Dmitriy007
commited on
Commit
•
986fa5a
1
Parent(s):
63123e4
Training in progress, step 3000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +43 -3
- last-checkpoint/training_args.bin +2 -2
- pytorch_model.bin +1 -1
- runs/Mar21_09-06-28_da74753029b6/events.out.tfevents.1679389598.da74753029b6.214.0 +2 -2
- runs/Mar21_09-39-35_da74753029b6/1679391593.2916124/events.out.tfevents.1679391593.da74753029b6.214.3 +3 -0
- runs/Mar21_09-39-35_da74753029b6/events.out.tfevents.1679391593.da74753029b6.214.2 +3 -0
- training_args.bin +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2847145157
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99aca7ebb70c068800a01f3f2bc558e86618447f48d39d96493907dae2d169e2
|
3 |
size 2847145157
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1f20ea17f50fb430fb528ba75a3dc4f5562847c1ff94148b0c2a30e84298afb
|
3 |
size 1524261149
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b236397a3c8069f104586e535dba9c48a651837fa9c511ff8c05fdab8ffc4abb
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:457eee4f58f802852f198511d6bc2fc834f63cd9658af75105e4cfa65c539aa6
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -26,11 +26,51 @@
|
|
26 |
"eval_samples_per_second": 15.475,
|
27 |
"eval_steps_per_second": 5.161,
|
28 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
}
|
30 |
],
|
31 |
"max_steps": 19990,
|
32 |
"num_train_epochs": 5,
|
33 |
-
"total_flos":
|
34 |
"trial_name": null,
|
35 |
"trial_params": null
|
36 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7503751875937968,
|
5 |
+
"global_step": 3000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
26 |
"eval_samples_per_second": 15.475,
|
27 |
"eval_steps_per_second": 5.161,
|
28 |
"step": 1000
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 0.38,
|
32 |
+
"learning_rate": 1.8499249624812408e-05,
|
33 |
+
"loss": 2.8083,
|
34 |
+
"step": 1500
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 0.5,
|
38 |
+
"learning_rate": 1.7998999499749875e-05,
|
39 |
+
"loss": 2.8023,
|
40 |
+
"step": 2000
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 0.5,
|
44 |
+
"eval_loss": 3.1418557167053223,
|
45 |
+
"eval_runtime": 136.6543,
|
46 |
+
"eval_samples_per_second": 15.492,
|
47 |
+
"eval_steps_per_second": 5.166,
|
48 |
+
"step": 2000
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 0.63,
|
52 |
+
"learning_rate": 1.7498749374687345e-05,
|
53 |
+
"loss": 2.8088,
|
54 |
+
"step": 2500
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.75,
|
58 |
+
"learning_rate": 1.6998499249624815e-05,
|
59 |
+
"loss": 2.826,
|
60 |
+
"step": 3000
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 0.75,
|
64 |
+
"eval_loss": 3.1343915462493896,
|
65 |
+
"eval_runtime": 137.3583,
|
66 |
+
"eval_samples_per_second": 15.412,
|
67 |
+
"eval_steps_per_second": 5.14,
|
68 |
+
"step": 3000
|
69 |
}
|
70 |
],
|
71 |
"max_steps": 19990,
|
72 |
"num_train_epochs": 5,
|
73 |
+
"total_flos": 4244452392960000.0,
|
74 |
"trial_name": null,
|
75 |
"trial_params": null
|
76 |
}
|
last-checkpoint/training_args.bin
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 sha256:918b854d4ced36747513144ebd0eebe9f265f3dbaedccdbeea45c88b4a5aac6b
|
3 |
+
size 3515
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1524261149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1f20ea17f50fb430fb528ba75a3dc4f5562847c1ff94148b0c2a30e84298afb
|
3 |
size 1524261149
|
runs/Mar21_09-06-28_da74753029b6/events.out.tfevents.1679389598.da74753029b6.214.0
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 sha256:6f8dca96f1cab23f1283eb228ef48f9c0f89413344c0be35fb391116530dcc8e
|
3 |
+
size 5368
|
runs/Mar21_09-39-35_da74753029b6/1679391593.2916124/events.out.tfevents.1679391593.da74753029b6.214.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d248302158160050484d584b627dbf670a152972ea4fed24e0e85d16f5c3f6f1
|
3 |
+
size 5742
|
runs/Mar21_09-39-35_da74753029b6/events.out.tfevents.1679391593.da74753029b6.214.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97cf29a000561f36e5b1b737ef8aab0daa80fe795b383cf0de3480aa91e7b4d7
|
3 |
+
size 4783
|
training_args.bin
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 sha256:918b854d4ced36747513144ebd0eebe9f265f3dbaedccdbeea45c88b4a5aac6b
|
3 |
+
size 3515
|