MohamedAhmedAE
commited on
Commit
•
1c2308f
1
Parent(s):
138a1de
Training in progress, step 9800, 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:f5abc00b30afb0cc7f11475da5329ddda7a8b54916957489c98976e9146772bb
|
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 sha256:20b2d331cc999028b7772cec2bf035150343c98c155579a40021dd1b08f46b51
|
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:c05839636fd5cb5be586f924cedf0045977d387805f980599c45c147e0e837b6
|
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:d8d0791f87a560d6e6d8a6da6d811e646baa7dcb34edbb7ffc991631590e30ba
|
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,
|
@@ -343,6 +343,13 @@
|
|
343 |
"learning_rate": 1.9999899624269806e-05,
|
344 |
"loss": 1.5278,
|
345 |
"step": 9600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
346 |
}
|
347 |
],
|
348 |
"logging_steps": 200,
|
@@ -350,7 +357,7 @@
|
|
350 |
"num_input_tokens_seen": 0,
|
351 |
"num_train_epochs": 5,
|
352 |
"save_steps": 200,
|
353 |
-
"total_flos": 1.
|
354 |
"train_batch_size": 1,
|
355 |
"trial_name": null,
|
356 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.007287897999174534,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 9800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
343 |
"learning_rate": 1.9999899624269806e-05,
|
344 |
"loss": 1.5278,
|
345 |
"step": 9600
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.01,
|
349 |
+
"grad_norm": 3.587338924407959,
|
350 |
+
"learning_rate": 1.9999895393491484e-05,
|
351 |
+
"loss": 1.566,
|
352 |
+
"step": 9800
|
353 |
}
|
354 |
],
|
355 |
"logging_steps": 200,
|
|
|
357 |
"num_input_tokens_seen": 0,
|
358 |
"num_train_epochs": 5,
|
359 |
"save_steps": 200,
|
360 |
+
"total_flos": 1.2813345198044774e+17,
|
361 |
"train_batch_size": 1,
|
362 |
"trial_name": null,
|
363 |
"trial_params": null
|