Upload trainer_state.json
Browse files- trainer_state.json +87 -0
trainer_state.json
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 880,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.45,
|
12 |
+
"eval_HasAns_exact": 43.43891402714932,
|
13 |
+
"eval_HasAns_f1": 69.1661607072733,
|
14 |
+
"eval_HasAns_total": 221,
|
15 |
+
"eval_best_exact": 43.43891402714932,
|
16 |
+
"eval_best_exact_thresh": 0.0,
|
17 |
+
"eval_best_f1": 69.1661607072733,
|
18 |
+
"eval_best_f1_thresh": 0.0,
|
19 |
+
"eval_exact": 43.43891402714932,
|
20 |
+
"eval_f1": 69.1661607072733,
|
21 |
+
"eval_total": 221,
|
22 |
+
"step": 200
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 0.91,
|
26 |
+
"eval_HasAns_exact": 49.321266968325794,
|
27 |
+
"eval_HasAns_f1": 70.42596830206043,
|
28 |
+
"eval_HasAns_total": 221,
|
29 |
+
"eval_best_exact": 49.321266968325794,
|
30 |
+
"eval_best_exact_thresh": 0.0,
|
31 |
+
"eval_best_f1": 70.42596830206043,
|
32 |
+
"eval_best_f1_thresh": 0.0,
|
33 |
+
"eval_exact": 49.321266968325794,
|
34 |
+
"eval_f1": 70.42596830206043,
|
35 |
+
"eval_total": 221,
|
36 |
+
"step": 400
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 1.14,
|
40 |
+
"learning_rate": 1.0795454545454547e-05,
|
41 |
+
"loss": 0.8745,
|
42 |
+
"step": 500
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 1.36,
|
46 |
+
"eval_HasAns_exact": 45.70135746606335,
|
47 |
+
"eval_HasAns_f1": 67.08475754056293,
|
48 |
+
"eval_HasAns_total": 221,
|
49 |
+
"eval_best_exact": 45.70135746606335,
|
50 |
+
"eval_best_exact_thresh": 0.0,
|
51 |
+
"eval_best_f1": 67.08475754056293,
|
52 |
+
"eval_best_f1_thresh": 0.0,
|
53 |
+
"eval_exact": 45.70135746606335,
|
54 |
+
"eval_f1": 67.08475754056293,
|
55 |
+
"eval_total": 221,
|
56 |
+
"step": 600
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.82,
|
60 |
+
"eval_HasAns_exact": 45.248868778280546,
|
61 |
+
"eval_HasAns_f1": 67.36800189264167,
|
62 |
+
"eval_HasAns_total": 221,
|
63 |
+
"eval_best_exact": 45.248868778280546,
|
64 |
+
"eval_best_exact_thresh": 0.0,
|
65 |
+
"eval_best_f1": 67.36800189264167,
|
66 |
+
"eval_best_f1_thresh": 0.0,
|
67 |
+
"eval_exact": 45.248868778280546,
|
68 |
+
"eval_f1": 67.36800189264167,
|
69 |
+
"eval_total": 221,
|
70 |
+
"step": 800
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 2.0,
|
74 |
+
"step": 880,
|
75 |
+
"total_flos": 1378079095025664.0,
|
76 |
+
"train_loss": 0.7235306653109463,
|
77 |
+
"train_runtime": 418.985,
|
78 |
+
"train_samples_per_second": 16.783,
|
79 |
+
"train_steps_per_second": 2.1
|
80 |
+
}
|
81 |
+
],
|
82 |
+
"max_steps": 880,
|
83 |
+
"num_train_epochs": 2,
|
84 |
+
"total_flos": 1378079095025664.0,
|
85 |
+
"trial_name": null,
|
86 |
+
"trial_params": null
|
87 |
+
}
|