End of training
Browse files
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.08333333333333333,
|
4 |
+
"eval_f1": 0.02227891156462585,
|
5 |
+
"eval_loss": 2.630253553390503,
|
6 |
+
"eval_runtime": 6.5623,
|
7 |
+
"eval_samples_per_second": 16.458,
|
8 |
+
"eval_steps_per_second": 1.067,
|
9 |
+
"predict_samples": 108,
|
10 |
+
"train_loss": 2.6225359439849854,
|
11 |
+
"train_runtime": 96.9726,
|
12 |
+
"train_samples": 318,
|
13 |
+
"train_samples_per_second": 9.838,
|
14 |
+
"train_steps_per_second": 0.155
|
15 |
+
}
|
predict_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.08333333333333333,
|
4 |
+
"eval_f1": 0.02227891156462585,
|
5 |
+
"eval_loss": 2.630253553390503,
|
6 |
+
"eval_runtime": 6.5623,
|
7 |
+
"eval_samples_per_second": 16.458,
|
8 |
+
"eval_steps_per_second": 1.067,
|
9 |
+
"predict_samples": 108
|
10 |
+
}
|
runs/Mar16_12-48-31_hf-paris-dgx-station-1/events.out.tfevents.1647431529.hf-paris-dgx-station-1.3958129.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a93f82ae4b3a53edcaf52b96cc81bc0fc394b9b3cf8c1f03403a5f404e3af539
|
3 |
+
size 402
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 2.6225359439849854,
|
4 |
+
"train_runtime": 96.9726,
|
5 |
+
"train_samples": 318,
|
6 |
+
"train_samples_per_second": 9.838,
|
7 |
+
"train_steps_per_second": 0.155
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 15,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.2,
|
12 |
+
"learning_rate": 0.0003,
|
13 |
+
"loss": 2.6389,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.4,
|
18 |
+
"learning_rate": 0.00027857142857142854,
|
19 |
+
"loss": 2.6419,
|
20 |
+
"step": 2
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.6,
|
24 |
+
"learning_rate": 0.0002571428571428571,
|
25 |
+
"loss": 2.6501,
|
26 |
+
"step": 3
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.8,
|
30 |
+
"learning_rate": 0.00023571428571428569,
|
31 |
+
"loss": 2.6429,
|
32 |
+
"step": 4
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.0,
|
36 |
+
"learning_rate": 0.00021428571428571427,
|
37 |
+
"loss": 2.6434,
|
38 |
+
"step": 5
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 1.2,
|
42 |
+
"learning_rate": 0.00019285714285714286,
|
43 |
+
"loss": 2.6262,
|
44 |
+
"step": 6
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.4,
|
48 |
+
"learning_rate": 0.0001714285714285714,
|
49 |
+
"loss": 2.6372,
|
50 |
+
"step": 7
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 1.6,
|
54 |
+
"learning_rate": 0.00015,
|
55 |
+
"loss": 2.6339,
|
56 |
+
"step": 8
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 1.8,
|
60 |
+
"learning_rate": 0.00012857142857142855,
|
61 |
+
"loss": 2.6276,
|
62 |
+
"step": 9
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 2.0,
|
66 |
+
"learning_rate": 0.00010714285714285714,
|
67 |
+
"loss": 2.5977,
|
68 |
+
"step": 10
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 2.2,
|
72 |
+
"learning_rate": 8.57142857142857e-05,
|
73 |
+
"loss": 2.6049,
|
74 |
+
"step": 11
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 2.4,
|
78 |
+
"learning_rate": 6.428571428571427e-05,
|
79 |
+
"loss": 2.6189,
|
80 |
+
"step": 12
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 2.6,
|
84 |
+
"learning_rate": 4.285714285714285e-05,
|
85 |
+
"loss": 2.6324,
|
86 |
+
"step": 13
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.8,
|
90 |
+
"learning_rate": 2.1428571428571425e-05,
|
91 |
+
"loss": 2.564,
|
92 |
+
"step": 14
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 3.0,
|
96 |
+
"learning_rate": 0.0,
|
97 |
+
"loss": 2.5782,
|
98 |
+
"step": 15
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 3.0,
|
102 |
+
"step": 15,
|
103 |
+
"total_flos": 5.963598898365727e+17,
|
104 |
+
"train_loss": 2.6225359439849854,
|
105 |
+
"train_runtime": 96.9726,
|
106 |
+
"train_samples_per_second": 9.838,
|
107 |
+
"train_steps_per_second": 0.155
|
108 |
+
}
|
109 |
+
],
|
110 |
+
"max_steps": 15,
|
111 |
+
"num_train_epochs": 3,
|
112 |
+
"total_flos": 5.963598898365727e+17,
|
113 |
+
"trial_name": null,
|
114 |
+
"trial_params": null
|
115 |
+
}
|