Commit ·
ff7648f
1
Parent(s): 3a52130
Upload folder using huggingface_hub
Browse files- config.json +37 -0
- generation_config.json +9 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +499 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bmd1905/vietnamese-correction",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"MBartForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"d_model": 1024,
|
| 12 |
+
"decoder_attention_heads": 16,
|
| 13 |
+
"decoder_ffn_dim": 4096,
|
| 14 |
+
"decoder_layerdrop": 0.0,
|
| 15 |
+
"decoder_layers": 12,
|
| 16 |
+
"decoder_start_token_id": 2,
|
| 17 |
+
"dropout": 0.1,
|
| 18 |
+
"encoder_attention_heads": 16,
|
| 19 |
+
"encoder_ffn_dim": 4096,
|
| 20 |
+
"encoder_layerdrop": 0.0,
|
| 21 |
+
"encoder_layers": 12,
|
| 22 |
+
"eos_token_id": 2,
|
| 23 |
+
"forced_eos_token_id": 2,
|
| 24 |
+
"gradient_checkpointing": false,
|
| 25 |
+
"init_std": 0.02,
|
| 26 |
+
"is_encoder_decoder": true,
|
| 27 |
+
"max_position_embeddings": 1024,
|
| 28 |
+
"model_type": "mbart",
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"scale_embedding": false,
|
| 32 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.33.0",
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 64002
|
| 37 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_eos_token_id": 2,
|
| 7 |
+
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "4.33.0"
|
| 9 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce951dfd11d5068a0b2cc9944ee4f5e84a2bdded56edd18a8f97602c12c31f24
|
| 3 |
+
size 3363329126
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1e66e908906fbc3e33377187c4cbe9a26b139873d9fa4c114e785eb0f694679
|
| 3 |
+
size 1681880797
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79260107fb39495a47cfdcfa17ff284e7ab4ac8acb3038ef0761086653add41f
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8094b28eee6977ee97ee47596baa7b067529c331d57a3d80bb9e5d60765a0c9
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,499 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.7161760674100723,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 5e-06,
|
| 14 |
+
"loss": 6.8393,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 1e-05,
|
| 20 |
+
"loss": 4.0541,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.03,
|
| 25 |
+
"learning_rate": 1.5e-05,
|
| 26 |
+
"loss": 3.3832,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.04,
|
| 31 |
+
"learning_rate": 2e-05,
|
| 32 |
+
"loss": 3.0121,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.04,
|
| 37 |
+
"learning_rate": 2.5e-05,
|
| 38 |
+
"loss": 2.7978,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.05,
|
| 43 |
+
"learning_rate": 3e-05,
|
| 44 |
+
"loss": 2.6647,
|
| 45 |
+
"step": 600
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"learning_rate": 3.5e-05,
|
| 50 |
+
"loss": 2.5648,
|
| 51 |
+
"step": 700
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07,
|
| 55 |
+
"learning_rate": 4e-05,
|
| 56 |
+
"loss": 2.4824,
|
| 57 |
+
"step": 800
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.08,
|
| 61 |
+
"learning_rate": 4.5e-05,
|
| 62 |
+
"loss": 2.4302,
|
| 63 |
+
"step": 900
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.09,
|
| 67 |
+
"learning_rate": 5e-05,
|
| 68 |
+
"loss": 2.3927,
|
| 69 |
+
"step": 1000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.1,
|
| 73 |
+
"learning_rate": 5.500000000000001e-05,
|
| 74 |
+
"loss": 2.3448,
|
| 75 |
+
"step": 1100
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.11,
|
| 79 |
+
"learning_rate": 6e-05,
|
| 80 |
+
"loss": 2.3187,
|
| 81 |
+
"step": 1200
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.12,
|
| 85 |
+
"learning_rate": 6.500000000000001e-05,
|
| 86 |
+
"loss": 2.2914,
|
| 87 |
+
"step": 1300
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.13,
|
| 91 |
+
"learning_rate": 7e-05,
|
| 92 |
+
"loss": 2.2567,
|
| 93 |
+
"step": 1400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.13,
|
| 97 |
+
"learning_rate": 7.500000000000001e-05,
|
| 98 |
+
"loss": 2.2325,
|
| 99 |
+
"step": 1500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.14,
|
| 103 |
+
"learning_rate": 8e-05,
|
| 104 |
+
"loss": 2.2113,
|
| 105 |
+
"step": 1600
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.15,
|
| 109 |
+
"learning_rate": 8.5e-05,
|
| 110 |
+
"loss": 2.1963,
|
| 111 |
+
"step": 1700
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.16,
|
| 115 |
+
"learning_rate": 9e-05,
|
| 116 |
+
"loss": 2.1679,
|
| 117 |
+
"step": 1800
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.17,
|
| 121 |
+
"learning_rate": 9.5e-05,
|
| 122 |
+
"loss": 2.1459,
|
| 123 |
+
"step": 1900
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.18,
|
| 127 |
+
"learning_rate": 0.0001,
|
| 128 |
+
"loss": 2.1606,
|
| 129 |
+
"step": 2000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.19,
|
| 133 |
+
"learning_rate": 9.890948745910579e-05,
|
| 134 |
+
"loss": 2.1069,
|
| 135 |
+
"step": 2100
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.2,
|
| 139 |
+
"learning_rate": 9.781897491821155e-05,
|
| 140 |
+
"loss": 2.1075,
|
| 141 |
+
"step": 2200
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.21,
|
| 145 |
+
"learning_rate": 9.672846237731734e-05,
|
| 146 |
+
"loss": 2.0788,
|
| 147 |
+
"step": 2300
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.21,
|
| 151 |
+
"learning_rate": 9.563794983642313e-05,
|
| 152 |
+
"loss": 2.0525,
|
| 153 |
+
"step": 2400
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.22,
|
| 157 |
+
"learning_rate": 9.45474372955289e-05,
|
| 158 |
+
"loss": 2.043,
|
| 159 |
+
"step": 2500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.23,
|
| 163 |
+
"learning_rate": 9.345692475463468e-05,
|
| 164 |
+
"loss": 2.0098,
|
| 165 |
+
"step": 2600
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.24,
|
| 169 |
+
"learning_rate": 9.236641221374047e-05,
|
| 170 |
+
"loss": 1.9921,
|
| 171 |
+
"step": 2700
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.25,
|
| 175 |
+
"learning_rate": 9.127589967284624e-05,
|
| 176 |
+
"loss": 1.9714,
|
| 177 |
+
"step": 2800
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.26,
|
| 181 |
+
"learning_rate": 9.018538713195203e-05,
|
| 182 |
+
"loss": 1.9696,
|
| 183 |
+
"step": 2900
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.27,
|
| 187 |
+
"learning_rate": 8.90948745910578e-05,
|
| 188 |
+
"loss": 1.9363,
|
| 189 |
+
"step": 3000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.28,
|
| 193 |
+
"learning_rate": 8.800436205016358e-05,
|
| 194 |
+
"loss": 1.9166,
|
| 195 |
+
"step": 3100
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.29,
|
| 199 |
+
"learning_rate": 8.691384950926937e-05,
|
| 200 |
+
"loss": 1.9182,
|
| 201 |
+
"step": 3200
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.3,
|
| 205 |
+
"learning_rate": 8.582333696837514e-05,
|
| 206 |
+
"loss": 1.9062,
|
| 207 |
+
"step": 3300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.3,
|
| 211 |
+
"learning_rate": 8.473282442748092e-05,
|
| 212 |
+
"loss": 1.8886,
|
| 213 |
+
"step": 3400
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.31,
|
| 217 |
+
"learning_rate": 8.36423118865867e-05,
|
| 218 |
+
"loss": 1.8874,
|
| 219 |
+
"step": 3500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.32,
|
| 223 |
+
"learning_rate": 8.255179934569248e-05,
|
| 224 |
+
"loss": 1.8618,
|
| 225 |
+
"step": 3600
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.33,
|
| 229 |
+
"learning_rate": 8.146128680479825e-05,
|
| 230 |
+
"loss": 1.8587,
|
| 231 |
+
"step": 3700
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.34,
|
| 235 |
+
"learning_rate": 8.037077426390404e-05,
|
| 236 |
+
"loss": 1.8326,
|
| 237 |
+
"step": 3800
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.35,
|
| 241 |
+
"learning_rate": 7.928026172300981e-05,
|
| 242 |
+
"loss": 1.8549,
|
| 243 |
+
"step": 3900
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.36,
|
| 247 |
+
"learning_rate": 7.81897491821156e-05,
|
| 248 |
+
"loss": 1.8167,
|
| 249 |
+
"step": 4000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.37,
|
| 253 |
+
"learning_rate": 7.709923664122138e-05,
|
| 254 |
+
"loss": 1.8316,
|
| 255 |
+
"step": 4100
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.38,
|
| 259 |
+
"learning_rate": 7.600872410032715e-05,
|
| 260 |
+
"loss": 1.8188,
|
| 261 |
+
"step": 4200
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.38,
|
| 265 |
+
"learning_rate": 7.491821155943294e-05,
|
| 266 |
+
"loss": 1.7976,
|
| 267 |
+
"step": 4300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.39,
|
| 271 |
+
"learning_rate": 7.382769901853873e-05,
|
| 272 |
+
"loss": 1.7888,
|
| 273 |
+
"step": 4400
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.4,
|
| 277 |
+
"learning_rate": 7.273718647764449e-05,
|
| 278 |
+
"loss": 1.7899,
|
| 279 |
+
"step": 4500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.41,
|
| 283 |
+
"learning_rate": 7.164667393675028e-05,
|
| 284 |
+
"loss": 1.79,
|
| 285 |
+
"step": 4600
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.42,
|
| 289 |
+
"learning_rate": 7.055616139585605e-05,
|
| 290 |
+
"loss": 1.7564,
|
| 291 |
+
"step": 4700
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.43,
|
| 295 |
+
"learning_rate": 6.946564885496184e-05,
|
| 296 |
+
"loss": 1.7666,
|
| 297 |
+
"step": 4800
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.44,
|
| 301 |
+
"learning_rate": 6.837513631406761e-05,
|
| 302 |
+
"loss": 1.7574,
|
| 303 |
+
"step": 4900
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.45,
|
| 307 |
+
"learning_rate": 6.728462377317339e-05,
|
| 308 |
+
"loss": 1.7588,
|
| 309 |
+
"step": 5000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.46,
|
| 313 |
+
"learning_rate": 6.619411123227918e-05,
|
| 314 |
+
"loss": 1.7476,
|
| 315 |
+
"step": 5100
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.47,
|
| 319 |
+
"learning_rate": 6.510359869138496e-05,
|
| 320 |
+
"loss": 1.7251,
|
| 321 |
+
"step": 5200
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.47,
|
| 325 |
+
"learning_rate": 6.401308615049072e-05,
|
| 326 |
+
"loss": 1.7143,
|
| 327 |
+
"step": 5300
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.48,
|
| 331 |
+
"learning_rate": 6.292257360959651e-05,
|
| 332 |
+
"loss": 1.703,
|
| 333 |
+
"step": 5400
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.49,
|
| 337 |
+
"learning_rate": 6.18320610687023e-05,
|
| 338 |
+
"loss": 1.71,
|
| 339 |
+
"step": 5500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.5,
|
| 343 |
+
"learning_rate": 6.074154852780807e-05,
|
| 344 |
+
"loss": 1.6915,
|
| 345 |
+
"step": 5600
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.51,
|
| 349 |
+
"learning_rate": 5.965103598691385e-05,
|
| 350 |
+
"loss": 1.6904,
|
| 351 |
+
"step": 5700
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.52,
|
| 355 |
+
"learning_rate": 5.856052344601963e-05,
|
| 356 |
+
"loss": 1.6986,
|
| 357 |
+
"step": 5800
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.53,
|
| 361 |
+
"learning_rate": 5.747001090512541e-05,
|
| 362 |
+
"loss": 1.686,
|
| 363 |
+
"step": 5900
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.54,
|
| 367 |
+
"learning_rate": 5.6379498364231187e-05,
|
| 368 |
+
"loss": 1.6657,
|
| 369 |
+
"step": 6000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.55,
|
| 373 |
+
"learning_rate": 5.528898582333697e-05,
|
| 374 |
+
"loss": 1.658,
|
| 375 |
+
"step": 6100
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.56,
|
| 379 |
+
"learning_rate": 5.419847328244275e-05,
|
| 380 |
+
"loss": 1.6649,
|
| 381 |
+
"step": 6200
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.56,
|
| 385 |
+
"learning_rate": 5.310796074154854e-05,
|
| 386 |
+
"loss": 1.6459,
|
| 387 |
+
"step": 6300
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.57,
|
| 391 |
+
"learning_rate": 5.2017448200654305e-05,
|
| 392 |
+
"loss": 1.6521,
|
| 393 |
+
"step": 6400
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.58,
|
| 397 |
+
"learning_rate": 5.0926935659760086e-05,
|
| 398 |
+
"loss": 1.6366,
|
| 399 |
+
"step": 6500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.59,
|
| 403 |
+
"learning_rate": 4.9836423118865874e-05,
|
| 404 |
+
"loss": 1.6311,
|
| 405 |
+
"step": 6600
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.6,
|
| 409 |
+
"learning_rate": 4.874591057797165e-05,
|
| 410 |
+
"loss": 1.6279,
|
| 411 |
+
"step": 6700
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.61,
|
| 415 |
+
"learning_rate": 4.765539803707743e-05,
|
| 416 |
+
"loss": 1.6249,
|
| 417 |
+
"step": 6800
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.62,
|
| 421 |
+
"learning_rate": 4.656488549618321e-05,
|
| 422 |
+
"loss": 1.6161,
|
| 423 |
+
"step": 6900
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.63,
|
| 427 |
+
"learning_rate": 4.547437295528899e-05,
|
| 428 |
+
"loss": 1.612,
|
| 429 |
+
"step": 7000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.64,
|
| 433 |
+
"learning_rate": 4.438386041439477e-05,
|
| 434 |
+
"loss": 1.6116,
|
| 435 |
+
"step": 7100
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.64,
|
| 439 |
+
"learning_rate": 4.329334787350055e-05,
|
| 440 |
+
"loss": 1.589,
|
| 441 |
+
"step": 7200
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.65,
|
| 445 |
+
"learning_rate": 4.220283533260633e-05,
|
| 446 |
+
"loss": 1.6049,
|
| 447 |
+
"step": 7300
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.66,
|
| 451 |
+
"learning_rate": 4.1112322791712104e-05,
|
| 452 |
+
"loss": 1.5986,
|
| 453 |
+
"step": 7400
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.67,
|
| 457 |
+
"learning_rate": 4.0021810250817885e-05,
|
| 458 |
+
"loss": 1.5782,
|
| 459 |
+
"step": 7500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.68,
|
| 463 |
+
"learning_rate": 3.8931297709923666e-05,
|
| 464 |
+
"loss": 1.5872,
|
| 465 |
+
"step": 7600
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.69,
|
| 469 |
+
"learning_rate": 3.784078516902945e-05,
|
| 470 |
+
"loss": 1.5697,
|
| 471 |
+
"step": 7700
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.7,
|
| 475 |
+
"learning_rate": 3.675027262813522e-05,
|
| 476 |
+
"loss": 1.5666,
|
| 477 |
+
"step": 7800
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.71,
|
| 481 |
+
"learning_rate": 3.565976008724101e-05,
|
| 482 |
+
"loss": 1.5668,
|
| 483 |
+
"step": 7900
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.72,
|
| 487 |
+
"learning_rate": 3.4569247546346784e-05,
|
| 488 |
+
"loss": 1.571,
|
| 489 |
+
"step": 8000
|
| 490 |
+
}
|
| 491 |
+
],
|
| 492 |
+
"logging_steps": 100,
|
| 493 |
+
"max_steps": 11170,
|
| 494 |
+
"num_train_epochs": 1,
|
| 495 |
+
"save_steps": 1000,
|
| 496 |
+
"total_flos": 1.90707419578368e+17,
|
| 497 |
+
"trial_name": null,
|
| 498 |
+
"trial_params": null
|
| 499 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:192c5e11577d38899432f11c33004f02e390279d3eff53455ae6b847e57f8458
|
| 3 |
+
size 4155
|