Hugging Face's logo

svenkate
/
EsperBERTo

Fill-Mask
Transformers
PyTorch
TensorBoard
roberta
Inference Endpoints
Model card Files Metrics Community
svenkate commited on
Commit
b124759
•
1 Parent(s): fd5123d

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. .gitattributes +1 -0
  2. checkpoint-10000/config.json +26 -0
  3. checkpoint-10000/optimizer.pt +3 -0
  4. checkpoint-10000/pytorch_model.bin +3 -0
  5. checkpoint-10000/rng_state.pth +3 -0
  6. checkpoint-10000/scheduler.pt +3 -0
  7. checkpoint-10000/trainer_state.json +139 -0
  8. checkpoint-10000/training_args.bin +3 -0
  9. config.json +26 -0
  10. merges.txt +0 -0
  11. pytorch_model.bin +3 -0
  12. runs/Aug22_16-50-50_ip-172-31-3-177/events.out.tfevents.1692723053.ip-172-31-3-177.31559.0 +3 -0
  13. runs/Aug22_16-54-06_ip-172-31-3-177/events.out.tfevents.1692723248.ip-172-31-3-177.31606.0 +3 -0
  14. runs/Aug22_16-57-43_ip-172-31-3-177/events.out.tfevents.1692723465.ip-172-31-3-177.31644.0 +3 -0
  15. runs/Aug22_17-01-28_ip-172-31-3-177/events.out.tfevents.1692723691.ip-172-31-3-177.31684.0 +3 -0
  16. runs/Aug22_17-05-23_ip-172-31-3-177/events.out.tfevents.1692723926.ip-172-31-3-177.31739.0 +3 -0
  17. training_args.bin +3 -0
  18. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ eo_data/oscar_eo/oscar.eo.txt filter=lfs diff=lfs merge=lfs -text
checkpoint-10000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
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": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.32.0",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
checkpoint-10000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79ec46b0168ead76c757f7b3c598434f98b3dbfbfc6826c0694831da1d060a10
3
+ size 668123781
checkpoint-10000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f9bc3bee6092eeddff2c27c91df1571b93922a815548c68aebd471aa703f173
3
+ size 334053941
checkpoint-10000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ff15aec10958b1e14b7b8173cd561903ecf3b7ecba25667ab4fed6e38ceee3b
3
+ size 14575
checkpoint-10000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bafd5a298c70e98b28773d89c0a8b9d32fb851af2695d9ff15b50b05136c9bad
3
+ size 627
checkpoint-10000/trainer_state.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.6566850538481744,
5
+ "eval_steps": 500,
6
+ "global_step": 10000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.03,
13
+ "learning_rate": 4.8358287365379566e-05,
14
+ "loss": 7.8532,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.07,
19
+ "learning_rate": 4.671657473075913e-05,
20
+ "loss": 7.2621,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.1,
25
+ "learning_rate": 4.5074862096138694e-05,
26
+ "loss": 7.0977,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.13,
31
+ "learning_rate": 4.343314946151826e-05,
32
+ "loss": 6.97,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.16,
37
+ "learning_rate": 4.179143682689782e-05,
38
+ "loss": 6.8599,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 0.2,
43
+ "learning_rate": 4.0149724192277385e-05,
44
+ "loss": 6.8055,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 0.23,
49
+ "learning_rate": 3.850801155765695e-05,
50
+ "loss": 6.755,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 0.26,
55
+ "learning_rate": 3.686629892303651e-05,
56
+ "loss": 6.688,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 0.3,
61
+ "learning_rate": 3.522458628841608e-05,
62
+ "loss": 6.6518,
63
+ "step": 4500
64
+ },
65
+ {
66
+ "epoch": 0.33,
67
+ "learning_rate": 3.358287365379564e-05,
68
+ "loss": 6.5813,
69
+ "step": 5000
70
+ },
71
+ {
72
+ "epoch": 0.36,
73
+ "learning_rate": 3.1941161019175205e-05,
74
+ "loss": 6.4522,
75
+ "step": 5500
76
+ },
77
+ {
78
+ "epoch": 0.39,
79
+ "learning_rate": 3.029944838455477e-05,
80
+ "loss": 6.2959,
81
+ "step": 6000
82
+ },
83
+ {
84
+ "epoch": 0.43,
85
+ "learning_rate": 2.8657735749934332e-05,
86
+ "loss": 6.1878,
87
+ "step": 6500
88
+ },
89
+ {
90
+ "epoch": 0.46,
91
+ "learning_rate": 2.70160231153139e-05,
92
+ "loss": 6.0263,
93
+ "step": 7000
94
+ },
95
+ {
96
+ "epoch": 0.49,
97
+ "learning_rate": 2.5374310480693457e-05,
98
+ "loss": 5.8944,
99
+ "step": 7500
100
+ },
101
+ {
102
+ "epoch": 0.53,
103
+ "learning_rate": 2.3732597846073024e-05,
104
+ "loss": 5.7961,
105
+ "step": 8000
106
+ },
107
+ {
108
+ "epoch": 0.56,
109
+ "learning_rate": 2.2090885211452588e-05,
110
+ "loss": 5.6999,
111
+ "step": 8500
112
+ },
113
+ {
114
+ "epoch": 0.59,
115
+ "learning_rate": 2.0449172576832152e-05,
116
+ "loss": 5.6185,
117
+ "step": 9000
118
+ },
119
+ {
120
+ "epoch": 0.62,
121
+ "learning_rate": 1.8807459942211716e-05,
122
+ "loss": 5.5302,
123
+ "step": 9500
124
+ },
125
+ {
126
+ "epoch": 0.66,
127
+ "learning_rate": 1.716574730759128e-05,
128
+ "loss": 5.4339,
129
+ "step": 10000
130
+ }
131
+ ],
132
+ "logging_steps": 500,
133
+ "max_steps": 15228,
134
+ "num_train_epochs": 1,
135
+ "save_steps": 10000,
136
+ "total_flos": 2.122025894995968e+16,
137
+ "trial_name": null,
138
+ "trial_params": null
139
+ }
checkpoint-10000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70669cff5a11123f6c5a2730931a5652c3d270ee84fce7baf065428f13253ce
3
+ size 4027
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
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": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.32.0",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be1cf09f0aff8a24464f4440d2bcb37a7c6f99ba8b41d45fd3e1daa5537330d7
3
+ size 334053941
runs/Aug22_16-50-50_ip-172-31-3-177/events.out.tfevents.1692723053.ip-172-31-3-177.31559.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9592c8edd3b483976c9f6253c5abfbfefcc740707f129f2bf6f61f60625e487
3
+ size 88
runs/Aug22_16-54-06_ip-172-31-3-177/events.out.tfevents.1692723248.ip-172-31-3-177.31606.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16689677a9c62c396c475fb5d0b20ea8dedd4e96e26c4b35e7ee80cd59e4a987
3
+ size 88
runs/Aug22_16-57-43_ip-172-31-3-177/events.out.tfevents.1692723465.ip-172-31-3-177.31644.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce805d691b55491c72beaefabd7cfc6096213b9476a411199de3014d1faa2c93
3
+ size 3993
runs/Aug22_17-01-28_ip-172-31-3-177/events.out.tfevents.1692723691.ip-172-31-3-177.31684.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:100978e3aef0c385828d3624fa6697089e0c311617fde3f9f9c759d5cea6db0f
3
+ size 88
runs/Aug22_17-05-23_ip-172-31-3-177/events.out.tfevents.1692723926.ip-172-31-3-177.31739.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:079a9bd869c0fea02c16e58c5a5194969411cde361aecf720245a1789b3848ba
3
+ size 9060
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70669cff5a11123f6c5a2730931a5652c3d270ee84fce7baf065428f13253ce
3
+ size 4027
vocab.json ADDED
The diff for this file is too large to render. See raw diff