Commit
路
1eb1a13
1
Parent(s):
e0f694a
End of training
Browse files- .gitattributes +1 -0
- all_results.json +11 -0
- eval_nbest_predictions.json +3 -0
- eval_predictions.json +0 -0
- eval_results.json +6 -0
- runs/Aug09_16-23-09_58e64a916bd5/events.out.tfevents.1660067587.58e64a916bd5.6121.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +97 -0
.gitattributes
CHANGED
@@ -29,3 +29,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
30 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
29 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
30 |
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
31 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
32 |
+
eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
|
all_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_exact_match": 79.33774834437087,
|
4 |
+
"eval_f1": 87.12191251890178,
|
5 |
+
"eval_samples": 12097,
|
6 |
+
"train_loss": 1.2300268692036653,
|
7 |
+
"train_runtime": 4576.3813,
|
8 |
+
"train_samples": 97408,
|
9 |
+
"train_samples_per_second": 21.285,
|
10 |
+
"train_steps_per_second": 1.33
|
11 |
+
}
|
eval_nbest_predictions.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0ff4aa82b05987f5fc97da148f6608891d99f0e6f3032d5196f81408c2b9329
|
3 |
+
size 49409449
|
eval_predictions.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
eval_results.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_exact_match": 79.33774834437087,
|
4 |
+
"eval_f1": 87.12191251890178,
|
5 |
+
"eval_samples": 12097
|
6 |
+
}
|
runs/Aug09_16-23-09_58e64a916bd5/events.out.tfevents.1660067587.58e64a916bd5.6121.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6c4689ee32794ea1f2dee8fcbfe83584a5b95ffd701f56149de7ce3e637e96a
|
3 |
+
size 191
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 1.2300268692036653,
|
4 |
+
"train_runtime": 4576.3813,
|
5 |
+
"train_samples": 97408,
|
6 |
+
"train_samples_per_second": 21.285,
|
7 |
+
"train_steps_per_second": 1.33
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 6088,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.08,
|
12 |
+
"learning_rate": 2.7536136662286466e-05,
|
13 |
+
"loss": 2.3317,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.16,
|
18 |
+
"learning_rate": 2.5072273324572932e-05,
|
19 |
+
"loss": 1.4294,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.25,
|
24 |
+
"learning_rate": 2.2608409986859398e-05,
|
25 |
+
"loss": 1.3087,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.33,
|
30 |
+
"learning_rate": 2.014454664914586e-05,
|
31 |
+
"loss": 1.2303,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.41,
|
36 |
+
"learning_rate": 1.7680683311432326e-05,
|
37 |
+
"loss": 1.1531,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.49,
|
42 |
+
"learning_rate": 1.5216819973718791e-05,
|
43 |
+
"loss": 1.1192,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.57,
|
48 |
+
"learning_rate": 1.2752956636005257e-05,
|
49 |
+
"loss": 1.0921,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.66,
|
54 |
+
"learning_rate": 1.0289093298291721e-05,
|
55 |
+
"loss": 1.078,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.74,
|
60 |
+
"learning_rate": 7.825229960578187e-06,
|
61 |
+
"loss": 1.043,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.82,
|
66 |
+
"learning_rate": 5.361366622864652e-06,
|
67 |
+
"loss": 0.9911,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.9,
|
72 |
+
"learning_rate": 2.8975032851511168e-06,
|
73 |
+
"loss": 1.006,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.99,
|
78 |
+
"learning_rate": 4.336399474375821e-07,
|
79 |
+
"loss": 1.02,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.0,
|
84 |
+
"step": 6088,
|
85 |
+
"total_flos": 1.2726197240070144e+16,
|
86 |
+
"train_loss": 1.2300268692036653,
|
87 |
+
"train_runtime": 4576.3813,
|
88 |
+
"train_samples_per_second": 21.285,
|
89 |
+
"train_steps_per_second": 1.33
|
90 |
+
}
|
91 |
+
],
|
92 |
+
"max_steps": 6088,
|
93 |
+
"num_train_epochs": 1,
|
94 |
+
"total_flos": 1.2726197240070144e+16,
|
95 |
+
"trial_name": null,
|
96 |
+
"trial_params": null
|
97 |
+
}
|