MohamedAhmedAE
commited on
Commit
•
3e5cdb1
1
Parent(s):
b2affd6
Training in progress, step 8600, 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 sha256:4533d0cc5d4d50b82cfb5df3d5e25daabf3844635d37d8a1136dc9efe3ae8cbf
|
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:d5c5d42eb180a29ed66f0b671c8c70e4743c5ad821b1415728c0f72958e41f51
|
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 sha256:46108bf4b002a3517fd8a49b94b3b4ed59fda2273b5a44b5a4115826d33fd2b4
|
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:bdd0fb75028b56249c2d8c029d1a64d4b86a271bd278ff63d1486066e1925aa9
|
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,
|
@@ -301,6 +301,13 @@
|
|
301 |
"learning_rate": 1.9999923174987494e-05,
|
302 |
"loss": 1.5533,
|
303 |
"step": 8400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
304 |
}
|
305 |
],
|
306 |
"logging_steps": 200,
|
@@ -308,7 +315,7 @@
|
|
308 |
"num_input_tokens_seen": 0,
|
309 |
"num_train_epochs": 5,
|
310 |
"save_steps": 200,
|
311 |
-
"total_flos": 1.
|
312 |
"train_batch_size": 1,
|
313 |
"trial_name": null,
|
314 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.006395502325806224,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 8600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
301 |
"learning_rate": 1.9999923174987494e-05,
|
302 |
"loss": 1.5533,
|
303 |
"step": 8400
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.01,
|
307 |
+
"grad_norm": 3.5668296813964844,
|
308 |
+
"learning_rate": 1.99999194681957e-05,
|
309 |
+
"loss": 1.5581,
|
310 |
+
"step": 8600
|
311 |
}
|
312 |
],
|
313 |
"logging_steps": 200,
|
|
|
315 |
"num_input_tokens_seen": 0,
|
316 |
"num_train_epochs": 5,
|
317 |
"save_steps": 200,
|
318 |
+
"total_flos": 1.1254267984893542e+17,
|
319 |
"train_batch_size": 1,
|
320 |
"trial_name": null,
|
321 |
"trial_params": null
|