MohamedAhmedAE
commited on
Commit
•
feaad17
1
Parent(s):
86e1573
Training in progress, step 400, 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 sha256:8fe26216da1bb3ebaab64bfdb360c9aaadefeb27a569d66bae7e6cb2e242a6d1
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3323fc1a621e1a5fbb6a729145d2305369dd78e4a6afb19820024f3325e85179
|
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 sha256:1cfd6051928a8e961ef995d4d43e26d5715feab4fcd701563228166343bafae5
|
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 sha256:481f596060c3212f56594c5c4670b5c573732140807b73f1dd3dd781bdd56d29
|
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,
|
@@ -14,6 +14,13 @@
|
|
14 |
"learning_rate": 1.9999999959757473e-05,
|
15 |
"loss": 1.835,
|
16 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 200,
|
@@ -21,7 +28,7 @@
|
|
21 |
"num_input_tokens_seen": 0,
|
22 |
"num_train_epochs": 5,
|
23 |
"save_steps": 200,
|
24 |
-
"total_flos":
|
25 |
"train_batch_size": 1,
|
26 |
"trial_name": null,
|
27 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00029746522445610346,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
14 |
"learning_rate": 1.9999999959757473e-05,
|
15 |
"loss": 1.835,
|
16 |
"step": 200
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0,
|
20 |
+
"grad_norm": 2.7373883724212646,
|
21 |
+
"learning_rate": 1.9999999832252933e-05,
|
22 |
+
"loss": 1.6278,
|
23 |
+
"step": 400
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 200,
|
|
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 5,
|
30 |
"save_steps": 200,
|
31 |
+
"total_flos": 4910339289341952.0,
|
32 |
"train_batch_size": 1,
|
33 |
"trial_name": null,
|
34 |
"trial_params": null
|