willtensora
commited on
Training in progress, step 3980, 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 +17 -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 281587880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7057efa04f84d06fb8967e215cd3ed4e982d7324a9964d6bbddac5f0e932d7f5
|
3 |
size 281587880
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 143366164
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e1eb62a18526c2a140b51e8df453f354efe9fff401a06b4a4b58ee9618117dd
|
3 |
size 143366164
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc3697b212f20146262137e7c1a969576663ccc4ae69304edc36288b1d18cfd1
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b9e6d31c8b9ec88e33f75ea2e1485990411f6bd2ad3eadb72c07fb2ff77cc4a
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d078af19d6439842c947502bac22108599fc2ee9fcd36b51d3f5f8765f9e42c
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5982284510275852c78aa2d02bd147d4856df83b4bf467c5c077c2680e8271c0
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0a4ea943eff6a00a0d44284eab894bea8fb50f7f4cf9fce50a355f53053d12e
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae334b3ce7770bc0260e90dc8782002eb4f829e4a83cf87989a3bcab2ddad5aa
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cec5f6de25d29de2f1bb3c4f3529450759465854bf2202d64d33659c58ee0a0e
|
3 |
size 15984
|
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 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd393c8d7b7d37049aa33eaacfe9ea78417f491646acb1001289f2f04bc216ff
|
3 |
size 15984
|
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:e374cd16ce446630eb5de7b6aef11f861ca1227fccdd18be31c30ca89d07e197
|
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": 99.
|
5 |
"eval_steps": 40,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -3579,6 +3579,20 @@
|
|
3579 |
"eval_samples_per_second": 110.154,
|
3580 |
"eval_steps_per_second": 15.299,
|
3581 |
"step": 3960
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3582 |
}
|
3583 |
],
|
3584 |
"logging_steps": 10,
|
@@ -3598,7 +3612,7 @@
|
|
3598 |
"attributes": {}
|
3599 |
}
|
3600 |
},
|
3601 |
-
"total_flos": 1.
|
3602 |
"train_batch_size": 1,
|
3603 |
"trial_name": null,
|
3604 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 99.5,
|
5 |
"eval_steps": 40,
|
6 |
+
"global_step": 3980,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
3579 |
"eval_samples_per_second": 110.154,
|
3580 |
"eval_steps_per_second": 15.299,
|
3581 |
"step": 3960
|
3582 |
+
},
|
3583 |
+
{
|
3584 |
+
"epoch": 99.25,
|
3585 |
+
"grad_norm": 1.4808772903052159e-05,
|
3586 |
+
"learning_rate": 2.8093068117240885e-08,
|
3587 |
+
"loss": 0.0,
|
3588 |
+
"step": 3970
|
3589 |
+
},
|
3590 |
+
{
|
3591 |
+
"epoch": 99.5,
|
3592 |
+
"grad_norm": 1.7599566490389407e-05,
|
3593 |
+
"learning_rate": 1.2486132855826781e-08,
|
3594 |
+
"loss": 0.0,
|
3595 |
+
"step": 3980
|
3596 |
}
|
3597 |
],
|
3598 |
"logging_steps": 10,
|
|
|
3612 |
"attributes": {}
|
3613 |
}
|
3614 |
},
|
3615 |
+
"total_flos": 1.6756598975863194e+17,
|
3616 |
"train_batch_size": 1,
|
3617 |
"trial_name": null,
|
3618 |
"trial_params": null
|