Upload folder using huggingface_hub
Browse files- config.json +33 -0
- generation_config.json +6 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +112 -0
- trainer_state.json +592 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "cjvt/t5-sl-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2816,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 1024,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.0,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"gradient_checkpointing": false,
|
| 16 |
+
"initializer_factor": 1.0,
|
| 17 |
+
"is_encoder_decoder": true,
|
| 18 |
+
"is_gated_act": true,
|
| 19 |
+
"layer_norm_epsilon": 1e-06,
|
| 20 |
+
"model_type": "t5",
|
| 21 |
+
"num_decoder_layers": 24,
|
| 22 |
+
"num_heads": 16,
|
| 23 |
+
"num_layers": 24,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.32.0.dev0",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32000
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.32.0.dev0"
|
| 6 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b3f0c66390bc367ba8bd35e8105e909f901a2185e4a6e7c7b9135d77abde510
|
| 3 |
+
size 5775789
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad959a1da947497ce1fe3091913fe35c110de97115335383888e4d3041a1b9a5
|
| 3 |
+
size 3131745093
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2233b71d28d82b8331de6224e1abb884bd9108ce746c680fd1c4d641c935668
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42270aa7fa99e9331dd44c709eb637ca9200f2099943a99f905d7cbfd140aefb
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
| 107 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79e3205b5a25b7a3b6fa48ea60d1c71d3b0f7adbaeb1d58949b04f8454946465
|
| 3 |
+
size 797053
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"clean_up_tokenization_spaces": true,
|
| 105 |
+
"eos_token": "</s>",
|
| 106 |
+
"extra_ids": 100,
|
| 107 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 108 |
+
"pad_token": "<pad>",
|
| 109 |
+
"sp_model_kwargs": {},
|
| 110 |
+
"tokenizer_class": "T5Tokenizer",
|
| 111 |
+
"unk_token": "<unk>"
|
| 112 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,592 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8388484120368958,
|
| 3 |
+
"best_model_checkpoint": "/d/hpc/projects/FRI/bb6846/run11//t5-sl-large/checkpoint-5541",
|
| 4 |
+
"epoch": 17.999729327378535,
|
| 5 |
+
"global_step": 33250,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.27,
|
| 12 |
+
"learning_rate": 0.0004966161342717921,
|
| 13 |
+
"loss": 1.5149,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.54,
|
| 18 |
+
"learning_rate": 0.0004932322685435842,
|
| 19 |
+
"loss": 1.2852,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.81,
|
| 24 |
+
"learning_rate": 0.0004898484028153763,
|
| 25 |
+
"loss": 1.1548,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.0,
|
| 30 |
+
"eval_LaBSE similarity": 0.6812127827302594,
|
| 31 |
+
"eval_bleu": 0.26085685311843865,
|
| 32 |
+
"eval_loss": 1.030735969543457,
|
| 33 |
+
"eval_runtime": 1202.6717,
|
| 34 |
+
"eval_samples_per_second": 11.621,
|
| 35 |
+
"eval_steps_per_second": 0.727,
|
| 36 |
+
"step": 1847
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.08,
|
| 40 |
+
"learning_rate": 0.00048646453708716834,
|
| 41 |
+
"loss": 0.9389,
|
| 42 |
+
"step": 2000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.35,
|
| 46 |
+
"learning_rate": 0.0004830806713589605,
|
| 47 |
+
"loss": 0.6595,
|
| 48 |
+
"step": 2500
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 1.62,
|
| 52 |
+
"learning_rate": 0.0004796968056307526,
|
| 53 |
+
"loss": 0.6495,
|
| 54 |
+
"step": 3000
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.89,
|
| 58 |
+
"learning_rate": 0.00047631293990254463,
|
| 59 |
+
"loss": 0.6266,
|
| 60 |
+
"step": 3500
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 2.0,
|
| 64 |
+
"eval_LaBSE similarity": 0.6908316853313329,
|
| 65 |
+
"eval_bleu": 0.2815949228649396,
|
| 66 |
+
"eval_loss": 0.8447950482368469,
|
| 67 |
+
"eval_runtime": 1213.9058,
|
| 68 |
+
"eval_samples_per_second": 11.513,
|
| 69 |
+
"eval_steps_per_second": 0.72,
|
| 70 |
+
"step": 3694
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 2.17,
|
| 74 |
+
"learning_rate": 0.0004729290741743368,
|
| 75 |
+
"loss": 0.4401,
|
| 76 |
+
"step": 4000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 2.44,
|
| 80 |
+
"learning_rate": 0.0004695452084461289,
|
| 81 |
+
"loss": 0.3565,
|
| 82 |
+
"step": 4500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 2.71,
|
| 86 |
+
"learning_rate": 0.000466161342717921,
|
| 87 |
+
"loss": 0.3761,
|
| 88 |
+
"step": 5000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.98,
|
| 92 |
+
"learning_rate": 0.00046277747698971307,
|
| 93 |
+
"loss": 0.383,
|
| 94 |
+
"step": 5500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 3.0,
|
| 98 |
+
"eval_LaBSE similarity": 0.6995571957101206,
|
| 99 |
+
"eval_bleu": 0.29809786923507614,
|
| 100 |
+
"eval_loss": 0.8388484120368958,
|
| 101 |
+
"eval_runtime": 1199.9823,
|
| 102 |
+
"eval_samples_per_second": 11.647,
|
| 103 |
+
"eval_steps_per_second": 0.728,
|
| 104 |
+
"step": 5541
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 3.25,
|
| 108 |
+
"learning_rate": 0.0004593936112615051,
|
| 109 |
+
"loss": 0.2344,
|
| 110 |
+
"step": 6000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.52,
|
| 114 |
+
"learning_rate": 0.00045600974553329727,
|
| 115 |
+
"loss": 0.2454,
|
| 116 |
+
"step": 6500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.79,
|
| 120 |
+
"learning_rate": 0.00045262587980508936,
|
| 121 |
+
"loss": 0.2646,
|
| 122 |
+
"step": 7000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 4.0,
|
| 126 |
+
"eval_LaBSE similarity": 0.6979512369452641,
|
| 127 |
+
"eval_bleu": 0.2997067254948018,
|
| 128 |
+
"eval_loss": 0.8804282546043396,
|
| 129 |
+
"eval_runtime": 1204.2265,
|
| 130 |
+
"eval_samples_per_second": 11.606,
|
| 131 |
+
"eval_steps_per_second": 0.726,
|
| 132 |
+
"step": 7389
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 4.06,
|
| 136 |
+
"learning_rate": 0.0004492420140768814,
|
| 137 |
+
"loss": 0.2489,
|
| 138 |
+
"step": 7500
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.33,
|
| 142 |
+
"learning_rate": 0.00044585814834867355,
|
| 143 |
+
"loss": 0.18,
|
| 144 |
+
"step": 8000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 4.6,
|
| 148 |
+
"learning_rate": 0.00044247428262046565,
|
| 149 |
+
"loss": 0.1993,
|
| 150 |
+
"step": 8500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 4.87,
|
| 154 |
+
"learning_rate": 0.0004390904168922577,
|
| 155 |
+
"loss": 0.2131,
|
| 156 |
+
"step": 9000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 5.0,
|
| 160 |
+
"eval_LaBSE similarity": 0.7007296268536876,
|
| 161 |
+
"eval_bleu": 0.3013868679121285,
|
| 162 |
+
"eval_loss": 0.9110961556434631,
|
| 163 |
+
"eval_runtime": 1215.4225,
|
| 164 |
+
"eval_samples_per_second": 11.499,
|
| 165 |
+
"eval_steps_per_second": 0.719,
|
| 166 |
+
"step": 9236
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 5.14,
|
| 170 |
+
"learning_rate": 0.00043570655116404984,
|
| 171 |
+
"loss": 0.178,
|
| 172 |
+
"step": 9500
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 5.41,
|
| 176 |
+
"learning_rate": 0.0004323226854358419,
|
| 177 |
+
"loss": 0.1556,
|
| 178 |
+
"step": 10000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 5.68,
|
| 182 |
+
"learning_rate": 0.000428938819707634,
|
| 183 |
+
"loss": 0.1717,
|
| 184 |
+
"step": 10500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 5.95,
|
| 188 |
+
"learning_rate": 0.00042555495397942613,
|
| 189 |
+
"loss": 0.1837,
|
| 190 |
+
"step": 11000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 6.0,
|
| 194 |
+
"eval_LaBSE similarity": 0.7018732900689151,
|
| 195 |
+
"eval_bleu": 0.3018978141259116,
|
| 196 |
+
"eval_loss": 0.9366760849952698,
|
| 197 |
+
"eval_runtime": 1203.8978,
|
| 198 |
+
"eval_samples_per_second": 11.609,
|
| 199 |
+
"eval_steps_per_second": 0.726,
|
| 200 |
+
"step": 11083
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 6.23,
|
| 204 |
+
"learning_rate": 0.0004221710882512182,
|
| 205 |
+
"loss": 0.1369,
|
| 206 |
+
"step": 11500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 6.5,
|
| 210 |
+
"learning_rate": 0.00041878722252301027,
|
| 211 |
+
"loss": 0.1428,
|
| 212 |
+
"step": 12000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 6.77,
|
| 216 |
+
"learning_rate": 0.0004154033567948024,
|
| 217 |
+
"loss": 0.1566,
|
| 218 |
+
"step": 12500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 7.0,
|
| 222 |
+
"eval_LaBSE similarity": 0.702976470663088,
|
| 223 |
+
"eval_bleu": 0.30368208309669026,
|
| 224 |
+
"eval_loss": 1.0034101009368896,
|
| 225 |
+
"eval_runtime": 1207.5273,
|
| 226 |
+
"eval_samples_per_second": 11.574,
|
| 227 |
+
"eval_steps_per_second": 0.724,
|
| 228 |
+
"step": 12930
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 7.04,
|
| 232 |
+
"learning_rate": 0.00041201949106659447,
|
| 233 |
+
"loss": 0.1566,
|
| 234 |
+
"step": 13000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 7.31,
|
| 238 |
+
"learning_rate": 0.0004086356253383866,
|
| 239 |
+
"loss": 0.1192,
|
| 240 |
+
"step": 13500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 7.58,
|
| 244 |
+
"learning_rate": 0.00040525175961017866,
|
| 245 |
+
"loss": 0.1323,
|
| 246 |
+
"step": 14000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 7.85,
|
| 250 |
+
"learning_rate": 0.00040186789388197076,
|
| 251 |
+
"loss": 0.1431,
|
| 252 |
+
"step": 14500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 8.0,
|
| 256 |
+
"eval_LaBSE similarity": 0.7013175535222604,
|
| 257 |
+
"eval_bleu": 0.3049308476119818,
|
| 258 |
+
"eval_loss": 1.0045561790466309,
|
| 259 |
+
"eval_runtime": 1204.442,
|
| 260 |
+
"eval_samples_per_second": 11.604,
|
| 261 |
+
"eval_steps_per_second": 0.726,
|
| 262 |
+
"step": 14778
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 8.12,
|
| 266 |
+
"learning_rate": 0.0003984840281537629,
|
| 267 |
+
"loss": 0.1289,
|
| 268 |
+
"step": 15000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 8.39,
|
| 272 |
+
"learning_rate": 0.00039510016242555495,
|
| 273 |
+
"loss": 0.1114,
|
| 274 |
+
"step": 15500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 8.66,
|
| 278 |
+
"learning_rate": 0.00039171629669734704,
|
| 279 |
+
"loss": 0.1252,
|
| 280 |
+
"step": 16000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 8.93,
|
| 284 |
+
"learning_rate": 0.0003883324309691392,
|
| 285 |
+
"loss": 0.1341,
|
| 286 |
+
"step": 16500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 9.0,
|
| 290 |
+
"eval_LaBSE similarity": 0.7028801773059591,
|
| 291 |
+
"eval_bleu": 0.3060926268506286,
|
| 292 |
+
"eval_loss": 0.9563193917274475,
|
| 293 |
+
"eval_runtime": 1204.9532,
|
| 294 |
+
"eval_samples_per_second": 11.599,
|
| 295 |
+
"eval_steps_per_second": 0.725,
|
| 296 |
+
"step": 16625
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 9.2,
|
| 300 |
+
"learning_rate": 0.00038494856524093124,
|
| 301 |
+
"loss": 0.1083,
|
| 302 |
+
"step": 17000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 9.47,
|
| 306 |
+
"learning_rate": 0.00038156469951272333,
|
| 307 |
+
"loss": 0.1099,
|
| 308 |
+
"step": 17500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 9.74,
|
| 312 |
+
"learning_rate": 0.00037818083378451543,
|
| 313 |
+
"loss": 0.1206,
|
| 314 |
+
"step": 18000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 10.0,
|
| 318 |
+
"eval_LaBSE similarity": 0.7016379604564951,
|
| 319 |
+
"eval_bleu": 0.3033423466794905,
|
| 320 |
+
"eval_loss": 1.041945219039917,
|
| 321 |
+
"eval_runtime": 1201.5959,
|
| 322 |
+
"eval_samples_per_second": 11.631,
|
| 323 |
+
"eval_steps_per_second": 0.727,
|
| 324 |
+
"step": 18472
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 10.01,
|
| 328 |
+
"learning_rate": 0.0003747969680563075,
|
| 329 |
+
"loss": 0.125,
|
| 330 |
+
"step": 18500
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 10.29,
|
| 334 |
+
"learning_rate": 0.0003714131023280996,
|
| 335 |
+
"loss": 0.0938,
|
| 336 |
+
"step": 19000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 10.56,
|
| 340 |
+
"learning_rate": 0.0003680292365998917,
|
| 341 |
+
"loss": 0.1063,
|
| 342 |
+
"step": 19500
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 10.83,
|
| 346 |
+
"learning_rate": 0.0003646453708716838,
|
| 347 |
+
"loss": 0.1157,
|
| 348 |
+
"step": 20000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 11.0,
|
| 352 |
+
"eval_LaBSE similarity": 0.7031656672306994,
|
| 353 |
+
"eval_bleu": 0.304420237465134,
|
| 354 |
+
"eval_loss": 1.0878944396972656,
|
| 355 |
+
"eval_runtime": 1198.7547,
|
| 356 |
+
"eval_samples_per_second": 11.659,
|
| 357 |
+
"eval_steps_per_second": 0.729,
|
| 358 |
+
"step": 20319
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 11.1,
|
| 362 |
+
"learning_rate": 0.0003612615051434759,
|
| 363 |
+
"loss": 0.1069,
|
| 364 |
+
"step": 20500
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 11.37,
|
| 368 |
+
"learning_rate": 0.000357877639415268,
|
| 369 |
+
"loss": 0.0938,
|
| 370 |
+
"step": 21000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 11.64,
|
| 374 |
+
"learning_rate": 0.0003544937736870601,
|
| 375 |
+
"loss": 0.1029,
|
| 376 |
+
"step": 21500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 11.91,
|
| 380 |
+
"learning_rate": 0.0003511099079588522,
|
| 381 |
+
"loss": 0.1095,
|
| 382 |
+
"step": 22000
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 12.0,
|
| 386 |
+
"eval_LaBSE similarity": 0.7013727569331282,
|
| 387 |
+
"eval_bleu": 0.3008776228703018,
|
| 388 |
+
"eval_loss": 1.091700553894043,
|
| 389 |
+
"eval_runtime": 1199.6915,
|
| 390 |
+
"eval_samples_per_second": 11.65,
|
| 391 |
+
"eval_steps_per_second": 0.729,
|
| 392 |
+
"step": 22167
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 12.18,
|
| 396 |
+
"learning_rate": 0.0003477260422306443,
|
| 397 |
+
"loss": 0.0931,
|
| 398 |
+
"step": 22500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 12.45,
|
| 402 |
+
"learning_rate": 0.0003443421765024364,
|
| 403 |
+
"loss": 0.0913,
|
| 404 |
+
"step": 23000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 12.72,
|
| 408 |
+
"learning_rate": 0.0003409583107742285,
|
| 409 |
+
"loss": 0.1011,
|
| 410 |
+
"step": 23500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 12.99,
|
| 414 |
+
"learning_rate": 0.0003375744450460206,
|
| 415 |
+
"loss": 0.106,
|
| 416 |
+
"step": 24000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 13.0,
|
| 420 |
+
"eval_LaBSE similarity": 0.7020342419015667,
|
| 421 |
+
"eval_bleu": 0.30263173440284996,
|
| 422 |
+
"eval_loss": 1.0771766901016235,
|
| 423 |
+
"eval_runtime": 1201.3264,
|
| 424 |
+
"eval_samples_per_second": 11.634,
|
| 425 |
+
"eval_steps_per_second": 0.728,
|
| 426 |
+
"step": 24014
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 13.26,
|
| 430 |
+
"learning_rate": 0.0003341905793178127,
|
| 431 |
+
"loss": 0.0804,
|
| 432 |
+
"step": 24500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 13.53,
|
| 436 |
+
"learning_rate": 0.0003308067135896048,
|
| 437 |
+
"loss": 0.0895,
|
| 438 |
+
"step": 25000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 13.8,
|
| 442 |
+
"learning_rate": 0.0003274228478613969,
|
| 443 |
+
"loss": 0.0969,
|
| 444 |
+
"step": 25500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 14.0,
|
| 448 |
+
"eval_LaBSE similarity": 0.7029242980227026,
|
| 449 |
+
"eval_bleu": 0.3052818250366099,
|
| 450 |
+
"eval_loss": 1.1355116367340088,
|
| 451 |
+
"eval_runtime": 1215.6829,
|
| 452 |
+
"eval_samples_per_second": 11.496,
|
| 453 |
+
"eval_steps_per_second": 0.719,
|
| 454 |
+
"step": 25861
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 14.07,
|
| 458 |
+
"learning_rate": 0.0003240389821331889,
|
| 459 |
+
"loss": 0.0941,
|
| 460 |
+
"step": 26000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 14.35,
|
| 464 |
+
"learning_rate": 0.00032065511640498107,
|
| 465 |
+
"loss": 0.0791,
|
| 466 |
+
"step": 26500
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 14.62,
|
| 470 |
+
"learning_rate": 0.00031727125067677317,
|
| 471 |
+
"loss": 0.0884,
|
| 472 |
+
"step": 27000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 14.89,
|
| 476 |
+
"learning_rate": 0.0003138873849485652,
|
| 477 |
+
"loss": 0.0937,
|
| 478 |
+
"step": 27500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 15.0,
|
| 482 |
+
"eval_LaBSE similarity": 0.7020669575193156,
|
| 483 |
+
"eval_bleu": 0.30208227926668096,
|
| 484 |
+
"eval_loss": 1.1526124477386475,
|
| 485 |
+
"eval_runtime": 1203.9587,
|
| 486 |
+
"eval_samples_per_second": 11.608,
|
| 487 |
+
"eval_steps_per_second": 0.726,
|
| 488 |
+
"step": 27708
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 15.16,
|
| 492 |
+
"learning_rate": 0.00031050351922035736,
|
| 493 |
+
"loss": 0.0813,
|
| 494 |
+
"step": 28000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 15.43,
|
| 498 |
+
"learning_rate": 0.00030711965349214946,
|
| 499 |
+
"loss": 0.0787,
|
| 500 |
+
"step": 28500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 15.7,
|
| 504 |
+
"learning_rate": 0.0003037357877639415,
|
| 505 |
+
"loss": 0.0869,
|
| 506 |
+
"step": 29000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 15.97,
|
| 510 |
+
"learning_rate": 0.00030035192203573365,
|
| 511 |
+
"loss": 0.0919,
|
| 512 |
+
"step": 29500
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 16.0,
|
| 516 |
+
"eval_LaBSE similarity": 0.7013649646287148,
|
| 517 |
+
"eval_bleu": 0.30275833235224037,
|
| 518 |
+
"eval_loss": 1.1413129568099976,
|
| 519 |
+
"eval_runtime": 1202.6189,
|
| 520 |
+
"eval_samples_per_second": 11.621,
|
| 521 |
+
"eval_steps_per_second": 0.727,
|
| 522 |
+
"step": 29556
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 16.24,
|
| 526 |
+
"learning_rate": 0.0002969680563075257,
|
| 527 |
+
"loss": 0.0712,
|
| 528 |
+
"step": 30000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 16.51,
|
| 532 |
+
"learning_rate": 0.00029358419057931784,
|
| 533 |
+
"loss": 0.0794,
|
| 534 |
+
"step": 30500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 16.78,
|
| 538 |
+
"learning_rate": 0.00029020032485110994,
|
| 539 |
+
"loss": 0.0854,
|
| 540 |
+
"step": 31000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 17.0,
|
| 544 |
+
"eval_LaBSE similarity": 0.7010715400030315,
|
| 545 |
+
"eval_bleu": 0.3027145728229586,
|
| 546 |
+
"eval_loss": 1.162865161895752,
|
| 547 |
+
"eval_runtime": 1202.091,
|
| 548 |
+
"eval_samples_per_second": 11.626,
|
| 549 |
+
"eval_steps_per_second": 0.727,
|
| 550 |
+
"step": 31403
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 17.05,
|
| 554 |
+
"learning_rate": 0.000286816459122902,
|
| 555 |
+
"loss": 0.0833,
|
| 556 |
+
"step": 31500
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 17.32,
|
| 560 |
+
"learning_rate": 0.00028343259339469413,
|
| 561 |
+
"loss": 0.0686,
|
| 562 |
+
"step": 32000
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 17.59,
|
| 566 |
+
"learning_rate": 0.00028004872766648623,
|
| 567 |
+
"loss": 0.0775,
|
| 568 |
+
"step": 32500
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 17.86,
|
| 572 |
+
"learning_rate": 0.00027666486193827827,
|
| 573 |
+
"loss": 0.0828,
|
| 574 |
+
"step": 33000
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 18.0,
|
| 578 |
+
"eval_LaBSE similarity": 0.7000625387362445,
|
| 579 |
+
"eval_bleu": 0.30075415431038816,
|
| 580 |
+
"eval_loss": 1.192597508430481,
|
| 581 |
+
"eval_runtime": 1208.0939,
|
| 582 |
+
"eval_samples_per_second": 11.569,
|
| 583 |
+
"eval_steps_per_second": 0.723,
|
| 584 |
+
"step": 33250
|
| 585 |
+
}
|
| 586 |
+
],
|
| 587 |
+
"max_steps": 73880,
|
| 588 |
+
"num_train_epochs": 40,
|
| 589 |
+
"total_flos": 5.982983397653299e+17,
|
| 590 |
+
"trial_name": null,
|
| 591 |
+
"trial_params": null
|
| 592 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0e2c472b0d1bf9e8f8fb277ab2c6970372827e72cd8157190d06914995ec797
|
| 3 |
+
size 4219
|