Einmalumdiewelt
commited on
Commit
·
a8e0004
1
Parent(s):
54bf6b5
End of training
Browse files- all_results.json +15 -15
- eval_results.json +10 -10
- train_results.json +5 -5
- trainer_state.json +39 -9
all_results.json
CHANGED
@@ -1,18 +1,18 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
-
"eval_gen_len":
|
4 |
-
"eval_loss": 2.
|
5 |
-
"eval_rouge1":
|
6 |
-
"eval_rouge2": 7.
|
7 |
-
"eval_rougeL": 18.
|
8 |
-
"eval_rougeLsum":
|
9 |
-
"eval_runtime":
|
10 |
-
"eval_samples":
|
11 |
-
"eval_samples_per_second":
|
12 |
-
"eval_steps_per_second": 0.
|
13 |
-
"train_loss": 2.
|
14 |
-
"train_runtime":
|
15 |
-
"train_samples":
|
16 |
-
"train_samples_per_second":
|
17 |
-
"train_steps_per_second": 0.
|
18 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"eval_gen_len": 55.018,
|
4 |
+
"eval_loss": 2.2143824100494385,
|
5 |
+
"eval_rouge1": 26.012,
|
6 |
+
"eval_rouge2": 7.0961,
|
7 |
+
"eval_rougeL": 18.1094,
|
8 |
+
"eval_rougeLsum": 22.507,
|
9 |
+
"eval_runtime": 560.2144,
|
10 |
+
"eval_samples": 1500,
|
11 |
+
"eval_samples_per_second": 2.678,
|
12 |
+
"eval_steps_per_second": 0.669,
|
13 |
+
"train_loss": 2.4165630696614584,
|
14 |
+
"train_runtime": 3505.1584,
|
15 |
+
"train_samples": 7000,
|
16 |
+
"train_samples_per_second": 5.991,
|
17 |
+
"train_steps_per_second": 0.749
|
18 |
}
|
eval_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
-
"eval_gen_len":
|
4 |
-
"eval_loss": 2.
|
5 |
-
"eval_rouge1":
|
6 |
-
"eval_rouge2": 7.
|
7 |
-
"eval_rougeL": 18.
|
8 |
-
"eval_rougeLsum":
|
9 |
-
"eval_runtime":
|
10 |
-
"eval_samples":
|
11 |
-
"eval_samples_per_second":
|
12 |
-
"eval_steps_per_second": 0.
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"eval_gen_len": 55.018,
|
4 |
+
"eval_loss": 2.2143824100494385,
|
5 |
+
"eval_rouge1": 26.012,
|
6 |
+
"eval_rouge2": 7.0961,
|
7 |
+
"eval_rougeL": 18.1094,
|
8 |
+
"eval_rougeLsum": 22.507,
|
9 |
+
"eval_runtime": 560.2144,
|
10 |
+
"eval_samples": 1500,
|
11 |
+
"eval_samples_per_second": 2.678,
|
12 |
+
"eval_steps_per_second": 0.669
|
13 |
}
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
-
"train_loss": 2.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 3.0,
|
3 |
+
"train_loss": 2.4165630696614584,
|
4 |
+
"train_runtime": 3505.1584,
|
5 |
+
"train_samples": 7000,
|
6 |
+
"train_samples_per_second": 5.991,
|
7 |
+
"train_steps_per_second": 0.749
|
8 |
}
|
trainer_state.json
CHANGED
@@ -2,24 +2,54 @@
|
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 3.0,
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
{
|
11 |
"epoch": 3.0,
|
12 |
-
"step":
|
13 |
-
"total_flos":
|
14 |
-
"train_loss": 2.
|
15 |
-
"train_runtime":
|
16 |
-
"train_samples_per_second":
|
17 |
-
"train_steps_per_second": 0.
|
18 |
}
|
19 |
],
|
20 |
-
"max_steps":
|
21 |
"num_train_epochs": 3,
|
22 |
-
"total_flos":
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|
|
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 3.0,
|
5 |
+
"global_step": 2625,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.57,
|
12 |
+
"learning_rate": 4.047619047619048e-05,
|
13 |
+
"loss": 2.5903,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.14,
|
18 |
+
"learning_rate": 3.095238095238095e-05,
|
19 |
+
"loss": 2.489,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.71,
|
24 |
+
"learning_rate": 2.1428571428571428e-05,
|
25 |
+
"loss": 2.3848,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 2.29,
|
30 |
+
"learning_rate": 1.1904761904761905e-05,
|
31 |
+
"loss": 2.3436,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.86,
|
36 |
+
"learning_rate": 2.3809523809523808e-06,
|
37 |
+
"loss": 2.3011,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
{
|
41 |
"epoch": 3.0,
|
42 |
+
"step": 2625,
|
43 |
+
"total_flos": 1.278595580424192e+16,
|
44 |
+
"train_loss": 2.4165630696614584,
|
45 |
+
"train_runtime": 3505.1584,
|
46 |
+
"train_samples_per_second": 5.991,
|
47 |
+
"train_steps_per_second": 0.749
|
48 |
}
|
49 |
],
|
50 |
+
"max_steps": 2625,
|
51 |
"num_train_epochs": 3,
|
52 |
+
"total_flos": 1.278595580424192e+16,
|
53 |
"trial_name": null,
|
54 |
"trial_params": null
|
55 |
}
|