Davlan commited on
Commit
042cd9a
1 Parent(s): 9925d7c

add MT model

Browse files
all_results.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_bleu": 13.4448,
4
+ "eval_gen_len": 40.838,
5
+ "eval_loss": 1.8132845163345337,
6
+ "eval_runtime": 749.0023,
7
+ "eval_samples": 1500,
8
+ "eval_samples_per_second": 2.003,
9
+ "eval_steps_per_second": 0.2,
10
+ "predict_bleu": 17.1406,
11
+ "predict_gen_len": 39.434,
12
+ "predict_loss": 1.6981964111328125,
13
+ "predict_runtime": 748.5762,
14
+ "predict_samples": 1500,
15
+ "predict_samples_per_second": 2.004,
16
+ "predict_steps_per_second": 0.2,
17
+ "train_loss": 1.7016529773530507,
18
+ "train_runtime": 1029.7789,
19
+ "train_samples": 6998,
20
+ "train_samples_per_second": 20.387,
21
+ "train_steps_per_second": 2.039
22
+ }
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mbart-large-50",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
+ "architectures": [
9
+ "MBartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "forced_bos_token_id": 250043,
29
+ "forced_eos_token_id": 2,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "max_length": 200,
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "normalize_before": true,
47
+ "normalize_embedding": true,
48
+ "num_beams": 5,
49
+ "num_hidden_layers": 12,
50
+ "output_past": true,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": true,
53
+ "static_position_embeddings": false,
54
+ "tokenizer_class": "MBart50Tokenizer",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.12.0",
57
+ "use_cache": true,
58
+ "vocab_size": 250054
59
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_bleu": 13.4448,
4
+ "eval_gen_len": 40.838,
5
+ "eval_loss": 1.8132845163345337,
6
+ "eval_runtime": 749.0023,
7
+ "eval_samples": 1500,
8
+ "eval_samples_per_second": 2.003,
9
+ "eval_steps_per_second": 0.2
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": 17.1406,
3
+ "predict_gen_len": 39.434,
4
+ "predict_loss": 1.6981964111328125,
5
+ "predict_runtime": 748.5762,
6
+ "predict_samples": 1500,
7
+ "predict_samples_per_second": 2.004,
8
+ "predict_steps_per_second": 0.2
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab7b89072feafaea925e05fcfa63c1c033f76ce76bec52c2f459ab46482fc25
3
+ size 2444722195
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": "facebook/mbart-large-50", "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": 3.0,
3
+ "train_loss": 1.7016529773530507,
4
+ "train_runtime": 1029.7789,
5
+ "train_samples": 6998,
6
+ "train_samples_per_second": 20.387,
7
+ "train_steps_per_second": 2.039
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
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": 0.71,
12
+ "learning_rate": 3.809523809523809e-05,
13
+ "loss": 2.8485,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.43,
18
+ "learning_rate": 2.6190476190476192e-05,
19
+ "loss": 1.7027,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 2.14,
24
+ "learning_rate": 1.4285714285714285e-05,
25
+ "loss": 1.3409,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 2.86,
30
+ "learning_rate": 2.3809523809523808e-06,
31
+ "loss": 1.0473,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 3.0,
36
+ "step": 2100,
37
+ "total_flos": 7634802405113856.0,
38
+ "train_loss": 1.7016529773530507,
39
+ "train_runtime": 1029.7789,
40
+ "train_samples_per_second": 20.387,
41
+ "train_steps_per_second": 2.039
42
+ }
43
+ ],
44
+ "max_steps": 2100,
45
+ "num_train_epochs": 3,
46
+ "total_flos": 7634802405113856.0,
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:e4f17ae516770630c18b6199870c909173270150da3ff1323f414f61c9df4ce2
3
+ size 2927