Commit
•
0b94e11
1
Parent(s):
c35a24f
End of training
Browse files- all_results.json +11 -11
- eval_results.json +7 -6
- train_results.json +5 -5
- trainer_state.json +21 -21
all_results.json
CHANGED
@@ -1,15 +1,15 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss":
|
5 |
-
"eval_runtime":
|
6 |
"eval_samples": 100,
|
7 |
-
"eval_samples_per_second":
|
8 |
-
"eval_steps_per_second":
|
9 |
-
"perplexity":
|
10 |
-
"train_loss": 1.
|
11 |
-
"train_runtime":
|
12 |
"train_samples": 1000,
|
13 |
-
"train_samples_per_second":
|
14 |
-
"train_steps_per_second":
|
15 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.99,
|
3 |
+
"eval_accuracy": 0.08528455284552845,
|
4 |
+
"eval_loss": 0.20656633377075195,
|
5 |
+
"eval_runtime": 2.0736,
|
6 |
"eval_samples": 100,
|
7 |
+
"eval_samples_per_second": 48.225,
|
8 |
+
"eval_steps_per_second": 1.929,
|
9 |
+
"perplexity": 1.2294492855192867,
|
10 |
+
"train_loss": 1.0375519144919612,
|
11 |
+
"train_runtime": 119.5105,
|
12 |
"train_samples": 1000,
|
13 |
+
"train_samples_per_second": 8.367,
|
14 |
+
"train_steps_per_second": 0.259
|
15 |
}
|
eval_results.json
CHANGED
@@ -1,9 +1,10 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
|
|
5 |
"eval_samples": 100,
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second":
|
8 |
-
"perplexity":
|
9 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.99,
|
3 |
+
"eval_accuracy": 0.08528455284552845,
|
4 |
+
"eval_loss": 0.20656633377075195,
|
5 |
+
"eval_runtime": 2.0736,
|
6 |
"eval_samples": 100,
|
7 |
+
"eval_samples_per_second": 48.225,
|
8 |
+
"eval_steps_per_second": 1.929,
|
9 |
+
"perplexity": 1.2294492855192867
|
10 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 1000,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.99,
|
3 |
+
"train_loss": 1.0375519144919612,
|
4 |
+
"train_runtime": 119.5105,
|
5 |
"train_samples": 1000,
|
6 |
+
"train_samples_per_second": 8.367,
|
7 |
+
"train_steps_per_second": 0.259
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -10,37 +10,37 @@
|
|
10 |
{
|
11 |
"epoch": 0.03,
|
12 |
"learning_rate": 5e-05,
|
13 |
-
"loss": 13.
|
14 |
"step": 1
|
15 |
},
|
16 |
{
|
17 |
-
"epoch": 0.
|
18 |
-
"learning_rate": 1.
|
19 |
-
"loss":
|
20 |
"step": 25
|
21 |
},
|
22 |
{
|
23 |
-
"epoch": 0.
|
24 |
-
"eval_accuracy": 0.
|
25 |
-
"eval_loss": 0.
|
26 |
-
"eval_runtime": 1.
|
27 |
-
"eval_samples_per_second": 52.
|
28 |
-
"eval_steps_per_second": 2.
|
29 |
"step": 25
|
30 |
},
|
31 |
{
|
32 |
-
"epoch":
|
33 |
-
"step":
|
34 |
-
"total_flos":
|
35 |
-
"train_loss": 1.
|
36 |
-
"train_runtime":
|
37 |
-
"train_samples_per_second":
|
38 |
-
"train_steps_per_second":
|
39 |
}
|
40 |
],
|
41 |
-
"max_steps":
|
42 |
"num_train_epochs": 1,
|
43 |
-
"total_flos":
|
44 |
"trial_name": null,
|
45 |
"trial_params": null
|
46 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.992,
|
5 |
+
"global_step": 31,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
10 |
{
|
11 |
"epoch": 0.03,
|
12 |
"learning_rate": 5e-05,
|
13 |
+
"loss": 13.7576,
|
14 |
"step": 1
|
15 |
},
|
16 |
{
|
17 |
+
"epoch": 0.8,
|
18 |
+
"learning_rate": 1.129032258064516e-05,
|
19 |
+
"loss": 0.761,
|
20 |
"step": 25
|
21 |
},
|
22 |
{
|
23 |
+
"epoch": 0.8,
|
24 |
+
"eval_accuracy": 0.0851829268292683,
|
25 |
+
"eval_loss": 0.21037571132183075,
|
26 |
+
"eval_runtime": 1.8873,
|
27 |
+
"eval_samples_per_second": 52.986,
|
28 |
+
"eval_steps_per_second": 2.119,
|
29 |
"step": 25
|
30 |
},
|
31 |
{
|
32 |
+
"epoch": 0.99,
|
33 |
+
"step": 31,
|
34 |
+
"total_flos": 938904995758080.0,
|
35 |
+
"train_loss": 1.0375519144919612,
|
36 |
+
"train_runtime": 119.5105,
|
37 |
+
"train_samples_per_second": 8.367,
|
38 |
+
"train_steps_per_second": 0.259
|
39 |
}
|
40 |
],
|
41 |
+
"max_steps": 31,
|
42 |
"num_train_epochs": 1,
|
43 |
+
"total_flos": 938904995758080.0,
|
44 |
"trial_name": null,
|
45 |
"trial_params": null
|
46 |
}
|