Training in progress, step 800
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/Jun10_02-32-14_764db004b06b/events.out.tfevents.1686364349.764db004b06b.573.0 +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 2067085189
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4507fd123793cb472cad2bf0682be92ba99bee83a3dd9aaaa5f80f9e8721e5b9
|
3 |
size 2067085189
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2242911029
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fa28531aebac0baf3244aaaab67f5710521f285be1b82b0ec144e45c66ff0d0
|
3 |
size 2242911029
|
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:b60be0a5e95a9ac9be50ab2e09d47c260a487b4ac8e8385c03c83b7dda951cb4
|
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 sha256:5ae712ec7dd92528eac8eb031cea511d8dfe6b3e0076491db75bdae964ff3123
|
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,
|
@@ -16,11 +16,27 @@
|
|
16 |
"eval_samples_per_second": 248.431,
|
17 |
"eval_steps_per_second": 0.971,
|
18 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
}
|
20 |
],
|
21 |
"max_steps": 953000,
|
22 |
"num_train_epochs": 100,
|
23 |
-
"total_flos":
|
24 |
"trial_name": null,
|
25 |
"trial_params": null
|
26 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.08394543546694648,
|
5 |
+
"global_step": 800,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
16 |
"eval_samples_per_second": 248.431,
|
17 |
"eval_steps_per_second": 0.971,
|
18 |
"step": 400
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 0.05,
|
22 |
+
"learning_rate": 9.994805876180483e-06,
|
23 |
+
"loss": 1.4969,
|
24 |
+
"step": 500
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.08,
|
28 |
+
"eval_accuracy": 0.741024657291682,
|
29 |
+
"eval_f1": 0.7346338559187492,
|
30 |
+
"eval_loss": 1.0078158378601074,
|
31 |
+
"eval_runtime": 547.2541,
|
32 |
+
"eval_samples_per_second": 247.669,
|
33 |
+
"eval_steps_per_second": 0.968,
|
34 |
+
"step": 800
|
35 |
}
|
36 |
],
|
37 |
"max_steps": 953000,
|
38 |
"num_train_epochs": 100,
|
39 |
+
"total_flos": 3.288257080770816e+16,
|
40 |
"trial_name": null,
|
41 |
"trial_params": null
|
42 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2242911029
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fa28531aebac0baf3244aaaab67f5710521f285be1b82b0ec144e45c66ff0d0
|
3 |
size 2242911029
|
runs/Jun10_02-32-14_764db004b06b/events.out.tfevents.1686364349.764db004b06b.573.0
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 sha256:5fc2f99e58218140040ce4d0e3a685dcc822ea7aa1b553e24cf643e00f9288ab
|
3 |
+
size 5247
|