Commit
•
48d55f1
1
Parent(s):
4fe4412
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 +2 -2
- scheduler.pt +1 -1
- trainer_state.json +548 -6
- 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/m1jtunaa/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/2xezqr9j) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2xezqr9j/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 0.
|
|
|
|
| 1 |
+
{"eval_loss": 0.6717901825904846, "eval_runtime": 32.3581, "eval_samples_per_second": 21.077, "eval_steps_per_second": 2.658, "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 sha256:9e4996cc5b01b2f5df2097ea186a2e86f7ee3597d536c4f655a2fc46fe7ba2cc
|
| 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 sha256:71a25a4b42966c35fad23512f0a00af907488f398f69579bbf6993f208f7875f
|
| 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:d9621b75ec1fc38e7c917e2fcc638921268a3d38f2762a4ff89a10975fc0830c
|
| 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81db186b04d47e780c47c135689736ec200f7e269a91591d61577bc87d72dc42
|
| 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:e0d0227464d22267541364a30983be6a0f32a9f218c9367e12431d626c7660eb
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 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,
|
|
@@ -1108,11 +1108,553 @@
|
|
| 1108 |
"eval_samples_per_second": 76.95,
|
| 1109 |
"eval_steps_per_second": 9.649,
|
| 1110 |
"step": 908
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1111 |
}
|
| 1112 |
],
|
| 1113 |
-
"max_steps":
|
| 1114 |
"num_train_epochs": 3,
|
| 1115 |
-
"total_flos":
|
| 1116 |
"trial_name": null,
|
| 1117 |
"trial_params": null
|
| 1118 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.6717901825904846,
|
| 3 |
+
"best_model_checkpoint": "output/eminem/checkpoint-1350",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 1350,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 1108 |
"eval_samples_per_second": 76.95,
|
| 1109 |
"eval_steps_per_second": 9.649,
|
| 1110 |
"step": 908
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 2.02,
|
| 1114 |
+
"learning_rate": 3.939154059863554e-05,
|
| 1115 |
+
"loss": 1.0652,
|
| 1116 |
+
"step": 910
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.03,
|
| 1120 |
+
"learning_rate": 4.157558500206058e-05,
|
| 1121 |
+
"loss": 0.9825,
|
| 1122 |
+
"step": 915
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.04,
|
| 1126 |
+
"learning_rate": 4.379255449236861e-05,
|
| 1127 |
+
"loss": 0.8959,
|
| 1128 |
+
"step": 920
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 2.06,
|
| 1132 |
+
"learning_rate": 4.603974803373273e-05,
|
| 1133 |
+
"loss": 1.0768,
|
| 1134 |
+
"step": 925
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 2.07,
|
| 1138 |
+
"learning_rate": 4.831442776697826e-05,
|
| 1139 |
+
"loss": 0.9137,
|
| 1140 |
+
"step": 930
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 2.08,
|
| 1144 |
+
"learning_rate": 5.061382234523686e-05,
|
| 1145 |
+
"loss": 0.9653,
|
| 1146 |
+
"step": 935
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 2.09,
|
| 1150 |
+
"learning_rate": 5.293513031040953e-05,
|
| 1151 |
+
"loss": 0.921,
|
| 1152 |
+
"step": 940
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 2.1,
|
| 1156 |
+
"learning_rate": 5.527552350630886e-05,
|
| 1157 |
+
"loss": 0.9621,
|
| 1158 |
+
"step": 945
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.11,
|
| 1162 |
+
"learning_rate": 5.763215052433939e-05,
|
| 1163 |
+
"loss": 0.933,
|
| 1164 |
+
"step": 950
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 2.12,
|
| 1168 |
+
"learning_rate": 6.000214017748833e-05,
|
| 1169 |
+
"loss": 1.1698,
|
| 1170 |
+
"step": 955
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 2.13,
|
| 1174 |
+
"learning_rate": 6.238260499843221e-05,
|
| 1175 |
+
"loss": 1.0466,
|
| 1176 |
+
"step": 960
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 2.14,
|
| 1180 |
+
"learning_rate": 6.477064475746826e-05,
|
| 1181 |
+
"loss": 0.9793,
|
| 1182 |
+
"step": 965
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 2.16,
|
| 1186 |
+
"learning_rate": 6.716334999600135e-05,
|
| 1187 |
+
"loss": 1.0029,
|
| 1188 |
+
"step": 970
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 2.17,
|
| 1192 |
+
"learning_rate": 6.955780557126535e-05,
|
| 1193 |
+
"loss": 0.901,
|
| 1194 |
+
"step": 975
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.18,
|
| 1198 |
+
"learning_rate": 7.195109420797938e-05,
|
| 1199 |
+
"loss": 0.8933,
|
| 1200 |
+
"step": 980
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.19,
|
| 1204 |
+
"learning_rate": 7.434030005259555e-05,
|
| 1205 |
+
"loss": 0.9533,
|
| 1206 |
+
"step": 985
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.2,
|
| 1210 |
+
"learning_rate": 7.672251222582502e-05,
|
| 1211 |
+
"loss": 1.0477,
|
| 1212 |
+
"step": 990
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 2.21,
|
| 1216 |
+
"learning_rate": 7.90948283690844e-05,
|
| 1217 |
+
"loss": 1.0604,
|
| 1218 |
+
"step": 995
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 2.22,
|
| 1222 |
+
"learning_rate": 8.145435818058043e-05,
|
| 1223 |
+
"loss": 1.0593,
|
| 1224 |
+
"step": 1000
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 2.23,
|
| 1228 |
+
"learning_rate": 8.379822693669456e-05,
|
| 1229 |
+
"loss": 0.889,
|
| 1230 |
+
"step": 1005
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 2.24,
|
| 1234 |
+
"learning_rate": 8.612357899439467e-05,
|
| 1235 |
+
"loss": 1.0466,
|
| 1236 |
+
"step": 1010
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 2.26,
|
| 1240 |
+
"learning_rate": 8.842758127039052e-05,
|
| 1241 |
+
"loss": 0.8741,
|
| 1242 |
+
"step": 1015
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.27,
|
| 1246 |
+
"learning_rate": 9.070742669281316e-05,
|
| 1247 |
+
"loss": 0.9787,
|
| 1248 |
+
"step": 1020
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.28,
|
| 1252 |
+
"learning_rate": 9.296033762119679e-05,
|
| 1253 |
+
"loss": 0.9187,
|
| 1254 |
+
"step": 1025
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 2.29,
|
| 1258 |
+
"learning_rate": 9.518356923061407e-05,
|
| 1259 |
+
"loss": 0.918,
|
| 1260 |
+
"step": 1030
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 2.3,
|
| 1264 |
+
"learning_rate": 9.737441285580787e-05,
|
| 1265 |
+
"loss": 0.887,
|
| 1266 |
+
"step": 1035
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 2.31,
|
| 1270 |
+
"learning_rate": 9.953019929129537e-05,
|
| 1271 |
+
"loss": 1.0572,
|
| 1272 |
+
"step": 1040
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 2.32,
|
| 1276 |
+
"learning_rate": 0.00010164830204337668,
|
| 1277 |
+
"loss": 0.9164,
|
| 1278 |
+
"step": 1045
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 2.33,
|
| 1282 |
+
"learning_rate": 0.00010372614053012052,
|
| 1283 |
+
"loss": 0.9702,
|
| 1284 |
+
"step": 1050
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.34,
|
| 1288 |
+
"learning_rate": 0.00010576118322539557,
|
| 1289 |
+
"loss": 1.0737,
|
| 1290 |
+
"step": 1055
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.36,
|
| 1294 |
+
"learning_rate": 0.00010775095074315191,
|
| 1295 |
+
"loss": 0.9764,
|
| 1296 |
+
"step": 1060
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 2.37,
|
| 1300 |
+
"learning_rate": 0.00010969301885816937,
|
| 1301 |
+
"loss": 1.0461,
|
| 1302 |
+
"step": 1065
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 2.38,
|
| 1306 |
+
"learning_rate": 0.00011158502145960167,
|
| 1307 |
+
"loss": 1.034,
|
| 1308 |
+
"step": 1070
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 2.39,
|
| 1312 |
+
"learning_rate": 0.00011342465343372117,
|
| 1313 |
+
"loss": 0.9559,
|
| 1314 |
+
"step": 1075
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 2.4,
|
| 1318 |
+
"learning_rate": 0.00011520967347234022,
|
| 1319 |
+
"loss": 1.0916,
|
| 1320 |
+
"step": 1080
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.41,
|
| 1324 |
+
"learning_rate": 0.00011693790680350301,
|
| 1325 |
+
"loss": 0.9443,
|
| 1326 |
+
"step": 1085
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.42,
|
| 1330 |
+
"learning_rate": 0.00011860724784110814,
|
| 1331 |
+
"loss": 0.9271,
|
| 1332 |
+
"step": 1090
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.43,
|
| 1336 |
+
"learning_rate": 0.00012021566275024623,
|
| 1337 |
+
"loss": 0.9245,
|
| 1338 |
+
"step": 1095
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 2.44,
|
| 1342 |
+
"learning_rate": 0.00012176119192510649,
|
| 1343 |
+
"loss": 0.8889,
|
| 1344 |
+
"step": 1100
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 2.46,
|
| 1348 |
+
"learning_rate": 0.00012324195237645988,
|
| 1349 |
+
"loss": 0.9344,
|
| 1350 |
+
"step": 1105
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 2.47,
|
| 1354 |
+
"learning_rate": 0.00012465614002578945,
|
| 1355 |
+
"loss": 1.0672,
|
| 1356 |
+
"step": 1110
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 2.48,
|
| 1360 |
+
"learning_rate": 0.0001260020319032846,
|
| 1361 |
+
"loss": 0.9582,
|
| 1362 |
+
"step": 1115
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.49,
|
| 1366 |
+
"learning_rate": 0.00012727798824701078,
|
| 1367 |
+
"loss": 0.9114,
|
| 1368 |
+
"step": 1120
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.5,
|
| 1372 |
+
"learning_rate": 0.00012848245450070912,
|
| 1373 |
+
"loss": 1.1439,
|
| 1374 |
+
"step": 1125
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.51,
|
| 1378 |
+
"learning_rate": 0.00012961396320778244,
|
| 1379 |
+
"loss": 1.0116,
|
| 1380 |
+
"step": 1130
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 2.52,
|
| 1384 |
+
"learning_rate": 0.00013067113579916855,
|
| 1385 |
+
"loss": 0.8955,
|
| 1386 |
+
"step": 1135
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 2.53,
|
| 1390 |
+
"learning_rate": 0.00013165268427290888,
|
| 1391 |
+
"loss": 1.1116,
|
| 1392 |
+
"step": 1140
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 2.54,
|
| 1396 |
+
"learning_rate": 0.0001325574127633844,
|
| 1397 |
+
"loss": 0.9538,
|
| 1398 |
+
"step": 1145
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 2.56,
|
| 1402 |
+
"learning_rate": 0.00013338421899829092,
|
| 1403 |
+
"loss": 1.0351,
|
| 1404 |
+
"step": 1150
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 2.57,
|
| 1408 |
+
"learning_rate": 0.00013413209564159262,
|
| 1409 |
+
"loss": 1.0751,
|
| 1410 |
+
"step": 1155
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.58,
|
| 1414 |
+
"learning_rate": 0.0001348001315208005,
|
| 1415 |
+
"loss": 1.0118,
|
| 1416 |
+
"step": 1160
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.59,
|
| 1420 |
+
"learning_rate": 0.00013538751273709884,
|
| 1421 |
+
"loss": 1.0048,
|
| 1422 |
+
"step": 1165
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 2.6,
|
| 1426 |
+
"learning_rate": 0.00013589352365695444,
|
| 1427 |
+
"loss": 1.0141,
|
| 1428 |
+
"step": 1170
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 2.61,
|
| 1432 |
+
"learning_rate": 0.00013631754778400696,
|
| 1433 |
+
"loss": 1.0117,
|
| 1434 |
+
"step": 1175
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 2.62,
|
| 1438 |
+
"learning_rate": 0.0001366590685101732,
|
| 1439 |
+
"loss": 1.0794,
|
| 1440 |
+
"step": 1180
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 2.63,
|
| 1444 |
+
"learning_rate": 0.00013691766974505563,
|
| 1445 |
+
"loss": 1.1812,
|
| 1446 |
+
"step": 1185
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 2.64,
|
| 1450 |
+
"learning_rate": 0.00013709303642288383,
|
| 1451 |
+
"loss": 1.2511,
|
| 1452 |
+
"step": 1190
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.66,
|
| 1456 |
+
"learning_rate": 0.0001371849548863744,
|
| 1457 |
+
"loss": 0.8512,
|
| 1458 |
+
"step": 1195
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.67,
|
| 1462 |
+
"learning_rate": 0.00013719331314703827,
|
| 1463 |
+
"loss": 1.0474,
|
| 1464 |
+
"step": 1200
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 2.68,
|
| 1468 |
+
"learning_rate": 0.00013711810102162237,
|
| 1469 |
+
"loss": 1.0574,
|
| 1470 |
+
"step": 1205
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 2.69,
|
| 1474 |
+
"learning_rate": 0.00013695941014451606,
|
| 1475 |
+
"loss": 1.2136,
|
| 1476 |
+
"step": 1210
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 2.7,
|
| 1480 |
+
"learning_rate": 0.00013671743385610847,
|
| 1481 |
+
"loss": 1.1405,
|
| 1482 |
+
"step": 1215
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 2.71,
|
| 1486 |
+
"learning_rate": 0.00013639246696723354,
|
| 1487 |
+
"loss": 0.9608,
|
| 1488 |
+
"step": 1220
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 2.72,
|
| 1492 |
+
"learning_rate": 0.000135984905399988,
|
| 1493 |
+
"loss": 1.0797,
|
| 1494 |
+
"step": 1225
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.73,
|
| 1498 |
+
"learning_rate": 0.00013549524570536192,
|
| 1499 |
+
"loss": 1.1173,
|
| 1500 |
+
"step": 1230
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.74,
|
| 1504 |
+
"learning_rate": 0.00013492408445826617,
|
| 1505 |
+
"loss": 1.0319,
|
| 1506 |
+
"step": 1235
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 2.76,
|
| 1510 |
+
"learning_rate": 0.0001342721175307,
|
| 1511 |
+
"loss": 1.1431,
|
| 1512 |
+
"step": 1240
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 2.77,
|
| 1516 |
+
"learning_rate": 0.00013354013924393685,
|
| 1517 |
+
"loss": 1.1817,
|
| 1518 |
+
"step": 1245
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 2.78,
|
| 1522 |
+
"learning_rate": 0.00013272904140076693,
|
| 1523 |
+
"loss": 1.1562,
|
| 1524 |
+
"step": 1250
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 2.79,
|
| 1528 |
+
"learning_rate": 0.00013183981219897135,
|
| 1529 |
+
"loss": 0.9705,
|
| 1530 |
+
"step": 1255
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 2.8,
|
| 1534 |
+
"learning_rate": 0.00013087353502735764,
|
| 1535 |
+
"loss": 0.9752,
|
| 1536 |
+
"step": 1260
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.81,
|
| 1540 |
+
"learning_rate": 0.00012983138714581574,
|
| 1541 |
+
"loss": 1.1247,
|
| 1542 |
+
"step": 1265
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.82,
|
| 1546 |
+
"learning_rate": 0.00012871463825100976,
|
| 1547 |
+
"loss": 1.001,
|
| 1548 |
+
"step": 1270
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 2.83,
|
| 1552 |
+
"learning_rate": 0.00012752464892944418,
|
| 1553 |
+
"loss": 1.0426,
|
| 1554 |
+
"step": 1275
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 2.84,
|
| 1558 |
+
"learning_rate": 0.00012626286899980387,
|
| 1559 |
+
"loss": 1.128,
|
| 1560 |
+
"step": 1280
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 2.86,
|
| 1564 |
+
"learning_rate": 0.0001249308357465718,
|
| 1565 |
+
"loss": 1.1501,
|
| 1566 |
+
"step": 1285
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 2.87,
|
| 1570 |
+
"learning_rate": 0.0001235301720470826,
|
| 1571 |
+
"loss": 0.9987,
|
| 1572 |
+
"step": 1290
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 2.88,
|
| 1576 |
+
"learning_rate": 0.00012206258439429962,
|
| 1577 |
+
"loss": 1.1401,
|
| 1578 |
+
"step": 1295
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.89,
|
| 1582 |
+
"learning_rate": 0.0001205298608177108,
|
| 1583 |
+
"loss": 0.9013,
|
| 1584 |
+
"step": 1300
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 2.9,
|
| 1588 |
+
"learning_rate": 0.0001189338687048974,
|
| 1589 |
+
"loss": 1.0983,
|
| 1590 |
+
"step": 1305
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 2.91,
|
| 1594 |
+
"learning_rate": 0.00011727655252640518,
|
| 1595 |
+
"loss": 1.0951,
|
| 1596 |
+
"step": 1310
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 2.92,
|
| 1600 |
+
"learning_rate": 0.00011555993146670835,
|
| 1601 |
+
"loss": 1.097,
|
| 1602 |
+
"step": 1315
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 2.93,
|
| 1606 |
+
"learning_rate": 0.00011378609696414153,
|
| 1607 |
+
"loss": 1.1505,
|
| 1608 |
+
"step": 1320
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 2.94,
|
| 1612 |
+
"learning_rate": 0.00011195721016280857,
|
| 1613 |
+
"loss": 1.0955,
|
| 1614 |
+
"step": 1325
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.96,
|
| 1618 |
+
"learning_rate": 0.00011007549927955844,
|
| 1619 |
+
"loss": 1.0874,
|
| 1620 |
+
"step": 1330
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.97,
|
| 1624 |
+
"learning_rate": 0.00010814325688924864,
|
| 1625 |
+
"loss": 1.04,
|
| 1626 |
+
"step": 1335
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 2.98,
|
| 1630 |
+
"learning_rate": 0.00010616283713158952,
|
| 1631 |
+
"loss": 1.1124,
|
| 1632 |
+
"step": 1340
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 2.99,
|
| 1636 |
+
"learning_rate": 0.00010413665284299701,
|
| 1637 |
+
"loss": 1.0374,
|
| 1638 |
+
"step": 1345
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 3.0,
|
| 1642 |
+
"learning_rate": 0.00010206717261691705,
|
| 1643 |
+
"loss": 1.103,
|
| 1644 |
+
"step": 1350
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 3.0,
|
| 1648 |
+
"eval_loss": 0.6717901825904846,
|
| 1649 |
+
"eval_runtime": 32.3216,
|
| 1650 |
+
"eval_samples_per_second": 21.1,
|
| 1651 |
+
"eval_steps_per_second": 2.661,
|
| 1652 |
+
"step": 1350
|
| 1653 |
}
|
| 1654 |
],
|
| 1655 |
+
"max_steps": 1350,
|
| 1656 |
"num_train_epochs": 3,
|
| 1657 |
+
"total_flos": 1410062450688000.0,
|
| 1658 |
"trial_name": null,
|
| 1659 |
"trial_params": null
|
| 1660 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2863
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad2c17509308df0501daa22f7c38deda6ee50f01e56c9f0747a3c0dbf3f69a2e
|
| 3 |
size 2863
|