Training in progress, step 10, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,12 +20,12 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
|
|
24 |
"down_proj",
|
25 |
"q_proj",
|
26 |
-
"k_proj",
|
27 |
-
"v_proj",
|
28 |
"gate_proj",
|
|
|
29 |
"up_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"k_proj",
|
25 |
"down_proj",
|
26 |
"q_proj",
|
|
|
|
|
27 |
"gate_proj",
|
28 |
+
"o_proj",
|
29 |
"up_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 48679352
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1837de8c2c0ae3a2f2f3846fbbd705e8cd52007adce1b834ff59810d4ca67e84
|
3 |
size 48679352
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 97487290
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43f33a43f2f746ac6888cb21c207e227ebdb333d740cb1f15c50df452a4ea4b9
|
3 |
size 97487290
|
last-checkpoint/trainer_state.json
CHANGED
@@ -10,7 +10,7 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.00018793459875963165,
|
13 |
-
"grad_norm": 0.
|
14 |
"learning_rate": 2e-05,
|
15 |
"loss": 2.0097,
|
16 |
"step": 1
|
@@ -18,96 +18,96 @@
|
|
18 |
{
|
19 |
"epoch": 0.00018793459875963165,
|
20 |
"eval_loss": 2.225860595703125,
|
21 |
-
"eval_runtime": 104.
|
22 |
-
"eval_samples_per_second": 10.
|
23 |
-
"eval_steps_per_second": 10.
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.0003758691975192633,
|
28 |
-
"grad_norm": 0.
|
29 |
"learning_rate": 4e-05,
|
30 |
"loss": 2.0424,
|
31 |
"step": 2
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.0005638037962788949,
|
35 |
-
"grad_norm": 0.
|
36 |
"learning_rate": 6e-05,
|
37 |
-
"loss": 2.
|
38 |
"step": 3
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.0005638037962788949,
|
42 |
-
"eval_loss": 2.
|
43 |
-
"eval_runtime": 105.
|
44 |
-
"eval_samples_per_second": 10.
|
45 |
-
"eval_steps_per_second": 10.
|
46 |
"step": 3
|
47 |
},
|
48 |
{
|
49 |
"epoch": 0.0007517383950385266,
|
50 |
-
"grad_norm": 0.
|
51 |
"learning_rate": 8e-05,
|
52 |
-
"loss": 2.
|
53 |
"step": 4
|
54 |
},
|
55 |
{
|
56 |
"epoch": 0.0009396729937981583,
|
57 |
-
"grad_norm": 0.
|
58 |
"learning_rate": 0.0001,
|
59 |
"loss": 2.2092,
|
60 |
"step": 5
|
61 |
},
|
62 |
{
|
63 |
"epoch": 0.0011276075925577898,
|
64 |
-
"grad_norm": 0.
|
65 |
"learning_rate": 0.00012,
|
66 |
-
"loss": 2.
|
67 |
"step": 6
|
68 |
},
|
69 |
{
|
70 |
"epoch": 0.0011276075925577898,
|
71 |
-
"eval_loss": 2.
|
72 |
-
"eval_runtime": 104.
|
73 |
-
"eval_samples_per_second": 10.
|
74 |
-
"eval_steps_per_second": 10.
|
75 |
"step": 6
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.0013155421913174216,
|
79 |
-
"grad_norm": 0.
|
80 |
"learning_rate": 0.00014,
|
81 |
-
"loss": 2.
|
82 |
"step": 7
|
83 |
},
|
84 |
{
|
85 |
"epoch": 0.0015034767900770532,
|
86 |
-
"grad_norm": 0.
|
87 |
"learning_rate": 0.00016,
|
88 |
-
"loss": 2.
|
89 |
"step": 8
|
90 |
},
|
91 |
{
|
92 |
"epoch": 0.001691411388836685,
|
93 |
-
"grad_norm": 0.
|
94 |
"learning_rate": 0.00018,
|
95 |
-
"loss": 2.
|
96 |
"step": 9
|
97 |
},
|
98 |
{
|
99 |
"epoch": 0.001691411388836685,
|
100 |
-
"eval_loss": 2.
|
101 |
-
"eval_runtime":
|
102 |
-
"eval_samples_per_second": 10.
|
103 |
-
"eval_steps_per_second": 10.
|
104 |
"step": 9
|
105 |
},
|
106 |
{
|
107 |
"epoch": 0.0018793459875963165,
|
108 |
-
"grad_norm": 0.
|
109 |
"learning_rate": 0.0002,
|
110 |
-
"loss": 2.
|
111 |
"step": 10
|
112 |
}
|
113 |
],
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.00018793459875963165,
|
13 |
+
"grad_norm": 0.40805867314338684,
|
14 |
"learning_rate": 2e-05,
|
15 |
"loss": 2.0097,
|
16 |
"step": 1
|
|
|
18 |
{
|
19 |
"epoch": 0.00018793459875963165,
|
20 |
"eval_loss": 2.225860595703125,
|
21 |
+
"eval_runtime": 104.7616,
|
22 |
+
"eval_samples_per_second": 10.7,
|
23 |
+
"eval_steps_per_second": 10.7,
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.0003758691975192633,
|
28 |
+
"grad_norm": 0.3363264501094818,
|
29 |
"learning_rate": 4e-05,
|
30 |
"loss": 2.0424,
|
31 |
"step": 2
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.0005638037962788949,
|
35 |
+
"grad_norm": 0.4387308359146118,
|
36 |
"learning_rate": 6e-05,
|
37 |
+
"loss": 2.2437,
|
38 |
"step": 3
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.0005638037962788949,
|
42 |
+
"eval_loss": 2.223356246948242,
|
43 |
+
"eval_runtime": 105.324,
|
44 |
+
"eval_samples_per_second": 10.643,
|
45 |
+
"eval_steps_per_second": 10.643,
|
46 |
"step": 3
|
47 |
},
|
48 |
{
|
49 |
"epoch": 0.0007517383950385266,
|
50 |
+
"grad_norm": 0.30487483739852905,
|
51 |
"learning_rate": 8e-05,
|
52 |
+
"loss": 2.1183,
|
53 |
"step": 4
|
54 |
},
|
55 |
{
|
56 |
"epoch": 0.0009396729937981583,
|
57 |
+
"grad_norm": 0.44409823417663574,
|
58 |
"learning_rate": 0.0001,
|
59 |
"loss": 2.2092,
|
60 |
"step": 5
|
61 |
},
|
62 |
{
|
63 |
"epoch": 0.0011276075925577898,
|
64 |
+
"grad_norm": 0.31591424345970154,
|
65 |
"learning_rate": 0.00012,
|
66 |
+
"loss": 2.223,
|
67 |
"step": 6
|
68 |
},
|
69 |
{
|
70 |
"epoch": 0.0011276075925577898,
|
71 |
+
"eval_loss": 2.2032065391540527,
|
72 |
+
"eval_runtime": 104.9365,
|
73 |
+
"eval_samples_per_second": 10.683,
|
74 |
+
"eval_steps_per_second": 10.683,
|
75 |
"step": 6
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.0013155421913174216,
|
79 |
+
"grad_norm": 0.49352651834487915,
|
80 |
"learning_rate": 0.00014,
|
81 |
+
"loss": 2.1991,
|
82 |
"step": 7
|
83 |
},
|
84 |
{
|
85 |
"epoch": 0.0015034767900770532,
|
86 |
+
"grad_norm": 0.3866937458515167,
|
87 |
"learning_rate": 0.00016,
|
88 |
+
"loss": 2.1441,
|
89 |
"step": 8
|
90 |
},
|
91 |
{
|
92 |
"epoch": 0.001691411388836685,
|
93 |
+
"grad_norm": 0.3655875623226166,
|
94 |
"learning_rate": 0.00018,
|
95 |
+
"loss": 2.0592,
|
96 |
"step": 9
|
97 |
},
|
98 |
{
|
99 |
"epoch": 0.001691411388836685,
|
100 |
+
"eval_loss": 2.1501598358154297,
|
101 |
+
"eval_runtime": 105.4766,
|
102 |
+
"eval_samples_per_second": 10.628,
|
103 |
+
"eval_steps_per_second": 10.628,
|
104 |
"step": 9
|
105 |
},
|
106 |
{
|
107 |
"epoch": 0.0018793459875963165,
|
108 |
+
"grad_norm": 0.36404484510421753,
|
109 |
"learning_rate": 0.0002,
|
110 |
+
"loss": 2.0794,
|
111 |
"step": 10
|
112 |
}
|
113 |
],
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acaeb28a4fb49aa88292474a6784853956ad77b62156abc6a5e8cbc29594a649
|
3 |
size 6776
|