End of training
Browse files- README.md +3 -3
- adapter_config.json +8 -2
- adapter_model.safetensors +3 -0
- runs/Nov19_10-37-54_ruche-gpu15.cluster/events.out.tfevents.1700386683.ruche-gpu15.cluster.25952.0 +3 -0
- runs/Nov19_11-22-22_ruche-gpu19.cluster/events.out.tfevents.1700389353.ruche-gpu19.cluster.11052.0 +3 -0
- runs/Nov19_11-30-00_ruche-gpu19.cluster/events.out.tfevents.1700389803.ruche-gpu19.cluster.14164.0 +3 -0
- runs/Nov19_11-33-15_ruche-gpu19.cluster/events.out.tfevents.1700389998.ruche-gpu19.cluster.15552.0 +3 -0
- tokenizer.json +1 -6
- training_args.bin +1 -1
README.md
CHANGED
@@ -31,15 +31,15 @@ More information needed
|
|
31 |
|
32 |
The following hyperparameters were used during training:
|
33 |
- learning_rate: 5e-05
|
34 |
-
- train_batch_size:
|
35 |
- eval_batch_size: 8
|
36 |
- seed: 42
|
37 |
-
- gradient_accumulation_steps:
|
38 |
- total_train_batch_size: 16
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: cosine
|
41 |
- lr_scheduler_warmup_ratio: 0.1
|
42 |
-
- num_epochs:
|
43 |
- mixed_precision_training: Native AMP
|
44 |
|
45 |
### Training results
|
|
|
31 |
|
32 |
The following hyperparameters were used during training:
|
33 |
- learning_rate: 5e-05
|
34 |
+
- train_batch_size: 4
|
35 |
- eval_batch_size: 8
|
36 |
- seed: 42
|
37 |
+
- gradient_accumulation_steps: 4
|
38 |
- total_train_batch_size: 16
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: cosine
|
41 |
- lr_scheduler_warmup_ratio: 0.1
|
42 |
+
- num_epochs: 2
|
43 |
- mixed_precision_training: Native AMP
|
44 |
|
45 |
### Training results
|
adapter_config.json
CHANGED
@@ -1,17 +1,23 @@
|
|
1 |
{
|
|
|
|
|
2 |
"base_model_name_or_path": "../croissant_models/DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small5+UseDeepSpeed.true+UseExternal.falsehalf/",
|
3 |
"bias": "none",
|
4 |
"fan_in_fan_out": false,
|
5 |
"inference_mode": true,
|
6 |
"init_lora_weights": true,
|
|
|
|
|
7 |
"lora_alpha": 32,
|
8 |
"lora_dropout": 0.05,
|
9 |
"modules_to_save": null,
|
10 |
"peft_type": "LORA",
|
11 |
"r": 16,
|
|
|
|
|
12 |
"target_modules": [
|
13 |
-
"
|
14 |
-
"
|
15 |
],
|
16 |
"task_type": "CAUSAL_LM"
|
17 |
}
|
|
|
1 |
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
"base_model_name_or_path": "../croissant_models/DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small5+UseDeepSpeed.true+UseExternal.falsehalf/",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
8 |
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
"lora_alpha": 32,
|
12 |
"lora_dropout": 0.05,
|
13 |
"modules_to_save": null,
|
14 |
"peft_type": "LORA",
|
15 |
"r": 16,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"v_proj",
|
20 |
+
"q_proj"
|
21 |
],
|
22 |
"task_type": "CAUSAL_LM"
|
23 |
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91055d3540a291c79f755bb9a543aa63944b9df77ce135980eb4d75321cd0936
|
3 |
+
size 12595704
|
runs/Nov19_10-37-54_ruche-gpu15.cluster/events.out.tfevents.1700386683.ruche-gpu15.cluster.25952.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8167e7ca94897d292e28351e34b215bd6623991e13f9b937a9225b4ced923120
|
3 |
+
size 20975
|
runs/Nov19_11-22-22_ruche-gpu19.cluster/events.out.tfevents.1700389353.ruche-gpu19.cluster.11052.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3abc5cbbf6bbaf785f938cbc986f22aeea439c7bfab5202bf65ecd55be389cb0
|
3 |
+
size 7473
|
runs/Nov19_11-30-00_ruche-gpu19.cluster/events.out.tfevents.1700389803.ruche-gpu19.cluster.14164.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6bd85b2fb086625f2ee546bc58cd627dbd46d1ad47d5b374f9b3202bc434817
|
3 |
+
size 4369
|
runs/Nov19_11-33-15_ruche-gpu19.cluster/events.out.tfevents.1700389998.ruche-gpu19.cluster.15552.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1066310f78bd045b6f769521b1781f76c8059dbd969a3172dd5a99550a31fe0
|
3 |
+
size 19759
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 1024,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4155
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6382eb0e7fd5b980de0de4099192ab393248e9bd59433fdd6a7ad2c60ee837a0
|
3 |
size 4155
|