Training in progress, step 4, 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 150486964
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac94be5a702eee2f14cc221105b3ab133906410af20bbd73640a5c66ab880edb
|
3 |
size 150486964
|
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 sha256:2b62f6eddadd89cd3e9be43881bd6539f70eb520b8e491e1b083e4d1af0b28bf
|
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":
|
5 |
"eval_steps": 1,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -23,6 +23,29 @@
|
|
23 |
"eval_samples_per_second": 35.585,
|
24 |
"eval_steps_per_second": 5.931,
|
25 |
"step": 2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
],
|
28 |
"logging_steps": 3,
|
@@ -42,7 +65,7 @@
|
|
42 |
"attributes": {}
|
43 |
}
|
44 |
},
|
45 |
-
"total_flos":
|
46 |
"train_batch_size": 8,
|
47 |
"trial_name": null,
|
48 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.2307692307692308,
|
5 |
"eval_steps": 1,
|
6 |
+
"global_step": 4,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
23 |
"eval_samples_per_second": 35.585,
|
24 |
"eval_steps_per_second": 5.931,
|
25 |
"step": 2
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.9230769230769231,
|
29 |
+
"grad_norm": NaN,
|
30 |
+
"learning_rate": 3e-05,
|
31 |
+
"loss": 0.0,
|
32 |
+
"step": 3
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.9230769230769231,
|
36 |
+
"eval_loss": NaN,
|
37 |
+
"eval_runtime": 0.1721,
|
38 |
+
"eval_samples_per_second": 34.857,
|
39 |
+
"eval_steps_per_second": 5.809,
|
40 |
+
"step": 3
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 1.2307692307692308,
|
44 |
+
"eval_loss": NaN,
|
45 |
+
"eval_runtime": 0.1687,
|
46 |
+
"eval_samples_per_second": 35.562,
|
47 |
+
"eval_steps_per_second": 5.927,
|
48 |
+
"step": 4
|
49 |
}
|
50 |
],
|
51 |
"logging_steps": 3,
|
|
|
65 |
"attributes": {}
|
66 |
}
|
67 |
},
|
68 |
+
"total_flos": 1046056308572160.0,
|
69 |
"train_batch_size": 8,
|
70 |
"trial_name": null,
|
71 |
"trial_params": null
|