Training in progress, step 300, 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 sha256:4b58c031ecf068113eaf372cdd39d13ff7045ace90ed74c85b758acdd7705065
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5d5b37fd6a74396682d04b9fa16668f14d7584c8d0a8f2707f598d123fd0193
|
3 |
+
size 20524127
|
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 sha256:85ec935bf7605484d881e59df21389f866fb1fad88f225a6fcb0526d417076a0
|
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 sha256:4c061cc93bc8f89035440fff607b7c18ef87206a55525ba751b807a11abf6d3e
|
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": 0.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -33,13 +33,26 @@
|
|
33 |
"eval_samples_per_second": 1.755,
|
34 |
"eval_steps_per_second": 0.22,
|
35 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
}
|
37 |
],
|
38 |
"logging_steps": 100,
|
39 |
"max_steps": 957,
|
40 |
"num_train_epochs": 3,
|
41 |
"save_steps": 100,
|
42 |
-
"total_flos":
|
43 |
"trial_name": null,
|
44 |
"trial_params": null
|
45 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9404388714733543,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 300,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
33 |
"eval_samples_per_second": 1.755,
|
34 |
"eval_steps_per_second": 0.22,
|
35 |
"step": 200
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 0.94,
|
39 |
+
"learning_rate": 0.0002,
|
40 |
+
"loss": 0.5863,
|
41 |
+
"step": 300
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.94,
|
45 |
+
"eval_runtime": 513.6336,
|
46 |
+
"eval_samples_per_second": 1.752,
|
47 |
+
"eval_steps_per_second": 0.22,
|
48 |
+
"step": 300
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 100,
|
52 |
"max_steps": 957,
|
53 |
"num_train_epochs": 3,
|
54 |
"save_steps": 100,
|
55 |
+
"total_flos": 4.98303246532608e+16,
|
56 |
"trial_name": null,
|
57 |
"trial_params": null
|
58 |
}
|