inflaton commited on
Commit
e9de5a8
1 Parent(s): 40ebd38

Training in progress, step 1500

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55a3484b48419f07c424793a636f438e5be98723c7e023c9e2e29ef5900e6a64
3
  size 1340618660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34252db81cafe6a3ad993f4e72c27bb8ca09b8d29c44a432a87a0190ba4cb73f
3
  size 1340618660
run-1/checkpoint-1000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.40.1",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-1/checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d009ef357a0829c93c09d8ce00ff26dd6c1e096b8dfc35bd3f95b216e74ae25d
3
+ size 1340618660
run-1/checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08f70da47dad28d4b85e22f4f0e057e5980de9db99aecec2b091cffaa85872a7
3
+ size 2681472237
run-1/checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e1a256d949d074cb5d76270949caf88a9f9cee6049fc1f352d070a28cfba690
3
+ size 14244
run-1/checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef3f76393e84c597145bff194cbeb6bd4e66003f9432ec0a78465f3a6ad9518d
3
+ size 1064
run-1/checkpoint-1000/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-1/checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1000/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-1/checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.3404825737265416,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6702412868632708,
13
+ "grad_norm": 2.054403066635132,
14
+ "learning_rate": 6.75599008099931e-05,
15
+ "loss": 0.6856,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.4924572706222534,
21
+ "eval_loss": 0.6931472420692444,
22
+ "eval_runtime": 8.9909,
23
+ "eval_samples_per_second": 331.779,
24
+ "eval_steps_per_second": 20.799,
25
+ "step": 746
26
+ },
27
+ {
28
+ "epoch": 1.3404825737265416,
29
+ "grad_norm": 1.88927161693573,
30
+ "learning_rate": 6.270645965984992e-05,
31
+ "loss": 0.7049,
32
+ "step": 1000
33
+ }
34
+ ],
35
+ "logging_steps": 500,
36
+ "max_steps": 7460,
37
+ "num_input_tokens_seen": 0,
38
+ "num_train_epochs": 10,
39
+ "save_steps": 500,
40
+ "total_flos": 2602962871446816.0,
41
+ "train_batch_size": 16,
42
+ "trial_name": null,
43
+ "trial_params": {
44
+ "learning_rate": 7.241334196013627e-05,
45
+ "per_device_train_batch_size": 16
46
+ }
47
+ }
run-1/checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8b84e61f586cb20b2c4e1e6244f78e82e764d02e70b26c7984764a166fcb30
3
+ size 5048
run-1/checkpoint-1000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1500/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.40.1",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-1/checkpoint-1500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34252db81cafe6a3ad993f4e72c27bb8ca09b8d29c44a432a87a0190ba4cb73f
3
+ size 1340618660
run-1/checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41705f21a2f001d0c2ab8307d3fe982c3a22481a66c467f852a2b7b1f78fb46a
3
+ size 2681472237
run-1/checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec6c109e0b81728091fd53d38fe23ff184b43ac15b141962e34b108757cda4da
3
+ size 14244
run-1/checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1efabb19c2bdaab4465db8143c6f335c994077e57f9a75bbcfe8dca89ec017a1
3
+ size 1064
run-1/checkpoint-1500/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-1/checkpoint-1500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1500/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-1/checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0107238605898123,
5
+ "eval_steps": 500,
6
+ "global_step": 1500,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6702412868632708,
13
+ "grad_norm": 2.054403066635132,
14
+ "learning_rate": 6.75599008099931e-05,
15
+ "loss": 0.6856,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.4924572706222534,
21
+ "eval_loss": 0.6931472420692444,
22
+ "eval_runtime": 8.9909,
23
+ "eval_samples_per_second": 331.779,
24
+ "eval_steps_per_second": 20.799,
25
+ "step": 746
26
+ },
27
+ {
28
+ "epoch": 1.3404825737265416,
29
+ "grad_norm": 1.88927161693573,
30
+ "learning_rate": 6.270645965984992e-05,
31
+ "loss": 0.7049,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.5129064917564392,
37
+ "eval_loss": 0.6931472420692444,
38
+ "eval_runtime": 9.0209,
39
+ "eval_samples_per_second": 330.678,
40
+ "eval_steps_per_second": 20.73,
41
+ "step": 1492
42
+ },
43
+ {
44
+ "epoch": 2.0107238605898123,
45
+ "grad_norm": 1.888950228691101,
46
+ "learning_rate": 5.7853018509706724e-05,
47
+ "loss": 0.7041,
48
+ "step": 1500
49
+ }
50
+ ],
51
+ "logging_steps": 500,
52
+ "max_steps": 7460,
53
+ "num_input_tokens_seen": 0,
54
+ "num_train_epochs": 10,
55
+ "save_steps": 500,
56
+ "total_flos": 3914742842009676.0,
57
+ "train_batch_size": 16,
58
+ "trial_name": null,
59
+ "trial_params": {
60
+ "learning_rate": 7.241334196013627e-05,
61
+ "per_device_train_batch_size": 16
62
+ }
63
+ }
run-1/checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8b84e61f586cb20b2c4e1e6244f78e82e764d02e70b26c7984764a166fcb30
3
+ size 5048
run-1/checkpoint-1500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff