KoseiUemura commited on
Commit
029b7ca
·
verified ·
1 Parent(s): 6a2650f

Add checkpoint checkpoint-1500 - ME5 instruct model for African languages

Browse files
.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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "intfloat/multilingual-e5-large-instruct",
3
+ "architectures": [
4
+ "XLMRobertaModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "xlm-roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "output_past": true,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.46.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 250002
28
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49bafa61e49e700572302c7c6af520009d3b815316cc61dae03d8d481249c9c2
3
+ size 2239607176
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:798c21ead8473f29aeed9baa74dee3564c63ef286748e4f92aaa8587511bd1d8
3
+ size 4471061702
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6366867e4fa9cd1a62dabaf6b6c78c911be6a3d604189aabf384b01cc67c213a
3
+ size 14645
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0de44f0967594b3c208a10cfcf7140bb75543cb51a3f8a883528df55171034
3
+ size 1465
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
3
+ size 17082832
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [],
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 512,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "XLMRobertaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
trainer_state.json ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.029584048281166796,
5
+ "eval_steps": 500,
6
+ "global_step": 1500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0019722698854111194,
13
+ "grad_norm": 67.04732513427734,
14
+ "learning_rate": 1.8931177282587262e-07,
15
+ "loss": 3.4926,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.003944539770822239,
20
+ "grad_norm": 39.206844329833984,
21
+ "learning_rate": 3.845395385525538e-07,
22
+ "loss": 2.7703,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.005916809656233359,
27
+ "grad_norm": 27.58599281311035,
28
+ "learning_rate": 5.817393019128378e-07,
29
+ "loss": 2.4388,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.007889079541644478,
34
+ "grad_norm": 34.81669616699219,
35
+ "learning_rate": 7.789390652731218e-07,
36
+ "loss": 2.2036,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.009861349427055598,
41
+ "grad_norm": 32.964962005615234,
42
+ "learning_rate": 9.761388286334058e-07,
43
+ "loss": 2.0266,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.011833619312466718,
48
+ "grad_norm": 42.337581634521484,
49
+ "learning_rate": 1.1733385919936897e-06,
50
+ "loss": 2.1158,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.013805889197877837,
55
+ "grad_norm": 21.399593353271484,
56
+ "learning_rate": 1.3705383553539735e-06,
57
+ "loss": 2.2383,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.015778159083288956,
62
+ "grad_norm": 21.51966667175293,
63
+ "learning_rate": 1.5677381187142576e-06,
64
+ "loss": 2.0389,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.017750428968700077,
69
+ "grad_norm": 34.57212448120117,
70
+ "learning_rate": 1.7649378820745417e-06,
71
+ "loss": 2.0948,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.019722698854111195,
76
+ "grad_norm": 25.938730239868164,
77
+ "learning_rate": 1.9621376454348255e-06,
78
+ "loss": 2.0942,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.021694968739522317,
83
+ "grad_norm": 32.7101936340332,
84
+ "learning_rate": 2.15933740879511e-06,
85
+ "loss": 2.1916,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.023667238624933435,
90
+ "grad_norm": 25.46886444091797,
91
+ "learning_rate": 2.3565371721553937e-06,
92
+ "loss": 2.0302,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.025639508510344557,
97
+ "grad_norm": 32.50448226928711,
98
+ "learning_rate": 2.5537369355156775e-06,
99
+ "loss": 2.0705,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.027611778395755675,
104
+ "grad_norm": 22.87787628173828,
105
+ "learning_rate": 2.750936698875962e-06,
106
+ "loss": 2.2077,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.029584048281166796,
111
+ "grad_norm": 26.768518447875977,
112
+ "learning_rate": 2.9481364622362457e-06,
113
+ "loss": 2.0721,
114
+ "step": 1500
115
+ }
116
+ ],
117
+ "logging_steps": 100,
118
+ "max_steps": 50703,
119
+ "num_input_tokens_seen": 0,
120
+ "num_train_epochs": 1,
121
+ "save_steps": 100,
122
+ "stateful_callbacks": {
123
+ "TrainerControl": {
124
+ "args": {
125
+ "should_epoch_stop": false,
126
+ "should_evaluate": false,
127
+ "should_log": false,
128
+ "should_save": true,
129
+ "should_training_stop": false
130
+ },
131
+ "attributes": {}
132
+ }
133
+ },
134
+ "total_flos": 0.0,
135
+ "train_batch_size": 1,
136
+ "trial_name": null,
137
+ "trial_params": null
138
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089e9ad122468b88d15c7ea47eace242541e0922c0f2126e0a2520c382ad8b25
3
+ size 6033