Training in progress, step 9, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
|
|
24 |
"o_proj",
|
25 |
"q_proj",
|
26 |
-
"k_proj",
|
27 |
-
"down_proj",
|
28 |
"gate_proj",
|
29 |
-
"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"down_proj",
|
25 |
"o_proj",
|
26 |
"q_proj",
|
|
|
|
|
27 |
"gate_proj",
|
28 |
+
"up_proj",
|
29 |
+
"k_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 50503544
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a8a93262756e47d5839bbfbfd6e1782b4a4b115858b7bbfbdb48d6b2a2d648f
|
3 |
size 50503544
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25986148
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12b51d7b9e7762dad6ee06eb74391d6cd0b59e3429ee051e55c386ab2b1404e7
|
3 |
size 25986148
|
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 sha256:46a60f1f8a64a67c522a32b2bb6298c6721f7223b751a5f8a8dd5bea9d110e86
|
3 |
size 14244
|
last-checkpoint/trainer_state.json
CHANGED
@@ -10,7 +10,7 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.00010075820549636011,
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 2e-05,
|
15 |
"loss": 1.8654,
|
16 |
"step": 1
|
@@ -18,88 +18,88 @@
|
|
18 |
{
|
19 |
"epoch": 0.00010075820549636011,
|
20 |
"eval_loss": 1.7779617309570312,
|
21 |
-
"eval_runtime": 1454.
|
22 |
-
"eval_samples_per_second": 2.
|
23 |
-
"eval_steps_per_second": 1.
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.00020151641099272022,
|
28 |
-
"grad_norm": 2.
|
29 |
"learning_rate": 4e-05,
|
30 |
"loss": 1.3359,
|
31 |
"step": 2
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.0003022746164890803,
|
35 |
-
"grad_norm":
|
36 |
"learning_rate": 6e-05,
|
37 |
-
"loss": 1.
|
38 |
"step": 3
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.0003022746164890803,
|
42 |
-
"eval_loss": 1.
|
43 |
-
"eval_runtime": 1454.
|
44 |
-
"eval_samples_per_second": 2.
|
45 |
"eval_steps_per_second": 1.437,
|
46 |
"step": 3
|
47 |
},
|
48 |
{
|
49 |
"epoch": 0.00040303282198544043,
|
50 |
-
"grad_norm":
|
51 |
"learning_rate": 8e-05,
|
52 |
-
"loss": 1.
|
53 |
"step": 4
|
54 |
},
|
55 |
{
|
56 |
"epoch": 0.0005037910274818005,
|
57 |
-
"grad_norm":
|
58 |
"learning_rate": 0.0001,
|
59 |
-
"loss": 1.
|
60 |
"step": 5
|
61 |
},
|
62 |
{
|
63 |
"epoch": 0.0006045492329781607,
|
64 |
-
"grad_norm":
|
65 |
"learning_rate": 0.00012,
|
66 |
-
"loss": 1.
|
67 |
"step": 6
|
68 |
},
|
69 |
{
|
70 |
"epoch": 0.0006045492329781607,
|
71 |
-
"eval_loss": 1.
|
72 |
-
"eval_runtime": 1454.
|
73 |
-
"eval_samples_per_second": 2.
|
74 |
"eval_steps_per_second": 1.437,
|
75 |
"step": 6
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.0007053074384745208,
|
79 |
-
"grad_norm":
|
80 |
"learning_rate": 0.00014,
|
81 |
-
"loss": 1.
|
82 |
"step": 7
|
83 |
},
|
84 |
{
|
85 |
"epoch": 0.0008060656439708809,
|
86 |
-
"grad_norm":
|
87 |
"learning_rate": 0.00016,
|
88 |
-
"loss": 1.
|
89 |
"step": 8
|
90 |
},
|
91 |
{
|
92 |
"epoch": 0.000906823849467241,
|
93 |
-
"grad_norm": 1.
|
94 |
"learning_rate": 0.00018,
|
95 |
-
"loss": 1.
|
96 |
"step": 9
|
97 |
},
|
98 |
{
|
99 |
"epoch": 0.000906823849467241,
|
100 |
-
"eval_loss": 1.
|
101 |
-
"eval_runtime":
|
102 |
-
"eval_samples_per_second": 2.
|
103 |
"eval_steps_per_second": 1.436,
|
104 |
"step": 9
|
105 |
}
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.00010075820549636011,
|
13 |
+
"grad_norm": 8.359752932236722e+18,
|
14 |
"learning_rate": 2e-05,
|
15 |
"loss": 1.8654,
|
16 |
"step": 1
|
|
|
18 |
{
|
19 |
"epoch": 0.00010075820549636011,
|
20 |
"eval_loss": 1.7779617309570312,
|
21 |
+
"eval_runtime": 1454.9416,
|
22 |
+
"eval_samples_per_second": 2.872,
|
23 |
+
"eval_steps_per_second": 1.436,
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.00020151641099272022,
|
28 |
+
"grad_norm": 2.626370165041791e+18,
|
29 |
"learning_rate": 4e-05,
|
30 |
"loss": 1.3359,
|
31 |
"step": 2
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.0003022746164890803,
|
35 |
+
"grad_norm": 3.249743505089626e+18,
|
36 |
"learning_rate": 6e-05,
|
37 |
+
"loss": 1.3042,
|
38 |
"step": 3
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.0003022746164890803,
|
42 |
+
"eval_loss": 1.7708849906921387,
|
43 |
+
"eval_runtime": 1454.6249,
|
44 |
+
"eval_samples_per_second": 2.873,
|
45 |
"eval_steps_per_second": 1.437,
|
46 |
"step": 3
|
47 |
},
|
48 |
{
|
49 |
"epoch": 0.00040303282198544043,
|
50 |
+
"grad_norm": 8.100253344674611e+18,
|
51 |
"learning_rate": 8e-05,
|
52 |
+
"loss": 1.5396,
|
53 |
"step": 4
|
54 |
},
|
55 |
{
|
56 |
"epoch": 0.0005037910274818005,
|
57 |
+
"grad_norm": 4.612551334078448e+18,
|
58 |
"learning_rate": 0.0001,
|
59 |
+
"loss": 1.2117,
|
60 |
"step": 5
|
61 |
},
|
62 |
{
|
63 |
"epoch": 0.0006045492329781607,
|
64 |
+
"grad_norm": 6.333141896013021e+18,
|
65 |
"learning_rate": 0.00012,
|
66 |
+
"loss": 1.6426,
|
67 |
"step": 6
|
68 |
},
|
69 |
{
|
70 |
"epoch": 0.0006045492329781607,
|
71 |
+
"eval_loss": 1.7828969955444336,
|
72 |
+
"eval_runtime": 1454.0873,
|
73 |
+
"eval_samples_per_second": 2.874,
|
74 |
"eval_steps_per_second": 1.437,
|
75 |
"step": 6
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.0007053074384745208,
|
79 |
+
"grad_norm": 5.453606261071282e+18,
|
80 |
"learning_rate": 0.00014,
|
81 |
+
"loss": 1.3789,
|
82 |
"step": 7
|
83 |
},
|
84 |
{
|
85 |
"epoch": 0.0008060656439708809,
|
86 |
+
"grad_norm": 7.580743446399287e+18,
|
87 |
"learning_rate": 0.00016,
|
88 |
+
"loss": 1.4,
|
89 |
"step": 8
|
90 |
},
|
91 |
{
|
92 |
"epoch": 0.000906823849467241,
|
93 |
+
"grad_norm": 1.1626996814149845e+19,
|
94 |
"learning_rate": 0.00018,
|
95 |
+
"loss": 1.3397,
|
96 |
"step": 9
|
97 |
},
|
98 |
{
|
99 |
"epoch": 0.000906823849467241,
|
100 |
+
"eval_loss": 1.7769960165023804,
|
101 |
+
"eval_runtime": 1454.9997,
|
102 |
+
"eval_samples_per_second": 2.872,
|
103 |
"eval_steps_per_second": 1.436,
|
104 |
"step": 9
|
105 |
}
|
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 sha256:58a3eb8d82e5fbac81f07720d857f56891a89c37b161f0eab5a75ef832506307
|
3 |
size 6776
|