lilyray commited on
Commit
4dbd1f4
·
verified ·
1 Parent(s): 9941c9a

Training in progress, epoch 3

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ace8a2f152db9071b6bb464dff88f04f38ab58371107db9738b74a4595b1799f
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2879abc7be6aef976932b6d29af4fd40ed759b8e63a1faa30b9010b72b3ddda3
3
  size 267832560
run-3/checkpoint-1074/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-3/checkpoint-1074/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2879abc7be6aef976932b6d29af4fd40ed759b8e63a1faa30b9010b72b3ddda3
3
+ size 267832560
run-3/checkpoint-1074/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54a3dc8748f50a0adffd98afd30f6c73d37f5e12cc870fd60eb622a51e9c4ae
3
+ size 535727290
run-3/checkpoint-1074/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21f063bf51385855ee89e28ce64539016efc2bde8e6061c4466e70112f02bdc3
3
+ size 14308
run-3/checkpoint-1074/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06a1298ed89c9a679676d619037f149865a3d66053d1ef229be0cc2ed9121f37
3
+ size 1064
run-3/checkpoint-1074/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-1074/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": "DistilBertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-3/checkpoint-1074/trainer_state.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6397279500961304,
3
+ "best_model_checkpoint": "./results/run-3/checkpoint-716",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1074,
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
+ "eval_accuracy": 0.6294507575757575,
14
+ "eval_loss": 0.6492276787757874,
15
+ "eval_runtime": 5.5974,
16
+ "eval_samples_per_second": 170.616,
17
+ "eval_steps_per_second": 10.719,
18
+ "step": 358
19
+ },
20
+ {
21
+ "epoch": 1.4,
22
+ "grad_norm": 3.4728548526763916,
23
+ "learning_rate": 4.0879833805706716e-05,
24
+ "loss": 0.6351,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.6777462121212121,
30
+ "eval_loss": 0.6397279500961304,
31
+ "eval_runtime": 5.9337,
32
+ "eval_samples_per_second": 160.946,
33
+ "eval_steps_per_second": 10.112,
34
+ "step": 716
35
+ },
36
+ {
37
+ "epoch": 2.79,
38
+ "grad_norm": 9.018095970153809,
39
+ "learning_rate": 5.270222476693896e-06,
40
+ "loss": 0.3908,
41
+ "step": 1000
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "eval_accuracy": 0.6548295454545454,
46
+ "eval_loss": 1.046752691268921,
47
+ "eval_runtime": 5.5064,
48
+ "eval_samples_per_second": 173.434,
49
+ "eval_steps_per_second": 10.896,
50
+ "step": 1074
51
+ }
52
+ ],
53
+ "logging_steps": 500,
54
+ "max_steps": 1074,
55
+ "num_input_tokens_seen": 0,
56
+ "num_train_epochs": 3,
57
+ "save_steps": 500,
58
+ "total_flos": 1059209319653376.0,
59
+ "train_batch_size": 8,
60
+ "trial_name": null,
61
+ "trial_params": {
62
+ "learning_rate": 7.648944513471952e-05,
63
+ "num_train_epochs": 3,
64
+ "per_device_train_batch_size": 8,
65
+ "seed": 17
66
+ }
67
+ }
run-3/checkpoint-1074/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d942e96edd825810bea99d8e9ba8c3e79dee5d5f647f4c147e0b3268db47d468
3
+ size 4920
run-3/checkpoint-1074/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-358/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-3/checkpoint-358/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace8a2f152db9071b6bb464dff88f04f38ab58371107db9738b74a4595b1799f
3
+ size 267832560
run-3/checkpoint-358/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:568502e6ceb7c9740d8f210dc5d855d7bd4328b4cbe611d5634991b99dfb0c52
3
+ size 535727290
run-3/checkpoint-358/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35231d0c05fbe203dd82f0d3a925b7c7eb38b282236e1ecdf1abe67df1c64f19
3
+ size 14308
run-3/checkpoint-358/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d19253e2e95a48d950a6a6544c603ce6076563125502f693fa6d0e553c4861f0
3
+ size 1064
run-3/checkpoint-358/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-358/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": "DistilBertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-3/checkpoint-358/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6492276787757874,
3
+ "best_model_checkpoint": "./results/run-3/checkpoint-358",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 358,
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
+ "eval_accuracy": 0.6294507575757575,
14
+ "eval_loss": 0.6492276787757874,
15
+ "eval_runtime": 5.5974,
16
+ "eval_samples_per_second": 170.616,
17
+ "eval_steps_per_second": 10.719,
18
+ "step": 358
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 1074,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 8,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 7.648944513471952e-05,
31
+ "num_train_epochs": 3,
32
+ "per_device_train_batch_size": 8,
33
+ "seed": 17
34
+ }
35
+ }
run-3/checkpoint-358/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d942e96edd825810bea99d8e9ba8c3e79dee5d5f647f4c147e0b3268db47d468
3
+ size 4920
run-3/checkpoint-358/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-716/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-3/checkpoint-716/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051516f0dff9662986cb5741ee97c45cfbd15c246e827db0615a225bff39e15c
3
+ size 267832560
run-3/checkpoint-716/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce0814dabd7ddbd46917f02dd8eef650b9c534d3c11ba3b955e3f4296378e6e
3
+ size 535727290
run-3/checkpoint-716/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df3dc1af02a8fb2b3c64c68fa1cb23e6932c3f82615ecdd553b880ba6ee555fc
3
+ size 14308
run-3/checkpoint-716/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5819205d15aead59618f063ceeff972156da25d0d241cc46f3f9375c0e66852e
3
+ size 1064
run-3/checkpoint-716/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-716/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": "DistilBertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-3/checkpoint-716/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6397279500961304,
3
+ "best_model_checkpoint": "./results/run-3/checkpoint-716",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 716,
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
+ "eval_accuracy": 0.6294507575757575,
14
+ "eval_loss": 0.6492276787757874,
15
+ "eval_runtime": 5.5974,
16
+ "eval_samples_per_second": 170.616,
17
+ "eval_steps_per_second": 10.719,
18
+ "step": 358
19
+ },
20
+ {
21
+ "epoch": 1.4,
22
+ "grad_norm": 3.4728548526763916,
23
+ "learning_rate": 4.0879833805706716e-05,
24
+ "loss": 0.6351,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.6777462121212121,
30
+ "eval_loss": 0.6397279500961304,
31
+ "eval_runtime": 5.9337,
32
+ "eval_samples_per_second": 160.946,
33
+ "eval_steps_per_second": 10.112,
34
+ "step": 716
35
+ }
36
+ ],
37
+ "logging_steps": 500,
38
+ "max_steps": 1074,
39
+ "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 3,
41
+ "save_steps": 500,
42
+ "total_flos": 529604659826688.0,
43
+ "train_batch_size": 8,
44
+ "trial_name": null,
45
+ "trial_params": {
46
+ "learning_rate": 7.648944513471952e-05,
47
+ "num_train_epochs": 3,
48
+ "per_device_train_batch_size": 8,
49
+ "seed": 17
50
+ }
51
+ }
run-3/checkpoint-716/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d942e96edd825810bea99d8e9ba8c3e79dee5d5f647f4c147e0b3268db47d468
3
+ size 4920
run-3/checkpoint-716/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar09_20-10-28_12ef847df42e/events.out.tfevents.1710016064.12ef847df42e.2239.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fa9c5948345390d285ae9d07ddc423fa6f15d9667153b2ec30bcd3e28c77b80
3
- size 5296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23c4043969dc4a5d5639878268b2a85466b7e6408e5cdb7222484ef17ff0ee5a
3
+ size 6184