Upload 13 files
Browse files- all_results.json +23 -0
- config.json +38 -0
- eval_results.json +10 -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 +109 -0
- tokenizer_config.json +119 -0
- train_results.json +9 -0
- trainer_state.json +181 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_bleu": 8.7462,
|
| 4 |
+
"eval_gen_len": 42.6262,
|
| 5 |
+
"eval_loss": 3.8143951892852783,
|
| 6 |
+
"eval_runtime": 622.8474,
|
| 7 |
+
"eval_samples": 1506,
|
| 8 |
+
"eval_samples_per_second": 2.418,
|
| 9 |
+
"eval_steps_per_second": 0.242,
|
| 10 |
+
"predict_bleu": 7.672,
|
| 11 |
+
"predict_gen_len": 44.52,
|
| 12 |
+
"predict_loss": 3.8288064002990723,
|
| 13 |
+
"predict_runtime": 654.7493,
|
| 14 |
+
"predict_samples": 1500,
|
| 15 |
+
"predict_samples_per_second": 2.291,
|
| 16 |
+
"predict_steps_per_second": 0.229,
|
| 17 |
+
"total_flos": 2.659014067347456e+16,
|
| 18 |
+
"train_loss": 0.3552576902189425,
|
| 19 |
+
"train_runtime": 12919.7128,
|
| 20 |
+
"train_samples": 3360,
|
| 21 |
+
"train_samples_per_second": 10.403,
|
| 22 |
+
"train_steps_per_second": 1.04
|
| 23 |
+
}
|
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": 128098,
|
| 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": "4.24.0",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 128112
|
| 38 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_bleu": 8.7462,
|
| 4 |
+
"eval_gen_len": 42.6262,
|
| 5 |
+
"eval_loss": 3.8143951892852783,
|
| 6 |
+
"eval_runtime": 622.8474,
|
| 7 |
+
"eval_samples": 1506,
|
| 8 |
+
"eval_samples_per_second": 2.418,
|
| 9 |
+
"eval_steps_per_second": 0.242
|
| 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": 7.672,
|
| 3 |
+
"predict_gen_len": 44.52,
|
| 4 |
+
"predict_loss": 3.8288064002990723,
|
| 5 |
+
"predict_runtime": 654.7493,
|
| 6 |
+
"predict_samples": 1500,
|
| 7 |
+
"predict_samples_per_second": 2.291,
|
| 8 |
+
"predict_steps_per_second": 0.229
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14df56cc397af36b4a22ef77f243e1d2529bb4c43af69b657cecc941cf885866
|
| 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 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"__af__",
|
| 4 |
+
"__am__",
|
| 5 |
+
"__ar__",
|
| 6 |
+
"__ast__",
|
| 7 |
+
"__az__",
|
| 8 |
+
"__ba__",
|
| 9 |
+
"__be__",
|
| 10 |
+
"__bg__",
|
| 11 |
+
"__bn__",
|
| 12 |
+
"__br__",
|
| 13 |
+
"__bs__",
|
| 14 |
+
"__ca__",
|
| 15 |
+
"__ceb__",
|
| 16 |
+
"__cs__",
|
| 17 |
+
"__cy__",
|
| 18 |
+
"__da__",
|
| 19 |
+
"__de__",
|
| 20 |
+
"__el__",
|
| 21 |
+
"__en__",
|
| 22 |
+
"__es__",
|
| 23 |
+
"__et__",
|
| 24 |
+
"__fa__",
|
| 25 |
+
"__ff__",
|
| 26 |
+
"__fi__",
|
| 27 |
+
"__fr__",
|
| 28 |
+
"__fy__",
|
| 29 |
+
"__ga__",
|
| 30 |
+
"__gd__",
|
| 31 |
+
"__gl__",
|
| 32 |
+
"__gu__",
|
| 33 |
+
"__ha__",
|
| 34 |
+
"__he__",
|
| 35 |
+
"__hi__",
|
| 36 |
+
"__hr__",
|
| 37 |
+
"__ht__",
|
| 38 |
+
"__hu__",
|
| 39 |
+
"__hy__",
|
| 40 |
+
"__id__",
|
| 41 |
+
"__ig__",
|
| 42 |
+
"__ilo__",
|
| 43 |
+
"__is__",
|
| 44 |
+
"__it__",
|
| 45 |
+
"__ja__",
|
| 46 |
+
"__jv__",
|
| 47 |
+
"__ka__",
|
| 48 |
+
"__kk__",
|
| 49 |
+
"__km__",
|
| 50 |
+
"__kn__",
|
| 51 |
+
"__ko__",
|
| 52 |
+
"__lb__",
|
| 53 |
+
"__lg__",
|
| 54 |
+
"__ln__",
|
| 55 |
+
"__lo__",
|
| 56 |
+
"__lt__",
|
| 57 |
+
"__lv__",
|
| 58 |
+
"__mg__",
|
| 59 |
+
"__mk__",
|
| 60 |
+
"__ml__",
|
| 61 |
+
"__mn__",
|
| 62 |
+
"__mr__",
|
| 63 |
+
"__ms__",
|
| 64 |
+
"__my__",
|
| 65 |
+
"__ne__",
|
| 66 |
+
"__nl__",
|
| 67 |
+
"__no__",
|
| 68 |
+
"__ns__",
|
| 69 |
+
"__oc__",
|
| 70 |
+
"__or__",
|
| 71 |
+
"__pa__",
|
| 72 |
+
"__pl__",
|
| 73 |
+
"__ps__",
|
| 74 |
+
"__pt__",
|
| 75 |
+
"__ro__",
|
| 76 |
+
"__ru__",
|
| 77 |
+
"__sd__",
|
| 78 |
+
"__si__",
|
| 79 |
+
"__sk__",
|
| 80 |
+
"__sl__",
|
| 81 |
+
"__so__",
|
| 82 |
+
"__sq__",
|
| 83 |
+
"__sr__",
|
| 84 |
+
"__ss__",
|
| 85 |
+
"__su__",
|
| 86 |
+
"__sv__",
|
| 87 |
+
"__sw__",
|
| 88 |
+
"__ta__",
|
| 89 |
+
"__th__",
|
| 90 |
+
"__tl__",
|
| 91 |
+
"__tn__",
|
| 92 |
+
"__tr__",
|
| 93 |
+
"__uk__",
|
| 94 |
+
"__ur__",
|
| 95 |
+
"__uz__",
|
| 96 |
+
"__vi__",
|
| 97 |
+
"__wo__",
|
| 98 |
+
"__xh__",
|
| 99 |
+
"__yi__",
|
| 100 |
+
"__yo__",
|
| 101 |
+
"__zh__",
|
| 102 |
+
"__zu__"
|
| 103 |
+
],
|
| 104 |
+
"bos_token": "<s>",
|
| 105 |
+
"eos_token": "</s>",
|
| 106 |
+
"pad_token": "<pad>",
|
| 107 |
+
"sep_token": "</s>",
|
| 108 |
+
"unk_token": "<unk>"
|
| 109 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"__af__",
|
| 4 |
+
"__am__",
|
| 5 |
+
"__ar__",
|
| 6 |
+
"__ast__",
|
| 7 |
+
"__az__",
|
| 8 |
+
"__ba__",
|
| 9 |
+
"__be__",
|
| 10 |
+
"__bg__",
|
| 11 |
+
"__bn__",
|
| 12 |
+
"__br__",
|
| 13 |
+
"__bs__",
|
| 14 |
+
"__ca__",
|
| 15 |
+
"__ceb__",
|
| 16 |
+
"__cs__",
|
| 17 |
+
"__cy__",
|
| 18 |
+
"__da__",
|
| 19 |
+
"__de__",
|
| 20 |
+
"__el__",
|
| 21 |
+
"__en__",
|
| 22 |
+
"__es__",
|
| 23 |
+
"__et__",
|
| 24 |
+
"__fa__",
|
| 25 |
+
"__ff__",
|
| 26 |
+
"__fi__",
|
| 27 |
+
"__fr__",
|
| 28 |
+
"__fy__",
|
| 29 |
+
"__ga__",
|
| 30 |
+
"__gd__",
|
| 31 |
+
"__gl__",
|
| 32 |
+
"__gu__",
|
| 33 |
+
"__ha__",
|
| 34 |
+
"__he__",
|
| 35 |
+
"__hi__",
|
| 36 |
+
"__hr__",
|
| 37 |
+
"__ht__",
|
| 38 |
+
"__hu__",
|
| 39 |
+
"__hy__",
|
| 40 |
+
"__id__",
|
| 41 |
+
"__ig__",
|
| 42 |
+
"__ilo__",
|
| 43 |
+
"__is__",
|
| 44 |
+
"__it__",
|
| 45 |
+
"__ja__",
|
| 46 |
+
"__jv__",
|
| 47 |
+
"__ka__",
|
| 48 |
+
"__kk__",
|
| 49 |
+
"__km__",
|
| 50 |
+
"__kn__",
|
| 51 |
+
"__ko__",
|
| 52 |
+
"__lb__",
|
| 53 |
+
"__lg__",
|
| 54 |
+
"__ln__",
|
| 55 |
+
"__lo__",
|
| 56 |
+
"__lt__",
|
| 57 |
+
"__lv__",
|
| 58 |
+
"__mg__",
|
| 59 |
+
"__mk__",
|
| 60 |
+
"__ml__",
|
| 61 |
+
"__mn__",
|
| 62 |
+
"__mr__",
|
| 63 |
+
"__ms__",
|
| 64 |
+
"__my__",
|
| 65 |
+
"__ne__",
|
| 66 |
+
"__nl__",
|
| 67 |
+
"__no__",
|
| 68 |
+
"__ns__",
|
| 69 |
+
"__oc__",
|
| 70 |
+
"__or__",
|
| 71 |
+
"__pa__",
|
| 72 |
+
"__pl__",
|
| 73 |
+
"__ps__",
|
| 74 |
+
"__pt__",
|
| 75 |
+
"__ro__",
|
| 76 |
+
"__ru__",
|
| 77 |
+
"__sd__",
|
| 78 |
+
"__si__",
|
| 79 |
+
"__sk__",
|
| 80 |
+
"__sl__",
|
| 81 |
+
"__so__",
|
| 82 |
+
"__sq__",
|
| 83 |
+
"__sr__",
|
| 84 |
+
"__ss__",
|
| 85 |
+
"__su__",
|
| 86 |
+
"__sv__",
|
| 87 |
+
"__sw__",
|
| 88 |
+
"__ta__",
|
| 89 |
+
"__th__",
|
| 90 |
+
"__tl__",
|
| 91 |
+
"__tn__",
|
| 92 |
+
"__tr__",
|
| 93 |
+
"__uk__",
|
| 94 |
+
"__ur__",
|
| 95 |
+
"__uz__",
|
| 96 |
+
"__vi__",
|
| 97 |
+
"__wo__",
|
| 98 |
+
"__xh__",
|
| 99 |
+
"__yi__",
|
| 100 |
+
"__yo__",
|
| 101 |
+
"__zh__",
|
| 102 |
+
"__zu__"
|
| 103 |
+
],
|
| 104 |
+
"bos_token": "<s>",
|
| 105 |
+
"eos_token": "</s>",
|
| 106 |
+
"language_codes": "m2m100",
|
| 107 |
+
"model_max_length": 1024,
|
| 108 |
+
"name_or_path": "facebook/m2m100_418M",
|
| 109 |
+
"num_madeup_words": 8,
|
| 110 |
+
"pad_token": "<pad>",
|
| 111 |
+
"sep_token": "</s>",
|
| 112 |
+
"sp_model_kwargs": {},
|
| 113 |
+
"special_tokens_map_file": "m2m_100_1.2B_v2/special_tokens_map.json",
|
| 114 |
+
"src_lang": null,
|
| 115 |
+
"tgt_lang": null,
|
| 116 |
+
"tokenizer_class": "M2M100Tokenizer",
|
| 117 |
+
"tokenizer_file": null,
|
| 118 |
+
"unk_token": "<unk>"
|
| 119 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"total_flos": 2.659014067347456e+16,
|
| 4 |
+
"train_loss": 0.3552576902189425,
|
| 5 |
+
"train_runtime": 12919.7128,
|
| 6 |
+
"train_samples": 3360,
|
| 7 |
+
"train_samples_per_second": 10.403,
|
| 8 |
+
"train_steps_per_second": 1.04
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,181 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 40.0,
|
| 5 |
+
"global_step": 13440,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.49,
|
| 12 |
+
"learning_rate": 4.813988095238096e-05,
|
| 13 |
+
"loss": 2.8945,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 2.98,
|
| 18 |
+
"learning_rate": 4.627976190476191e-05,
|
| 19 |
+
"loss": 2.0495,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 4.46,
|
| 24 |
+
"learning_rate": 4.4419642857142854e-05,
|
| 25 |
+
"loss": 1.4014,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 5.95,
|
| 30 |
+
"learning_rate": 4.255952380952381e-05,
|
| 31 |
+
"loss": 1.0101,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 7.44,
|
| 36 |
+
"learning_rate": 4.0699404761904763e-05,
|
| 37 |
+
"loss": 0.6316,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 8.93,
|
| 42 |
+
"learning_rate": 3.883928571428572e-05,
|
| 43 |
+
"loss": 0.4292,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 10.42,
|
| 48 |
+
"learning_rate": 3.697916666666667e-05,
|
| 49 |
+
"loss": 0.2596,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 11.9,
|
| 54 |
+
"learning_rate": 3.511904761904762e-05,
|
| 55 |
+
"loss": 0.1828,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 13.39,
|
| 60 |
+
"learning_rate": 3.325892857142857e-05,
|
| 61 |
+
"loss": 0.1367,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 14.88,
|
| 66 |
+
"learning_rate": 3.1398809523809525e-05,
|
| 67 |
+
"loss": 0.0986,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 16.37,
|
| 72 |
+
"learning_rate": 2.953869047619048e-05,
|
| 73 |
+
"loss": 0.0818,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 17.86,
|
| 78 |
+
"learning_rate": 2.767857142857143e-05,
|
| 79 |
+
"loss": 0.0581,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 19.35,
|
| 84 |
+
"learning_rate": 2.5818452380952386e-05,
|
| 85 |
+
"loss": 0.0502,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 20.83,
|
| 90 |
+
"learning_rate": 2.3958333333333334e-05,
|
| 91 |
+
"loss": 0.0445,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 22.32,
|
| 96 |
+
"learning_rate": 2.2098214285714286e-05,
|
| 97 |
+
"loss": 0.036,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 23.81,
|
| 102 |
+
"learning_rate": 2.023809523809524e-05,
|
| 103 |
+
"loss": 0.0291,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 25.3,
|
| 108 |
+
"learning_rate": 1.8377976190476192e-05,
|
| 109 |
+
"loss": 0.0371,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 26.79,
|
| 114 |
+
"learning_rate": 1.6517857142857144e-05,
|
| 115 |
+
"loss": 0.0204,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 28.27,
|
| 120 |
+
"learning_rate": 1.4657738095238097e-05,
|
| 121 |
+
"loss": 0.0181,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 29.76,
|
| 126 |
+
"learning_rate": 1.2797619047619047e-05,
|
| 127 |
+
"loss": 0.0156,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 31.25,
|
| 132 |
+
"learning_rate": 1.09375e-05,
|
| 133 |
+
"loss": 0.013,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 32.74,
|
| 138 |
+
"learning_rate": 9.077380952380953e-06,
|
| 139 |
+
"loss": 0.0118,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 34.23,
|
| 144 |
+
"learning_rate": 7.217261904761905e-06,
|
| 145 |
+
"loss": 0.009,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 35.71,
|
| 150 |
+
"learning_rate": 5.357142857142857e-06,
|
| 151 |
+
"loss": 0.0079,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 37.2,
|
| 156 |
+
"learning_rate": 3.49702380952381e-06,
|
| 157 |
+
"loss": 0.0082,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 38.69,
|
| 162 |
+
"learning_rate": 1.636904761904762e-06,
|
| 163 |
+
"loss": 0.0084,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 40.0,
|
| 168 |
+
"step": 13440,
|
| 169 |
+
"total_flos": 2.659014067347456e+16,
|
| 170 |
+
"train_loss": 0.3552576902189425,
|
| 171 |
+
"train_runtime": 12919.7128,
|
| 172 |
+
"train_samples_per_second": 10.403,
|
| 173 |
+
"train_steps_per_second": 1.04
|
| 174 |
+
}
|
| 175 |
+
],
|
| 176 |
+
"max_steps": 13440,
|
| 177 |
+
"num_train_epochs": 40,
|
| 178 |
+
"total_flos": 2.659014067347456e+16,
|
| 179 |
+
"trial_name": null,
|
| 180 |
+
"trial_params": null
|
| 181 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0150239dd9875ee30a1f882e34aca0c189797c359a4b886dc762d0bc41d73fb3
|
| 3 |
+
size 3503
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|