add MT model
Browse files- all_results.json +15 -0
- config.json +38 -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_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +727 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"predict_bleu": 2.3502,
|
4 |
+
"predict_gen_len": 55.6112,
|
5 |
+
"predict_loss": 4.63706636428833,
|
6 |
+
"predict_runtime": 708.0703,
|
7 |
+
"predict_samples": 1574,
|
8 |
+
"predict_samples_per_second": 2.223,
|
9 |
+
"predict_steps_per_second": 0.223,
|
10 |
+
"train_loss": 1.0935829183452552,
|
11 |
+
"train_runtime": 19576.7665,
|
12 |
+
"train_samples": 196321,
|
13 |
+
"train_samples_per_second": 30.085,
|
14 |
+
"train_steps_per_second": 3.009
|
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": 128088,
|
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": 2.3502,
|
3 |
+
"predict_gen_len": 55.6112,
|
4 |
+
"predict_loss": 4.63706636428833,
|
5 |
+
"predict_runtime": 708.0703,
|
6 |
+
"predict_samples": 1574,
|
7 |
+
"predict_samples_per_second": 2.223,
|
8 |
+
"predict_steps_per_second": 0.223
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d9a2156d68f12593c2aad3c83825f437a0a931815b16774a92554393c988655
|
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": 3.0,
|
3 |
+
"train_loss": 1.0935829183452552,
|
4 |
+
"train_runtime": 19576.7665,
|
5 |
+
"train_samples": 196321,
|
6 |
+
"train_samples_per_second": 30.085,
|
7 |
+
"train_steps_per_second": 3.009
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,727 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 58899,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.03,
|
12 |
+
"learning_rate": 4.95755445763086e-05,
|
13 |
+
"loss": 2.797,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.05,
|
18 |
+
"learning_rate": 4.91510891526172e-05,
|
19 |
+
"loss": 2.0557,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.08,
|
24 |
+
"learning_rate": 4.872663372892579e-05,
|
25 |
+
"loss": 1.8501,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.1,
|
30 |
+
"learning_rate": 4.830217830523439e-05,
|
31 |
+
"loss": 1.7462,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.13,
|
36 |
+
"learning_rate": 4.787772288154298e-05,
|
37 |
+
"loss": 1.6583,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.15,
|
42 |
+
"learning_rate": 4.745326745785158e-05,
|
43 |
+
"loss": 1.5985,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.18,
|
48 |
+
"learning_rate": 4.7028812034160174e-05,
|
49 |
+
"loss": 1.5383,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.2,
|
54 |
+
"learning_rate": 4.660435661046877e-05,
|
55 |
+
"loss": 1.5078,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.23,
|
60 |
+
"learning_rate": 4.617990118677737e-05,
|
61 |
+
"loss": 1.4759,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.25,
|
66 |
+
"learning_rate": 4.575544576308596e-05,
|
67 |
+
"loss": 1.4643,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.28,
|
72 |
+
"learning_rate": 4.533099033939456e-05,
|
73 |
+
"loss": 1.4383,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.31,
|
78 |
+
"learning_rate": 4.490653491570315e-05,
|
79 |
+
"loss": 1.4008,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.33,
|
84 |
+
"learning_rate": 4.4482079492011754e-05,
|
85 |
+
"loss": 1.3803,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.36,
|
90 |
+
"learning_rate": 4.4057624068320345e-05,
|
91 |
+
"loss": 1.3634,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.38,
|
96 |
+
"learning_rate": 4.363316864462894e-05,
|
97 |
+
"loss": 1.351,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.41,
|
102 |
+
"learning_rate": 4.320871322093754e-05,
|
103 |
+
"loss": 1.3307,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.43,
|
108 |
+
"learning_rate": 4.278425779724614e-05,
|
109 |
+
"loss": 1.3303,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.46,
|
114 |
+
"learning_rate": 4.235980237355473e-05,
|
115 |
+
"loss": 1.3105,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.48,
|
120 |
+
"learning_rate": 4.193534694986333e-05,
|
121 |
+
"loss": 1.3139,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.51,
|
126 |
+
"learning_rate": 4.1510891526171925e-05,
|
127 |
+
"loss": 1.2975,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.53,
|
132 |
+
"learning_rate": 4.1086436102480516e-05,
|
133 |
+
"loss": 1.2893,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.56,
|
138 |
+
"learning_rate": 4.0661980678789114e-05,
|
139 |
+
"loss": 1.2754,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.59,
|
144 |
+
"learning_rate": 4.023752525509771e-05,
|
145 |
+
"loss": 1.2749,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.61,
|
150 |
+
"learning_rate": 3.981306983140631e-05,
|
151 |
+
"loss": 1.2569,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.64,
|
156 |
+
"learning_rate": 3.93886144077149e-05,
|
157 |
+
"loss": 1.2517,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.66,
|
162 |
+
"learning_rate": 3.8964158984023505e-05,
|
163 |
+
"loss": 1.2547,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.69,
|
168 |
+
"learning_rate": 3.8539703560332096e-05,
|
169 |
+
"loss": 1.2295,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.71,
|
174 |
+
"learning_rate": 3.8115248136640694e-05,
|
175 |
+
"loss": 1.2121,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.74,
|
180 |
+
"learning_rate": 3.7690792712949285e-05,
|
181 |
+
"loss": 1.2246,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.76,
|
186 |
+
"learning_rate": 3.726633728925788e-05,
|
187 |
+
"loss": 1.2127,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.79,
|
192 |
+
"learning_rate": 3.684188186556648e-05,
|
193 |
+
"loss": 1.1937,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.81,
|
198 |
+
"learning_rate": 3.641742644187507e-05,
|
199 |
+
"loss": 1.191,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.84,
|
204 |
+
"learning_rate": 3.5992971018183676e-05,
|
205 |
+
"loss": 1.1785,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.87,
|
210 |
+
"learning_rate": 3.556851559449227e-05,
|
211 |
+
"loss": 1.1734,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.89,
|
216 |
+
"learning_rate": 3.5144060170800865e-05,
|
217 |
+
"loss": 1.1964,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.92,
|
222 |
+
"learning_rate": 3.4719604747109456e-05,
|
223 |
+
"loss": 1.1786,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.94,
|
228 |
+
"learning_rate": 3.429514932341806e-05,
|
229 |
+
"loss": 1.1424,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.97,
|
234 |
+
"learning_rate": 3.387069389972665e-05,
|
235 |
+
"loss": 1.1677,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.99,
|
240 |
+
"learning_rate": 3.344623847603525e-05,
|
241 |
+
"loss": 1.1628,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.02,
|
246 |
+
"learning_rate": 3.302178305234385e-05,
|
247 |
+
"loss": 1.0756,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 1.04,
|
252 |
+
"learning_rate": 3.259732762865244e-05,
|
253 |
+
"loss": 1.0654,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.07,
|
258 |
+
"learning_rate": 3.2172872204961036e-05,
|
259 |
+
"loss": 1.0666,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.1,
|
264 |
+
"learning_rate": 3.174841678126963e-05,
|
265 |
+
"loss": 1.0594,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.12,
|
270 |
+
"learning_rate": 3.132396135757823e-05,
|
271 |
+
"loss": 1.0642,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.15,
|
276 |
+
"learning_rate": 3.089950593388682e-05,
|
277 |
+
"loss": 1.0594,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.17,
|
282 |
+
"learning_rate": 3.0475050510195417e-05,
|
283 |
+
"loss": 1.0581,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.2,
|
288 |
+
"learning_rate": 3.005059508650402e-05,
|
289 |
+
"loss": 1.0561,
|
290 |
+
"step": 23500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.22,
|
294 |
+
"learning_rate": 2.9626139662812613e-05,
|
295 |
+
"loss": 1.0298,
|
296 |
+
"step": 24000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.25,
|
300 |
+
"learning_rate": 2.9201684239121207e-05,
|
301 |
+
"loss": 1.0451,
|
302 |
+
"step": 24500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.27,
|
306 |
+
"learning_rate": 2.877722881542981e-05,
|
307 |
+
"loss": 1.0611,
|
308 |
+
"step": 25000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.3,
|
312 |
+
"learning_rate": 2.8352773391738403e-05,
|
313 |
+
"loss": 1.0445,
|
314 |
+
"step": 25500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.32,
|
318 |
+
"learning_rate": 2.7928317968046997e-05,
|
319 |
+
"loss": 1.0592,
|
320 |
+
"step": 26000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 1.35,
|
324 |
+
"learning_rate": 2.7503862544355592e-05,
|
325 |
+
"loss": 1.0445,
|
326 |
+
"step": 26500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 1.38,
|
330 |
+
"learning_rate": 2.707940712066419e-05,
|
331 |
+
"loss": 1.0338,
|
332 |
+
"step": 27000
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.4,
|
336 |
+
"learning_rate": 2.6654951696972784e-05,
|
337 |
+
"loss": 1.0331,
|
338 |
+
"step": 27500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.43,
|
342 |
+
"learning_rate": 2.623049627328138e-05,
|
343 |
+
"loss": 1.0308,
|
344 |
+
"step": 28000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.45,
|
348 |
+
"learning_rate": 2.580604084958998e-05,
|
349 |
+
"loss": 1.0329,
|
350 |
+
"step": 28500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 1.48,
|
354 |
+
"learning_rate": 2.5381585425898574e-05,
|
355 |
+
"loss": 1.0178,
|
356 |
+
"step": 29000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.5,
|
360 |
+
"learning_rate": 2.495713000220717e-05,
|
361 |
+
"loss": 1.0197,
|
362 |
+
"step": 29500
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 1.53,
|
366 |
+
"learning_rate": 2.4532674578515766e-05,
|
367 |
+
"loss": 1.0168,
|
368 |
+
"step": 30000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 1.55,
|
372 |
+
"learning_rate": 2.410821915482436e-05,
|
373 |
+
"loss": 1.007,
|
374 |
+
"step": 30500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.58,
|
378 |
+
"learning_rate": 2.368376373113296e-05,
|
379 |
+
"loss": 1.0249,
|
380 |
+
"step": 31000
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.6,
|
384 |
+
"learning_rate": 2.3259308307441553e-05,
|
385 |
+
"loss": 1.0178,
|
386 |
+
"step": 31500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 1.63,
|
390 |
+
"learning_rate": 2.2834852883750148e-05,
|
391 |
+
"loss": 1.0199,
|
392 |
+
"step": 32000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 1.66,
|
396 |
+
"learning_rate": 2.2410397460058745e-05,
|
397 |
+
"loss": 1.0089,
|
398 |
+
"step": 32500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.68,
|
402 |
+
"learning_rate": 2.198594203636734e-05,
|
403 |
+
"loss": 1.0016,
|
404 |
+
"step": 33000
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 1.71,
|
408 |
+
"learning_rate": 2.1561486612675938e-05,
|
409 |
+
"loss": 1.0011,
|
410 |
+
"step": 33500
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 1.73,
|
414 |
+
"learning_rate": 2.1137031188984535e-05,
|
415 |
+
"loss": 0.9975,
|
416 |
+
"step": 34000
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.76,
|
420 |
+
"learning_rate": 2.071257576529313e-05,
|
421 |
+
"loss": 0.9856,
|
422 |
+
"step": 34500
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.78,
|
426 |
+
"learning_rate": 2.0288120341601728e-05,
|
427 |
+
"loss": 0.9977,
|
428 |
+
"step": 35000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 1.81,
|
432 |
+
"learning_rate": 1.9863664917910322e-05,
|
433 |
+
"loss": 0.9933,
|
434 |
+
"step": 35500
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 1.83,
|
438 |
+
"learning_rate": 1.943920949421892e-05,
|
439 |
+
"loss": 1.0059,
|
440 |
+
"step": 36000
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 1.86,
|
444 |
+
"learning_rate": 1.9014754070527514e-05,
|
445 |
+
"loss": 1.0033,
|
446 |
+
"step": 36500
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 1.88,
|
450 |
+
"learning_rate": 1.859029864683611e-05,
|
451 |
+
"loss": 0.9744,
|
452 |
+
"step": 37000
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 1.91,
|
456 |
+
"learning_rate": 1.8165843223144707e-05,
|
457 |
+
"loss": 0.986,
|
458 |
+
"step": 37500
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.94,
|
462 |
+
"learning_rate": 1.77413877994533e-05,
|
463 |
+
"loss": 0.9853,
|
464 |
+
"step": 38000
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 1.96,
|
468 |
+
"learning_rate": 1.73169323757619e-05,
|
469 |
+
"loss": 0.9758,
|
470 |
+
"step": 38500
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 1.99,
|
474 |
+
"learning_rate": 1.6892476952070493e-05,
|
475 |
+
"loss": 0.9772,
|
476 |
+
"step": 39000
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 2.01,
|
480 |
+
"learning_rate": 1.646802152837909e-05,
|
481 |
+
"loss": 0.946,
|
482 |
+
"step": 39500
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 2.04,
|
486 |
+
"learning_rate": 1.604356610468769e-05,
|
487 |
+
"loss": 0.8919,
|
488 |
+
"step": 40000
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 2.06,
|
492 |
+
"learning_rate": 1.5619110680996283e-05,
|
493 |
+
"loss": 0.8903,
|
494 |
+
"step": 40500
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 2.09,
|
498 |
+
"learning_rate": 1.519465525730488e-05,
|
499 |
+
"loss": 0.8867,
|
500 |
+
"step": 41000
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 2.11,
|
504 |
+
"learning_rate": 1.4770199833613474e-05,
|
505 |
+
"loss": 0.8749,
|
506 |
+
"step": 41500
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 2.14,
|
510 |
+
"learning_rate": 1.4345744409922072e-05,
|
511 |
+
"loss": 0.8733,
|
512 |
+
"step": 42000
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 2.16,
|
516 |
+
"learning_rate": 1.3921288986230666e-05,
|
517 |
+
"loss": 0.8909,
|
518 |
+
"step": 42500
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 2.19,
|
522 |
+
"learning_rate": 1.3496833562539262e-05,
|
523 |
+
"loss": 0.871,
|
524 |
+
"step": 43000
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 2.22,
|
528 |
+
"learning_rate": 1.307237813884786e-05,
|
529 |
+
"loss": 0.8741,
|
530 |
+
"step": 43500
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 2.24,
|
534 |
+
"learning_rate": 1.2647922715156455e-05,
|
535 |
+
"loss": 0.8856,
|
536 |
+
"step": 44000
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 2.27,
|
540 |
+
"learning_rate": 1.222346729146505e-05,
|
541 |
+
"loss": 0.8833,
|
542 |
+
"step": 44500
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 2.29,
|
546 |
+
"learning_rate": 1.1799011867773647e-05,
|
547 |
+
"loss": 0.8824,
|
548 |
+
"step": 45000
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 2.32,
|
552 |
+
"learning_rate": 1.1374556444082243e-05,
|
553 |
+
"loss": 0.8711,
|
554 |
+
"step": 45500
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 2.34,
|
558 |
+
"learning_rate": 1.0950101020390839e-05,
|
559 |
+
"loss": 0.8789,
|
560 |
+
"step": 46000
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 2.37,
|
564 |
+
"learning_rate": 1.0525645596699435e-05,
|
565 |
+
"loss": 0.8823,
|
566 |
+
"step": 46500
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 2.39,
|
570 |
+
"learning_rate": 1.0101190173008031e-05,
|
571 |
+
"loss": 0.8755,
|
572 |
+
"step": 47000
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 2.42,
|
576 |
+
"learning_rate": 9.676734749316626e-06,
|
577 |
+
"loss": 0.8715,
|
578 |
+
"step": 47500
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 2.44,
|
582 |
+
"learning_rate": 9.252279325625224e-06,
|
583 |
+
"loss": 0.8726,
|
584 |
+
"step": 48000
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 2.47,
|
588 |
+
"learning_rate": 8.82782390193382e-06,
|
589 |
+
"loss": 0.8811,
|
590 |
+
"step": 48500
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 2.5,
|
594 |
+
"learning_rate": 8.403368478242416e-06,
|
595 |
+
"loss": 0.8676,
|
596 |
+
"step": 49000
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 2.52,
|
600 |
+
"learning_rate": 7.978913054551012e-06,
|
601 |
+
"loss": 0.8727,
|
602 |
+
"step": 49500
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 2.55,
|
606 |
+
"learning_rate": 7.554457630859607e-06,
|
607 |
+
"loss": 0.8572,
|
608 |
+
"step": 50000
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 2.57,
|
612 |
+
"learning_rate": 7.1300022071682025e-06,
|
613 |
+
"loss": 0.86,
|
614 |
+
"step": 50500
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 2.6,
|
618 |
+
"learning_rate": 6.7055467834768e-06,
|
619 |
+
"loss": 0.8571,
|
620 |
+
"step": 51000
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 2.62,
|
624 |
+
"learning_rate": 6.281091359785396e-06,
|
625 |
+
"loss": 0.8488,
|
626 |
+
"step": 51500
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 2.65,
|
630 |
+
"learning_rate": 5.856635936093992e-06,
|
631 |
+
"loss": 0.857,
|
632 |
+
"step": 52000
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 2.67,
|
636 |
+
"learning_rate": 5.432180512402588e-06,
|
637 |
+
"loss": 0.8544,
|
638 |
+
"step": 52500
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 2.7,
|
642 |
+
"learning_rate": 5.007725088711183e-06,
|
643 |
+
"loss": 0.8611,
|
644 |
+
"step": 53000
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 2.73,
|
648 |
+
"learning_rate": 4.58326966501978e-06,
|
649 |
+
"loss": 0.8542,
|
650 |
+
"step": 53500
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 2.75,
|
654 |
+
"learning_rate": 4.158814241328375e-06,
|
655 |
+
"loss": 0.867,
|
656 |
+
"step": 54000
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 2.78,
|
660 |
+
"learning_rate": 3.7343588176369715e-06,
|
661 |
+
"loss": 0.8534,
|
662 |
+
"step": 54500
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 2.8,
|
666 |
+
"learning_rate": 3.309903393945568e-06,
|
667 |
+
"loss": 0.8754,
|
668 |
+
"step": 55000
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 2.83,
|
672 |
+
"learning_rate": 2.8854479702541638e-06,
|
673 |
+
"loss": 0.8451,
|
674 |
+
"step": 55500
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 2.85,
|
678 |
+
"learning_rate": 2.4609925465627603e-06,
|
679 |
+
"loss": 0.8531,
|
680 |
+
"step": 56000
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 2.88,
|
684 |
+
"learning_rate": 2.0365371228713564e-06,
|
685 |
+
"loss": 0.8538,
|
686 |
+
"step": 56500
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 2.9,
|
690 |
+
"learning_rate": 1.6120816991799521e-06,
|
691 |
+
"loss": 0.8474,
|
692 |
+
"step": 57000
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 2.93,
|
696 |
+
"learning_rate": 1.1876262754885483e-06,
|
697 |
+
"loss": 0.8585,
|
698 |
+
"step": 57500
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 2.95,
|
702 |
+
"learning_rate": 7.631708517971443e-07,
|
703 |
+
"loss": 0.8511,
|
704 |
+
"step": 58000
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 2.98,
|
708 |
+
"learning_rate": 3.3871542810574035e-07,
|
709 |
+
"loss": 0.8521,
|
710 |
+
"step": 58500
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 3.0,
|
714 |
+
"step": 58899,
|
715 |
+
"total_flos": 8.70325170291671e+16,
|
716 |
+
"train_loss": 1.0935829183452552,
|
717 |
+
"train_runtime": 19576.7665,
|
718 |
+
"train_samples_per_second": 30.085,
|
719 |
+
"train_steps_per_second": 3.009
|
720 |
+
}
|
721 |
+
],
|
722 |
+
"max_steps": 58899,
|
723 |
+
"num_train_epochs": 3,
|
724 |
+
"total_flos": 8.70325170291671e+16,
|
725 |
+
"trial_name": null,
|
726 |
+
"trial_params": null
|
727 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eab95a47533a153ac7281868808666ea79556ced09b7e6a5813af609664e484d
|
3 |
+
size 2735
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|