Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-5/checkpoint-156/config.json +27 -0
- run-5/checkpoint-156/model.safetensors +3 -0
- run-5/checkpoint-156/optimizer.pt +3 -0
- run-5/checkpoint-156/rng_state.pth +3 -0
- run-5/checkpoint-156/scheduler.pt +3 -0
- run-5/checkpoint-156/special_tokens_map.json +7 -0
- run-5/checkpoint-156/tokenizer.json +0 -0
- run-5/checkpoint-156/tokenizer_config.json +55 -0
- run-5/checkpoint-156/trainer_state.json +57 -0
- run-5/checkpoint-156/training_args.bin +3 -0
- run-5/checkpoint-156/vocab.txt +0 -0
- run-5/checkpoint-234/config.json +27 -0
- run-5/checkpoint-234/model.safetensors +3 -0
- run-5/checkpoint-234/optimizer.pt +3 -0
- run-5/checkpoint-234/rng_state.pth +3 -0
- run-5/checkpoint-234/scheduler.pt +3 -0
- run-5/checkpoint-234/special_tokens_map.json +7 -0
- run-5/checkpoint-234/tokenizer.json +0 -0
- run-5/checkpoint-234/tokenizer_config.json +55 -0
- run-5/checkpoint-234/trainer_state.json +66 -0
- run-5/checkpoint-234/training_args.bin +3 -0
- run-5/checkpoint-234/vocab.txt +0 -0
- run-6/checkpoint-78/config.json +2 -1
- run-6/checkpoint-78/model.safetensors +1 -1
- run-6/checkpoint-78/optimizer.pt +1 -1
- run-6/checkpoint-78/rng_state.pth +1 -1
- run-6/checkpoint-78/scheduler.pt +1 -1
- run-6/checkpoint-78/tokenizer_config.json +1 -2
- run-6/checkpoint-78/trainer_state.json +16 -26
- run-6/checkpoint-78/training_args.bin +2 -2
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 437958648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e89c04580471313c5c6f3b746ddd0ea568fdef9f5d539f6430e46b6bbe0b172d
|
3 |
size 437958648
|
run-5/checkpoint-156/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": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
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": "4.44.2",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 30522
|
27 |
+
}
|
run-5/checkpoint-156/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5b2de60c2a6549e2499a7589052291177d9ee1369517aefb1eca107e68f6d02
|
3 |
+
size 437958648
|
run-5/checkpoint-156/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d4c616a0ecd603a3ed217e18bc301b61b78c51c15bd41e15e98ec4baacabd43
|
3 |
+
size 876038394
|
run-5/checkpoint-156/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08b06d22713ab0eccf6163f8b0ec7376abad69fdc0b947461e0b301173cdd320
|
3 |
+
size 14244
|
run-5/checkpoint-156/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97515d31c8d3d5e7c210d86502845280551adc618f69ca7765b7b3854e0e8621
|
3 |
+
size 1064
|
run-5/checkpoint-156/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-5/checkpoint-156/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-5/checkpoint-156/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-5/checkpoint-156/trainer_state.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5487364620938628,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-5/checkpoint-156",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 156,
|
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": 0.5270758122743683,
|
14 |
+
"eval_loss": 0.6914958357810974,
|
15 |
+
"eval_runtime": 0.6672,
|
16 |
+
"eval_samples_per_second": 415.152,
|
17 |
+
"eval_steps_per_second": 13.489,
|
18 |
+
"step": 78
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.5487364620938628,
|
23 |
+
"eval_loss": 0.6853128671646118,
|
24 |
+
"eval_runtime": 0.7573,
|
25 |
+
"eval_samples_per_second": 365.789,
|
26 |
+
"eval_steps_per_second": 11.885,
|
27 |
+
"step": 156
|
28 |
+
}
|
29 |
+
],
|
30 |
+
"logging_steps": 500,
|
31 |
+
"max_steps": 234,
|
32 |
+
"num_input_tokens_seen": 0,
|
33 |
+
"num_train_epochs": 3,
|
34 |
+
"save_steps": 500,
|
35 |
+
"stateful_callbacks": {
|
36 |
+
"TrainerControl": {
|
37 |
+
"args": {
|
38 |
+
"should_epoch_stop": false,
|
39 |
+
"should_evaluate": false,
|
40 |
+
"should_log": false,
|
41 |
+
"should_save": true,
|
42 |
+
"should_training_stop": false
|
43 |
+
},
|
44 |
+
"attributes": {}
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"total_flos": 0,
|
48 |
+
"train_batch_size": 32,
|
49 |
+
"trial_name": null,
|
50 |
+
"trial_params": {
|
51 |
+
"dropout_rate": 0.18477489177290296,
|
52 |
+
"learning_rate": 9.403239275856386e-05,
|
53 |
+
"max_seq_length": 128,
|
54 |
+
"num_train_epochs": 3,
|
55 |
+
"per_device_train_batch_size": 32
|
56 |
+
}
|
57 |
+
}
|
run-5/checkpoint-156/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61b5a8c2f4c5528cbbda8daae81db05b04be07eb3f2cf93cc5023a85269a938c
|
3 |
+
size 5240
|
run-5/checkpoint-156/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-5/checkpoint-234/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": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
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": "4.44.2",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 30522
|
27 |
+
}
|
run-5/checkpoint-234/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc22f7cb76a34d12ad39906a380b8004706e7a3b0811a79f0846832bc63e03b2
|
3 |
+
size 437958648
|
run-5/checkpoint-234/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fd2825d220ecfc480e9b4b2154506740fa312b8aa2233e37334e0780f1a6a9e
|
3 |
+
size 876038394
|
run-5/checkpoint-234/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5893971a43e53d8cccb69cbc77f5b88d424dd9d85114d1b21fc0c54c6cb446cf
|
3 |
+
size 14244
|
run-5/checkpoint-234/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a0691afab820a80253937793254b1b6d173a2e170f524f46741e999b97a5b7c
|
3 |
+
size 1064
|
run-5/checkpoint-234/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-5/checkpoint-234/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-5/checkpoint-234/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-5/checkpoint-234/trainer_state.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6498194945848376,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-5/checkpoint-234",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 234,
|
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": 0.5270758122743683,
|
14 |
+
"eval_loss": 0.6914958357810974,
|
15 |
+
"eval_runtime": 0.6672,
|
16 |
+
"eval_samples_per_second": 415.152,
|
17 |
+
"eval_steps_per_second": 13.489,
|
18 |
+
"step": 78
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.5487364620938628,
|
23 |
+
"eval_loss": 0.6853128671646118,
|
24 |
+
"eval_runtime": 0.7573,
|
25 |
+
"eval_samples_per_second": 365.789,
|
26 |
+
"eval_steps_per_second": 11.885,
|
27 |
+
"step": 156
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 3.0,
|
31 |
+
"eval_accuracy": 0.6498194945848376,
|
32 |
+
"eval_loss": 0.6630895137786865,
|
33 |
+
"eval_runtime": 0.6982,
|
34 |
+
"eval_samples_per_second": 396.749,
|
35 |
+
"eval_steps_per_second": 12.891,
|
36 |
+
"step": 234
|
37 |
+
}
|
38 |
+
],
|
39 |
+
"logging_steps": 500,
|
40 |
+
"max_steps": 234,
|
41 |
+
"num_input_tokens_seen": 0,
|
42 |
+
"num_train_epochs": 3,
|
43 |
+
"save_steps": 500,
|
44 |
+
"stateful_callbacks": {
|
45 |
+
"TrainerControl": {
|
46 |
+
"args": {
|
47 |
+
"should_epoch_stop": false,
|
48 |
+
"should_evaluate": false,
|
49 |
+
"should_log": false,
|
50 |
+
"should_save": true,
|
51 |
+
"should_training_stop": true
|
52 |
+
},
|
53 |
+
"attributes": {}
|
54 |
+
}
|
55 |
+
},
|
56 |
+
"total_flos": 0,
|
57 |
+
"train_batch_size": 32,
|
58 |
+
"trial_name": null,
|
59 |
+
"trial_params": {
|
60 |
+
"dropout_rate": 0.18477489177290296,
|
61 |
+
"learning_rate": 9.403239275856386e-05,
|
62 |
+
"max_seq_length": 128,
|
63 |
+
"num_train_epochs": 3,
|
64 |
+
"per_device_train_batch_size": 32
|
65 |
+
}
|
66 |
+
}
|
run-5/checkpoint-234/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61b5a8c2f4c5528cbbda8daae81db05b04be07eb3f2cf93cc5023a85269a938c
|
3 |
+
size 5240
|
run-5/checkpoint-234/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-6/checkpoint-78/config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"BertForSequenceClassification"
|
4 |
],
|
@@ -19,7 +20,7 @@
|
|
19 |
"position_embedding_type": "absolute",
|
20 |
"problem_type": "single_label_classification",
|
21 |
"torch_dtype": "float32",
|
22 |
-
"transformers_version": "4.
|
23 |
"type_vocab_size": 2,
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 30522
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
|
|
20 |
"position_embedding_type": "absolute",
|
21 |
"problem_type": "single_label_classification",
|
22 |
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.44.2",
|
24 |
"type_vocab_size": 2,
|
25 |
"use_cache": true,
|
26 |
"vocab_size": 30522
|
run-6/checkpoint-78/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 437958648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e89c04580471313c5c6f3b746ddd0ea568fdef9f5d539f6430e46b6bbe0b172d
|
3 |
size 437958648
|
run-6/checkpoint-78/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 876038394
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6b1510657cbff2dcd4c6ce0841ee4c45f513590157895dbb68819946fefcbfe
|
3 |
size 876038394
|
run-6/checkpoint-78/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd53c5c3dd7d411230f105bda2473d2a3923ae5b6e14f965bb99d91f5a28c9b2
|
3 |
size 14244
|
run-6/checkpoint-78/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:360ee98d2ddf8bd8bbe9f381f550ba5951d974aab4cc86dad4ccf9be72b27837
|
3 |
size 1064
|
run-6/checkpoint-78/tokenizer_config.json
CHANGED
@@ -41,10 +41,9 @@
|
|
41 |
"special": true
|
42 |
}
|
43 |
},
|
44 |
-
"clean_up_tokenization_spaces":
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": true,
|
47 |
-
"extra_special_tokens": {},
|
48 |
"mask_token": "[MASK]",
|
49 |
"model_max_length": 512,
|
50 |
"pad_token": "[PAD]",
|
|
|
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]",
|
run-6/checkpoint-78/trainer_state.json
CHANGED
@@ -1,8 +1,7 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"epoch": 2.0,
|
6 |
"eval_steps": 500,
|
7 |
"global_step": 78,
|
8 |
"is_hyper_param_search": true,
|
@@ -11,27 +10,18 @@
|
|
11 |
"log_history": [
|
12 |
{
|
13 |
"epoch": 1.0,
|
14 |
-
"eval_accuracy": 0.
|
15 |
-
"eval_loss": 0.
|
16 |
-
"eval_runtime":
|
17 |
-
"eval_samples_per_second":
|
18 |
-
"eval_steps_per_second":
|
19 |
-
"step": 39
|
20 |
-
},
|
21 |
-
{
|
22 |
-
"epoch": 2.0,
|
23 |
-
"eval_accuracy": 0.4657039711191336,
|
24 |
-
"eval_loss": 0.7101424336433411,
|
25 |
-
"eval_runtime": 2.0197,
|
26 |
-
"eval_samples_per_second": 137.148,
|
27 |
-
"eval_steps_per_second": 2.476,
|
28 |
"step": 78
|
29 |
}
|
30 |
],
|
31 |
"logging_steps": 500,
|
32 |
-
"max_steps":
|
33 |
"num_input_tokens_seen": 0,
|
34 |
-
"num_train_epochs":
|
35 |
"save_steps": 500,
|
36 |
"stateful_callbacks": {
|
37 |
"TrainerControl": {
|
@@ -40,19 +30,19 @@
|
|
40 |
"should_evaluate": false,
|
41 |
"should_log": false,
|
42 |
"should_save": true,
|
43 |
-
"should_training_stop":
|
44 |
},
|
45 |
"attributes": {}
|
46 |
}
|
47 |
},
|
48 |
"total_flos": 0,
|
49 |
-
"train_batch_size":
|
50 |
"trial_name": null,
|
51 |
"trial_params": {
|
52 |
-
"dropout_rate": 0.
|
53 |
-
"learning_rate":
|
54 |
"max_seq_length": 64,
|
55 |
-
"num_train_epochs":
|
56 |
-
"per_device_train_batch_size":
|
57 |
}
|
58 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6389891696750902,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-6/checkpoint-78",
|
4 |
+
"epoch": 1.0,
|
|
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 78,
|
7 |
"is_hyper_param_search": true,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.6389891696750902,
|
14 |
+
"eval_loss": 0.6565788388252258,
|
15 |
+
"eval_runtime": 0.6675,
|
16 |
+
"eval_samples_per_second": 415.004,
|
17 |
+
"eval_steps_per_second": 13.484,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
"step": 78
|
19 |
}
|
20 |
],
|
21 |
"logging_steps": 500,
|
22 |
+
"max_steps": 234,
|
23 |
"num_input_tokens_seen": 0,
|
24 |
+
"num_train_epochs": 3,
|
25 |
"save_steps": 500,
|
26 |
"stateful_callbacks": {
|
27 |
"TrainerControl": {
|
|
|
30 |
"should_evaluate": false,
|
31 |
"should_log": false,
|
32 |
"should_save": true,
|
33 |
+
"should_training_stop": false
|
34 |
},
|
35 |
"attributes": {}
|
36 |
}
|
37 |
},
|
38 |
"total_flos": 0,
|
39 |
+
"train_batch_size": 32,
|
40 |
"trial_name": null,
|
41 |
"trial_params": {
|
42 |
+
"dropout_rate": 0.4981619199472148,
|
43 |
+
"learning_rate": 9.958228585906916e-05,
|
44 |
"max_seq_length": 64,
|
45 |
+
"num_train_epochs": 3,
|
46 |
+
"per_device_train_batch_size": 32
|
47 |
}
|
48 |
}
|
run-6/checkpoint-78/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ad0809de284770e15ca66b8b5774503102a1cc551fecb95f92e56ecf1f8151c
|
3 |
+
size 5240
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ad0809de284770e15ca66b8b5774503102a1cc551fecb95f92e56ecf1f8151c
|
3 |
size 5240
|