MohamedAhmedAE
commited on
Commit
•
78cd5fb
1
Parent(s):
4473b0e
Training in progress, step 800, 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 sha256:46722a6c1e8fcc1af409969eb6dda679f6ae4f5765bfa779279b1bbf7a6a1b81
|
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 sha256:051ec58c662275272caf7cf3e35e2605b9f5cd07bfadcb5837f612847dc33adf
|
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:c47dc8cc8d9492142296c3e4e14a06d78de1dc5b37a7008b6df2888e1109d0f8
|
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:e8f132012c5b818670e4adff6f24c665930d4cab15cd962aaaeccbdabdd884fe
|
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,
|
@@ -28,6 +28,13 @@
|
|
28 |
"learning_rate": 1.9999999617416517e-05,
|
29 |
"loss": 1.6314,
|
30 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
}
|
32 |
],
|
33 |
"logging_steps": 200,
|
@@ -35,7 +42,7 @@
|
|
35 |
"num_input_tokens_seen": 0,
|
36 |
"num_train_epochs": 5,
|
37 |
"save_steps": 200,
|
38 |
-
"total_flos":
|
39 |
"train_batch_size": 1,
|
40 |
"trial_name": null,
|
41 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0005949304489122069,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
28 |
"learning_rate": 1.9999999617416517e-05,
|
29 |
"loss": 1.6314,
|
30 |
"step": 600
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.0,
|
34 |
+
"grad_norm": 10.143038749694824,
|
35 |
+
"learning_rate": 1.999999931524823e-05,
|
36 |
+
"loss": 1.5416,
|
37 |
+
"step": 800
|
38 |
}
|
39 |
],
|
40 |
"logging_steps": 200,
|
|
|
42 |
"num_input_tokens_seen": 0,
|
43 |
"num_train_epochs": 5,
|
44 |
"save_steps": 200,
|
45 |
+
"total_flos": 9978438301335552.0,
|
46 |
"train_batch_size": 1,
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|