sirr
commited on
Commit
·
d53feaa
1
Parent(s):
5ec101b
Training in progress, step 175, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 40036040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4f3a22e8e651919aa007785e7caa8b12b3e818a0f0d760a5fdd70e9bb67b6ca
|
3 |
size 40036040
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 20523679
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:318c5bcaedd9153e8e8480089f00776e6580cbbb3b084f2d31c3b12ad574e34a
|
3 |
size 20523679
|
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:ca76ebdb2df210532f2f85c5d71f10145eb2e0feff4bc668b9ab7cf7ca8d362c
|
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:b3b65adebd890c42719861402ec044f609c3c6b752cf08b5f17dc5a3c9a4e8be
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -85,13 +85,26 @@
|
|
85 |
"eval_samples_per_second": 1.848,
|
86 |
"eval_steps_per_second": 0.157,
|
87 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
}
|
89 |
],
|
90 |
"logging_steps": 25,
|
91 |
"max_steps": 200,
|
92 |
"num_train_epochs": 2,
|
93 |
"save_steps": 25,
|
94 |
-
"total_flos": 2.
|
95 |
"trial_name": null,
|
96 |
"trial_params": null
|
97 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.75,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 175,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
85 |
"eval_samples_per_second": 1.848,
|
86 |
"eval_steps_per_second": 0.157,
|
87 |
"step": 150
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 1.75,
|
91 |
+
"learning_rate": 0.0001,
|
92 |
+
"loss": 0.5748,
|
93 |
+
"step": 175
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.75,
|
97 |
+
"eval_runtime": 216.7074,
|
98 |
+
"eval_samples_per_second": 1.846,
|
99 |
+
"eval_steps_per_second": 0.157,
|
100 |
+
"step": 175
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 25,
|
104 |
"max_steps": 200,
|
105 |
"num_train_epochs": 2,
|
106 |
"save_steps": 25,
|
107 |
+
"total_flos": 2.90676893810688e+16,
|
108 |
"trial_name": null,
|
109 |
"trial_params": null
|
110 |
}
|