Hugging Face's logo

Mega4alik
/
model_temp

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Inference Endpoints
Model card Files Metrics Community
Mega4alik commited on
Commit
49118e1
•
1 Parent(s): 04c4a24

Training in progress, step 600

Browse files
Files changed (32) hide show
  1. config.json +82 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +10 -0
  4. runs/Apr01_16-47-16_pc4/events.out.tfevents.1711972077.pc4 +3 -0
  5. runs/Apr01_16-57-40_pc4/events.out.tfevents.1711972699.pc4 +3 -0
  6. runs/Apr01_17-54-56_pc4/events.out.tfevents.1711976099.pc4 +3 -0
  7. runs/Apr01_17-55-36_pc4/events.out.tfevents.1711976139.pc4 +3 -0
  8. runs/Apr01_22-30-23_pc4/events.out.tfevents.1711997576.pc4 +3 -0
  9. runs/Mar14_16-23-22_pc4/events.out.tfevents.1710415408.pc4 +3 -0
  10. runs/Mar17_23-58-46_pc4/events.out.tfevents.1710701932.pc4 +3 -0
  11. runs/Mar19_23-02-24_pc4/events.out.tfevents.1710871349.pc4 +3 -0
  12. runs/Mar24_14-43-35_pc4/events.out.tfevents.1711273431.pc4 +3 -0
  13. runs/Mar27_09-42-03_pc4/events.out.tfevents.1711514543.pc4 +3 -0
  14. runs/Mar27_13-49-28_pc4/events.out.tfevents.1711529386.pc4 +3 -0
  15. runs/Mar27_18-48-23_pc4/events.out.tfevents.1711547321.pc4 +3 -0
  16. t1/checkpoint-100000/config.json +82 -0
  17. t1/checkpoint-100000/model.safetensors +3 -0
  18. t1/checkpoint-100000/optimizer.pt +3 -0
  19. t1/checkpoint-100000/preprocessor_config.json +11 -0
  20. t1/checkpoint-100000/rng_state.pth +3 -0
  21. t1/checkpoint-100000/scheduler.pt +3 -0
  22. t1/checkpoint-100000/trainer_state.json +51 -0
  23. t1/checkpoint-100000/training_args.bin +3 -0
  24. t1/checkpoint-50000/config.json +82 -0
  25. t1/checkpoint-50000/model.safetensors +3 -0
  26. t1/checkpoint-50000/optimizer.pt +3 -0
  27. t1/checkpoint-50000/preprocessor_config.json +11 -0
  28. t1/checkpoint-50000/rng_state.pth +3 -0
  29. t1/checkpoint-50000/scheduler.pt +3 -0
  30. t1/checkpoint-50000/trainer_state.json +51 -0
  31. t1/checkpoint-50000/training_args.bin +3 -0
  32. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/w2v-bert-2.0",
3
+ "activation_dropout": 0.0,
4
+ "adapter_act": "relu",
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": true,
8
+ "apply_spec_augment": false,
9
+ "architectures": [
10
+ "Wav2Vec2BertForCTC"
11
+ ],
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 768,
15
+ "codevector_dim": 768,
16
+ "conformer_conv_dropout": 0.1,
17
+ "contrastive_logits_temperature": 0.1,
18
+ "conv_depthwise_kernel_size": 31,
19
+ "ctc_loss_reduction": "mean",
20
+ "ctc_zero_infinity": false,
21
+ "diversity_loss_weight": 0.1,
22
+ "eos_token_id": 2,
23
+ "feat_proj_dropout": 0.0,
24
+ "feat_quantizer_dropout": 0.0,
25
+ "feature_projection_input_dim": 160,
26
+ "final_dropout": 0.1,
27
+ "hidden_act": "swish",
28
+ "hidden_dropout": 0.0,
29
+ "hidden_size": 1024,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 4096,
32
+ "layer_norm_eps": 1e-05,
33
+ "layerdrop": 0.0,
34
+ "left_max_position_embeddings": 64,
35
+ "mask_feature_length": 10,
36
+ "mask_feature_min_masks": 0,
37
+ "mask_feature_prob": 0.0,
38
+ "mask_time_length": 10,
39
+ "mask_time_min_masks": 2,
40
+ "mask_time_prob": 0.0,
41
+ "max_source_positions": 5000,
42
+ "model_type": "wav2vec2-bert",
43
+ "num_adapter_layers": 1,
44
+ "num_attention_heads": 16,
45
+ "num_codevector_groups": 2,
46
+ "num_codevectors_per_group": 320,
47
+ "num_hidden_layers": 24,
48
+ "num_negatives": 100,
49
+ "output_hidden_size": 1024,
50
+ "pad_token_id": 0,
51
+ "position_embeddings_type": "relative_key",
52
+ "proj_codevector_dim": 768,
53
+ "right_max_position_embeddings": 8,
54
+ "rotary_embedding_base": 10000,
55
+ "tdnn_dilation": [
56
+ 1,
57
+ 2,
58
+ 3,
59
+ 1,
60
+ 1
61
+ ],
62
+ "tdnn_dim": [
63
+ 512,
64
+ 512,
65
+ 512,
66
+ 512,
67
+ 1500
68
+ ],
69
+ "tdnn_kernel": [
70
+ 5,
71
+ 3,
72
+ 3,
73
+ 1,
74
+ 1
75
+ ],
76
+ "torch_dtype": "float32",
77
+ "transformers_version": "4.37.0",
78
+ "use_intermediate_ffn_before_adapter": false,
79
+ "use_weighted_layer_sum": false,
80
+ "vocab_size": 32,
81
+ "xvector_output_dim": 512
82
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c46f2a78f3b3e1e8faa16f52ce2f1197c6594da1365803f5b34af3b81bb45dbf
3
+ size 2422945760
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor_type": "SeamlessM4TFeatureExtractor",
3
+ "feature_size": 80,
4
+ "num_mel_bins": 80,
5
+ "padding_side": "right",
6
+ "padding_value": 0.0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000,
9
+ "stride": 2
10
+ }
runs/Apr01_16-47-16_pc4/events.out.tfevents.1711972077.pc4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af0755924cc00829178f650d0c38afe3ec096973f0fbc8bf442de9bdd8dfe2d5
3
+ size 5701
runs/Apr01_16-57-40_pc4/events.out.tfevents.1711972699.pc4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75e6e4ba50bd9f09cf245d4c5d9d56899a1bfa15b5949497b89d219e3ab88eac
3
+ size 6019
runs/Apr01_17-54-56_pc4/events.out.tfevents.1711976099.pc4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:769add6c5266bfa8b1575b615b31638a92fd8f63bb04ffd03cf821259055e45b
3
+ size 5540
runs/Apr01_17-55-36_pc4/events.out.tfevents.1711976139.pc4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1072be34d5edb0061f6b039efc418917e5c14c73d2ab1613f709f4b6d52f9a7b
3
+ size 5852
runs/Apr01_22-30-23_pc4/events.out.tfevents.1711997576.pc4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4beddab2ed1b8094f2bf9ef7d496e961a42f990779cc0e0e7fc9e9ad6cfa6731
3
+ size 5859
runs/Mar14_16-23-22_pc4/events.out.tfevents.1710415408.pc4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08fb32f864c83d2bac3423cde701c5dab6324bf3d604c58cafb192f0c5bdfb81
3
+ size 6517
runs/Mar17_23-58-46_pc4/events.out.tfevents.1710701932.pc4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c3470a81cc19a6f729c5ad94b1bf3eb95a2dbcb8eaf8dede217ceb28176cdfb
3
+ size 6518
runs/Mar19_23-02-24_pc4/events.out.tfevents.1710871349.pc4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78366ed267f0ca34a8754389571e1dea273449ae8d157b950d4aa92aa780dd34
3
+ size 8454
runs/Mar24_14-43-35_pc4/events.out.tfevents.1711273431.pc4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc4b74c9bbc6c3f25e3f4821d6f0284077c344a98870487d6bf5233ba83a4af5
3
+ size 10389
runs/Mar27_09-42-03_pc4/events.out.tfevents.1711514543.pc4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1570457a46c053274b980e5c9de339bf60e0e3b7b9ca7ee44fec61b2ad9fb115
3
+ size 6033
runs/Mar27_13-49-28_pc4/events.out.tfevents.1711529386.pc4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab0dc1bc32bab18491b292c2143d49afdd2162d3ad8a5e52da2e4992a313fbc
3
+ size 6033
runs/Mar27_18-48-23_pc4/events.out.tfevents.1711547321.pc4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc3a392779914ef861f8a4751ae9af376a52d9f73ab640d5cdb1a5045bca03cd
3
+ size 6020
t1/checkpoint-100000/config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/w2v-bert-2.0",
3
+ "activation_dropout": 0.0,
4
+ "adapter_act": "relu",
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": true,
8
+ "apply_spec_augment": false,
9
+ "architectures": [
10
+ "Wav2Vec2BertForCTC"
11
+ ],
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 768,
15
+ "codevector_dim": 768,
16
+ "conformer_conv_dropout": 0.1,
17
+ "contrastive_logits_temperature": 0.1,
18
+ "conv_depthwise_kernel_size": 31,
19
+ "ctc_loss_reduction": "mean",
20
+ "ctc_zero_infinity": false,
21
+ "diversity_loss_weight": 0.1,
22
+ "eos_token_id": 2,
23
+ "feat_proj_dropout": 0.0,
24
+ "feat_quantizer_dropout": 0.0,
25
+ "feature_projection_input_dim": 160,
26
+ "final_dropout": 0.1,
27
+ "hidden_act": "swish",
28
+ "hidden_dropout": 0.0,
29
+ "hidden_size": 1024,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 4096,
32
+ "layer_norm_eps": 1e-05,
33
+ "layerdrop": 0.0,
34
+ "left_max_position_embeddings": 64,
35
+ "mask_feature_length": 10,
36
+ "mask_feature_min_masks": 0,
37
+ "mask_feature_prob": 0.0,
38
+ "mask_time_length": 10,
39
+ "mask_time_min_masks": 2,
40
+ "mask_time_prob": 0.0,
41
+ "max_source_positions": 5000,
42
+ "model_type": "wav2vec2-bert",
43
+ "num_adapter_layers": 1,
44
+ "num_attention_heads": 16,
45
+ "num_codevector_groups": 2,
46
+ "num_codevectors_per_group": 320,
47
+ "num_hidden_layers": 24,
48
+ "num_negatives": 100,
49
+ "output_hidden_size": 1024,
50
+ "pad_token_id": 0,
51
+ "position_embeddings_type": "relative_key",
52
+ "proj_codevector_dim": 768,
53
+ "right_max_position_embeddings": 8,
54
+ "rotary_embedding_base": 10000,
55
+ "tdnn_dilation": [
56
+ 1,
57
+ 2,
58
+ 3,
59
+ 1,
60
+ 1
61
+ ],
62
+ "tdnn_dim": [
63
+ 512,
64
+ 512,
65
+ 512,
66
+ 512,
67
+ 1500
68
+ ],
69
+ "tdnn_kernel": [
70
+ 5,
71
+ 3,
72
+ 3,
73
+ 1,
74
+ 1
75
+ ],
76
+ "torch_dtype": "float32",
77
+ "transformers_version": "4.37.0",
78
+ "use_intermediate_ffn_before_adapter": false,
79
+ "use_weighted_layer_sum": false,
80
+ "vocab_size": 32,
81
+ "xvector_output_dim": 512
82
+ }
t1/checkpoint-100000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a882ab5b31773d4e63e6d17537c28d075ce9c25804914e0062f1c6011ad3a1
3
+ size 2422945760
t1/checkpoint-100000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c965f4c79ade91ef2e02de07670174c88269da3ff3419e85dc4da6c3bcf579f9
3
+ size 4846153113
t1/checkpoint-100000/preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor_type": "SeamlessM4TFeatureExtractor",
3
+ "feature_size": 80,
4
+ "num_mel_bins": 80,
5
+ "padding_side": "right",
6
+ "padding_value": 1,
7
+ "processor_class": "Wav2Vec2BertProcessor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000,
10
+ "stride": 2
11
+ }
t1/checkpoint-100000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee919c5045c953ba35254cdfcce2a63d580b90c964ebf2cd6f5af0972d072cad
3
+ size 14503
t1/checkpoint-100000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60386917ecd546576e1872c74581a94d98d24e42f33daad9ace06754c5d24a31
3
+ size 623
t1/checkpoint-100000/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.7773117271471035,
5
+ "eval_steps": 50000,
6
+ "global_step": 100000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.89,
13
+ "learning_rate": 3.45e-05,
14
+ "loss": 4996926.0134,
15
+ "step": 50000
16
+ },
17
+ {
18
+ "epoch": 0.89,
19
+ "eval_loss": NaN,
20
+ "eval_runtime": 13.236,
21
+ "eval_samples_per_second": 52.886,
22
+ "eval_steps_per_second": 6.649,
23
+ "eval_wer": 1.0,
24
+ "step": 50000
25
+ },
26
+ {
27
+ "epoch": 1.78,
28
+ "learning_rate": 3.45e-05,
29
+ "loss": 0.0,
30
+ "step": 100000
31
+ },
32
+ {
33
+ "epoch": 1.78,
34
+ "eval_loss": NaN,
35
+ "eval_runtime": 13.3509,
36
+ "eval_samples_per_second": 52.431,
37
+ "eval_steps_per_second": 6.591,
38
+ "eval_wer": 1.0,
39
+ "step": 100000
40
+ }
41
+ ],
42
+ "logging_steps": 50000,
43
+ "max_steps": 562640,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 10,
46
+ "save_steps": 50000,
47
+ "total_flos": 9.15368204731761e+20,
48
+ "train_batch_size": 8,
49
+ "trial_name": null,
50
+ "trial_params": null
51
+ }
t1/checkpoint-100000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c9bcab397042a9b7713fa95b76e628a3b9c008b6251fe118ad09751257fecea
3
+ size 4207
t1/checkpoint-50000/config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/w2v-bert-2.0",
3
+ "activation_dropout": 0.0,
4
+ "adapter_act": "relu",
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": false,
8
+ "apply_spec_augment": false,
9
+ "architectures": [
10
+ "Wav2Vec2BertForCTC"
11
+ ],
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 768,
15
+ "codevector_dim": 768,
16
+ "conformer_conv_dropout": 0.1,
17
+ "contrastive_logits_temperature": 0.1,
18
+ "conv_depthwise_kernel_size": 31,
19
+ "ctc_loss_reduction": "mean",
20
+ "ctc_zero_infinity": false,
21
+ "diversity_loss_weight": 0.1,
22
+ "eos_token_id": 2,
23
+ "feat_proj_dropout": 0.0,
24
+ "feat_quantizer_dropout": 0.0,
25
+ "feature_projection_input_dim": 160,
26
+ "final_dropout": 0.1,
27
+ "hidden_act": "swish",
28
+ "hidden_dropout": 0.0,
29
+ "hidden_size": 1024,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 4096,
32
+ "layer_norm_eps": 1e-05,
33
+ "layerdrop": 0.0,
34
+ "left_max_position_embeddings": 64,
35
+ "mask_feature_length": 10,
36
+ "mask_feature_min_masks": 0,
37
+ "mask_feature_prob": 0.0,
38
+ "mask_time_length": 10,
39
+ "mask_time_min_masks": 2,
40
+ "mask_time_prob": 0.0,
41
+ "max_source_positions": 5000,
42
+ "model_type": "wav2vec2-bert",
43
+ "num_adapter_layers": 1,
44
+ "num_attention_heads": 16,
45
+ "num_codevector_groups": 2,
46
+ "num_codevectors_per_group": 320,
47
+ "num_hidden_layers": 24,
48
+ "num_negatives": 100,
49
+ "output_hidden_size": 1024,
50
+ "pad_token_id": 0,
51
+ "position_embeddings_type": "relative_key",
52
+ "proj_codevector_dim": 768,
53
+ "right_max_position_embeddings": 8,
54
+ "rotary_embedding_base": 10000,
55
+ "tdnn_dilation": [
56
+ 1,
57
+ 2,
58
+ 3,
59
+ 1,
60
+ 1
61
+ ],
62
+ "tdnn_dim": [
63
+ 512,
64
+ 512,
65
+ 512,
66
+ 512,
67
+ 1500
68
+ ],
69
+ "tdnn_kernel": [
70
+ 5,
71
+ 3,
72
+ 3,
73
+ 1,
74
+ 1
75
+ ],
76
+ "torch_dtype": "float32",
77
+ "transformers_version": "4.37.0",
78
+ "use_intermediate_ffn_before_adapter": false,
79
+ "use_weighted_layer_sum": false,
80
+ "vocab_size": 32,
81
+ "xvector_output_dim": 512
82
+ }
t1/checkpoint-50000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee7a9f36abab0f3b1e6ae17ce0e6ec24613ba3d398ffd32e70ad21328a5c302
3
+ size 2322201712
t1/checkpoint-50000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7adc5e3e1b022aacd49f8bb9ac1b30fb6cea7bf1564564fa8ed1c346c306f3ce
3
+ size 4644657705
t1/checkpoint-50000/preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor_type": "SeamlessM4TFeatureExtractor",
3
+ "feature_size": 80,
4
+ "num_mel_bins": 80,
5
+ "padding_side": "right",
6
+ "padding_value": 1,
7
+ "processor_class": "Wav2Vec2BertProcessor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000,
10
+ "stride": 2
11
+ }
t1/checkpoint-50000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b005e2214c67a211e4ab6d885f030a731887b274a4aabb1a1f9a13ec87764ba
3
+ size 14503
t1/checkpoint-50000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cc6fff9f6803c2bc45342529c481616e72fdc56351df75f4fe2fca0e9effadc
3
+ size 623
t1/checkpoint-50000/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8886558635735519,
5
+ "eval_steps": 25000,
6
+ "global_step": 50000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.44,
13
+ "learning_rate": 4.782225068488277e-05,
14
+ "loss": 2.8517,
15
+ "step": 25000
16
+ },
17
+ {
18
+ "epoch": 0.44,
19
+ "eval_loss": 3.018819808959961,
20
+ "eval_runtime": 13.8146,
21
+ "eval_samples_per_second": 50.671,
22
+ "eval_steps_per_second": 6.37,
23
+ "eval_wer": 0.9749303621169917,
24
+ "step": 25000
25
+ },
26
+ {
27
+ "epoch": 0.89,
28
+ "learning_rate": 4.559993951684634e-05,
29
+ "loss": 2.8942,
30
+ "step": 50000
31
+ },
32
+ {
33
+ "epoch": 0.89,
34
+ "eval_loss": 3.0555782318115234,
35
+ "eval_runtime": 13.676,
36
+ "eval_samples_per_second": 51.185,
37
+ "eval_steps_per_second": 6.435,
38
+ "eval_wer": 0.9996285979572888,
39
+ "step": 50000
40
+ }
41
+ ],
42
+ "logging_steps": 25000,
43
+ "max_steps": 562640,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 10,
46
+ "save_steps": 50000,
47
+ "total_flos": 4.38681696546068e+20,
48
+ "train_batch_size": 8,
49
+ "trial_name": null,
50
+ "trial_params": null
51
+ }
t1/checkpoint-50000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93cfb00b0833d20ad8ab268248a616a63bb6f53dc442d4bb289bcedf8c006290
3
+ size 4207
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8ff5c892f6e0d0808ac70ee223cd0e1da5edcaffa8b217c1afef6b678663b6
3
+ size 4207