Upload 10 files
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +18 -3
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"train_loss": 1.7669375141701935,
|
4 |
+
"train_runtime": 10839.0571,
|
5 |
+
"train_samples": 9919,
|
6 |
+
"train_samples_per_second": 1.83,
|
7 |
+
"train_steps_per_second": 0.153
|
8 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1109883945
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8eaf58b36afa42bb977bf998a3929cb165d0a9f38d467d84c9710c16a19b199
|
3 |
size 1109883945
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"train_loss": 1.7669375141701935,
|
4 |
+
"train_runtime": 10839.0571,
|
5 |
+
"train_samples": 9919,
|
6 |
+
"train_samples_per_second": 1.83,
|
7 |
+
"train_steps_per_second": 0.153
|
8 |
+
}
|
trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
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,
|
@@ -19,13 +19,28 @@
|
|
19 |
"learning_rate": 1.1862152357920194e-05,
|
20 |
"loss": 1.7773,
|
21 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
}
|
23 |
],
|
24 |
"logging_steps": 500,
|
25 |
"max_steps": 1654,
|
26 |
"num_train_epochs": 2,
|
27 |
"save_steps": 500,
|
28 |
-
"total_flos":
|
29 |
"trial_name": null,
|
30 |
"trial_params": null
|
31 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1654,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
19 |
"learning_rate": 1.1862152357920194e-05,
|
20 |
"loss": 1.7773,
|
21 |
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.81,
|
25 |
+
"learning_rate": 2.7932285368802904e-06,
|
26 |
+
"loss": 1.4845,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.0,
|
31 |
+
"step": 1654,
|
32 |
+
"total_flos": 3887703795096576.0,
|
33 |
+
"train_loss": 1.7669375141701935,
|
34 |
+
"train_runtime": 10839.0571,
|
35 |
+
"train_samples_per_second": 1.83,
|
36 |
+
"train_steps_per_second": 0.153
|
37 |
}
|
38 |
],
|
39 |
"logging_steps": 500,
|
40 |
"max_steps": 1654,
|
41 |
"num_train_epochs": 2,
|
42 |
"save_steps": 500,
|
43 |
+
"total_flos": 3887703795096576.0,
|
44 |
"trial_name": null,
|
45 |
"trial_params": null
|
46 |
}
|