Training in progress, step 300, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 160285149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c379412e43b828c4f834738bf3859e9b72cd4483da794f92ccc258e1da4ba76
|
3 |
size 160285149
|
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 sha256:37f266dce13902dcd132a0f2e952191cdba75f4d6424635380e0dcb339856fe0
|
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 sha256:60deaf5bce1420ec9463a4509f65e88e0a5a4f9976041c81ec5379366458be94
|
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": 1.903,
|
34 |
"eval_steps_per_second": 0.239,
|
35 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
}
|
37 |
],
|
38 |
"logging_steps": 100,
|
39 |
"max_steps": 2025,
|
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": 0.4444444444444444,
|
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": 1.903,
|
34 |
"eval_steps_per_second": 0.239,
|
35 |
"step": 200
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 0.44,
|
39 |
+
"learning_rate": 0.0,
|
40 |
+
"loss": 8.4751,
|
41 |
+
"step": 300
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.44,
|
45 |
+
"eval_runtime": 787.7273,
|
46 |
+
"eval_samples_per_second": 1.904,
|
47 |
+
"eval_steps_per_second": 0.239,
|
48 |
+
"step": 300
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 100,
|
52 |
"max_steps": 2025,
|
53 |
"num_train_epochs": 3,
|
54 |
"save_steps": 100,
|
55 |
+
"total_flos": 6.2472119648256e+16,
|
56 |
"trial_name": null,
|
57 |
"trial_params": null
|
58 |
}
|