Hugging Face's logo

Hailay
/
xlmr-amharic-mlm

Fill-Mask
Transformers
Safetensors
Amharic
xlm-roberta
amharic
masked-language-modeling
xlmr
low-resource
multilingual
Model card Files
xet
Community
Hailay Kidu Teklehaymanot commited on
Commit
b5379b3
·
1 Parent(s): f9e2a7c

Upload fine-tuned XLM-R model for Amharic MLM

Browse files
Files changed (16) hide show
  1. checkpoint-381/config.json +27 -0
  2. checkpoint-381/model.safetensors +3 -0
  3. checkpoint-381/optimizer.pt +3 -0
  4. checkpoint-381/rng_state.pth +3 -0
  5. checkpoint-381/scheduler.pt +3 -0
  6. checkpoint-381/special_tokens_map.json +37 -0
  7. checkpoint-381/tokenizer.json +0 -0
  8. checkpoint-381/tokenizer_config.json +58 -0
  9. checkpoint-381/trainer_state.json +55 -0
  10. checkpoint-381/training_args.bin +3 -0
  11. config.json +27 -0
  12. model.safetensors +3 -0
  13. special_tokens_map.json +37 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +58 -0
  16. training_args.bin +3 -0
checkpoint-381/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForMaskedLM"
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-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "xlm-roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "output_past": true,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.52.3",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 22243
27
+ }
checkpoint-381/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98125b2990e9ab41ee341f847a54b58ffaacacae5c6d3c8109414abb498c4436
3
+ size 412618244
checkpoint-381/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:679194fe99a3b110b1bec276b7e2f32dfc18cfc08711cf61aac34a2a3aaab68d
3
+ size 825351418
checkpoint-381/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3b3470933056f1339c5f65d7e4594d04050609c9694c00e950de23c75fbb3d
3
+ size 13990
checkpoint-381/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c4d46aeb68612c330a05f0cde26ce1f011836a5e471f11f83f5b3097f7cd937
3
+ size 1064
checkpoint-381/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-381/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-381/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
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": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "auto_map": {
45
+ "AutoTokenizer": [
46
+ "tokenizer.json"
47
+ ]
48
+ },
49
+ "bos_token": "<s>",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "</s>",
52
+ "extra_special_tokens": {},
53
+ "mask_token": "<mask>",
54
+ "model_max_length": 512,
55
+ "pad_token": "<pad>",
56
+ "tokenizer_class": "PreTrainedTokenizer",
57
+ "unk_token": "<unk>"
58
+ }
checkpoint-381/trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 381,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.7874015748031497,
14
+ "grad_norm": 34.244510650634766,
15
+ "learning_rate": 9.900000000000002e-06,
16
+ "loss": 8.7755,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 1.574803149606299,
21
+ "grad_norm": 30.647747039794922,
22
+ "learning_rate": 1.9900000000000003e-05,
23
+ "loss": 8.0943,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 2.362204724409449,
28
+ "grad_norm": 20.079347610473633,
29
+ "learning_rate": 2.9900000000000002e-05,
30
+ "loss": 7.8645,
31
+ "step": 300
32
+ }
33
+ ],
34
+ "logging_steps": 100,
35
+ "max_steps": 381,
36
+ "num_input_tokens_seen": 0,
37
+ "num_train_epochs": 3,
38
+ "save_steps": 500,
39
+ "stateful_callbacks": {
40
+ "TrainerControl": {
41
+ "args": {
42
+ "should_epoch_stop": false,
43
+ "should_evaluate": false,
44
+ "should_log": false,
45
+ "should_save": true,
46
+ "should_training_stop": true
47
+ },
48
+ "attributes": {}
49
+ }
50
+ },
51
+ "total_flos": 400690605611520.0,
52
+ "train_batch_size": 16,
53
+ "trial_name": null,
54
+ "trial_params": null
55
+ }
checkpoint-381/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ad4d1274a5bebfc2c52e9a412077727af3ece6c2e10c18393e59ac114dff2b
3
+ size 5240
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaForMaskedLM"
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-05,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "xlm-roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "output_past": true,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.52.3",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 22243
27
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98125b2990e9ab41ee341f847a54b58ffaacacae5c6d3c8109414abb498c4436
3
+ size 412618244
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
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": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "auto_map": {
45
+ "AutoTokenizer": [
46
+ "tokenizer.json"
47
+ ]
48
+ },
49
+ "bos_token": "<s>",
50
+ "clean_up_tokenization_spaces": false,
51
+ "eos_token": "</s>",
52
+ "extra_special_tokens": {},
53
+ "mask_token": "<mask>",
54
+ "model_max_length": 512,
55
+ "pad_token": "<pad>",
56
+ "tokenizer_class": "PreTrainedTokenizer",
57
+ "unk_token": "<unk>"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ad4d1274a5bebfc2c52e9a412077727af3ece6c2e10c18393e59ac114dff2b
3
+ size 5240