Hugging Face's logo

language-ml-lab
/
fasttext-azb

Feature Extraction
fastText
Azerbaijani
Model card Files Community
1
mahsaamani commited on
Commit
dc6096e
·
1 Parent(s): 9e7ce88

Upload 5 files

Browse files
Files changed (5) hide show
  1. AzerBert/checkpoint-11630/config.json +24 -0
  2. AzerBert/checkpoint-11630/rng_state.pth +3 -0
  3. AzerBert/checkpoint-11630/scheduler.pt +3 -0
  4. AzerBert/checkpoint-11630/trainer_state.json +156 -0
  5. AzerBert/checkpoint-11630/training_args.bin +3 -0
AzerBert/checkpoint-11630/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 64,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 12,
17
+ "pad_token_id": 0,
18
+ "position_embedding_type": "absolute",
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.25.1",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 10000
24
+ }
AzerBert/checkpoint-11630/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b588b438d2b69a66d5c6abfa9b328da5e340a65b3154a855fdd230efb149af5e
3
+ size 14575
AzerBert/checkpoint-11630/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dc266dec275e1301f79f52a19a51c4c45d7d7ada972fd5299b2bff17c8153e1
3
+ size 627
AzerBert/checkpoint-11630/trainer_state.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.8772294521331787,
3
+ "best_model_checkpoint": "/content/drive/MyDrive/Azari/Models/AzerBert_v2/checkpoint-11630",
4
+ "epoch": 10.0,
5
+ "global_step": 11630,
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": 4.5e-05,
13
+ "loss": 6.7343,
14
+ "step": 1163
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 6.081459045410156,
19
+ "eval_runtime": 503.0003,
20
+ "eval_samples_per_second": 263.048,
21
+ "eval_steps_per_second": 2.056,
22
+ "step": 1163
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 4e-05,
27
+ "loss": 5.7511,
28
+ "step": 2326
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 5.344614028930664,
33
+ "eval_runtime": 516.7667,
34
+ "eval_samples_per_second": 256.04,
35
+ "eval_steps_per_second": 2.001,
36
+ "step": 2326
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 3.5e-05,
41
+ "loss": 5.2027,
42
+ "step": 3489
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 4.8805670738220215,
47
+ "eval_runtime": 513.7912,
48
+ "eval_samples_per_second": 257.523,
49
+ "eval_steps_per_second": 2.012,
50
+ "step": 3489
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 3e-05,
55
+ "loss": 4.8194,
56
+ "step": 4652
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 4.549716472625732,
61
+ "eval_runtime": 489.7556,
62
+ "eval_samples_per_second": 270.161,
63
+ "eval_steps_per_second": 2.111,
64
+ "step": 4652
65
+ },
66
+ {
67
+ "epoch": 5.0,
68
+ "learning_rate": 2.5e-05,
69
+ "loss": 4.5507,
70
+ "step": 5815
71
+ },
72
+ {
73
+ "epoch": 5.0,
74
+ "eval_loss": 4.3259382247924805,
75
+ "eval_runtime": 475.757,
76
+ "eval_samples_per_second": 278.11,
77
+ "eval_steps_per_second": 2.173,
78
+ "step": 5815
79
+ },
80
+ {
81
+ "epoch": 6.0,
82
+ "learning_rate": 2e-05,
83
+ "loss": 4.3528,
84
+ "step": 6978
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "eval_loss": 4.155429363250732,
89
+ "eval_runtime": 485.1031,
90
+ "eval_samples_per_second": 272.752,
91
+ "eval_steps_per_second": 2.132,
92
+ "step": 6978
93
+ },
94
+ {
95
+ "epoch": 7.0,
96
+ "learning_rate": 1.5e-05,
97
+ "loss": 4.2138,
98
+ "step": 8141
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "eval_loss": 4.037585258483887,
103
+ "eval_runtime": 549.6833,
104
+ "eval_samples_per_second": 240.708,
105
+ "eval_steps_per_second": 1.881,
106
+ "step": 8141
107
+ },
108
+ {
109
+ "epoch": 8.0,
110
+ "learning_rate": 1e-05,
111
+ "loss": 4.1146,
112
+ "step": 9304
113
+ },
114
+ {
115
+ "epoch": 8.0,
116
+ "eval_loss": 3.954880714416504,
117
+ "eval_runtime": 527.3306,
118
+ "eval_samples_per_second": 250.911,
119
+ "eval_steps_per_second": 1.961,
120
+ "step": 9304
121
+ },
122
+ {
123
+ "epoch": 9.0,
124
+ "learning_rate": 5e-06,
125
+ "loss": 4.0459,
126
+ "step": 10467
127
+ },
128
+ {
129
+ "epoch": 9.0,
130
+ "eval_loss": 3.9045631885528564,
131
+ "eval_runtime": 520.0259,
132
+ "eval_samples_per_second": 254.435,
133
+ "eval_steps_per_second": 1.988,
134
+ "step": 10467
135
+ },
136
+ {
137
+ "epoch": 10.0,
138
+ "learning_rate": 0.0,
139
+ "loss": 4.0144,
140
+ "step": 11630
141
+ },
142
+ {
143
+ "epoch": 10.0,
144
+ "eval_loss": 3.8772294521331787,
145
+ "eval_runtime": 540.0798,
146
+ "eval_samples_per_second": 244.988,
147
+ "eval_steps_per_second": 1.915,
148
+ "step": 11630
149
+ }
150
+ ],
151
+ "max_steps": 11630,
152
+ "num_train_epochs": 10,
153
+ "total_flos": 3.9169211524061184e+17,
154
+ "trial_name": null,
155
+ "trial_params": null
156
+ }
AzerBert/checkpoint-11630/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e88a116e80cce8d4a21fd2f349cbda3d07262443d4c08bf3372e62a9e1708472
3
+ size 3451