Commit
·
1633930
1
Parent(s):
622b31a
Upload 16 files
Browse files- ToxicityModel.ipynb +0 -0
- ToxicityModel_emissions.csv +1 -1
- config.json +3 -3
- hatecheck_portuguese_eval.parquet +2 -2
- model.safetensors +3 -0
- optimizer.pt +2 -2
- pytorch_model.bin +2 -2
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- tokenizer.json +2 -2
- told_br_eval.parquet +2 -2
- trainer_state.json +17 -26
- training_args.bin +2 -2
ToxicityModel.ipynb
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
ToxicityModel_emissions.csv
CHANGED
@@ -1,2 +1,2 @@
|
|
1 |
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
2 |
-
2023-
|
|
|
1 |
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
2 |
+
2023-08-30T22:38:52,ToxicityModelPT_emissions,4f01ba2f-c660-4807-804c-38ce233554b9,839.0415558815002,0.03882264552525452,4.627022970807126e-05,42.5,244.43829717531244,31.305280208587646,0.009904010806812183,0.062368301561268,0.0072925608127904825,0.07956487318087073,Singapore,SGP,,,,Linux-5.15.109+-x86_64-with-glibc2.35,3.10.12,2.3.1,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,103.8547,1.2929,83.48074722290039,machine,N,1.0
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
@@ -10,12 +10,12 @@
|
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
-
"0": "
|
14 |
},
|
15 |
"initializer_range": 0.02,
|
16 |
"intermediate_size": 3072,
|
17 |
"label2id": {
|
18 |
-
"
|
19 |
},
|
20 |
"layer_norm_eps": 1e-12,
|
21 |
"max_position_embeddings": 512,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "./",
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
|
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
+
"0": "LABEL_0"
|
14 |
},
|
15 |
"initializer_range": 0.02,
|
16 |
"intermediate_size": 3072,
|
17 |
"label2id": {
|
18 |
+
"LABEL_0": 0
|
19 |
},
|
20 |
"layer_norm_eps": 1e-12,
|
21 |
"max_position_embeddings": 512,
|
hatecheck_portuguese_eval.parquet
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 sha256:771a5563f564fb37f748dbb786f9137852bf6a3073cb6e809aa6b3f317f7e19e
|
3 |
+
size 88458
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e530f3364b2775924cf816b8311ca75633aa95a3194265358ba6179a6479476d
|
3 |
+
size 435723340
|
optimizer.pt
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:a7c488b6db398ef0697c68608e9d4c505b42eb815e143df10c2d4228e0f3459f
|
3 |
+
size 871558917
|
pytorch_model.bin
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:fb1fc3b90d2d9b1d7f3c23448a0ecdbaf7d3b9e3ea5391df2a8dd3fe45451639
|
3 |
+
size 435764017
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47c7bc294f7681acc46c1e4f836260052b87b62038e513f436ac65635b46b3d6
|
3 |
size 14575
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:133e1b303b40bc0ac7b8746676795707c8bfd57280d5ac77b652ba71fbb40b42
|
3 |
size 627
|
tokenizer.json
CHANGED
@@ -2,13 +2,13 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
-
"Fixed":
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 400,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
+
"Fixed": 400
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
told_br_eval.parquet
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 sha256:90bcbaffa95d6565373790c39626eb5c5cb9bb13b1175b7c5352ad94db20ddd1
|
3 |
+
size 160374
|
trainer_state.json
CHANGED
@@ -1,45 +1,36 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
5 |
-
"
|
|
|
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.
|
12 |
-
"learning_rate": 3.
|
13 |
-
"loss": 0.
|
14 |
"step": 200
|
15 |
},
|
16 |
{
|
17 |
-
"epoch": 0
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"eval_runtime": 39.2999,
|
21 |
-
"eval_samples_per_second": 106.438,
|
22 |
-
"eval_steps_per_second": 2.545,
|
23 |
-
"step": 200
|
24 |
-
},
|
25 |
-
{
|
26 |
-
"epoch": 1.34,
|
27 |
-
"learning_rate": 2.770345596432553e-05,
|
28 |
-
"loss": 0.1738,
|
29 |
"step": 400
|
30 |
},
|
31 |
{
|
32 |
-
"epoch": 1.
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"eval_samples_per_second": 106.513,
|
37 |
-
"eval_steps_per_second": 2.546,
|
38 |
-
"step": 400
|
39 |
}
|
40 |
],
|
41 |
-
"
|
42 |
-
"
|
|
|
|
|
43 |
"total_flos": 0.0,
|
44 |
"trial_name": null,
|
45 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.5037593984962405,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.5,
|
13 |
+
"learning_rate": 3.3333333333333335e-05,
|
14 |
+
"loss": 0.2832,
|
15 |
"step": 200
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 1.0,
|
19 |
+
"learning_rate": 1.6666666666666667e-05,
|
20 |
+
"loss": 0.219,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"step": 400
|
22 |
},
|
23 |
{
|
24 |
+
"epoch": 1.5,
|
25 |
+
"learning_rate": 0.0,
|
26 |
+
"loss": 0.1236,
|
27 |
+
"step": 600
|
|
|
|
|
|
|
28 |
}
|
29 |
],
|
30 |
+
"logging_steps": 200,
|
31 |
+
"max_steps": 600,
|
32 |
+
"num_train_epochs": 2,
|
33 |
+
"save_steps": 200,
|
34 |
"total_flos": 0.0,
|
35 |
"trial_name": null,
|
36 |
"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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f3230e9176ed745792c1cff989f66641a97ab7205c03cfb75ee71fc123994f2
|
3 |
+
size 4091
|