Training in progress, step 50, checkpoint
Browse files
last-checkpoint/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 109098378
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c2788e275ff2fdbfec012ac7fb8eafac091166de57508ee4416b9718122b093
|
3 |
size 109098378
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 218182458
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:823b4e4029fd13474140170c0acdd875c9e17032fb391afea7ce793b1623ae13
|
3 |
size 218182458
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1e4342dc5be99a549a981dd65556fed85d338ccd355122fefa870d54060017c
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d97348f8f3f5f96f2cacef5e1a65c040f53a19642348f1f05fea5ba1b9158e9
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -11,69 +11,21 @@
|
|
11 |
{
|
12 |
"epoch": 0.13,
|
13 |
"learning_rate": 0.0001975746552556772,
|
14 |
-
"loss": 0.
|
15 |
"step": 25
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.26,
|
19 |
"learning_rate": 0.00018550053929480202,
|
20 |
-
"loss": 0.
|
21 |
"step": 50
|
22 |
-
},
|
23 |
-
{
|
24 |
-
"epoch": 0.39,
|
25 |
-
"learning_rate": 0.00016449948488669639,
|
26 |
-
"loss": 0.6045,
|
27 |
-
"step": 75
|
28 |
-
},
|
29 |
-
{
|
30 |
-
"epoch": 0.52,
|
31 |
-
"learning_rate": 0.000136764169663272,
|
32 |
-
"loss": 0.5813,
|
33 |
-
"step": 100
|
34 |
-
},
|
35 |
-
{
|
36 |
-
"epoch": 0.65,
|
37 |
-
"learning_rate": 0.00010519038181318999,
|
38 |
-
"loss": 0.5774,
|
39 |
-
"step": 125
|
40 |
-
},
|
41 |
-
{
|
42 |
-
"epoch": 0.78,
|
43 |
-
"learning_rate": 7.307467669163655e-05,
|
44 |
-
"loss": 0.5623,
|
45 |
-
"step": 150
|
46 |
-
},
|
47 |
-
{
|
48 |
-
"epoch": 0.91,
|
49 |
-
"learning_rate": 4.377019014049223e-05,
|
50 |
-
"loss": 0.5581,
|
51 |
-
"step": 175
|
52 |
-
},
|
53 |
-
{
|
54 |
-
"epoch": 1.04,
|
55 |
-
"learning_rate": 2.03365443542764e-05,
|
56 |
-
"loss": 0.5384,
|
57 |
-
"step": 200
|
58 |
-
},
|
59 |
-
{
|
60 |
-
"epoch": 1.17,
|
61 |
-
"learning_rate": 5.22039891260262e-06,
|
62 |
-
"loss": 0.537,
|
63 |
-
"step": 225
|
64 |
-
},
|
65 |
-
{
|
66 |
-
"epoch": 1.3,
|
67 |
-
"learning_rate": 0.0,
|
68 |
-
"loss": 0.4969,
|
69 |
-
"step": 250
|
70 |
}
|
71 |
],
|
72 |
"logging_steps": 25,
|
73 |
"max_steps": 250,
|
74 |
"num_train_epochs": 2,
|
75 |
"save_steps": 50,
|
76 |
-
"total_flos":
|
77 |
"trial_name": null,
|
78 |
"trial_params": null
|
79 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2604166666666667,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
11 |
{
|
12 |
"epoch": 0.13,
|
13 |
"learning_rate": 0.0001975746552556772,
|
14 |
+
"loss": 0.8825,
|
15 |
"step": 25
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.26,
|
19 |
"learning_rate": 0.00018550053929480202,
|
20 |
+
"loss": 0.6524,
|
21 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
}
|
23 |
],
|
24 |
"logging_steps": 25,
|
25 |
"max_steps": 250,
|
26 |
"num_train_epochs": 2,
|
27 |
"save_steps": 50,
|
28 |
+
"total_flos": 2825629156638720.0,
|
29 |
"trial_name": null,
|
30 |
"trial_params": null
|
31 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:642f80b637a5515fcc8833439eb2a37a5ee487f5a6d30b6350fd317f616d97f3
|
3 |
size 4536
|