Ahmed HAZOURLI (BFR)
commited on
Commit
•
5d43385
1
Parent(s):
6a060b6
FinancialBERT model
Browse files- config.json +3 -4
- optimizer.pt +3 -0
- pytorch_model.bin +2 -2
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- trainer_state.json +376 -0
- training_args.bin +3 -0
config.json
CHANGED
|
@@ -1,11 +1,10 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
| 8 |
-
"gradient_checkpointing": false,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
|
@@ -19,7 +18,7 @@
|
|
| 19 |
"pad_token_id": 0,
|
| 20 |
"position_embedding_type": "absolute",
|
| 21 |
"torch_dtype": "float32",
|
| 22 |
-
"transformers_version": "4.3
|
| 23 |
"type_vocab_size": 2,
|
| 24 |
"use_cache": true,
|
| 25 |
"vocab_size": 30873
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "yiyanghkust/finbert-pretrain",
|
| 3 |
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
|
|
|
| 8 |
"hidden_act": "gelu",
|
| 9 |
"hidden_dropout_prob": 0.1,
|
| 10 |
"hidden_size": 768,
|
|
|
|
| 18 |
"pad_token_id": 0,
|
| 19 |
"position_embedding_type": "absolute",
|
| 20 |
"torch_dtype": "float32",
|
| 21 |
+
"transformers_version": "4.11.3",
|
| 22 |
"type_vocab_size": 2,
|
| 23 |
"use_cache": true,
|
| 24 |
"vocab_size": 30873
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:341d38f413808753b6021444cbb214fabef5ffaf71fe393503a38489ee4faaec
|
| 3 |
+
size 878393999
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ca8d153f1176ab4c32c84920399708f9b141829f6634b8121cdc3a8a59dd690
|
| 3 |
+
size 439223687
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26c4882ca45d2d5f53ca75d9e2b10b1d72c61b642b4e81ff2280af722bd2d378
|
| 3 |
+
size 13623
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2db0d79aac40995c74029f564da57bd35d556559edd54ee0b5744bbd7cdc1125
|
| 3 |
+
size 623
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "
|
|
|
|
| 1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": null, "name_or_path": "yiyanghkust/finbert-pretrain", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,376 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.8670770831526923,
|
| 5 |
+
"global_step": 30000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 4.9277435764039425e-05,
|
| 13 |
+
"loss": 4.5138,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 4.855487152807885e-05,
|
| 19 |
+
"loss": 4.3608,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.04,
|
| 24 |
+
"learning_rate": 4.783230729211827e-05,
|
| 25 |
+
"loss": 4.031,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.06,
|
| 30 |
+
"learning_rate": 4.710974305615769e-05,
|
| 31 |
+
"loss": 3.3475,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.07,
|
| 36 |
+
"learning_rate": 4.638717882019712e-05,
|
| 37 |
+
"loss": 2.8365,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09,
|
| 42 |
+
"learning_rate": 4.5664614584236545e-05,
|
| 43 |
+
"loss": 2.5081,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1,
|
| 48 |
+
"learning_rate": 4.494205034827597e-05,
|
| 49 |
+
"loss": 2.2906,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.12,
|
| 54 |
+
"learning_rate": 4.421948611231539e-05,
|
| 55 |
+
"loss": 2.1787,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.13,
|
| 60 |
+
"learning_rate": 4.349692187635481e-05,
|
| 61 |
+
"loss": 2.1026,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.14,
|
| 66 |
+
"learning_rate": 4.277435764039423e-05,
|
| 67 |
+
"loss": 2.0387,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.16,
|
| 72 |
+
"learning_rate": 4.205179340443365e-05,
|
| 73 |
+
"loss": 2.0001,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.17,
|
| 78 |
+
"learning_rate": 4.1329229168473074e-05,
|
| 79 |
+
"loss": 1.9804,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.19,
|
| 84 |
+
"learning_rate": 4.06066649325125e-05,
|
| 85 |
+
"loss": 1.951,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2,
|
| 90 |
+
"learning_rate": 3.9884100696551927e-05,
|
| 91 |
+
"loss": 1.9113,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.22,
|
| 96 |
+
"learning_rate": 3.916153646059135e-05,
|
| 97 |
+
"loss": 1.9078,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.23,
|
| 102 |
+
"learning_rate": 3.843897222463077e-05,
|
| 103 |
+
"loss": 1.8793,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.25,
|
| 108 |
+
"learning_rate": 3.7716407988670195e-05,
|
| 109 |
+
"loss": 1.8833,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.26,
|
| 114 |
+
"learning_rate": 3.699384375270962e-05,
|
| 115 |
+
"loss": 1.8618,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.27,
|
| 120 |
+
"learning_rate": 3.627127951674904e-05,
|
| 121 |
+
"loss": 1.835,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.29,
|
| 126 |
+
"learning_rate": 3.554871528078846e-05,
|
| 127 |
+
"loss": 1.8187,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3,
|
| 132 |
+
"learning_rate": 3.4826151044827885e-05,
|
| 133 |
+
"loss": 1.8097,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.32,
|
| 138 |
+
"learning_rate": 3.410358680886731e-05,
|
| 139 |
+
"loss": 1.7973,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.33,
|
| 144 |
+
"learning_rate": 3.338102257290673e-05,
|
| 145 |
+
"loss": 1.8006,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.35,
|
| 150 |
+
"learning_rate": 3.265845833694616e-05,
|
| 151 |
+
"loss": 1.7698,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.36,
|
| 156 |
+
"learning_rate": 3.193589410098558e-05,
|
| 157 |
+
"loss": 1.7673,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.38,
|
| 162 |
+
"learning_rate": 3.1213329865025005e-05,
|
| 163 |
+
"loss": 1.7731,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.39,
|
| 168 |
+
"learning_rate": 3.0490765629064428e-05,
|
| 169 |
+
"loss": 1.7643,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.4,
|
| 174 |
+
"learning_rate": 2.976820139310385e-05,
|
| 175 |
+
"loss": 1.7534,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.42,
|
| 180 |
+
"learning_rate": 2.9045637157143273e-05,
|
| 181 |
+
"loss": 1.7307,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.43,
|
| 186 |
+
"learning_rate": 2.8323072921182693e-05,
|
| 187 |
+
"loss": 1.7279,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.45,
|
| 192 |
+
"learning_rate": 2.7600508685222115e-05,
|
| 193 |
+
"loss": 1.7162,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.46,
|
| 198 |
+
"learning_rate": 2.6877944449261538e-05,
|
| 199 |
+
"loss": 1.7006,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.48,
|
| 204 |
+
"learning_rate": 2.615538021330096e-05,
|
| 205 |
+
"loss": 1.7176,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.49,
|
| 210 |
+
"learning_rate": 2.5432815977340387e-05,
|
| 211 |
+
"loss": 1.6928,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.51,
|
| 216 |
+
"learning_rate": 2.471025174137981e-05,
|
| 217 |
+
"loss": 1.6819,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.52,
|
| 222 |
+
"learning_rate": 2.3987687505419232e-05,
|
| 223 |
+
"loss": 1.6864,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.53,
|
| 228 |
+
"learning_rate": 2.3265123269458655e-05,
|
| 229 |
+
"loss": 1.6813,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.55,
|
| 234 |
+
"learning_rate": 2.2542559033498077e-05,
|
| 235 |
+
"loss": 1.6785,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.56,
|
| 240 |
+
"learning_rate": 2.1819994797537503e-05,
|
| 241 |
+
"loss": 1.6734,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.58,
|
| 246 |
+
"learning_rate": 2.1097430561576926e-05,
|
| 247 |
+
"loss": 1.6543,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.59,
|
| 252 |
+
"learning_rate": 2.037486632561635e-05,
|
| 253 |
+
"loss": 1.6633,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.61,
|
| 258 |
+
"learning_rate": 1.965230208965577e-05,
|
| 259 |
+
"loss": 1.668,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.62,
|
| 264 |
+
"learning_rate": 1.8929737853695194e-05,
|
| 265 |
+
"loss": 1.6554,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.64,
|
| 270 |
+
"learning_rate": 1.820717361773462e-05,
|
| 271 |
+
"loss": 1.6451,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.65,
|
| 276 |
+
"learning_rate": 1.748460938177404e-05,
|
| 277 |
+
"loss": 1.6347,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.66,
|
| 282 |
+
"learning_rate": 1.6762045145813462e-05,
|
| 283 |
+
"loss": 1.6288,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.68,
|
| 288 |
+
"learning_rate": 1.6039480909852885e-05,
|
| 289 |
+
"loss": 1.6476,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.69,
|
| 294 |
+
"learning_rate": 1.531691667389231e-05,
|
| 295 |
+
"loss": 1.629,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.71,
|
| 300 |
+
"learning_rate": 1.4594352437931733e-05,
|
| 301 |
+
"loss": 1.6197,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.72,
|
| 306 |
+
"learning_rate": 1.3871788201971156e-05,
|
| 307 |
+
"loss": 1.6158,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.74,
|
| 312 |
+
"learning_rate": 1.3149223966010579e-05,
|
| 313 |
+
"loss": 1.6208,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.75,
|
| 318 |
+
"learning_rate": 1.2426659730050003e-05,
|
| 319 |
+
"loss": 1.6081,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.77,
|
| 324 |
+
"learning_rate": 1.1704095494089424e-05,
|
| 325 |
+
"loss": 1.6147,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 0.78,
|
| 330 |
+
"learning_rate": 1.0981531258128848e-05,
|
| 331 |
+
"loss": 1.6003,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.79,
|
| 336 |
+
"learning_rate": 1.0258967022168271e-05,
|
| 337 |
+
"loss": 1.5853,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.81,
|
| 342 |
+
"learning_rate": 9.536402786207694e-06,
|
| 343 |
+
"loss": 1.6039,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.82,
|
| 348 |
+
"learning_rate": 8.813838550247118e-06,
|
| 349 |
+
"loss": 1.594,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.84,
|
| 354 |
+
"learning_rate": 8.091274314286539e-06,
|
| 355 |
+
"loss": 1.5874,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.85,
|
| 360 |
+
"learning_rate": 7.3687100783259635e-06,
|
| 361 |
+
"loss": 1.5707,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.87,
|
| 366 |
+
"learning_rate": 6.646145842365387e-06,
|
| 367 |
+
"loss": 1.5902,
|
| 368 |
+
"step": 30000
|
| 369 |
+
}
|
| 370 |
+
],
|
| 371 |
+
"max_steps": 34599,
|
| 372 |
+
"num_train_epochs": 1,
|
| 373 |
+
"total_flos": 7.89617673216e+16,
|
| 374 |
+
"trial_name": null,
|
| 375 |
+
"trial_params": null
|
| 376 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0472f6463f4dfa6cf999584b9d6fd53d1a5eb8f38caaaef68f2961121dd5e971
|
| 3 |
+
size 2863
|