MohamedAhmedAE
commited on
Commit
•
c54cb9b
1
Parent(s):
43e292e
Training in progress, step 7600, 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:f68c43c7f004c1eadd91b9fe7a30fc2b0fd69b4f58b1bc37e1b8caf12c6810ef
|
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:c2e2d7e319df6b910d8660f90fe9f5f432aa3e2fcf0fc9f644ada3faf7f04901
|
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:d10e311d00a264a46fa5f0eed688f7217fcace7c41779a2ffd66f55f87f67920
|
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 sha256:18fe99cd7e53dc1def962f8fb0d7ad9ae866de71ef7bffa4b49eb8c6cbd19c21
|
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,
|
@@ -266,6 +266,13 @@
|
|
266 |
"learning_rate": 1.999994039897775e-05,
|
267 |
"loss": 1.5864,
|
268 |
"step": 7400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
269 |
}
|
270 |
],
|
271 |
"logging_steps": 200,
|
@@ -273,7 +280,7 @@
|
|
273 |
"num_input_tokens_seen": 0,
|
274 |
"num_train_epochs": 5,
|
275 |
"save_steps": 200,
|
276 |
-
"total_flos": 9.
|
277 |
"train_batch_size": 1,
|
278 |
"trial_name": null,
|
279 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.005651839264665965,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 7600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
266 |
"learning_rate": 1.999994039897775e-05,
|
267 |
"loss": 1.5864,
|
268 |
"step": 7400
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.01,
|
272 |
+
"grad_norm": 2.2379679679870605,
|
273 |
+
"learning_rate": 1.9999937128842296e-05,
|
274 |
+
"loss": 1.6411,
|
275 |
+
"step": 7600
|
276 |
}
|
277 |
],
|
278 |
"logging_steps": 200,
|
|
|
280 |
"num_input_tokens_seen": 0,
|
281 |
"num_train_epochs": 5,
|
282 |
"save_steps": 200,
|
283 |
+
"total_flos": 9.98269473472512e+16,
|
284 |
"train_batch_size": 1,
|
285 |
"trial_name": null,
|
286 |
"trial_params": null
|