Upload 6 files
Browse files- scheduler.pt +3 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- tokenizer_config.json +112 -0
- trainer_state.json +316 -0
- training_args.bin +3 -0
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68f74a41e34e76db3f5bd921a21812d8f8950b1dfdb2838bbd9ffc573736a880
|
| 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:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
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": 512,
|
| 108 |
+
"pad_token": "<pad>",
|
| 109 |
+
"sp_model_kwargs": {},
|
| 110 |
+
"tokenizer_class": "T5Tokenizer",
|
| 111 |
+
"unk_token": "<unk>"
|
| 112 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,316 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.88,
|
| 5 |
+
"global_step": 9000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.96,
|
| 12 |
+
"learning_rate": 6.805111821086262e-05,
|
| 13 |
+
"loss": 0.8467,
|
| 14 |
+
"step": 300
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.96,
|
| 18 |
+
"eval_loss": 11.306694030761719,
|
| 19 |
+
"eval_meteor": 0,
|
| 20 |
+
"eval_runtime": 15.5559,
|
| 21 |
+
"eval_samples_per_second": 6.428,
|
| 22 |
+
"eval_steps_per_second": 0.45,
|
| 23 |
+
"step": 300
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.92,
|
| 27 |
+
"learning_rate": 3.610223642172524e-05,
|
| 28 |
+
"loss": 0.2373,
|
| 29 |
+
"step": 600
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.92,
|
| 33 |
+
"eval_loss": 11.511818885803223,
|
| 34 |
+
"eval_meteor": 0,
|
| 35 |
+
"eval_runtime": 13.8771,
|
| 36 |
+
"eval_samples_per_second": 7.206,
|
| 37 |
+
"eval_steps_per_second": 0.504,
|
| 38 |
+
"step": 600
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.88,
|
| 42 |
+
"learning_rate": 4.153354632587859e-06,
|
| 43 |
+
"loss": 0.2084,
|
| 44 |
+
"step": 900
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.88,
|
| 48 |
+
"eval_loss": 11.402015686035156,
|
| 49 |
+
"eval_meteor": 0,
|
| 50 |
+
"eval_runtime": 13.9339,
|
| 51 |
+
"eval_samples_per_second": 7.177,
|
| 52 |
+
"eval_steps_per_second": 0.502,
|
| 53 |
+
"step": 900
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.32,
|
| 57 |
+
"learning_rate": 8.933333333333334e-05,
|
| 58 |
+
"loss": 0.2015,
|
| 59 |
+
"step": 1000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.32,
|
| 63 |
+
"eval_loss": 10.56881332397461,
|
| 64 |
+
"eval_meteor": 0.0,
|
| 65 |
+
"eval_runtime": 14.4237,
|
| 66 |
+
"eval_samples_per_second": 6.933,
|
| 67 |
+
"eval_steps_per_second": 0.485,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.48,
|
| 72 |
+
"learning_rate": 8.4e-05,
|
| 73 |
+
"loss": 0.1958,
|
| 74 |
+
"step": 1500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.48,
|
| 78 |
+
"eval_loss": 11.447636604309082,
|
| 79 |
+
"eval_meteor": 0.0,
|
| 80 |
+
"eval_runtime": 12.9601,
|
| 81 |
+
"eval_samples_per_second": 7.716,
|
| 82 |
+
"eval_steps_per_second": 0.54,
|
| 83 |
+
"step": 1500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.64,
|
| 87 |
+
"learning_rate": 7.866666666666666e-05,
|
| 88 |
+
"loss": 0.1921,
|
| 89 |
+
"step": 2000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.64,
|
| 93 |
+
"eval_loss": 11.779410362243652,
|
| 94 |
+
"eval_meteor": 0.0,
|
| 95 |
+
"eval_runtime": 12.9944,
|
| 96 |
+
"eval_samples_per_second": 7.696,
|
| 97 |
+
"eval_steps_per_second": 0.539,
|
| 98 |
+
"step": 2000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.8,
|
| 102 |
+
"learning_rate": 7.333333333333333e-05,
|
| 103 |
+
"loss": 0.189,
|
| 104 |
+
"step": 2500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.8,
|
| 108 |
+
"eval_loss": 11.277334213256836,
|
| 109 |
+
"eval_meteor": 0.0,
|
| 110 |
+
"eval_runtime": 13.0206,
|
| 111 |
+
"eval_samples_per_second": 7.68,
|
| 112 |
+
"eval_steps_per_second": 0.538,
|
| 113 |
+
"step": 2500
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.96,
|
| 117 |
+
"learning_rate": 6.800000000000001e-05,
|
| 118 |
+
"loss": 0.1831,
|
| 119 |
+
"step": 3000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.96,
|
| 123 |
+
"eval_loss": 12.441211700439453,
|
| 124 |
+
"eval_meteor": 0.0,
|
| 125 |
+
"eval_runtime": 13.1556,
|
| 126 |
+
"eval_samples_per_second": 7.601,
|
| 127 |
+
"eval_steps_per_second": 0.532,
|
| 128 |
+
"step": 3000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.12,
|
| 132 |
+
"learning_rate": 6.266666666666667e-05,
|
| 133 |
+
"loss": 0.1679,
|
| 134 |
+
"step": 3500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.12,
|
| 138 |
+
"eval_loss": 11.94626235961914,
|
| 139 |
+
"eval_meteor": 0.0,
|
| 140 |
+
"eval_runtime": 13.0053,
|
| 141 |
+
"eval_samples_per_second": 7.689,
|
| 142 |
+
"eval_steps_per_second": 0.538,
|
| 143 |
+
"step": 3500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.28,
|
| 147 |
+
"learning_rate": 5.7333333333333336e-05,
|
| 148 |
+
"loss": 0.1653,
|
| 149 |
+
"step": 4000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.28,
|
| 153 |
+
"eval_loss": 11.814840316772461,
|
| 154 |
+
"eval_meteor": 0.0,
|
| 155 |
+
"eval_runtime": 13.0463,
|
| 156 |
+
"eval_samples_per_second": 7.665,
|
| 157 |
+
"eval_steps_per_second": 0.537,
|
| 158 |
+
"step": 4000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.44,
|
| 162 |
+
"learning_rate": 5.2000000000000004e-05,
|
| 163 |
+
"loss": 0.1644,
|
| 164 |
+
"step": 4500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.44,
|
| 168 |
+
"eval_loss": 12.166290283203125,
|
| 169 |
+
"eval_meteor": 0.0,
|
| 170 |
+
"eval_runtime": 13.0378,
|
| 171 |
+
"eval_samples_per_second": 7.67,
|
| 172 |
+
"eval_steps_per_second": 0.537,
|
| 173 |
+
"step": 4500
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.6,
|
| 177 |
+
"learning_rate": 4.666666666666667e-05,
|
| 178 |
+
"loss": 0.1642,
|
| 179 |
+
"step": 5000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.6,
|
| 183 |
+
"eval_loss": 11.968828201293945,
|
| 184 |
+
"eval_meteor": 0.0,
|
| 185 |
+
"eval_runtime": 12.9985,
|
| 186 |
+
"eval_samples_per_second": 7.693,
|
| 187 |
+
"eval_steps_per_second": 0.539,
|
| 188 |
+
"step": 5000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.76,
|
| 192 |
+
"learning_rate": 4.133333333333333e-05,
|
| 193 |
+
"loss": 0.1641,
|
| 194 |
+
"step": 5500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.76,
|
| 198 |
+
"eval_loss": 12.146567344665527,
|
| 199 |
+
"eval_meteor": 0.0,
|
| 200 |
+
"eval_runtime": 13.0609,
|
| 201 |
+
"eval_samples_per_second": 7.656,
|
| 202 |
+
"eval_steps_per_second": 0.536,
|
| 203 |
+
"step": 5500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.92,
|
| 207 |
+
"learning_rate": 3.6e-05,
|
| 208 |
+
"loss": 0.1633,
|
| 209 |
+
"step": 6000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.92,
|
| 213 |
+
"eval_loss": 12.101709365844727,
|
| 214 |
+
"eval_meteor": 0.0,
|
| 215 |
+
"eval_runtime": 13.0856,
|
| 216 |
+
"eval_samples_per_second": 7.642,
|
| 217 |
+
"eval_steps_per_second": 0.535,
|
| 218 |
+
"step": 6000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.08,
|
| 222 |
+
"learning_rate": 3.066666666666667e-05,
|
| 223 |
+
"loss": 0.1525,
|
| 224 |
+
"step": 6500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.08,
|
| 228 |
+
"eval_loss": 12.363394737243652,
|
| 229 |
+
"eval_meteor": 0.0,
|
| 230 |
+
"eval_runtime": 13.5503,
|
| 231 |
+
"eval_samples_per_second": 7.38,
|
| 232 |
+
"eval_steps_per_second": 0.517,
|
| 233 |
+
"step": 6500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.24,
|
| 237 |
+
"learning_rate": 2.5333333333333337e-05,
|
| 238 |
+
"loss": 0.1434,
|
| 239 |
+
"step": 7000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.24,
|
| 243 |
+
"eval_loss": 12.543970108032227,
|
| 244 |
+
"eval_meteor": 0.0,
|
| 245 |
+
"eval_runtime": 13.9628,
|
| 246 |
+
"eval_samples_per_second": 7.162,
|
| 247 |
+
"eval_steps_per_second": 0.501,
|
| 248 |
+
"step": 7000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.4,
|
| 252 |
+
"learning_rate": 2e-05,
|
| 253 |
+
"loss": 0.1456,
|
| 254 |
+
"step": 7500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.4,
|
| 258 |
+
"eval_loss": 12.349944114685059,
|
| 259 |
+
"eval_meteor": 0.0,
|
| 260 |
+
"eval_runtime": 13.1423,
|
| 261 |
+
"eval_samples_per_second": 7.609,
|
| 262 |
+
"eval_steps_per_second": 0.533,
|
| 263 |
+
"step": 7500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.56,
|
| 267 |
+
"learning_rate": 1.4666666666666668e-05,
|
| 268 |
+
"loss": 0.1437,
|
| 269 |
+
"step": 8000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.56,
|
| 273 |
+
"eval_loss": 12.369497299194336,
|
| 274 |
+
"eval_meteor": 0.0,
|
| 275 |
+
"eval_runtime": 13.3304,
|
| 276 |
+
"eval_samples_per_second": 7.502,
|
| 277 |
+
"eval_steps_per_second": 0.525,
|
| 278 |
+
"step": 8000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.72,
|
| 282 |
+
"learning_rate": 9.333333333333334e-06,
|
| 283 |
+
"loss": 0.1414,
|
| 284 |
+
"step": 8500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.72,
|
| 288 |
+
"eval_loss": 12.623024940490723,
|
| 289 |
+
"eval_meteor": 0.0,
|
| 290 |
+
"eval_runtime": 13.0594,
|
| 291 |
+
"eval_samples_per_second": 7.657,
|
| 292 |
+
"eval_steps_per_second": 0.536,
|
| 293 |
+
"step": 8500
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.88,
|
| 297 |
+
"learning_rate": 4.000000000000001e-06,
|
| 298 |
+
"loss": 0.1443,
|
| 299 |
+
"step": 9000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.88,
|
| 303 |
+
"eval_loss": 12.473442077636719,
|
| 304 |
+
"eval_meteor": 0.0,
|
| 305 |
+
"eval_runtime": 13.0574,
|
| 306 |
+
"eval_samples_per_second": 7.659,
|
| 307 |
+
"eval_steps_per_second": 0.536,
|
| 308 |
+
"step": 9000
|
| 309 |
+
}
|
| 310 |
+
],
|
| 311 |
+
"max_steps": 9375,
|
| 312 |
+
"num_train_epochs": 3,
|
| 313 |
+
"total_flos": 3.11732169867264e+17,
|
| 314 |
+
"trial_name": null,
|
| 315 |
+
"trial_params": null
|
| 316 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b51d71518cc5295a6f9e9fd602d8514ca5292b220f078fa12785a46362a077cb
|
| 3 |
+
size 4027
|