MohamedAhmedAE
commited on
Commit
•
6040b9f
1
Parent(s):
9bb0593
Training in progress, step 9600, 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 sha256:757dda966b2f4d181a128ff59f9b919daff4e506360c00213ab3ec0c0ff2691e
|
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 sha256:07c1cbeda60e9c2a4013fcd83f0f4b91298e0a0b17ca0cb5693b8fb2316ae9ce
|
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 sha256:83bf192647771b3f8523529c1a3c6ebe56340eb008266267aa5af12c0294e34e
|
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:ce7729d52ceb1dabda5590c3c4f3afbbf1ca186490116815086c48ad76afb3f6
|
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,
|
@@ -336,6 +336,13 @@
|
|
336 |
"learning_rate": 1.9999903767717127e-05,
|
337 |
"loss": 1.5388,
|
338 |
"step": 9400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
339 |
}
|
340 |
],
|
341 |
"logging_steps": 200,
|
@@ -343,7 +350,7 @@
|
|
343 |
"num_input_tokens_seen": 0,
|
344 |
"num_train_epochs": 5,
|
345 |
"save_steps": 200,
|
346 |
-
"total_flos": 1.
|
347 |
"train_batch_size": 1,
|
348 |
"trial_name": null,
|
349 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.007139165386946482,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 9600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
336 |
"learning_rate": 1.9999903767717127e-05,
|
337 |
"loss": 1.5388,
|
338 |
"step": 9400
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.01,
|
342 |
+
"grad_norm": 4.206201076507568,
|
343 |
+
"learning_rate": 1.9999899624269806e-05,
|
344 |
+
"loss": 1.5278,
|
345 |
+
"step": 9600
|
346 |
}
|
347 |
],
|
348 |
"logging_steps": 200,
|
|
|
350 |
"num_input_tokens_seen": 0,
|
351 |
"num_train_epochs": 5,
|
352 |
"save_steps": 200,
|
353 |
+
"total_flos": 1.2573875538675302e+17,
|
354 |
"train_batch_size": 1,
|
355 |
"trial_name": null,
|
356 |
"trial_params": null
|