Training in progress, step 10, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -21,12 +21,12 @@
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"gate_proj",
|
24 |
-
"
|
25 |
-
"v_proj",
|
26 |
-
"down_proj",
|
27 |
"q_proj",
|
28 |
"k_proj",
|
29 |
-
"
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
"gate_proj",
|
24 |
+
"up_proj",
|
|
|
|
|
25 |
"q_proj",
|
26 |
"k_proj",
|
27 |
+
"o_proj",
|
28 |
+
"v_proj",
|
29 |
+
"down_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 767856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:063267c323f826559daebddfb148a7f94fe2794e06e76b00be9adba90041236a
|
3 |
size 767856
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1003002
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69e646d156a3f343a326d0a1045edc00b5f3e7a0f67e9ca0ecb5eddb920ce240
|
3 |
size 1003002
|
last-checkpoint/trainer_state.json
CHANGED
@@ -18,9 +18,9 @@
|
|
18 |
{
|
19 |
"epoch": 0.00554016620498615,
|
20 |
"eval_loss": 10.876238822937012,
|
21 |
-
"eval_runtime": 1.
|
22 |
-
"eval_samples_per_second":
|
23 |
-
"eval_steps_per_second": 33.
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
@@ -40,74 +40,74 @@
|
|
40 |
{
|
41 |
"epoch": 0.01662049861495845,
|
42 |
"eval_loss": 10.876238822937012,
|
43 |
-
"eval_runtime": 1.
|
44 |
-
"eval_samples_per_second":
|
45 |
-
"eval_steps_per_second":
|
46 |
"step": 3
|
47 |
},
|
48 |
{
|
49 |
"epoch": 0.0221606648199446,
|
50 |
-
"grad_norm": 17.
|
51 |
"learning_rate": 2e-05,
|
52 |
"loss": 11.1469,
|
53 |
"step": 4
|
54 |
},
|
55 |
{
|
56 |
"epoch": 0.027700831024930747,
|
57 |
-
"grad_norm": 17.
|
58 |
"learning_rate": 4e-05,
|
59 |
"loss": 10.8969,
|
60 |
"step": 5
|
61 |
},
|
62 |
{
|
63 |
"epoch": 0.0332409972299169,
|
64 |
-
"grad_norm":
|
65 |
"learning_rate": 6e-05,
|
66 |
-
"loss": 10.
|
67 |
"step": 6
|
68 |
},
|
69 |
{
|
70 |
"epoch": 0.0332409972299169,
|
71 |
-
"eval_loss": 10.
|
72 |
-
"eval_runtime": 1.
|
73 |
-
"eval_samples_per_second":
|
74 |
-
"eval_steps_per_second":
|
75 |
"step": 6
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.038781163434903045,
|
79 |
-
"grad_norm": 23.
|
80 |
"learning_rate": 8e-05,
|
81 |
-
"loss": 10.
|
82 |
"step": 7
|
83 |
},
|
84 |
{
|
85 |
"epoch": 0.0443213296398892,
|
86 |
-
"grad_norm":
|
87 |
"learning_rate": 0.0001,
|
88 |
-
"loss": 10.
|
89 |
"step": 8
|
90 |
},
|
91 |
{
|
92 |
"epoch": 0.04986149584487535,
|
93 |
-
"grad_norm": 16.
|
94 |
"learning_rate": 0.00012,
|
95 |
-
"loss": 10.
|
96 |
"step": 9
|
97 |
},
|
98 |
{
|
99 |
"epoch": 0.04986149584487535,
|
100 |
-
"eval_loss": 10.
|
101 |
-
"eval_runtime": 1.
|
102 |
-
"eval_samples_per_second":
|
103 |
-
"eval_steps_per_second":
|
104 |
"step": 9
|
105 |
},
|
106 |
{
|
107 |
"epoch": 0.055401662049861494,
|
108 |
-
"grad_norm":
|
109 |
"learning_rate": 0.00014,
|
110 |
-
"loss": 10.
|
111 |
"step": 10
|
112 |
}
|
113 |
],
|
|
|
18 |
{
|
19 |
"epoch": 0.00554016620498615,
|
20 |
"eval_loss": 10.876238822937012,
|
21 |
+
"eval_runtime": 1.1301,
|
22 |
+
"eval_samples_per_second": 67.253,
|
23 |
+
"eval_steps_per_second": 33.627,
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
|
|
40 |
{
|
41 |
"epoch": 0.01662049861495845,
|
42 |
"eval_loss": 10.876238822937012,
|
43 |
+
"eval_runtime": 1.0865,
|
44 |
+
"eval_samples_per_second": 69.949,
|
45 |
+
"eval_steps_per_second": 34.975,
|
46 |
"step": 3
|
47 |
},
|
48 |
{
|
49 |
"epoch": 0.0221606648199446,
|
50 |
+
"grad_norm": 17.566349029541016,
|
51 |
"learning_rate": 2e-05,
|
52 |
"loss": 11.1469,
|
53 |
"step": 4
|
54 |
},
|
55 |
{
|
56 |
"epoch": 0.027700831024930747,
|
57 |
+
"grad_norm": 17.940860748291016,
|
58 |
"learning_rate": 4e-05,
|
59 |
"loss": 10.8969,
|
60 |
"step": 5
|
61 |
},
|
62 |
{
|
63 |
"epoch": 0.0332409972299169,
|
64 |
+
"grad_norm": 20.539535522460938,
|
65 |
"learning_rate": 6e-05,
|
66 |
+
"loss": 10.8141,
|
67 |
"step": 6
|
68 |
},
|
69 |
{
|
70 |
"epoch": 0.0332409972299169,
|
71 |
+
"eval_loss": 10.789344787597656,
|
72 |
+
"eval_runtime": 1.1219,
|
73 |
+
"eval_samples_per_second": 67.744,
|
74 |
+
"eval_steps_per_second": 33.872,
|
75 |
"step": 6
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.038781163434903045,
|
79 |
+
"grad_norm": 23.39402961730957,
|
80 |
"learning_rate": 8e-05,
|
81 |
+
"loss": 10.8841,
|
82 |
"step": 7
|
83 |
},
|
84 |
{
|
85 |
"epoch": 0.0443213296398892,
|
86 |
+
"grad_norm": 17.9848690032959,
|
87 |
"learning_rate": 0.0001,
|
88 |
+
"loss": 10.4167,
|
89 |
"step": 8
|
90 |
},
|
91 |
{
|
92 |
"epoch": 0.04986149584487535,
|
93 |
+
"grad_norm": 16.139219284057617,
|
94 |
"learning_rate": 0.00012,
|
95 |
+
"loss": 10.8235,
|
96 |
"step": 9
|
97 |
},
|
98 |
{
|
99 |
"epoch": 0.04986149584487535,
|
100 |
+
"eval_loss": 10.459603309631348,
|
101 |
+
"eval_runtime": 1.1553,
|
102 |
+
"eval_samples_per_second": 65.786,
|
103 |
+
"eval_steps_per_second": 32.893,
|
104 |
"step": 9
|
105 |
},
|
106 |
{
|
107 |
"epoch": 0.055401662049861494,
|
108 |
+
"grad_norm": 20.555219650268555,
|
109 |
"learning_rate": 0.00014,
|
110 |
+
"loss": 10.6594,
|
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 6712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9bb8d12ab7d3707b6887bbd0a3831cfac8994e15c07c849a86e5da758026626
|
3 |
size 6712
|