sayanbanerjee32
commited on
Commit
•
d396859
1
Parent(s):
c7c2db3
Upload folder using huggingface_hub
Browse files- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- image_projector.pth +1 -1
- lora_weights.pt +1 -1
- trainer_state.json +13 -21
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"o_proj",
|
24 |
-
"down_proj",
|
25 |
-
"gate_proj",
|
26 |
-
"up_proj",
|
27 |
"q_proj",
|
|
|
|
|
28 |
"k_proj",
|
29 |
-
"
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
|
|
|
|
23 |
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"up_proj",
|
26 |
"k_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"down_proj",
|
29 |
+
"o_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 35669232
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11d1c4e445e3a3dd51364a38d601ad5285f8864799fe280d3f40dc071326d865
|
3 |
size 35669232
|
image_projector.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 29379352
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b74ef56f2f9b977464120883b7026e9ea47ac548728bd4c3551988f27f22785
|
3 |
size 29379352
|
lora_weights.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 35697862
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a9b1f82efa677f77b81b7f178e0f1150e640ec1e501e4fcd755ab426a1b3b26
|
3 |
size 35697862
|
trainer_state.json
CHANGED
@@ -1,29 +1,21 @@
|
|
1 |
{
|
2 |
-
"epoch": 0.
|
3 |
-
"global_step":
|
4 |
-
"max_steps":
|
5 |
-
"logging_steps":
|
6 |
-
"eval_steps":
|
7 |
-
"save_steps":
|
8 |
"train_batch_size": 8,
|
9 |
"num_train_epochs": 1,
|
10 |
"num_input_tokens_seen": 0,
|
11 |
-
"total_flos":
|
12 |
"log_history": [
|
13 |
{
|
14 |
-
"loss":
|
15 |
-
"grad_norm":
|
16 |
-
"learning_rate":
|
17 |
-
"epoch": 0.
|
18 |
-
"step":
|
19 |
-
},
|
20 |
-
{
|
21 |
-
"eval_loss": 0.31789010763168335,
|
22 |
-
"eval_runtime": 428.825,
|
23 |
-
"eval_samples_per_second": 0.529,
|
24 |
-
"eval_steps_per_second": 0.133,
|
25 |
-
"epoch": 0.07407407407407407,
|
26 |
-
"step": 10
|
27 |
}
|
28 |
],
|
29 |
"best_metric": null,
|
@@ -36,7 +28,7 @@
|
|
36 |
"stateful_callbacks": {
|
37 |
"TrainerControl": {
|
38 |
"args": {
|
39 |
-
"should_training_stop":
|
40 |
"should_epoch_stop": false,
|
41 |
"should_save": true,
|
42 |
"should_evaluate": false,
|
|
|
1 |
{
|
2 |
+
"epoch": 0.011649580615097856,
|
3 |
+
"global_step": 25,
|
4 |
+
"max_steps": 2146,
|
5 |
+
"logging_steps": 25,
|
6 |
+
"eval_steps": 50,
|
7 |
+
"save_steps": 25,
|
8 |
"train_batch_size": 8,
|
9 |
"num_train_epochs": 1,
|
10 |
"num_input_tokens_seen": 0,
|
11 |
+
"total_flos": 1.3005907607519232e+16,
|
12 |
"log_history": [
|
13 |
{
|
14 |
+
"loss": 3.9545,
|
15 |
+
"grad_norm": 20.241615295410156,
|
16 |
+
"learning_rate": 5.8139534883720933e-05,
|
17 |
+
"epoch": 0.011649580615097856,
|
18 |
+
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
}
|
20 |
],
|
21 |
"best_metric": null,
|
|
|
28 |
"stateful_callbacks": {
|
29 |
"TrainerControl": {
|
30 |
"args": {
|
31 |
+
"should_training_stop": false,
|
32 |
"should_epoch_stop": false,
|
33 |
"should_save": true,
|
34 |
"should_evaluate": false,
|