Upload 9 files
Browse files- config.json +32 -0
- generation_config.json +6 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +150 -0
- tokenizer_config.json +157 -0
- trainer_state.json +762 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "byt5-base-id_id",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 3584,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 1472,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "gated-gelu",
|
| 14 |
+
"gradient_checkpointing": false,
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"num_decoder_layers": 4,
|
| 21 |
+
"num_heads": 6,
|
| 22 |
+
"num_layers": 12,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"relative_attention_max_distance": 128,
|
| 25 |
+
"relative_attention_num_buckets": 32,
|
| 26 |
+
"tie_word_embeddings": false,
|
| 27 |
+
"tokenizer_class": "ByT5Tokenizer",
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.30.2",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 384
|
| 32 |
+
}
|
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": "4.30.2"
|
| 6 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c30ba9085c889439ef9fa99fd0b1a216f118ce03e3a672302167bdf81c95cd2
|
| 3 |
+
size 1937466
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3df8ccc7671a810bbc588fe25159ff2950357749b8a163678496d4c82fa74ee
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50b2dc5e48e087e36857b474ca02841852ff1155874dd97842e4f7b8e7a9f50e
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,150 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"<extra_id_100>",
|
| 104 |
+
"<extra_id_101>",
|
| 105 |
+
"<extra_id_102>",
|
| 106 |
+
"<extra_id_103>",
|
| 107 |
+
"<extra_id_104>",
|
| 108 |
+
"<extra_id_105>",
|
| 109 |
+
"<extra_id_106>",
|
| 110 |
+
"<extra_id_107>",
|
| 111 |
+
"<extra_id_108>",
|
| 112 |
+
"<extra_id_109>",
|
| 113 |
+
"<extra_id_110>",
|
| 114 |
+
"<extra_id_111>",
|
| 115 |
+
"<extra_id_112>",
|
| 116 |
+
"<extra_id_113>",
|
| 117 |
+
"<extra_id_114>",
|
| 118 |
+
"<extra_id_115>",
|
| 119 |
+
"<extra_id_116>",
|
| 120 |
+
"<extra_id_117>",
|
| 121 |
+
"<extra_id_118>",
|
| 122 |
+
"<extra_id_119>",
|
| 123 |
+
"<extra_id_120>",
|
| 124 |
+
"<extra_id_121>",
|
| 125 |
+
"<extra_id_122>",
|
| 126 |
+
"<extra_id_123>",
|
| 127 |
+
"<extra_id_124>"
|
| 128 |
+
],
|
| 129 |
+
"eos_token": {
|
| 130 |
+
"content": "</s>",
|
| 131 |
+
"lstrip": false,
|
| 132 |
+
"normalized": true,
|
| 133 |
+
"rstrip": false,
|
| 134 |
+
"single_word": false
|
| 135 |
+
},
|
| 136 |
+
"pad_token": {
|
| 137 |
+
"content": "<pad>",
|
| 138 |
+
"lstrip": false,
|
| 139 |
+
"normalized": true,
|
| 140 |
+
"rstrip": false,
|
| 141 |
+
"single_word": false
|
| 142 |
+
},
|
| 143 |
+
"unk_token": {
|
| 144 |
+
"content": "<unk>",
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"normalized": true,
|
| 147 |
+
"rstrip": false,
|
| 148 |
+
"single_word": false
|
| 149 |
+
}
|
| 150 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,157 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"<extra_id_100>",
|
| 104 |
+
"<extra_id_101>",
|
| 105 |
+
"<extra_id_102>",
|
| 106 |
+
"<extra_id_103>",
|
| 107 |
+
"<extra_id_104>",
|
| 108 |
+
"<extra_id_105>",
|
| 109 |
+
"<extra_id_106>",
|
| 110 |
+
"<extra_id_107>",
|
| 111 |
+
"<extra_id_108>",
|
| 112 |
+
"<extra_id_109>",
|
| 113 |
+
"<extra_id_110>",
|
| 114 |
+
"<extra_id_111>",
|
| 115 |
+
"<extra_id_112>",
|
| 116 |
+
"<extra_id_113>",
|
| 117 |
+
"<extra_id_114>",
|
| 118 |
+
"<extra_id_115>",
|
| 119 |
+
"<extra_id_116>",
|
| 120 |
+
"<extra_id_117>",
|
| 121 |
+
"<extra_id_118>",
|
| 122 |
+
"<extra_id_119>",
|
| 123 |
+
"<extra_id_120>",
|
| 124 |
+
"<extra_id_121>",
|
| 125 |
+
"<extra_id_122>",
|
| 126 |
+
"<extra_id_123>",
|
| 127 |
+
"<extra_id_124>"
|
| 128 |
+
],
|
| 129 |
+
"clean_up_tokenization_spaces": true,
|
| 130 |
+
"eos_token": {
|
| 131 |
+
"__type": "AddedToken",
|
| 132 |
+
"content": "</s>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false
|
| 137 |
+
},
|
| 138 |
+
"extra_ids": 125,
|
| 139 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 140 |
+
"pad_token": {
|
| 141 |
+
"__type": "AddedToken",
|
| 142 |
+
"content": "<pad>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": true,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false
|
| 147 |
+
},
|
| 148 |
+
"tokenizer_class": "ByT5Tokenizer",
|
| 149 |
+
"unk_token": {
|
| 150 |
+
"__type": "AddedToken",
|
| 151 |
+
"content": "<unk>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false
|
| 156 |
+
}
|
| 157 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,762 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.031905961376994,
|
| 5 |
+
"global_step": 60500,
|
| 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": 0.0002992803166606693,
|
| 13 |
+
"loss": 0.0141,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 0.0002985606333213386,
|
| 19 |
+
"loss": 0.0149,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.05,
|
| 24 |
+
"learning_rate": 0.0002978409499820079,
|
| 25 |
+
"loss": 0.0134,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.07,
|
| 30 |
+
"learning_rate": 0.0002971212666426772,
|
| 31 |
+
"loss": 0.0142,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.08,
|
| 36 |
+
"learning_rate": 0.0002964015833033465,
|
| 37 |
+
"loss": 0.0147,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1,
|
| 42 |
+
"learning_rate": 0.0002956818999640158,
|
| 43 |
+
"loss": 0.0132,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12,
|
| 48 |
+
"learning_rate": 0.0002949622166246851,
|
| 49 |
+
"loss": 0.0137,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.13,
|
| 54 |
+
"learning_rate": 0.0002942425332853544,
|
| 55 |
+
"loss": 0.0146,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.15,
|
| 60 |
+
"learning_rate": 0.0002935228499460237,
|
| 61 |
+
"loss": 0.0146,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.17,
|
| 66 |
+
"learning_rate": 0.000292803166606693,
|
| 67 |
+
"loss": 0.0118,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.18,
|
| 72 |
+
"learning_rate": 0.00029208348326736233,
|
| 73 |
+
"loss": 0.0144,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.2,
|
| 78 |
+
"learning_rate": 0.00029136379992803163,
|
| 79 |
+
"loss": 0.0132,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.22,
|
| 84 |
+
"learning_rate": 0.00029064411658870094,
|
| 85 |
+
"loss": 0.0122,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.24,
|
| 90 |
+
"learning_rate": 0.00028992443324937024,
|
| 91 |
+
"loss": 0.011,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.25,
|
| 96 |
+
"learning_rate": 0.00028920474991003955,
|
| 97 |
+
"loss": 0.0146,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.27,
|
| 102 |
+
"learning_rate": 0.00028848506657070885,
|
| 103 |
+
"loss": 0.0128,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.29,
|
| 108 |
+
"learning_rate": 0.00028776538323137816,
|
| 109 |
+
"loss": 0.0137,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.3,
|
| 114 |
+
"learning_rate": 0.00028704569989204746,
|
| 115 |
+
"loss": 0.0133,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.32,
|
| 120 |
+
"learning_rate": 0.00028632601655271677,
|
| 121 |
+
"loss": 0.0125,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.34,
|
| 126 |
+
"learning_rate": 0.00028560633321338607,
|
| 127 |
+
"loss": 0.0134,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.35,
|
| 132 |
+
"learning_rate": 0.0002848866498740554,
|
| 133 |
+
"loss": 0.0142,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.37,
|
| 138 |
+
"learning_rate": 0.0002841669665347247,
|
| 139 |
+
"loss": 0.0126,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.39,
|
| 144 |
+
"learning_rate": 0.00028344728319539404,
|
| 145 |
+
"loss": 0.0128,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.4,
|
| 150 |
+
"learning_rate": 0.0002827275998560633,
|
| 151 |
+
"loss": 0.0126,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.42,
|
| 156 |
+
"learning_rate": 0.0002820079165167326,
|
| 157 |
+
"loss": 0.0151,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.44,
|
| 162 |
+
"learning_rate": 0.0002812882331774019,
|
| 163 |
+
"loss": 0.0127,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.45,
|
| 168 |
+
"learning_rate": 0.0002805685498380712,
|
| 169 |
+
"loss": 0.0113,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.47,
|
| 174 |
+
"learning_rate": 0.00027984886649874057,
|
| 175 |
+
"loss": 0.012,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.49,
|
| 180 |
+
"learning_rate": 0.0002791291831594098,
|
| 181 |
+
"loss": 0.0137,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.5,
|
| 186 |
+
"learning_rate": 0.0002784094998200791,
|
| 187 |
+
"loss": 0.0123,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.52,
|
| 192 |
+
"learning_rate": 0.0002776898164807484,
|
| 193 |
+
"loss": 0.013,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.54,
|
| 198 |
+
"learning_rate": 0.00027697013314141773,
|
| 199 |
+
"loss": 0.0128,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.55,
|
| 204 |
+
"learning_rate": 0.0002762504498020871,
|
| 205 |
+
"loss": 0.0126,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.57,
|
| 210 |
+
"learning_rate": 0.0002755307664627564,
|
| 211 |
+
"loss": 0.0141,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.59,
|
| 216 |
+
"learning_rate": 0.00027481108312342565,
|
| 217 |
+
"loss": 0.0131,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.6,
|
| 222 |
+
"learning_rate": 0.00027409139978409495,
|
| 223 |
+
"loss": 0.0138,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.62,
|
| 228 |
+
"learning_rate": 0.00027337171644476426,
|
| 229 |
+
"loss": 0.0133,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.64,
|
| 234 |
+
"learning_rate": 0.0002726520331054336,
|
| 235 |
+
"loss": 0.0123,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.65,
|
| 240 |
+
"learning_rate": 0.0002719323497661029,
|
| 241 |
+
"loss": 0.0108,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.67,
|
| 246 |
+
"learning_rate": 0.00027121266642677217,
|
| 247 |
+
"loss": 0.0131,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.69,
|
| 252 |
+
"learning_rate": 0.0002704929830874415,
|
| 253 |
+
"loss": 0.0111,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.71,
|
| 258 |
+
"learning_rate": 0.0002697732997481108,
|
| 259 |
+
"loss": 0.0128,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.72,
|
| 264 |
+
"learning_rate": 0.00026905361640878014,
|
| 265 |
+
"loss": 0.0118,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.74,
|
| 270 |
+
"learning_rate": 0.00026833393306944944,
|
| 271 |
+
"loss": 0.0125,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.76,
|
| 276 |
+
"learning_rate": 0.00026761424973011875,
|
| 277 |
+
"loss": 0.0123,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.77,
|
| 282 |
+
"learning_rate": 0.000266894566390788,
|
| 283 |
+
"loss": 0.0112,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.79,
|
| 288 |
+
"learning_rate": 0.0002661748830514573,
|
| 289 |
+
"loss": 0.0114,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.81,
|
| 294 |
+
"learning_rate": 0.00026545519971212666,
|
| 295 |
+
"loss": 0.0123,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.82,
|
| 300 |
+
"learning_rate": 0.00026473551637279597,
|
| 301 |
+
"loss": 0.012,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.84,
|
| 306 |
+
"learning_rate": 0.0002640158330334653,
|
| 307 |
+
"loss": 0.0113,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.86,
|
| 312 |
+
"learning_rate": 0.0002632961496941345,
|
| 313 |
+
"loss": 0.0124,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.87,
|
| 318 |
+
"learning_rate": 0.00026257646635480383,
|
| 319 |
+
"loss": 0.0128,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.89,
|
| 324 |
+
"learning_rate": 0.0002618567830154732,
|
| 325 |
+
"loss": 0.0122,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.91,
|
| 330 |
+
"learning_rate": 0.0002611370996761425,
|
| 331 |
+
"loss": 0.0118,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.92,
|
| 336 |
+
"learning_rate": 0.0002604174163368118,
|
| 337 |
+
"loss": 0.0138,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.94,
|
| 342 |
+
"learning_rate": 0.0002596977329974811,
|
| 343 |
+
"loss": 0.013,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.96,
|
| 348 |
+
"learning_rate": 0.00025897804965815035,
|
| 349 |
+
"loss": 0.0137,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.97,
|
| 354 |
+
"learning_rate": 0.0002582583663188197,
|
| 355 |
+
"loss": 0.012,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.99,
|
| 360 |
+
"learning_rate": 0.000257538682979489,
|
| 361 |
+
"loss": 0.0115,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.0,
|
| 366 |
+
"eval_bleu": 41.1255,
|
| 367 |
+
"eval_gen_len": 12.9555,
|
| 368 |
+
"eval_loss": 0.009961633943021297,
|
| 369 |
+
"eval_runtime": 1035.9589,
|
| 370 |
+
"eval_samples_per_second": 12.775,
|
| 371 |
+
"eval_steps_per_second": 6.387,
|
| 372 |
+
"step": 29775
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.01,
|
| 376 |
+
"learning_rate": 0.0002568189996401583,
|
| 377 |
+
"loss": 0.0112,
|
| 378 |
+
"step": 30000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.02,
|
| 382 |
+
"learning_rate": 0.00025609931630082763,
|
| 383 |
+
"loss": 0.0075,
|
| 384 |
+
"step": 30500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.04,
|
| 388 |
+
"learning_rate": 0.00025537963296149693,
|
| 389 |
+
"loss": 0.0088,
|
| 390 |
+
"step": 31000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.06,
|
| 394 |
+
"learning_rate": 0.00025465994962216624,
|
| 395 |
+
"loss": 0.0089,
|
| 396 |
+
"step": 31500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.07,
|
| 400 |
+
"learning_rate": 0.00025394026628283554,
|
| 401 |
+
"loss": 0.0088,
|
| 402 |
+
"step": 32000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.09,
|
| 406 |
+
"learning_rate": 0.00025322058294350485,
|
| 407 |
+
"loss": 0.0096,
|
| 408 |
+
"step": 32500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.11,
|
| 412 |
+
"learning_rate": 0.00025250089960417415,
|
| 413 |
+
"loss": 0.009,
|
| 414 |
+
"step": 33000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.13,
|
| 418 |
+
"learning_rate": 0.00025178121626484346,
|
| 419 |
+
"loss": 0.0097,
|
| 420 |
+
"step": 33500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.14,
|
| 424 |
+
"learning_rate": 0.00025106153292551276,
|
| 425 |
+
"loss": 0.0086,
|
| 426 |
+
"step": 34000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.16,
|
| 430 |
+
"learning_rate": 0.00025034184958618207,
|
| 431 |
+
"loss": 0.0093,
|
| 432 |
+
"step": 34500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.18,
|
| 436 |
+
"learning_rate": 0.00024962216624685137,
|
| 437 |
+
"loss": 0.0097,
|
| 438 |
+
"step": 35000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.19,
|
| 442 |
+
"learning_rate": 0.0002489024829075207,
|
| 443 |
+
"loss": 0.0095,
|
| 444 |
+
"step": 35500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.21,
|
| 448 |
+
"learning_rate": 0.00024818279956819,
|
| 449 |
+
"loss": 0.0086,
|
| 450 |
+
"step": 36000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.23,
|
| 454 |
+
"learning_rate": 0.0002474631162288593,
|
| 455 |
+
"loss": 0.0089,
|
| 456 |
+
"step": 36500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.24,
|
| 460 |
+
"learning_rate": 0.0002467434328895286,
|
| 461 |
+
"loss": 0.0101,
|
| 462 |
+
"step": 37000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.26,
|
| 466 |
+
"learning_rate": 0.0002460237495501979,
|
| 467 |
+
"loss": 0.009,
|
| 468 |
+
"step": 37500
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.28,
|
| 472 |
+
"learning_rate": 0.0002453040662108672,
|
| 473 |
+
"loss": 0.0084,
|
| 474 |
+
"step": 38000
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.29,
|
| 478 |
+
"learning_rate": 0.0002445843828715365,
|
| 479 |
+
"loss": 0.0099,
|
| 480 |
+
"step": 38500
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.31,
|
| 484 |
+
"learning_rate": 0.0002438646995322058,
|
| 485 |
+
"loss": 0.0088,
|
| 486 |
+
"step": 39000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.33,
|
| 490 |
+
"learning_rate": 0.00024314501619287512,
|
| 491 |
+
"loss": 0.0096,
|
| 492 |
+
"step": 39500
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.34,
|
| 496 |
+
"learning_rate": 0.00024242533285354442,
|
| 497 |
+
"loss": 0.01,
|
| 498 |
+
"step": 40000
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.36,
|
| 502 |
+
"learning_rate": 0.00024170564951421373,
|
| 503 |
+
"loss": 0.0088,
|
| 504 |
+
"step": 40500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.38,
|
| 508 |
+
"learning_rate": 0.000240985966174883,
|
| 509 |
+
"loss": 0.0101,
|
| 510 |
+
"step": 41000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.39,
|
| 514 |
+
"learning_rate": 0.00024026628283555234,
|
| 515 |
+
"loss": 0.0093,
|
| 516 |
+
"step": 41500
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.41,
|
| 520 |
+
"learning_rate": 0.00023954659949622164,
|
| 521 |
+
"loss": 0.009,
|
| 522 |
+
"step": 42000
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.43,
|
| 526 |
+
"learning_rate": 0.00023882691615689094,
|
| 527 |
+
"loss": 0.0093,
|
| 528 |
+
"step": 42500
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.44,
|
| 532 |
+
"learning_rate": 0.00023810723281756025,
|
| 533 |
+
"loss": 0.0092,
|
| 534 |
+
"step": 43000
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.46,
|
| 538 |
+
"learning_rate": 0.00023738754947822955,
|
| 539 |
+
"loss": 0.01,
|
| 540 |
+
"step": 43500
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.48,
|
| 544 |
+
"learning_rate": 0.0002366678661388989,
|
| 545 |
+
"loss": 0.0089,
|
| 546 |
+
"step": 44000
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.49,
|
| 550 |
+
"learning_rate": 0.00023594818279956816,
|
| 551 |
+
"loss": 0.0079,
|
| 552 |
+
"step": 44500
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.51,
|
| 556 |
+
"learning_rate": 0.00023522849946023747,
|
| 557 |
+
"loss": 0.0091,
|
| 558 |
+
"step": 45000
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 1.53,
|
| 562 |
+
"learning_rate": 0.00023450881612090677,
|
| 563 |
+
"loss": 0.009,
|
| 564 |
+
"step": 45500
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.54,
|
| 568 |
+
"learning_rate": 0.00023378913278157608,
|
| 569 |
+
"loss": 0.01,
|
| 570 |
+
"step": 46000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.56,
|
| 574 |
+
"learning_rate": 0.0002330694494422454,
|
| 575 |
+
"loss": 0.0093,
|
| 576 |
+
"step": 46500
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.58,
|
| 580 |
+
"learning_rate": 0.00023234976610291472,
|
| 581 |
+
"loss": 0.0089,
|
| 582 |
+
"step": 47000
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.6,
|
| 586 |
+
"learning_rate": 0.000231630082763584,
|
| 587 |
+
"loss": 0.0098,
|
| 588 |
+
"step": 47500
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.61,
|
| 592 |
+
"learning_rate": 0.0002309103994242533,
|
| 593 |
+
"loss": 0.0101,
|
| 594 |
+
"step": 48000
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.63,
|
| 598 |
+
"learning_rate": 0.0002301907160849226,
|
| 599 |
+
"loss": 0.0094,
|
| 600 |
+
"step": 48500
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 1.65,
|
| 604 |
+
"learning_rate": 0.00022947103274559194,
|
| 605 |
+
"loss": 0.0092,
|
| 606 |
+
"step": 49000
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 1.66,
|
| 610 |
+
"learning_rate": 0.00022875134940626124,
|
| 611 |
+
"loss": 0.0102,
|
| 612 |
+
"step": 49500
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.68,
|
| 616 |
+
"learning_rate": 0.00022803166606693052,
|
| 617 |
+
"loss": 0.0091,
|
| 618 |
+
"step": 50000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.7,
|
| 622 |
+
"learning_rate": 0.00022731198272759982,
|
| 623 |
+
"loss": 0.0095,
|
| 624 |
+
"step": 50500
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.71,
|
| 628 |
+
"learning_rate": 0.00022659229938826913,
|
| 629 |
+
"loss": 0.0094,
|
| 630 |
+
"step": 51000
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 1.73,
|
| 634 |
+
"learning_rate": 0.00022587261604893846,
|
| 635 |
+
"loss": 0.0091,
|
| 636 |
+
"step": 51500
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.75,
|
| 640 |
+
"learning_rate": 0.00022515293270960777,
|
| 641 |
+
"loss": 0.0099,
|
| 642 |
+
"step": 52000
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.76,
|
| 646 |
+
"learning_rate": 0.00022443324937027707,
|
| 647 |
+
"loss": 0.0103,
|
| 648 |
+
"step": 52500
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.78,
|
| 652 |
+
"learning_rate": 0.00022371356603094635,
|
| 653 |
+
"loss": 0.0103,
|
| 654 |
+
"step": 53000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.8,
|
| 658 |
+
"learning_rate": 0.00022299388269161565,
|
| 659 |
+
"loss": 0.0105,
|
| 660 |
+
"step": 53500
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.81,
|
| 664 |
+
"learning_rate": 0.00022227419935228498,
|
| 665 |
+
"loss": 0.0097,
|
| 666 |
+
"step": 54000
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.83,
|
| 670 |
+
"learning_rate": 0.0002215545160129543,
|
| 671 |
+
"loss": 0.0099,
|
| 672 |
+
"step": 54500
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.85,
|
| 676 |
+
"learning_rate": 0.0002208348326736236,
|
| 677 |
+
"loss": 0.0099,
|
| 678 |
+
"step": 55000
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.86,
|
| 682 |
+
"learning_rate": 0.00022011514933429287,
|
| 683 |
+
"loss": 0.0099,
|
| 684 |
+
"step": 55500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.88,
|
| 688 |
+
"learning_rate": 0.00021939546599496218,
|
| 689 |
+
"loss": 0.0093,
|
| 690 |
+
"step": 56000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.9,
|
| 694 |
+
"learning_rate": 0.0002186757826556315,
|
| 695 |
+
"loss": 0.0091,
|
| 696 |
+
"step": 56500
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.91,
|
| 700 |
+
"learning_rate": 0.00021795609931630081,
|
| 701 |
+
"loss": 0.0096,
|
| 702 |
+
"step": 57000
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.93,
|
| 706 |
+
"learning_rate": 0.00021723641597697012,
|
| 707 |
+
"loss": 0.0103,
|
| 708 |
+
"step": 57500
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 1.95,
|
| 712 |
+
"learning_rate": 0.00021651673263763942,
|
| 713 |
+
"loss": 0.0095,
|
| 714 |
+
"step": 58000
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.96,
|
| 718 |
+
"learning_rate": 0.0002157970492983087,
|
| 719 |
+
"loss": 0.0104,
|
| 720 |
+
"step": 58500
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.98,
|
| 724 |
+
"learning_rate": 0.00021507736595897803,
|
| 725 |
+
"loss": 0.009,
|
| 726 |
+
"step": 59000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 2.0,
|
| 730 |
+
"learning_rate": 0.00021435768261964734,
|
| 731 |
+
"loss": 0.0097,
|
| 732 |
+
"step": 59500
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.0,
|
| 736 |
+
"eval_bleu": 41.3133,
|
| 737 |
+
"eval_gen_len": 13.0472,
|
| 738 |
+
"eval_loss": 0.01007869653403759,
|
| 739 |
+
"eval_runtime": 1065.665,
|
| 740 |
+
"eval_samples_per_second": 12.419,
|
| 741 |
+
"eval_steps_per_second": 6.209,
|
| 742 |
+
"step": 59550
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.02,
|
| 746 |
+
"learning_rate": 0.00021363799928031664,
|
| 747 |
+
"loss": 0.0073,
|
| 748 |
+
"step": 60000
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 2.03,
|
| 752 |
+
"learning_rate": 0.00021291831594098595,
|
| 753 |
+
"loss": 0.0066,
|
| 754 |
+
"step": 60500
|
| 755 |
+
}
|
| 756 |
+
],
|
| 757 |
+
"max_steps": 208425,
|
| 758 |
+
"num_train_epochs": 7,
|
| 759 |
+
"total_flos": 6.31369374988032e+16,
|
| 760 |
+
"trial_name": null,
|
| 761 |
+
"trial_params": null
|
| 762 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:359dedea125b9802a1c943527eae31642067b5fa2bebef90d2e1ebaf62108ca7
|
| 3 |
+
size 4536
|