Training in progress, step 4, 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 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e3b2734b3de8b9018d1e489fd085289bc50aa37a9dc2060454879d1630e29ca
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43122580
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc99bb428e07e5daccebeae44d47d8333700e5cdefe2f0f9ec1dce6373577dbf
|
3 |
size 43122580
|
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 sha256:5063e42d33236efce97a1743e854e894f2a2c7cac2e300112055d90419bf6d8f
|
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:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
|
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": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -29,6 +29,28 @@
|
|
29 |
"learning_rate": 2e-05,
|
30 |
"loss": 4.2225,
|
31 |
"step": 2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|
33 |
],
|
34 |
"logging_steps": 1,
|
@@ -48,7 +70,7 @@
|
|
48 |
"attributes": {}
|
49 |
}
|
50 |
},
|
51 |
-
"total_flos":
|
52 |
"train_batch_size": 1,
|
53 |
"trial_name": null,
|
54 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0004694525742872023,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 4,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
29 |
"learning_rate": 2e-05,
|
30 |
"loss": 4.2225,
|
31 |
"step": 2
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.0003520894307154017,
|
35 |
+
"grad_norm": 1.3053418397903442,
|
36 |
+
"learning_rate": 3e-05,
|
37 |
+
"loss": 2.4203,
|
38 |
+
"step": 3
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.0003520894307154017,
|
42 |
+
"eval_loss": 3.2794156074523926,
|
43 |
+
"eval_runtime": 1578.0902,
|
44 |
+
"eval_samples_per_second": 4.547,
|
45 |
+
"eval_steps_per_second": 4.547,
|
46 |
+
"step": 3
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.0004694525742872023,
|
50 |
+
"grad_norm": 1.3151017427444458,
|
51 |
+
"learning_rate": 4e-05,
|
52 |
+
"loss": 2.5524,
|
53 |
+
"step": 4
|
54 |
}
|
55 |
],
|
56 |
"logging_steps": 1,
|
|
|
70 |
"attributes": {}
|
71 |
}
|
72 |
},
|
73 |
+
"total_flos": 1502770951618560.0,
|
74 |
"train_batch_size": 1,
|
75 |
"trial_name": null,
|
76 |
"trial_params": null
|