Training in progress, step 37, 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:b0d8ab1636ffe7ae412b879e5b6cf5c52a8e326a70d50f5bc83081e71ce4ce03
|
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 sha256:8033b16113852c52e57c3613f71bd170538ddb845dbc3d71842080503a9d969a
|
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 sha256:936ee85bcb507716e18474dc9cdf2a95bc2e2f298bec38ce951a907f92c6a06e
|
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,
|
@@ -259,6 +259,13 @@
|
|
259 |
"learning_rate": 7.2e-05,
|
260 |
"loss": 1.4151,
|
261 |
"step": 36
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
262 |
}
|
263 |
],
|
264 |
"logging_steps": 1,
|
@@ -278,7 +285,7 @@
|
|
278 |
"attributes": {}
|
279 |
}
|
280 |
},
|
281 |
-
"total_flos": 4.
|
282 |
"train_batch_size": 4,
|
283 |
"trial_name": null,
|
284 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.10150891632373114,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 37,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
259 |
"learning_rate": 7.2e-05,
|
260 |
"loss": 1.4151,
|
261 |
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.10150891632373114,
|
265 |
+
"grad_norm": 0.34214499592781067,
|
266 |
+
"learning_rate": 7.4e-05,
|
267 |
+
"loss": 1.4451,
|
268 |
+
"step": 37
|
269 |
}
|
270 |
],
|
271 |
"logging_steps": 1,
|
|
|
285 |
"attributes": {}
|
286 |
}
|
287 |
},
|
288 |
+
"total_flos": 4.56958749169705e+16,
|
289 |
"train_batch_size": 4,
|
290 |
"trial_name": null,
|
291 |
"trial_params": null
|