Davlan commited on
Commit
14cb0af
1 Parent(s): f03c3a9

add MT model

Browse files
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "predict_bleu": 14.7425,
4
+ "predict_gen_len": 49.0307,
5
+ "predict_loss": 2.3840110301971436,
6
+ "predict_runtime": 738.3343,
7
+ "predict_samples": 1500,
8
+ "predict_samples_per_second": 2.032,
9
+ "predict_steps_per_second": 0.203,
10
+ "train_loss": 1.565825419272146,
11
+ "train_runtime": 1234.3282,
12
+ "train_samples": 3098,
13
+ "train_samples_per_second": 25.099,
14
+ "train_steps_per_second": 2.511
15
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/m2m100_418M",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "M2M100ForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "d_model": 1024,
11
+ "decoder_attention_heads": 16,
12
+ "decoder_ffn_dim": 4096,
13
+ "decoder_layerdrop": 0.05,
14
+ "decoder_layers": 12,
15
+ "decoder_start_token_id": 2,
16
+ "dropout": 0.1,
17
+ "early_stopping": true,
18
+ "encoder_attention_heads": 16,
19
+ "encoder_ffn_dim": 4096,
20
+ "encoder_layerdrop": 0.05,
21
+ "encoder_layers": 12,
22
+ "eos_token_id": 2,
23
+ "forced_bos_token_id": 128034,
24
+ "gradient_checkpointing": false,
25
+ "init_std": 0.02,
26
+ "is_encoder_decoder": true,
27
+ "max_length": 200,
28
+ "max_position_embeddings": 1024,
29
+ "model_type": "m2m_100",
30
+ "num_beams": 5,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 1,
33
+ "scale_embedding": true,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.10.3",
36
+ "use_cache": true,
37
+ "vocab_size": 128112
38
+ }
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": 14.7425,
3
+ "predict_gen_len": 49.0307,
4
+ "predict_loss": 2.3840110301971436,
5
+ "predict_runtime": 738.3343,
6
+ "predict_samples": 1500,
7
+ "predict_samples_per_second": 2.032,
8
+ "predict_steps_per_second": 0.203
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0d55c26f0e513bdc64cfd5f8df624ed23edd8f49f889362d66d3a869c61f953
3
+ size 1935792071
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f7c76ed2a5e0822be39f0a4f95a55eb19c78f4593ce609e2edbc2aea4d380a
3
+ size 2423393
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "additional_special_tokens": ["__af__", "__am__", "__ar__", "__ast__", "__az__", "__ba__", "__be__", "__bg__", "__bn__", "__br__", "__bs__", "__ca__", "__ceb__", "__cs__", "__cy__", "__da__", "__de__", "__el__", "__en__", "__es__", "__et__", "__fa__", "__ff__", "__fi__", "__fr__", "__fy__", "__ga__", "__gd__", "__gl__", "__gu__", "__ha__", "__he__", "__hi__", "__hr__", "__ht__", "__hu__", "__hy__", "__id__", "__ig__", "__ilo__", "__is__", "__it__", "__ja__", "__jv__", "__ka__", "__kk__", "__km__", "__kn__", "__ko__", "__lb__", "__lg__", "__ln__", "__lo__", "__lt__", "__lv__", "__mg__", "__mk__", "__ml__", "__mn__", "__mr__", "__ms__", "__my__", "__ne__", "__nl__", "__no__", "__ns__", "__oc__", "__or__", "__pa__", "__pl__", "__ps__", "__pt__", "__ro__", "__ru__", "__sd__", "__si__", "__sk__", "__sl__", "__so__", "__sq__", "__sr__", "__ss__", "__su__", "__sv__", "__sw__", "__ta__", "__th__", "__tl__", "__tn__", "__tr__", "__uk__", "__ur__", "__uz__", "__vi__", "__wo__", "__xh__", "__yi__", "__yo__", "__zh__", "__zu__"]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"src_lang": null, "tgt_lang": null, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "sp_model_kwargs": {}, "special_tokens_map_file": "m2m_100_1.2B_v2/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "facebook/m2m100_418M", "model_max_length": 1024, "additional_special_tokens": ["__af__", "__am__", "__ar__", "__ast__", "__az__", "__ba__", "__be__", "__bg__", "__bn__", "__br__", "__bs__", "__ca__", "__ceb__", "__cs__", "__cy__", "__da__", "__de__", "__el__", "__en__", "__es__", "__et__", "__fa__", "__ff__", "__fi__", "__fr__", "__fy__", "__ga__", "__gd__", "__gl__", "__gu__", "__ha__", "__he__", "__hi__", "__hr__", "__ht__", "__hu__", "__hy__", "__id__", "__ig__", "__ilo__", "__is__", "__it__", "__ja__", "__jv__", "__ka__", "__kk__", "__km__", "__kn__", "__ko__", "__lb__", "__lg__", "__ln__", "__lo__", "__lt__", "__lv__", "__mg__", "__mk__", "__ml__", "__mn__", "__mr__", "__ms__", "__my__", "__ne__", "__nl__", "__no__", "__ns__", "__oc__", "__or__", "__pa__", "__pl__", "__ps__", "__pt__", "__ro__", "__ru__", "__sd__", "__si__", "__sk__", "__sl__", "__so__", "__sq__", "__sr__", "__ss__", "__su__", "__sv__", "__sw__", "__ta__", "__th__", "__tl__", "__tn__", "__tr__", "__uk__", "__ur__", "__uz__", "__vi__", "__wo__", "__xh__", "__yi__", "__yo__", "__zh__", "__zu__"], "tokenizer_class": "M2M100Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 1.565825419272146,
4
+ "train_runtime": 1234.3282,
5
+ "train_samples": 3098,
6
+ "train_samples_per_second": 25.099,
7
+ "train_steps_per_second": 2.511
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 3100,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.61,
12
+ "learning_rate": 4.1935483870967746e-05,
13
+ "loss": 3.184,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 3.23,
18
+ "learning_rate": 3.387096774193548e-05,
19
+ "loss": 2.0618,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 4.84,
24
+ "learning_rate": 2.5806451612903226e-05,
25
+ "loss": 1.5201,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 6.45,
30
+ "learning_rate": 1.774193548387097e-05,
31
+ "loss": 1.1521,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 8.06,
36
+ "learning_rate": 9.67741935483871e-06,
37
+ "loss": 0.9138,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 9.68,
42
+ "learning_rate": 1.6129032258064516e-06,
43
+ "loss": 0.7343,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 10.0,
48
+ "step": 3100,
49
+ "total_flos": 5883825531125760.0,
50
+ "train_loss": 1.565825419272146,
51
+ "train_runtime": 1234.3282,
52
+ "train_samples_per_second": 25.099,
53
+ "train_steps_per_second": 2.511
54
+ }
55
+ ],
56
+ "max_steps": 3100,
57
+ "num_train_epochs": 10,
58
+ "total_flos": 5883825531125760.0,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcc3a3297564e73ccca59e2dbcc03fa6206eca617df753b8f6e3ed7b87526bbc
3
+ size 2799
vocab.json ADDED
The diff for this file is too large to render. See raw diff