Tech-oriented commited on
Commit
c2e82f6
1 Parent(s): 416167f

Training in progress, epoch 2

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:593ae89289d9d92e361ca2ceb9582a6f6b4c7fc7b4c7b9ae371f5bb3b67a40e1
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a33f6af52515c9b232db426ae70cd0781e64260d8aa0084cc4eb33d3f812202
3
  size 437958648
run-6/checkpoint-16838/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.4,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.4,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-6/checkpoint-16838/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a33f6af52515c9b232db426ae70cd0781e64260d8aa0084cc4eb33d3f812202
3
+ size 437958648
run-6/checkpoint-16838/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45656ec8e114749940ad11aaa284ac02f7be27ef0636bf510e998170610978e6
3
+ size 876038394
run-6/checkpoint-16838/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9af226e732c97fde89f01fd2c516fa16b929601d73614f43176d1e07edfd7dd
3
+ size 14308
run-6/checkpoint-16838/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b192d5274273f9f59eb18098ddbbb9e9b28a9ea3974e9eafed09a363051170e7
3
+ size 1064
run-6/checkpoint-16838/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-6/checkpoint-16838/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-16838/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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-6/checkpoint-16838/trainer_state.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9139908256880734,
3
+ "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-6/checkpoint-8419",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 16838,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5,
13
+ "grad_norm": 35.4764289855957,
14
+ "learning_rate": 1.4625672140464685e-05,
15
+ "loss": 0.452,
16
+ "step": 4209
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "grad_norm": 2.615936040878296,
21
+ "learning_rate": 1.2536574029383954e-05,
22
+ "loss": 0.354,
23
+ "step": 8418
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_accuracy": 0.9139908256880734,
28
+ "eval_loss": 0.36559009552001953,
29
+ "eval_runtime": 2.4317,
30
+ "eval_samples_per_second": 358.596,
31
+ "eval_steps_per_second": 22.618,
32
+ "step": 8419
33
+ },
34
+ {
35
+ "epoch": 1.5,
36
+ "grad_norm": 1.231093406677246,
37
+ "learning_rate": 1.0447475918303226e-05,
38
+ "loss": 0.3236,
39
+ "step": 12627
40
+ },
41
+ {
42
+ "epoch": 2.0,
43
+ "grad_norm": 66.64139556884766,
44
+ "learning_rate": 8.358377807222495e-06,
45
+ "loss": 0.303,
46
+ "step": 16836
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "eval_accuracy": 0.9025229357798165,
51
+ "eval_loss": 0.4449034631252289,
52
+ "eval_runtime": 2.4314,
53
+ "eval_samples_per_second": 358.637,
54
+ "eval_steps_per_second": 22.62,
55
+ "step": 16838
56
+ }
57
+ ],
58
+ "logging_steps": 4209,
59
+ "max_steps": 33676,
60
+ "num_input_tokens_seen": 0,
61
+ "num_train_epochs": 4,
62
+ "save_steps": 500,
63
+ "total_flos": 3441334840253340.0,
64
+ "train_batch_size": 8,
65
+ "trial_name": null,
66
+ "trial_params": {
67
+ "learning_rate": 1.6714770251545413e-05,
68
+ "num_train_epochs": 4,
69
+ "per_device_train_batch_size": 8,
70
+ "seed": 32,
71
+ "weight_decay": 0.41710891288145024
72
+ }
73
+ }
run-6/checkpoint-16838/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f473f968b7e87229e13a2aa91b256ae59a2f8fb544c7ea1c0d31b1fdaca756e5
3
+ size 4984
run-6/checkpoint-16838/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar06_18-14-36_e017d622c671/events.out.tfevents.1709764768.e017d622c671.539.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29e4b8170ff8208713642b930ac173476c12df8574fdc997ce0161b4d8c77647
3
- size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e60fe196a10bba79322e4dd4bbd7a7c7a17e362ee82d11e3a137e17e7b35770
3
+ size 6251