Training in progress, step 840, 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 40036040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c53135849dc04cc65b369eb490a7a8f655dc6159ed38aea9f68b90e0ffdca490
|
3 |
size 40036040
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 20524127
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05c7f1840c59b7e05079bade98860da96807471d2246d58bc57d415a5f47ca50
|
3 |
size 20524127
|
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 sha256:9ec1259429b87ac6f4ca3569d5b0f362a16738b5286a1874d947a518fc2a2983
|
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 sha256:35b2c315e825043036cabe0b621568bd0f3b5d9852144632bacc4a8b852454d0
|
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": 2.
|
5 |
"eval_steps": 60,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -176,13 +176,26 @@
|
|
176 |
"eval_samples_per_second": 1.92,
|
177 |
"eval_steps_per_second": 0.24,
|
178 |
"step": 780
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
179 |
}
|
180 |
],
|
181 |
"logging_steps": 60,
|
182 |
"max_steps": 1011,
|
183 |
"num_train_epochs": 3,
|
184 |
"save_steps": 60,
|
185 |
-
"total_flos": 1.
|
186 |
"trial_name": null,
|
187 |
"trial_params": null
|
188 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.488888888888889,
|
5 |
"eval_steps": 60,
|
6 |
+
"global_step": 840,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
176 |
"eval_samples_per_second": 1.92,
|
177 |
"eval_steps_per_second": 0.24,
|
178 |
"step": 780
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 2.49,
|
182 |
+
"learning_rate": 0.0002,
|
183 |
+
"loss": 0.5125,
|
184 |
+
"step": 840
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.49,
|
188 |
+
"eval_runtime": 312.7044,
|
189 |
+
"eval_samples_per_second": 1.919,
|
190 |
+
"eval_steps_per_second": 0.24,
|
191 |
+
"step": 840
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 60,
|
195 |
"max_steps": 1011,
|
196 |
"num_train_epochs": 3,
|
197 |
"save_steps": 60,
|
198 |
+
"total_flos": 1.3952490902913024e+17,
|
199 |
"trial_name": null,
|
200 |
"trial_params": null
|
201 |
}
|