Kira-Floris commited on
Commit
3aeaf57
·
verified ·
1 Parent(s): e19d310

Training in progress, epoch 1

Browse files
logs/events.out.tfevents.1719308784.852b1e905a9a.223.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:844a0464575996ef9f317803cc9351f0115165050c50747adeb346cf4243d375
3
- size 8098
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071a618d557460ff6d3b2ac87265bdfaa8234b5a6c5170ccccf43398dae8d897
3
+ size 8986
logs/events.out.tfevents.1719310143.852b1e905a9a.223.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83f939892134c8facac858ae800c6d61895a95d3580946d0af3cde38d01fd498
3
+ size 4894
logs/events.out.tfevents.1719310313.852b1e905a9a.223.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40dd7e9b5670b46dc7a6663a517ea1b9da12a2014e95a3a84bcb900af0806e36
3
+ size 5429
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:050b2db8a7faf810b1b2e4395161325773cc1fe1b670a1f39b5cd6a63508710f
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae20a202c55d96dbc7a99eb68b3c49d5f2889c97c0f7b7581a4369c38393b73
3
  size 17549312
run-0/checkpoint-527/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa21ae55c664d183ed99418fbb9247b4b7ee6800ae3d0ed0500451e8a3bebc7d
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ae20a202c55d96dbc7a99eb68b3c49d5f2889c97c0f7b7581a4369c38393b73
3
  size 17549312
run-0/checkpoint-527/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e506fba24486a7972abbb52ec5ae9c62885914bc48d0e441ab7b5e31648df8f9
3
  size 35123898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53a8520796ad50f6ff85e7e87d2a41102c44b1f2273e6444ae31344537166243
3
  size 35123898
run-0/checkpoint-527/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d4bcffeec60c929d14a9cd81e26902c97bfab40e5297db923c2b617e690f8bb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5d8781fb59c88c7bad07954373a93237cb20c6820b8da7eae26083a78c3d342
3
  size 1064
run-0/checkpoint-527/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.7339449541284404,
3
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-527",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,25 +10,25 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "grad_norm": 5.95961856842041,
14
- "learning_rate": 9.55389368279823e-06,
15
- "loss": 1.5369,
16
  "step": 527
17
  },
18
  {
19
  "epoch": 1.0,
20
- "eval_accuracy": 0.7339449541284404,
21
- "eval_loss": 1.2773902416229248,
22
- "eval_runtime": 2.5957,
23
- "eval_samples_per_second": 335.939,
24
- "eval_steps_per_second": 2.697,
25
  "step": 527
26
  }
27
  ],
28
  "logging_steps": 500,
29
- "max_steps": 5270,
30
  "num_input_tokens_seen": 0,
31
- "num_train_epochs": 10,
32
  "save_steps": 500,
33
  "stateful_callbacks": {
34
  "TrainerControl": {
@@ -46,9 +46,9 @@
46
  "train_batch_size": 128,
47
  "trial_name": null,
48
  "trial_params": {
49
- "alpha": 0.27608826195592573,
50
- "learning_rate": 1.0615437425331367e-05,
51
- "num_train_epochs": 10,
52
- "temperature": 2
53
  }
54
  }
 
1
  {
2
+ "best_metric": 0.7672018348623854,
3
  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-527",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "grad_norm": 12.377176284790039,
14
+ "learning_rate": 1.5980854192157344e-05,
15
+ "loss": 3.0218,
16
  "step": 527
17
  },
18
  {
19
  "epoch": 1.0,
20
+ "eval_accuracy": 0.7672018348623854,
21
+ "eval_loss": 2.191861391067505,
22
+ "eval_runtime": 2.5906,
23
+ "eval_samples_per_second": 336.603,
24
+ "eval_steps_per_second": 2.702,
25
  "step": 527
26
  }
27
  ],
28
  "logging_steps": 500,
29
+ "max_steps": 3162,
30
  "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 6,
32
  "save_steps": 500,
33
  "stateful_callbacks": {
34
  "TrainerControl": {
 
46
  "train_batch_size": 128,
47
  "trial_name": null,
48
  "trial_params": {
49
+ "alpha": 0.275210688972374,
50
+ "learning_rate": 1.9177025030588814e-05,
51
+ "num_train_epochs": 6,
52
+ "temperature": 6
53
  }
54
  }
run-0/checkpoint-527/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8b6a60f7b85b38fa45cddf1a417ee51250fe5822237403416bf2406ff2cdb84
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15e7b4feae857373f91378a3d0efc15d0ec396bfba71e74c965086843aa6acf4
3
  size 5176
run-3/checkpoint-3689/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-3689/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7eee3cf5a9df0ff57d28e2043d0f36eabecdac20b5a01c2de00fadf84811087
3
+ size 17549312
run-3/checkpoint-3689/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b458b642afbc71180e5d3885ae3980471882b8a1195bfb91aaf51efb20c8cf23
3
+ size 35123898
run-3/checkpoint-3689/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e550a7bb338b84ab374b4609347d77ec664e40f8a6b6837a56e299227ab3fcb7
3
+ size 14308
run-3/checkpoint-3689/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d226bd4f2d4f94bdcd4e8754da97158c0f168ff1ac52bc3f613abe7647a673b2
3
+ size 1064
run-3/checkpoint-3689/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-3689/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-3689/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-3689/trainer_state.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8360091743119266,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-3689",
4
+ "epoch": 7.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3689,
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
+ "epoch": 2.0,
29
+ "grad_norm": 51.49909591674805,
30
+ "learning_rate": 5.9055073680756574e-05,
31
+ "loss": 1.2849,
32
+ "step": 1054
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8176605504587156,
37
+ "eval_loss": 1.7333961725234985,
38
+ "eval_runtime": 2.54,
39
+ "eval_samples_per_second": 343.313,
40
+ "eval_steps_per_second": 2.756,
41
+ "step": 1054
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "grad_norm": 84.45722961425781,
46
+ "learning_rate": 4.72485396026994e-05,
47
+ "loss": 0.9617,
48
+ "step": 1581
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8245412844036697,
53
+ "eval_loss": 1.7150405645370483,
54
+ "eval_runtime": 2.5578,
55
+ "eval_samples_per_second": 340.916,
56
+ "eval_steps_per_second": 2.737,
57
+ "step": 1581
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "grad_norm": 30.98444938659668,
62
+ "learning_rate": 3.5442005524642224e-05,
63
+ "loss": 0.8154,
64
+ "step": 2108
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_accuracy": 0.8222477064220184,
69
+ "eval_loss": 1.6820627450942993,
70
+ "eval_runtime": 2.5749,
71
+ "eval_samples_per_second": 338.654,
72
+ "eval_steps_per_second": 2.719,
73
+ "step": 2108
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 18.188648223876953,
78
+ "learning_rate": 2.3635471446585048e-05,
79
+ "loss": 0.7233,
80
+ "step": 2635
81
+ },
82
+ {
83
+ "epoch": 5.0,
84
+ "eval_accuracy": 0.8245412844036697,
85
+ "eval_loss": 1.7338383197784424,
86
+ "eval_runtime": 2.5776,
87
+ "eval_samples_per_second": 338.302,
88
+ "eval_steps_per_second": 2.716,
89
+ "step": 2635
90
+ },
91
+ {
92
+ "epoch": 6.0,
93
+ "grad_norm": Infinity,
94
+ "learning_rate": 1.1851340658998569e-05,
95
+ "loss": 0.6653,
96
+ "step": 3162
97
+ },
98
+ {
99
+ "epoch": 6.0,
100
+ "eval_accuracy": 0.8325688073394495,
101
+ "eval_loss": 1.7560914754867554,
102
+ "eval_runtime": 2.5981,
103
+ "eval_samples_per_second": 335.631,
104
+ "eval_steps_per_second": 2.694,
105
+ "step": 3162
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "grad_norm": 36.049232482910156,
110
+ "learning_rate": 4.4806580941393454e-08,
111
+ "loss": 0.6314,
112
+ "step": 3689
113
+ },
114
+ {
115
+ "epoch": 7.0,
116
+ "eval_accuracy": 0.8360091743119266,
117
+ "eval_loss": 1.7600533962249756,
118
+ "eval_runtime": 2.5655,
119
+ "eval_samples_per_second": 339.892,
120
+ "eval_steps_per_second": 2.728,
121
+ "step": 3689
122
+ }
123
+ ],
124
+ "logging_steps": 500,
125
+ "max_steps": 3689,
126
+ "num_input_tokens_seen": 0,
127
+ "num_train_epochs": 7,
128
+ "save_steps": 500,
129
+ "stateful_callbacks": {
130
+ "TrainerControl": {
131
+ "args": {
132
+ "should_epoch_stop": false,
133
+ "should_evaluate": false,
134
+ "should_log": false,
135
+ "should_save": true,
136
+ "should_training_stop": true
137
+ },
138
+ "attributes": {}
139
+ }
140
+ },
141
+ "total_flos": 56628612372420.0,
142
+ "train_batch_size": 128,
143
+ "trial_name": null,
144
+ "trial_params": {
145
+ "alpha": 0.1351029311037084,
146
+ "learning_rate": 8.264573854640023e-05,
147
+ "num_train_epochs": 7,
148
+ "temperature": 16
149
+ }
150
+ }
run-3/checkpoint-3689/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-3689/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:fb39e5a6519b65bdbd04bcdb6f5e6f1991f6196e0c3617b3126fe14176729f26
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15e7b4feae857373f91378a3d0efc15d0ec396bfba71e74c965086843aa6acf4
3
  size 5176