Upload 12 files
Browse filesAdding first files.
- all_results.json +23 -0
- config.json +38 -0
- eval_results.json +10 -0
- generation_config.json +11 -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 +115 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_bleu": 28.5377,
|
| 4 |
+
"eval_gen_len": 34.2604,
|
| 5 |
+
"eval_loss": 1.8521575927734375,
|
| 6 |
+
"eval_runtime": 584.9245,
|
| 7 |
+
"eval_samples": 1513,
|
| 8 |
+
"eval_samples_per_second": 2.587,
|
| 9 |
+
"eval_steps_per_second": 0.648,
|
| 10 |
+
"predict_bleu": 28.7245,
|
| 11 |
+
"predict_gen_len": 34.8057,
|
| 12 |
+
"predict_loss": 1.8454431295394897,
|
| 13 |
+
"predict_runtime": 1207.8207,
|
| 14 |
+
"predict_samples": 3027,
|
| 15 |
+
"predict_samples_per_second": 2.506,
|
| 16 |
+
"predict_steps_per_second": 0.627,
|
| 17 |
+
"total_flos": 5838088796626944.0,
|
| 18 |
+
"train_loss": 1.867107309785279,
|
| 19 |
+
"train_runtime": 3985.5921,
|
| 20 |
+
"train_samples": 10599,
|
| 21 |
+
"train_samples_per_second": 7.978,
|
| 22 |
+
"train_steps_per_second": 1.995
|
| 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": 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": "4.26.0",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 128112
|
| 38 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_bleu": 28.5377,
|
| 4 |
+
"eval_gen_len": 34.2604,
|
| 5 |
+
"eval_loss": 1.8521575927734375,
|
| 6 |
+
"eval_runtime": 584.9245,
|
| 7 |
+
"eval_samples": 1513,
|
| 8 |
+
"eval_samples_per_second": 2.587,
|
| 9 |
+
"eval_steps_per_second": 0.648
|
| 10 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"max_length": 200,
|
| 8 |
+
"num_beams": 5,
|
| 9 |
+
"pad_token_id": 1,
|
| 10 |
+
"transformers_version": "4.26.0"
|
| 11 |
+
}
|
predict_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_bleu": 28.7245,
|
| 3 |
+
"predict_gen_len": 34.8057,
|
| 4 |
+
"predict_loss": 1.8454431295394897,
|
| 5 |
+
"predict_runtime": 1207.8207,
|
| 6 |
+
"predict_samples": 3027,
|
| 7 |
+
"predict_samples_per_second": 2.506,
|
| 8 |
+
"predict_steps_per_second": 0.627
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac7eed8f3a9de8cda070890ac492e30363cb87d43fb17f20f9c481bd14411fc3
|
| 3 |
+
size 1944201353
|
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": 3.0,
|
| 3 |
+
"total_flos": 5838088796626944.0,
|
| 4 |
+
"train_loss": 1.867107309785279,
|
| 5 |
+
"train_runtime": 3985.5921,
|
| 6 |
+
"train_samples": 10599,
|
| 7 |
+
"train_samples_per_second": 7.978,
|
| 8 |
+
"train_steps_per_second": 1.995
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 7950,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.19,
|
| 12 |
+
"learning_rate": 4.685534591194969e-05,
|
| 13 |
+
"loss": 3.2357,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.38,
|
| 18 |
+
"learning_rate": 4.3710691823899376e-05,
|
| 19 |
+
"loss": 2.6834,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.57,
|
| 24 |
+
"learning_rate": 4.0566037735849064e-05,
|
| 25 |
+
"loss": 2.4737,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.75,
|
| 30 |
+
"learning_rate": 3.7421383647798744e-05,
|
| 31 |
+
"loss": 2.3981,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.94,
|
| 36 |
+
"learning_rate": 3.4276729559748424e-05,
|
| 37 |
+
"loss": 2.2355,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.13,
|
| 42 |
+
"learning_rate": 3.113207547169811e-05,
|
| 43 |
+
"loss": 1.9009,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.32,
|
| 48 |
+
"learning_rate": 2.7987421383647798e-05,
|
| 49 |
+
"loss": 1.7445,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.51,
|
| 54 |
+
"learning_rate": 2.4842767295597485e-05,
|
| 55 |
+
"loss": 1.7823,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.7,
|
| 60 |
+
"learning_rate": 2.1698113207547172e-05,
|
| 61 |
+
"loss": 1.7014,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.89,
|
| 66 |
+
"learning_rate": 1.8553459119496856e-05,
|
| 67 |
+
"loss": 1.7119,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 2.08,
|
| 72 |
+
"learning_rate": 1.540880503144654e-05,
|
| 73 |
+
"loss": 1.4952,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.26,
|
| 78 |
+
"learning_rate": 1.2264150943396227e-05,
|
| 79 |
+
"loss": 1.2917,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.45,
|
| 84 |
+
"learning_rate": 9.119496855345912e-06,
|
| 85 |
+
"loss": 1.2734,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.64,
|
| 90 |
+
"learning_rate": 5.974842767295598e-06,
|
| 91 |
+
"loss": 1.3188,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.83,
|
| 96 |
+
"learning_rate": 2.830188679245283e-06,
|
| 97 |
+
"loss": 1.2928,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 3.0,
|
| 102 |
+
"step": 7950,
|
| 103 |
+
"total_flos": 5838088796626944.0,
|
| 104 |
+
"train_loss": 1.867107309785279,
|
| 105 |
+
"train_runtime": 3985.5921,
|
| 106 |
+
"train_samples_per_second": 7.978,
|
| 107 |
+
"train_steps_per_second": 1.995
|
| 108 |
+
}
|
| 109 |
+
],
|
| 110 |
+
"max_steps": 7950,
|
| 111 |
+
"num_train_epochs": 3,
|
| 112 |
+
"total_flos": 5838088796626944.0,
|
| 113 |
+
"trial_name": null,
|
| 114 |
+
"trial_params": null
|
| 115 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4174d6e765c92a608cd6d04eafa7d1c0f8db078ca3a1f3e1fd131519fdd83c9d
|
| 3 |
+
size 3643
|