add MT model
Browse files- all_results.json +15 -0
- config.json +29 -0
- generated_predictions.txt +0 -0
- predict_results.json +9 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +55 -0
- training_args.bin +3 -0
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"predict_bleu": 3.9735,
|
4 |
+
"predict_gen_len": 77.7606,
|
5 |
+
"predict_loss": 2.503878355026245,
|
6 |
+
"predict_runtime": 1998.7807,
|
7 |
+
"predict_samples": 1579,
|
8 |
+
"predict_samples_per_second": 0.79,
|
9 |
+
"predict_steps_per_second": 0.079,
|
10 |
+
"train_loss": 2.5975774013634885,
|
11 |
+
"train_runtime": 1089.5447,
|
12 |
+
"train_samples": 2637,
|
13 |
+
"train_samples_per_second": 24.203,
|
14 |
+
"train_steps_per_second": 2.423
|
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": 3.9735,
|
3 |
+
"predict_gen_len": 77.7606,
|
4 |
+
"predict_loss": 2.503878355026245,
|
5 |
+
"predict_runtime": 1998.7807,
|
6 |
+
"predict_samples": 1579,
|
7 |
+
"predict_samples_per_second": 0.79,
|
8 |
+
"predict_steps_per_second": 0.079
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5380663df153b9c7ecd097830e0fab6bf0db6ca7259e760262df389144e89e18
|
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": 2.5975774013634885,
|
4 |
+
"train_runtime": 1089.5447,
|
5 |
+
"train_samples": 2637,
|
6 |
+
"train_samples_per_second": 24.203,
|
7 |
+
"train_steps_per_second": 2.423
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 2640,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.89,
|
12 |
+
"learning_rate": 4.053030303030303e-05,
|
13 |
+
"loss": 3.2888,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 3.79,
|
18 |
+
"learning_rate": 3.106060606060606e-05,
|
19 |
+
"loss": 2.6645,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 5.68,
|
24 |
+
"learning_rate": 2.1590909090909093e-05,
|
25 |
+
"loss": 2.4659,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 7.58,
|
30 |
+
"learning_rate": 1.2121212121212122e-05,
|
31 |
+
"loss": 2.361,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 9.47,
|
36 |
+
"learning_rate": 2.651515151515152e-06,
|
37 |
+
"loss": 2.2917,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 10.0,
|
42 |
+
"step": 2640,
|
43 |
+
"total_flos": 1.613998356083712e+16,
|
44 |
+
"train_loss": 2.5975774013634885,
|
45 |
+
"train_runtime": 1089.5447,
|
46 |
+
"train_samples_per_second": 24.203,
|
47 |
+
"train_steps_per_second": 2.423
|
48 |
+
}
|
49 |
+
],
|
50 |
+
"max_steps": 2640,
|
51 |
+
"num_train_epochs": 10,
|
52 |
+
"total_flos": 1.613998356083712e+16,
|
53 |
+
"trial_name": null,
|
54 |
+
"trial_params": null
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fadaf44ff8a3f2fe9643d8221182e2c6c6bb087f192febeaf0c41224985faa73
|
3 |
+
size 2799
|