Upload my model weights
Browse files- adapter_config.json +9 -9
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- trainer_state.json +22 -22
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -27,20 +27,20 @@
|
|
27 |
"rank_pattern": {},
|
28 |
"revision": null,
|
29 |
"target_modules": [
|
30 |
-
"model.layers.0.mlp.down_proj",
|
31 |
"model.layers.0.self_attn.o_proj",
|
32 |
-
"model.layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
"model.layers.1.mlp.down_proj",
|
34 |
"model.layers.0.mlp.up_proj",
|
|
|
35 |
"model.layers.1.self_attn.v_proj",
|
36 |
-
"model.layers.0.self_attn.v_proj",
|
37 |
-
"model.layers.0.self_attn.q_proj",
|
38 |
"model.layers.1.self_attn.o_proj",
|
39 |
-
"model.layers.
|
40 |
-
"model.layers.0.mlp.gate_proj",
|
41 |
-
"model.layers.0.self_attn.k_proj",
|
42 |
-
"model.layers.1.self_attn.k_proj",
|
43 |
-
"model.layers.1.mlp.up_proj"
|
44 |
],
|
45 |
"task_type": "SEQ_CLS",
|
46 |
"trainable_token_indices": null,
|
|
|
27 |
"rank_pattern": {},
|
28 |
"revision": null,
|
29 |
"target_modules": [
|
|
|
30 |
"model.layers.0.self_attn.o_proj",
|
31 |
+
"model.layers.0.self_attn.v_proj",
|
32 |
+
"model.layers.1.self_attn.k_proj",
|
33 |
+
"model.layers.0.mlp.down_proj",
|
34 |
+
"model.layers.0.self_attn.k_proj",
|
35 |
+
"model.layers.0.mlp.gate_proj",
|
36 |
+
"model.layers.1.mlp.gate_proj",
|
37 |
+
"model.layers.1.mlp.up_proj",
|
38 |
"model.layers.1.mlp.down_proj",
|
39 |
"model.layers.0.mlp.up_proj",
|
40 |
+
"model.layers.1.self_attn.q_proj",
|
41 |
"model.layers.1.self_attn.v_proj",
|
|
|
|
|
42 |
"model.layers.1.self_attn.o_proj",
|
43 |
+
"model.layers.0.self_attn.q_proj"
|
|
|
|
|
|
|
|
|
44 |
],
|
45 |
"task_type": "SEQ_CLS",
|
46 |
"trainable_token_indices": null,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 97952
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ff1f98d89d83f0936be32d305fcef4367caa5702874c90f1b8eea11d0b74378
|
3 |
size 97952
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 212551
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:697ac17d793715300eeb41bc5805d45218d6f69fa9d26a3773e20354e23cb0fa
|
3 |
size 212551
|
trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"best_global_step": 315,
|
3 |
-
"best_metric": 0.
|
4 |
-
"best_model_checkpoint": "/home/kat/git-repos/icse/results/rsa/20-05-2025:14-
|
5 |
"epoch": 1.0,
|
6 |
"eval_steps": 500,
|
7 |
"global_step": 315,
|
@@ -11,57 +11,57 @@
|
|
11 |
"log_history": [
|
12 |
{
|
13 |
"epoch": 0.15873015873015872,
|
14 |
-
"grad_norm":
|
15 |
"learning_rate": 1.688888888888889e-05,
|
16 |
-
"loss": 0.
|
17 |
"step": 50
|
18 |
},
|
19 |
{
|
20 |
"epoch": 0.31746031746031744,
|
21 |
-
"grad_norm":
|
22 |
"learning_rate": 1.3714285714285716e-05,
|
23 |
-
"loss": 0.
|
24 |
"step": 100
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.47619047619047616,
|
28 |
-
"grad_norm":
|
29 |
"learning_rate": 1.053968253968254e-05,
|
30 |
-
"loss": 0.
|
31 |
"step": 150
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.6349206349206349,
|
35 |
-
"grad_norm": 2.
|
36 |
"learning_rate": 7.3650793650793666e-06,
|
37 |
-
"loss": 0.
|
38 |
"step": 200
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.7936507936507936,
|
42 |
-
"grad_norm":
|
43 |
"learning_rate": 4.190476190476191e-06,
|
44 |
-
"loss": 0.
|
45 |
"step": 250
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.9523809523809523,
|
49 |
-
"grad_norm":
|
50 |
"learning_rate": 1.015873015873016e-06,
|
51 |
-
"loss": 0.
|
52 |
"step": 300
|
53 |
},
|
54 |
{
|
55 |
"epoch": 1.0,
|
56 |
-
"eval_accuracy": 0.
|
57 |
"eval_balanced_accuracy": 0.0,
|
58 |
-
"eval_f1_score": 0.
|
59 |
-
"eval_loss": 0.
|
60 |
-
"eval_precision": 0.
|
61 |
-
"eval_recall": 0.
|
62 |
-
"eval_runtime": 2.
|
63 |
-
"eval_samples_per_second":
|
64 |
-
"eval_steps_per_second":
|
65 |
"step": 315
|
66 |
}
|
67 |
],
|
|
|
1 |
{
|
2 |
"best_global_step": 315,
|
3 |
+
"best_metric": 0.3333333333333333,
|
4 |
+
"best_model_checkpoint": "/home/kat/git-repos/icse/results/rsa/20-05-2025:14-47-09/checkpoint-315",
|
5 |
"epoch": 1.0,
|
6 |
"eval_steps": 500,
|
7 |
"global_step": 315,
|
|
|
11 |
"log_history": [
|
12 |
{
|
13 |
"epoch": 0.15873015873015872,
|
14 |
+
"grad_norm": 3.1602320671081543,
|
15 |
"learning_rate": 1.688888888888889e-05,
|
16 |
+
"loss": 0.7162,
|
17 |
"step": 50
|
18 |
},
|
19 |
{
|
20 |
"epoch": 0.31746031746031744,
|
21 |
+
"grad_norm": 3.1608448028564453,
|
22 |
"learning_rate": 1.3714285714285716e-05,
|
23 |
+
"loss": 0.7011,
|
24 |
"step": 100
|
25 |
},
|
26 |
{
|
27 |
"epoch": 0.47619047619047616,
|
28 |
+
"grad_norm": 3.158813238143921,
|
29 |
"learning_rate": 1.053968253968254e-05,
|
30 |
+
"loss": 0.7355,
|
31 |
"step": 150
|
32 |
},
|
33 |
{
|
34 |
"epoch": 0.6349206349206349,
|
35 |
+
"grad_norm": 2.464698553085327,
|
36 |
"learning_rate": 7.3650793650793666e-06,
|
37 |
+
"loss": 0.6762,
|
38 |
"step": 200
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.7936507936507936,
|
42 |
+
"grad_norm": 3.153306007385254,
|
43 |
"learning_rate": 4.190476190476191e-06,
|
44 |
+
"loss": 0.7057,
|
45 |
"step": 250
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.9523809523809523,
|
49 |
+
"grad_norm": 3.15567684173584,
|
50 |
"learning_rate": 1.015873015873016e-06,
|
51 |
+
"loss": 0.6662,
|
52 |
"step": 300
|
53 |
},
|
54 |
{
|
55 |
"epoch": 1.0,
|
56 |
+
"eval_accuracy": 0.5,
|
57 |
"eval_balanced_accuracy": 0.0,
|
58 |
+
"eval_f1_score": 0.3333333333333333,
|
59 |
+
"eval_loss": 0.7008427381515503,
|
60 |
+
"eval_precision": 0.25,
|
61 |
+
"eval_recall": 0.5,
|
62 |
+
"eval_runtime": 2.266,
|
63 |
+
"eval_samples_per_second": 28.243,
|
64 |
+
"eval_steps_per_second": 28.243,
|
65 |
"step": 315
|
66 |
}
|
67 |
],
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91601ee75b1a901f6c6bd3dc28f96c341cbcba2088f24be211328a29d0c7dc29
|
3 |
size 5432
|