Kira-Floris commited on
Commit
ac08c10
1 Parent(s): fb0b1cc

Training in progress, epoch 1

Browse files
logs/events.out.tfevents.1719308394.852b1e905a9a.223.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7efd478f107ca4f1883dcadcd0f9c13a4134ef3a0a09df08209c5d7eb464e70
3
- size 5425
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:641d452db1b644d628ee9e9b4b516ffa168d4059d9bd920333601e51406bac14
3
+ size 6313
logs/events.out.tfevents.1719308784.852b1e905a9a.223.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c1d2207cfa3f7875182aa2da4f63d9a8fee5570c98a8358f025fd6e3281b13c
3
+ size 5428
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5361497fa8c3908c4e84511eaa41d8b5ac65c9b38c9547e3f8b6f779afff1b90
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed291268775732577fb8c37a401132258d34469a5f13f5747b1cc9dc93e8e561
3
  size 17549312
run-2/checkpoint-1054/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.41.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-2/checkpoint-1054/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b172e6bb62d0112222872982384e8522ee106d78fcd87aa7b152344ec6a15eac
3
+ size 17549312
run-2/checkpoint-1054/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e88327de27dbabf00233b3fc1fec3987f3ed90d225094911a64983ade02fcd6e
3
+ size 35123898
run-2/checkpoint-1054/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9cd26c18bd73de03f23efd45b2b9c4ed2da8b8be6f5803534539d3670c38edc
3
+ size 14308
run-2/checkpoint-1054/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69684c0cbcb0459b1e181ac3d3dd4e95933c803e920e07cb73a7a95461c03314
3
+ size 1064
run-2/checkpoint-1054/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-1054/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-1054/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-2/checkpoint-1054/trainer_state.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7901376146788991,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-1054",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1054,
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
+ "grad_norm": 7.264369964599609,
14
+ "learning_rate": 2.1662503772415e-05,
15
+ "loss": 0.9021,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.783256880733945,
21
+ "eval_loss": 0.7694150805473328,
22
+ "eval_runtime": 2.5918,
23
+ "eval_samples_per_second": 336.446,
24
+ "eval_steps_per_second": 2.701,
25
+ "step": 527
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "grad_norm": 13.286161422729492,
30
+ "learning_rate": 0.0,
31
+ "loss": 0.6713,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.7901376146788991,
37
+ "eval_loss": 0.7401114702224731,
38
+ "eval_runtime": 2.6174,
39
+ "eval_samples_per_second": 333.153,
40
+ "eval_steps_per_second": 2.674,
41
+ "step": 1054
42
+ }
43
+ ],
44
+ "logging_steps": 500,
45
+ "max_steps": 1054,
46
+ "num_input_tokens_seen": 0,
47
+ "num_train_epochs": 2,
48
+ "save_steps": 500,
49
+ "stateful_callbacks": {
50
+ "TrainerControl": {
51
+ "args": {
52
+ "should_epoch_stop": false,
53
+ "should_evaluate": false,
54
+ "should_log": false,
55
+ "should_save": true,
56
+ "should_training_stop": true
57
+ },
58
+ "attributes": {}
59
+ }
60
+ },
61
+ "total_flos": 16141525436100.0,
62
+ "train_batch_size": 128,
63
+ "trial_name": null,
64
+ "trial_params": {
65
+ "alpha": 0.8796304515753969,
66
+ "learning_rate": 4.332500754483e-05,
67
+ "num_train_epochs": 2,
68
+ "temperature": 9
69
+ }
70
+ }
run-2/checkpoint-1054/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:359429d5b1f7cc1db58636608797470b13c3be9f3776c3e27ced616a7a5e5783
3
+ size 5176
run-2/checkpoint-1054/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-527/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.41.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-3/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed291268775732577fb8c37a401132258d34469a5f13f5747b1cc9dc93e8e561
3
+ size 17549312
run-3/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f21051507635e0b85590bb063521a8b30631cb28a67478c852fa4b66ff6e4c17
3
+ size 35123898
run-3/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9733f27bb728718f7284348156186daf975855376673d9de7e218a8cff476307
3
+ size 14308
run-3/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9afca5405afcee434bb1a77268d5b264c14f32531ad613f6700d37fc9b58f3cb
3
+ size 1064
run-3/checkpoint-527/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-3/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-527/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-3/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8061926605504587,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-527",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 527,
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
+ "grad_norm": 31.228694915771484,
14
+ "learning_rate": 7.086160775881376e-05,
15
+ "loss": 2.5988,
16
+ "step": 527
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8061926605504587,
21
+ "eval_loss": 1.924224615097046,
22
+ "eval_runtime": 2.5772,
23
+ "eval_samples_per_second": 338.351,
24
+ "eval_steps_per_second": 2.716,
25
+ "step": 527
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 3689,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 7,
32
+ "save_steps": 500,
33
+ "stateful_callbacks": {
34
+ "TrainerControl": {
35
+ "args": {
36
+ "should_epoch_stop": false,
37
+ "should_evaluate": false,
38
+ "should_log": false,
39
+ "should_save": true,
40
+ "should_training_stop": false
41
+ },
42
+ "attributes": {}
43
+ }
44
+ },
45
+ "total_flos": 8057768762220.0,
46
+ "train_batch_size": 128,
47
+ "trial_name": null,
48
+ "trial_params": {
49
+ "alpha": 0.1351029311037084,
50
+ "learning_rate": 8.264573854640023e-05,
51
+ "num_train_epochs": 7,
52
+ "temperature": 16
53
+ }
54
+ }
run-3/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb39e5a6519b65bdbd04bcdb6f5e6f1991f6196e0c3617b3126fe14176729f26
3
+ size 5176
run-3/checkpoint-527/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:359429d5b1f7cc1db58636608797470b13c3be9f3776c3e27ced616a7a5e5783
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb39e5a6519b65bdbd04bcdb6f5e6f1991f6196e0c3617b3126fe14176729f26
3
  size 5176