Training in progress, step 720, 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 sha256:495dd77edec3ea9f23dfcba4f605cacfc0d0be47c79f084cf6896493d0ee3234
|
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 sha256:1dfd8892dfe7556b9a4d09bf9c5c8ff187c2c826f40fd6b36778000ef6585186
|
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 sha256:1f1a9fd09dbddb9f8108555ef34a700fc36e30ad0e2161706a3514ea6fd388bd
|
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 sha256:6436ce12a9b5cd3c291f48f2d393b518fb7e8838562b720c6cb2f3dd6750c386
|
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":
|
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,
|
@@ -150,13 +150,26 @@
|
|
150 |
"eval_samples_per_second": 1.919,
|
151 |
"eval_steps_per_second": 0.24,
|
152 |
"step": 660
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
153 |
}
|
154 |
],
|
155 |
"logging_steps": 60,
|
156 |
"max_steps": 1011,
|
157 |
"num_train_epochs": 3,
|
158 |
"save_steps": 60,
|
159 |
-
"total_flos": 1.
|
160 |
"trial_name": null,
|
161 |
"trial_params": null
|
162 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.1333333333333333,
|
5 |
"eval_steps": 60,
|
6 |
+
"global_step": 720,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
150 |
"eval_samples_per_second": 1.919,
|
151 |
"eval_steps_per_second": 0.24,
|
152 |
"step": 660
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 2.13,
|
156 |
+
"learning_rate": 0.0002,
|
157 |
+
"loss": 0.5315,
|
158 |
+
"step": 720
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.13,
|
162 |
+
"eval_runtime": 312.3646,
|
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": 1.1959277916782592e+17,
|
173 |
"trial_name": null,
|
174 |
"trial_params": null
|
175 |
}
|