Upload folder using huggingface_hub
Browse files- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- checkpoint-10/adapter_config.json +2 -2
- checkpoint-10/adapter_model.safetensors +1 -1
- checkpoint-10/optimizer.pt +1 -1
- checkpoint-10/rng_state_0.pth +1 -1
- checkpoint-10/rng_state_1.pth +1 -1
- checkpoint-10/trainer_state.json +6 -6
- checkpoint-10/training_args.bin +1 -1
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -21,8 +21,8 @@
|
|
21 |
"target_modules": [
|
22 |
"k_proj",
|
23 |
"v_proj",
|
24 |
-
"
|
25 |
-
"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
28 |
"use_rslora": false
|
|
|
21 |
"target_modules": [
|
22 |
"k_proj",
|
23 |
"v_proj",
|
24 |
+
"q_proj",
|
25 |
+
"o_proj"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
28 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 27297032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15ae5932d2117a9fe102743dce9227b614a7f7e67bd4612c850f63e7ec055e7c
|
3 |
size 27297032
|
checkpoint-10/adapter_config.json
CHANGED
@@ -21,8 +21,8 @@
|
|
21 |
"target_modules": [
|
22 |
"k_proj",
|
23 |
"v_proj",
|
24 |
-
"
|
25 |
-
"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
28 |
"use_rslora": false
|
|
|
21 |
"target_modules": [
|
22 |
"k_proj",
|
23 |
"v_proj",
|
24 |
+
"q_proj",
|
25 |
+
"o_proj"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
28 |
"use_rslora": false
|
checkpoint-10/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 27297032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15ae5932d2117a9fe102743dce9227b614a7f7e67bd4612c850f63e7ec055e7c
|
3 |
size 27297032
|
checkpoint-10/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 54678010
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01dddfc0dd86a2b4573d485e442360222cc561b471bb2f610b5f44b1c390e9a1
|
3 |
size 54678010
|
checkpoint-10/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:965202796c6aa89694fc280d55ec3a965bdea05297618ca5204beb258f29acbb
|
3 |
size 14512
|
checkpoint-10/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14512
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e64ab752dbb68c5e75ddb592f9ba807f28ad33b4959ba527eed1f91dd74d99d
|
3 |
size 14512
|
checkpoint-10/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
"best_model_checkpoint": "./mistral/29-02-24-Weni-test-folder-upload_Zeroshot-2_max_steps-30_batch_8_2024-02-29_ppid_7/checkpoint-10",
|
4 |
"epoch": 0.006199628022318661,
|
5 |
"eval_steps": 10,
|
@@ -10,10 +10,10 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.01,
|
13 |
-
"eval_loss": 1.
|
14 |
-
"eval_runtime":
|
15 |
-
"eval_samples_per_second": 13.
|
16 |
-
"eval_steps_per_second": 3.
|
17 |
"step": 10
|
18 |
}
|
19 |
],
|
@@ -22,7 +22,7 @@
|
|
22 |
"num_input_tokens_seen": 0,
|
23 |
"num_train_epochs": 1,
|
24 |
"save_steps": 10,
|
25 |
-
"total_flos":
|
26 |
"train_batch_size": 8,
|
27 |
"trial_name": null,
|
28 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.1801708936691284,
|
3 |
"best_model_checkpoint": "./mistral/29-02-24-Weni-test-folder-upload_Zeroshot-2_max_steps-30_batch_8_2024-02-29_ppid_7/checkpoint-10",
|
4 |
"epoch": 0.006199628022318661,
|
5 |
"eval_steps": 10,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.01,
|
13 |
+
"eval_loss": 1.1801708936691284,
|
14 |
+
"eval_runtime": 206.9482,
|
15 |
+
"eval_samples_per_second": 13.854,
|
16 |
+
"eval_steps_per_second": 3.465,
|
17 |
"step": 10
|
18 |
}
|
19 |
],
|
|
|
22 |
"num_input_tokens_seen": 0,
|
23 |
"num_train_epochs": 1,
|
24 |
"save_steps": 10,
|
25 |
+
"total_flos": 4575910770507776.0,
|
26 |
"train_batch_size": 8,
|
27 |
"trial_name": null,
|
28 |
"trial_params": null
|
checkpoint-10/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d4c9c5bf1f39262ed092c14f2781858ebaaf53fd5ab0433213c6b7ee0a70c7c
|
3 |
size 5112
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d4c9c5bf1f39262ed092c14f2781858ebaaf53fd5ab0433213c6b7ee0a70c7c
|
3 |
size 5112
|