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
6b0ae6d
•
1 Parent(s): 53cd7e6

Training in progress, step 2000

Browse files
Files changed (20) hide show
  1. {checkpoint-576 → checkpoint-2000}/config.json +0 -0
  2. {checkpoint-576 → checkpoint-2000}/optimizer.pt +1 -1
  3. {checkpoint-576 → checkpoint-2000}/preprocessor_config.json +0 -0
  4. {checkpoint-672 → checkpoint-2000}/pytorch_model.bin +1 -1
  5. {checkpoint-672 → checkpoint-2000}/rng_state.pth +1 -1
  6. {checkpoint-672 → checkpoint-2000}/scaler.pt +1 -1
  7. {checkpoint-576 → checkpoint-2000}/scheduler.pt +1 -1
  8. checkpoint-2000/trainer_state.json +154 -0
  9. {checkpoint-672 → checkpoint-2000}/training_args.bin +1 -1
  10. checkpoint-576/pytorch_model.bin +0 -3
  11. checkpoint-576/rng_state.pth +0 -3
  12. checkpoint-576/scaler.pt +0 -3
  13. checkpoint-576/trainer_state.json +0 -100
  14. checkpoint-576/training_args.bin +0 -3
  15. checkpoint-672/config.json +0 -115
  16. checkpoint-672/optimizer.pt +0 -3
  17. checkpoint-672/preprocessor_config.json +0 -9
  18. checkpoint-672/scheduler.pt +0 -3
  19. checkpoint-672/trainer_state.json +0 -115
  20. pytorch_model.bin +1 -1
{checkpoint-576 → checkpoint-2000}/config.json RENAMED
File without changes
{checkpoint-576 → checkpoint-2000}/optimizer.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cb1350ff6e9893acaf16619961010f4c79ea8a244d121ac1c7e394f0ec20fe3
3
  size 2490337809
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cbed71746846766d0ee32fd1c3d30a051fe1cd5fa1a364116a8331a718ac106
3
  size 2490337809
{checkpoint-576 → checkpoint-2000}/preprocessor_config.json RENAMED
File without changes
{checkpoint-672 → checkpoint-2000}/pytorch_model.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cda6c609d26894118f60831d66a918be45540d348cdd4e71e2cfd6c4296b3de
3
  size 1262063089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1b4db9fe6fc412c5bb7bf8cacc52fb1a6a7a9a2c5203f2e3246fbbc44c01f8d
3
  size 1262063089
{checkpoint-672 → checkpoint-2000}/rng_state.pth RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebfa122200e74335f79d2f8a43ce26c726efd4c21ffe6331de97989b229b381e
3
  size 14567
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df565685c0e4849507cfdc6dc93987c2f9ca38e629be718a83015272881f9e14
3
  size 14567
{checkpoint-672 → checkpoint-2000}/scaler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03f55b5a17595526cb1157c4710c777fc0eafef249129dba3a1e2632c2bb5762
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22e86abaf1861fe41e7a0f8a14cd1180d020d6a1ae32de680f6edcf6afc3ebd8
3
  size 559
{checkpoint-576 → checkpoint-2000}/scheduler.pt RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02bf983fc7d4d4e99567cd4deb53f5271898d5335892a0fd4365a6bb08882199
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8974dc324f1da04e1c2f621f09ee80bb5dcc0fac900f8f887ccf3266bcd8368d
3
  size 623
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 20.83116883116883,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.04,
12
+ "learning_rate": 3.828125e-06,
13
+ "loss": 15.104,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 2.08,
18
+ "learning_rate": 7.6953125e-06,
19
+ "loss": 12.2149,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 3.12,
24
+ "learning_rate": 1.16015625e-05,
25
+ "loss": 4.9885,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 4.17,
30
+ "learning_rate": 1.55078125e-05,
31
+ "loss": 3.3788,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 5.21,
36
+ "learning_rate": 1.94140625e-05,
37
+ "loss": 3.1705,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 6.25,
42
+ "learning_rate": 2.3320312499999995e-05,
43
+ "loss": 3.11,
44
+ "step": 600
45
+ },
46
+ {
47
+ "epoch": 7.29,
48
+ "learning_rate": 2.72265625e-05,
49
+ "loss": 3.0526,
50
+ "step": 700
51
+ },
52
+ {
53
+ "epoch": 8.33,
54
+ "learning_rate": 3.11328125e-05,
55
+ "loss": 3.0113,
56
+ "step": 800
57
+ },
58
+ {
59
+ "epoch": 9.37,
60
+ "learning_rate": 3.5039062499999995e-05,
61
+ "loss": 2.9601,
62
+ "step": 900
63
+ },
64
+ {
65
+ "epoch": 10.42,
66
+ "learning_rate": 3.89453125e-05,
67
+ "loss": 2.9099,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 10.42,
72
+ "eval_loss": 2.8369038105010986,
73
+ "eval_runtime": 198.5866,
74
+ "eval_samples_per_second": 25.405,
75
+ "eval_steps_per_second": 0.796,
76
+ "eval_wer": 1.0,
77
+ "step": 1000
78
+ },
79
+ {
80
+ "epoch": 11.46,
81
+ "learning_rate": 4.28515625e-05,
82
+ "loss": 2.6653,
83
+ "step": 1100
84
+ },
85
+ {
86
+ "epoch": 12.5,
87
+ "learning_rate": 4.675781249999999e-05,
88
+ "loss": 1.8958,
89
+ "step": 1200
90
+ },
91
+ {
92
+ "epoch": 13.54,
93
+ "learning_rate": 5.0664062499999996e-05,
94
+ "loss": 1.4812,
95
+ "step": 1300
96
+ },
97
+ {
98
+ "epoch": 14.58,
99
+ "learning_rate": 5.45703125e-05,
100
+ "loss": 1.3358,
101
+ "step": 1400
102
+ },
103
+ {
104
+ "epoch": 15.62,
105
+ "learning_rate": 5.8476562499999996e-05,
106
+ "loss": 1.2522,
107
+ "step": 1500
108
+ },
109
+ {
110
+ "epoch": 16.66,
111
+ "learning_rate": 6.238281249999999e-05,
112
+ "loss": 1.1919,
113
+ "step": 1600
114
+ },
115
+ {
116
+ "epoch": 17.71,
117
+ "learning_rate": 6.62890625e-05,
118
+ "loss": 1.1663,
119
+ "step": 1700
120
+ },
121
+ {
122
+ "epoch": 18.75,
123
+ "learning_rate": 7.019531249999999e-05,
124
+ "loss": 1.1289,
125
+ "step": 1800
126
+ },
127
+ {
128
+ "epoch": 19.79,
129
+ "learning_rate": 7.410156249999999e-05,
130
+ "loss": 1.0902,
131
+ "step": 1900
132
+ },
133
+ {
134
+ "epoch": 20.83,
135
+ "learning_rate": 7.4248046875e-05,
136
+ "loss": 1.0745,
137
+ "step": 2000
138
+ },
139
+ {
140
+ "epoch": 20.83,
141
+ "eval_loss": 0.19572903215885162,
142
+ "eval_runtime": 202.06,
143
+ "eval_samples_per_second": 24.968,
144
+ "eval_steps_per_second": 0.782,
145
+ "eval_wer": 0.16725371193237237,
146
+ "step": 2000
147
+ }
148
+ ],
149
+ "max_steps": 9600,
150
+ "num_train_epochs": 100,
151
+ "total_flos": 3.1116125970966065e+19,
152
+ "trial_name": null,
153
+ "trial_params": null
154
+ }
{checkpoint-672 → checkpoint-2000}/training_args.bin RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e36b0de66081b1e60759283ec925cb14218ac8e4b7758178a38fee27a8df110c
3
  size 3055
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28f8dab6838e0cc8a253bbc1fb16c34a7a36619cf3b9e2bd9c1e4027635a3b2b
3
  size 3055
checkpoint-576/pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a4eb5262362bc942997943e8cac7304bde0ff46a7d74568873dcc9435010d2b
3
- size 1262063089
 
 
 
 
checkpoint-576/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7623b4c7baef3e7f83b53332857785fb33c5c12d7f39597ff07744e1bac86639
3
- size 14567
 
 
 
 
checkpoint-576/scaler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a4bfd784255410181d8b7f330e21b3d72f67d7de17ce03ce3ddbfe13e1014a2
3
- size 559
 
 
 
 
checkpoint-576/trainer_state.json DELETED
@@ -1,100 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 5.997402597402598,
5
- "global_step": 576,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 1.0,
12
- "eval_loss": 18.22025489807129,
13
- "eval_runtime": 188.3513,
14
- "eval_samples_per_second": 26.785,
15
- "eval_steps_per_second": 0.839,
16
- "eval_wer": 1.0021133629565406,
17
- "step": 96
18
- },
19
- {
20
- "epoch": 1.04,
21
- "learning_rate": 1.5156249999999998e-06,
22
- "loss": 15.219,
23
- "step": 100
24
- },
25
- {
26
- "epoch": 2.0,
27
- "eval_loss": 17.49703025817871,
28
- "eval_runtime": 186.0672,
29
- "eval_samples_per_second": 27.114,
30
- "eval_steps_per_second": 0.849,
31
- "eval_wer": 1.0,
32
- "step": 192
33
- },
34
- {
35
- "epoch": 2.08,
36
- "learning_rate": 3.0781249999999994e-06,
37
- "loss": 14.7046,
38
- "step": 200
39
- },
40
- {
41
- "epoch": 3.0,
42
- "eval_loss": 11.056963920593262,
43
- "eval_runtime": 184.9586,
44
- "eval_samples_per_second": 27.276,
45
- "eval_steps_per_second": 0.854,
46
- "eval_wer": 1.0,
47
- "step": 288
48
- },
49
- {
50
- "epoch": 3.12,
51
- "learning_rate": 4.640624999999999e-06,
52
- "loss": 11.6089,
53
- "step": 300
54
- },
55
- {
56
- "epoch": 4.0,
57
- "eval_loss": 5.172672271728516,
58
- "eval_runtime": 185.1159,
59
- "eval_samples_per_second": 27.253,
60
- "eval_steps_per_second": 0.854,
61
- "eval_wer": 1.0,
62
- "step": 384
63
- },
64
- {
65
- "epoch": 4.17,
66
- "learning_rate": 6.203124999999999e-06,
67
- "loss": 5.9408,
68
- "step": 400
69
- },
70
- {
71
- "epoch": 5.0,
72
- "eval_loss": 3.6944665908813477,
73
- "eval_runtime": 186.0698,
74
- "eval_samples_per_second": 27.113,
75
- "eval_steps_per_second": 0.849,
76
- "eval_wer": 1.0,
77
- "step": 480
78
- },
79
- {
80
- "epoch": 5.21,
81
- "learning_rate": 7.765624999999999e-06,
82
- "loss": 3.8196,
83
- "step": 500
84
- },
85
- {
86
- "epoch": 6.0,
87
- "eval_loss": 3.3380837440490723,
88
- "eval_runtime": 183.9322,
89
- "eval_samples_per_second": 27.429,
90
- "eval_steps_per_second": 0.859,
91
- "eval_wer": 1.0,
92
- "step": 576
93
- }
94
- ],
95
- "max_steps": 19200,
96
- "num_train_epochs": 200,
97
- "total_flos": 8.945907324105985e+18,
98
- "trial_name": null,
99
- "trial_params": null
100
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-576/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e36b0de66081b1e60759283ec925cb14218ac8e4b7758178a38fee27a8df110c
3
- size 3055
 
 
 
 
checkpoint-672/config.json DELETED
@@ -1,115 +0,0 @@
1
- {
2
- "_name_or_path": "KBLab/wav2vec2-large-voxrex",
3
- "activation_dropout": 0.15,
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_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": 64,
68
- "mask_feature_min_masks": 0,
69
- "mask_feature_prob": 0.25,
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": 0.75,
75
- "mask_time_selection": "static",
76
- "model_type": "wav2vec2",
77
- "num_adapter_layers": 3,
78
- "num_attention_heads": 16,
79
- "num_codevector_groups": 2,
80
- "num_codevectors_per_group": 320,
81
- "num_conv_pos_embedding_groups": 16,
82
- "num_conv_pos_embeddings": 128,
83
- "num_feat_extract_layers": 7,
84
- "num_hidden_layers": 24,
85
- "num_negatives": 100,
86
- "output_hidden_size": 1024,
87
- "pad_token_id": 31,
88
- "proj_codevector_dim": 768,
89
- "tdnn_dilation": [
90
- 1,
91
- 2,
92
- 3,
93
- 1,
94
- 1
95
- ],
96
- "tdnn_dim": [
97
- 512,
98
- 512,
99
- 512,
100
- 512,
101
- 1500
102
- ],
103
- "tdnn_kernel": [
104
- 5,
105
- 3,
106
- 3,
107
- 1,
108
- 1
109
- ],
110
- "torch_dtype": "float32",
111
- "transformers_version": "4.17.0.dev0",
112
- "use_weighted_layer_sum": false,
113
- "vocab_size": 34,
114
- "xvector_output_dim": 512
115
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-672/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bfba90dfb145308edc9cc54791241d132cd937db592ef07d6e7026b82f83748
3
- size 2490337809
 
 
 
 
checkpoint-672/preprocessor_config.json DELETED
@@ -1,9 +0,0 @@
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-672/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bb60131ff9244ecc96d9d9ae122e339002db12489062cce1759d60df5d23b66
3
- size 623
 
 
 
 
checkpoint-672/trainer_state.json DELETED
@@ -1,115 +0,0 @@
1
- {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 6.997402597402598,
5
- "global_step": 672,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 1.0,
12
- "eval_loss": 18.22025489807129,
13
- "eval_runtime": 188.3513,
14
- "eval_samples_per_second": 26.785,
15
- "eval_steps_per_second": 0.839,
16
- "eval_wer": 1.0021133629565406,
17
- "step": 96
18
- },
19
- {
20
- "epoch": 1.04,
21
- "learning_rate": 1.5156249999999998e-06,
22
- "loss": 15.219,
23
- "step": 100
24
- },
25
- {
26
- "epoch": 2.0,
27
- "eval_loss": 17.49703025817871,
28
- "eval_runtime": 186.0672,
29
- "eval_samples_per_second": 27.114,
30
- "eval_steps_per_second": 0.849,
31
- "eval_wer": 1.0,
32
- "step": 192
33
- },
34
- {
35
- "epoch": 2.08,
36
- "learning_rate": 3.0781249999999994e-06,
37
- "loss": 14.7046,
38
- "step": 200
39
- },
40
- {
41
- "epoch": 3.0,
42
- "eval_loss": 11.056963920593262,
43
- "eval_runtime": 184.9586,
44
- "eval_samples_per_second": 27.276,
45
- "eval_steps_per_second": 0.854,
46
- "eval_wer": 1.0,
47
- "step": 288
48
- },
49
- {
50
- "epoch": 3.12,
51
- "learning_rate": 4.640624999999999e-06,
52
- "loss": 11.6089,
53
- "step": 300
54
- },
55
- {
56
- "epoch": 4.0,
57
- "eval_loss": 5.172672271728516,
58
- "eval_runtime": 185.1159,
59
- "eval_samples_per_second": 27.253,
60
- "eval_steps_per_second": 0.854,
61
- "eval_wer": 1.0,
62
- "step": 384
63
- },
64
- {
65
- "epoch": 4.17,
66
- "learning_rate": 6.203124999999999e-06,
67
- "loss": 5.9408,
68
- "step": 400
69
- },
70
- {
71
- "epoch": 5.0,
72
- "eval_loss": 3.6944665908813477,
73
- "eval_runtime": 186.0698,
74
- "eval_samples_per_second": 27.113,
75
- "eval_steps_per_second": 0.849,
76
- "eval_wer": 1.0,
77
- "step": 480
78
- },
79
- {
80
- "epoch": 5.21,
81
- "learning_rate": 7.765624999999999e-06,
82
- "loss": 3.8196,
83
- "step": 500
84
- },
85
- {
86
- "epoch": 6.0,
87
- "eval_loss": 3.3380837440490723,
88
- "eval_runtime": 183.9322,
89
- "eval_samples_per_second": 27.429,
90
- "eval_steps_per_second": 0.859,
91
- "eval_wer": 1.0,
92
- "step": 576
93
- },
94
- {
95
- "epoch": 6.25,
96
- "learning_rate": 9.328125e-06,
97
- "loss": 3.3535,
98
- "step": 600
99
- },
100
- {
101
- "epoch": 7.0,
102
- "eval_loss": 3.2117931842803955,
103
- "eval_runtime": 186.1,
104
- "eval_samples_per_second": 27.109,
105
- "eval_steps_per_second": 0.849,
106
- "eval_wer": 1.0,
107
- "step": 672
108
- }
109
- ],
110
- "max_steps": 19200,
111
- "num_train_epochs": 200,
112
- "total_flos": 1.0436571367071685e+19,
113
- "trial_name": null,
114
- "trial_params": null
115
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c9ea0cc96b8e5bbae5dd33b444779900e8411a85ceceeeb644e8b71cf1d6010
3
  size 1262063089
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1b4db9fe6fc412c5bb7bf8cacc52fb1a6a7a9a2c5203f2e3246fbbc44c01f8d
3
  size 1262063089