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 |
"gate_proj",
|
24 |
-
"v_proj",
|
25 |
-
"k_proj",
|
26 |
-
"down_proj",
|
27 |
"o_proj",
|
28 |
-
"
|
29 |
-
"
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
"gate_proj",
|
|
|
|
|
|
|
25 |
"o_proj",
|
26 |
+
"up_proj",
|
27 |
+
"down_proj",
|
28 |
+
"v_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 9048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eaf406d8cdb6b52f8a340431d451dc1fc4681e2ed0bc3663717273a1b9b3ef12
|
3 |
size 9048
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 28134
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a9285a5e0e1816273de107fab9026259478a32528f645b209923a81b449ca3d
|
3 |
size 28134
|
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 sha256:3371d8262583e71fbd2dbc164d88e0c7a9f17a572e2f30bb0e3d8e809fca6486
|
3 |
size 14244
|
last-checkpoint/trainer_state.json
CHANGED
@@ -10,17 +10,17 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0002666666666666667,
|
13 |
-
"grad_norm": 0.
|
14 |
"learning_rate": 0.0,
|
15 |
"loss": 11.9308,
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.0002666666666666667,
|
20 |
-
"eval_loss": 11.
|
21 |
-
"eval_runtime": 0.
|
22 |
-
"eval_samples_per_second":
|
23 |
-
"eval_steps_per_second":
|
24 |
"step": 1
|
25 |
}
|
26 |
],
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.0002666666666666667,
|
13 |
+
"grad_norm": 0.013214402832090855,
|
14 |
"learning_rate": 0.0,
|
15 |
"loss": 11.9308,
|
16 |
"step": 1
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.0002666666666666667,
|
20 |
+
"eval_loss": 11.933879852294922,
|
21 |
+
"eval_runtime": 0.0614,
|
22 |
+
"eval_samples_per_second": 260.741,
|
23 |
+
"eval_steps_per_second": 65.185,
|
24 |
"step": 1
|
25 |
}
|
26 |
],
|
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 sha256:9e1debdbe4095d32d1d33ca4aa71553472896ec45d93796674ecc45e1e93db66
|
3 |
size 6776
|