Training in progress, step 780, 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:c1c08e0e9ce6afdc903da9cc75b614e76cae23c9beb42db40256c151ad34e81a
|
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:b9188036a13204df967c90460aa239c68c499ddaf237d2285245db3a78e06669
|
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:d0335dc509cd507d59d1d5942a8f635cafde96078d0fb69d9bc544c5eecbf40e
|
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:efa38f4b48c5832a199be588272d799af5ee23605631829045514ae027904f11
|
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,
|
@@ -163,13 +163,26 @@
|
|
163 |
"eval_samples_per_second": 1.921,
|
164 |
"eval_steps_per_second": 0.24,
|
165 |
"step": 720
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
166 |
}
|
167 |
],
|
168 |
"logging_steps": 60,
|
169 |
"max_steps": 1011,
|
170 |
"num_train_epochs": 3,
|
171 |
"save_steps": 60,
|
172 |
-
"total_flos": 1.
|
173 |
"trial_name": null,
|
174 |
"trial_params": null
|
175 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.311111111111111,
|
5 |
"eval_steps": 60,
|
6 |
+
"global_step": 780,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
163 |
"eval_samples_per_second": 1.921,
|
164 |
"eval_steps_per_second": 0.24,
|
165 |
"step": 720
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 2.31,
|
169 |
+
"learning_rate": 0.0002,
|
170 |
+
"loss": 0.5064,
|
171 |
+
"step": 780
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 2.31,
|
175 |
+
"eval_runtime": 312.4619,
|
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": 1.2955884409847808e+17,
|
186 |
"trial_name": null,
|
187 |
"trial_params": null
|
188 |
}
|