Model save
Browse files- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- all_results.json +7 -7
- eval_results.json +4 -4
- runs/Dec13_00-46-21_beta-a100-3-do-not-terminate/events.out.tfevents.1702428403.beta-a100-3-do-not-terminate.217104.0 +3 -0
- runs/Dec13_00-46-21_beta-a100-3-do-not-terminate/events.out.tfevents.1702440028.beta-a100-3-do-not-terminate.217104.1 +3 -0
- runs/Dec14_01-13-37_beta-a100-3-do-not-terminate/events.out.tfevents.1702516438.beta-a100-3-do-not-terminate.138470.0 +3 -0
- runs/Dec14_01-13-37_beta-a100-3-do-not-terminate/events.out.tfevents.1702528057.beta-a100-3-do-not-terminate.138470.1 +3 -0
- train_results.json +3 -3
- trainer_state.json +8 -8
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -16,10 +16,10 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"
|
20 |
"k_proj",
|
21 |
-
"
|
22 |
-
"
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
25 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"v_proj",
|
20 |
"k_proj",
|
21 |
+
"q_proj",
|
22 |
+
"o_proj"
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM"
|
25 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 134252592
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8759f698b86fb6403fa30c3804a9371f2755833aaec0846cfdc6e5d684a48cf
|
3 |
size 134252592
|
all_results.json
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 0.69,
|
3 |
-
"eval_loss": 1.
|
4 |
-
"eval_runtime": 364.
|
5 |
"eval_samples": 23110,
|
6 |
-
"eval_samples_per_second": 63.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
-
"train_loss": 1.
|
9 |
-
"train_runtime":
|
10 |
"train_samples": 207865,
|
11 |
-
"train_samples_per_second": 18.
|
12 |
"train_steps_per_second": 0.004
|
13 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.69,
|
3 |
+
"eval_loss": 1.4448800086975098,
|
4 |
+
"eval_runtime": 364.2589,
|
5 |
"eval_samples": 23110,
|
6 |
+
"eval_samples_per_second": 63.444,
|
7 |
+
"eval_steps_per_second": 0.994,
|
8 |
+
"train_loss": 1.5280117051942008,
|
9 |
+
"train_runtime": 11254.0874,
|
10 |
"train_samples": 207865,
|
11 |
+
"train_samples_per_second": 18.47,
|
12 |
"train_steps_per_second": 0.004
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 0.69,
|
3 |
-
"eval_loss": 1.
|
4 |
-
"eval_runtime": 364.
|
5 |
"eval_samples": 23110,
|
6 |
-
"eval_samples_per_second": 63.
|
7 |
-
"eval_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.69,
|
3 |
+
"eval_loss": 1.4448800086975098,
|
4 |
+
"eval_runtime": 364.2589,
|
5 |
"eval_samples": 23110,
|
6 |
+
"eval_samples_per_second": 63.444,
|
7 |
+
"eval_steps_per_second": 0.994
|
8 |
}
|
runs/Dec13_00-46-21_beta-a100-3-do-not-terminate/events.out.tfevents.1702428403.beta-a100-3-do-not-terminate.217104.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a26254b493347b70477c0601cce9a4a2f9895191bc3a761e23e3674eb24dc509
|
3 |
+
size 6175
|
runs/Dec13_00-46-21_beta-a100-3-do-not-terminate/events.out.tfevents.1702440028.beta-a100-3-do-not-terminate.217104.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf830b49f144710da00042bc2914793d91abdc701454c75940c31e9ed194f4d7
|
3 |
+
size 354
|
runs/Dec14_01-13-37_beta-a100-3-do-not-terminate/events.out.tfevents.1702516438.beta-a100-3-do-not-terminate.138470.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac90361b8e7c966d70eee639bf9f75e1367c3e6fb1c9d9a369499f69deeeab43
|
3 |
+
size 6174
|
runs/Dec14_01-13-37_beta-a100-3-do-not-terminate/events.out.tfevents.1702528057.beta-a100-3-do-not-terminate.138470.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54c85d0f45c46ee8c4d1334a44751d6c2b0156ee3012e7b4642063d09a0645ce
|
3 |
+
size 354
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 0.69,
|
3 |
-
"train_loss": 1.
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 207865,
|
6 |
-
"train_samples_per_second": 18.
|
7 |
"train_steps_per_second": 0.004
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 0.69,
|
3 |
+
"train_loss": 1.5280117051942008,
|
4 |
+
"train_runtime": 11254.0874,
|
5 |
"train_samples": 207865,
|
6 |
+
"train_samples_per_second": 18.47,
|
7 |
"train_steps_per_second": 0.004
|
8 |
}
|
trainer_state.json
CHANGED
@@ -35,7 +35,7 @@
|
|
35 |
{
|
36 |
"epoch": 0.39,
|
37 |
"learning_rate": 1.3090169943749475e-05,
|
38 |
-
"loss": 1.
|
39 |
"step": 20
|
40 |
},
|
41 |
{
|
@@ -58,19 +58,19 @@
|
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.69,
|
61 |
-
"eval_loss": 1.
|
62 |
-
"eval_runtime":
|
63 |
-
"eval_samples_per_second": 63.
|
64 |
-
"eval_steps_per_second": 0.
|
65 |
"step": 35
|
66 |
},
|
67 |
{
|
68 |
"epoch": 0.69,
|
69 |
"step": 35,
|
70 |
"total_flos": 9.151767518380032e+16,
|
71 |
-
"train_loss": 1.
|
72 |
-
"train_runtime":
|
73 |
-
"train_samples_per_second": 18.
|
74 |
"train_steps_per_second": 0.004
|
75 |
}
|
76 |
],
|
|
|
35 |
{
|
36 |
"epoch": 0.39,
|
37 |
"learning_rate": 1.3090169943749475e-05,
|
38 |
+
"loss": 1.5004,
|
39 |
"step": 20
|
40 |
},
|
41 |
{
|
|
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.69,
|
61 |
+
"eval_loss": 1.4448364973068237,
|
62 |
+
"eval_runtime": 364.9385,
|
63 |
+
"eval_samples_per_second": 63.326,
|
64 |
+
"eval_steps_per_second": 0.992,
|
65 |
"step": 35
|
66 |
},
|
67 |
{
|
68 |
"epoch": 0.69,
|
69 |
"step": 35,
|
70 |
"total_flos": 9.151767518380032e+16,
|
71 |
+
"train_loss": 1.5280117051942008,
|
72 |
+
"train_runtime": 11254.0874,
|
73 |
+
"train_samples_per_second": 18.47,
|
74 |
"train_steps_per_second": 0.004
|
75 |
}
|
76 |
],
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5688
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52a306d4ecde95dd84ae209f63e8478c3974b9697577dc45f5e182706bec8810
|
3 |
size 5688
|