add MT model
Browse files- all_results.json +15 -0
- config.json +63 -0
- generated_predictions.txt +0 -0
- predict_results.json +9 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +67 -0
- training_args.bin +3 -0
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"predict_bleu": 16.5499,
|
4 |
+
"predict_gen_len": 52.8126,
|
5 |
+
"predict_loss": 3.067568302154541,
|
6 |
+
"predict_runtime": 656.2829,
|
7 |
+
"predict_samples": 998,
|
8 |
+
"predict_samples_per_second": 1.521,
|
9 |
+
"predict_steps_per_second": 0.152,
|
10 |
+
"train_loss": 1.2667300415039062,
|
11 |
+
"train_runtime": 1675.224,
|
12 |
+
"train_samples": 3500,
|
13 |
+
"train_samples_per_second": 20.893,
|
14 |
+
"train_steps_per_second": 2.089
|
15 |
+
}
|
config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/data/users/didelani/afribart/afrimbart",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"adapters": {
|
7 |
+
"adapters": {},
|
8 |
+
"config_map": {},
|
9 |
+
"fusion_config_map": {},
|
10 |
+
"fusions": {}
|
11 |
+
},
|
12 |
+
"add_bias_logits": false,
|
13 |
+
"add_final_layer_norm": true,
|
14 |
+
"architectures": [
|
15 |
+
"MBartForConditionalGeneration"
|
16 |
+
],
|
17 |
+
"attention_dropout": 0.0,
|
18 |
+
"bos_token_id": 0,
|
19 |
+
"classif_dropout": 0.0,
|
20 |
+
"classifier_dropout": 0.0,
|
21 |
+
"d_model": 1024,
|
22 |
+
"decoder_attention_heads": 16,
|
23 |
+
"decoder_ffn_dim": 4096,
|
24 |
+
"decoder_layerdrop": 0.0,
|
25 |
+
"decoder_layers": 12,
|
26 |
+
"decoder_start_token_id": 250020,
|
27 |
+
"dropout": 0.1,
|
28 |
+
"encoder_attention_heads": 16,
|
29 |
+
"encoder_ffn_dim": 4096,
|
30 |
+
"encoder_layerdrop": 0.0,
|
31 |
+
"encoder_layers": 12,
|
32 |
+
"eos_token_id": 2,
|
33 |
+
"forced_bos_token_id": 250050,
|
34 |
+
"forced_eos_token_id": 2,
|
35 |
+
"gradient_checkpointing": false,
|
36 |
+
"id2label": {
|
37 |
+
"0": "LABEL_0",
|
38 |
+
"1": "LABEL_1",
|
39 |
+
"2": "LABEL_2"
|
40 |
+
},
|
41 |
+
"init_std": 0.02,
|
42 |
+
"is_encoder_decoder": true,
|
43 |
+
"label2id": {
|
44 |
+
"LABEL_0": 0,
|
45 |
+
"LABEL_1": 1,
|
46 |
+
"LABEL_2": 2
|
47 |
+
},
|
48 |
+
"max_length": 1024,
|
49 |
+
"max_position_embeddings": 1024,
|
50 |
+
"model_type": "mbart",
|
51 |
+
"normalize_before": true,
|
52 |
+
"normalize_embedding": true,
|
53 |
+
"num_beams": 5,
|
54 |
+
"num_hidden_layers": 12,
|
55 |
+
"output_past": true,
|
56 |
+
"pad_token_id": 1,
|
57 |
+
"scale_embedding": true,
|
58 |
+
"static_position_embeddings": false,
|
59 |
+
"torch_dtype": "float32",
|
60 |
+
"transformers_version": "4.10.3",
|
61 |
+
"use_cache": true,
|
62 |
+
"vocab_size": 250054
|
63 |
+
}
|
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": 16.5499,
|
3 |
+
"predict_gen_len": 52.8126,
|
4 |
+
"predict_loss": 3.067568302154541,
|
5 |
+
"predict_runtime": 656.2829,
|
6 |
+
"predict_samples": 998,
|
7 |
+
"predict_samples_per_second": 1.521,
|
8 |
+
"predict_steps_per_second": 0.152
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43cff6e85cf7b5098f77417640b28b1c8e0c07f53f7eecf2eaeaaa27f5e63e37
|
3 |
+
size 2444723641
|
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 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"]}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"src_lang": null, "tgt_lang": null, "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": "<s>", "model_max_length": 1024, "name_or_path": "/data/users/didelani/afribart/afrimbart", "special_tokens_map_file": "/home/suraj/projects/mbart-50/hf_models/mbart-50-large/special_tokens_map.json", "additional_special_tokens": ["ar_AR", "cs_CZ", "de_DE", "en_XX", "es_XX", "et_EE", "fi_FI", "fr_XX", "gu_IN", "hi_IN", "it_IT", "ja_XX", "kk_KZ", "ko_KR", "lt_LT", "lv_LV", "my_MM", "ne_NP", "nl_XX", "ro_RO", "ru_RU", "si_LK", "tr_TR", "vi_VN", "zh_CN", "af_ZA", "az_AZ", "bn_IN", "fa_IR", "he_IL", "hr_HR", "id_ID", "ka_GE", "km_KH", "mk_MK", "ml_IN", "mn_MN", "mr_IN", "pl_PL", "ps_AF", "pt_XX", "sv_SE", "sw_KE", "ta_IN", "te_IN", "th_TH", "tl_XX", "uk_UA", "ur_PK", "xh_ZA", "gl_ES", "sl_SI"], "sp_model_kwargs": {}, "tokenizer_class": "MBart50Tokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 1.2667300415039062,
|
4 |
+
"train_runtime": 1675.224,
|
5 |
+
"train_samples": 3500,
|
6 |
+
"train_samples_per_second": 20.893,
|
7 |
+
"train_steps_per_second": 2.089
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 3500,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.43,
|
12 |
+
"learning_rate": 4.2857142857142856e-05,
|
13 |
+
"loss": 3.4957,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 2.86,
|
18 |
+
"learning_rate": 3.571428571428572e-05,
|
19 |
+
"loss": 2.1493,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 4.29,
|
24 |
+
"learning_rate": 2.857142857142857e-05,
|
25 |
+
"loss": 1.3363,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 5.71,
|
30 |
+
"learning_rate": 2.1428571428571428e-05,
|
31 |
+
"loss": 0.8278,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 7.14,
|
36 |
+
"learning_rate": 1.4285714285714285e-05,
|
37 |
+
"loss": 0.5068,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 8.57,
|
42 |
+
"learning_rate": 7.142857142857143e-06,
|
43 |
+
"loss": 0.3163,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 10.0,
|
48 |
+
"learning_rate": 0.0,
|
49 |
+
"loss": 0.2349,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 10.0,
|
54 |
+
"step": 3500,
|
55 |
+
"total_flos": 1.389991530676224e+16,
|
56 |
+
"train_loss": 1.2667300415039062,
|
57 |
+
"train_runtime": 1675.224,
|
58 |
+
"train_samples_per_second": 20.893,
|
59 |
+
"train_steps_per_second": 2.089
|
60 |
+
}
|
61 |
+
],
|
62 |
+
"max_steps": 3500,
|
63 |
+
"num_train_epochs": 10,
|
64 |
+
"total_flos": 1.389991530676224e+16,
|
65 |
+
"trial_name": null,
|
66 |
+
"trial_params": null
|
67 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e69f86f5c2ba5a60b1527e43ec4f2c9fa4b6001d57c7a0c7a32f7917597830d9
|
3 |
+
size 2799
|