Commit
·
3c99844
1
Parent(s):
278086c
huggingartists
Browse files- README.md +3 -3
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +537 -7
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
| 45 |
dataset = load_dataset("huggingartists/eminem")
|
| 46 |
```
|
| 47 |
|
| 48 |
-
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 49 |
|
| 50 |
## Training procedure
|
| 51 |
|
| 52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Eminem's lyrics.
|
| 53 |
|
| 54 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 55 |
|
| 56 |
-
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
|
|
|
| 45 |
dataset = load_dataset("huggingartists/eminem")
|
| 46 |
```
|
| 47 |
|
| 48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1mu4lqjp/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
|
| 49 |
|
| 50 |
## Training procedure
|
| 51 |
|
| 52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Eminem's lyrics.
|
| 53 |
|
| 54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2q3s5jtp) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2q3s5jtp/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 2.
|
|
|
|
| 1 |
+
{"eval_loss": 2.2795188426971436, "eval_runtime": 31.0656, "eval_samples_per_second": 22.275, "eval_steps_per_second": 2.801, "epoch": 3.0}
|
flax_model.msgpack
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497764120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:778af938d1eaa3d3f9dabbca66905ddad8fd0ef1c2c6856e32e51560809f9528
|
| 3 |
size 497764120
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 995604017
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f78b60a25dedda811fb282751adbda74c6f4550043a2cf072063f6a0c4267b91
|
| 3 |
size 995604017
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 510403817
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ceaf064a30f42afdc18a8bbf3c37df3a2224d7bdbc5d2eb4450c995c4f5e6d6
|
| 3 |
size 510403817
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d122a44853bfd4a9455393e12da8ebc33e470bae150af53bcaf049c301e63b3
|
| 3 |
size 14503
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a0f31f350ab98f69a90467f5115b0c4ab363327ccd3ccde8a452d9f884d07bb
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 3 |
-
"best_model_checkpoint": "output/eminem/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -1114,11 +1114,541 @@
|
|
| 1114 |
"eval_samples_per_second": 20.932,
|
| 1115 |
"eval_steps_per_second": 2.645,
|
| 1116 |
"step": 910
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1117 |
}
|
| 1118 |
],
|
| 1119 |
-
"max_steps":
|
| 1120 |
-
"num_train_epochs":
|
| 1121 |
-
"total_flos":
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
| 1124 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.2795188426971436,
|
| 3 |
+
"best_model_checkpoint": "output/eminem/checkpoint-1347",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 1347,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 1114 |
"eval_samples_per_second": 20.932,
|
| 1115 |
"eval_steps_per_second": 2.645,
|
| 1116 |
"step": 910
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.04,
|
| 1120 |
+
"learning_rate": 1.1246491964533778e-05,
|
| 1121 |
+
"loss": 2.424,
|
| 1122 |
+
"step": 915
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.05,
|
| 1126 |
+
"learning_rate": 1.2598018517843792e-05,
|
| 1127 |
+
"loss": 2.5084,
|
| 1128 |
+
"step": 920
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 2.06,
|
| 1132 |
+
"learning_rate": 1.4018079085430647e-05,
|
| 1133 |
+
"loss": 2.3701,
|
| 1134 |
+
"step": 925
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.07,
|
| 1138 |
+
"learning_rate": 1.5504935827871155e-05,
|
| 1139 |
+
"loss": 2.4517,
|
| 1140 |
+
"step": 930
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 2.08,
|
| 1144 |
+
"learning_rate": 1.7056769162026474e-05,
|
| 1145 |
+
"loss": 2.6206,
|
| 1146 |
+
"step": 935
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 2.09,
|
| 1150 |
+
"learning_rate": 1.867167998781036e-05,
|
| 1151 |
+
"loss": 2.5704,
|
| 1152 |
+
"step": 940
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 2.1,
|
| 1156 |
+
"learning_rate": 2.0347692012266013e-05,
|
| 1157 |
+
"loss": 2.4849,
|
| 1158 |
+
"step": 945
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.12,
|
| 1162 |
+
"learning_rate": 2.208275416810954e-05,
|
| 1163 |
+
"loss": 2.5616,
|
| 1164 |
+
"step": 950
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.13,
|
| 1168 |
+
"learning_rate": 2.3874743123783855e-05,
|
| 1169 |
+
"loss": 2.3109,
|
| 1170 |
+
"step": 955
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 2.14,
|
| 1174 |
+
"learning_rate": 2.572146588194454e-05,
|
| 1175 |
+
"loss": 2.4892,
|
| 1176 |
+
"step": 960
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 2.15,
|
| 1180 |
+
"learning_rate": 2.7620662463202956e-05,
|
| 1181 |
+
"loss": 2.443,
|
| 1182 |
+
"step": 965
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 2.16,
|
| 1186 |
+
"learning_rate": 2.957000867184013e-05,
|
| 1187 |
+
"loss": 2.4545,
|
| 1188 |
+
"step": 970
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 2.17,
|
| 1192 |
+
"learning_rate": 3.156711894010725e-05,
|
| 1193 |
+
"loss": 2.4657,
|
| 1194 |
+
"step": 975
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.18,
|
| 1198 |
+
"learning_rate": 3.360954924763191e-05,
|
| 1199 |
+
"loss": 2.1432,
|
| 1200 |
+
"step": 980
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.19,
|
| 1204 |
+
"learning_rate": 3.569480011235739e-05,
|
| 1205 |
+
"loss": 2.5793,
|
| 1206 |
+
"step": 985
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.2,
|
| 1210 |
+
"learning_rate": 3.782031964935521e-05,
|
| 1211 |
+
"loss": 2.3062,
|
| 1212 |
+
"step": 990
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 2.22,
|
| 1216 |
+
"learning_rate": 3.998350669376499e-05,
|
| 1217 |
+
"loss": 2.3345,
|
| 1218 |
+
"step": 995
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 2.23,
|
| 1222 |
+
"learning_rate": 4.218171398404682e-05,
|
| 1223 |
+
"loss": 2.5329,
|
| 1224 |
+
"step": 1000
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 2.24,
|
| 1228 |
+
"learning_rate": 4.4412251401639226e-05,
|
| 1229 |
+
"loss": 2.201,
|
| 1230 |
+
"step": 1005
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 2.25,
|
| 1234 |
+
"learning_rate": 4.667238926307116e-05,
|
| 1235 |
+
"loss": 2.5198,
|
| 1236 |
+
"step": 1010
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 2.26,
|
| 1240 |
+
"learning_rate": 4.895936166048787e-05,
|
| 1241 |
+
"loss": 2.5241,
|
| 1242 |
+
"step": 1015
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.27,
|
| 1246 |
+
"learning_rate": 5.1270369846509574e-05,
|
| 1247 |
+
"loss": 2.4079,
|
| 1248 |
+
"step": 1020
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.28,
|
| 1252 |
+
"learning_rate": 5.360258565927803e-05,
|
| 1253 |
+
"loss": 2.5147,
|
| 1254 |
+
"step": 1025
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 2.29,
|
| 1258 |
+
"learning_rate": 5.595315498349983e-05,
|
| 1259 |
+
"loss": 2.5063,
|
| 1260 |
+
"step": 1030
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 2.31,
|
| 1264 |
+
"learning_rate": 5.83192012432515e-05,
|
| 1265 |
+
"loss": 2.3742,
|
| 1266 |
+
"step": 1035
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 2.32,
|
| 1270 |
+
"learning_rate": 6.069782892226903e-05,
|
| 1271 |
+
"loss": 2.625,
|
| 1272 |
+
"step": 1040
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 2.33,
|
| 1276 |
+
"learning_rate": 6.308612710742091e-05,
|
| 1277 |
+
"loss": 2.4382,
|
| 1278 |
+
"step": 1045
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 2.34,
|
| 1282 |
+
"learning_rate": 6.548117305101883e-05,
|
| 1283 |
+
"loss": 2.4238,
|
| 1284 |
+
"step": 1050
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.35,
|
| 1288 |
+
"learning_rate": 6.788003574761404e-05,
|
| 1289 |
+
"loss": 2.4157,
|
| 1290 |
+
"step": 1055
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.36,
|
| 1294 |
+
"learning_rate": 7.027977952089649e-05,
|
| 1295 |
+
"loss": 2.5458,
|
| 1296 |
+
"step": 1060
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 2.37,
|
| 1300 |
+
"learning_rate": 7.267746761631506e-05,
|
| 1301 |
+
"loss": 2.5048,
|
| 1302 |
+
"step": 1065
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 2.38,
|
| 1306 |
+
"learning_rate": 7.507016579501221e-05,
|
| 1307 |
+
"loss": 2.5779,
|
| 1308 |
+
"step": 1070
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 2.39,
|
| 1312 |
+
"learning_rate": 7.745494592468267e-05,
|
| 1313 |
+
"loss": 2.5149,
|
| 1314 |
+
"step": 1075
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 2.41,
|
| 1318 |
+
"learning_rate": 7.98288895629588e-05,
|
| 1319 |
+
"loss": 2.4972,
|
| 1320 |
+
"step": 1080
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.42,
|
| 1324 |
+
"learning_rate": 8.218909152893547e-05,
|
| 1325 |
+
"loss": 2.2248,
|
| 1326 |
+
"step": 1085
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.43,
|
| 1330 |
+
"learning_rate": 8.453266345847049e-05,
|
| 1331 |
+
"loss": 2.3945,
|
| 1332 |
+
"step": 1090
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.44,
|
| 1336 |
+
"learning_rate": 8.685673733890025e-05,
|
| 1337 |
+
"loss": 2.4223,
|
| 1338 |
+
"step": 1095
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 2.45,
|
| 1342 |
+
"learning_rate": 8.915846901885212e-05,
|
| 1343 |
+
"loss": 2.5513,
|
| 1344 |
+
"step": 1100
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 2.46,
|
| 1348 |
+
"learning_rate": 9.143504168885545e-05,
|
| 1349 |
+
"loss": 2.527,
|
| 1350 |
+
"step": 1105
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 2.47,
|
| 1354 |
+
"learning_rate": 9.368366932849205e-05,
|
| 1355 |
+
"loss": 2.6526,
|
| 1356 |
+
"step": 1110
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 2.48,
|
| 1360 |
+
"learning_rate": 9.590160011586822e-05,
|
| 1361 |
+
"loss": 2.6926,
|
| 1362 |
+
"step": 1115
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.49,
|
| 1366 |
+
"learning_rate": 9.808611979523307e-05,
|
| 1367 |
+
"loss": 2.4965,
|
| 1368 |
+
"step": 1120
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.51,
|
| 1372 |
+
"learning_rate": 0.00010023455499862926,
|
| 1373 |
+
"loss": 2.4985,
|
| 1374 |
+
"step": 1125
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.52,
|
| 1378 |
+
"learning_rate": 0.00010234427651749925,
|
| 1379 |
+
"loss": 2.6502,
|
| 1380 |
+
"step": 1130
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 2.53,
|
| 1384 |
+
"learning_rate": 0.00010441270252025704,
|
| 1385 |
+
"loss": 2.5715,
|
| 1386 |
+
"step": 1135
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 2.54,
|
| 1390 |
+
"learning_rate": 0.00010643730171187608,
|
| 1391 |
+
"loss": 2.1817,
|
| 1392 |
+
"step": 1140
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 2.55,
|
| 1396 |
+
"learning_rate": 0.00010841559643163376,
|
| 1397 |
+
"loss": 2.3754,
|
| 1398 |
+
"step": 1145
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 2.56,
|
| 1402 |
+
"learning_rate": 0.00011034516568521922,
|
| 1403 |
+
"loss": 2.8706,
|
| 1404 |
+
"step": 1150
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 2.57,
|
| 1408 |
+
"learning_rate": 0.0001122236481074937,
|
| 1409 |
+
"loss": 2.6822,
|
| 1410 |
+
"step": 1155
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.58,
|
| 1414 |
+
"learning_rate": 0.0001140487448522782,
|
| 1415 |
+
"loss": 2.5523,
|
| 1416 |
+
"step": 1160
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.59,
|
| 1420 |
+
"learning_rate": 0.0001158182224056317,
|
| 1421 |
+
"loss": 2.4356,
|
| 1422 |
+
"step": 1165
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 2.61,
|
| 1426 |
+
"learning_rate": 0.00011752991531917766,
|
| 1427 |
+
"loss": 2.5516,
|
| 1428 |
+
"step": 1170
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 2.62,
|
| 1432 |
+
"learning_rate": 0.00011918172886013147,
|
| 1433 |
+
"loss": 2.4273,
|
| 1434 |
+
"step": 1175
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 2.63,
|
| 1438 |
+
"learning_rate": 0.00012077164157479157,
|
| 1439 |
+
"loss": 2.2673,
|
| 1440 |
+
"step": 1180
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 2.64,
|
| 1444 |
+
"learning_rate": 0.00012229770776234816,
|
| 1445 |
+
"loss": 2.6163,
|
| 1446 |
+
"step": 1185
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 2.65,
|
| 1450 |
+
"learning_rate": 0.000123758059855992,
|
| 1451 |
+
"loss": 2.5445,
|
| 1452 |
+
"step": 1190
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.66,
|
| 1456 |
+
"learning_rate": 0.00012515091070840103,
|
| 1457 |
+
"loss": 2.3948,
|
| 1458 |
+
"step": 1195
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.67,
|
| 1462 |
+
"learning_rate": 0.00012647455577881304,
|
| 1463 |
+
"loss": 2.5891,
|
| 1464 |
+
"step": 1200
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 2.68,
|
| 1468 |
+
"learning_rate": 0.00012772737521900558,
|
| 1469 |
+
"loss": 2.5894,
|
| 1470 |
+
"step": 1205
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 2.69,
|
| 1474 |
+
"learning_rate": 0.00012890783585563144,
|
| 1475 |
+
"loss": 2.5051,
|
| 1476 |
+
"step": 1210
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 2.71,
|
| 1480 |
+
"learning_rate": 0.0001300144930664832,
|
| 1481 |
+
"loss": 2.4751,
|
| 1482 |
+
"step": 1215
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 2.72,
|
| 1486 |
+
"learning_rate": 0.00013104599254838963,
|
| 1487 |
+
"loss": 2.4493,
|
| 1488 |
+
"step": 1220
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 2.73,
|
| 1492 |
+
"learning_rate": 0.00013200107197458417,
|
| 1493 |
+
"loss": 2.4946,
|
| 1494 |
+
"step": 1225
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.74,
|
| 1498 |
+
"learning_rate": 0.0001328785625395121,
|
| 1499 |
+
"loss": 2.4618,
|
| 1500 |
+
"step": 1230
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.75,
|
| 1504 |
+
"learning_rate": 0.00013367739038918988,
|
| 1505 |
+
"loss": 2.5223,
|
| 1506 |
+
"step": 1235
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 2.76,
|
| 1510 |
+
"learning_rate": 0.0001343965779353643,
|
| 1511 |
+
"loss": 2.4409,
|
| 1512 |
+
"step": 1240
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 2.77,
|
| 1516 |
+
"learning_rate": 0.0001350352450518637,
|
| 1517 |
+
"loss": 2.3083,
|
| 1518 |
+
"step": 1245
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 2.78,
|
| 1522 |
+
"learning_rate": 0.00013559261015167785,
|
| 1523 |
+
"loss": 2.4411,
|
| 1524 |
+
"step": 1250
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 2.8,
|
| 1528 |
+
"learning_rate": 0.0001360679911434468,
|
| 1529 |
+
"loss": 2.3657,
|
| 1530 |
+
"step": 1255
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 2.81,
|
| 1534 |
+
"learning_rate": 0.00013646080626618978,
|
| 1535 |
+
"loss": 2.4467,
|
| 1536 |
+
"step": 1260
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.82,
|
| 1540 |
+
"learning_rate": 0.0001367705748012514,
|
| 1541 |
+
"loss": 2.3811,
|
| 1542 |
+
"step": 1265
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.83,
|
| 1546 |
+
"learning_rate": 0.0001369969176605951,
|
| 1547 |
+
"loss": 2.5053,
|
| 1548 |
+
"step": 1270
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 2.84,
|
| 1552 |
+
"learning_rate": 0.00013713955785072274,
|
| 1553 |
+
"loss": 2.7194,
|
| 1554 |
+
"step": 1275
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 2.85,
|
| 1558 |
+
"learning_rate": 0.0001371983208116533,
|
| 1559 |
+
"loss": 2.5204,
|
| 1560 |
+
"step": 1280
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 2.86,
|
| 1564 |
+
"learning_rate": 0.0001371731346305456,
|
| 1565 |
+
"loss": 2.5025,
|
| 1566 |
+
"step": 1285
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 2.87,
|
| 1570 |
+
"learning_rate": 0.00013706403012970347,
|
| 1571 |
+
"loss": 2.4982,
|
| 1572 |
+
"step": 1290
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 2.88,
|
| 1576 |
+
"learning_rate": 0.00013687114082885652,
|
| 1577 |
+
"loss": 2.7208,
|
| 1578 |
+
"step": 1295
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.9,
|
| 1582 |
+
"learning_rate": 0.00013659470278176106,
|
| 1583 |
+
"loss": 2.5839,
|
| 1584 |
+
"step": 1300
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 2.91,
|
| 1588 |
+
"learning_rate": 0.00013623505428732318,
|
| 1589 |
+
"loss": 2.5333,
|
| 1590 |
+
"step": 1305
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 2.92,
|
| 1594 |
+
"learning_rate": 0.0001357926354755953,
|
| 1595 |
+
"loss": 2.5095,
|
| 1596 |
+
"step": 1310
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 2.93,
|
| 1600 |
+
"learning_rate": 0.0001352679877691551,
|
| 1601 |
+
"loss": 2.2663,
|
| 1602 |
+
"step": 1315
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 2.94,
|
| 1606 |
+
"learning_rate": 0.00013466175322052366,
|
| 1607 |
+
"loss": 2.5816,
|
| 1608 |
+
"step": 1320
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 2.95,
|
| 1612 |
+
"learning_rate": 0.00013397467372643594,
|
| 1613 |
+
"loss": 2.4828,
|
| 1614 |
+
"step": 1325
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.96,
|
| 1618 |
+
"learning_rate": 0.00013320759011992343,
|
| 1619 |
+
"loss": 2.5478,
|
| 1620 |
+
"step": 1330
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.97,
|
| 1624 |
+
"learning_rate": 0.00013236144114132077,
|
| 1625 |
+
"loss": 2.5125,
|
| 1626 |
+
"step": 1335
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 2.98,
|
| 1630 |
+
"learning_rate": 0.0001314372622894558,
|
| 1631 |
+
"loss": 2.5845,
|
| 1632 |
+
"step": 1340
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 3.0,
|
| 1636 |
+
"learning_rate": 0.00013043618455442838,
|
| 1637 |
+
"loss": 2.6289,
|
| 1638 |
+
"step": 1345
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 3.0,
|
| 1642 |
+
"eval_loss": 2.2795188426971436,
|
| 1643 |
+
"eval_runtime": 30.9908,
|
| 1644 |
+
"eval_samples_per_second": 22.329,
|
| 1645 |
+
"eval_steps_per_second": 2.807,
|
| 1646 |
+
"step": 1347
|
| 1647 |
}
|
| 1648 |
],
|
| 1649 |
+
"max_steps": 1347,
|
| 1650 |
+
"num_train_epochs": 3,
|
| 1651 |
+
"total_flos": 1406012424192000.0,
|
| 1652 |
"trial_name": null,
|
| 1653 |
"trial_params": null
|
| 1654 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2671
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a20a91a1d8b949d119304f2ada1bfca86587c3aa3a905b75978d6260abbfcff4
|
| 3 |
size 2671
|