Upload trainer_state.json
Browse files- trainer_state.json +57 -15
trainer_state.json
CHANGED
@@ -2,36 +2,78 @@
|
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 1.0,
|
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": 0.
|
12 |
-
"learning_rate":
|
13 |
-
"loss":
|
14 |
"step": 500
|
15 |
},
|
16 |
{
|
17 |
-
"epoch": 0.
|
18 |
-
"learning_rate":
|
19 |
-
"loss": 1.
|
20 |
"step": 1000
|
21 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
{
|
23 |
"epoch": 1.0,
|
24 |
-
"step":
|
25 |
-
"total_flos":
|
26 |
-
"train_loss": 1.
|
27 |
-
"train_runtime":
|
28 |
-
"train_samples_per_second":
|
29 |
-
"train_steps_per_second":
|
30 |
}
|
31 |
],
|
32 |
-
"max_steps":
|
33 |
"num_train_epochs": 1,
|
34 |
-
"total_flos":
|
35 |
"trial_name": null,
|
36 |
"trial_params": null
|
37 |
}
|
|
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 1.0,
|
5 |
+
"global_step": 4685,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 0.11,
|
12 |
+
"learning_rate": 2.67982924226254e-05,
|
13 |
+
"loss": 2.2761,
|
14 |
"step": 500
|
15 |
},
|
16 |
{
|
17 |
+
"epoch": 0.21,
|
18 |
+
"learning_rate": 2.35965848452508e-05,
|
19 |
+
"loss": 1.6473,
|
20 |
"step": 1000
|
21 |
},
|
22 |
+
{
|
23 |
+
"epoch": 0.32,
|
24 |
+
"learning_rate": 2.0394877267876203e-05,
|
25 |
+
"loss": 1.5402,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.43,
|
30 |
+
"learning_rate": 1.7193169690501603e-05,
|
31 |
+
"loss": 1.4675,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.53,
|
36 |
+
"learning_rate": 1.3991462113127e-05,
|
37 |
+
"loss": 1.4086,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.64,
|
42 |
+
"learning_rate": 1.0789754535752402e-05,
|
43 |
+
"loss": 1.3708,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.75,
|
48 |
+
"learning_rate": 7.588046958377802e-06,
|
49 |
+
"loss": 1.3538,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.85,
|
54 |
+
"learning_rate": 4.386339381003202e-06,
|
55 |
+
"loss": 1.2966,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.96,
|
60 |
+
"learning_rate": 1.1846318036286021e-06,
|
61 |
+
"loss": 1.2822,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
{
|
65 |
"epoch": 1.0,
|
66 |
+
"step": 4685,
|
67 |
+
"total_flos": 1.1016793857503232e+16,
|
68 |
+
"train_loss": 1.5054649426308615,
|
69 |
+
"train_runtime": 2424.9282,
|
70 |
+
"train_samples_per_second": 23.183,
|
71 |
+
"train_steps_per_second": 1.932
|
72 |
}
|
73 |
],
|
74 |
+
"max_steps": 4685,
|
75 |
"num_train_epochs": 1,
|
76 |
+
"total_flos": 1.1016793857503232e+16,
|
77 |
"trial_name": null,
|
78 |
"trial_params": null
|
79 |
}
|