willtensora
commited on
Training in progress, epoch 0, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
"up_proj",
|
25 |
-
"down_proj",
|
26 |
-
"o_proj",
|
27 |
"q_proj",
|
|
|
|
|
28 |
"v_proj",
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
"up_proj",
|
|
|
|
|
25 |
"q_proj",
|
26 |
+
"o_proj",
|
27 |
+
"down_proj",
|
28 |
"v_proj",
|
29 |
+
"gate_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 14696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b223e30d8c9bbebf54351b7cf7b34b0849a4652f452b06d4ef2624ec31855119
|
3 |
size 14696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 39398
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0d3470004bc3d15c18ea2624c80f07ad8a5ed20b05b353785a3c2fa87f54c561
|
3 |
size 39398
|
last-checkpoint/trainer_state.json
CHANGED
@@ -10,24 +10,24 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 6.727664155005382e-05,
|
13 |
-
"grad_norm": 0.
|
14 |
"learning_rate": 0.0001,
|
15 |
"loss": 11.9692,
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.00013455328310010763,
|
20 |
-
"grad_norm": 0.
|
21 |
"learning_rate": 0.0002,
|
22 |
"loss": 11.931,
|
23 |
"step": 2
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.00013455328310010763,
|
27 |
-
"eval_loss": 11.
|
28 |
-
"eval_runtime": 0.
|
29 |
-
"eval_samples_per_second":
|
30 |
-
"eval_steps_per_second":
|
31 |
"step": 2
|
32 |
}
|
33 |
],
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 6.727664155005382e-05,
|
13 |
+
"grad_norm": 0.13251228630542755,
|
14 |
"learning_rate": 0.0001,
|
15 |
"loss": 11.9692,
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.00013455328310010763,
|
20 |
+
"grad_norm": 0.032421912997961044,
|
21 |
"learning_rate": 0.0002,
|
22 |
"loss": 11.931,
|
23 |
"step": 2
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.00013455328310010763,
|
27 |
+
"eval_loss": 11.932136535644531,
|
28 |
+
"eval_runtime": 0.7625,
|
29 |
+
"eval_samples_per_second": 198.036,
|
30 |
+
"eval_steps_per_second": 198.036,
|
31 |
"step": 2
|
32 |
}
|
33 |
],
|
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:dce5acab224b5c3a108ca0fe2f9d758fbfc0ad3d00d3c86ddb99c6b0338681e0
|
3 |
size 6776
|