Training in progress, step 2800
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 +19 -3
- pytorch_model.bin +1 -1
- runs/Jun19_23-46-48_f901b8a7e814/events.out.tfevents.1687219534.f901b8a7e814.988.0 +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 2117841669
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a6ffcf3289587cd2cd2d1fbebec6f7dc591becd7671d83187efb7cfd5124b3b
|
3 |
size 2117841669
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2268278205
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d0eb1a4d92eef5efbba1f1d134550f041d1e64dba85cbb9f34fb382efb6639b
|
3 |
size 2268278205
|
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:cc8bdcdf6ae5bb56594025a46bc3a87c08586c897c39f1fd126e0d80ee5f9dcd
|
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 sha256:88f2da83d5e98a6e0eae48d2816e4a5eaf0b946b0b39dd36d126cccbda276923
|
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,
|
@@ -90,11 +90,27 @@
|
|
90 |
"eval_samples_per_second": 180.926,
|
91 |
"eval_steps_per_second": 0.707,
|
92 |
"step": 2400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
93 |
}
|
94 |
],
|
95 |
"max_steps": 953000,
|
96 |
"num_train_epochs": 100,
|
97 |
-
"total_flos": 1.
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|
100 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2938090241343127,
|
5 |
+
"global_step": 2800,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
90 |
"eval_samples_per_second": 180.926,
|
91 |
"eval_steps_per_second": 0.707,
|
92 |
"step": 2400
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.26,
|
96 |
+
"learning_rate": 9.973840503672613e-06,
|
97 |
+
"loss": 0.7517,
|
98 |
+
"step": 2500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.29,
|
102 |
+
"eval_accuracy": 0.8668491493160589,
|
103 |
+
"eval_f1": 0.8662439909072627,
|
104 |
+
"eval_loss": 0.7115087509155273,
|
105 |
+
"eval_runtime": 748.5848,
|
106 |
+
"eval_samples_per_second": 181.059,
|
107 |
+
"eval_steps_per_second": 0.708,
|
108 |
+
"step": 2800
|
109 |
}
|
110 |
],
|
111 |
"max_steps": 953000,
|
112 |
"num_train_epochs": 100,
|
113 |
+
"total_flos": 1.1748750372701952e+17,
|
114 |
"trial_name": null,
|
115 |
"trial_params": null
|
116 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2268278205
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d0eb1a4d92eef5efbba1f1d134550f041d1e64dba85cbb9f34fb382efb6639b
|
3 |
size 2268278205
|
runs/Jun19_23-46-48_f901b8a7e814/events.out.tfevents.1687219534.f901b8a7e814.988.0
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:dcb11010ab6e4429b333d127796173af1ce9c8657b7097707f1de6ecd47d9718
|
3 |
+
size 5247
|