Hugging Face's logo

masakhane
/
afrimt5_lug_en_news

Text2Text Generation
Transformers
PyTorch
Ganda
English
mt5
Inference Endpoints
Model card Files Community
2
Davlan commited on
Commit
80adfd9
•
1 Parent(s): 10be1cb

add MT model

Browse files
Files changed (12) hide show
  1. all_results.json +15 -0
  2. config.json +29 -0
  3. generated_predictions.txt +0 -0
  4. predict_results.json +9 -0
  5. pytorch_model.bin +3 -0
  6. special_tokens_map.json +1 -0
  7. spiece.model +3 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +1 -0
  10. train_results.json +8 -0
  11. trainer_state.json +73 -0
  12. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "predict_bleu": 14.835,
4
+ "predict_gen_len": 26.9187,
5
+ "predict_loss": 2.111769199371338,
6
+ "predict_runtime": 434.01,
7
+ "predict_samples": 1500,
8
+ "predict_samples_per_second": 3.456,
9
+ "predict_steps_per_second": 0.346,
10
+ "train_loss": 2.617105708402746,
11
+ "train_runtime": 1062.2047,
12
+ "train_samples": 4075,
13
+ "train_samples_per_second": 38.364,
14
+ "train_steps_per_second": 3.841
15
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "afriT5_1",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "mt5",
17
+ "num_decoder_layers": 12,
18
+ "num_heads": 12,
19
+ "num_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "relative_attention_num_buckets": 32,
23
+ "tie_word_embeddings": false,
24
+ "tokenizer_class": "T5Tokenizer",
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.10.3",
27
+ "use_cache": true,
28
+ "vocab_size": 250100
29
+ }
generated_predictions.txt ADDED
The diff for this file is too large to render. See raw diff
 
predict_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_bleu": 14.835,
3
+ "predict_gen_len": 26.9187,
4
+ "predict_loss": 2.111769199371338,
5
+ "predict_runtime": 434.01,
6
+ "predict_samples": 1500,
7
+ "predict_samples_per_second": 3.456,
8
+ "predict_steps_per_second": 0.346
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d5102dcd9c367f99e7274d3c0d400687518090242d0bcfd23edc2f74fed0d39
3
+ size 2329626573
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "afriT5_1", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 2.617105708402746,
4
+ "train_runtime": 1062.2047,
5
+ "train_samples": 4075,
6
+ "train_samples_per_second": 38.364,
7
+ "train_steps_per_second": 3.841
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 4080,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.23,
12
+ "learning_rate": 4.387254901960784e-05,
13
+ "loss": 3.811,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 2.45,
18
+ "learning_rate": 3.774509803921569e-05,
19
+ "loss": 2.8598,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 3.68,
24
+ "learning_rate": 3.161764705882353e-05,
25
+ "loss": 2.637,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 4.9,
30
+ "learning_rate": 2.5490196078431373e-05,
31
+ "loss": 2.5016,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 6.13,
36
+ "learning_rate": 1.936274509803922e-05,
37
+ "loss": 2.3794,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 7.35,
42
+ "learning_rate": 1.323529411764706e-05,
43
+ "loss": 2.324,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 8.58,
48
+ "learning_rate": 7.107843137254902e-06,
49
+ "loss": 2.2579,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 9.8,
54
+ "learning_rate": 9.80392156862745e-07,
55
+ "loss": 2.2347,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 10.0,
60
+ "step": 4080,
61
+ "total_flos": 1.29736772522496e+16,
62
+ "train_loss": 2.617105708402746,
63
+ "train_runtime": 1062.2047,
64
+ "train_samples_per_second": 38.364,
65
+ "train_steps_per_second": 3.841
66
+ }
67
+ ],
68
+ "max_steps": 4080,
69
+ "num_train_epochs": 10,
70
+ "total_flos": 1.29736772522496e+16,
71
+ "trial_name": null,
72
+ "trial_params": null
73
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3389b0199dddc8ff1d7ad67799b028d03f714c91176af198027fe1fe0d52c5d
3
+ size 2799