Training in progress, step 200, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +11 -3
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 161495976
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22fe979fa21a573d259e66a6652cfdaf2b4268c3842d3833c0e66e3286cc9562
|
3 |
size 161495976
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 323030394
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e11352626ee848cd64bae5844b3927249421fe12ebb856262024ee5ead3fed8
|
3 |
size 323030394
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fcfcb52531ddebc39d615047d0388df1e6690712dc6edf33ff6a454c4650834
|
3 |
size 15920
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef468d1a591fdb6758c6a7221f171c62c758bedd4b8c43e43a23ba0267fab370
|
3 |
size 15920
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d95620ec3c3871de4ef7878e97a2bd252471cd1cbdb2852cc1a3244f331ac2b
|
3 |
size 15920
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d63e1c9414cd00553fb70d5d30d6686fe59cb4e8bd15c3a4648938b274fc669
|
3 |
size 15920
|
last-checkpoint/rng_state_4.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:563a15ecfe5aed2d0a635efffb8809c5c091e687f41c8d80a3e7062c153c4c55
|
3 |
size 15920
|
last-checkpoint/rng_state_5.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6eadb24591dec720aad963693bfdb95431e1973871f2f318bbe81499b6c0d608
|
3 |
size 15920
|
last-checkpoint/rng_state_6.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9235bc1df8e4004193c2e0d797bd4e557eb27e9628abc75034b298a7b84212b3
|
3 |
size 15920
|
last-checkpoint/rng_state_7.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cdb343de060bf59f85f6f7203acc73d37706692d7829abb5936811bffb64802
|
3 |
size 15920
|
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:a27ddb51c34d2aa75074ed0d8a35c26fb0cf078a8da84a293dd1d830c82af59f
|
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": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -15,6 +15,14 @@
|
|
15 |
"eval_samples_per_second": 12.969,
|
16 |
"eval_steps_per_second": 0.405,
|
17 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
}
|
19 |
],
|
20 |
"logging_steps": 500,
|
@@ -34,7 +42,7 @@
|
|
34 |
"attributes": {}
|
35 |
}
|
36 |
},
|
37 |
-
"total_flos":
|
38 |
"train_batch_size": 4,
|
39 |
"trial_name": null,
|
40 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.24024024024024024,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
15 |
"eval_samples_per_second": 12.969,
|
16 |
"eval_steps_per_second": 0.405,
|
17 |
"step": 100
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.24024024024024024,
|
21 |
+
"eval_loss": 0.3434170186519623,
|
22 |
+
"eval_runtime": 2.4641,
|
23 |
+
"eval_samples_per_second": 12.987,
|
24 |
+
"eval_steps_per_second": 0.406,
|
25 |
+
"step": 200
|
26 |
}
|
27 |
],
|
28 |
"logging_steps": 500,
|
|
|
42 |
"attributes": {}
|
43 |
}
|
44 |
},
|
45 |
+
"total_flos": 3.92429856165462e+17,
|
46 |
"train_batch_size": 4,
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|