Training in progress, step 12000
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +51 -3
- pytorch_model.bin +1 -1
- runs/May10_03-30-00_b2d6d2516701/events.out.tfevents.1683689456.b2d6d2516701.33377.0 +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 3871543575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8373da8a35ea2973595aaa754eb1ce4ce158cf82e530eb5f3d3263c26016eafe
|
3 |
size 3871543575
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f0c1477718f243e5c2feb4582e32e5aec1009dee1bba00375d74beb1c51e8b6
|
3 |
size 1944201353
|
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:b3c214362304afce4731fa2f0b02f3ed0d948ac7e1592784b2fc59f7d950813d
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b3ea0646994a87a4341acac6bafbc5e858aebc07f9ae2570dcf52ec4e42c905
|
3 |
size 557
|
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:aba867de59f21a3b55b7c3b356f82675050d5da836e24f4ec1d060a995ce5ac1
|
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,
|
@@ -102,11 +102,59 @@
|
|
102 |
"learning_rate": 1.8046919211584273e-05,
|
103 |
"loss": 1.6065,
|
104 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
}
|
106 |
],
|
107 |
"max_steps": 14178,
|
108 |
"num_train_epochs": 1,
|
109 |
-
"total_flos":
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|
112 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.8463817181548878,
|
5 |
+
"global_step": 12000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
102 |
"learning_rate": 1.8046919211584273e-05,
|
103 |
"loss": 1.6065,
|
104 |
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.6,
|
108 |
+
"learning_rate": 1.569505472339987e-05,
|
109 |
+
"loss": 1.6454,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.63,
|
114 |
+
"learning_rate": 1.3404218833084988e-05,
|
115 |
+
"loss": 1.6504,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.67,
|
120 |
+
"learning_rate": 1.1206887331469077e-05,
|
121 |
+
"loss": 1.6647,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.71,
|
126 |
+
"learning_rate": 9.134210454381382e-06,
|
127 |
+
"loss": 1.7032,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.74,
|
132 |
+
"learning_rate": 7.215571284652925e-06,
|
133 |
+
"loss": 1.6892,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.78,
|
138 |
+
"learning_rate": 5.478169205974455e-06,
|
139 |
+
"loss": 1.7176,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.81,
|
144 |
+
"learning_rate": 3.946634313732729e-06,
|
145 |
+
"loss": 1.7457,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.85,
|
150 |
+
"learning_rate": 2.645046185968865e-06,
|
151 |
+
"loss": 1.7474,
|
152 |
+
"step": 12000
|
153 |
}
|
154 |
],
|
155 |
"max_steps": 14178,
|
156 |
"num_train_epochs": 1,
|
157 |
+
"total_flos": 1.2217331547734016e+16,
|
158 |
"trial_name": null,
|
159 |
"trial_params": null
|
160 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1944201353
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f0c1477718f243e5c2feb4582e32e5aec1009dee1bba00375d74beb1c51e8b6
|
3 |
size 1944201353
|
runs/May10_03-30-00_b2d6d2516701/events.out.tfevents.1683689456.b2d6d2516701.33377.0
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 sha256:2baa34955eb027dbe249395493ed4910cb78637a0b8e2f32db680729a5f5a058
|
3 |
+
size 6660
|