SjardiWillems commited on
Commit
d29d117
·
verified ·
1 Parent(s): b97fa27

Training in progress, epoch 1

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:137ea9a9d64c2fca4ff0672ce3b388497cdd88b583117dcb14cf56ef06450dd2
3
  size 267829484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81b8c78fe5026c94af7a8215ef418f077d1b268ab1a05d9f5b3ae585fa964aa3
3
  size 267829484
run-4/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-4/checkpoint-36/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75bd7b149fb8cbcc4a98c1a500b77cf2498f7d115a33b7c3c58030ec49f7ab84
3
  size 267829484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d20118c73fee6e2ffd1a04b4ef9b5c0bae119e45aa91b1b9e7fbb3d10c8d80c0
3
  size 267829484
run-4/checkpoint-36/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b9ee39c83a3485f89033746bc673df88e46052d3beddf40596ab7d759b591dc
3
  size 535721146
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66aa05a285d25e91b539d74ff9b7f232f2067ac95c9fbc27db8c037ef4626e8e
3
  size 535721146
run-4/checkpoint-36/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fef671614c0d6f27cd73dcd86b2ff032aa12d8c88e7fd3678f3e0a264d90dbfa
3
- size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb8f8664a2b45cfb12e77df00681b8d6678be929fd7d39849fa12809d714800
3
+ size 14180
run-4/checkpoint-36/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5fd7f61c7117cf44e1b5dcb41fba06e442d903463f3acc9daaac3751d9061b0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d42f3f1deeff721e6f888ada4bb06135f66f6bba142092c77481410eacdc7fb9
3
  size 1064
run-4/checkpoint-36/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.24101392328980611,
3
- "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-9",
4
- "epoch": 4.0,
5
  "eval_steps": 500,
6
  "global_step": 36,
7
  "is_hyper_param_search": true,
@@ -10,57 +10,37 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 6.916525363922119,
14
- "eval_pearson": 0.24101392328980611,
15
- "eval_runtime": 0.9549,
16
- "eval_samples_per_second": 1570.783,
17
- "eval_spearmanr": 0.23527578828258416,
18
- "eval_steps_per_second": 98.436,
19
- "step": 9
20
- },
21
- {
22
- "epoch": 2.0,
23
- "eval_loss": 6.322813987731934,
24
- "eval_pearson": 0.21685934779589452,
25
- "eval_runtime": 1.3518,
26
- "eval_samples_per_second": 1109.622,
27
- "eval_spearmanr": 0.19981399518979143,
28
- "eval_steps_per_second": 69.536,
29
  "step": 18
30
  },
31
  {
32
- "epoch": 3.0,
33
- "eval_loss": 5.925507068634033,
34
- "eval_pearson": 0.19966300919689736,
35
- "eval_runtime": 2.0553,
36
- "eval_samples_per_second": 729.829,
37
- "eval_spearmanr": 0.18294599603450873,
38
- "eval_steps_per_second": 45.736,
39
- "step": 27
40
- },
41
- {
42
- "epoch": 4.0,
43
- "eval_loss": 5.775755882263184,
44
- "eval_pearson": 0.19587323739505505,
45
- "eval_runtime": 1.1748,
46
- "eval_samples_per_second": 1276.801,
47
- "eval_spearmanr": 0.17919550590843902,
48
- "eval_steps_per_second": 80.013,
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": 4.463445057905012e-06,
62
- "num_train_epochs": 4,
63
- "per_device_train_batch_size": 64,
64
- "seed": 5
65
  }
66
  }
 
1
  {
2
+ "best_metric": 0.8698177849938507,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-18",
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 36,
7
  "is_hyper_param_search": true,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.5605268478393555,
14
+ "eval_pearson": 0.8698177849938507,
15
+ "eval_runtime": 0.7833,
16
+ "eval_samples_per_second": 1914.894,
17
+ "eval_spearmanr": 0.8653376248792928,
18
+ "eval_steps_per_second": 120.0,
 
 
 
 
 
 
 
 
 
 
19
  "step": 18
20
  },
21
  {
22
+ "epoch": 2.0,
23
+ "eval_loss": 0.5489152073860168,
24
+ "eval_pearson": 0.8696541826078176,
25
+ "eval_runtime": 0.7851,
26
+ "eval_samples_per_second": 1910.528,
27
+ "eval_spearmanr": 0.8655096971822834,
28
+ "eval_steps_per_second": 119.726,
 
 
 
 
 
 
 
 
 
 
29
  "step": 36
30
  }
31
  ],
32
  "logging_steps": 500,
33
+ "max_steps": 54,
34
  "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 3,
36
  "save_steps": 500,
37
  "total_flos": 0,
38
+ "train_batch_size": 32,
39
  "trial_name": null,
40
  "trial_params": {
41
+ "learning_rate": 9.914291118758786e-06,
42
+ "num_train_epochs": 3,
43
+ "per_device_train_batch_size": 32,
44
+ "seed": 10
45
  }
46
  }
run-4/checkpoint-36/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf3f62aadffc261f72a51d4b7c87acc76e6bc2705585514f61113a84b0e34fd3
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0fb3669a562055766866e71b54806bb7235c4677b6cb8f825acdf2c31236bf5
3
  size 4920
run-4/checkpoint-54/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-4/checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffe9007611f884e116c02af1450a6ea7a4cca0d81efdc65c004a05c6068dd98d
3
+ size 267829484
run-4/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5356380fd3cb58cb7788d39f619ed30d551db8078949ef0e3be3df07ea01645b
3
+ size 535721146
run-4/checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e75092925b793a7e14690b52acc499966fcbf55d1d06b60e264fc46fdeb79e2
3
+ size 14180
run-4/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab0a8c83eeb1b42d77610423156308d391ce4b7ebb7414a69c163eb17ad2200
3
+ size 1064
run-4/checkpoint-54/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-4/checkpoint-54/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-54/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-4/checkpoint-54/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8701155553176486,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-54",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 54,
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": 0.5605268478393555,
14
+ "eval_pearson": 0.8698177849938507,
15
+ "eval_runtime": 0.7833,
16
+ "eval_samples_per_second": 1914.894,
17
+ "eval_spearmanr": 0.8653376248792928,
18
+ "eval_steps_per_second": 120.0,
19
+ "step": 18
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_loss": 0.5489152073860168,
24
+ "eval_pearson": 0.8696541826078176,
25
+ "eval_runtime": 0.7851,
26
+ "eval_samples_per_second": 1910.528,
27
+ "eval_spearmanr": 0.8655096971822834,
28
+ "eval_steps_per_second": 119.726,
29
+ "step": 36
30
+ },
31
+ {
32
+ "epoch": 3.0,
33
+ "eval_loss": 0.549419105052948,
34
+ "eval_pearson": 0.8701155553176486,
35
+ "eval_runtime": 0.8019,
36
+ "eval_samples_per_second": 1870.6,
37
+ "eval_spearmanr": 0.8658778646954919,
38
+ "eval_steps_per_second": 117.224,
39
+ "step": 54
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 54,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 3,
46
+ "save_steps": 500,
47
+ "total_flos": 0,
48
+ "train_batch_size": 32,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 9.914291118758786e-06,
52
+ "num_train_epochs": 3,
53
+ "per_device_train_batch_size": 32,
54
+ "seed": 10
55
+ }
56
+ }
run-4/checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0fb3669a562055766866e71b54806bb7235c4677b6cb8f825acdf2c31236bf5
3
+ size 4920
run-4/checkpoint-54/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-144/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-5/checkpoint-144/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81b8c78fe5026c94af7a8215ef418f077d1b268ab1a05d9f5b3ae585fa964aa3
3
+ size 267829484
run-5/checkpoint-144/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2e898b213865cdbafdc40d4f32a7a60c49225d80a2a137a76c66b042daf74a5
3
+ size 535721146
run-5/checkpoint-144/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac0847bf7b0d2d1b12819a366eeb9e1b4ebb44345cc05a157292c4374c504256
3
+ size 14308
run-5/checkpoint-144/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7a84ac9d8ad12c2f54714f2acbd2618b49e7bb05812cded36a7af97954492e9
3
+ size 1064
run-5/checkpoint-144/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-5/checkpoint-144/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-144/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-5/checkpoint-144/trainer_state.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8704356686123957,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-5/checkpoint-144",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 144,
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": 0.5534277558326721,
14
+ "eval_pearson": 0.8704356686123957,
15
+ "eval_runtime": 0.7898,
16
+ "eval_samples_per_second": 1899.33,
17
+ "eval_spearmanr": 0.8659393895289175,
18
+ "eval_steps_per_second": 119.025,
19
+ "step": 144
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 432,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 3,
26
+ "save_steps": 500,
27
+ "total_flos": 0,
28
+ "train_batch_size": 4,
29
+ "trial_name": null,
30
+ "trial_params": {
31
+ "learning_rate": 2.532250940931899e-06,
32
+ "num_train_epochs": 3,
33
+ "per_device_train_batch_size": 4,
34
+ "seed": 33
35
+ }
36
+ }
run-5/checkpoint-144/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d063450f94a7ab133a59ea26cf4a1835754e836fb09e39b3319de7656bcf4f60
3
+ size 4920
run-5/checkpoint-144/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar10_22-33-58_0f0a24039c15/events.out.tfevents.1710110580.0f0a24039c15.273.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ebf3153777d46dd7a35a2207cfad0c837c51383d5a75bbad83121822e5728c1
3
+ size 6188
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0fb3669a562055766866e71b54806bb7235c4677b6cb8f825acdf2c31236bf5
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d063450f94a7ab133a59ea26cf4a1835754e836fb09e39b3319de7656bcf4f60
3
  size 4920