Hugging Face's logo

ulyanaisaeva
/
udmurt-bert-base-uncased

Fill-Mask
Transformers
PyTorch
TensorBoard
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ulyanaisaeva commited on
Commit
451893a
·
1 Parent(s): 1718eb7

End of training

Browse files
Files changed (34) hide show
  1. checkpoint-12838/config.json +31 -0
  2. checkpoint-12838/optimizer.pt +3 -0
  3. checkpoint-12838/pytorch_model.bin +3 -0
  4. checkpoint-12838/rng_state.pth +3 -0
  5. checkpoint-12838/scaler.pt +3 -0
  6. checkpoint-12838/scheduler.pt +3 -0
  7. checkpoint-12838/trainer_state.json +44 -0
  8. checkpoint-12838/training_args.bin +3 -0
  9. checkpoint-19257/config.json +31 -0
  10. checkpoint-19257/optimizer.pt +3 -0
  11. checkpoint-19257/pytorch_model.bin +3 -0
  12. checkpoint-19257/rng_state.pth +3 -0
  13. checkpoint-19257/scaler.pt +3 -0
  14. checkpoint-19257/scheduler.pt +3 -0
  15. checkpoint-19257/trainer_state.json +58 -0
  16. checkpoint-19257/training_args.bin +3 -0
  17. checkpoint-25676/config.json +31 -0
  18. checkpoint-25676/optimizer.pt +3 -0
  19. checkpoint-25676/pytorch_model.bin +3 -0
  20. checkpoint-25676/rng_state.pth +3 -0
  21. checkpoint-25676/scaler.pt +3 -0
  22. checkpoint-25676/scheduler.pt +3 -0
  23. checkpoint-25676/trainer_state.json +72 -0
  24. checkpoint-25676/training_args.bin +3 -0
  25. checkpoint-32095/config.json +31 -0
  26. checkpoint-32095/optimizer.pt +3 -0
  27. checkpoint-32095/pytorch_model.bin +3 -0
  28. checkpoint-32095/rng_state.pth +3 -0
  29. checkpoint-32095/scaler.pt +3 -0
  30. checkpoint-32095/scheduler.pt +3 -0
  31. checkpoint-32095/trainer_state.json +86 -0
  32. checkpoint-32095/training_args.bin +3 -0
  33. pytorch_model.bin +1 -1
  34. runs/May30_14-29-18_9a4805da8a6d/events.out.tfevents.1653920983.9a4805da8a6d.80.3 +2 -2
checkpoint-12838/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/models/bert_modif_emb",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.19.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
checkpoint-12838/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea61bf44d61641d59103e829adc93090b8d7eb92f1505e9b815b6731dec3cbd
3
+ size 885324121
checkpoint-12838/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f606c8d4900a8209c79fbcf5235e936287b216774982c26f3f734d30ea91e23
3
+ size 442675179
checkpoint-12838/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccd73439f3d9f0a1b3501ea081c02b7b7471ec025c2fbebecd68b79e7c35bf3a
3
+ size 14503
checkpoint-12838/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6017fdcf5f56dbcc9a92708c8c0ceded87054b03a1ffd0cd7fc66c53ff5ec716
3
+ size 559
checkpoint-12838/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d35205cd0217c54f2c2ba9dcdf2a3d3976b059cc6222cff585d4954618b8d0c4
3
+ size 623
checkpoint-12838/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 12838,
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
+ "learning_rate": 8.889735156655704e-06,
13
+ "loss": 7.3112,
14
+ "step": 6419
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 6.181427955627441,
19
+ "eval_runtime": 64.709,
20
+ "eval_samples_per_second": 198.396,
21
+ "eval_steps_per_second": 9.921,
22
+ "step": 6419
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 6.668513069066991e-06,
27
+ "loss": 5.8524,
28
+ "step": 12838
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 5.407498359680176,
33
+ "eval_runtime": 64.7053,
34
+ "eval_samples_per_second": 198.407,
35
+ "eval_steps_per_second": 9.922,
36
+ "step": 12838
37
+ }
38
+ ],
39
+ "max_steps": 32095,
40
+ "num_train_epochs": 5,
41
+ "total_flos": 1.689540838293504e+16,
42
+ "trial_name": null,
43
+ "trial_params": null
44
+ }
checkpoint-12838/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc6a6e3558851af45bb5a2bf276230e5bbacabfdee3309629484b8049458d984
3
+ size 3247
checkpoint-19257/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/models/bert_modif_emb",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.19.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
checkpoint-19257/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba999c3c1a2f308f80b5d8f367693c35e7c07ebb9d0fcd2e1cc1fa51d831c77
3
+ size 885324121
checkpoint-19257/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e516c7051df0161c608388e3b3c76ac27ad4aa82542e5e94ec299d8824b759e
3
+ size 442675179
checkpoint-19257/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bb60a63e8305a0c2468f008d689d5a382029bb9705d7b6233766a7d33af3c2f
3
+ size 14503
checkpoint-19257/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa387421e8fe914b42d6078556cf371000d33113d1ad9297d06114cb86b119fb
3
+ size 559
checkpoint-19257/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f5089926f44d1d87946b35c57b32d5688daa313074a5417b78cd3064326b65
3
+ size 623
checkpoint-19257/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 19257,
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
+ "learning_rate": 8.889735156655704e-06,
13
+ "loss": 7.3112,
14
+ "step": 6419
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 6.181427955627441,
19
+ "eval_runtime": 64.709,
20
+ "eval_samples_per_second": 198.396,
21
+ "eval_steps_per_second": 9.921,
22
+ "step": 6419
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 6.668513069066991e-06,
27
+ "loss": 5.8524,
28
+ "step": 12838
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 5.407498359680176,
33
+ "eval_runtime": 64.7053,
34
+ "eval_samples_per_second": 198.407,
35
+ "eval_steps_per_second": 9.922,
36
+ "step": 12838
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 4.446944781028216e-06,
41
+ "loss": 5.3392,
42
+ "step": 19257
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 5.080959320068359,
47
+ "eval_runtime": 64.6173,
48
+ "eval_samples_per_second": 198.677,
49
+ "eval_steps_per_second": 9.935,
50
+ "step": 19257
51
+ }
52
+ ],
53
+ "max_steps": 32095,
54
+ "num_train_epochs": 5,
55
+ "total_flos": 2.534311257440256e+16,
56
+ "trial_name": null,
57
+ "trial_params": null
58
+ }
checkpoint-19257/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc6a6e3558851af45bb5a2bf276230e5bbacabfdee3309629484b8049458d984
3
+ size 3247
checkpoint-25676/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/models/bert_modif_emb",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.19.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
checkpoint-25676/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1783ea3d8ddef597c36cf4796d000e8bc78b7ef67b81447dac38840f4f554da
3
+ size 885324121
checkpoint-25676/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34265a9a39e091e716cb212258982ed86c6fe6a820c6c01fc203b4cd63e01312
3
+ size 442675179
checkpoint-25676/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26102bb97204416066f0b77f4c616d6ed8a4bf9b0b9d81f125050fc47b6422af
3
+ size 14503
checkpoint-25676/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49785070d9351e7bf61535d02deb7a939472be3ed62e579420dd3ca01272af6b
3
+ size 559
checkpoint-25676/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96739ca6df7177c5a0f01b44a659f5de9f9f62a41bc1c71ede2605e338ea6225
3
+ size 623
checkpoint-25676/trainer_state.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "global_step": 25676,
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
+ "learning_rate": 8.889735156655704e-06,
13
+ "loss": 7.3112,
14
+ "step": 6419
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 6.181427955627441,
19
+ "eval_runtime": 64.709,
20
+ "eval_samples_per_second": 198.396,
21
+ "eval_steps_per_second": 9.921,
22
+ "step": 6419
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 6.668513069066991e-06,
27
+ "loss": 5.8524,
28
+ "step": 12838
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 5.407498359680176,
33
+ "eval_runtime": 64.7053,
34
+ "eval_samples_per_second": 198.407,
35
+ "eval_steps_per_second": 9.922,
36
+ "step": 12838
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 4.446944781028216e-06,
41
+ "loss": 5.3392,
42
+ "step": 19257
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 5.080959320068359,
47
+ "eval_runtime": 64.6173,
48
+ "eval_samples_per_second": 198.677,
49
+ "eval_steps_per_second": 9.935,
50
+ "step": 19257
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 2.2257226934395014e-06,
55
+ "loss": 5.0958,
56
+ "step": 25676
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 4.901454448699951,
61
+ "eval_runtime": 64.6233,
62
+ "eval_samples_per_second": 198.659,
63
+ "eval_steps_per_second": 9.934,
64
+ "step": 25676
65
+ }
66
+ ],
67
+ "max_steps": 32095,
68
+ "num_train_epochs": 5,
69
+ "total_flos": 3.379081676587008e+16,
70
+ "trial_name": null,
71
+ "trial_params": null
72
+ }
checkpoint-25676/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc6a6e3558851af45bb5a2bf276230e5bbacabfdee3309629484b8049458d984
3
+ size 3247
checkpoint-32095/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/models/bert_modif_emb",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "pooler_fc_size": 768,
21
+ "pooler_num_attention_heads": 12,
22
+ "pooler_num_fc_layers": 3,
23
+ "pooler_size_per_head": 128,
24
+ "pooler_type": "first_token_transform",
25
+ "position_embedding_type": "absolute",
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.19.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
checkpoint-32095/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaa394a7c8aec3a985b42599594f002ba9e313953930a7c953ae21adf27ef3c8
3
+ size 885324121
checkpoint-32095/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd771f458e46629f7fec5a86b90f3cfffb7e9b86f545ceeb7ce7499afb73ebe1
3
+ size 442675179
checkpoint-32095/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fdcc33a7aaa71308c29d1b50659ebc6a78284fa1a8c59733ef3edc8276bedb0
3
+ size 14503
checkpoint-32095/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d71b5382592d2ff7e32a0603d0e9db0a81425654dc7c7b16b5692a252cf24e3
3
+ size 559
checkpoint-32095/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd5ebce471016eec2f5eba2e97fee128ad5ffece685a5a95de6042eaea5877ae
3
+ size 623
checkpoint-32095/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "global_step": 32095,
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
+ "learning_rate": 8.889735156655704e-06,
13
+ "loss": 7.3112,
14
+ "step": 6419
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 6.181427955627441,
19
+ "eval_runtime": 64.709,
20
+ "eval_samples_per_second": 198.396,
21
+ "eval_steps_per_second": 9.921,
22
+ "step": 6419
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 6.668513069066991e-06,
27
+ "loss": 5.8524,
28
+ "step": 12838
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 5.407498359680176,
33
+ "eval_runtime": 64.7053,
34
+ "eval_samples_per_second": 198.407,
35
+ "eval_steps_per_second": 9.922,
36
+ "step": 12838
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 4.446944781028216e-06,
41
+ "loss": 5.3392,
42
+ "step": 19257
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 5.080959320068359,
47
+ "eval_runtime": 64.6173,
48
+ "eval_samples_per_second": 198.677,
49
+ "eval_steps_per_second": 9.935,
50
+ "step": 19257
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 2.2257226934395014e-06,
55
+ "loss": 5.0958,
56
+ "step": 25676
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 4.901454448699951,
61
+ "eval_runtime": 64.6233,
62
+ "eval_samples_per_second": 198.659,
63
+ "eval_steps_per_second": 9.934,
64
+ "step": 25676
65
+ },
66
+ {
67
+ "epoch": 5.0,
68
+ "learning_rate": 4.154405400727021e-09,
69
+ "loss": 4.9897,
70
+ "step": 32095
71
+ },
72
+ {
73
+ "epoch": 5.0,
74
+ "eval_loss": 4.8497138023376465,
75
+ "eval_runtime": 64.6531,
76
+ "eval_samples_per_second": 198.568,
77
+ "eval_steps_per_second": 9.93,
78
+ "step": 32095
79
+ }
80
+ ],
81
+ "max_steps": 32095,
82
+ "num_train_epochs": 5,
83
+ "total_flos": 4.22385209573376e+16,
84
+ "trial_name": null,
85
+ "trial_params": null
86
+ }
checkpoint-32095/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc6a6e3558851af45bb5a2bf276230e5bbacabfdee3309629484b8049458d984
3
+ size 3247
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:329903eb21f8e1e3ce9cc8e0ba643e55099c4ea5d438b8b865c431c1f0f79edd
3
  size 442675179
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd771f458e46629f7fec5a86b90f3cfffb7e9b86f545ceeb7ce7499afb73ebe1
3
  size 442675179
runs/May30_14-29-18_9a4805da8a6d/events.out.tfevents.1653920983.9a4805da8a6d.80.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60b240f84ee5518bb7967f12af5ab459198f650123c185689b4f331eff03dc64
3
- size 4232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96fe8d6bc35252e7b3d6b0d20ee5d996b6ea657f82decf53cd95ab548a54be3d
3
+ size 6328