DeepDream2045
commited on
Commit
•
fa14848
1
Parent(s):
8812c67
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 |
"gate_proj",
|
|
|
25 |
"k_proj",
|
26 |
-
"up_proj",
|
27 |
-
"down_proj",
|
28 |
"q_proj",
|
|
|
29 |
"o_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"up_proj",
|
24 |
"gate_proj",
|
25 |
+
"v_proj",
|
26 |
"k_proj",
|
|
|
|
|
27 |
"q_proj",
|
28 |
+
"down_proj",
|
29 |
"o_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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3293a8a1eb1d98f95ae6a8e8eb8951ff87094792bb9a7203c4c68eb0e1b7fa27
|
3 |
size 73911112
|
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 sha256:12652e548395ac54f34186413124cf818db17e2dae781e78f969b6d3fed44e53
|
3 |
size 14244
|
last-checkpoint/trainer_state.json
CHANGED
@@ -18,9 +18,9 @@
|
|
18 |
{
|
19 |
"epoch": 0.00016649323621227888,
|
20 |
"eval_loss": NaN,
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second": 4.
|
23 |
-
"eval_steps_per_second": 2.
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
@@ -40,9 +40,9 @@
|
|
40 |
{
|
41 |
"epoch": 0.0004994797086368366,
|
42 |
"eval_loss": NaN,
|
43 |
-
"eval_runtime": 540.
|
44 |
-
"eval_samples_per_second": 4.
|
45 |
-
"eval_steps_per_second": 2.
|
46 |
"step": 3
|
47 |
},
|
48 |
{
|
@@ -69,9 +69,9 @@
|
|
69 |
{
|
70 |
"epoch": 0.0009989594172736733,
|
71 |
"eval_loss": NaN,
|
72 |
-
"eval_runtime":
|
73 |
-
"eval_samples_per_second": 4.
|
74 |
-
"eval_steps_per_second": 2.
|
75 |
"step": 6
|
76 |
},
|
77 |
{
|
@@ -98,9 +98,9 @@
|
|
98 |
{
|
99 |
"epoch": 0.00149843912591051,
|
100 |
"eval_loss": NaN,
|
101 |
-
"eval_runtime": 540.
|
102 |
"eval_samples_per_second": 4.677,
|
103 |
-
"eval_steps_per_second": 2.
|
104 |
"step": 9
|
105 |
},
|
106 |
{
|
|
|
18 |
{
|
19 |
"epoch": 0.00016649323621227888,
|
20 |
"eval_loss": NaN,
|
21 |
+
"eval_runtime": 541.5183,
|
22 |
+
"eval_samples_per_second": 4.67,
|
23 |
+
"eval_steps_per_second": 2.336,
|
24 |
"step": 1
|
25 |
},
|
26 |
{
|
|
|
40 |
{
|
41 |
"epoch": 0.0004994797086368366,
|
42 |
"eval_loss": NaN,
|
43 |
+
"eval_runtime": 540.5845,
|
44 |
+
"eval_samples_per_second": 4.678,
|
45 |
+
"eval_steps_per_second": 2.34,
|
46 |
"step": 3
|
47 |
},
|
48 |
{
|
|
|
69 |
{
|
70 |
"epoch": 0.0009989594172736733,
|
71 |
"eval_loss": NaN,
|
72 |
+
"eval_runtime": 540.514,
|
73 |
+
"eval_samples_per_second": 4.679,
|
74 |
+
"eval_steps_per_second": 2.34,
|
75 |
"step": 6
|
76 |
},
|
77 |
{
|
|
|
98 |
{
|
99 |
"epoch": 0.00149843912591051,
|
100 |
"eval_loss": NaN,
|
101 |
+
"eval_runtime": 540.6919,
|
102 |
"eval_samples_per_second": 4.677,
|
103 |
+
"eval_steps_per_second": 2.34,
|
104 |
"step": 9
|
105 |
},
|
106 |
{
|
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:edd5c8003dc212a5d55ed2476be46f188433095a148c73d1f0610fae7d6df834
|
3 |
size 6776
|