Training in progress, step 180, 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:f0d03dc2c5080519825972e024b38e999449f23530ed4f0fe0c47652870a49d4
|
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 sha256:4703465e446a43e848f0d3d3a1dfacf4bf2f20c48f43bf4aab69c92e56d3537c
|
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:fcc7c896cfcbe08cf8fdf20e5c7a45cbdf6bc54356887b87f152567644d8dee4
|
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 sha256:9215b3b637190dcb854b6b9d07a42848f1add2f44ebb6ff93fdde96621dce483
|
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": 60,
|
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": 1.915,
|
34 |
"eval_steps_per_second": 0.239,
|
35 |
"step": 120
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
}
|
37 |
],
|
38 |
"logging_steps": 60,
|
39 |
"max_steps": 1011,
|
40 |
"num_train_epochs": 3,
|
41 |
"save_steps": 60,
|
42 |
-
"total_flos":
|
43 |
"trial_name": null,
|
44 |
"trial_params": null
|
45 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5333333333333333,
|
5 |
"eval_steps": 60,
|
6 |
+
"global_step": 180,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
33 |
"eval_samples_per_second": 1.915,
|
34 |
"eval_steps_per_second": 0.239,
|
35 |
"step": 120
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 0.53,
|
39 |
+
"learning_rate": 0.0002,
|
40 |
+
"loss": 0.6332,
|
41 |
+
"step": 180
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.53,
|
45 |
+
"eval_runtime": 313.7062,
|
46 |
+
"eval_samples_per_second": 1.913,
|
47 |
+
"eval_steps_per_second": 0.239,
|
48 |
+
"step": 180
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 60,
|
52 |
"max_steps": 1011,
|
53 |
"num_train_epochs": 3,
|
54 |
"save_steps": 60,
|
55 |
+
"total_flos": 2.989819479195648e+16,
|
56 |
"trial_name": null,
|
57 |
"trial_params": null
|
58 |
}
|