player1537
commited on
Commit
•
b557d4a
1
Parent(s):
961afc6
Training in progress, step 262
Browse files- .gitignore +1 -0
- adapter_config.json +20 -0
- adapter_model.bin +3 -0
- last-checkpoint/README.md +9 -0
- last-checkpoint/adapter_config.json +20 -0
- last-checkpoint/adapter_model.bin +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +82 -0
- last-checkpoint/training_args.bin +3 -0
- runs/Jul30_21-05-41_04d48b04b124/events.out.tfevents.1690751152.04d48b04b124.500.0 +3 -0
- runs/Jul30_21-14-56_04d48b04b124/events.out.tfevents.1690751700.04d48b04b124.3813.0 +3 -0
- runs/Jul30_21-17-36_04d48b04b124/events.out.tfevents.1690751861.04d48b04b124.4697.0 +3 -0
- runs/Jul30_21-20-01_04d48b04b124/events.out.tfevents.1690752006.04d48b04b124.5530.0 +3 -0
- runs/Jul30_21-32-24_04d48b04b124/events.out.tfevents.1690752749.04d48b04b124.8763.0 +3 -0
- runs/Jul30_21-35-26_04d48b04b124/events.out.tfevents.1690752932.04d48b04b124.9743.0 +3 -0
- runs/Jul30_21-38-14_04d48b04b124/events.out.tfevents.1690753098.04d48b04b124.10647.0 +3 -0
- runs/Jul30_21-45-15_04d48b04b124/events.out.tfevents.1690753519.04d48b04b124.12710.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
adapter_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "bigscience/bloom-560m",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"query_key_value"
|
18 |
+
],
|
19 |
+
"task_type": "CAUSAL_LM"
|
20 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb3c4343d5b79891e68e969b5db2e8b5a3bba2fc92883108865dd3097a7d1357
|
3 |
+
size 3163457
|
last-checkpoint/README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
### Framework versions
|
7 |
+
|
8 |
+
|
9 |
+
- PEFT 0.4.0
|
last-checkpoint/adapter_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "bigscience/bloom-560m",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32,
|
11 |
+
"lora_dropout": 0.1,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 8,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"query_key_value"
|
18 |
+
],
|
19 |
+
"task_type": "CAUSAL_LM"
|
20 |
+
}
|
last-checkpoint/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb3c4343d5b79891e68e969b5db2e8b5a3bba2fc92883108865dd3097a7d1357
|
3 |
+
size 3163457
|
last-checkpoint/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8901fba30f9688d20aa8e15379a7066e298045a8bb0b9de8851afdbe035d623
|
3 |
+
size 6319689
|
last-checkpoint/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5063f67e2c88884cab54e05296e5e83ac9a3c954c9e23cfb2d9a21a6c8d8e10
|
3 |
+
size 14639
|
last-checkpoint/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a55327b521b10efdd88cd32140805678860f8977b7eba62e5ac86192f50bb738
|
3 |
+
size 627
|
last-checkpoint/trainer_state.json
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.1501432664756447,
|
5 |
+
"global_step": 262,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 1.9988538681948425e-05,
|
13 |
+
"loss": 3.3001,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.01,
|
18 |
+
"learning_rate": 1.970200573065903e-05,
|
19 |
+
"loss": 2.9734,
|
20 |
+
"step": 26
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.03,
|
24 |
+
"learning_rate": 1.9404011461318052e-05,
|
25 |
+
"loss": 2.9919,
|
26 |
+
"step": 52
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.04,
|
30 |
+
"learning_rate": 1.910601719197708e-05,
|
31 |
+
"loss": 2.9257,
|
32 |
+
"step": 78
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.06,
|
36 |
+
"learning_rate": 1.8808022922636103e-05,
|
37 |
+
"loss": 2.9255,
|
38 |
+
"step": 104
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.07,
|
42 |
+
"learning_rate": 1.851002865329513e-05,
|
43 |
+
"loss": 2.9036,
|
44 |
+
"step": 130
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.09,
|
48 |
+
"learning_rate": 1.8212034383954157e-05,
|
49 |
+
"loss": 2.9194,
|
50 |
+
"step": 156
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.1,
|
54 |
+
"learning_rate": 1.791404011461318e-05,
|
55 |
+
"loss": 2.726,
|
56 |
+
"step": 182
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.12,
|
60 |
+
"learning_rate": 1.7616045845272208e-05,
|
61 |
+
"loss": 2.909,
|
62 |
+
"step": 208
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.13,
|
66 |
+
"learning_rate": 1.7318051575931235e-05,
|
67 |
+
"loss": 2.6554,
|
68 |
+
"step": 234
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.15,
|
72 |
+
"learning_rate": 1.702005730659026e-05,
|
73 |
+
"loss": 2.7529,
|
74 |
+
"step": 260
|
75 |
+
}
|
76 |
+
],
|
77 |
+
"max_steps": 1745,
|
78 |
+
"num_train_epochs": 1,
|
79 |
+
"total_flos": 487908402266112.0,
|
80 |
+
"trial_name": null,
|
81 |
+
"trial_params": null
|
82 |
+
}
|
last-checkpoint/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdb95308720d4497fd5245399d223487b98a1eda7b2b9a7b69e1bde4f1d73925
|
3 |
+
size 4027
|
runs/Jul30_21-05-41_04d48b04b124/events.out.tfevents.1690751152.04d48b04b124.500.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c20881500feccca3d2d296945cc507e31175ea843e4b7a1ea8bf0a06724f867
|
3 |
+
size 4360
|
runs/Jul30_21-14-56_04d48b04b124/events.out.tfevents.1690751700.04d48b04b124.3813.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4d94d3cf419b5b7d692c7e21d94fbb303b1b9ce2731185d69617b1db0310294
|
3 |
+
size 4184
|
runs/Jul30_21-17-36_04d48b04b124/events.out.tfevents.1690751861.04d48b04b124.4697.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78aafbbf60c0b4080c985c4fffd5c85958cedac00749eee2095b1355328b9f30
|
3 |
+
size 4360
|
runs/Jul30_21-20-01_04d48b04b124/events.out.tfevents.1690752006.04d48b04b124.5530.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23a134bbc2dd279a212a51a69f1a33ebb64d547001872a6ea817636252ab3edd
|
3 |
+
size 4360
|
runs/Jul30_21-32-24_04d48b04b124/events.out.tfevents.1690752749.04d48b04b124.8763.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4126998287e67518f71492dc2de7d84dbf62d339ea28666c39f1a6226cfb754a
|
3 |
+
size 4360
|
runs/Jul30_21-35-26_04d48b04b124/events.out.tfevents.1690752932.04d48b04b124.9743.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53ef9bc6e5fee140f904d4b825811e2bdd082e3b4014d28dc07d13dcaca5a4e3
|
3 |
+
size 4360
|
runs/Jul30_21-38-14_04d48b04b124/events.out.tfevents.1690753098.04d48b04b124.10647.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be2d6d5f36a64339a0650fcf3df48c2e171aa3d14c58265055d06a23a9dfcfdf
|
3 |
+
size 4360
|
runs/Jul30_21-45-15_04d48b04b124/events.out.tfevents.1690753519.04d48b04b124.12710.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:862ab2bfec1ac04bfcc6c7b6745e05a9197bf0013e1824069f79c8e70bec11ee
|
3 |
+
size 5915
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdb95308720d4497fd5245399d223487b98a1eda7b2b9a7b69e1bde4f1d73925
|
3 |
+
size 4027
|