Training in progress, step 500
Browse files- model.safetensors +1 -1
- run-10/checkpoint-500/config.json +26 -0
- run-10/checkpoint-500/model.safetensors +3 -0
- run-10/checkpoint-500/optimizer.pt +3 -0
- run-10/checkpoint-500/rng_state.pth +3 -0
- run-10/checkpoint-500/scheduler.pt +3 -0
- run-10/checkpoint-500/special_tokens_map.json +7 -0
- run-10/checkpoint-500/tokenizer.json +0 -0
- run-10/checkpoint-500/tokenizer_config.json +55 -0
- run-10/checkpoint-500/trainer_state.json +49 -0
- run-10/checkpoint-500/training_args.bin +3 -0
- run-10/checkpoint-500/vocab.txt +0 -0
- run-9/checkpoint-1500/config.json +26 -0
- run-9/checkpoint-1500/model.safetensors +3 -0
- run-9/checkpoint-1500/optimizer.pt +3 -0
- run-9/checkpoint-1500/rng_state.pth +3 -0
- run-9/checkpoint-1500/scheduler.pt +3 -0
- run-9/checkpoint-1500/special_tokens_map.json +7 -0
- run-9/checkpoint-1500/tokenizer.json +0 -0
- run-9/checkpoint-1500/tokenizer_config.json +55 -0
- run-9/checkpoint-1500/trainer_state.json +81 -0
- run-9/checkpoint-1500/training_args.bin +3 -0
- run-9/checkpoint-1500/vocab.txt +0 -0
- run-9/checkpoint-2000/config.json +26 -0
- run-9/checkpoint-2000/model.safetensors +3 -0
- run-9/checkpoint-2000/optimizer.pt +3 -0
- run-9/checkpoint-2000/rng_state.pth +3 -0
- run-9/checkpoint-2000/scheduler.pt +3 -0
- run-9/checkpoint-2000/special_tokens_map.json +7 -0
- run-9/checkpoint-2000/tokenizer.json +0 -0
- run-9/checkpoint-2000/tokenizer_config.json +55 -0
- run-9/checkpoint-2000/trainer_state.json +97 -0
- run-9/checkpoint-2000/training_args.bin +3 -0
- run-9/checkpoint-2000/vocab.txt +0 -0
- 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 1340618660
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:314fca40dce046335f6f2e1b99d6bd581da6efddc8ada3abf60ab9fb65036c14
|
3 |
size 1340618660
|
run-10/checkpoint-500/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-10/checkpoint-500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:314fca40dce046335f6f2e1b99d6bd581da6efddc8ada3abf60ab9fb65036c14
|
3 |
+
size 1340618660
|
run-10/checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a3eff862cd776550fee31ca541a576263eb6260cc39dbf7232628acb093123f
|
3 |
+
size 2681472237
|
run-10/checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cb98e7f396f8e059c8d47db8cc319556058ea6647e1637d6876176292860582
|
3 |
+
size 14244
|
run-10/checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e83fb4fb7292daf79ae2b4ce292d11349cf6548f88551d3f585939c670647568
|
3 |
+
size 1064
|
run-10/checkpoint-500/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-10/checkpoint-500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-10/checkpoint-500/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-10/checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.6737967914438503,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
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": 0.7418705821037292,
|
14 |
+
"eval_loss": 0.4915386140346527,
|
15 |
+
"eval_runtime": 9.0118,
|
16 |
+
"eval_samples_per_second": 331.011,
|
17 |
+
"eval_steps_per_second": 20.751,
|
18 |
+
"step": 187
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.7596379518508911,
|
23 |
+
"eval_loss": 0.5060486197471619,
|
24 |
+
"eval_runtime": 9.006,
|
25 |
+
"eval_samples_per_second": 331.224,
|
26 |
+
"eval_steps_per_second": 20.764,
|
27 |
+
"step": 374
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.6737967914438503,
|
31 |
+
"grad_norm": 6.023440837860107,
|
32 |
+
"learning_rate": 1.743940882471145e-05,
|
33 |
+
"loss": 0.4047,
|
34 |
+
"step": 500
|
35 |
+
}
|
36 |
+
],
|
37 |
+
"logging_steps": 500,
|
38 |
+
"max_steps": 1870,
|
39 |
+
"num_input_tokens_seen": 0,
|
40 |
+
"num_train_epochs": 10,
|
41 |
+
"save_steps": 500,
|
42 |
+
"total_flos": 6672544130162484.0,
|
43 |
+
"train_batch_size": 64,
|
44 |
+
"trial_name": null,
|
45 |
+
"trial_params": {
|
46 |
+
"learning_rate": 2.3804156570956505e-05,
|
47 |
+
"per_device_train_batch_size": 64
|
48 |
+
}
|
49 |
+
}
|
run-10/checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc5dc945d20af18c94d03892d0b724309a25886ca2a3a6557699258d1d340072
|
3 |
+
size 5048
|
run-10/checkpoint-500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-9/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-9/checkpoint-1500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39e8c5ad33cf8164f024f87dc36a22563acf29ae592e1c71705037ec7667320c
|
3 |
+
size 1340618660
|
run-9/checkpoint-1500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f12d667f5c67fd69e8e772778d89a8dcb99e11ee7f9a596de8c5404545a0e226
|
3 |
+
size 2681472237
|
run-9/checkpoint-1500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd348b5ed52326f9e7c0a4fc04aeede902c855e83469ebb30ebe75d48562d6f0
|
3 |
+
size 14244
|
run-9/checkpoint-1500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebc76ec48ceaac6e0f7b27e9f803095c2f4bae177411fb0385a7a5f96a94f615
|
3 |
+
size 1064
|
run-9/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-9/checkpoint-1500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-9/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-9/checkpoint-1500/trainer_state.json
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.021447721179625,
|
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": 1.0,
|
13 |
+
"eval_accuracy": 0.7425410747528076,
|
14 |
+
"eval_loss": 0.48700496554374695,
|
15 |
+
"eval_runtime": 8.9854,
|
16 |
+
"eval_samples_per_second": 331.985,
|
17 |
+
"eval_steps_per_second": 20.812,
|
18 |
+
"step": 373
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.3404825737265416,
|
22 |
+
"grad_norm": 33.510581970214844,
|
23 |
+
"learning_rate": 6.933164670907242e-06,
|
24 |
+
"loss": 0.5256,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.755950391292572,
|
30 |
+
"eval_loss": 0.5059512257575989,
|
31 |
+
"eval_runtime": 8.9914,
|
32 |
+
"eval_samples_per_second": 331.761,
|
33 |
+
"eval_steps_per_second": 20.798,
|
34 |
+
"step": 746
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.680965147453083,
|
38 |
+
"grad_norm": 13.22558307647705,
|
39 |
+
"learning_rate": 5.859919365813242e-06,
|
40 |
+
"loss": 0.3496,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_accuracy": 0.7542742490768433,
|
46 |
+
"eval_loss": 0.5935600399971008,
|
47 |
+
"eval_runtime": 8.9199,
|
48 |
+
"eval_samples_per_second": 334.419,
|
49 |
+
"eval_steps_per_second": 20.964,
|
50 |
+
"step": 1119
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.7579618096351624,
|
55 |
+
"eval_loss": 0.7120195031166077,
|
56 |
+
"eval_runtime": 8.9843,
|
57 |
+
"eval_samples_per_second": 332.025,
|
58 |
+
"eval_steps_per_second": 20.814,
|
59 |
+
"step": 1492
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.021447721179625,
|
63 |
+
"grad_norm": 4.5996317863464355,
|
64 |
+
"learning_rate": 4.786674060719241e-06,
|
65 |
+
"loss": 0.224,
|
66 |
+
"step": 1500
|
67 |
+
}
|
68 |
+
],
|
69 |
+
"logging_steps": 500,
|
70 |
+
"max_steps": 3730,
|
71 |
+
"num_input_tokens_seen": 0,
|
72 |
+
"num_train_epochs": 10,
|
73 |
+
"save_steps": 500,
|
74 |
+
"total_flos": 8230018237658640.0,
|
75 |
+
"train_batch_size": 32,
|
76 |
+
"trial_name": null,
|
77 |
+
"trial_params": {
|
78 |
+
"learning_rate": 8.006409976001242e-06,
|
79 |
+
"per_device_train_batch_size": 32
|
80 |
+
}
|
81 |
+
}
|
run-9/checkpoint-1500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f0ff942363245c6e2961749a3a4b02247c94221a607d4e27e54c30a91cf599e
|
3 |
+
size 5048
|
run-9/checkpoint-1500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-9/checkpoint-2000/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-9/checkpoint-2000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0327a11df11a52e28cabfdf5d156563bf4697816de121be56e1e7563710d16d3
|
3 |
+
size 1340618660
|
run-9/checkpoint-2000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c98d93abd1b2bd5688e1c07030de498d8fbd04c4b735cb04077d8fbad23c69b9
|
3 |
+
size 2681472237
|
run-9/checkpoint-2000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b49bea260ecfd05aebf3d6cf4bfc1d44acdc012600b03e899ea43dd79114c75d
|
3 |
+
size 14244
|
run-9/checkpoint-2000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b7e9cd1680f5afecb745b0b35f28123d60300c6af101e6f74f975f2597d00b1
|
3 |
+
size 1064
|
run-9/checkpoint-2000/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-9/checkpoint-2000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-9/checkpoint-2000/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-9/checkpoint-2000/trainer_state.json
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.361930294906166,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2000,
|
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": 0.7425410747528076,
|
14 |
+
"eval_loss": 0.48700496554374695,
|
15 |
+
"eval_runtime": 8.9854,
|
16 |
+
"eval_samples_per_second": 331.985,
|
17 |
+
"eval_steps_per_second": 20.812,
|
18 |
+
"step": 373
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.3404825737265416,
|
22 |
+
"grad_norm": 33.510581970214844,
|
23 |
+
"learning_rate": 6.933164670907242e-06,
|
24 |
+
"loss": 0.5256,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.755950391292572,
|
30 |
+
"eval_loss": 0.5059512257575989,
|
31 |
+
"eval_runtime": 8.9914,
|
32 |
+
"eval_samples_per_second": 331.761,
|
33 |
+
"eval_steps_per_second": 20.798,
|
34 |
+
"step": 746
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.680965147453083,
|
38 |
+
"grad_norm": 13.22558307647705,
|
39 |
+
"learning_rate": 5.859919365813242e-06,
|
40 |
+
"loss": 0.3496,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_accuracy": 0.7542742490768433,
|
46 |
+
"eval_loss": 0.5935600399971008,
|
47 |
+
"eval_runtime": 8.9199,
|
48 |
+
"eval_samples_per_second": 334.419,
|
49 |
+
"eval_steps_per_second": 20.964,
|
50 |
+
"step": 1119
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.7579618096351624,
|
55 |
+
"eval_loss": 0.7120195031166077,
|
56 |
+
"eval_runtime": 8.9843,
|
57 |
+
"eval_samples_per_second": 332.025,
|
58 |
+
"eval_steps_per_second": 20.814,
|
59 |
+
"step": 1492
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.021447721179625,
|
63 |
+
"grad_norm": 4.5996317863464355,
|
64 |
+
"learning_rate": 4.786674060719241e-06,
|
65 |
+
"loss": 0.224,
|
66 |
+
"step": 1500
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 5.0,
|
70 |
+
"eval_accuracy": 0.7582970261573792,
|
71 |
+
"eval_loss": 0.767949104309082,
|
72 |
+
"eval_runtime": 8.9834,
|
73 |
+
"eval_samples_per_second": 332.058,
|
74 |
+
"eval_steps_per_second": 20.816,
|
75 |
+
"step": 1865
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 5.361930294906166,
|
79 |
+
"grad_norm": 3.896700620651245,
|
80 |
+
"learning_rate": 3.7134287556252405e-06,
|
81 |
+
"loss": 0.1296,
|
82 |
+
"step": 2000
|
83 |
+
}
|
84 |
+
],
|
85 |
+
"logging_steps": 500,
|
86 |
+
"max_steps": 3730,
|
87 |
+
"num_input_tokens_seen": 0,
|
88 |
+
"num_train_epochs": 10,
|
89 |
+
"save_steps": 500,
|
90 |
+
"total_flos": 1.0780349007052152e+16,
|
91 |
+
"train_batch_size": 32,
|
92 |
+
"trial_name": null,
|
93 |
+
"trial_params": {
|
94 |
+
"learning_rate": 8.006409976001242e-06,
|
95 |
+
"per_device_train_batch_size": 32
|
96 |
+
}
|
97 |
+
}
|
run-9/checkpoint-2000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f0ff942363245c6e2961749a3a4b02247c94221a607d4e27e54c30a91cf599e
|
3 |
+
size 5048
|
run-9/checkpoint-2000/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc5dc945d20af18c94d03892d0b724309a25886ca2a3a6557699258d1d340072
|
3 |
size 5048
|