Upload folder using huggingface_hub
Browse files- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +15 -8
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -20,10 +20,10 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"gate_up_proj",
|
24 |
"down_proj",
|
|
|
25 |
"o_proj",
|
26 |
-
"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"down_proj",
|
24 |
+
"qkv_proj",
|
25 |
"o_proj",
|
26 |
+
"gate_up_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"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 1671212336
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d9e7e6e58e1602d0fc9f6833921165fd8bd25c5ac6ebd0efc58c7c87a6b5a04
|
3 |
size 1671212336
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 849024805
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26132871b2a91e0812f2f06e1f2c459b1dc72cd527f446516dae0cdc446be458
|
3 |
size 849024805
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14645
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:873f6503ef67b297aff30dbeed96c14a567fc3c35eee7665a905b7c4c1c7eb3d
|
3 |
size 14645
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1465
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70ec5656cb5df7f1d52a61930dc86413e2b7365b3c707692864ddef6e8bfc5ce
|
3 |
size 1465
|
trainer_state.json
CHANGED
@@ -1,23 +1,30 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch":
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 0.
|
15 |
-
"loss":
|
16 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 20,
|
20 |
-
"max_steps":
|
21 |
"num_input_tokens_seen": 0,
|
22 |
"num_train_epochs": 3,
|
23 |
"save_steps": 500,
|
@@ -33,7 +40,7 @@
|
|
33 |
"attributes": {}
|
34 |
}
|
35 |
},
|
36 |
-
"total_flos":
|
37 |
"train_batch_size": 1,
|
38 |
"trial_name": null,
|
39 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.8,
|
13 |
+
"grad_norm": 0.4785412847995758,
|
14 |
+
"learning_rate": 0.00018295745859082095,
|
15 |
+
"loss": 0.9961,
|
16 |
"step": 20
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.6,
|
20 |
+
"grad_norm": 1.4140418767929077,
|
21 |
+
"learning_rate": 0.0001245127148743087,
|
22 |
+
"loss": 0.6728,
|
23 |
+
"step": 40
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 20,
|
27 |
+
"max_steps": 75,
|
28 |
"num_input_tokens_seen": 0,
|
29 |
"num_train_epochs": 3,
|
30 |
"save_steps": 500,
|
|
|
40 |
"attributes": {}
|
41 |
}
|
42 |
},
|
43 |
+
"total_flos": 3.40634643861504e+16,
|
44 |
"train_batch_size": 1,
|
45 |
"trial_name": null,
|
46 |
"trial_params": null
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5905
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e71ce490c35f09b0e4991bd8720f211574a9577ed3b0bdd82bc8ee2e497b310b
|
3 |
size 5905
|