anas-awadalla
commited on
Commit
•
b390c67
1
Parent(s):
9d625f6
End of training
Browse files- all_results.json +11 -0
- eval_results.json +6 -0
- runs/Oct08_14-24-40_g3076/events.out.tfevents.1665265356.g3076.14352.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +73 -0
all_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 35.0,
|
3 |
+
"eval_exact_match": 75.37369914853359,
|
4 |
+
"eval_f1": 85.15686632663389,
|
5 |
+
"eval_samples": 10570,
|
6 |
+
"train_loss": 0.9091585227421352,
|
7 |
+
"train_runtime": 611.6069,
|
8 |
+
"train_samples": 512,
|
9 |
+
"train_samples_per_second": 29.3,
|
10 |
+
"train_steps_per_second": 7.325
|
11 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 35.0,
|
3 |
+
"eval_exact_match": 75.37369914853359,
|
4 |
+
"eval_f1": 85.15686632663389,
|
5 |
+
"eval_samples": 10570
|
6 |
+
}
|
runs/Oct08_14-24-40_g3076/events.out.tfevents.1665265356.g3076.14352.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78ed2363d4799237ed77686ab4f91826eed547654906d2ac634df40df58ea913
|
3 |
+
size 191
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 35.0,
|
3 |
+
"train_loss": 0.9091585227421352,
|
4 |
+
"train_runtime": 611.6069,
|
5 |
+
"train_samples": 512,
|
6 |
+
"train_samples_per_second": 29.3,
|
7 |
+
"train_steps_per_second": 7.325
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 35.0,
|
5 |
+
"global_step": 4480,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 3.91,
|
12 |
+
"learning_rate": 1.7767857142857143e-05,
|
13 |
+
"loss": 3.4911,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 7.81,
|
18 |
+
"learning_rate": 1.553571428571429e-05,
|
19 |
+
"loss": 1.1908,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 11.72,
|
24 |
+
"learning_rate": 1.3303571428571429e-05,
|
25 |
+
"loss": 0.8102,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 15.62,
|
30 |
+
"learning_rate": 1.1071428571428572e-05,
|
31 |
+
"loss": 0.632,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 19.53,
|
36 |
+
"learning_rate": 8.839285714285714e-06,
|
37 |
+
"loss": 0.508,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 23.44,
|
42 |
+
"learning_rate": 6.607142857142858e-06,
|
43 |
+
"loss": 0.4371,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 27.34,
|
48 |
+
"learning_rate": 4.3750000000000005e-06,
|
49 |
+
"loss": 0.3877,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 31.25,
|
54 |
+
"learning_rate": 2.1428571428571427e-06,
|
55 |
+
"loss": 0.3677,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 35.0,
|
60 |
+
"step": 4480,
|
61 |
+
"total_flos": 6656119413719040.0,
|
62 |
+
"train_loss": 0.9091585227421352,
|
63 |
+
"train_runtime": 611.6069,
|
64 |
+
"train_samples_per_second": 29.3,
|
65 |
+
"train_steps_per_second": 7.325
|
66 |
+
}
|
67 |
+
],
|
68 |
+
"max_steps": 4480,
|
69 |
+
"num_train_epochs": 35,
|
70 |
+
"total_flos": 6656119413719040.0,
|
71 |
+
"trial_name": null,
|
72 |
+
"trial_params": null
|
73 |
+
}
|