End of training
Browse files- README.md +4 -6
- adapter_config.json +2 -5
- adapter_model.safetensors +2 -2
- runs/Feb21_08-55-21_512faa0505b2/events.out.tfevents.1708505722.512faa0505b2.5658.0 +3 -0
- runs/Feb21_08-57-40_512faa0505b2/events.out.tfevents.1708505861.512faa0505b2.5658.1 +3 -0
- runs/Feb21_09-05-59_512faa0505b2/events.out.tfevents.1708506359.512faa0505b2.5658.2 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -2,8 +2,6 @@
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
-
- trl
|
6 |
-
- sft
|
7 |
- generated_from_trainer
|
8 |
base_model: vilsonrodrigues/falcon-7b-instruct-sharded
|
9 |
model-index:
|
@@ -36,15 +34,15 @@ More information needed
|
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 0.0002
|
39 |
-
- train_batch_size:
|
40 |
- eval_batch_size: 8
|
41 |
- seed: 42
|
42 |
- gradient_accumulation_steps: 4
|
43 |
-
- total_train_batch_size:
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: cosine
|
46 |
-
- lr_scheduler_warmup_ratio: 0.
|
47 |
-
-
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
|
|
2 |
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
|
|
5 |
- generated_from_trainer
|
6 |
base_model: vilsonrodrigues/falcon-7b-instruct-sharded
|
7 |
model-index:
|
|
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 0.0002
|
37 |
+
- train_batch_size: 1
|
38 |
- eval_batch_size: 8
|
39 |
- seed: 42
|
40 |
- gradient_accumulation_steps: 4
|
41 |
+
- total_train_batch_size: 4
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: cosine
|
44 |
+
- lr_scheduler_warmup_ratio: 0.05
|
45 |
+
- num_epochs: 10
|
46 |
- mixed_precision_training: Native AMP
|
47 |
|
48 |
### Training results
|
adapter_config.json
CHANGED
@@ -15,14 +15,11 @@
|
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
-
"r":
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"query_key_value",
|
24 |
-
"dense",
|
25 |
-
"dense_4h_to_h"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
28 |
"use_rslora": false
|
|
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
+
"r": 16,
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"query_key_value"
|
|
|
|
|
|
|
23 |
],
|
24 |
"task_type": "CAUSAL_LM",
|
25 |
"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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c941424e554bc50c9bceb7f9ee5d873bd619a4565fb7a6d9f127ce97f4cbc8f
|
3 |
+
size 18883912
|
runs/Feb21_08-55-21_512faa0505b2/events.out.tfevents.1708505722.512faa0505b2.5658.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a880b88705358113bac8359738dcfd3af20e4e0e9c6c04e5bfd1177cc110270
|
3 |
+
size 12468
|
runs/Feb21_08-57-40_512faa0505b2/events.out.tfevents.1708505861.512faa0505b2.5658.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7029a668708f6a855cde142f52c03e65cb7201ebab94f047b9aa68ce100821f2
|
3 |
+
size 37459
|
runs/Feb21_09-05-59_512faa0505b2/events.out.tfevents.1708506359.512faa0505b2.5658.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db3fb15d3799f88c872469f10c971552d22e8e0ec6a4481a5d3d1df415ef6234
|
3 |
+
size 72982
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de9d00e9d163f1d242baf776dbaca2ea6a80ee779389307f42d889e63c5d4cbe
|
3 |
size 4728
|