Training in progress, step 3600
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 sha256:6b515fd3d11f5b10211b01af6872b2f9b2e47ca4461155af7c064b3f12466398
|
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:dfa8e88f1ef2108a5112aa122906add0c35300930609a9dab3afa24f9f959e3e
|
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:ad85bf597a828151074cbe8ecc3bc32353990ed9c8dfc936d0f59db3d59bfec2
|
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:c861132fff3e01c50e89d9863013383588fde3bf21f375c228cd2b244b9d9dfe
|
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,
|
@@ -122,11 +122,27 @@
|
|
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.
|
130 |
"trial_name": null,
|
131 |
"trial_params": null
|
132 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3777544596012592,
|
5 |
+
"global_step": 3600,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
122 |
"eval_samples_per_second": 244.98,
|
123 |
"eval_steps_per_second": 0.958,
|
124 |
"step": 3200
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 0.37,
|
128 |
+
"learning_rate": 9.963483735571879e-06,
|
129 |
+
"loss": 0.8814,
|
130 |
+
"step": 3500
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 0.38,
|
134 |
+
"eval_accuracy": 0.8263365255500302,
|
135 |
+
"eval_f1": 0.8258586186708066,
|
136 |
+
"eval_loss": 0.8168812990188599,
|
137 |
+
"eval_runtime": 552.7858,
|
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": 1.4800403774985523e+17,
|
146 |
"trial_name": null,
|
147 |
"trial_params": null
|
148 |
}
|
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:dfa8e88f1ef2108a5112aa122906add0c35300930609a9dab3afa24f9f959e3e
|
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 sha256:490ab4ee75efcaa711c96bf2bb12f18c021416e1da63fd70810a9164a4f81503
|
3 |
+
size 5930
|