Training in progress, step 14500, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df153e2b68d2a9610611bbea018029c9ed4e9f282e1501e464298b99d68edaeb
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da99fdde9c2172b84053582c25d7a3ca04541c3317694556f84d04188f3607c3
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32dd23f8bccd4e3ea7c87c279b793f3dc99695bcc2a9ced7f6f6b74af90f2794
|
| 3 |
size 15006
|
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 sha256:7dbcc644babab78a4f1af1646b1c89168aace3f006aa80fe27a175849c621a79
|
| 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": 28.
|
| 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,
|
|
@@ -1239,6 +1239,21 @@
|
|
| 1239 |
"learning_rate": 4.000000000000001e-06,
|
| 1240 |
"loss": 1.2207,
|
| 1241 |
"step": 14400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1242 |
}
|
| 1243 |
],
|
| 1244 |
"logging_steps": 100,
|
|
@@ -1258,7 +1273,7 @@
|
|
| 1258 |
"attributes": {}
|
| 1259 |
}
|
| 1260 |
},
|
| 1261 |
-
"total_flos": 2.
|
| 1262 |
"train_batch_size": 8,
|
| 1263 |
"trial_name": null,
|
| 1264 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 28.995469457897205,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 14500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1239 |
"learning_rate": 4.000000000000001e-06,
|
| 1240 |
"loss": 1.2207,
|
| 1241 |
"step": 14400
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 28.995469457897205,
|
| 1245 |
+
"grad_norm": 0.24009475111961365,
|
| 1246 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 1247 |
+
"loss": 1.2157,
|
| 1248 |
+
"step": 14500
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 28.995469457897205,
|
| 1252 |
+
"eval_loss": 1.0933923721313477,
|
| 1253 |
+
"eval_runtime": 779.8849,
|
| 1254 |
+
"eval_samples_per_second": 19.903,
|
| 1255 |
+
"eval_steps_per_second": 2.489,
|
| 1256 |
+
"step": 14500
|
| 1257 |
}
|
| 1258 |
],
|
| 1259 |
"logging_steps": 100,
|
|
|
|
| 1273 |
"attributes": {}
|
| 1274 |
}
|
| 1275 |
},
|
| 1276 |
+
"total_flos": 2.2630614429916463e+19,
|
| 1277 |
"train_batch_size": 8,
|
| 1278 |
"trial_name": null,
|
| 1279 |
"trial_params": null
|