Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-2/checkpoint-288/config.json +31 -0
- run-2/checkpoint-288/model.safetensors +3 -0
- run-2/checkpoint-288/optimizer.pt +3 -0
- run-2/checkpoint-288/rng_state.pth +3 -0
- run-2/checkpoint-288/scheduler.pt +3 -0
- run-2/checkpoint-288/special_tokens_map.json +7 -0
- run-2/checkpoint-288/tokenizer.json +0 -0
- run-2/checkpoint-288/tokenizer_config.json +55 -0
- run-2/checkpoint-288/trainer_state.json +46 -0
- run-2/checkpoint-288/training_args.bin +3 -0
- run-2/checkpoint-288/vocab.txt +0 -0
- run-3/checkpoint-18/config.json +1 -1
- run-3/checkpoint-18/model.safetensors +1 -1
- run-3/checkpoint-18/optimizer.pt +1 -1
- run-3/checkpoint-18/rng_state.pth +2 -2
- run-3/checkpoint-18/scheduler.pt +1 -1
- run-3/checkpoint-18/trainer_state.json +13 -23
- run-3/checkpoint-18/training_args.bin +1 -1
- runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110384.0f0a24039c15.273.5 +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 sha256:0c72c160ce745efa2a168ba3065831c2eb692ce9297265e22265b0352f137ee9
|
3 |
size 267829484
|
run-2/checkpoint-288/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "SjardiWillems/distilbert-base-uncased-finetuned-stsb",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"LABEL_0": 0
|
17 |
+
},
|
18 |
+
"max_position_embeddings": 512,
|
19 |
+
"model_type": "distilbert",
|
20 |
+
"n_heads": 12,
|
21 |
+
"n_layers": 6,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"problem_type": "regression",
|
24 |
+
"qa_dropout": 0.1,
|
25 |
+
"seq_classif_dropout": 0.2,
|
26 |
+
"sinusoidal_pos_embds": false,
|
27 |
+
"tie_weights_": true,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.38.2",
|
30 |
+
"vocab_size": 30522
|
31 |
+
}
|
run-2/checkpoint-288/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:614189b65fba102d06159359331ffeb1953e2f7125e11bcc69949ffcb747a48d
|
3 |
+
size 267829484
|
run-2/checkpoint-288/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4b03782bfc350f9945c8e16d1e1b6a773cc80197d8703db9782c28b4b3e912b
|
3 |
+
size 535721146
|
run-2/checkpoint-288/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7059eec0255ffdc912f70633c83c9764bf6fc16919990e7ab44548a90030087c
|
3 |
+
size 14244
|
run-2/checkpoint-288/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db95cbff936e71fa082f1cfce602ec54cea6f6ee7a160fd818b0eefc21767602
|
3 |
+
size 1064
|
run-2/checkpoint-288/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-2/checkpoint-288/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-288/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-2/checkpoint-288/trainer_state.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8661005085464799,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-288",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 288,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": 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 |
+
"epoch": 2.0,
|
23 |
+
"eval_loss": 0.5721424221992493,
|
24 |
+
"eval_pearson": 0.8661005085464799,
|
25 |
+
"eval_runtime": 0.8164,
|
26 |
+
"eval_samples_per_second": 1837.328,
|
27 |
+
"eval_spearmanr": 0.862146981344484,
|
28 |
+
"eval_steps_per_second": 115.139,
|
29 |
+
"step": 288
|
30 |
+
}
|
31 |
+
],
|
32 |
+
"logging_steps": 500,
|
33 |
+
"max_steps": 288,
|
34 |
+
"num_input_tokens_seen": 0,
|
35 |
+
"num_train_epochs": 2,
|
36 |
+
"save_steps": 500,
|
37 |
+
"total_flos": 0,
|
38 |
+
"train_batch_size": 4,
|
39 |
+
"trial_name": null,
|
40 |
+
"trial_params": {
|
41 |
+
"learning_rate": 5.552203664807529e-05,
|
42 |
+
"num_train_epochs": 2,
|
43 |
+
"per_device_train_batch_size": 4,
|
44 |
+
"seed": 5
|
45 |
+
}
|
46 |
+
}
|
run-2/checkpoint-288/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:246413bd9d1435f6c7c69c70d1a2f8591cfec05c6bb21beef22e1bd41910e74b
|
3 |
+
size 4920
|
run-2/checkpoint-288/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/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-3/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 sha256:0c72c160ce745efa2a168ba3065831c2eb692ce9297265e22265b0352f137ee9
|
3 |
size 267829484
|
run-3/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 sha256:2f3756abeafbc8fb8b516c48dd4cbad4eeb6f69ae6f8b83a4baa8248f6850f2c
|
3 |
size 535721146
|
run-3/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 sha256:31fb11d3e165a3b516cbc59429a49c849c1bd3fe6ee9d654f1fbf083b2fddab2
|
3 |
+
size 14308
|
run-3/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 sha256:840046423a728241bc609475b779796bd125f6e74e3b919f8c4cf98b300055cc
|
3 |
size 1064
|
run-3/checkpoint-18/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-18",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 18,
|
7 |
"is_hyper_param_search": true,
|
@@ -10,37 +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 |
-
"epoch": 2.0,
|
23 |
-
"eval_loss": 6.31046724319458,
|
24 |
-
"eval_pearson": 0.0470495796010619,
|
25 |
-
"eval_runtime": 0.9557,
|
26 |
-
"eval_samples_per_second": 1569.521,
|
27 |
-
"eval_spearmanr": 0.048936574609921006,
|
28 |
-
"eval_steps_per_second": 98.357,
|
29 |
"step": 18
|
30 |
}
|
31 |
],
|
32 |
"logging_steps": 500,
|
33 |
-
"max_steps":
|
34 |
"num_input_tokens_seen": 0,
|
35 |
"num_train_epochs": 5,
|
36 |
"save_steps": 500,
|
37 |
"total_flos": 0,
|
38 |
-
"train_batch_size":
|
39 |
"trial_name": null,
|
40 |
"trial_params": {
|
41 |
-
"learning_rate": 5.
|
42 |
"num_train_epochs": 5,
|
43 |
-
"per_device_train_batch_size":
|
44 |
-
"seed":
|
45 |
}
|
46 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8640876954461902,
|
3 |
"best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-3/checkpoint-18",
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 18,
|
7 |
"is_hyper_param_search": true,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_loss": 0.6028859615325928,
|
14 |
+
"eval_pearson": 0.8640876954461902,
|
15 |
+
"eval_runtime": 0.7957,
|
16 |
+
"eval_samples_per_second": 1885.175,
|
17 |
+
"eval_spearmanr": 0.8614938677816929,
|
18 |
+
"eval_steps_per_second": 118.138,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
"step": 18
|
20 |
}
|
21 |
],
|
22 |
"logging_steps": 500,
|
23 |
+
"max_steps": 90,
|
24 |
"num_input_tokens_seen": 0,
|
25 |
"num_train_epochs": 5,
|
26 |
"save_steps": 500,
|
27 |
"total_flos": 0,
|
28 |
+
"train_batch_size": 32,
|
29 |
"trial_name": null,
|
30 |
"trial_params": {
|
31 |
+
"learning_rate": 5.304193372992487e-05,
|
32 |
"num_train_epochs": 5,
|
33 |
+
"per_device_train_batch_size": 32,
|
34 |
+
"seed": 31
|
35 |
}
|
36 |
}
|
run-3/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 sha256:39e6105fbde8ff9149ae2a4bbcd7a8dac84eb9cecad379f5bd1a4200bdc1f6ea
|
3 |
size 4920
|
runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110384.0f0a24039c15.273.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46e825ecbdbf00da1a52f3680848612270825feac9c2eb9b6149b758ba58b4dc
|
3 |
+
size 6898
|
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 sha256:39e6105fbde8ff9149ae2a4bbcd7a8dac84eb9cecad379f5bd1a4200bdc1f6ea
|
3 |
size 4920
|