Training in progress, step 185, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8911f9b112eca03691bcc9c5bf66e2bc59df7ef8a566e8b106bef1cefcfb149
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feb48f25b1822ecf3f10c339ed66d660f9609b8a2d68d0c6b4a7cf4fb16e0729
|
3 |
size 37430836
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40e552e18fdab2c10b14fb8fba4c8769fc41c72449b23123967073e6cf9198e2
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1295,6 +1295,13 @@
|
|
1295 |
"learning_rate": 0.00013636363636363637,
|
1296 |
"loss": 1.2423,
|
1297 |
"step": 184
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1298 |
}
|
1299 |
],
|
1300 |
"logging_steps": 1,
|
@@ -1314,7 +1321,7 @@
|
|
1314 |
"attributes": {}
|
1315 |
}
|
1316 |
},
|
1317 |
-
"total_flos": 2.
|
1318 |
"train_batch_size": 4,
|
1319 |
"trial_name": null,
|
1320 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5075445816186557,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 185,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1295 |
"learning_rate": 0.00013636363636363637,
|
1296 |
"loss": 1.2423,
|
1297 |
"step": 184
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 0.5075445816186557,
|
1301 |
+
"grad_norm": 0.1455039083957672,
|
1302 |
+
"learning_rate": 0.0001356060606060606,
|
1303 |
+
"loss": 1.2178,
|
1304 |
+
"step": 185
|
1305 |
}
|
1306 |
],
|
1307 |
"logging_steps": 1,
|
|
|
1321 |
"attributes": {}
|
1322 |
}
|
1323 |
},
|
1324 |
+
"total_flos": 2.2950403908175872e+17,
|
1325 |
"train_batch_size": 4,
|
1326 |
"trial_name": null,
|
1327 |
"trial_params": null
|