Hugging Face's logo

masakhane
/
mt5_en_tsn_news

Text2Text Generation
Transformers
PyTorch
English
Tswana
mt5
Inference Endpoints
Model card Files Community
2
Davlan commited on
Commit
4fa67ef
•
1 Parent(s): 7d1b777

add MT model

Browse files
Files changed (13) hide show
  1. all_results.json +15 -0
  2. config.json +29 -0
  3. eval_results.json +10 -0
  4. generated_predictions.txt +0 -0
  5. predict_results.json +9 -0
  6. pytorch_model.bin +3 -0
  7. special_tokens_map.json +1 -0
  8. spiece.model +3 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +1 -0
  11. train_results.json +8 -0
  12. trainer_state.json +49 -0
  13. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "predict_bleu": 3.2811,
4
+ "predict_gen_len": 116.302,
5
+ "predict_loss": 2.47963285446167,
6
+ "predict_runtime": 1955.107,
7
+ "predict_samples": 1500,
8
+ "predict_samples_per_second": 0.767,
9
+ "predict_steps_per_second": 0.077,
10
+ "train_loss": 4.22582760765439,
11
+ "train_runtime": 693.3373,
12
+ "train_samples": 2100,
13
+ "train_samples_per_second": 30.288,
14
+ "train_steps_per_second": 3.029
15
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-base",
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": "4.12.0",
27
+ "use_cache": true,
28
+ "vocab_size": 250100
29
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_bleu": 3.0847,
4
+ "eval_gen_len": 123.2426,
5
+ "eval_loss": 2.56530499458313,
6
+ "eval_runtime": 714.2754,
7
+ "eval_samples": 540,
8
+ "eval_samples_per_second": 0.756,
9
+ "eval_steps_per_second": 0.076
10
+ }
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": 3.2811,
3
+ "predict_gen_len": 116.302,
4
+ "predict_loss": 2.47963285446167,
5
+ "predict_runtime": 1955.107,
6
+ "predict_samples": 1500,
7
+ "predict_samples_per_second": 0.767,
8
+ "predict_steps_per_second": 0.077
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07d43d8afc7c7d9a7472f29c55f1bc1a8b867961cf27589ed7455d82d469c9a8
3
+ size 2329633625
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": "google/mt5-base", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 4.22582760765439,
4
+ "train_runtime": 693.3373,
5
+ "train_samples": 2100,
6
+ "train_samples_per_second": 30.288,
7
+ "train_steps_per_second": 3.029
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 2100,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.38,
12
+ "learning_rate": 3.809523809523809e-05,
13
+ "loss": 7.0294,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 4.76,
18
+ "learning_rate": 2.6190476190476192e-05,
19
+ "loss": 3.6582,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 7.14,
24
+ "learning_rate": 1.4285714285714285e-05,
25
+ "loss": 3.2986,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 9.52,
30
+ "learning_rate": 2.3809523809523808e-06,
31
+ "loss": 3.1398,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 10.0,
36
+ "step": 2100,
37
+ "total_flos": 7695352573747200.0,
38
+ "train_loss": 4.22582760765439,
39
+ "train_runtime": 693.3373,
40
+ "train_samples_per_second": 30.288,
41
+ "train_steps_per_second": 3.029
42
+ }
43
+ ],
44
+ "max_steps": 2100,
45
+ "num_train_epochs": 10,
46
+ "total_flos": 7695352573747200.0,
47
+ "trial_name": null,
48
+ "trial_params": null
49
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c164c97ae4b811a872f50e750a27c71b50c57bb49cca5f4fa2f172cf9d5cfa01
3
+ size 2927