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/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 sha256:7f92b8c43031f8ee3276b4dc256e795b7c677c7464e0ee7b1f7db89499f65bad
|
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 sha256:98aa7590b826f7c100bd25c1847697815e873e462bd83c4f92a4f67666e2faf5
|
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 sha256:7463bfe2c3f461a3b9c3dfa94385d94de5bb3917c831d3a99cec58ab3483967d
|
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 sha256:777b0b28b2c30a2f544cdf649007701bbb2374c6249a72c15fb9fa58f9c480dc
|
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": 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.
|
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": 181.059,
|
107 |
"eval_steps_per_second": 0.708,
|
108 |
"step": 2800
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.31,
|
112 |
+
"learning_rate": 9.968604407135362e-06,
|
113 |
+
"loss": 0.7386,
|
114 |
+
"step": 3000
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.34,
|
118 |
+
"eval_accuracy": 0.8676090837993773,
|
119 |
+
"eval_f1": 0.8684186652379281,
|
120 |
+
"eval_loss": 0.7080894708633423,
|
121 |
+
"eval_runtime": 748.8743,
|
122 |
+
"eval_samples_per_second": 180.989,
|
123 |
+
"eval_steps_per_second": 0.708,
|
124 |
+
"step": 3200
|
125 |
}
|
126 |
],
|
127 |
"max_steps": 953000,
|
128 |
"num_train_epochs": 100,
|
129 |
+
"total_flos": 1.3431142392673536e+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 2268278205
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98aa7590b826f7c100bd25c1847697815e873e462bd83c4f92a4f67666e2faf5
|
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 sha256:428d1fbe340390cb019574ef113eaa94c94c888872fe5975f243975803260250
|
3 |
+
size 5773
|