sayanbanerjee32
commited on
Commit
•
8615989
1
Parent(s):
a01827a
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 +5 -21
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"q_proj",
|
24 |
-
"up_proj",
|
25 |
-
"gate_proj",
|
26 |
-
"v_proj",
|
27 |
"o_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 |
"o_proj",
|
24 |
+
"down_proj",
|
25 |
+
"gate_proj",
|
26 |
+
"up_proj",
|
27 |
+
"q_proj",
|
28 |
"k_proj",
|
29 |
+
"v_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 sha256:5799657fa29ba66a19d55699457a6370189eed29c67d55e16fcc50e5df8f68b5
|
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:c6ec952f798a20b0c87b16275c8d1bb48811f389557e46acd2678fbec0833aaa
|
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:d167554ac040f779f3864519ef2bbeef018937be7bbd7fbcf2a7ce8e3cfb0651
|
3 |
size 35697862
|
trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"epoch": 0.
|
3 |
-
"global_step":
|
4 |
"max_steps": 12,
|
5 |
"logging_steps": 10,
|
6 |
"eval_steps": 10,
|
@@ -8,24 +8,8 @@
|
|
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": 6.35,
|
15 |
-
"grad_norm": 0.972251296043396,
|
16 |
-
"learning_rate": 0.0001,
|
17 |
-
"epoch": 0.07407407407407407,
|
18 |
-
"step": 10
|
19 |
-
},
|
20 |
-
{
|
21 |
-
"eval_loss": 0.3447871506214142,
|
22 |
-
"eval_runtime": 368.0618,
|
23 |
-
"eval_samples_per_second": 0.617,
|
24 |
-
"eval_steps_per_second": 0.155,
|
25 |
-
"epoch": 0.07407407407407407,
|
26 |
-
"step": 10
|
27 |
-
}
|
28 |
-
],
|
29 |
"best_metric": null,
|
30 |
"best_model_checkpoint": null,
|
31 |
"is_local_process_zero": true,
|
@@ -36,7 +20,7 @@
|
|
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": 0.037037037037037035,
|
3 |
+
"global_step": 5,
|
4 |
"max_steps": 12,
|
5 |
"logging_steps": 10,
|
6 |
"eval_steps": 10,
|
|
|
8 |
"train_batch_size": 8,
|
9 |
"num_train_epochs": 1,
|
10 |
"num_input_tokens_seen": 0,
|
11 |
+
"total_flos": 2779501332185088.0,
|
12 |
+
"log_history": [],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
"best_metric": null,
|
14 |
"best_model_checkpoint": null,
|
15 |
"is_local_process_zero": true,
|
|
|
20 |
"stateful_callbacks": {
|
21 |
"TrainerControl": {
|
22 |
"args": {
|
23 |
+
"should_training_stop": false,
|
24 |
"should_epoch_stop": false,
|
25 |
"should_save": true,
|
26 |
"should_evaluate": false,
|