Slava commited on
Commit
7f14c98
·
verified ·
1 Parent(s): 4dad64e

Training in progress, epoch 1

Browse files
logs/events.out.tfevents.1706203192.A-FVFFG2C4Q05P.18450.8 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d046c281753bf4c26e1198ee7a9434362389080758d411bc5ee034610061918
3
- size 4915
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a322f5bc9a3a55ef61ffab45ca17ce2e7b107cb2707a4fb731be52f6f06c3cca
3
+ size 5395
logs/events.out.tfevents.1706204360.A-FVFFG2C4Q05P.18450.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f945c187fb8708a64a3343cee39660f28dbef37fa783930a9e3f5be747e3dcc
3
+ size 4916
logs/events.out.tfevents.1706204945.A-FVFFG2C4Q05P.18450.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d838259511ac70ae1d6a6e8232d25a6f2843bb607f8088c172a8e1b288297bef
3
+ size 4916
logs/events.out.tfevents.1706205531.A-FVFFG2C4Q05P.18450.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:568bb09995b5dd71cd3b47c0eff8391ac7d766fe8c5078f2407eb2ac67535664
3
+ size 4916
logs/events.out.tfevents.1706213692.A-FVFFG2C4Q05P.18450.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62cc5bae5643e76f5fe7132152762e60f7c56f8a1f4dd8974ac1be3b8f3804b9
3
+ size 4915
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4752cf5f120177c3e3aba578558a649b420b3df93152e6ff5026422c284a331c
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23893f7224a7bc69c792d25073f9d6a6b006ae31c0a78b378e8e817d49d4fafc
3
  size 17549312
run-11/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": "4.37.1",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-11/checkpoint-527/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23893f7224a7bc69c792d25073f9d6a6b006ae31c0a78b378e8e817d49d4fafc
3
+ size 17549312
run-11/checkpoint-527/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:853249bf50906316a533cccaad6f3d1a5bf2e9982a9ca2f0e8f80f8687f65946
3
+ size 35122373
run-11/checkpoint-527/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f943a8d8f93fea7f44cad3b9bfb2d2b97d65b141eb704b9cba669cf42e776b14
3
+ size 13617
run-11/checkpoint-527/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0817d3adfcb49fc18d4f2acf378d63396e401a050828859c85fd8ab8b340387
3
+ size 627
run-11/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-11/checkpoint-527/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-11/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-11/checkpoint-527/trainer_state.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8130733944954128,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/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
+ "learning_rate": 0.00010911592510991879,
14
+ "loss": 1.2248,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8130733944954128,
20
+ "eval_loss": 1.0815833806991577,
21
+ "eval_runtime": 19.1179,
22
+ "eval_samples_per_second": 45.612,
23
+ "eval_steps_per_second": 0.366,
24
+ "step": 527
25
+ }
26
+ ],
27
+ "logging_steps": 500,
28
+ "max_steps": 3689,
29
+ "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 7,
31
+ "save_steps": 500,
32
+ "total_flos": 8069051778960.0,
33
+ "train_batch_size": 128,
34
+ "trial_name": null,
35
+ "trial_params": {
36
+ "alpha": 0.6271968482895725,
37
+ "learning_rate": 0.0001273019126282386,
38
+ "num_train_epochs": 7,
39
+ "temperature": 11
40
+ }
41
+ }
run-11/checkpoint-527/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff57408053b19dbf32dbe4dd4af251a79a2c99bea6a376004e876c375e910b86
3
+ size 4283
run-11/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:b22706842879ea7d033aff79fe8a23d07265bc544cd944fcd9991fea27c0e9ab
3
  size 4283
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff57408053b19dbf32dbe4dd4af251a79a2c99bea6a376004e876c375e910b86
3
  size 4283