Add model
Browse files- config.json +60 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +107 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +111 -0
- trainer_state.json +350 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "t5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 3072,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "relu",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "relu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": false,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "t5",
|
| 19 |
+
"n_positions": 512,
|
| 20 |
+
"num_decoder_layers": 12,
|
| 21 |
+
"num_heads": 12,
|
| 22 |
+
"num_layers": 12,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"task_specific_params": {
|
| 28 |
+
"summarization": {
|
| 29 |
+
"early_stopping": true,
|
| 30 |
+
"length_penalty": 2.0,
|
| 31 |
+
"max_length": 200,
|
| 32 |
+
"min_length": 30,
|
| 33 |
+
"no_repeat_ngram_size": 3,
|
| 34 |
+
"num_beams": 4,
|
| 35 |
+
"prefix": "summarize: "
|
| 36 |
+
},
|
| 37 |
+
"translation_en_to_de": {
|
| 38 |
+
"early_stopping": true,
|
| 39 |
+
"max_length": 300,
|
| 40 |
+
"num_beams": 4,
|
| 41 |
+
"prefix": "translate English to German: "
|
| 42 |
+
},
|
| 43 |
+
"translation_en_to_fr": {
|
| 44 |
+
"early_stopping": true,
|
| 45 |
+
"max_length": 300,
|
| 46 |
+
"num_beams": 4,
|
| 47 |
+
"prefix": "translate English to French: "
|
| 48 |
+
},
|
| 49 |
+
"translation_en_to_ro": {
|
| 50 |
+
"early_stopping": true,
|
| 51 |
+
"max_length": 300,
|
| 52 |
+
"num_beams": 4,
|
| 53 |
+
"prefix": "translate English to Romanian: "
|
| 54 |
+
}
|
| 55 |
+
},
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.27.2",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 32128
|
| 60 |
+
}
|
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": "4.27.2"
|
| 6 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5bd2dfbb9072d1361fc490f35139351645dc8c856ad953f059dc69fe2506437
|
| 3 |
+
size 891702929
|
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.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"extra_ids": 100,
|
| 106 |
+
"model_max_length": 512,
|
| 107 |
+
"pad_token": "<pad>",
|
| 108 |
+
"special_tokens_map_file": null,
|
| 109 |
+
"tokenizer_class": "T5Tokenizer",
|
| 110 |
+
"unk_token": "<unk>"
|
| 111 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,350 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9998730481147645,
|
| 5 |
+
"global_step": 3938,
|
| 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": 7.5e-05,
|
| 13 |
+
"loss": 3.8742,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 0.00015,
|
| 19 |
+
"loss": 1.2473,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.08,
|
| 24 |
+
"learning_rate": 0.000225,
|
| 25 |
+
"loss": 1.1998,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.1,
|
| 30 |
+
"learning_rate": 0.0003,
|
| 31 |
+
"loss": 1.1545,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.13,
|
| 36 |
+
"learning_rate": 0.0002915206331260599,
|
| 37 |
+
"loss": 1.1364,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.13,
|
| 42 |
+
"eval_bleu": 0.17166972696083574,
|
| 43 |
+
"eval_loss": 1.1582657098770142,
|
| 44 |
+
"eval_rouge1": 0.5000074515653312,
|
| 45 |
+
"eval_rouge2": 0.40559916777579735,
|
| 46 |
+
"eval_rougeL": 0.46317379201759545,
|
| 47 |
+
"eval_rougeLsum": 0.4632046447608197,
|
| 48 |
+
"eval_runtime": 211.1462,
|
| 49 |
+
"eval_samples_per_second": 22.226,
|
| 50 |
+
"eval_steps_per_second": 2.78,
|
| 51 |
+
"step": 500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.15,
|
| 55 |
+
"learning_rate": 0.0002830412662521198,
|
| 56 |
+
"loss": 1.1312,
|
| 57 |
+
"step": 600
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.18,
|
| 61 |
+
"learning_rate": 0.0002745618993781798,
|
| 62 |
+
"loss": 1.1164,
|
| 63 |
+
"step": 700
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.2,
|
| 67 |
+
"learning_rate": 0.00026608253250423966,
|
| 68 |
+
"loss": 1.1037,
|
| 69 |
+
"step": 800
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.23,
|
| 73 |
+
"learning_rate": 0.0002576031656302996,
|
| 74 |
+
"loss": 1.1084,
|
| 75 |
+
"step": 900
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.25,
|
| 79 |
+
"learning_rate": 0.00024912379875635947,
|
| 80 |
+
"loss": 1.0874,
|
| 81 |
+
"step": 1000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.25,
|
| 85 |
+
"eval_bleu": 0.174359464623795,
|
| 86 |
+
"eval_loss": 1.1108546257019043,
|
| 87 |
+
"eval_rouge1": 0.5050901535930163,
|
| 88 |
+
"eval_rouge2": 0.41029314654694715,
|
| 89 |
+
"eval_rougeL": 0.4678610312798079,
|
| 90 |
+
"eval_rougeLsum": 0.4679688863086813,
|
| 91 |
+
"eval_runtime": 208.6731,
|
| 92 |
+
"eval_samples_per_second": 22.49,
|
| 93 |
+
"eval_steps_per_second": 2.813,
|
| 94 |
+
"step": 1000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.28,
|
| 98 |
+
"learning_rate": 0.0002406444318824194,
|
| 99 |
+
"loss": 1.0758,
|
| 100 |
+
"step": 1100
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.3,
|
| 104 |
+
"learning_rate": 0.00023216506500847936,
|
| 105 |
+
"loss": 1.0899,
|
| 106 |
+
"step": 1200
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.33,
|
| 110 |
+
"learning_rate": 0.00022368569813453927,
|
| 111 |
+
"loss": 1.0728,
|
| 112 |
+
"step": 1300
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.36,
|
| 116 |
+
"learning_rate": 0.00021520633126059918,
|
| 117 |
+
"loss": 1.0751,
|
| 118 |
+
"step": 1400
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.38,
|
| 122 |
+
"learning_rate": 0.0002067269643866591,
|
| 123 |
+
"loss": 1.072,
|
| 124 |
+
"step": 1500
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.38,
|
| 128 |
+
"eval_bleu": 0.16964536883217013,
|
| 129 |
+
"eval_loss": 1.0908721685409546,
|
| 130 |
+
"eval_rouge1": 0.49944919713548785,
|
| 131 |
+
"eval_rouge2": 0.4041247246204984,
|
| 132 |
+
"eval_rougeL": 0.4622247411282464,
|
| 133 |
+
"eval_rougeLsum": 0.4622259005781699,
|
| 134 |
+
"eval_runtime": 214.1194,
|
| 135 |
+
"eval_samples_per_second": 21.918,
|
| 136 |
+
"eval_steps_per_second": 2.741,
|
| 137 |
+
"step": 1500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.41,
|
| 141 |
+
"learning_rate": 0.00019824759751271905,
|
| 142 |
+
"loss": 1.0601,
|
| 143 |
+
"step": 1600
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.43,
|
| 147 |
+
"learning_rate": 0.00018976823063877895,
|
| 148 |
+
"loss": 1.067,
|
| 149 |
+
"step": 1700
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.46,
|
| 153 |
+
"learning_rate": 0.00018128886376483889,
|
| 154 |
+
"loss": 1.0769,
|
| 155 |
+
"step": 1800
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.48,
|
| 159 |
+
"learning_rate": 0.0001728094968908988,
|
| 160 |
+
"loss": 1.0376,
|
| 161 |
+
"step": 1900
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.51,
|
| 165 |
+
"learning_rate": 0.0001643301300169587,
|
| 166 |
+
"loss": 1.0589,
|
| 167 |
+
"step": 2000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.51,
|
| 171 |
+
"eval_bleu": 0.17592370006590605,
|
| 172 |
+
"eval_loss": 1.0714174509048462,
|
| 173 |
+
"eval_rouge1": 0.5071117469721906,
|
| 174 |
+
"eval_rouge2": 0.412824258369919,
|
| 175 |
+
"eval_rougeL": 0.47019269708823,
|
| 176 |
+
"eval_rougeLsum": 0.4702462880937972,
|
| 177 |
+
"eval_runtime": 208.6946,
|
| 178 |
+
"eval_samples_per_second": 22.487,
|
| 179 |
+
"eval_steps_per_second": 2.813,
|
| 180 |
+
"step": 2000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.53,
|
| 184 |
+
"learning_rate": 0.00015585076314301866,
|
| 185 |
+
"loss": 1.0589,
|
| 186 |
+
"step": 2100
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.56,
|
| 190 |
+
"learning_rate": 0.00014737139626907857,
|
| 191 |
+
"loss": 1.0593,
|
| 192 |
+
"step": 2200
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.58,
|
| 196 |
+
"learning_rate": 0.00013889202939513847,
|
| 197 |
+
"loss": 1.0599,
|
| 198 |
+
"step": 2300
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.61,
|
| 202 |
+
"learning_rate": 0.0001304126625211984,
|
| 203 |
+
"loss": 1.0335,
|
| 204 |
+
"step": 2400
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.63,
|
| 208 |
+
"learning_rate": 0.00012193329564725833,
|
| 209 |
+
"loss": 1.0441,
|
| 210 |
+
"step": 2500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.63,
|
| 214 |
+
"eval_bleu": 0.16827637557044198,
|
| 215 |
+
"eval_loss": 1.0615065097808838,
|
| 216 |
+
"eval_rouge1": 0.500508116585923,
|
| 217 |
+
"eval_rouge2": 0.40524827339523467,
|
| 218 |
+
"eval_rougeL": 0.46325896066513017,
|
| 219 |
+
"eval_rougeLsum": 0.4633425344363471,
|
| 220 |
+
"eval_runtime": 211.7269,
|
| 221 |
+
"eval_samples_per_second": 22.165,
|
| 222 |
+
"eval_steps_per_second": 2.772,
|
| 223 |
+
"step": 2500
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.66,
|
| 227 |
+
"learning_rate": 0.00011345392877331824,
|
| 228 |
+
"loss": 1.0273,
|
| 229 |
+
"step": 2600
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.69,
|
| 233 |
+
"learning_rate": 0.00010497456189937817,
|
| 234 |
+
"loss": 1.0371,
|
| 235 |
+
"step": 2700
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.71,
|
| 239 |
+
"learning_rate": 9.649519502543809e-05,
|
| 240 |
+
"loss": 1.0219,
|
| 241 |
+
"step": 2800
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.74,
|
| 245 |
+
"learning_rate": 8.801582815149802e-05,
|
| 246 |
+
"loss": 1.0292,
|
| 247 |
+
"step": 2900
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.76,
|
| 251 |
+
"learning_rate": 7.953646127755793e-05,
|
| 252 |
+
"loss": 1.0292,
|
| 253 |
+
"step": 3000
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.76,
|
| 257 |
+
"eval_bleu": 0.17334929168529137,
|
| 258 |
+
"eval_loss": 1.0501199960708618,
|
| 259 |
+
"eval_rouge1": 0.5057510392904037,
|
| 260 |
+
"eval_rouge2": 0.41127958350841676,
|
| 261 |
+
"eval_rougeL": 0.46859672321186563,
|
| 262 |
+
"eval_rougeLsum": 0.4686909635105035,
|
| 263 |
+
"eval_runtime": 210.649,
|
| 264 |
+
"eval_samples_per_second": 22.279,
|
| 265 |
+
"eval_steps_per_second": 2.787,
|
| 266 |
+
"step": 3000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.79,
|
| 270 |
+
"learning_rate": 7.105709440361785e-05,
|
| 271 |
+
"loss": 1.0166,
|
| 272 |
+
"step": 3100
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.81,
|
| 276 |
+
"learning_rate": 6.257772752967779e-05,
|
| 277 |
+
"loss": 1.015,
|
| 278 |
+
"step": 3200
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.84,
|
| 282 |
+
"learning_rate": 5.40983606557377e-05,
|
| 283 |
+
"loss": 1.0142,
|
| 284 |
+
"step": 3300
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.86,
|
| 288 |
+
"learning_rate": 4.5618993781797626e-05,
|
| 289 |
+
"loss": 1.0256,
|
| 290 |
+
"step": 3400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.89,
|
| 294 |
+
"learning_rate": 3.713962690785755e-05,
|
| 295 |
+
"loss": 1.0094,
|
| 296 |
+
"step": 3500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.89,
|
| 300 |
+
"eval_bleu": 0.1714081170400144,
|
| 301 |
+
"eval_loss": 1.0423640012741089,
|
| 302 |
+
"eval_rouge1": 0.5035879586288757,
|
| 303 |
+
"eval_rouge2": 0.40851924259079697,
|
| 304 |
+
"eval_rougeL": 0.46637902927069697,
|
| 305 |
+
"eval_rougeLsum": 0.4663610962140706,
|
| 306 |
+
"eval_runtime": 210.1257,
|
| 307 |
+
"eval_samples_per_second": 22.334,
|
| 308 |
+
"eval_steps_per_second": 2.794,
|
| 309 |
+
"step": 3500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.91,
|
| 313 |
+
"learning_rate": 2.8660260033917467e-05,
|
| 314 |
+
"loss": 1.0099,
|
| 315 |
+
"step": 3600
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.94,
|
| 319 |
+
"learning_rate": 2.0180893159977384e-05,
|
| 320 |
+
"loss": 0.9959,
|
| 321 |
+
"step": 3700
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.96,
|
| 325 |
+
"learning_rate": 1.1701526286037308e-05,
|
| 326 |
+
"loss": 1.0107,
|
| 327 |
+
"step": 3800
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.99,
|
| 331 |
+
"learning_rate": 3.22215941209723e-06,
|
| 332 |
+
"loss": 1.0094,
|
| 333 |
+
"step": 3900
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.0,
|
| 337 |
+
"step": 3938,
|
| 338 |
+
"total_flos": 1.5343986185183232e+17,
|
| 339 |
+
"train_loss": 1.1361048782216892,
|
| 340 |
+
"train_runtime": 10695.8658,
|
| 341 |
+
"train_samples_per_second": 23.566,
|
| 342 |
+
"train_steps_per_second": 0.368
|
| 343 |
+
}
|
| 344 |
+
],
|
| 345 |
+
"max_steps": 3938,
|
| 346 |
+
"num_train_epochs": 1,
|
| 347 |
+
"total_flos": 1.5343986185183232e+17,
|
| 348 |
+
"trial_name": null,
|
| 349 |
+
"trial_params": null
|
| 350 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d257b8785969e580b977bc7ec11f0325810074b17a71ed09fd046781a44e9515
|
| 3 |
+
size 3835
|