Training in progress, epoch 1
Browse files- config.json +1 -1
- model.safetensors +1 -1
- run-0/checkpoint-18/config.json +1 -1
- run-0/checkpoint-18/model.safetensors +1 -1
- run-0/checkpoint-18/optimizer.pt +1 -1
- run-0/checkpoint-18/rng_state.pth +1 -1
- run-0/checkpoint-18/scheduler.pt +1 -1
- run-0/checkpoint-18/trainer_state.json +19 -19
- run-0/checkpoint-18/training_args.bin +1 -1
- run-0/checkpoint-27/config.json +1 -1
- run-0/checkpoint-27/model.safetensors +1 -1
- run-0/checkpoint-27/optimizer.pt +1 -1
- run-0/checkpoint-27/rng_state.pth +1 -1
- run-0/checkpoint-27/scheduler.pt +1 -1
- run-0/checkpoint-27/trainer_state.json +25 -25
- run-0/checkpoint-27/training_args.bin +1 -1
- run-0/checkpoint-36/config.json +1 -1
- run-0/checkpoint-36/model.safetensors +1 -1
- run-0/checkpoint-36/optimizer.pt +1 -1
- run-0/checkpoint-36/rng_state.pth +1 -1
- run-0/checkpoint-36/scheduler.pt +1 -1
- run-0/checkpoint-36/trainer_state.json +31 -31
- run-0/checkpoint-36/training_args.bin +1 -1
- run-0/checkpoint-9/config.json +1 -1
- run-0/checkpoint-9/model.safetensors +1 -1
- run-0/checkpoint-9/optimizer.pt +1 -1
- run-0/checkpoint-9/rng_state.pth +1 -1
- run-0/checkpoint-9/scheduler.pt +1 -1
- run-0/checkpoint-9/trainer_state.json +12 -12
- run-0/checkpoint-9/training_args.bin +1 -1
- run-1/checkpoint-18/config.json +1 -1
- run-1/checkpoint-18/model.safetensors +1 -1
- run-1/checkpoint-18/optimizer.pt +1 -1
- run-1/checkpoint-18/rng_state.pth +2 -2
- run-1/checkpoint-18/scheduler.pt +1 -1
- run-1/checkpoint-18/trainer_state.json +12 -12
- run-1/checkpoint-18/training_args.bin +1 -1
- runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110166.0f0a24039c15.273.2 +3 -0
- runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110209.0f0a24039c15.273.3 +3 -0
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267829484
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a25a8059c3029b9de30789699c137dc8b5ce341a94cb07d79ca20bf334b98b2
|
3 |
size 267829484
|
run-0/checkpoint-18/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
run-0/checkpoint-18/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267829484
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:250e556e5ecae9c440f30ad2f2b5412f125fa67c156fecc1239ac7ed30d3595d
|
3 |
size 267829484
|
run-0/checkpoint-18/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535721146
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc1394e44db87faa7b14ce3a2f7dd51f1c75521dee741b69c852df26046c8701
|
3 |
size 535721146
|
run-0/checkpoint-18/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61d8acc069ff07bdf99f8e314288dd4857d5a8e40efe1eb1479d12cc53a2d060
|
3 |
size 14244
|
run-0/checkpoint-18/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6518bd1ff3a8aabaaccae3c128329d66c13c19a4a3483ccf1540cb5b514a055c
|
3 |
size 1064
|
run-0/checkpoint-18/trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 18,
|
@@ -10,37 +10,37 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss":
|
14 |
-
"eval_pearson": 0.
|
15 |
-
"eval_runtime": 0.
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_spearmanr": 0.
|
18 |
-
"eval_steps_per_second":
|
19 |
"step": 9
|
20 |
},
|
21 |
{
|
22 |
"epoch": 2.0,
|
23 |
-
"eval_loss":
|
24 |
-
"eval_pearson": 0.
|
25 |
-
"eval_runtime":
|
26 |
-
"eval_samples_per_second":
|
27 |
-
"eval_spearmanr": 0.
|
28 |
-
"eval_steps_per_second":
|
29 |
"step": 18
|
30 |
}
|
31 |
],
|
32 |
"logging_steps": 500,
|
33 |
-
"max_steps":
|
34 |
"num_input_tokens_seen": 0,
|
35 |
-
"num_train_epochs":
|
36 |
"save_steps": 500,
|
37 |
"total_flos": 0,
|
38 |
"train_batch_size": 64,
|
39 |
"trial_name": null,
|
40 |
"trial_params": {
|
41 |
-
"learning_rate":
|
42 |
-
"num_train_epochs":
|
43 |
"per_device_train_batch_size": 64,
|
44 |
-
"seed":
|
45 |
}
|
46 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8721480853088006,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-9",
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 18,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.5447242259979248,
|
14 |
+
"eval_pearson": 0.8721480853088006,
|
15 |
+
"eval_runtime": 0.7832,
|
16 |
+
"eval_samples_per_second": 1915.272,
|
17 |
+
"eval_spearmanr": 0.8694199881300932,
|
18 |
+
"eval_steps_per_second": 120.024,
|
19 |
"step": 9
|
20 |
},
|
21 |
{
|
22 |
"epoch": 2.0,
|
23 |
+
"eval_loss": 0.5480599999427795,
|
24 |
+
"eval_pearson": 0.8721355234643248,
|
25 |
+
"eval_runtime": 0.7998,
|
26 |
+
"eval_samples_per_second": 1875.436,
|
27 |
+
"eval_spearmanr": 0.8693922461181149,
|
28 |
+
"eval_steps_per_second": 117.527,
|
29 |
"step": 18
|
30 |
}
|
31 |
],
|
32 |
"logging_steps": 500,
|
33 |
+
"max_steps": 36,
|
34 |
"num_input_tokens_seen": 0,
|
35 |
+
"num_train_epochs": 4,
|
36 |
"save_steps": 500,
|
37 |
"total_flos": 0,
|
38 |
"train_batch_size": 64,
|
39 |
"trial_name": null,
|
40 |
"trial_params": {
|
41 |
+
"learning_rate": 3.1992432473500055e-06,
|
42 |
+
"num_train_epochs": 4,
|
43 |
"per_device_train_batch_size": 64,
|
44 |
+
"seed": 25
|
45 |
}
|
46 |
}
|
run-0/checkpoint-18/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f60e6fcaaa02ec39d4a651a97e61c3bf1d26dfb974d7e291de6d7d5b31621d03
|
3 |
size 4920
|
run-0/checkpoint-27/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
run-0/checkpoint-27/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267829484
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57f7a07c1063c508b3d228e052775539361edffa3120f7ec8c441a206bd36e17
|
3 |
size 267829484
|
run-0/checkpoint-27/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535721146
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:049cb4ad328db832910db524db19174e82c3790dee996e2b4e5635e3017e549a
|
3 |
size 535721146
|
run-0/checkpoint-27/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94416933a34c33d9dc264b88e08186868fbfdcbbebdbe57b68f97fb4f5001a76
|
3 |
size 14244
|
run-0/checkpoint-27/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9711e1024fc5d0c4ccaf04a6f24bb39779ce3008a416334c416310f1561eb05c
|
3 |
size 1064
|
run-0/checkpoint-27/trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-
|
4 |
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 27,
|
@@ -10,47 +10,47 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss":
|
14 |
-
"eval_pearson": 0.
|
15 |
-
"eval_runtime": 0.
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_spearmanr": 0.
|
18 |
-
"eval_steps_per_second":
|
19 |
"step": 9
|
20 |
},
|
21 |
{
|
22 |
"epoch": 2.0,
|
23 |
-
"eval_loss":
|
24 |
-
"eval_pearson": 0.
|
25 |
-
"eval_runtime":
|
26 |
-
"eval_samples_per_second":
|
27 |
-
"eval_spearmanr": 0.
|
28 |
-
"eval_steps_per_second":
|
29 |
"step": 18
|
30 |
},
|
31 |
{
|
32 |
"epoch": 3.0,
|
33 |
-
"eval_loss":
|
34 |
-
"eval_pearson": 0.
|
35 |
-
"eval_runtime":
|
36 |
-
"eval_samples_per_second":
|
37 |
-
"eval_spearmanr": 0.
|
38 |
-
"eval_steps_per_second":
|
39 |
"step": 27
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 500,
|
43 |
-
"max_steps":
|
44 |
"num_input_tokens_seen": 0,
|
45 |
-
"num_train_epochs":
|
46 |
"save_steps": 500,
|
47 |
"total_flos": 0,
|
48 |
"train_batch_size": 64,
|
49 |
"trial_name": null,
|
50 |
"trial_params": {
|
51 |
-
"learning_rate":
|
52 |
-
"num_train_epochs":
|
53 |
"per_device_train_batch_size": 64,
|
54 |
-
"seed":
|
55 |
}
|
56 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8721480853088006,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-9",
|
4 |
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 27,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.5447242259979248,
|
14 |
+
"eval_pearson": 0.8721480853088006,
|
15 |
+
"eval_runtime": 0.7832,
|
16 |
+
"eval_samples_per_second": 1915.272,
|
17 |
+
"eval_spearmanr": 0.8694199881300932,
|
18 |
+
"eval_steps_per_second": 120.024,
|
19 |
"step": 9
|
20 |
},
|
21 |
{
|
22 |
"epoch": 2.0,
|
23 |
+
"eval_loss": 0.5480599999427795,
|
24 |
+
"eval_pearson": 0.8721355234643248,
|
25 |
+
"eval_runtime": 0.7998,
|
26 |
+
"eval_samples_per_second": 1875.436,
|
27 |
+
"eval_spearmanr": 0.8693922461181149,
|
28 |
+
"eval_steps_per_second": 117.527,
|
29 |
"step": 18
|
30 |
},
|
31 |
{
|
32 |
"epoch": 3.0,
|
33 |
+
"eval_loss": 0.5524753332138062,
|
34 |
+
"eval_pearson": 0.8720958832456878,
|
35 |
+
"eval_runtime": 0.8181,
|
36 |
+
"eval_samples_per_second": 1833.518,
|
37 |
+
"eval_spearmanr": 0.8692888421323478,
|
38 |
+
"eval_steps_per_second": 114.9,
|
39 |
"step": 27
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 500,
|
43 |
+
"max_steps": 36,
|
44 |
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 4,
|
46 |
"save_steps": 500,
|
47 |
"total_flos": 0,
|
48 |
"train_batch_size": 64,
|
49 |
"trial_name": null,
|
50 |
"trial_params": {
|
51 |
+
"learning_rate": 3.1992432473500055e-06,
|
52 |
+
"num_train_epochs": 4,
|
53 |
"per_device_train_batch_size": 64,
|
54 |
+
"seed": 25
|
55 |
}
|
56 |
}
|
run-0/checkpoint-27/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f60e6fcaaa02ec39d4a651a97e61c3bf1d26dfb974d7e291de6d7d5b31621d03
|
3 |
size 4920
|
run-0/checkpoint-36/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
run-0/checkpoint-36/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267829484
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99130246f850b335d16368056f449bcf22e5f0ac4608fd37c6ce45301896260e
|
3 |
size 267829484
|
run-0/checkpoint-36/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535721146
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3444f61430e39e85436c8651941ccf15a7102ca6e0df3e906b7bb1a59cda6a38
|
3 |
size 535721146
|
run-0/checkpoint-36/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb8170a1ecebb86f83c3c63adfe7ec6b60b173d1e2760643f11a339ed5fc9145
|
3 |
size 14244
|
run-0/checkpoint-36/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8bc4e4a4c4c97266dd280160c5cbd6b7a2031b23f141764dcc7d3246e73dd9ab
|
3 |
size 1064
|
run-0/checkpoint-36/trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-
|
4 |
"epoch": 4.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 36,
|
@@ -10,57 +10,57 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss":
|
14 |
-
"eval_pearson": 0.
|
15 |
-
"eval_runtime": 0.
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_spearmanr": 0.
|
18 |
-
"eval_steps_per_second":
|
19 |
"step": 9
|
20 |
},
|
21 |
{
|
22 |
"epoch": 2.0,
|
23 |
-
"eval_loss":
|
24 |
-
"eval_pearson": 0.
|
25 |
-
"eval_runtime":
|
26 |
-
"eval_samples_per_second":
|
27 |
-
"eval_spearmanr": 0.
|
28 |
-
"eval_steps_per_second":
|
29 |
"step": 18
|
30 |
},
|
31 |
{
|
32 |
"epoch": 3.0,
|
33 |
-
"eval_loss":
|
34 |
-
"eval_pearson": 0.
|
35 |
-
"eval_runtime":
|
36 |
-
"eval_samples_per_second":
|
37 |
-
"eval_spearmanr": 0.
|
38 |
-
"eval_steps_per_second":
|
39 |
"step": 27
|
40 |
},
|
41 |
{
|
42 |
"epoch": 4.0,
|
43 |
-
"eval_loss":
|
44 |
-
"eval_pearson": 0.
|
45 |
-
"eval_runtime":
|
46 |
-
"eval_samples_per_second":
|
47 |
-
"eval_spearmanr": 0.
|
48 |
-
"eval_steps_per_second":
|
49 |
"step": 36
|
50 |
}
|
51 |
],
|
52 |
"logging_steps": 500,
|
53 |
-
"max_steps":
|
54 |
"num_input_tokens_seen": 0,
|
55 |
-
"num_train_epochs":
|
56 |
"save_steps": 500,
|
57 |
"total_flos": 0,
|
58 |
"train_batch_size": 64,
|
59 |
"trial_name": null,
|
60 |
"trial_params": {
|
61 |
-
"learning_rate":
|
62 |
-
"num_train_epochs":
|
63 |
"per_device_train_batch_size": 64,
|
64 |
-
"seed":
|
65 |
}
|
66 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8721480853088006,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-9",
|
4 |
"epoch": 4.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 36,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.5447242259979248,
|
14 |
+
"eval_pearson": 0.8721480853088006,
|
15 |
+
"eval_runtime": 0.7832,
|
16 |
+
"eval_samples_per_second": 1915.272,
|
17 |
+
"eval_spearmanr": 0.8694199881300932,
|
18 |
+
"eval_steps_per_second": 120.024,
|
19 |
"step": 9
|
20 |
},
|
21 |
{
|
22 |
"epoch": 2.0,
|
23 |
+
"eval_loss": 0.5480599999427795,
|
24 |
+
"eval_pearson": 0.8721355234643248,
|
25 |
+
"eval_runtime": 0.7998,
|
26 |
+
"eval_samples_per_second": 1875.436,
|
27 |
+
"eval_spearmanr": 0.8693922461181149,
|
28 |
+
"eval_steps_per_second": 117.527,
|
29 |
"step": 18
|
30 |
},
|
31 |
{
|
32 |
"epoch": 3.0,
|
33 |
+
"eval_loss": 0.5524753332138062,
|
34 |
+
"eval_pearson": 0.8720958832456878,
|
35 |
+
"eval_runtime": 0.8181,
|
36 |
+
"eval_samples_per_second": 1833.518,
|
37 |
+
"eval_spearmanr": 0.8692888421323478,
|
38 |
+
"eval_steps_per_second": 114.9,
|
39 |
"step": 27
|
40 |
},
|
41 |
{
|
42 |
"epoch": 4.0,
|
43 |
+
"eval_loss": 0.551840603351593,
|
44 |
+
"eval_pearson": 0.8720820978778318,
|
45 |
+
"eval_runtime": 0.8121,
|
46 |
+
"eval_samples_per_second": 1847.035,
|
47 |
+
"eval_spearmanr": 0.8692799150799397,
|
48 |
+
"eval_steps_per_second": 115.748,
|
49 |
"step": 36
|
50 |
}
|
51 |
],
|
52 |
"logging_steps": 500,
|
53 |
+
"max_steps": 36,
|
54 |
"num_input_tokens_seen": 0,
|
55 |
+
"num_train_epochs": 4,
|
56 |
"save_steps": 500,
|
57 |
"total_flos": 0,
|
58 |
"train_batch_size": 64,
|
59 |
"trial_name": null,
|
60 |
"trial_params": {
|
61 |
+
"learning_rate": 3.1992432473500055e-06,
|
62 |
+
"num_train_epochs": 4,
|
63 |
"per_device_train_batch_size": 64,
|
64 |
+
"seed": 25
|
65 |
}
|
66 |
}
|
run-0/checkpoint-36/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f60e6fcaaa02ec39d4a651a97e61c3bf1d26dfb974d7e291de6d7d5b31621d03
|
3 |
size 4920
|
run-0/checkpoint-9/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
run-0/checkpoint-9/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267829484
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e39a74e3412b7ce246af399e46ae105919f882a446102bcaf23e220168790195
|
3 |
size 267829484
|
run-0/checkpoint-9/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535721146
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c08dd262e470e0524997cb67fb2e3a4c2db33dd0edd707187872dd19ba15a24d
|
3 |
size 535721146
|
run-0/checkpoint-9/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1c477474348c1df62a9084b72b01c804768024f0fbdc61c346010f9d1b10922
|
3 |
size 14244
|
run-0/checkpoint-9/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d63b663be8c07f0ce81b50e045f2c99645bc25fac3d7678962e0b549daa6a8a
|
3 |
size 1064
|
run-0/checkpoint-9/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-9",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
@@ -10,27 +10,27 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss":
|
14 |
-
"eval_pearson": 0.
|
15 |
-
"eval_runtime": 0.
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_spearmanr": 0.
|
18 |
-
"eval_steps_per_second":
|
19 |
"step": 9
|
20 |
}
|
21 |
],
|
22 |
"logging_steps": 500,
|
23 |
-
"max_steps":
|
24 |
"num_input_tokens_seen": 0,
|
25 |
-
"num_train_epochs":
|
26 |
"save_steps": 500,
|
27 |
"total_flos": 0,
|
28 |
"train_batch_size": 64,
|
29 |
"trial_name": null,
|
30 |
"trial_params": {
|
31 |
-
"learning_rate":
|
32 |
-
"num_train_epochs":
|
33 |
"per_device_train_batch_size": 64,
|
34 |
-
"seed":
|
35 |
}
|
36 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8721480853088006,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-0/checkpoint-9",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.5447242259979248,
|
14 |
+
"eval_pearson": 0.8721480853088006,
|
15 |
+
"eval_runtime": 0.7832,
|
16 |
+
"eval_samples_per_second": 1915.272,
|
17 |
+
"eval_spearmanr": 0.8694199881300932,
|
18 |
+
"eval_steps_per_second": 120.024,
|
19 |
"step": 9
|
20 |
}
|
21 |
],
|
22 |
"logging_steps": 500,
|
23 |
+
"max_steps": 36,
|
24 |
"num_input_tokens_seen": 0,
|
25 |
+
"num_train_epochs": 4,
|
26 |
"save_steps": 500,
|
27 |
"total_flos": 0,
|
28 |
"train_batch_size": 64,
|
29 |
"trial_name": null,
|
30 |
"trial_params": {
|
31 |
+
"learning_rate": 3.1992432473500055e-06,
|
32 |
+
"num_train_epochs": 4,
|
33 |
"per_device_train_batch_size": 64,
|
34 |
+
"seed": 25
|
35 |
}
|
36 |
}
|
run-0/checkpoint-9/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f60e6fcaaa02ec39d4a651a97e61c3bf1d26dfb974d7e291de6d7d5b31621d03
|
3 |
size 4920
|
run-1/checkpoint-18/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
run-1/checkpoint-18/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267829484
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a25a8059c3029b9de30789699c137dc8b5ce341a94cb07d79ca20bf334b98b2
|
3 |
size 267829484
|
run-1/checkpoint-18/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535721146
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11c39a820456e5835a872fdfc74c59117037bc93fba03a5357f8df563755d701
|
3 |
size 535721146
|
run-1/checkpoint-18/rng_state.pth
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 sha256:38d9c8211eaefc1de952192b16ec0ad898149980c1c189259271b0fe27693dff
|
3 |
+
size 14244
|
run-1/checkpoint-18/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16e3964de5e9a4cac9c51d262db82d939d6ab3cbc33cf27a50e6f5d3f0cf52da
|
3 |
size 1064
|
run-1/checkpoint-18/trainer_state.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-18",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
@@ -10,27 +10,27 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
-
"eval_loss":
|
14 |
-
"eval_pearson": 0.
|
15 |
-
"eval_runtime": 0.
|
16 |
-
"eval_samples_per_second":
|
17 |
-
"eval_spearmanr": 0.
|
18 |
-
"eval_steps_per_second":
|
19 |
"step": 18
|
20 |
}
|
21 |
],
|
22 |
"logging_steps": 500,
|
23 |
-
"max_steps":
|
24 |
"num_input_tokens_seen": 0,
|
25 |
-
"num_train_epochs":
|
26 |
"save_steps": 500,
|
27 |
"total_flos": 0,
|
28 |
"train_batch_size": 32,
|
29 |
"trial_name": null,
|
30 |
"trial_params": {
|
31 |
-
"learning_rate":
|
32 |
-
"num_train_epochs":
|
33 |
"per_device_train_batch_size": 32,
|
34 |
-
"seed":
|
35 |
}
|
36 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8691249759376469,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-18",
|
4 |
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.557124674320221,
|
14 |
+
"eval_pearson": 0.8691249759376469,
|
15 |
+
"eval_runtime": 0.7812,
|
16 |
+
"eval_samples_per_second": 1920.155,
|
17 |
+
"eval_spearmanr": 0.8666509292845571,
|
18 |
+
"eval_steps_per_second": 120.33,
|
19 |
"step": 18
|
20 |
}
|
21 |
],
|
22 |
"logging_steps": 500,
|
23 |
+
"max_steps": 72,
|
24 |
"num_input_tokens_seen": 0,
|
25 |
+
"num_train_epochs": 4,
|
26 |
"save_steps": 500,
|
27 |
"total_flos": 0,
|
28 |
"train_batch_size": 32,
|
29 |
"trial_name": null,
|
30 |
"trial_params": {
|
31 |
+
"learning_rate": 7.44467340014099e-06,
|
32 |
+
"num_train_epochs": 4,
|
33 |
"per_device_train_batch_size": 32,
|
34 |
+
"seed": 30
|
35 |
}
|
36 |
}
|
run-1/checkpoint-18/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8bbecda551ee7774c80dd57136f1f1d264226e7fa9fd5f1198bdad5c555c247
|
3 |
size 4920
|
runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110166.0f0a24039c15.273.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20da40305ac9cb0da0e16503277b2787835958cc23e488d4dc715582e182d309
|
3 |
+
size 6531
|
runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110209.0f0a24039c15.273.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70ff2b6dd32dda34d84eed876ca4506798f04db6ec7261b2cf9312b1fa41de9f
|
3 |
+
size 6529
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8bbecda551ee7774c80dd57136f1f1d264226e7fa9fd5f1198bdad5c555c247
|
3 |
size 4920
|