MohamedAhmedAE
commited on
Commit
•
a43e2cf
1
Parent(s):
04332f3
Training in progress, step 11400, 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:ac7e07e5bb14a4a4cc0964f7cd728e86c6dd0e469b29f0710b6d7a1c335fbffc
|
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:f0f695b9724dd9d30c7d12e2655c18b7ebd533daeee1146ff450bbab43e321fb
|
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 sha256:66ec65a4ec9e27552c1d645b591799723672eef7af9c95a4e66173a21b097caf
|
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:b40e1ebe979c78c76ee0b89adbef70ff0ea3286d5b63b173abcc348d810db8e6
|
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,
|
@@ -399,6 +399,13 @@
|
|
399 |
"learning_rate": 1.9999863357206127e-05,
|
400 |
"loss": 1.5328,
|
401 |
"step": 11200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
402 |
}
|
403 |
],
|
404 |
"logging_steps": 200,
|
@@ -406,7 +413,7 @@
|
|
406 |
"num_input_tokens_seen": 0,
|
407 |
"num_train_epochs": 5,
|
408 |
"save_steps": 200,
|
409 |
-
"total_flos": 1.
|
410 |
"train_batch_size": 1,
|
411 |
"trial_name": null,
|
412 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.008477758896998948,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 11400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
399 |
"learning_rate": 1.9999863357206127e-05,
|
400 |
"loss": 1.5328,
|
401 |
"step": 11200
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.01,
|
405 |
+
"grad_norm": 5.111497402191162,
|
406 |
+
"learning_rate": 1.9999858428217852e-05,
|
407 |
+
"loss": 1.6124,
|
408 |
+
"step": 11400
|
409 |
}
|
410 |
],
|
411 |
"logging_steps": 200,
|
|
|
413 |
"num_input_tokens_seen": 0,
|
414 |
"num_train_epochs": 5,
|
415 |
"save_steps": 200,
|
416 |
+
"total_flos": 1.4908117193876275e+17,
|
417 |
"train_batch_size": 1,
|
418 |
"trial_name": null,
|
419 |
"trial_params": null
|