Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-1/checkpoint-36/config.json +1 -1
- run-1/checkpoint-36/model.safetensors +1 -1
- run-1/checkpoint-36/optimizer.pt +1 -1
- run-1/checkpoint-36/rng_state.pth +2 -2
- run-1/checkpoint-36/scheduler.pt +1 -1
- run-1/checkpoint-36/trainer_state.json +19 -19
- run-1/checkpoint-36/training_args.bin +1 -1
- run-1/checkpoint-54/config.json +1 -1
- run-1/checkpoint-54/model.safetensors +1 -1
- run-1/checkpoint-54/optimizer.pt +1 -1
- run-1/checkpoint-54/rng_state.pth +2 -2
- run-1/checkpoint-54/scheduler.pt +1 -1
- run-1/checkpoint-54/trainer_state.json +24 -24
- run-1/checkpoint-54/training_args.bin +1 -1
- run-1/checkpoint-72/config.json +1 -1
- run-1/checkpoint-72/model.safetensors +1 -1
- run-1/checkpoint-72/optimizer.pt +1 -1
- run-1/checkpoint-72/rng_state.pth +1 -1
- run-1/checkpoint-72/scheduler.pt +1 -1
- run-1/checkpoint-72/trainer_state.json +43 -13
- run-1/checkpoint-72/training_args.bin +1 -1
- run-2/checkpoint-144/config.json +1 -1
- run-2/checkpoint-144/model.safetensors +1 -1
- run-2/checkpoint-144/optimizer.pt +1 -1
- run-2/checkpoint-144/rng_state.pth +2 -2
- run-2/checkpoint-144/scheduler.pt +1 -1
- run-2/checkpoint-144/trainer_state.json +15 -45
- run-2/checkpoint-144/training_args.bin +1 -1
- runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110291.0f0a24039c15.273.4 +3 -0
- training_args.bin +1 -1
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:e3a1eb309bec98e4c0bf7dfee033a0074f1dde2d1f2ad466a0454ff6be9c67fd
|
3 |
size 267829484
|
run-1/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-1/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 sha256:8fce7fd94d9aa9ee2e72ccc9878f25c8a5d30b856594e58faa20f893cd362005
|
3 |
size 267829484
|
run-1/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:c0a8f5042fe84dc19a93b01885cf29ca4ba9f632352ac0655469290de35980be
|
3 |
size 535721146
|
run-1/checkpoint-36/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 sha256:763dc2936cffbb83623d0ff45da566347251e3a91775ab2c2f890cd3bfb51264
|
3 |
+
size 14244
|
run-1/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 sha256:694314996efb1877aa61a45d179b77a8f24e61fc5567f5cdb506339b9ef5587d
|
3 |
size 1064
|
run-1/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-1/checkpoint-
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 36,
|
@@ -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": 18
|
20 |
},
|
21 |
{
|
22 |
"epoch": 2.0,
|
23 |
-
"eval_loss":
|
24 |
-
"eval_pearson": 0.
|
25 |
-
"eval_runtime": 0.
|
26 |
-
"eval_samples_per_second":
|
27 |
-
"eval_spearmanr": 0.
|
28 |
-
"eval_steps_per_second":
|
29 |
"step": 36
|
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": 32,
|
39 |
"trial_name": null,
|
40 |
"trial_params": {
|
41 |
-
"learning_rate":
|
42 |
-
"num_train_epochs":
|
43 |
"per_device_train_batch_size": 32,
|
44 |
-
"seed":
|
45 |
}
|
46 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8700848426046829,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-36",
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 36,
|
|
|
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 |
"epoch": 2.0,
|
23 |
+
"eval_loss": 0.5615702271461487,
|
24 |
+
"eval_pearson": 0.8700848426046829,
|
25 |
+
"eval_runtime": 0.7956,
|
26 |
+
"eval_samples_per_second": 1885.306,
|
27 |
+
"eval_spearmanr": 0.8669432177419766,
|
28 |
+
"eval_steps_per_second": 118.146,
|
29 |
"step": 36
|
30 |
}
|
31 |
],
|
32 |
"logging_steps": 500,
|
33 |
+
"max_steps": 72,
|
34 |
"num_input_tokens_seen": 0,
|
35 |
+
"num_train_epochs": 4,
|
36 |
"save_steps": 500,
|
37 |
"total_flos": 0,
|
38 |
"train_batch_size": 32,
|
39 |
"trial_name": null,
|
40 |
"trial_params": {
|
41 |
+
"learning_rate": 7.44467340014099e-06,
|
42 |
+
"num_train_epochs": 4,
|
43 |
"per_device_train_batch_size": 32,
|
44 |
+
"seed": 30
|
45 |
}
|
46 |
}
|
run-1/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:d8bbecda551ee7774c80dd57136f1f1d264226e7fa9fd5f1198bdad5c555c247
|
3 |
size 4920
|
run-1/checkpoint-54/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-54/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 sha256:92cf87857417fd5a271ff8e3f7f05cb8f2b3bf9ced6ab19218e0d44292e6e573
|
3 |
size 267829484
|
run-1/checkpoint-54/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 sha256:602377490593dd37cc80e0dfaed2a31800416f9f3dd72174f881cf2bc10a80d3
|
3 |
size 535721146
|
run-1/checkpoint-54/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 sha256:68f892555cbc4056068c9e64ae67a38154f7c60b59e48ad5d5c1ac881101373b
|
3 |
+
size 14244
|
run-1/checkpoint-54/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 sha256:237de7348e4b2b8379bbb720c2de796479774aa723e7c98c8e4695ddf53e3654
|
3 |
size 1064
|
run-1/checkpoint-54/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-54",
|
4 |
"epoch": 3.0,
|
5 |
"eval_steps": 500,
|
@@ -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": 18
|
20 |
},
|
21 |
{
|
22 |
"epoch": 2.0,
|
23 |
-
"eval_loss":
|
24 |
-
"eval_pearson": 0.
|
25 |
-
"eval_runtime": 0.
|
26 |
-
"eval_samples_per_second":
|
27 |
-
"eval_spearmanr": 0.
|
28 |
-
"eval_steps_per_second":
|
29 |
"step": 36
|
30 |
},
|
31 |
{
|
32 |
"epoch": 3.0,
|
33 |
-
"eval_loss": 0.
|
34 |
-
"eval_pearson": 0.
|
35 |
-
"eval_runtime": 0.
|
36 |
-
"eval_samples_per_second":
|
37 |
-
"eval_spearmanr": 0.
|
38 |
-
"eval_steps_per_second":
|
39 |
"step": 54
|
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": 32,
|
49 |
"trial_name": null,
|
50 |
"trial_params": {
|
51 |
-
"learning_rate":
|
52 |
-
"num_train_epochs":
|
53 |
"per_device_train_batch_size": 32,
|
54 |
-
"seed":
|
55 |
}
|
56 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8703279305082289,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-54",
|
4 |
"epoch": 3.0,
|
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 |
"epoch": 2.0,
|
23 |
+
"eval_loss": 0.5615702271461487,
|
24 |
+
"eval_pearson": 0.8700848426046829,
|
25 |
+
"eval_runtime": 0.7956,
|
26 |
+
"eval_samples_per_second": 1885.306,
|
27 |
+
"eval_spearmanr": 0.8669432177419766,
|
28 |
+
"eval_steps_per_second": 118.146,
|
29 |
"step": 36
|
30 |
},
|
31 |
{
|
32 |
"epoch": 3.0,
|
33 |
+
"eval_loss": 0.5521649718284607,
|
34 |
+
"eval_pearson": 0.8703279305082289,
|
35 |
+
"eval_runtime": 0.7876,
|
36 |
+
"eval_samples_per_second": 1904.585,
|
37 |
+
"eval_spearmanr": 0.8674130106513307,
|
38 |
+
"eval_steps_per_second": 119.354,
|
39 |
"step": 54
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 500,
|
43 |
+
"max_steps": 72,
|
44 |
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 4,
|
46 |
"save_steps": 500,
|
47 |
"total_flos": 0,
|
48 |
"train_batch_size": 32,
|
49 |
"trial_name": null,
|
50 |
"trial_params": {
|
51 |
+
"learning_rate": 7.44467340014099e-06,
|
52 |
+
"num_train_epochs": 4,
|
53 |
"per_device_train_batch_size": 32,
|
54 |
+
"seed": 30
|
55 |
}
|
56 |
}
|
run-1/checkpoint-54/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
|
run-1/checkpoint-72/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-72/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 sha256:09010ab4aec3f4314a6fbf19d5d86f50e152065c1bdbf728595e8144b34007e0
|
3 |
size 267829484
|
run-1/checkpoint-72/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:c87e402023ea08da918ecf79e43f22a594af2d86d852fabd48fc9b30c4cdc883
|
3 |
size 535721146
|
run-1/checkpoint-72/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 sha256:16a65aa2435b210924c288e0d36fb69e0b9ec9a6eedd973dd78c384345eb5385
|
3 |
size 14244
|
run-1/checkpoint-72/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 sha256:550af093d9b55e6aceb90b4bf22d2d160e1129317cef30da18d37429cab377a7
|
3 |
size 1064
|
run-1/checkpoint-72/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-72",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 72,
|
7 |
"is_hyper_param_search": true,
|
@@ -10,27 +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": 72
|
20 |
}
|
21 |
],
|
22 |
"logging_steps": 500,
|
23 |
-
"max_steps":
|
24 |
"num_input_tokens_seen": 0,
|
25 |
"num_train_epochs": 4,
|
26 |
"save_steps": 500,
|
27 |
"total_flos": 0,
|
28 |
-
"train_batch_size":
|
29 |
"trial_name": null,
|
30 |
"trial_params": {
|
31 |
-
"learning_rate":
|
32 |
"num_train_epochs": 4,
|
33 |
-
"per_device_train_batch_size":
|
34 |
-
"seed":
|
35 |
}
|
36 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8705613575789081,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-72",
|
4 |
+
"epoch": 4.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 72,
|
7 |
"is_hyper_param_search": true,
|
|
|
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 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 0.5615702271461487,
|
24 |
+
"eval_pearson": 0.8700848426046829,
|
25 |
+
"eval_runtime": 0.7956,
|
26 |
+
"eval_samples_per_second": 1885.306,
|
27 |
+
"eval_spearmanr": 0.8669432177419766,
|
28 |
+
"eval_steps_per_second": 118.146,
|
29 |
+
"step": 36
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 3.0,
|
33 |
+
"eval_loss": 0.5521649718284607,
|
34 |
+
"eval_pearson": 0.8703279305082289,
|
35 |
+
"eval_runtime": 0.7876,
|
36 |
+
"eval_samples_per_second": 1904.585,
|
37 |
+
"eval_spearmanr": 0.8674130106513307,
|
38 |
+
"eval_steps_per_second": 119.354,
|
39 |
+
"step": 54
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 4.0,
|
43 |
+
"eval_loss": 0.5556716322898865,
|
44 |
+
"eval_pearson": 0.8705613575789081,
|
45 |
+
"eval_runtime": 0.8109,
|
46 |
+
"eval_samples_per_second": 1849.903,
|
47 |
+
"eval_spearmanr": 0.8677375225591853,
|
48 |
+
"eval_steps_per_second": 115.927,
|
49 |
"step": 72
|
50 |
}
|
51 |
],
|
52 |
"logging_steps": 500,
|
53 |
+
"max_steps": 72,
|
54 |
"num_input_tokens_seen": 0,
|
55 |
"num_train_epochs": 4,
|
56 |
"save_steps": 500,
|
57 |
"total_flos": 0,
|
58 |
+
"train_batch_size": 32,
|
59 |
"trial_name": null,
|
60 |
"trial_params": {
|
61 |
+
"learning_rate": 7.44467340014099e-06,
|
62 |
"num_train_epochs": 4,
|
63 |
+
"per_device_train_batch_size": 32,
|
64 |
+
"seed": 30
|
65 |
}
|
66 |
}
|
run-1/checkpoint-72/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
|
run-2/checkpoint-144/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-2/checkpoint-144/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:e3a1eb309bec98e4c0bf7dfee033a0074f1dde2d1f2ad466a0454ff6be9c67fd
|
3 |
size 267829484
|
run-2/checkpoint-144/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 sha256:6df663a46d003badc963eb0bb254e855924846efa666ebd7f71b034bc82e3d7a
|
3 |
size 535721146
|
run-2/checkpoint-144/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 sha256:077f4a3002f49f9466f33d2622e7fdb5cb86e5761168a9f2f3bba8a5ee7f6694
|
3 |
+
size 14244
|
run-2/checkpoint-144/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 sha256:422ae6c60d9b7e721217d84cfa37769d43f300330524252f7d9f3c18abb48a49
|
3 |
size 1064
|
run-2/checkpoint-144/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-144",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 144,
|
7 |
"is_hyper_param_search": true,
|
@@ -10,57 +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": 36
|
20 |
-
},
|
21 |
-
{
|
22 |
-
"epoch": 2.0,
|
23 |
-
"eval_loss": 1.1902464628219604,
|
24 |
-
"eval_pearson": 0.774068032504475,
|
25 |
-
"eval_runtime": 0.9073,
|
26 |
-
"eval_samples_per_second": 1653.256,
|
27 |
-
"eval_spearmanr": 0.7685396079860547,
|
28 |
-
"eval_steps_per_second": 103.604,
|
29 |
-
"step": 72
|
30 |
-
},
|
31 |
-
{
|
32 |
-
"epoch": 3.0,
|
33 |
-
"eval_loss": 0.845661461353302,
|
34 |
-
"eval_pearson": 0.8156384301074189,
|
35 |
-
"eval_runtime": 0.9602,
|
36 |
-
"eval_samples_per_second": 1562.214,
|
37 |
-
"eval_spearmanr": 0.8142363416044488,
|
38 |
-
"eval_steps_per_second": 97.899,
|
39 |
-
"step": 108
|
40 |
-
},
|
41 |
-
{
|
42 |
-
"epoch": 4.0,
|
43 |
-
"eval_loss": 0.7359773516654968,
|
44 |
-
"eval_pearson": 0.820309116112808,
|
45 |
-
"eval_runtime": 0.9488,
|
46 |
-
"eval_samples_per_second": 1580.967,
|
47 |
-
"eval_spearmanr": 0.8207010328870485,
|
48 |
-
"eval_steps_per_second": 99.074,
|
49 |
"step": 144
|
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":
|
59 |
"trial_name": null,
|
60 |
"trial_params": {
|
61 |
-
"learning_rate":
|
62 |
-
"num_train_epochs":
|
63 |
-
"per_device_train_batch_size":
|
64 |
-
"seed":
|
65 |
}
|
66 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8355986744784069,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-144",
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 144,
|
7 |
"is_hyper_param_search": true,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.9578061699867249,
|
14 |
+
"eval_pearson": 0.8355986744784069,
|
15 |
+
"eval_runtime": 0.7883,
|
16 |
+
"eval_samples_per_second": 1902.903,
|
17 |
+
"eval_spearmanr": 0.8478883362984728,
|
18 |
+
"eval_steps_per_second": 119.249,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
"step": 144
|
20 |
}
|
21 |
],
|
22 |
"logging_steps": 500,
|
23 |
+
"max_steps": 288,
|
24 |
"num_input_tokens_seen": 0,
|
25 |
+
"num_train_epochs": 2,
|
26 |
"save_steps": 500,
|
27 |
"total_flos": 0,
|
28 |
+
"train_batch_size": 4,
|
29 |
"trial_name": null,
|
30 |
"trial_params": {
|
31 |
+
"learning_rate": 5.552203664807529e-05,
|
32 |
+
"num_train_epochs": 2,
|
33 |
+
"per_device_train_batch_size": 4,
|
34 |
+
"seed": 5
|
35 |
}
|
36 |
}
|
run-2/checkpoint-144/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 sha256:246413bd9d1435f6c7c69c70d1a2f8591cfec05c6bb21beef22e1bd41910e74b
|
3 |
size 4920
|
runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110291.0f0a24039c15.273.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a8264c20603bb7a5d00d4cb5cf4d15adea2ce41c92307ca7b2f54048be5b298
|
3 |
+
size 5812
|
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 sha256:246413bd9d1435f6c7c69c70d1a2f8591cfec05c6bb21beef22e1bd41910e74b
|
3 |
size 4920
|