Training in progress, step 500
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- model.safetensors +1 -1
- run-11/checkpoint-500/config.json +26 -0
- run-11/checkpoint-500/model.safetensors +3 -0
- run-11/checkpoint-500/optimizer.pt +3 -0
- run-11/checkpoint-500/rng_state.pth +3 -0
- run-11/checkpoint-500/scheduler.pt +3 -0
- run-11/checkpoint-500/special_tokens_map.json +7 -0
- run-11/checkpoint-500/tokenizer.json +0 -0
- run-11/checkpoint-500/tokenizer_config.json +55 -0
- run-11/checkpoint-500/trainer_state.json +43 -0
- run-11/checkpoint-500/training_args.bin +3 -0
- run-11/checkpoint-500/vocab.txt +0 -0
- run-13/checkpoint-500/config.json +26 -0
- run-13/checkpoint-500/model.safetensors +3 -0
- run-13/checkpoint-500/optimizer.pt +3 -0
- run-13/checkpoint-500/rng_state.pth +3 -0
- run-13/checkpoint-500/scheduler.pt +3 -0
- run-13/checkpoint-500/special_tokens_map.json +7 -0
- run-13/checkpoint-500/tokenizer.json +0 -0
- run-13/checkpoint-500/tokenizer_config.json +55 -0
- run-13/checkpoint-500/trainer_state.json +43 -0
- run-13/checkpoint-500/training_args.bin +3 -0
- run-13/checkpoint-500/vocab.txt +0 -0
- run-14/checkpoint-1000/config.json +26 -0
- run-14/checkpoint-1000/model.safetensors +3 -0
- run-14/checkpoint-1000/optimizer.pt +3 -0
- run-14/checkpoint-1000/rng_state.pth +3 -0
- run-14/checkpoint-1000/scheduler.pt +3 -0
- run-14/checkpoint-1000/special_tokens_map.json +7 -0
- run-14/checkpoint-1000/tokenizer.json +0 -0
- run-14/checkpoint-1000/tokenizer_config.json +55 -0
- run-14/checkpoint-1000/trainer_state.json +68 -0
- run-14/checkpoint-1000/training_args.bin +3 -0
- run-14/checkpoint-1000/vocab.txt +0 -0
- run-14/checkpoint-1500/config.json +26 -0
- run-14/checkpoint-1500/model.safetensors +3 -0
- run-14/checkpoint-1500/optimizer.pt +3 -0
- run-14/checkpoint-1500/rng_state.pth +3 -0
- run-14/checkpoint-1500/scheduler.pt +3 -0
- run-14/checkpoint-1500/special_tokens_map.json +7 -0
- run-14/checkpoint-1500/tokenizer.json +0 -0
- run-14/checkpoint-1500/tokenizer_config.json +55 -0
- run-14/checkpoint-1500/trainer_state.json +93 -0
- run-14/checkpoint-1500/training_args.bin +3 -0
- run-14/checkpoint-1500/vocab.txt +0 -0
- run-14/checkpoint-2000/config.json +26 -0
- run-14/checkpoint-2000/model.safetensors +3 -0
- run-14/checkpoint-2000/optimizer.pt +3 -0
- run-14/checkpoint-2000/rng_state.pth +3 -0
- run-14/checkpoint-2000/scheduler.pt +3 -0
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 437955572
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4effc6e3fda704d75346bc1ff2fe3b7a0f5d58156313147c44c17deaed0a45b9
|
3 |
size 437955572
|
run-11/checkpoint-500/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-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": 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 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.41.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
run-11/checkpoint-500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3341a952d44f8c270267c1a24a30e66c4d190d4a36775047b953491494996e6
|
3 |
+
size 437955572
|
run-11/checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d670a3393503f7d5cd51faf4e59bf0b42fabc5d9aeaf503a7245359f495a9d7
|
3 |
+
size 876032250
|
run-11/checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a5a554a6a0caa6bc70d99f85df9b76b92ec635bcf7bf27f721c0541d4244d39
|
3 |
+
size 14244
|
run-11/checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:42d84dbcc61b99984680940b5a01534f914a4b5f87c355411253960ecea2e578
|
3 |
+
size 1064
|
run-11/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-11/checkpoint-500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-11/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-11/checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6702412868632708,
|
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": 0.6702412868632708,
|
13 |
+
"grad_norm": 5.156455039978027,
|
14 |
+
"learning_rate": 3.6315186794345e-05,
|
15 |
+
"loss": 0.5505,
|
16 |
+
"step": 500
|
17 |
+
}
|
18 |
+
],
|
19 |
+
"logging_steps": 500,
|
20 |
+
"max_steps": 7460,
|
21 |
+
"num_input_tokens_seen": 0,
|
22 |
+
"num_train_epochs": 10,
|
23 |
+
"save_steps": 500,
|
24 |
+
"stateful_callbacks": {
|
25 |
+
"TrainerControl": {
|
26 |
+
"args": {
|
27 |
+
"should_epoch_stop": false,
|
28 |
+
"should_evaluate": false,
|
29 |
+
"should_log": false,
|
30 |
+
"should_save": true,
|
31 |
+
"should_training_stop": false
|
32 |
+
},
|
33 |
+
"attributes": {}
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"total_flos": 2178183342362556.0,
|
37 |
+
"train_batch_size": 16,
|
38 |
+
"trial_name": null,
|
39 |
+
"trial_params": {
|
40 |
+
"learning_rate": 3.8924036420375534e-05,
|
41 |
+
"per_device_train_batch_size": 16
|
42 |
+
}
|
43 |
+
}
|
run-11/checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c9d3a1a223b1dd59d45cd2048927a516e81a5158631270535b1d9b64c418c0b
|
3 |
+
size 5176
|
run-11/checkpoint-500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-13/checkpoint-500/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-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": 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 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.41.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
run-13/checkpoint-500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3426d316c62744ec26e418dd4d0ff1797eb12a1403e9d670f9b93959d8f5f01d
|
3 |
+
size 437955572
|
run-13/checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c36260139953d439afce5f2b3b1b49199082b45cb8cd681bba11c70e11ccdd2
|
3 |
+
size 876032250
|
run-13/checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a5a554a6a0caa6bc70d99f85df9b76b92ec635bcf7bf27f721c0541d4244d39
|
3 |
+
size 14244
|
run-13/checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfb71f18694a43f2943c55b41bfaf760dfa1cab6e222e2aeaf3195b6d64c1ce8
|
3 |
+
size 1064
|
run-13/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-13/checkpoint-500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-13/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-13/checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6702412868632708,
|
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": 0.6702412868632708,
|
13 |
+
"grad_norm": 8.853421211242676,
|
14 |
+
"learning_rate": 8.82942420165961e-05,
|
15 |
+
"loss": 0.5774,
|
16 |
+
"step": 500
|
17 |
+
}
|
18 |
+
],
|
19 |
+
"logging_steps": 500,
|
20 |
+
"max_steps": 7460,
|
21 |
+
"num_input_tokens_seen": 0,
|
22 |
+
"num_train_epochs": 10,
|
23 |
+
"save_steps": 500,
|
24 |
+
"stateful_callbacks": {
|
25 |
+
"TrainerControl": {
|
26 |
+
"args": {
|
27 |
+
"should_epoch_stop": false,
|
28 |
+
"should_evaluate": false,
|
29 |
+
"should_log": false,
|
30 |
+
"should_save": true,
|
31 |
+
"should_training_stop": false
|
32 |
+
},
|
33 |
+
"attributes": {}
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"total_flos": 1071623206726440.0,
|
37 |
+
"train_batch_size": 16,
|
38 |
+
"trial_name": null,
|
39 |
+
"trial_params": {
|
40 |
+
"learning_rate": 9.463721917296077e-05,
|
41 |
+
"per_device_train_batch_size": 16
|
42 |
+
}
|
43 |
+
}
|
run-13/checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ac17a5a09caf1866ca357f3f19d54118d51396eebd33bd9df62ce3f17bfc44f
|
3 |
+
size 5176
|
run-13/checkpoint-500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-14/checkpoint-1000/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-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": 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 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.41.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
run-14/checkpoint-1000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99e80b291bd7568a61c8a913e704cc788b6ed3ed795a5e585e704a16d7949c88
|
3 |
+
size 437955572
|
run-14/checkpoint-1000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93e6b7ae4fe1077f09fc4cb4862940c37fadd5706b55910aa9a3a7a842a22ac0
|
3 |
+
size 876032250
|
run-14/checkpoint-1000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a643a0f91d5441fe1ad76d0f4f51f1b40cb1298fde9a97e55ea3bd43aab817ad
|
3 |
+
size 14244
|
run-14/checkpoint-1000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77fb6f3535c518ff7c9ca4a02f17468ecc2145a1285a8a2aa16a96f8dff8c6f8
|
3 |
+
size 1064
|
run-14/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-14/checkpoint-1000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-14/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-14/checkpoint-1000/trainer_state.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.680965147453083,
|
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": 1.0,
|
13 |
+
"eval_accuracy": 0.7505866289138794,
|
14 |
+
"eval_loss": 0.49016305804252625,
|
15 |
+
"eval_runtime": 15.5971,
|
16 |
+
"eval_samples_per_second": 191.254,
|
17 |
+
"eval_steps_per_second": 11.989,
|
18 |
+
"step": 373
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.3404825737265416,
|
22 |
+
"grad_norm": 12.849295616149902,
|
23 |
+
"learning_rate": 2.556606277870055e-05,
|
24 |
+
"loss": 0.4759,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.755950391292572,
|
30 |
+
"eval_loss": 0.5790446996688843,
|
31 |
+
"eval_runtime": 15.5284,
|
32 |
+
"eval_samples_per_second": 192.099,
|
33 |
+
"eval_steps_per_second": 12.042,
|
34 |
+
"step": 746
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.680965147453083,
|
38 |
+
"grad_norm": 10.756426811218262,
|
39 |
+
"learning_rate": 2.1608467921316566e-05,
|
40 |
+
"loss": 0.2131,
|
41 |
+
"step": 1000
|
42 |
+
}
|
43 |
+
],
|
44 |
+
"logging_steps": 500,
|
45 |
+
"max_steps": 3730,
|
46 |
+
"num_input_tokens_seen": 0,
|
47 |
+
"num_train_epochs": 10,
|
48 |
+
"save_steps": 500,
|
49 |
+
"stateful_callbacks": {
|
50 |
+
"TrainerControl": {
|
51 |
+
"args": {
|
52 |
+
"should_epoch_stop": false,
|
53 |
+
"should_evaluate": false,
|
54 |
+
"should_log": false,
|
55 |
+
"should_save": true,
|
56 |
+
"should_training_stop": false
|
57 |
+
},
|
58 |
+
"attributes": {}
|
59 |
+
}
|
60 |
+
},
|
61 |
+
"total_flos": 1596747047205192.0,
|
62 |
+
"train_batch_size": 32,
|
63 |
+
"trial_name": null,
|
64 |
+
"trial_params": {
|
65 |
+
"learning_rate": 2.9523657636084537e-05,
|
66 |
+
"per_device_train_batch_size": 32
|
67 |
+
}
|
68 |
+
}
|
run-14/checkpoint-1000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:194bd44be4aed5dd0d691adec2431dc0a381cb8d6a79de0ede4273d0d418f89b
|
3 |
+
size 5176
|
run-14/checkpoint-1000/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-14/checkpoint-1500/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-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": 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 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.41.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
run-14/checkpoint-1500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:522684b5abbc20719210b3b816f4f89a42ef0833ec8db582a4798dc1fa7c60d8
|
3 |
+
size 437955572
|
run-14/checkpoint-1500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5ac8fa7ae8c7d0f86aad9f30365a6d358a8a304e69b2acbe9937774a0fbb440
|
3 |
+
size 876032250
|
run-14/checkpoint-1500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c2e322649b8daf8c1f5e9cf2f36895895f458a82c0fee3bf9e0a84bb31e0897
|
3 |
+
size 14244
|
run-14/checkpoint-1500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b78e52be286505b3e58d2852ffed94921f30bd285253f2b4c36391992f9fa27
|
3 |
+
size 1064
|
run-14/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-14/checkpoint-1500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-14/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-14/checkpoint-1500/trainer_state.json
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": 0.7505866289138794,
|
14 |
+
"eval_loss": 0.49016305804252625,
|
15 |
+
"eval_runtime": 15.5971,
|
16 |
+
"eval_samples_per_second": 191.254,
|
17 |
+
"eval_steps_per_second": 11.989,
|
18 |
+
"step": 373
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 1.3404825737265416,
|
22 |
+
"grad_norm": 12.849295616149902,
|
23 |
+
"learning_rate": 2.556606277870055e-05,
|
24 |
+
"loss": 0.4759,
|
25 |
+
"step": 500
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"eval_accuracy": 0.755950391292572,
|
30 |
+
"eval_loss": 0.5790446996688843,
|
31 |
+
"eval_runtime": 15.5284,
|
32 |
+
"eval_samples_per_second": 192.099,
|
33 |
+
"eval_steps_per_second": 12.042,
|
34 |
+
"step": 746
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.680965147453083,
|
38 |
+
"grad_norm": 10.756426811218262,
|
39 |
+
"learning_rate": 2.1608467921316566e-05,
|
40 |
+
"loss": 0.2131,
|
41 |
+
"step": 1000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"eval_accuracy": 0.7589674592018127,
|
46 |
+
"eval_loss": 0.7497361302375793,
|
47 |
+
"eval_runtime": 16.4879,
|
48 |
+
"eval_samples_per_second": 180.921,
|
49 |
+
"eval_steps_per_second": 11.342,
|
50 |
+
"step": 1119
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"eval_accuracy": 0.7579618096351624,
|
55 |
+
"eval_loss": 0.970737636089325,
|
56 |
+
"eval_runtime": 15.8973,
|
57 |
+
"eval_samples_per_second": 187.641,
|
58 |
+
"eval_steps_per_second": 11.763,
|
59 |
+
"step": 1492
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.021447721179625,
|
63 |
+
"grad_norm": 0.3542397916316986,
|
64 |
+
"learning_rate": 1.7650873063932577e-05,
|
65 |
+
"loss": 0.0842,
|
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 |
+
"stateful_callbacks": {
|
75 |
+
"TrainerControl": {
|
76 |
+
"args": {
|
77 |
+
"should_epoch_stop": false,
|
78 |
+
"should_evaluate": false,
|
79 |
+
"should_log": false,
|
80 |
+
"should_save": true,
|
81 |
+
"should_training_stop": false
|
82 |
+
},
|
83 |
+
"attributes": {}
|
84 |
+
}
|
85 |
+
},
|
86 |
+
"total_flos": 2315934104132184.0,
|
87 |
+
"train_batch_size": 32,
|
88 |
+
"trial_name": null,
|
89 |
+
"trial_params": {
|
90 |
+
"learning_rate": 2.9523657636084537e-05,
|
91 |
+
"per_device_train_batch_size": 32
|
92 |
+
}
|
93 |
+
}
|
run-14/checkpoint-1500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:194bd44be4aed5dd0d691adec2431dc0a381cb8d6a79de0ede4273d0d418f89b
|
3 |
+
size 5176
|
run-14/checkpoint-1500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-14/checkpoint-2000/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-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": 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 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.41.2",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
run-14/checkpoint-2000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3918b4799c79d25c9c164f7457a9eaf8040fbb1aac7582858d935ca3411b351
|
3 |
+
size 437955572
|
run-14/checkpoint-2000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66e4a08b52c7e58606749322738332e8dc282701828ab4f7ece27f2c903ac34d
|
3 |
+
size 876032250
|
run-14/checkpoint-2000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb916c03fd91db0d3fdc3b875384e99fcd4fcd79c2cbbae6cdee885856e2c3d0
|
3 |
+
size 14244
|
run-14/checkpoint-2000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4f7316d5816af2559a04347dc3e09603b17ec4353b80c0e308aca4b6ed93eca
|
3 |
+
size 1064
|