sayanbanerjee32
commited on
Commit
•
f54b496
1
Parent(s):
f1395c0
Upload folder using huggingface_hub
Browse files- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- image_projector.pth +2 -2
- lora_weights.pt +1 -1
- trainer_state.json +10 -3
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
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 |
-
"
|
|
|
|
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
|
|
|
|
23 |
"gate_proj",
|
24 |
"down_proj",
|
25 |
+
"v_proj",
|
26 |
+
"o_proj",
|
27 |
+
"q_proj",
|
28 |
+
"up_proj",
|
29 |
+
"k_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:ded5364855d145f720ea7e00dc68cf96967cb2c2a0ce8c86772e68e7294ab5a7
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64fd5e1ea7b8443db753d169bc706acaf8e1a1fca73042f29a25af4323e8528a
|
3 |
+
size 22031128
|
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:ae5b274f8048254edcd77a1bd6b687e9a1d2eb23a8e7d3300614e5d23c63b803
|
3 |
size 35697862
|
trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"epoch": 0.
|
3 |
-
"global_step":
|
4 |
"max_steps": 2146,
|
5 |
"logging_steps": 25,
|
6 |
"eval_steps": 50,
|
@@ -8,7 +8,7 @@
|
|
8 |
"train_batch_size": 8,
|
9 |
"num_train_epochs": 1,
|
10 |
"num_input_tokens_seen": 0,
|
11 |
-
"total_flos": 1.
|
12 |
"log_history": [
|
13 |
{
|
14 |
"loss": 3.9545,
|
@@ -163,6 +163,13 @@
|
|
163 |
"eval_steps_per_second": 0.14,
|
164 |
"epoch": 0.16309412861137,
|
165 |
"step": 350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
166 |
}
|
167 |
],
|
168 |
"best_metric": null,
|
|
|
1 |
{
|
2 |
+
"epoch": 0.17474370922646784,
|
3 |
+
"global_step": 375,
|
4 |
"max_steps": 2146,
|
5 |
"logging_steps": 25,
|
6 |
"eval_steps": 50,
|
|
|
8 |
"train_batch_size": 8,
|
9 |
"num_train_epochs": 1,
|
10 |
"num_input_tokens_seen": 0,
|
11 |
+
"total_flos": 1.73442819438379e+17,
|
12 |
"log_history": [
|
13 |
{
|
14 |
"loss": 3.9545,
|
|
|
163 |
"eval_steps_per_second": 0.14,
|
164 |
"epoch": 0.16309412861137,
|
165 |
"step": 350
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"loss": 198.4288,
|
169 |
+
"grad_norm": NaN,
|
170 |
+
"learning_rate": 5.8139534883720933e-05,
|
171 |
+
"epoch": 0.17474370922646784,
|
172 |
+
"step": 375
|
173 |
}
|
174 |
],
|
175 |
"best_metric": null,
|