Training in progress, step 1300, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 160285149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:73c72087c278a19d041000058ef12b3a0f26d21baaaa01b7d96279e32367abfa
|
3 |
size 160285149
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22f55e2747dba123d2b4ec620eafd1a6796097d64b95110119ff4da1c567fe11
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b07bb44c7eb6649b82d385b24afe36ce65d36c6d2f9dadc9eabdc31b084d574b
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -163,13 +163,26 @@
|
|
163 |
"eval_samples_per_second": 1.903,
|
164 |
"eval_steps_per_second": 0.239,
|
165 |
"step": 1200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
166 |
}
|
167 |
],
|
168 |
"logging_steps": 100,
|
169 |
"max_steps": 2025,
|
170 |
"num_train_epochs": 3,
|
171 |
"save_steps": 100,
|
172 |
-
"total_flos": 2.
|
173 |
"trial_name": null,
|
174 |
"trial_params": null
|
175 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.925925925925926,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1300,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
163 |
"eval_samples_per_second": 1.903,
|
164 |
"eval_steps_per_second": 0.239,
|
165 |
"step": 1200
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 1.93,
|
169 |
+
"learning_rate": 0.0,
|
170 |
+
"loss": 8.6986,
|
171 |
+
"step": 1300
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 1.93,
|
175 |
+
"eval_runtime": 787.9067,
|
176 |
+
"eval_samples_per_second": 1.904,
|
177 |
+
"eval_steps_per_second": 0.239,
|
178 |
+
"step": 1300
|
179 |
}
|
180 |
],
|
181 |
"logging_steps": 100,
|
182 |
"max_steps": 2025,
|
183 |
"num_train_epochs": 3,
|
184 |
"save_steps": 100,
|
185 |
+
"total_flos": 2.70712518475776e+17,
|
186 |
"trial_name": null,
|
187 |
"trial_params": null
|
188 |
}
|