Training in progress, step 4000
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 sha256:981f677fcc15865be15a1414ef2839a31ba535ad15805bf98b10f0fa9e0205d2
|
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:da56a2889edc75ea532c9a3290ea8d064ca1e14655cd073baa3d0241d1edbe13
|
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 sha256:3dfa48f997ab9962fc5faba7f606b37d054968eb6bdea62ccf0c925c6deb9ac2
|
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:dcf89b4eea8440e8774b9690e94c270a2014296ff209cfc285d74fbc54c9c796
|
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,
|
@@ -138,11 +138,27 @@
|
|
138 |
"eval_samples_per_second": 245.191,
|
139 |
"eval_steps_per_second": 0.959,
|
140 |
"step": 3600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
141 |
}
|
142 |
],
|
143 |
"max_steps": 953000,
|
144 |
"num_train_epochs": 100,
|
145 |
-
"total_flos": 1.
|
146 |
"trial_name": null,
|
147 |
"trial_params": null
|
148 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.4197271773347324,
|
5 |
+
"global_step": 4000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
138 |
"eval_samples_per_second": 245.191,
|
139 |
"eval_steps_per_second": 0.959,
|
140 |
"step": 3600
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.42,
|
144 |
+
"learning_rate": 9.958247639034628e-06,
|
145 |
+
"loss": 0.8691,
|
146 |
+
"step": 4000
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.42,
|
150 |
+
"eval_accuracy": 0.8314199707831014,
|
151 |
+
"eval_f1": 0.831654438222622,
|
152 |
+
"eval_loss": 0.8018559813499451,
|
153 |
+
"eval_runtime": 553.5512,
|
154 |
+
"eval_samples_per_second": 244.852,
|
155 |
+
"eval_steps_per_second": 0.957,
|
156 |
+
"step": 4000
|
157 |
}
|
158 |
],
|
159 |
"max_steps": 953000,
|
160 |
"num_train_epochs": 100,
|
161 |
+
"total_flos": 1.6446377682348134e+17,
|
162 |
"trial_name": null,
|
163 |
"trial_params": null
|
164 |
}
|
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:da56a2889edc75ea532c9a3290ea8d064ca1e14655cd073baa3d0241d1edbe13
|
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:a9481b9cfab145b4a3c0e2baff73ddc5940a690f61c498fe9c105ea6be47c602
|
3 |
+
size 6456
|