Training in progress, step 500
Browse files- all_results.json +7 -0
- pytorch_model.bin +1 -1
- runs/Apr19_20-38-27_brutasse/events.out.tfevents.1650401133.brutasse.608.2 +3 -0
- runs/Apr20_07-07-30_brutasse/1650438456.790587/events.out.tfevents.1650438456.brutasse.8400.1 +3 -0
- runs/Apr20_07-07-30_brutasse/events.out.tfevents.1650438456.brutasse.8400.0 +3 -0
- train_results.json +7 -0
- trainer_state.json +31 -0
- training_args.bin +1 -1
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 1.7828999766597042,
|
4 |
+
"train_runtime": 262.2877,
|
5 |
+
"train_samples_per_second": 32.407,
|
6 |
+
"train_steps_per_second": 2.059
|
7 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14963873
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15220a59cf9d0b59a536cc8dd191f40d9943d354c3ea7e7fceeeca7a21b66799
|
3 |
size 14963873
|
runs/Apr19_20-38-27_brutasse/events.out.tfevents.1650401133.brutasse.608.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:703b935bf6bc7875ca7e2e04560773e3b416f6d4fcbfc5cff99f8a32b630e5ec
|
3 |
+
size 5039
|
runs/Apr20_07-07-30_brutasse/1650438456.790587/events.out.tfevents.1650438456.brutasse.8400.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee59be231e304cda6d2d9a6ec657094067bc5e34d3f85f19035ed28db5fb104c
|
3 |
+
size 5031
|
runs/Apr20_07-07-30_brutasse/events.out.tfevents.1650438456.brutasse.8400.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c169acf00ebb18631f1a047190a6fa936ae101f6f89858e545f8a07be2856900
|
3 |
+
size 6016
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 1.7828999766597042,
|
4 |
+
"train_runtime": 262.2877,
|
5 |
+
"train_samples_per_second": 32.407,
|
6 |
+
"train_steps_per_second": 2.059
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 540,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 9.26,
|
12 |
+
"learning_rate": 3.7037037037037037e-06,
|
13 |
+
"loss": 1.8155,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 10.0,
|
18 |
+
"step": 540,
|
19 |
+
"total_flos": 1.49327778152448e+17,
|
20 |
+
"train_loss": 1.7828999766597042,
|
21 |
+
"train_runtime": 262.2877,
|
22 |
+
"train_samples_per_second": 32.407,
|
23 |
+
"train_steps_per_second": 2.059
|
24 |
+
}
|
25 |
+
],
|
26 |
+
"max_steps": 540,
|
27 |
+
"num_train_epochs": 10,
|
28 |
+
"total_flos": 1.49327778152448e+17,
|
29 |
+
"trial_name": null,
|
30 |
+
"trial_params": null
|
31 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3183
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2a654e1acd7b8a239678b453bf5155a59ac4f6b0b6a5c65c0a096ebd2b02549
|
3 |
size 3183
|