ramdhanfirdaus
commited on
Commit
•
50449f8
1
Parent(s):
7abf14f
Training in progress, step 1300, 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 50338848
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ea64bf82ae4b08573cb6e6d1879770260a74cdc4b19ab15105c74d680b2ac55
|
3 |
size 50338848
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100693001
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5a48386b967f019814b752c31724ba92b9b722edcc4f5ee859c15baa000d357
|
3 |
size 100693001
|
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 sha256:4d068296d3f9011b33a34c8187d97d4e5a695d49d324e8c6f6a7442a620b5590
|
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:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 0.
|
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,
|
@@ -175,13 +175,27 @@
|
|
175 |
"eval_samples_per_second": 43.703,
|
176 |
"eval_steps_per_second": 5.468,
|
177 |
"step": 1200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
178 |
}
|
179 |
],
|
180 |
"logging_steps": 100,
|
181 |
"max_steps": 4116,
|
182 |
"num_train_epochs": 3,
|
183 |
"save_steps": 100,
|
184 |
-
"total_flos": 7.
|
185 |
"trial_name": null,
|
186 |
"trial_params": null
|
187 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.5822986364364624,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1300",
|
4 |
+
"epoch": 0.9471766848816029,
|
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,
|
|
|
175 |
"eval_samples_per_second": 43.703,
|
176 |
"eval_steps_per_second": 5.468,
|
177 |
"step": 1200
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.95,
|
181 |
+
"learning_rate": 0.0002,
|
182 |
+
"loss": 1.6101,
|
183 |
+
"step": 1300
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.95,
|
187 |
+
"eval_loss": 1.5822986364364624,
|
188 |
+
"eval_runtime": 143.5287,
|
189 |
+
"eval_samples_per_second": 43.713,
|
190 |
+
"eval_steps_per_second": 5.469,
|
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": 7.750057637589811e+16,
|
199 |
"trial_name": null,
|
200 |
"trial_params": null
|
201 |
}
|