SjardiWillems commited on
Commit
d9deea5
·
verified ·
1 Parent(s): de961c9

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 sha256:01f5c629441e431c292478817904a48fc60bd6a25aaec9fae7c494ea780a6941
3
  size 267829484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f87cf2bf59060d3a0048c5a8c89d46ad6fbbda7e7277d36534ba5b40602188
3
  size 267829484
run-4/checkpoint-144/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67b96031aac114c6e35186c47bedb6093c9b1d8d7a35080d4af0e5427b7c0e7a
3
  size 267829484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c73a5225f6f8ff5decc155d3d351f83dfcf0ce9aaf6c45a279ae41fb4449ee24
3
  size 267829484
run-4/checkpoint-144/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb35cac1bb27bfb5fff6849dd603b20c0df6498f36f3c3399382e82c90dbfd99
3
  size 535721146
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ad524efcad3a6ddbfb63ab93577f87e0d7f7b4e402ca5f9057e542f22055002
3
  size 535721146
run-4/checkpoint-144/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba4ef1c5e753a9401f18db6dd0e9badc9fb4e3e4956aafa5bbed209ec8cba9e0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f6b60aad452bff3447ffca2a36beeee0343938e34ba314a3008c1ede5f8c3f6
3
  size 14244
run-4/checkpoint-144/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a78e4fab71e71f8cfdac39d3ebd41054aafb6de39f3ccc727afec93c8a6994f8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24cb08a5f47f3b09c6191ca27ce63f964273a32bc35b3de399ba3391421dc493
3
  size 1064
run-4/checkpoint-144/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.8072119226154155,
3
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-144",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
@@ -10,37 +10,37 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 1.9030543565750122,
14
- "eval_pearson": 0.6173001362903047,
15
- "eval_runtime": 0.7967,
16
- "eval_samples_per_second": 1882.655,
17
- "eval_spearmanr": 0.6065460603935124,
18
- "eval_steps_per_second": 117.98,
19
  "step": 72
20
  },
21
  {
22
  "epoch": 2.0,
23
- "eval_loss": 1.0358508825302124,
24
- "eval_pearson": 0.8072119226154155,
25
- "eval_runtime": 0.8084,
26
- "eval_samples_per_second": 1855.522,
27
- "eval_spearmanr": 0.8100114657508573,
28
- "eval_steps_per_second": 116.279,
29
  "step": 144
30
  }
31
  ],
32
  "logging_steps": 500,
33
- "max_steps": 288,
34
  "num_input_tokens_seen": 0,
35
- "num_train_epochs": 4,
36
  "save_steps": 500,
37
  "total_flos": 0,
38
  "train_batch_size": 8,
39
  "trial_name": null,
40
  "trial_params": {
41
- "learning_rate": 2.5574276250903696e-05,
42
- "num_train_epochs": 4,
43
  "per_device_train_batch_size": 8,
44
- "seed": 40
45
  }
46
  }
 
1
  {
2
+ "best_metric": 0.8221827565737537,
3
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-144",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.8611708283424377,
14
+ "eval_pearson": 0.7953877953260705,
15
+ "eval_runtime": 0.8553,
16
+ "eval_samples_per_second": 1753.857,
17
+ "eval_spearmanr": 0.7996594648437907,
18
+ "eval_steps_per_second": 109.908,
19
  "step": 72
20
  },
21
  {
22
  "epoch": 2.0,
23
+ "eval_loss": 0.7928332686424255,
24
+ "eval_pearson": 0.8221827565737537,
25
+ "eval_runtime": 0.8614,
26
+ "eval_samples_per_second": 1741.283,
27
+ "eval_spearmanr": 0.8208920009900285,
28
+ "eval_steps_per_second": 109.12,
29
  "step": 144
30
  }
31
  ],
32
  "logging_steps": 500,
33
+ "max_steps": 216,
34
  "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 3,
36
  "save_steps": 500,
37
  "total_flos": 0,
38
  "train_batch_size": 8,
39
  "trial_name": null,
40
  "trial_params": {
41
+ "learning_rate": 8.502777165949994e-05,
42
+ "num_train_epochs": 3,
43
  "per_device_train_batch_size": 8,
44
+ "seed": 19
45
  }
46
  }
run-4/checkpoint-144/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:feadc6806513ec4d8a685f2034114bf8544eb719bcbc361b5282de434aef445a
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e809e9199816ee8172204222af345fed40c54314e26cb4383f4a491343c532
3
  size 4920
run-4/checkpoint-216/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98e7ed4567edaf8cafd3b04aab5b2c4357198ecc55e0a732fb05e92389af23be
3
  size 267829484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9cc46d46871c720e6e25d063fe577e0b47a56ed46be3e82e1851ee8cf48303c
3
  size 267829484
run-4/checkpoint-216/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:445fbf7678428da33cc6ef3dab5c6183654679f7828b6489a42b3512166af7e3
3
  size 535721146
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dd36370b0b1ed1879223c5e6383d42bcb9e59580277c5bb8ebe64db5f757c8a
3
  size 535721146
run-4/checkpoint-216/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:038e71594f5547a63cb7e467f33b50c0377a188cf2dc5dbbab756833f58c85c4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dea1e3237b5de73b8d4f4afa8a389d9785cb7e1f3d1738843f3cd66c39f997fb
3
  size 14244
run-4/checkpoint-216/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a286dc983477a9eeb41942ec56313b71758475c64c11b6678337da3196238271
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23c54cb0947a5fd07e5fe04185ac1939bfe0e5cdb73f4d9f05a3f00c8c151940
3
  size 1064
run-4/checkpoint-216/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.811708722217708,
3
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-216",
4
  "epoch": 3.0,
5
  "eval_steps": 500,
@@ -10,47 +10,47 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 1.9030543565750122,
14
- "eval_pearson": 0.6173001362903047,
15
- "eval_runtime": 0.7967,
16
- "eval_samples_per_second": 1882.655,
17
- "eval_spearmanr": 0.6065460603935124,
18
- "eval_steps_per_second": 117.98,
19
  "step": 72
20
  },
21
  {
22
  "epoch": 2.0,
23
- "eval_loss": 1.0358508825302124,
24
- "eval_pearson": 0.8072119226154155,
25
- "eval_runtime": 0.8084,
26
- "eval_samples_per_second": 1855.522,
27
- "eval_spearmanr": 0.8100114657508573,
28
- "eval_steps_per_second": 116.279,
29
  "step": 144
30
  },
31
  {
32
  "epoch": 3.0,
33
- "eval_loss": 0.8175650238990784,
34
- "eval_pearson": 0.811708722217708,
35
- "eval_runtime": 0.7965,
36
- "eval_samples_per_second": 1883.148,
37
- "eval_spearmanr": 0.81090938379838,
38
- "eval_steps_per_second": 118.011,
39
  "step": 216
40
  }
41
  ],
42
  "logging_steps": 500,
43
- "max_steps": 288,
44
  "num_input_tokens_seen": 0,
45
- "num_train_epochs": 4,
46
  "save_steps": 500,
47
  "total_flos": 0,
48
  "train_batch_size": 8,
49
  "trial_name": null,
50
  "trial_params": {
51
- "learning_rate": 2.5574276250903696e-05,
52
- "num_train_epochs": 4,
53
  "per_device_train_batch_size": 8,
54
- "seed": 40
55
  }
56
  }
 
1
  {
2
+ "best_metric": 0.8338559298590572,
3
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-4/checkpoint-216",
4
  "epoch": 3.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.8611708283424377,
14
+ "eval_pearson": 0.7953877953260705,
15
+ "eval_runtime": 0.8553,
16
+ "eval_samples_per_second": 1753.857,
17
+ "eval_spearmanr": 0.7996594648437907,
18
+ "eval_steps_per_second": 109.908,
19
  "step": 72
20
  },
21
  {
22
  "epoch": 2.0,
23
+ "eval_loss": 0.7928332686424255,
24
+ "eval_pearson": 0.8221827565737537,
25
+ "eval_runtime": 0.8614,
26
+ "eval_samples_per_second": 1741.283,
27
+ "eval_spearmanr": 0.8208920009900285,
28
+ "eval_steps_per_second": 109.12,
29
  "step": 144
30
  },
31
  {
32
  "epoch": 3.0,
33
+ "eval_loss": 0.6891829967498779,
34
+ "eval_pearson": 0.8338559298590572,
35
+ "eval_runtime": 0.8695,
36
+ "eval_samples_per_second": 1725.217,
37
+ "eval_spearmanr": 0.8309150363589644,
38
+ "eval_steps_per_second": 108.114,
39
  "step": 216
40
  }
41
  ],
42
  "logging_steps": 500,
43
+ "max_steps": 216,
44
  "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 3,
46
  "save_steps": 500,
47
  "total_flos": 0,
48
  "train_batch_size": 8,
49
  "trial_name": null,
50
  "trial_params": {
51
+ "learning_rate": 8.502777165949994e-05,
52
+ "num_train_epochs": 3,
53
  "per_device_train_batch_size": 8,
54
+ "seed": 19
55
  }
56
  }
run-4/checkpoint-216/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:feadc6806513ec4d8a685f2034114bf8544eb719bcbc361b5282de434aef445a
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e809e9199816ee8172204222af345fed40c54314e26cb4383f4a491343c532
3
  size 4920
run-8/checkpoint-36/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
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-8/checkpoint-36/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f87cf2bf59060d3a0048c5a8c89d46ad6fbbda7e7277d36534ba5b40602188
3
+ size 267829484
run-8/checkpoint-36/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b767f45412f2c684679b9fb33446783175c7043516dbb87b80745203bbc4c7b
3
+ size 535721146
run-8/checkpoint-36/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f663ac3d6fdee92e133d3c7c5493cc1047112c0b2c69cb8a334baa59a84a22
3
+ size 14308
run-8/checkpoint-36/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d4eb5f7f97d88d3219be58a8a19533f283f48ba8461d527bb29a342bde9aff
3
+ size 1064
run-8/checkpoint-36/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-8/checkpoint-36/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-36/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-8/checkpoint-36/trainer_state.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7318354585295763,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-8/checkpoint-36",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 36,
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": 1.3752338886260986,
14
+ "eval_pearson": 0.7318354585295763,
15
+ "eval_runtime": 0.8667,
16
+ "eval_samples_per_second": 1730.617,
17
+ "eval_spearmanr": 0.7352649171390578,
18
+ "eval_steps_per_second": 108.452,
19
+ "step": 36
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 108,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 3,
26
+ "save_steps": 500,
27
+ "total_flos": 0,
28
+ "train_batch_size": 16,
29
+ "trial_name": null,
30
+ "trial_params": {
31
+ "learning_rate": 8.023427611654661e-05,
32
+ "num_train_epochs": 3,
33
+ "per_device_train_batch_size": 16,
34
+ "seed": 32
35
+ }
36
+ }
run-8/checkpoint-36/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbc9ff8b6111b24f8c33c7c89aa6bd61df59ec50315b654becfc206c361b6086
3
+ size 4920
run-8/checkpoint-36/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar07_01-09-00_6dcd98e81284/events.out.tfevents.1709774166.6dcd98e81284.961.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6ac276f06255b427f86bab200ea2d5b880735b99ec593b3e2dd681354ec62d5
3
+ size 4980
runs/Mar07_01-09-00_6dcd98e81284/events.out.tfevents.1709774171.6dcd98e81284.961.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662f7c59c314eaf00d2e990ce52aea4d59beabfc2f12e875a1523b059564f064
3
+ size 4981
runs/Mar07_01-09-00_6dcd98e81284/events.out.tfevents.1709774177.6dcd98e81284.961.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8146cffc8f448ba257a85fbaa9355d32aad63b8184785963ad81f741abbfa72
3
+ size 4975
runs/Mar07_01-09-00_6dcd98e81284/events.out.tfevents.1709774180.6dcd98e81284.961.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e1b69cc854fd7fc04664067af54f5d73a66debde355560221338249f51df65
3
+ size 6059
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99e809e9199816ee8172204222af345fed40c54314e26cb4383f4a491343c532
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbc9ff8b6111b24f8c33c7c89aa6bd61df59ec50315b654becfc206c361b6086
3
  size 4920