69
+ "learning_rate": 3.3749999999999994e-05,
70
+ "loss": 11.9858,
71
+ "step": 9
72
+ },
73
+ {
74
+ "epoch": 0.03,
75
+ "learning_rate": 3.75e-05,
76
+ "loss": 11.9029,
77
+ "step": 10
78
+ },
79
+ {
80
+ "epoch": 0.03,
81
+ "eval_loss": 14.213573455810547,
82
+ "eval_runtime": 160.2552,
83
+ "eval_samples_per_second": 28.829,
84
+ "eval_steps_per_second": 3.607,
85
+ "eval_wer": 1.0,
86
+ "step": 10
87
+ },
88
+ {
89
+ "epoch": 0.03,
90
+ "step": 10,
91
+ "total_flos": 4.405923604988928e+16,
92
+ "train_loss": 12.162414741516113,
93
+ "train_runtime": 400.3916,
94
+ "train_samples_per_second": 0.799,
95
+ "train_steps_per_second": 0.025
96
+ }
97
+ ],
98
+ "max_steps": 10,
99
+ "num_train_epochs": 1,
100
+ "total_flos": 4.405923604988928e+16,
101
+ "trial_name": null,
102
+ "trial_params": null
103
+ }