Training in progress, step 3200
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/Jun11_01-13-42_3ff04b58b9a0/events.out.tfevents.1686447207.3ff04b58b9a0.473.0 +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:d643777e7fbd76351e4bc7595c4120f46659ffb8f647e42ba2fbea1408bf2b7a
|
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:bd5cb4005475f16ff6bf556d48a1bc4d2a359f90b41a7ec37c65217d37cf53b6
|
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:db8a09215b8ac12259f9f1e1025378f0a1c43e69e7b3f05657f8af4daccc4832
|
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:b327a6e82bce37f4dc3e7426607b436e3f0350a6ddf784305d402b77e8f40263
|
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,
|
@@ -106,11 +106,27 @@
|
|
106 |
"eval_samples_per_second": 245.039,
|
107 |
"eval_steps_per_second": 0.958,
|
108 |
"step": 2800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
109 |
}
|
110 |
],
|
111 |
"max_steps": 953000,
|
112 |
"num_train_epochs": 100,
|
113 |
-
"total_flos": 1.
|
114 |
"trial_name": null,
|
115 |
"trial_params": null
|
116 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3357817418677859,
|
5 |
+
"global_step": 3200,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
106 |
"eval_samples_per_second": 245.039,
|
107 |
"eval_steps_per_second": 0.958,
|
108 |
"step": 2800
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.31,
|
112 |
+
"learning_rate": 9.968730325288564e-06,
|
113 |
+
"loss": 0.9058,
|
114 |
+
"step": 3000
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.34,
|
118 |
+
"eval_accuracy": 0.8222122209269725,
|
119 |
+
"eval_f1": 0.8218673977332275,
|
120 |
+
"eval_loss": 0.828486442565918,
|
121 |
+
"eval_runtime": 553.2621,
|
122 |
+
"eval_samples_per_second": 244.98,
|
123 |
+
"eval_steps_per_second": 0.958,
|
124 |
+
"step": 3200
|
125 |
}
|
126 |
],
|
127 |
"max_steps": 953000,
|
128 |
"num_train_epochs": 100,
|
129 |
+
"total_flos": 1.315755998376146e+17,
|
130 |
"trial_name": null,
|
131 |
"trial_params": null
|
132 |
}
|
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:bd5cb4005475f16ff6bf556d48a1bc4d2a359f90b41a7ec37c65217d37cf53b6
|
3 |
size 2242911029
|
runs/Jun11_01-13-42_3ff04b58b9a0/events.out.tfevents.1686447207.3ff04b58b9a0.473.0
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 sha256:394295c49d92be1e48a6d7f188e35c11794f98467c00c44a85c1b3ae9760d6b0
|
3 |
+
size 5404
|