MohamedAhmedAE
commited on
Commit
•
dcabb66
1
Parent(s):
5be9074
Training in progress, step 10000, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1e13a85964ab8808bfc2b3469a4b76bee0bd96f331a8f39748e7032dc454ef7
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84581014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac5ecf7fc68ce9f8cbd917b2dbb333c1ccbe8c2f546fdb594ee0191e94f36b9b
|
3 |
size 84581014
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4453b9d90bd6b82be8e97e83b1ca59d9d5397ee45aa220e04d942e0915e20392
|
3 |
size 14244
|
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:acbeb015d4bc7f990999b8518ed60979c4618ba57aa1e5c62c07a2978164609d
|
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": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -350,6 +350,13 @@
|
|
350 |
"learning_rate": 1.9999895393491484e-05,
|
351 |
"loss": 1.566,
|
352 |
"step": 9800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
353 |
}
|
354 |
],
|
355 |
"logging_steps": 200,
|
@@ -357,7 +364,7 @@
|
|
357 |
"num_input_tokens_seen": 0,
|
358 |
"num_train_epochs": 5,
|
359 |
"save_steps": 200,
|
360 |
-
"total_flos": 1.
|
361 |
"train_batch_size": 1,
|
362 |
"trial_name": null,
|
363 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.007436630611402585,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 10000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
350 |
"learning_rate": 1.9999895393491484e-05,
|
351 |
"loss": 1.566,
|
352 |
"step": 9800
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.01,
|
356 |
+
"grad_norm": 4.078786849975586,
|
357 |
+
"learning_rate": 1.9999891075382195e-05,
|
358 |
+
"loss": 1.5554,
|
359 |
+
"step": 10000
|
360 |
}
|
361 |
],
|
362 |
"logging_steps": 200,
|
|
|
364 |
"num_input_tokens_seen": 0,
|
365 |
"num_train_epochs": 5,
|
366 |
"save_steps": 200,
|
367 |
+
"total_flos": 1.3069591544338022e+17,
|
368 |
"train_batch_size": 1,
|
369 |
"trial_name": null,
|
370 |
"trial_params": null
|