Training in progress, step 1200
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 sha256:931527c8c88660c2666a43213924a4437fb26598f8d694633e6addd30a25cf30
|
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 sha256:0ac6cec13eb192114484753da8e12b55696fb6df1f67bff8a866135805e1b710
|
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:aa03d66ad4fd99facf691c9f33587a2332d5ec86a1219a59259cf0fc6ed903bc
|
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 sha256:6e9e069c3b7bb9e5c6e73416e11704fa0cdbc8efb80dddb0c74892ca1b31b28f
|
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,
|
@@ -32,11 +32,27 @@
|
|
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":
|
40 |
"trial_name": null,
|
41 |
"trial_params": null
|
42 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.1259181532004197,
|
5 |
+
"global_step": 1200,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
32 |
"eval_samples_per_second": 247.669,
|
33 |
"eval_steps_per_second": 0.968,
|
34 |
"step": 800
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 0.1,
|
38 |
+
"learning_rate": 9.9895592864638e-06,
|
39 |
+
"loss": 1.0807,
|
40 |
+
"step": 1000
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 0.13,
|
44 |
+
"eval_accuracy": 0.7675633401702844,
|
45 |
+
"eval_f1": 0.7670752144773497,
|
46 |
+
"eval_loss": 0.9420500993728638,
|
47 |
+
"eval_runtime": 547.3649,
|
48 |
+
"eval_samples_per_second": 247.619,
|
49 |
+
"eval_steps_per_second": 0.968,
|
50 |
+
"step": 1200
|
51 |
}
|
52 |
],
|
53 |
"max_steps": 953000,
|
54 |
"num_train_epochs": 100,
|
55 |
+
"total_flos": 4.919234461559194e+16,
|
56 |
"trial_name": null,
|
57 |
"trial_params": null
|
58 |
}
|
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 sha256:0ac6cec13eb192114484753da8e12b55696fb6df1f67bff8a866135805e1b710
|
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:dd177559e350d3861b9ae4f88b4b4d77e74f450016e2cfd62e23206588f5a1d0
|
3 |
+
size 5773
|