Training in progress, step 37, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 275817586
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e6e20eccdfff1bbad3326adbd63cccd2c5343f9250e84d3cff96dd9df609e76
|
3 |
size 275817586
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6eeb7eb440a178d4657c6e6fa3c383b79eae99168c0f75d2751a9dc5722d00b9
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:403a4035e63034a6e33503614432aa83d524d5b8ffac47cac18a35f9606be4b7
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -169,12 +169,12 @@
|
|
169 |
"should_evaluate": false,
|
170 |
"should_log": false,
|
171 |
"should_save": true,
|
172 |
-
"should_training_stop":
|
173 |
},
|
174 |
"attributes": {}
|
175 |
}
|
176 |
},
|
177 |
-
"total_flos": 2.
|
178 |
"train_batch_size": 2,
|
179 |
"trial_name": null,
|
180 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.015240448975388735,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 37,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
169 |
"should_evaluate": false,
|
170 |
"should_log": false,
|
171 |
"should_save": true,
|
172 |
+
"should_training_stop": true
|
173 |
},
|
174 |
"attributes": {}
|
175 |
}
|
176 |
},
|
177 |
+
"total_flos": 2.6197187817897984e+16,
|
178 |
"train_batch_size": 2,
|
179 |
"trial_name": null,
|
180 |
"trial_params": null
|