Add files
Browse files- README.md +68 -0
- all_results.json +8 -0
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +398 -3
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: out
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# out
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [/1TB_SSD/SB_AI/out_orig2](https://huggingface.co//1TB_SSD/SB_AI/out_orig2) on an unknown dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.0619
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 5e-05
|
| 36 |
+
- train_batch_size: 1
|
| 37 |
+
- eval_batch_size: 1
|
| 38 |
+
- seed: 3784447887
|
| 39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
+
- lr_scheduler_type: linear
|
| 41 |
+
- num_epochs: 1
|
| 42 |
+
|
| 43 |
+
### Training results
|
| 44 |
+
|
| 45 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 46 |
+
|:-------------:|:-----:|:-------:|:---------------:|
|
| 47 |
+
| 0.0867 | 0.07 | 75000 | 0.0742 |
|
| 48 |
+
| 0.0783 | 0.13 | 150000 | 0.0695 |
|
| 49 |
+
| 0.0719 | 0.2 | 225000 | 0.0732 |
|
| 50 |
+
| 0.0743 | 0.27 | 300000 | 0.0663 |
|
| 51 |
+
| 0.0659 | 0.34 | 375000 | 0.0686 |
|
| 52 |
+
| 0.0664 | 0.4 | 450000 | 0.0683 |
|
| 53 |
+
| 0.0637 | 0.47 | 525000 | 0.0680 |
|
| 54 |
+
| 0.0655 | 0.54 | 600000 | 0.0641 |
|
| 55 |
+
| 0.0676 | 0.6 | 675000 | 0.0644 |
|
| 56 |
+
| 0.0704 | 0.67 | 750000 | 0.0645 |
|
| 57 |
+
| 0.0687 | 0.74 | 825000 | 0.0610 |
|
| 58 |
+
| 0.059 | 0.81 | 900000 | 0.0652 |
|
| 59 |
+
| 0.0666 | 0.87 | 975000 | 0.0619 |
|
| 60 |
+
| 0.0624 | 0.94 | 1050000 | 0.0619 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- Transformers 4.15.0
|
| 66 |
+
- Pytorch 1.10.1+cu113
|
| 67 |
+
- Datasets 1.17.0
|
| 68 |
+
- Tokenizers 0.10.3
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.0695511792498969,
|
| 4 |
+
"train_runtime": 176193.0564,
|
| 5 |
+
"train_samples": 1116594,
|
| 6 |
+
"train_samples_per_second": 6.337,
|
| 7 |
+
"train_steps_per_second": 6.337
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 891703231
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fb22fb40259e3ef7d648c85bc99a714855c5d5d75c32dd548bebf38df101aea
|
| 3 |
size 891703231
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.0695511792498969,
|
| 4 |
+
"train_runtime": 176193.0564,
|
| 5 |
+
"train_samples": 1116594,
|
| 6 |
+
"train_samples_per_second": 6.337,
|
| 7 |
+
"train_steps_per_second": 6.337
|
| 8 |
+
}
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -1070,11 +1070,406 @@
|
|
| 1070 |
"learning_rate": 1.328119262686348e-05,
|
| 1071 |
"loss": 0.0676,
|
| 1072 |
"step": 820000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1073 |
}
|
| 1074 |
],
|
| 1075 |
"max_steps": 1116594,
|
| 1076 |
"num_train_epochs": 1,
|
| 1077 |
-
"total_flos":
|
| 1078 |
"trial_name": null,
|
| 1079 |
"trial_params": null
|
| 1080 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"global_step": 1116594,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 1070 |
"learning_rate": 1.328119262686348e-05,
|
| 1071 |
"loss": 0.0676,
|
| 1072 |
"step": 820000
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 0.74,
|
| 1076 |
+
"learning_rate": 1.305729745995411e-05,
|
| 1077 |
+
"loss": 0.0687,
|
| 1078 |
+
"step": 825000
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 0.74,
|
| 1082 |
+
"eval_loss": 0.061014574021101,
|
| 1083 |
+
"eval_runtime": 1687.4471,
|
| 1084 |
+
"eval_samples_per_second": 36.761,
|
| 1085 |
+
"eval_steps_per_second": 36.761,
|
| 1086 |
+
"step": 825000
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 0.74,
|
| 1090 |
+
"learning_rate": 1.2833402293044742e-05,
|
| 1091 |
+
"loss": 0.0679,
|
| 1092 |
+
"step": 830000
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 0.75,
|
| 1096 |
+
"learning_rate": 1.2609507126135372e-05,
|
| 1097 |
+
"loss": 0.0683,
|
| 1098 |
+
"step": 835000
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.75,
|
| 1102 |
+
"learning_rate": 1.2385611959226004e-05,
|
| 1103 |
+
"loss": 0.0702,
|
| 1104 |
+
"step": 840000
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.76,
|
| 1108 |
+
"learning_rate": 1.2161716792316636e-05,
|
| 1109 |
+
"loss": 0.0652,
|
| 1110 |
+
"step": 845000
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 0.76,
|
| 1114 |
+
"learning_rate": 1.1937821625407265e-05,
|
| 1115 |
+
"loss": 0.0636,
|
| 1116 |
+
"step": 850000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.77,
|
| 1120 |
+
"learning_rate": 1.1713926458497897e-05,
|
| 1121 |
+
"loss": 0.0637,
|
| 1122 |
+
"step": 855000
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.77,
|
| 1126 |
+
"learning_rate": 1.1490031291588529e-05,
|
| 1127 |
+
"loss": 0.0628,
|
| 1128 |
+
"step": 860000
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 0.77,
|
| 1132 |
+
"learning_rate": 1.126613612467916e-05,
|
| 1133 |
+
"loss": 0.0701,
|
| 1134 |
+
"step": 865000
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.78,
|
| 1138 |
+
"learning_rate": 1.104224095776979e-05,
|
| 1139 |
+
"loss": 0.0663,
|
| 1140 |
+
"step": 870000
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.78,
|
| 1144 |
+
"learning_rate": 1.081834579086042e-05,
|
| 1145 |
+
"loss": 0.0686,
|
| 1146 |
+
"step": 875000
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.79,
|
| 1150 |
+
"learning_rate": 1.0594450623951052e-05,
|
| 1151 |
+
"loss": 0.0655,
|
| 1152 |
+
"step": 880000
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 0.79,
|
| 1156 |
+
"learning_rate": 1.0370555457041682e-05,
|
| 1157 |
+
"loss": 0.0622,
|
| 1158 |
+
"step": 885000
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.8,
|
| 1162 |
+
"learning_rate": 1.0146660290132313e-05,
|
| 1163 |
+
"loss": 0.0585,
|
| 1164 |
+
"step": 890000
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.8,
|
| 1168 |
+
"learning_rate": 9.922765123222945e-06,
|
| 1169 |
+
"loss": 0.0658,
|
| 1170 |
+
"step": 895000
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.81,
|
| 1174 |
+
"learning_rate": 9.698869956313575e-06,
|
| 1175 |
+
"loss": 0.059,
|
| 1176 |
+
"step": 900000
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 0.81,
|
| 1180 |
+
"eval_loss": 0.06522925943136215,
|
| 1181 |
+
"eval_runtime": 1686.0104,
|
| 1182 |
+
"eval_samples_per_second": 36.793,
|
| 1183 |
+
"eval_steps_per_second": 36.793,
|
| 1184 |
+
"step": 900000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 0.81,
|
| 1188 |
+
"learning_rate": 9.474974789404206e-06,
|
| 1189 |
+
"loss": 0.0624,
|
| 1190 |
+
"step": 905000
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 0.81,
|
| 1194 |
+
"learning_rate": 9.251079622494838e-06,
|
| 1195 |
+
"loss": 0.0722,
|
| 1196 |
+
"step": 910000
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.82,
|
| 1200 |
+
"learning_rate": 9.02718445558547e-06,
|
| 1201 |
+
"loss": 0.0599,
|
| 1202 |
+
"step": 915000
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.82,
|
| 1206 |
+
"learning_rate": 8.803289288676098e-06,
|
| 1207 |
+
"loss": 0.0699,
|
| 1208 |
+
"step": 920000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.83,
|
| 1212 |
+
"learning_rate": 8.57939412176673e-06,
|
| 1213 |
+
"loss": 0.0606,
|
| 1214 |
+
"step": 925000
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.83,
|
| 1218 |
+
"learning_rate": 8.355498954857361e-06,
|
| 1219 |
+
"loss": 0.0696,
|
| 1220 |
+
"step": 930000
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.84,
|
| 1224 |
+
"learning_rate": 8.131603787947991e-06,
|
| 1225 |
+
"loss": 0.0626,
|
| 1226 |
+
"step": 935000
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 0.84,
|
| 1230 |
+
"learning_rate": 7.907708621038623e-06,
|
| 1231 |
+
"loss": 0.0658,
|
| 1232 |
+
"step": 940000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 0.85,
|
| 1236 |
+
"learning_rate": 7.683813454129254e-06,
|
| 1237 |
+
"loss": 0.0641,
|
| 1238 |
+
"step": 945000
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.85,
|
| 1242 |
+
"learning_rate": 7.459918287219884e-06,
|
| 1243 |
+
"loss": 0.0659,
|
| 1244 |
+
"step": 950000
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 0.86,
|
| 1248 |
+
"learning_rate": 7.236023120310516e-06,
|
| 1249 |
+
"loss": 0.062,
|
| 1250 |
+
"step": 955000
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.86,
|
| 1254 |
+
"learning_rate": 7.012127953401147e-06,
|
| 1255 |
+
"loss": 0.0658,
|
| 1256 |
+
"step": 960000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.86,
|
| 1260 |
+
"learning_rate": 6.788232786491779e-06,
|
| 1261 |
+
"loss": 0.0624,
|
| 1262 |
+
"step": 965000
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.87,
|
| 1266 |
+
"learning_rate": 6.564337619582408e-06,
|
| 1267 |
+
"loss": 0.0619,
|
| 1268 |
+
"step": 970000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 0.87,
|
| 1272 |
+
"learning_rate": 6.34044245267304e-06,
|
| 1273 |
+
"loss": 0.0666,
|
| 1274 |
+
"step": 975000
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 0.87,
|
| 1278 |
+
"eval_loss": 0.061893004924058914,
|
| 1279 |
+
"eval_runtime": 1682.9916,
|
| 1280 |
+
"eval_samples_per_second": 36.859,
|
| 1281 |
+
"eval_steps_per_second": 36.859,
|
| 1282 |
+
"step": 975000
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 0.88,
|
| 1286 |
+
"learning_rate": 6.116547285763671e-06,
|
| 1287 |
+
"loss": 0.0665,
|
| 1288 |
+
"step": 980000
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 0.88,
|
| 1292 |
+
"learning_rate": 5.892652118854302e-06,
|
| 1293 |
+
"loss": 0.0687,
|
| 1294 |
+
"step": 985000
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.89,
|
| 1298 |
+
"learning_rate": 5.668756951944933e-06,
|
| 1299 |
+
"loss": 0.0656,
|
| 1300 |
+
"step": 990000
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.89,
|
| 1304 |
+
"learning_rate": 5.444861785035564e-06,
|
| 1305 |
+
"loss": 0.0678,
|
| 1306 |
+
"step": 995000
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.9,
|
| 1310 |
+
"learning_rate": 5.220966618126195e-06,
|
| 1311 |
+
"loss": 0.0645,
|
| 1312 |
+
"step": 1000000
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.9,
|
| 1316 |
+
"learning_rate": 4.997071451216825e-06,
|
| 1317 |
+
"loss": 0.0661,
|
| 1318 |
+
"step": 1005000
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.9,
|
| 1322 |
+
"learning_rate": 4.773176284307457e-06,
|
| 1323 |
+
"loss": 0.0672,
|
| 1324 |
+
"step": 1010000
|
| 1325 |
+
},
|
| 1326 |
+
{
|
| 1327 |
+
"epoch": 0.91,
|
| 1328 |
+
"learning_rate": 4.5492811173980875e-06,
|
| 1329 |
+
"loss": 0.0618,
|
| 1330 |
+
"step": 1015000
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 0.91,
|
| 1334 |
+
"learning_rate": 4.325385950488719e-06,
|
| 1335 |
+
"loss": 0.064,
|
| 1336 |
+
"step": 1020000
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.92,
|
| 1340 |
+
"learning_rate": 4.101490783579349e-06,
|
| 1341 |
+
"loss": 0.0622,
|
| 1342 |
+
"step": 1025000
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.92,
|
| 1346 |
+
"learning_rate": 3.87759561666998e-06,
|
| 1347 |
+
"loss": 0.0673,
|
| 1348 |
+
"step": 1030000
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 0.93,
|
| 1352 |
+
"learning_rate": 3.6537004497606115e-06,
|
| 1353 |
+
"loss": 0.0643,
|
| 1354 |
+
"step": 1035000
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.93,
|
| 1358 |
+
"learning_rate": 3.4298052828512423e-06,
|
| 1359 |
+
"loss": 0.0688,
|
| 1360 |
+
"step": 1040000
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.94,
|
| 1364 |
+
"learning_rate": 3.2059101159418736e-06,
|
| 1365 |
+
"loss": 0.0642,
|
| 1366 |
+
"step": 1045000
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 0.94,
|
| 1370 |
+
"learning_rate": 2.9820149490325044e-06,
|
| 1371 |
+
"loss": 0.0624,
|
| 1372 |
+
"step": 1050000
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 0.94,
|
| 1376 |
+
"eval_loss": 0.061922721564769745,
|
| 1377 |
+
"eval_runtime": 1682.5086,
|
| 1378 |
+
"eval_samples_per_second": 36.869,
|
| 1379 |
+
"eval_steps_per_second": 36.869,
|
| 1380 |
+
"step": 1050000
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 0.94,
|
| 1384 |
+
"learning_rate": 2.758119782123135e-06,
|
| 1385 |
+
"loss": 0.0636,
|
| 1386 |
+
"step": 1055000
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 0.95,
|
| 1390 |
+
"learning_rate": 2.5342246152137664e-06,
|
| 1391 |
+
"loss": 0.0636,
|
| 1392 |
+
"step": 1060000
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.95,
|
| 1396 |
+
"learning_rate": 2.310329448304397e-06,
|
| 1397 |
+
"loss": 0.0669,
|
| 1398 |
+
"step": 1065000
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 0.96,
|
| 1402 |
+
"learning_rate": 2.086434281395028e-06,
|
| 1403 |
+
"loss": 0.0608,
|
| 1404 |
+
"step": 1070000
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 0.96,
|
| 1408 |
+
"learning_rate": 1.862539114485659e-06,
|
| 1409 |
+
"loss": 0.0604,
|
| 1410 |
+
"step": 1075000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.97,
|
| 1414 |
+
"learning_rate": 1.63864394757629e-06,
|
| 1415 |
+
"loss": 0.0656,
|
| 1416 |
+
"step": 1080000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.97,
|
| 1420 |
+
"learning_rate": 1.4147487806669212e-06,
|
| 1421 |
+
"loss": 0.0693,
|
| 1422 |
+
"step": 1085000
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 0.98,
|
| 1426 |
+
"learning_rate": 1.190853613757552e-06,
|
| 1427 |
+
"loss": 0.0604,
|
| 1428 |
+
"step": 1090000
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 0.98,
|
| 1432 |
+
"learning_rate": 9.66958446848183e-07,
|
| 1433 |
+
"loss": 0.0665,
|
| 1434 |
+
"step": 1095000
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.99,
|
| 1438 |
+
"learning_rate": 7.43063279938814e-07,
|
| 1439 |
+
"loss": 0.0642,
|
| 1440 |
+
"step": 1100000
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 0.99,
|
| 1444 |
+
"learning_rate": 5.191681130294449e-07,
|
| 1445 |
+
"loss": 0.067,
|
| 1446 |
+
"step": 1105000
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 0.99,
|
| 1450 |
+
"learning_rate": 2.952729461200759e-07,
|
| 1451 |
+
"loss": 0.0638,
|
| 1452 |
+
"step": 1110000
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.0,
|
| 1456 |
+
"learning_rate": 7.137777921070686e-08,
|
| 1457 |
+
"loss": 0.0596,
|
| 1458 |
+
"step": 1115000
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.0,
|
| 1462 |
+
"step": 1116594,
|
| 1463 |
+
"total_flos": 3.3533589180916224e+17,
|
| 1464 |
+
"train_loss": 0.0695511792498969,
|
| 1465 |
+
"train_runtime": 176193.0564,
|
| 1466 |
+
"train_samples_per_second": 6.337,
|
| 1467 |
+
"train_steps_per_second": 6.337
|
| 1468 |
}
|
| 1469 |
],
|
| 1470 |
"max_steps": 1116594,
|
| 1471 |
"num_train_epochs": 1,
|
| 1472 |
+
"total_flos": 3.3533589180916224e+17,
|
| 1473 |
"trial_name": null,
|
| 1474 |
"trial_params": null
|
| 1475 |
}
|