add model
Browse files- config.json +60 -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 +973 -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": "4.24.0",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 32128
|
| 60 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bc2457afdabd2cd385d5a14e1fedb27de31fce1927798456d159bab017b1d27
|
| 3 |
+
size 1783381253
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3885d020094f1b55ebc97320d3fdedcc130747d79edd6a6fdf5f19252981973b
|
| 3 |
+
size 891702929
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:627dad3e69439177a334883f827dfeb132cad8d5ed65e566006a7ed9cb6ebf73
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4ca02b42dda87eae1f459f5612ce04d7d315a41f30465487297bda13c7d35e5
|
| 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.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 |
+
"eos_token": "</s>",
|
| 105 |
+
"extra_ids": 100,
|
| 106 |
+
"model_max_length": 512,
|
| 107 |
+
"name_or_path": "t5-base",
|
| 108 |
+
"pad_token": "<pad>",
|
| 109 |
+
"special_tokens_map_file": null,
|
| 110 |
+
"tokenizer_class": "T5Tokenizer",
|
| 111 |
+
"unk_token": "<unk>"
|
| 112 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,973 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 76518,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 1.9869311795917304e-05,
|
| 13 |
+
"loss": 1.2439,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 1.9738623591834603e-05,
|
| 19 |
+
"loss": 0.6806,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.06,
|
| 24 |
+
"learning_rate": 1.9607935387751905e-05,
|
| 25 |
+
"loss": 0.6678,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.08,
|
| 30 |
+
"learning_rate": 1.9477247183669204e-05,
|
| 31 |
+
"loss": 0.6594,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.1,
|
| 36 |
+
"learning_rate": 1.9346558979586506e-05,
|
| 37 |
+
"loss": 0.6537,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.12,
|
| 42 |
+
"learning_rate": 1.9215870775503805e-05,
|
| 43 |
+
"loss": 0.6493,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.14,
|
| 48 |
+
"learning_rate": 1.9085182571421107e-05,
|
| 49 |
+
"loss": 0.646,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.16,
|
| 54 |
+
"learning_rate": 1.8954494367338406e-05,
|
| 55 |
+
"loss": 0.6475,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.18,
|
| 60 |
+
"learning_rate": 1.8823806163255708e-05,
|
| 61 |
+
"loss": 0.6358,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.2,
|
| 66 |
+
"learning_rate": 1.8693117959173007e-05,
|
| 67 |
+
"loss": 0.6404,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.22,
|
| 72 |
+
"learning_rate": 1.856242975509031e-05,
|
| 73 |
+
"loss": 0.636,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.24,
|
| 78 |
+
"learning_rate": 1.8431741551007608e-05,
|
| 79 |
+
"loss": 0.6307,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.25,
|
| 84 |
+
"learning_rate": 1.830105334692491e-05,
|
| 85 |
+
"loss": 0.6292,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.27,
|
| 90 |
+
"learning_rate": 1.817036514284221e-05,
|
| 91 |
+
"loss": 0.6254,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.29,
|
| 96 |
+
"learning_rate": 1.803967693875951e-05,
|
| 97 |
+
"loss": 0.632,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.31,
|
| 102 |
+
"learning_rate": 1.790898873467681e-05,
|
| 103 |
+
"loss": 0.6276,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.33,
|
| 108 |
+
"learning_rate": 1.7778300530594112e-05,
|
| 109 |
+
"loss": 0.6295,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.35,
|
| 114 |
+
"learning_rate": 1.764761232651141e-05,
|
| 115 |
+
"loss": 0.625,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.37,
|
| 120 |
+
"learning_rate": 1.751692412242871e-05,
|
| 121 |
+
"loss": 0.6272,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.39,
|
| 126 |
+
"learning_rate": 1.7386235918346012e-05,
|
| 127 |
+
"loss": 0.6241,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.41,
|
| 132 |
+
"learning_rate": 1.725554771426331e-05,
|
| 133 |
+
"loss": 0.6208,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.43,
|
| 138 |
+
"learning_rate": 1.7124859510180613e-05,
|
| 139 |
+
"loss": 0.6201,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.45,
|
| 144 |
+
"learning_rate": 1.699417130609791e-05,
|
| 145 |
+
"loss": 0.6271,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.47,
|
| 150 |
+
"learning_rate": 1.6863483102015214e-05,
|
| 151 |
+
"loss": 0.6173,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.49,
|
| 156 |
+
"learning_rate": 1.6732794897932513e-05,
|
| 157 |
+
"loss": 0.6172,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.51,
|
| 162 |
+
"learning_rate": 1.6602106693849815e-05,
|
| 163 |
+
"loss": 0.6135,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.53,
|
| 168 |
+
"learning_rate": 1.6471418489767114e-05,
|
| 169 |
+
"loss": 0.6115,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.55,
|
| 174 |
+
"learning_rate": 1.6340730285684416e-05,
|
| 175 |
+
"loss": 0.6191,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.57,
|
| 180 |
+
"learning_rate": 1.6210042081601715e-05,
|
| 181 |
+
"loss": 0.6177,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.59,
|
| 186 |
+
"learning_rate": 1.6079353877519017e-05,
|
| 187 |
+
"loss": 0.6171,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.61,
|
| 192 |
+
"learning_rate": 1.5948665673436316e-05,
|
| 193 |
+
"loss": 0.6225,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.63,
|
| 198 |
+
"learning_rate": 1.5817977469353618e-05,
|
| 199 |
+
"loss": 0.6078,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.65,
|
| 204 |
+
"learning_rate": 1.5687289265270917e-05,
|
| 205 |
+
"loss": 0.6115,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.67,
|
| 210 |
+
"learning_rate": 1.555660106118822e-05,
|
| 211 |
+
"loss": 0.6085,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.69,
|
| 216 |
+
"learning_rate": 1.5425912857105518e-05,
|
| 217 |
+
"loss": 0.6011,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.71,
|
| 222 |
+
"learning_rate": 1.529522465302282e-05,
|
| 223 |
+
"loss": 0.6096,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.73,
|
| 228 |
+
"learning_rate": 1.5164536448940119e-05,
|
| 229 |
+
"loss": 0.6144,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.74,
|
| 234 |
+
"learning_rate": 1.5033848244857421e-05,
|
| 235 |
+
"loss": 0.6042,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.76,
|
| 240 |
+
"learning_rate": 1.490316004077472e-05,
|
| 241 |
+
"loss": 0.6149,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.78,
|
| 246 |
+
"learning_rate": 1.4772471836692022e-05,
|
| 247 |
+
"loss": 0.6024,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.8,
|
| 252 |
+
"learning_rate": 1.464178363260932e-05,
|
| 253 |
+
"loss": 0.603,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.82,
|
| 258 |
+
"learning_rate": 1.4511095428526623e-05,
|
| 259 |
+
"loss": 0.6062,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.84,
|
| 264 |
+
"learning_rate": 1.4380407224443922e-05,
|
| 265 |
+
"loss": 0.6073,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.86,
|
| 270 |
+
"learning_rate": 1.4249719020361224e-05,
|
| 271 |
+
"loss": 0.6058,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.88,
|
| 276 |
+
"learning_rate": 1.4119030816278523e-05,
|
| 277 |
+
"loss": 0.6066,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.9,
|
| 282 |
+
"learning_rate": 1.3988342612195825e-05,
|
| 283 |
+
"loss": 0.6008,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.92,
|
| 288 |
+
"learning_rate": 1.3857654408113126e-05,
|
| 289 |
+
"loss": 0.622,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.94,
|
| 294 |
+
"learning_rate": 1.3726966204030424e-05,
|
| 295 |
+
"loss": 0.6013,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.96,
|
| 300 |
+
"learning_rate": 1.3596277999947727e-05,
|
| 301 |
+
"loss": 0.6073,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.98,
|
| 306 |
+
"learning_rate": 1.3465589795865025e-05,
|
| 307 |
+
"loss": 0.5973,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.0,
|
| 312 |
+
"learning_rate": 1.3334901591782328e-05,
|
| 313 |
+
"loss": 0.6065,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.0,
|
| 318 |
+
"eval_gen_len": 18.7995,
|
| 319 |
+
"eval_loss": 0.547476589679718,
|
| 320 |
+
"eval_rouge1": 34.0929,
|
| 321 |
+
"eval_rouge2": 12.225,
|
| 322 |
+
"eval_rougeL": 27.465,
|
| 323 |
+
"eval_rougeLsum": 27.4736,
|
| 324 |
+
"eval_runtime": 1500.9794,
|
| 325 |
+
"eval_samples_per_second": 7.55,
|
| 326 |
+
"eval_steps_per_second": 1.887,
|
| 327 |
+
"step": 25506
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.02,
|
| 331 |
+
"learning_rate": 1.3204213387699626e-05,
|
| 332 |
+
"loss": 0.5931,
|
| 333 |
+
"step": 26000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.04,
|
| 337 |
+
"learning_rate": 1.3073525183616929e-05,
|
| 338 |
+
"loss": 0.5981,
|
| 339 |
+
"step": 26500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.06,
|
| 343 |
+
"learning_rate": 1.2942836979534227e-05,
|
| 344 |
+
"loss": 0.5865,
|
| 345 |
+
"step": 27000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.08,
|
| 349 |
+
"learning_rate": 1.281214877545153e-05,
|
| 350 |
+
"loss": 0.5894,
|
| 351 |
+
"step": 27500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.1,
|
| 355 |
+
"learning_rate": 1.2681460571368828e-05,
|
| 356 |
+
"loss": 0.5844,
|
| 357 |
+
"step": 28000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.12,
|
| 361 |
+
"learning_rate": 1.255077236728613e-05,
|
| 362 |
+
"loss": 0.5928,
|
| 363 |
+
"step": 28500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.14,
|
| 367 |
+
"learning_rate": 1.242008416320343e-05,
|
| 368 |
+
"loss": 0.5891,
|
| 369 |
+
"step": 29000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.16,
|
| 373 |
+
"learning_rate": 1.2289395959120732e-05,
|
| 374 |
+
"loss": 0.5868,
|
| 375 |
+
"step": 29500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.18,
|
| 379 |
+
"learning_rate": 1.215870775503803e-05,
|
| 380 |
+
"loss": 0.5831,
|
| 381 |
+
"step": 30000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.2,
|
| 385 |
+
"learning_rate": 1.2028019550955333e-05,
|
| 386 |
+
"loss": 0.5894,
|
| 387 |
+
"step": 30500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.22,
|
| 391 |
+
"learning_rate": 1.1897331346872632e-05,
|
| 392 |
+
"loss": 0.5926,
|
| 393 |
+
"step": 31000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.24,
|
| 397 |
+
"learning_rate": 1.1766643142789934e-05,
|
| 398 |
+
"loss": 0.5891,
|
| 399 |
+
"step": 31500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.25,
|
| 403 |
+
"learning_rate": 1.1635954938707233e-05,
|
| 404 |
+
"loss": 0.5925,
|
| 405 |
+
"step": 32000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.27,
|
| 409 |
+
"learning_rate": 1.1505266734624533e-05,
|
| 410 |
+
"loss": 0.582,
|
| 411 |
+
"step": 32500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.29,
|
| 415 |
+
"learning_rate": 1.1374578530541834e-05,
|
| 416 |
+
"loss": 0.5904,
|
| 417 |
+
"step": 33000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.31,
|
| 421 |
+
"learning_rate": 1.1243890326459134e-05,
|
| 422 |
+
"loss": 0.596,
|
| 423 |
+
"step": 33500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.33,
|
| 427 |
+
"learning_rate": 1.1113202122376435e-05,
|
| 428 |
+
"loss": 0.5851,
|
| 429 |
+
"step": 34000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.35,
|
| 433 |
+
"learning_rate": 1.0982513918293735e-05,
|
| 434 |
+
"loss": 0.5852,
|
| 435 |
+
"step": 34500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.37,
|
| 439 |
+
"learning_rate": 1.0851825714211037e-05,
|
| 440 |
+
"loss": 0.5952,
|
| 441 |
+
"step": 35000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.39,
|
| 445 |
+
"learning_rate": 1.0721137510128336e-05,
|
| 446 |
+
"loss": 0.5857,
|
| 447 |
+
"step": 35500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.41,
|
| 451 |
+
"learning_rate": 1.0590449306045638e-05,
|
| 452 |
+
"loss": 0.5875,
|
| 453 |
+
"step": 36000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.43,
|
| 457 |
+
"learning_rate": 1.0459761101962937e-05,
|
| 458 |
+
"loss": 0.5901,
|
| 459 |
+
"step": 36500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.45,
|
| 463 |
+
"learning_rate": 1.032907289788024e-05,
|
| 464 |
+
"loss": 0.5883,
|
| 465 |
+
"step": 37000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.47,
|
| 469 |
+
"learning_rate": 1.0198384693797538e-05,
|
| 470 |
+
"loss": 0.5893,
|
| 471 |
+
"step": 37500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.49,
|
| 475 |
+
"learning_rate": 1.006769648971484e-05,
|
| 476 |
+
"loss": 0.5853,
|
| 477 |
+
"step": 38000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.51,
|
| 481 |
+
"learning_rate": 9.93700828563214e-06,
|
| 482 |
+
"loss": 0.5839,
|
| 483 |
+
"step": 38500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.53,
|
| 487 |
+
"learning_rate": 9.80632008154944e-06,
|
| 488 |
+
"loss": 0.5877,
|
| 489 |
+
"step": 39000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.55,
|
| 493 |
+
"learning_rate": 9.67563187746674e-06,
|
| 494 |
+
"loss": 0.5904,
|
| 495 |
+
"step": 39500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.57,
|
| 499 |
+
"learning_rate": 9.54494367338404e-06,
|
| 500 |
+
"loss": 0.5753,
|
| 501 |
+
"step": 40000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.59,
|
| 505 |
+
"learning_rate": 9.414255469301343e-06,
|
| 506 |
+
"loss": 0.5855,
|
| 507 |
+
"step": 40500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.61,
|
| 511 |
+
"learning_rate": 9.283567265218643e-06,
|
| 512 |
+
"loss": 0.5917,
|
| 513 |
+
"step": 41000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.63,
|
| 517 |
+
"learning_rate": 9.152879061135942e-06,
|
| 518 |
+
"loss": 0.5818,
|
| 519 |
+
"step": 41500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.65,
|
| 523 |
+
"learning_rate": 9.022190857053243e-06,
|
| 524 |
+
"loss": 0.578,
|
| 525 |
+
"step": 42000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.67,
|
| 529 |
+
"learning_rate": 8.891502652970543e-06,
|
| 530 |
+
"loss": 0.5831,
|
| 531 |
+
"step": 42500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.69,
|
| 535 |
+
"learning_rate": 8.760814448887844e-06,
|
| 536 |
+
"loss": 0.583,
|
| 537 |
+
"step": 43000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.71,
|
| 541 |
+
"learning_rate": 8.630126244805144e-06,
|
| 542 |
+
"loss": 0.5869,
|
| 543 |
+
"step": 43500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.73,
|
| 547 |
+
"learning_rate": 8.499438040722445e-06,
|
| 548 |
+
"loss": 0.5802,
|
| 549 |
+
"step": 44000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.74,
|
| 553 |
+
"learning_rate": 8.368749836639745e-06,
|
| 554 |
+
"loss": 0.5776,
|
| 555 |
+
"step": 44500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.76,
|
| 559 |
+
"learning_rate": 8.238061632557046e-06,
|
| 560 |
+
"loss": 0.5833,
|
| 561 |
+
"step": 45000
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.78,
|
| 565 |
+
"learning_rate": 8.107373428474346e-06,
|
| 566 |
+
"loss": 0.5844,
|
| 567 |
+
"step": 45500
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.8,
|
| 571 |
+
"learning_rate": 7.976685224391647e-06,
|
| 572 |
+
"loss": 0.5834,
|
| 573 |
+
"step": 46000
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.82,
|
| 577 |
+
"learning_rate": 7.845997020308947e-06,
|
| 578 |
+
"loss": 0.5829,
|
| 579 |
+
"step": 46500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.84,
|
| 583 |
+
"learning_rate": 7.715308816226248e-06,
|
| 584 |
+
"loss": 0.5849,
|
| 585 |
+
"step": 47000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.86,
|
| 589 |
+
"learning_rate": 7.584620612143548e-06,
|
| 590 |
+
"loss": 0.5874,
|
| 591 |
+
"step": 47500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.88,
|
| 595 |
+
"learning_rate": 7.453932408060849e-06,
|
| 596 |
+
"loss": 0.5879,
|
| 597 |
+
"step": 48000
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.9,
|
| 601 |
+
"learning_rate": 7.323244203978149e-06,
|
| 602 |
+
"loss": 0.577,
|
| 603 |
+
"step": 48500
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.92,
|
| 607 |
+
"learning_rate": 7.19255599989545e-06,
|
| 608 |
+
"loss": 0.5807,
|
| 609 |
+
"step": 49000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.94,
|
| 613 |
+
"learning_rate": 7.06186779581275e-06,
|
| 614 |
+
"loss": 0.5865,
|
| 615 |
+
"step": 49500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.96,
|
| 619 |
+
"learning_rate": 6.931179591730051e-06,
|
| 620 |
+
"loss": 0.5765,
|
| 621 |
+
"step": 50000
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.98,
|
| 625 |
+
"learning_rate": 6.8004913876473514e-06,
|
| 626 |
+
"loss": 0.5883,
|
| 627 |
+
"step": 50500
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.0,
|
| 631 |
+
"learning_rate": 6.669803183564651e-06,
|
| 632 |
+
"loss": 0.5787,
|
| 633 |
+
"step": 51000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.0,
|
| 637 |
+
"eval_gen_len": 18.8155,
|
| 638 |
+
"eval_loss": 0.5370269417762756,
|
| 639 |
+
"eval_rouge1": 34.4751,
|
| 640 |
+
"eval_rouge2": 12.6984,
|
| 641 |
+
"eval_rougeL": 27.9605,
|
| 642 |
+
"eval_rougeLsum": 27.9586,
|
| 643 |
+
"eval_runtime": 1516.6364,
|
| 644 |
+
"eval_samples_per_second": 7.472,
|
| 645 |
+
"eval_steps_per_second": 1.868,
|
| 646 |
+
"step": 51012
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 2.02,
|
| 650 |
+
"learning_rate": 6.539114979481952e-06,
|
| 651 |
+
"loss": 0.5674,
|
| 652 |
+
"step": 51500
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 2.04,
|
| 656 |
+
"learning_rate": 6.408426775399254e-06,
|
| 657 |
+
"loss": 0.5708,
|
| 658 |
+
"step": 52000
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 2.06,
|
| 662 |
+
"learning_rate": 6.277738571316554e-06,
|
| 663 |
+
"loss": 0.5746,
|
| 664 |
+
"step": 52500
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 2.08,
|
| 668 |
+
"learning_rate": 6.147050367233854e-06,
|
| 669 |
+
"loss": 0.5726,
|
| 670 |
+
"step": 53000
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 2.1,
|
| 674 |
+
"learning_rate": 6.0163621631511545e-06,
|
| 675 |
+
"loss": 0.5789,
|
| 676 |
+
"step": 53500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.12,
|
| 680 |
+
"learning_rate": 5.885673959068455e-06,
|
| 681 |
+
"loss": 0.5693,
|
| 682 |
+
"step": 54000
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 2.14,
|
| 686 |
+
"learning_rate": 5.7549857549857555e-06,
|
| 687 |
+
"loss": 0.5677,
|
| 688 |
+
"step": 54500
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 2.16,
|
| 692 |
+
"learning_rate": 5.624297550903056e-06,
|
| 693 |
+
"loss": 0.5724,
|
| 694 |
+
"step": 55000
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 2.18,
|
| 698 |
+
"learning_rate": 5.4936093468203565e-06,
|
| 699 |
+
"loss": 0.5737,
|
| 700 |
+
"step": 55500
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.2,
|
| 704 |
+
"learning_rate": 5.362921142737657e-06,
|
| 705 |
+
"loss": 0.5758,
|
| 706 |
+
"step": 56000
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 2.22,
|
| 710 |
+
"learning_rate": 5.2322329386549575e-06,
|
| 711 |
+
"loss": 0.5693,
|
| 712 |
+
"step": 56500
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 2.23,
|
| 716 |
+
"learning_rate": 5.101544734572258e-06,
|
| 717 |
+
"loss": 0.5772,
|
| 718 |
+
"step": 57000
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.25,
|
| 722 |
+
"learning_rate": 4.9708565304895586e-06,
|
| 723 |
+
"loss": 0.5793,
|
| 724 |
+
"step": 57500
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 2.27,
|
| 728 |
+
"learning_rate": 4.840168326406859e-06,
|
| 729 |
+
"loss": 0.576,
|
| 730 |
+
"step": 58000
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 2.29,
|
| 734 |
+
"learning_rate": 4.70948012232416e-06,
|
| 735 |
+
"loss": 0.5768,
|
| 736 |
+
"step": 58500
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 2.31,
|
| 740 |
+
"learning_rate": 4.57879191824146e-06,
|
| 741 |
+
"loss": 0.5685,
|
| 742 |
+
"step": 59000
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.33,
|
| 746 |
+
"learning_rate": 4.448103714158761e-06,
|
| 747 |
+
"loss": 0.5706,
|
| 748 |
+
"step": 59500
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 2.35,
|
| 752 |
+
"learning_rate": 4.31741551007606e-06,
|
| 753 |
+
"loss": 0.5796,
|
| 754 |
+
"step": 60000
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 2.37,
|
| 758 |
+
"learning_rate": 4.186727305993362e-06,
|
| 759 |
+
"loss": 0.5763,
|
| 760 |
+
"step": 60500
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.39,
|
| 764 |
+
"learning_rate": 4.056039101910662e-06,
|
| 765 |
+
"loss": 0.5707,
|
| 766 |
+
"step": 61000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 2.41,
|
| 770 |
+
"learning_rate": 3.925350897827963e-06,
|
| 771 |
+
"loss": 0.5748,
|
| 772 |
+
"step": 61500
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 2.43,
|
| 776 |
+
"learning_rate": 3.794662693745263e-06,
|
| 777 |
+
"loss": 0.5762,
|
| 778 |
+
"step": 62000
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 2.45,
|
| 782 |
+
"learning_rate": 3.6639744896625632e-06,
|
| 783 |
+
"loss": 0.5693,
|
| 784 |
+
"step": 62500
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 2.47,
|
| 788 |
+
"learning_rate": 3.5332862855798637e-06,
|
| 789 |
+
"loss": 0.5754,
|
| 790 |
+
"step": 63000
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 2.49,
|
| 794 |
+
"learning_rate": 3.4025980814971643e-06,
|
| 795 |
+
"loss": 0.5832,
|
| 796 |
+
"step": 63500
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 2.51,
|
| 800 |
+
"learning_rate": 3.2719098774144648e-06,
|
| 801 |
+
"loss": 0.5653,
|
| 802 |
+
"step": 64000
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.53,
|
| 806 |
+
"learning_rate": 3.1412216733317653e-06,
|
| 807 |
+
"loss": 0.5635,
|
| 808 |
+
"step": 64500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 2.55,
|
| 812 |
+
"learning_rate": 3.0105334692490658e-06,
|
| 813 |
+
"loss": 0.5743,
|
| 814 |
+
"step": 65000
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 2.57,
|
| 818 |
+
"learning_rate": 2.8798452651663663e-06,
|
| 819 |
+
"loss": 0.5633,
|
| 820 |
+
"step": 65500
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 2.59,
|
| 824 |
+
"learning_rate": 2.7491570610836672e-06,
|
| 825 |
+
"loss": 0.5741,
|
| 826 |
+
"step": 66000
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.61,
|
| 830 |
+
"learning_rate": 2.6184688570009677e-06,
|
| 831 |
+
"loss": 0.5691,
|
| 832 |
+
"step": 66500
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 2.63,
|
| 836 |
+
"learning_rate": 2.487780652918268e-06,
|
| 837 |
+
"loss": 0.5758,
|
| 838 |
+
"step": 67000
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 2.65,
|
| 842 |
+
"learning_rate": 2.3570924488355683e-06,
|
| 843 |
+
"loss": 0.5637,
|
| 844 |
+
"step": 67500
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.67,
|
| 848 |
+
"learning_rate": 2.226404244752869e-06,
|
| 849 |
+
"loss": 0.5753,
|
| 850 |
+
"step": 68000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 2.69,
|
| 854 |
+
"learning_rate": 2.0957160406701694e-06,
|
| 855 |
+
"loss": 0.5763,
|
| 856 |
+
"step": 68500
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 2.71,
|
| 860 |
+
"learning_rate": 1.96502783658747e-06,
|
| 861 |
+
"loss": 0.5738,
|
| 862 |
+
"step": 69000
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 2.72,
|
| 866 |
+
"learning_rate": 1.8343396325047702e-06,
|
| 867 |
+
"loss": 0.5698,
|
| 868 |
+
"step": 69500
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 2.74,
|
| 872 |
+
"learning_rate": 1.7036514284220707e-06,
|
| 873 |
+
"loss": 0.5725,
|
| 874 |
+
"step": 70000
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 2.76,
|
| 878 |
+
"learning_rate": 1.5729632243393714e-06,
|
| 879 |
+
"loss": 0.5733,
|
| 880 |
+
"step": 70500
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 2.78,
|
| 884 |
+
"learning_rate": 1.442275020256672e-06,
|
| 885 |
+
"loss": 0.578,
|
| 886 |
+
"step": 71000
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.8,
|
| 890 |
+
"learning_rate": 1.3115868161739722e-06,
|
| 891 |
+
"loss": 0.5755,
|
| 892 |
+
"step": 71500
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 2.82,
|
| 896 |
+
"learning_rate": 1.1808986120912727e-06,
|
| 897 |
+
"loss": 0.5806,
|
| 898 |
+
"step": 72000
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.84,
|
| 902 |
+
"learning_rate": 1.0502104080085732e-06,
|
| 903 |
+
"loss": 0.5736,
|
| 904 |
+
"step": 72500
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 2.86,
|
| 908 |
+
"learning_rate": 9.195222039258737e-07,
|
| 909 |
+
"loss": 0.5665,
|
| 910 |
+
"step": 73000
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 2.88,
|
| 914 |
+
"learning_rate": 7.888339998431741e-07,
|
| 915 |
+
"loss": 0.5711,
|
| 916 |
+
"step": 73500
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 2.9,
|
| 920 |
+
"learning_rate": 6.581457957604747e-07,
|
| 921 |
+
"loss": 0.5699,
|
| 922 |
+
"step": 74000
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 2.92,
|
| 926 |
+
"learning_rate": 5.274575916777753e-07,
|
| 927 |
+
"loss": 0.5727,
|
| 928 |
+
"step": 74500
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.94,
|
| 932 |
+
"learning_rate": 3.967693875950757e-07,
|
| 933 |
+
"loss": 0.5702,
|
| 934 |
+
"step": 75000
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.96,
|
| 938 |
+
"learning_rate": 2.660811835123762e-07,
|
| 939 |
+
"loss": 0.5697,
|
| 940 |
+
"step": 75500
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 2.98,
|
| 944 |
+
"learning_rate": 1.3539297942967668e-07,
|
| 945 |
+
"loss": 0.5658,
|
| 946 |
+
"step": 76000
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 3.0,
|
| 950 |
+
"learning_rate": 4.704775346977182e-09,
|
| 951 |
+
"loss": 0.5692,
|
| 952 |
+
"step": 76500
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 3.0,
|
| 956 |
+
"eval_gen_len": 18.8131,
|
| 957 |
+
"eval_loss": 0.5340152382850647,
|
| 958 |
+
"eval_rouge1": 34.6791,
|
| 959 |
+
"eval_rouge2": 12.8236,
|
| 960 |
+
"eval_rougeL": 28.1201,
|
| 961 |
+
"eval_rougeLsum": 28.1241,
|
| 962 |
+
"eval_runtime": 1504.5288,
|
| 963 |
+
"eval_samples_per_second": 7.532,
|
| 964 |
+
"eval_steps_per_second": 1.883,
|
| 965 |
+
"step": 76518
|
| 966 |
+
}
|
| 967 |
+
],
|
| 968 |
+
"max_steps": 76518,
|
| 969 |
+
"num_train_epochs": 3,
|
| 970 |
+
"total_flos": 3.727644383379456e+17,
|
| 971 |
+
"trial_name": null,
|
| 972 |
+
"trial_params": null
|
| 973 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:236f2c0af576db87bfc0927c49495cb90721ef763a4661f2fb9191a830470ddc
|
| 3 |
+
size 3579
|