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 67143296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df819a8b23c91fd8737730695d619c253e06b55990eead6187bb1cc39f37dccb
|
3 |
size 67143296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 33920095
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb5986a78af3d5efce48df6f0d940dc241b62f837110ba25deb42406111c5f6b
|
3 |
size 33920095
|
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:f72087b9bf736ff0875f5ba21d638035ba90cd100d329b4fee8ee289829b197a
|
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 sha256:0a45b73b9e427bf816ec84ae293407d29e526cb951db69b163b11e361f1a1947
|
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": 7.
|
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": 2.036,
|
164 |
"eval_steps_per_second": 0.266,
|
165 |
"step": 1200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
166 |
}
|
167 |
],
|
168 |
"logging_steps": 100,
|
169 |
"max_steps": 1312,
|
170 |
"num_train_epochs": 8,
|
171 |
"save_steps": 100,
|
172 |
-
"total_flos":
|
173 |
"trial_name": null,
|
174 |
"trial_params": null
|
175 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.926829268292683,
|
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": 2.036,
|
164 |
"eval_steps_per_second": 0.266,
|
165 |
"step": 1200
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 7.93,
|
169 |
+
"learning_rate": 0.0002,
|
170 |
+
"loss": 0.0257,
|
171 |
+
"step": 1300
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 7.93,
|
175 |
+
"eval_runtime": 33.8768,
|
176 |
+
"eval_samples_per_second": 2.037,
|
177 |
+
"eval_steps_per_second": 0.266,
|
178 |
+
"step": 1300
|
179 |
}
|
180 |
],
|
181 |
"logging_steps": 100,
|
182 |
"max_steps": 1312,
|
183 |
"num_train_epochs": 8,
|
184 |
"save_steps": 100,
|
185 |
+
"total_flos": 1.0796396610532147e+17,
|
186 |
"trial_name": null,
|
187 |
"trial_params": null
|
188 |
}
|