Commit
·
7468a6b
1
Parent(s):
5486ed1
Training in progress, step 1500, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1625426996
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed82d2d3fd3dca5c56db6bb6f389e1c264d8a4f733329c457b26cad0f1e94eae
|
3 |
size 1625426996
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3250745679
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a7e90b7d7b76bcf81f764ef2452898faaea25b5d7e461d45a1464ec3fc0923c
|
3 |
size 3250745679
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13990
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef1b6ee4749d1a3d9805190b4dc5cb543f0ffb0a14d498a79d69fe68014a6896
|
3 |
size 13990
|
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 sha256:04f172f01cb77e8d14118289d685eb7f697a2a376c73318b03a86d16e22b22dd
|
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": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -35,13 +35,27 @@
|
|
35 |
"eval_samples_per_second": 0.198,
|
36 |
"eval_steps_per_second": 0.049,
|
37 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
}
|
39 |
],
|
40 |
"logging_steps": 500,
|
41 |
"max_steps": 6000,
|
42 |
"num_train_epochs": 3,
|
43 |
"save_steps": 500,
|
44 |
-
"total_flos":
|
45 |
"trial_name": null,
|
46 |
"trial_params": null
|
47 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.75,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
35 |
"eval_samples_per_second": 0.198,
|
36 |
"eval_steps_per_second": 0.049,
|
37 |
"step": 1000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.75,
|
41 |
+
"learning_rate": 3.756260434056762e-05,
|
42 |
+
"loss": 0.1096,
|
43 |
+
"step": 1500
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 0.75,
|
47 |
+
"eval_loss": 0.041419126093387604,
|
48 |
+
"eval_runtime": 2505.8009,
|
49 |
+
"eval_samples_per_second": 0.2,
|
50 |
+
"eval_steps_per_second": 0.05,
|
51 |
+
"step": 1500
|
52 |
}
|
53 |
],
|
54 |
"logging_steps": 500,
|
55 |
"max_steps": 6000,
|
56 |
"num_train_epochs": 3,
|
57 |
"save_steps": 500,
|
58 |
+
"total_flos": 6501313806336000.0,
|
59 |
"trial_name": null,
|
60 |
"trial_params": null
|
61 |
}
|