Training in progress, step 300, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +2 -2
- 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 109069176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57e0346512b938a383f37320e5d343222cd2331e25cd1ec55fbe02ea29369be6
|
3 |
size 109069176
|
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:f146237b7dfca63586345fb8a59504e97e02f0ccb823442a8f14fc374051d511
|
3 |
+
size 218182650
|
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:da052e96cf9af7d29510259261932db0d2c43a9e4ae003efa69491424598d0e8
|
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:a2e3621c30fd722124835e1051457822683acabc33f5d4c8ed43ad91d36b67ee
|
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:aa49469c46eb3264eff0265e070e7170722684015227e85a7f7ac7a111a6b892
|
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 sha256:2e882ac8b19c8d121eccd15242ddb9097a7b4460c11dad8faf48a7cb56a1bdec
|
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 sha256:636b91c84ea158c73721ddc6e02c605f049f1e7eccdf6dfb1f72a5d988e01bf7
|
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 sha256:152e2166d3f07edd04f4a5a5c028e4755961fc291a022e2d72de72bd18616a56
|
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:e1e20b00ec8a787841f931236b32b37685817fd25f2f6bd0d0d872066d4eeb5f
|
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 sha256:1cc7681c3ba2584248ab1e45157c987143d248209b684c086287377ebe012996
|
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 sha256:7c54e92cf0ebd7f7b8abb44373651ce86715309e5b7eac555dc11af1056377f8
|
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,
|
@@ -23,6 +23,14 @@
|
|
23 |
"eval_samples_per_second": 9.355,
|
24 |
"eval_steps_per_second": 0.292,
|
25 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
],
|
28 |
"logging_steps": 500,
|
@@ -42,7 +50,7 @@
|
|
42 |
"attributes": {}
|
43 |
}
|
44 |
},
|
45 |
-
"total_flos":
|
46 |
"train_batch_size": 4,
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.75,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 300,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
23 |
"eval_samples_per_second": 9.355,
|
24 |
"eval_steps_per_second": 0.292,
|
25 |
"step": 200
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.75,
|
29 |
+
"eval_loss": 0.018071258440613747,
|
30 |
+
"eval_runtime": 3.4148,
|
31 |
+
"eval_samples_per_second": 9.371,
|
32 |
+
"eval_steps_per_second": 0.293,
|
33 |
+
"step": 300
|
34 |
}
|
35 |
],
|
36 |
"logging_steps": 500,
|
|
|
50 |
"attributes": {}
|
51 |
}
|
52 |
},
|
53 |
+
"total_flos": 4.4426652083552256e+17,
|
54 |
"train_batch_size": 4,
|
55 |
"trial_name": null,
|
56 |
"trial_params": null
|