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 19859140
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9afb5cbb9b1d607a432e6531275e6be72bcdab2f951cb6afc7be3daedad4fe72
|
3 |
size 19859140
|
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 sha256:5e6627bb3a9d2b253070f7ee775093053ef501dfa0768b70d6a195c5b4ea5c1d
|
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,
|
@@ -31,6 +31,14 @@
|
|
31 |
"eval_samples_per_second": 19.752,
|
32 |
"eval_steps_per_second": 9.876,
|
33 |
"step": 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
}
|
35 |
],
|
36 |
"logging_steps": 5,
|
@@ -45,12 +53,12 @@
|
|
45 |
"should_evaluate": false,
|
46 |
"should_log": false,
|
47 |
"should_save": true,
|
48 |
-
"should_training_stop":
|
49 |
},
|
50 |
"attributes": {}
|
51 |
}
|
52 |
},
|
53 |
-
"total_flos":
|
54 |
"train_batch_size": 2,
|
55 |
"trial_name": null,
|
56 |
"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,
|
|
|
31 |
"eval_samples_per_second": 19.752,
|
32 |
"eval_steps_per_second": 9.876,
|
33 |
"step": 3
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.2307692307692308,
|
37 |
+
"eval_loss": NaN,
|
38 |
+
"eval_runtime": 0.1006,
|
39 |
+
"eval_samples_per_second": 19.871,
|
40 |
+
"eval_steps_per_second": 9.936,
|
41 |
+
"step": 4
|
42 |
}
|
43 |
],
|
44 |
"logging_steps": 5,
|
|
|
53 |
"should_evaluate": false,
|
54 |
"should_log": false,
|
55 |
"should_save": true,
|
56 |
+
"should_training_stop": true
|
57 |
},
|
58 |
"attributes": {}
|
59 |
}
|
60 |
},
|
61 |
+
"total_flos": 125665575174144.0,
|
62 |
"train_batch_size": 2,
|
63 |
"trial_name": null,
|
64 |
"trial_params": null
|