joseph10 commited on
Commit
86e904c
·
1 Parent(s): bcfeb3f

Training in progress, epoch 4

Browse files
logs/events.out.tfevents.1701759678.joseph_legion.10272.16 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20a575187bc205693860317cc3d4f6847e30a04ecf1bbdcfe42288654591f0e0
3
- size 5735
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e45a247480ebc96f209baecd56acbc5368dad6e274a3e9595cb141e93c2059
3
+ size 6215
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:925921b9b07083b1c95d88d742a959ecc2be94ee1816e6f8df9e1479526a6047
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4cc67758e9a4f5985c447e41bf77d5dd887aedb083af407a31e26afd6302ab9
3
  size 17549312
run-15/checkpoint-2108/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": "4.35.2",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-15/checkpoint-2108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4cc67758e9a4f5985c447e41bf77d5dd887aedb083af407a31e26afd6302ab9
3
+ size 17549312
run-15/checkpoint-2108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d97802d7ae93adc2ccd20d0677e170bb60b967c3f12719c59648159047e777c
3
+ size 35123898
run-15/checkpoint-2108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a020c8677f8fadfc307a6b0f0852435c8b675caad3b164c3943e9e61d914105
3
+ size 14308
run-15/checkpoint-2108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8c019d46cf68a5ef978137337625ffb052e3efa1b113d3e3c81707b3dda8963
3
+ size 1064
run-15/checkpoint-2108/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-15/checkpoint-2108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-15/checkpoint-2108/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-15/checkpoint-2108/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8314220183486238,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-15\\checkpoint-527",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2108,
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": 0.00025200338594854476,
14
+ "loss": 0.9759,
15
+ "step": 527
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.8314220183486238,
20
+ "eval_loss": 1.0490596294403076,
21
+ "eval_runtime": 1.7959,
22
+ "eval_samples_per_second": 485.544,
23
+ "eval_steps_per_second": 3.898,
24
+ "step": 527
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "learning_rate": 0.00018900253946140859,
29
+ "loss": 0.4734,
30
+ "step": 1054
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_accuracy": 0.823394495412844,
35
+ "eval_loss": 1.201561450958252,
36
+ "eval_runtime": 1.7799,
37
+ "eval_samples_per_second": 489.914,
38
+ "eval_steps_per_second": 3.933,
39
+ "step": 1054
40
+ },
41
+ {
42
+ "epoch": 3.0,
43
+ "learning_rate": 0.00012600169297427238,
44
+ "loss": 0.3336,
45
+ "step": 1581
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_accuracy": 0.8188073394495413,
50
+ "eval_loss": 1.2774909734725952,
51
+ "eval_runtime": 1.7767,
52
+ "eval_samples_per_second": 490.805,
53
+ "eval_steps_per_second": 3.94,
54
+ "step": 1581
55
+ },
56
+ {
57
+ "epoch": 4.0,
58
+ "learning_rate": 6.300084648713619e-05,
59
+ "loss": 0.2564,
60
+ "step": 2108
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_accuracy": 0.8176605504587156,
65
+ "eval_loss": 1.3708006143569946,
66
+ "eval_runtime": 1.8028,
67
+ "eval_samples_per_second": 483.681,
68
+ "eval_steps_per_second": 3.883,
69
+ "step": 2108
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 2635,
74
+ "num_train_epochs": 5,
75
+ "save_steps": 500,
76
+ "total_flos": 32351505805740.0,
77
+ "trial_name": null,
78
+ "trial_params": {
79
+ "alpha": 0.6153233971144083,
80
+ "learning_rate": 0.00031500423243568097,
81
+ "num_train_epochs": 5,
82
+ "temperature": 14
83
+ }
84
+ }
run-15/checkpoint-2108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fd5459235a8577a6454d836553135f3519b14545a636877d353491a383dc742
3
+ size 4664
run-15/checkpoint-2108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff