Hugging Face's logo

JuanPajero
/
FT-S5-LM

PyTorch
TensorBoard
wav2vec2
Generated from Trainer
Model card Files
xet
 Metrics Community
1
JuanPajero commited on
Commit
3b3507d
·
1 Parent(s): de5a849

Training in progress, step 42600

Browse files
Files changed (13) hide show
  1. checkpoint-42600/config.json +117 -0
  2. checkpoint-42600/optimizer.pt +3 -0
  3. checkpoint-42600/preprocessor_config.json +9 -0
  4. checkpoint-42600/pytorch_model.bin +3 -0
  5. checkpoint-42600/rng_state.pth +3 -0
  6. checkpoint-42600/scaler.pt +3 -0
  7. checkpoint-42600/scheduler.pt +3 -0
  8. checkpoint-42600/trainer_state.json +106 -0
  9. checkpoint-42600/training_args.bin +3 -0
  10. pytorch_model.bin +2 -2
  11. runs/Apr02_11-39-56_364af271dda7/1775136463.0385299/events.out.tfevents.1775136463.364af271dda7.26706.1 +3 -0
  12. runs/Apr02_11-39-56_364af271dda7/events.out.tfevents.1775136463.364af271dda7.26706.0 +3 -0
  13. training_args.bin +2 -2
checkpoint-42600/config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/wav2vec2-base",
3
+ "activation_dropout": 0.0,
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": 0.1,
12
+ "bos_token_id": 1,
13
+ "classifier_proj_size": 256,
14
+ "codevector_dim": 256,
15
+ "contrastive_logits_temperature": 0.1,
16
+ "conv_bias": false,
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": false,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.1,
52
+ "feat_quantizer_dropout": 0.0,
53
+ "final_dropout": 0.0,
54
+ "freeze_feat_extract_train": true,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "initializer_range": 0.02,
59
+ "intermediate_size": 3072,
60
+ "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.0,
62
+ "mask_channel_length": 10,
63
+ "mask_channel_min_space": 1,
64
+ "mask_channel_other": 0.0,
65
+ "mask_channel_prob": 0.0,
66
+ "mask_channel_selection": "static",
67
+ "mask_feature_length": 10,
68
+ "mask_feature_min_masks": 0,
69
+ "mask_feature_prob": 0.0,
70
+ "mask_time_length": 10,
71
+ "mask_time_min_masks": 2,
72
+ "mask_time_min_space": 1,
73
+ "mask_time_other": 0.0,
74
+ "mask_time_prob": 0.05,
75
+ "mask_time_selection": "static",
76
+ "model_type": "wav2vec2",
77
+ "no_mask_channel_overlap": false,
78
+ "no_mask_time_overlap": false,
79
+ "num_adapter_layers": 3,
80
+ "num_attention_heads": 12,
81
+ "num_codevector_groups": 2,
82
+ "num_codevectors_per_group": 320,
83
+ "num_conv_pos_embedding_groups": 16,
84
+ "num_conv_pos_embeddings": 128,
85
+ "num_feat_extract_layers": 7,
86
+ "num_hidden_layers": 12,
87
+ "num_negatives": 100,
88
+ "output_hidden_size": 768,
89
+ "pad_token_id": 29,
90
+ "proj_codevector_dim": 256,
91
+ "tdnn_dilation": [
92
+ 1,
93
+ 2,
94
+ 3,
95
+ 1,
96
+ 1
97
+ ],
98
+ "tdnn_dim": [
99
+ 512,
100
+ 512,
101
+ 512,
102
+ 512,
103
+ 1500
104
+ ],
105
+ "tdnn_kernel": [
106
+ 5,
107
+ 3,
108
+ 3,
109
+ 1,
110
+ 1
111
+ ],
112
+ "torch_dtype": "float32",
113
+ "transformers_version": "4.17.0",
114
+ "use_weighted_layer_sum": false,
115
+ "vocab_size": 32,
116
+ "xvector_output_dim": 512
117
+ }
checkpoint-42600/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b4c4b333b97f0149964651f74eaa66101d66e936fbc61ebe79da9a0ee2c197c
3
+ size 721687098
checkpoint-42600/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": 0.0,
7
+ "return_attention_mask": false,
8
+ "sampling_rate": 16000
9
+ }
checkpoint-42600/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d71780a36fc085126b5a0a4ef930e98f7ece9349bee575d90e4a0f81c475c48
3
+ size 377673950
checkpoint-42600/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5ec54c45daae3ad43ee6e040a40ed36b5d581e594bbd01e674c86829218d1f
3
+ size 14308
checkpoint-42600/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d73036264655c5c1491cf5fff954a0cc29c3156f389e14cb5234dfaa4706556
3
+ size 988
checkpoint-42600/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a37fc39caa933e6c8f072c0eacc110c699acb993c4c2163f268da0d9550b53f2
3
+ size 1064
checkpoint-42600/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.711880624294281,
3
+ "best_model_checkpoint": "JuanPajero/FT-S5-LM/checkpoint-28400",
4
+ "epoch": 5.924895688456189,
5
+ "global_step": 42600,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.99,
12
+ "learning_rate": 2.9599443671766344e-05,
13
+ "loss": 1.9414,
14
+ "step": 7100
15
+ },
16
+ {
17
+ "epoch": 0.99,
18
+ "eval_loss": 0.8335326910018921,
19
+ "eval_runtime": 1360.1504,
20
+ "eval_samples_per_second": 14.653,
21
+ "eval_steps_per_second": 1.832,
22
+ "eval_wer": 0.36493978206843813,
23
+ "step": 7100
24
+ },
25
+ {
26
+ "epoch": 1.97,
27
+ "learning_rate": 2.67538247566064e-05,
28
+ "loss": 0.408,
29
+ "step": 14200
30
+ },
31
+ {
32
+ "epoch": 1.97,
33
+ "eval_loss": 0.7351572513580322,
34
+ "eval_runtime": 1358.9899,
35
+ "eval_samples_per_second": 14.665,
36
+ "eval_steps_per_second": 1.834,
37
+ "eval_wer": 0.30366915185114385,
38
+ "step": 14200
39
+ },
40
+ {
41
+ "epoch": 2.96,
42
+ "learning_rate": 2.3463606861381546e-05,
43
+ "loss": 0.3353,
44
+ "step": 21300
45
+ },
46
+ {
47
+ "epoch": 2.96,
48
+ "eval_loss": 0.7796653509140015,
49
+ "eval_runtime": 1356.2281,
50
+ "eval_samples_per_second": 14.695,
51
+ "eval_steps_per_second": 1.837,
52
+ "eval_wer": 0.29224494997769707,
53
+ "step": 21300
54
+ },
55
+ {
56
+ "epoch": 3.95,
57
+ "learning_rate": 2.01733889661567e-05,
58
+ "loss": 0.2987,
59
+ "step": 28400
60
+ },
61
+ {
62
+ "epoch": 3.95,
63
+ "eval_loss": 0.711880624294281,
64
+ "eval_runtime": 1361.6488,
65
+ "eval_samples_per_second": 14.637,
66
+ "eval_steps_per_second": 1.83,
67
+ "eval_wer": 0.28044605875230993,
68
+ "step": 28400
69
+ },
70
+ {
71
+ "epoch": 4.94,
72
+ "learning_rate": 1.6881780250347706e-05,
73
+ "loss": 0.2745,
74
+ "step": 35500
75
+ },
76
+ {
77
+ "epoch": 4.94,
78
+ "eval_loss": 0.7512252926826477,
79
+ "eval_runtime": 1356.3308,
80
+ "eval_samples_per_second": 14.694,
81
+ "eval_steps_per_second": 1.837,
82
+ "eval_wer": 0.27383164468234245,
83
+ "step": 35500
84
+ },
85
+ {
86
+ "epoch": 5.92,
87
+ "learning_rate": 1.3592025961984237e-05,
88
+ "loss": 0.2565,
89
+ "step": 42600
90
+ },
91
+ {
92
+ "epoch": 5.92,
93
+ "eval_loss": 0.7549805045127869,
94
+ "eval_runtime": 1225.2522,
95
+ "eval_samples_per_second": 16.264,
96
+ "eval_steps_per_second": 2.033,
97
+ "eval_wer": 0.2705310068428191,
98
+ "step": 42600
99
+ }
100
+ ],
101
+ "max_steps": 71900,
102
+ "num_train_epochs": 10,
103
+ "total_flos": 5.089903415040246e+19,
104
+ "trial_name": null,
105
+ "trial_params": null
106
+ }
checkpoint-42600/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb5c936e2bed1fcba8598d1651ae9feb05ba224acab141e9c89fb7fe00c9faa
3
+ size 3512
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25eb6802cf1c505fb18c7da90333257255ed42790e9d9309091793334e84d9ba
3
- size 377674359
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d71780a36fc085126b5a0a4ef930e98f7ece9349bee575d90e4a0f81c475c48
3
+ size 377673950
runs/Apr02_11-39-56_364af271dda7/1775136463.0385299/events.out.tfevents.1775136463.364af271dda7.26706.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7293118f5fe1b81fb5079d62149f69bdbf76b78789b29d1380851c1cbb7b4cb3
3
+ size 4856
runs/Apr02_11-39-56_364af271dda7/events.out.tfevents.1775136463.364af271dda7.26706.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cafb75901d86850ccd1d9dad6035c3bfa63329990af11fd40c05026ce873859a
3
+ size 5554
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92831e3dde557c0ac1ed5581de6b5f29e4012bc89328c613f8ee387cb824f24f
3
- size 3921
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb5c936e2bed1fcba8598d1651ae9feb05ba224acab141e9c89fb7fe00c9faa
3
+ size 3512