Mariaaaaa commited on
Commit
dd3f68f
1 Parent(s): 526bf36

Mariaaaaa/best_model_with_bitfit

Browse files
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: prajjwal1/bert-tiny
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: checkpoints
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # checkpoints
17
+
18
+ This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6530
21
+ - Accuracy: 0.6392
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 0.0003
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 500
47
+ - num_epochs: 4
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
53
+ | 0.6751 | 1.0 | 1250 | 0.6668 | 0.626 |
54
+ | 0.6634 | 2.0 | 2500 | 0.6576 | 0.634 |
55
+ | 0.6584 | 3.0 | 3750 | 0.6556 | 0.6286 |
56
+ | 0.6548 | 4.0 | 5000 | 0.6530 | 0.6392 |
57
+
58
+
59
+ ### Framework versions
60
+
61
+ - Transformers 4.37.2
62
+ - Pytorch 2.1.0+cu121
63
+ - Datasets 2.17.1
64
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "prajjwal1/bert-tiny",
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
+ "initializer_range": 0.02,
12
+ "intermediate_size": 512,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 2,
17
+ "num_hidden_layers": 2,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.37.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c087f92c89fb34ecd55ac65bd9d9d391513e79a359c7cc035c159f654476c25c
3
+ size 17549312
run-0/checkpoint-1250/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "prajjwal1/bert-tiny",
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
+ "initializer_range": 0.02,
12
+ "intermediate_size": 512,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 2,
17
+ "num_hidden_layers": 2,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.37.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-0/checkpoint-1250/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cb0ac9475dee574184a31476daf56392c2590cac155d3ff2fe8224036d5cac7
3
+ size 17549312
run-0/checkpoint-1250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31f67dc4ad932fd15a74f16fa3a55e515f7a9e96794ff0fb4daee51a3e4db2c9
3
+ size 40805
run-0/checkpoint-1250/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7b1c3ccb4d2d5a9a8b3bdae1c75223fdd55a7bd761dd089194d28f49f825aa1
3
+ size 14244
run-0/checkpoint-1250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b8b77870406f2bacaaaa993ed168a3f9a9f933ef6201d2c8a4a8a690384667
3
+ size 1064
run-0/checkpoint-1250/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.626,
3
+ "best_model_checkpoint": "./checkpoints/run-0/checkpoint-1250",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1250,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.25,
13
+ "learning_rate": 0.00018779999999999998,
14
+ "loss": 0.6899,
15
+ "step": 313
16
+ },
17
+ {
18
+ "epoch": 0.5,
19
+ "learning_rate": 0.0002916,
20
+ "loss": 0.6815,
21
+ "step": 626
22
+ },
23
+ {
24
+ "epoch": 0.75,
25
+ "learning_rate": 0.0002707333333333333,
26
+ "loss": 0.6751,
27
+ "step": 939
28
+ },
29
+ {
30
+ "epoch": 1.0,
31
+ "eval_accuracy": 0.626,
32
+ "eval_loss": 0.6668456792831421,
33
+ "eval_runtime": 7.6525,
34
+ "eval_samples_per_second": 653.38,
35
+ "eval_steps_per_second": 81.672,
36
+ "step": 1250
37
+ }
38
+ ],
39
+ "logging_steps": 313,
40
+ "max_steps": 5000,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
43
+ "save_steps": 500,
44
+ "total_flos": 19087797288960.0,
45
+ "train_batch_size": 16,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 0.0003,
49
+ "per_device_train_batch_size": 16
50
+ }
51
+ }
run-0/checkpoint-1250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3236f86e0b159c9991b34d915361fd9b07b129777aa98cc5e19134aa7282032c
3
+ size 4664
run-0/checkpoint-2500/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "prajjwal1/bert-tiny",
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
+ "initializer_range": 0.02,
12
+ "intermediate_size": 512,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 2,
17
+ "num_hidden_layers": 2,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.37.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-0/checkpoint-2500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0629337c2173551a7e99b0fc8b7c97988eb9fdf4362409a8f46a0eeb28bba97d
3
+ size 17549312
run-0/checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f54192d7c77fd2eb6116a2fda633c238187f364f86c8dab47bfd3f0a43b5e811
3
+ size 40805
run-0/checkpoint-2500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d57ee2f69dbb1c189c7399630a4a96ea91cac95e08c010611169b72e42e1495f
3
+ size 14244
run-0/checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b27237992201a74abf308a5fe5eecd5e38f8498240f4f2ef7d630676fc7d3a09
3
+ size 1064
run-0/checkpoint-2500/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.634,
3
+ "best_model_checkpoint": "./checkpoints/run-0/checkpoint-2500",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2500,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.25,
13
+ "learning_rate": 0.00018779999999999998,
14
+ "loss": 0.6899,
15
+ "step": 313
16
+ },
17
+ {
18
+ "epoch": 0.5,
19
+ "learning_rate": 0.0002916,
20
+ "loss": 0.6815,
21
+ "step": 626
22
+ },
23
+ {
24
+ "epoch": 0.75,
25
+ "learning_rate": 0.0002707333333333333,
26
+ "loss": 0.6751,
27
+ "step": 939
28
+ },
29
+ {
30
+ "epoch": 1.0,
31
+ "eval_accuracy": 0.626,
32
+ "eval_loss": 0.6668456792831421,
33
+ "eval_runtime": 7.6525,
34
+ "eval_samples_per_second": 653.38,
35
+ "eval_steps_per_second": 81.672,
36
+ "step": 1250
37
+ },
38
+ {
39
+ "epoch": 1.0,
40
+ "learning_rate": 0.00024986666666666665,
41
+ "loss": 0.6697,
42
+ "step": 1252
43
+ },
44
+ {
45
+ "epoch": 1.25,
46
+ "learning_rate": 0.00022899999999999998,
47
+ "loss": 0.6678,
48
+ "step": 1565
49
+ },
50
+ {
51
+ "epoch": 1.5,
52
+ "learning_rate": 0.00020813333333333334,
53
+ "loss": 0.6671,
54
+ "step": 1878
55
+ },
56
+ {
57
+ "epoch": 1.75,
58
+ "learning_rate": 0.00018726666666666665,
59
+ "loss": 0.6634,
60
+ "step": 2191
61
+ },
62
+ {
63
+ "epoch": 2.0,
64
+ "eval_accuracy": 0.634,
65
+ "eval_loss": 0.6575816869735718,
66
+ "eval_runtime": 7.6029,
67
+ "eval_samples_per_second": 657.642,
68
+ "eval_steps_per_second": 82.205,
69
+ "step": 2500
70
+ }
71
+ ],
72
+ "logging_steps": 313,
73
+ "max_steps": 5000,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 4,
76
+ "save_steps": 500,
77
+ "total_flos": 44538193674240.0,
78
+ "train_batch_size": 16,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "learning_rate": 0.0003,
82
+ "per_device_train_batch_size": 16
83
+ }
84
+ }
run-0/checkpoint-2500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3236f86e0b159c9991b34d915361fd9b07b129777aa98cc5e19134aa7282032c
3
+ size 4664
run-0/checkpoint-3750/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "prajjwal1/bert-tiny",
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
+ "initializer_range": 0.02,
12
+ "intermediate_size": 512,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 2,
17
+ "num_hidden_layers": 2,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.37.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-0/checkpoint-3750/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8addbedaf442e1bf9f5fea405f726b19c2734f37bb807cbdb61480a632858b8
3
+ size 17549312
run-0/checkpoint-3750/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffaeb45c8708f9f8b578462ae2801235386a569b9c51336b6995daff0741d3c1
3
+ size 40805
run-0/checkpoint-3750/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3098b823e87fe48df3b74feeaa69c5bd28d4f5b615ec3f26585fbe5696b01048
3
+ size 14244
run-0/checkpoint-3750/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca4494508bf2ee18104465611a37a19c2ea8f26b1e37e181499ab7525c1aae8e
3
+ size 1064
run-0/checkpoint-3750/trainer_state.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.634,
3
+ "best_model_checkpoint": "./checkpoints/run-0/checkpoint-2500",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3750,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.25,
13
+ "learning_rate": 0.00018779999999999998,
14
+ "loss": 0.6899,
15
+ "step": 313
16
+ },
17
+ {
18
+ "epoch": 0.5,
19
+ "learning_rate": 0.0002916,
20
+ "loss": 0.6815,
21
+ "step": 626
22
+ },
23
+ {
24
+ "epoch": 0.75,
25
+ "learning_rate": 0.0002707333333333333,
26
+ "loss": 0.6751,
27
+ "step": 939
28
+ },
29
+ {
30
+ "epoch": 1.0,
31
+ "eval_accuracy": 0.626,
32
+ "eval_loss": 0.6668456792831421,
33
+ "eval_runtime": 7.6525,
34
+ "eval_samples_per_second": 653.38,
35
+ "eval_steps_per_second": 81.672,
36
+ "step": 1250
37
+ },
38
+ {
39
+ "epoch": 1.0,
40
+ "learning_rate": 0.00024986666666666665,
41
+ "loss": 0.6697,
42
+ "step": 1252
43
+ },
44
+ {
45
+ "epoch": 1.25,
46
+ "learning_rate": 0.00022899999999999998,
47
+ "loss": 0.6678,
48
+ "step": 1565
49
+ },
50
+ {
51
+ "epoch": 1.5,
52
+ "learning_rate": 0.00020813333333333334,
53
+ "loss": 0.6671,
54
+ "step": 1878
55
+ },
56
+ {
57
+ "epoch": 1.75,
58
+ "learning_rate": 0.00018726666666666665,
59
+ "loss": 0.6634,
60
+ "step": 2191
61
+ },
62
+ {
63
+ "epoch": 2.0,
64
+ "eval_accuracy": 0.634,
65
+ "eval_loss": 0.6575816869735718,
66
+ "eval_runtime": 7.6029,
67
+ "eval_samples_per_second": 657.642,
68
+ "eval_steps_per_second": 82.205,
69
+ "step": 2500
70
+ },
71
+ {
72
+ "epoch": 2.0,
73
+ "learning_rate": 0.00016639999999999998,
74
+ "loss": 0.6587,
75
+ "step": 2504
76
+ },
77
+ {
78
+ "epoch": 2.25,
79
+ "learning_rate": 0.0001455333333333333,
80
+ "loss": 0.6592,
81
+ "step": 2817
82
+ },
83
+ {
84
+ "epoch": 2.5,
85
+ "learning_rate": 0.00012466666666666667,
86
+ "loss": 0.6576,
87
+ "step": 3130
88
+ },
89
+ {
90
+ "epoch": 2.75,
91
+ "learning_rate": 0.00010379999999999999,
92
+ "loss": 0.6584,
93
+ "step": 3443
94
+ },
95
+ {
96
+ "epoch": 3.0,
97
+ "eval_accuracy": 0.6286,
98
+ "eval_loss": 0.6556090712547302,
99
+ "eval_runtime": 7.6842,
100
+ "eval_samples_per_second": 650.684,
101
+ "eval_steps_per_second": 81.335,
102
+ "step": 3750
103
+ }
104
+ ],
105
+ "logging_steps": 313,
106
+ "max_steps": 5000,
107
+ "num_input_tokens_seen": 0,
108
+ "num_train_epochs": 4,
109
+ "save_steps": 500,
110
+ "total_flos": 69988590059520.0,
111
+ "train_batch_size": 16,
112
+ "trial_name": null,
113
+ "trial_params": {
114
+ "learning_rate": 0.0003,
115
+ "per_device_train_batch_size": 16
116
+ }
117
+ }
run-0/checkpoint-3750/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3236f86e0b159c9991b34d915361fd9b07b129777aa98cc5e19134aa7282032c
3
+ size 4664
run-0/checkpoint-5000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "prajjwal1/bert-tiny",
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
+ "initializer_range": 0.02,
12
+ "intermediate_size": 512,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 2,
17
+ "num_hidden_layers": 2,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.37.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-0/checkpoint-5000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c087f92c89fb34ecd55ac65bd9d9d391513e79a359c7cc035c159f654476c25c
3
+ size 17549312
run-0/checkpoint-5000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0a36d74fcc2b4a08025b97cbc8cb387d95eb4aa0aa07af7fc4f6410b0c1c0be
3
+ size 40805
run-0/checkpoint-5000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7d540daf0a7410db08f8a7673a817be2bc75893e9826b486974ca3ff5dc6c74
3
+ size 14244
run-0/checkpoint-5000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5ea909a9a1709835fb587fc769c92ff497ebd1ac747a4345abd483b61f725e8
3
+ size 1064
run-0/checkpoint-5000/trainer_state.json ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6392,
3
+ "best_model_checkpoint": "./checkpoints/run-0/checkpoint-5000",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5000,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.25,
13
+ "learning_rate": 0.00018779999999999998,
14
+ "loss": 0.6899,
15
+ "step": 313
16
+ },
17
+ {
18
+ "epoch": 0.5,
19
+ "learning_rate": 0.0002916,
20
+ "loss": 0.6815,
21
+ "step": 626
22
+ },
23
+ {
24
+ "epoch": 0.75,
25
+ "learning_rate": 0.0002707333333333333,
26
+ "loss": 0.6751,
27
+ "step": 939
28
+ },
29
+ {
30
+ "epoch": 1.0,
31
+ "eval_accuracy": 0.626,
32
+ "eval_loss": 0.6668456792831421,
33
+ "eval_runtime": 7.6525,
34
+ "eval_samples_per_second": 653.38,
35
+ "eval_steps_per_second": 81.672,
36
+ "step": 1250
37
+ },
38
+ {
39
+ "epoch": 1.0,
40
+ "learning_rate": 0.00024986666666666665,
41
+ "loss": 0.6697,
42
+ "step": 1252
43
+ },
44
+ {
45
+ "epoch": 1.25,
46
+ "learning_rate": 0.00022899999999999998,
47
+ "loss": 0.6678,
48
+ "step": 1565
49
+ },
50
+ {
51
+ "epoch": 1.5,
52
+ "learning_rate": 0.00020813333333333334,
53
+ "loss": 0.6671,
54
+ "step": 1878
55
+ },
56
+ {
57
+ "epoch": 1.75,
58
+ "learning_rate": 0.00018726666666666665,
59
+ "loss": 0.6634,
60
+ "step": 2191
61
+ },
62
+ {
63
+ "epoch": 2.0,
64
+ "eval_accuracy": 0.634,
65
+ "eval_loss": 0.6575816869735718,
66
+ "eval_runtime": 7.6029,
67
+ "eval_samples_per_second": 657.642,
68
+ "eval_steps_per_second": 82.205,
69
+ "step": 2500
70
+ },
71
+ {
72
+ "epoch": 2.0,
73
+ "learning_rate": 0.00016639999999999998,
74
+ "loss": 0.6587,
75
+ "step": 2504
76
+ },
77
+ {
78
+ "epoch": 2.25,
79
+ "learning_rate": 0.0001455333333333333,
80
+ "loss": 0.6592,
81
+ "step": 2817
82
+ },
83
+ {
84
+ "epoch": 2.5,
85
+ "learning_rate": 0.00012466666666666667,
86
+ "loss": 0.6576,
87
+ "step": 3130
88
+ },
89
+ {
90
+ "epoch": 2.75,
91
+ "learning_rate": 0.00010379999999999999,
92
+ "loss": 0.6584,
93
+ "step": 3443
94
+ },
95
+ {
96
+ "epoch": 3.0,
97
+ "eval_accuracy": 0.6286,
98
+ "eval_loss": 0.6556090712547302,
99
+ "eval_runtime": 7.6842,
100
+ "eval_samples_per_second": 650.684,
101
+ "eval_steps_per_second": 81.335,
102
+ "step": 3750
103
+ },
104
+ {
105
+ "epoch": 3.0,
106
+ "learning_rate": 8.293333333333332e-05,
107
+ "loss": 0.6575,
108
+ "step": 3756
109
+ },
110
+ {
111
+ "epoch": 3.26,
112
+ "learning_rate": 6.206666666666667e-05,
113
+ "loss": 0.6566,
114
+ "step": 4069
115
+ },
116
+ {
117
+ "epoch": 3.51,
118
+ "learning_rate": 4.12e-05,
119
+ "loss": 0.6554,
120
+ "step": 4382
121
+ },
122
+ {
123
+ "epoch": 3.76,
124
+ "learning_rate": 2.0333333333333334e-05,
125
+ "loss": 0.6548,
126
+ "step": 4695
127
+ },
128
+ {
129
+ "epoch": 4.0,
130
+ "eval_accuracy": 0.6392,
131
+ "eval_loss": 0.6530249714851379,
132
+ "eval_runtime": 6.6707,
133
+ "eval_samples_per_second": 749.551,
134
+ "eval_steps_per_second": 93.694,
135
+ "step": 5000
136
+ }
137
+ ],
138
+ "logging_steps": 313,
139
+ "max_steps": 5000,
140
+ "num_input_tokens_seen": 0,
141
+ "num_train_epochs": 4,
142
+ "save_steps": 500,
143
+ "total_flos": 95438986444800.0,
144
+ "train_batch_size": 16,
145
+ "trial_name": null,
146
+ "trial_params": {
147
+ "learning_rate": 0.0003,
148
+ "per_device_train_batch_size": 16
149
+ }
150
+ }
run-0/checkpoint-5000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3236f86e0b159c9991b34d915361fd9b07b129777aa98cc5e19134aa7282032c
3
+ size 4664
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3236f86e0b159c9991b34d915361fd9b07b129777aa98cc5e19134aa7282032c
3
+ size 4664