Training in progress, step 1400, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2997376ab844c12f08e3428c9aa7d03b6a6727cbaf336c2b03afa3934a5dead4
|
3 |
size 9444296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18902665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e56c0b19c9a1e30a3ebf19084d381eb679a18abdbcabb4d8aec647d93f45278
|
3 |
size 18902665
|
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 sha256:3e4490c26af2695a2b327922ff3f2cc285daad2f6354ff581e32798a9b8e42b8
|
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:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch":
|
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,
|
@@ -189,13 +189,27 @@
|
|
189 |
"eval_samples_per_second": 30.363,
|
190 |
"eval_steps_per_second": 3.799,
|
191 |
"step": 1300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 100,
|
195 |
"max_steps": 4116,
|
196 |
"num_train_epochs": 3,
|
197 |
"save_steps": 100,
|
198 |
-
"total_flos":
|
199 |
"trial_name": null,
|
200 |
"trial_params": null
|
201 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.3094112873077393,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1400",
|
4 |
+
"epoch": 1.0200364298724955,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
189 |
"eval_samples_per_second": 30.363,
|
190 |
"eval_steps_per_second": 3.799,
|
191 |
"step": 1300
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.02,
|
195 |
+
"learning_rate": 0.0002,
|
196 |
+
"loss": 2.3013,
|
197 |
+
"step": 1400
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 1.02,
|
201 |
+
"eval_loss": 2.3094112873077393,
|
202 |
+
"eval_runtime": 206.8997,
|
203 |
+
"eval_samples_per_second": 30.324,
|
204 |
+
"eval_steps_per_second": 3.794,
|
205 |
+
"step": 1400
|
206 |
}
|
207 |
],
|
208 |
"logging_steps": 100,
|
209 |
"max_steps": 4116,
|
210 |
"num_train_epochs": 3,
|
211 |
"save_steps": 100,
|
212 |
+
"total_flos": 4.091805541361664e+16,
|
213 |
"trial_name": null,
|
214 |
"trial_params": null
|
215 |
}
|