Training in progress, step 7000
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- model.safetensors +1 -1
- run-19/checkpoint-4000/config.json +26 -0
- run-19/checkpoint-4000/model.safetensors +3 -0
- run-19/checkpoint-4000/optimizer.pt +3 -0
- run-19/checkpoint-4000/rng_state.pth +3 -0
- run-19/checkpoint-4000/scheduler.pt +3 -0
- run-19/checkpoint-4000/special_tokens_map.json +7 -0
- run-19/checkpoint-4000/tokenizer.json +0 -0
- run-19/checkpoint-4000/tokenizer_config.json +55 -0
- run-19/checkpoint-4000/trainer_state.json +125 -0
- run-19/checkpoint-4000/training_args.bin +3 -0
- run-19/checkpoint-4000/vocab.txt +0 -0
- run-19/checkpoint-4500/config.json +26 -0
- run-19/checkpoint-4500/model.safetensors +3 -0
- run-19/checkpoint-4500/optimizer.pt +3 -0
- run-19/checkpoint-4500/rng_state.pth +3 -0
- run-19/checkpoint-4500/scheduler.pt +3 -0
- run-19/checkpoint-4500/special_tokens_map.json +7 -0
- run-19/checkpoint-4500/tokenizer.json +0 -0
- run-19/checkpoint-4500/tokenizer_config.json +55 -0
- run-19/checkpoint-4500/trainer_state.json +141 -0
- run-19/checkpoint-4500/training_args.bin +3 -0
- run-19/checkpoint-4500/vocab.txt +0 -0
- run-19/checkpoint-5000/config.json +26 -0
- run-19/checkpoint-5000/model.safetensors +3 -0
- run-19/checkpoint-5000/optimizer.pt +3 -0
- run-19/checkpoint-5000/rng_state.pth +3 -0
- run-19/checkpoint-5000/scheduler.pt +3 -0
- run-19/checkpoint-5000/special_tokens_map.json +7 -0
- run-19/checkpoint-5000/tokenizer.json +0 -0
- run-19/checkpoint-5000/tokenizer_config.json +55 -0
- run-19/checkpoint-5000/trainer_state.json +148 -0
- run-19/checkpoint-5000/training_args.bin +3 -0
- run-19/checkpoint-5000/vocab.txt +0 -0
- run-19/checkpoint-5500/config.json +26 -0
- run-19/checkpoint-5500/model.safetensors +3 -0
- run-19/checkpoint-5500/optimizer.pt +3 -0
- run-19/checkpoint-5500/rng_state.pth +3 -0
- run-19/checkpoint-5500/scheduler.pt +3 -0
- run-19/checkpoint-5500/special_tokens_map.json +7 -0
- run-19/checkpoint-5500/tokenizer.json +0 -0
- run-19/checkpoint-5500/tokenizer_config.json +55 -0
- run-19/checkpoint-5500/trainer_state.json +164 -0
- run-19/checkpoint-5500/training_args.bin +3 -0
- run-19/checkpoint-5500/vocab.txt +0 -0
- run-19/checkpoint-6000/config.json +26 -0
- run-19/checkpoint-6000/model.safetensors +3 -0
- run-19/checkpoint-6000/optimizer.pt +3 -0
- run-19/checkpoint-6000/rng_state.pth +3 -0
- run-19/checkpoint-6000/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 1340618660
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4aefc1e273c7b854ce79fbf89143ffaaa58dc72848293d37f97e6122859bdb79
|
3 |
size 1340618660
|
run-19/checkpoint-4000/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-19/checkpoint-4000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb0f559f09f91876b2789941332e0a0bbf3886569d5a1dfc1e73beb7ef660215
|
3 |
+
size 1340618660
|
run-19/checkpoint-4000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a7ff18a8f5398a8ff2b875bbab9ee0e5b148ec37d225e9c0402eaefc9ad6660
|
3 |
+
size 2681472237
|
run-19/checkpoint-4000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:964f4b0fc1ae48263176e28a78d31a31267f7cb8f04acc9b199d89800cfff478
|
3 |
+
size 14244
|
run-19/checkpoint-4000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bb6f332dbf9964cc35b17527f063876c1eda946a2e6e032ef0f7c2dfcab5209
|
3 |
+
size 1064
|
run-19/checkpoint-4000/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-19/checkpoint-4000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-19/checkpoint-4000/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-19/checkpoint-4000/trainer_state.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.361930294906166,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 4000,
|
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": 12.96187973022461,
|
14 |
+
"learning_rate": 5.852478627669732e-06,
|
15 |
+
"loss": 0.5779,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7619845867156982,
|
21 |
+
"eval_loss": 0.48268476128578186,
|
22 |
+
"eval_runtime": 9.469,
|
23 |
+
"eval_samples_per_second": 315.027,
|
24 |
+
"eval_steps_per_second": 19.749,
|
25 |
+
"step": 746
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.3404825737265416,
|
29 |
+
"grad_norm": 19.64900779724121,
|
30 |
+
"learning_rate": 5.432041944647482e-06,
|
31 |
+
"loss": 0.464,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.7680187821388245,
|
37 |
+
"eval_loss": 0.5030698180198669,
|
38 |
+
"eval_runtime": 9.5015,
|
39 |
+
"eval_samples_per_second": 313.951,
|
40 |
+
"eval_steps_per_second": 19.681,
|
41 |
+
"step": 1492
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.0107238605898123,
|
45 |
+
"grad_norm": 9.11796760559082,
|
46 |
+
"learning_rate": 5.0116052616252305e-06,
|
47 |
+
"loss": 0.4025,
|
48 |
+
"step": 1500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.680965147453083,
|
52 |
+
"grad_norm": 11.002016067504883,
|
53 |
+
"learning_rate": 4.59116857860298e-06,
|
54 |
+
"loss": 0.2688,
|
55 |
+
"step": 2000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 3.0,
|
59 |
+
"eval_accuracy": 0.7747234106063843,
|
60 |
+
"eval_loss": 0.5899690389633179,
|
61 |
+
"eval_runtime": 9.4806,
|
62 |
+
"eval_samples_per_second": 314.643,
|
63 |
+
"eval_steps_per_second": 19.725,
|
64 |
+
"step": 2238
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 3.351206434316354,
|
68 |
+
"grad_norm": 3.2045211791992188,
|
69 |
+
"learning_rate": 4.170731895580729e-06,
|
70 |
+
"loss": 0.2182,
|
71 |
+
"step": 2500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 4.0,
|
75 |
+
"eval_accuracy": 0.7673482894897461,
|
76 |
+
"eval_loss": 0.7394132614135742,
|
77 |
+
"eval_runtime": 9.6202,
|
78 |
+
"eval_samples_per_second": 310.077,
|
79 |
+
"eval_steps_per_second": 19.438,
|
80 |
+
"step": 2984
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 4.021447721179625,
|
84 |
+
"grad_norm": 0.5618192553520203,
|
85 |
+
"learning_rate": 3.7502952125584775e-06,
|
86 |
+
"loss": 0.1644,
|
87 |
+
"step": 3000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 4.6916890080428955,
|
91 |
+
"grad_norm": 19.86639976501465,
|
92 |
+
"learning_rate": 3.3298585295362272e-06,
|
93 |
+
"loss": 0.1173,
|
94 |
+
"step": 3500
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 5.0,
|
98 |
+
"eval_accuracy": 0.7646664381027222,
|
99 |
+
"eval_loss": 0.7920505404472351,
|
100 |
+
"eval_runtime": 9.4974,
|
101 |
+
"eval_samples_per_second": 314.085,
|
102 |
+
"eval_steps_per_second": 19.69,
|
103 |
+
"step": 3730
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 5.361930294906166,
|
107 |
+
"grad_norm": 7.497531414031982,
|
108 |
+
"learning_rate": 2.909421846513976e-06,
|
109 |
+
"loss": 0.1026,
|
110 |
+
"step": 4000
|
111 |
+
}
|
112 |
+
],
|
113 |
+
"logging_steps": 500,
|
114 |
+
"max_steps": 7460,
|
115 |
+
"num_input_tokens_seen": 0,
|
116 |
+
"num_train_epochs": 10,
|
117 |
+
"save_steps": 500,
|
118 |
+
"total_flos": 1.1054878313466996e+16,
|
119 |
+
"train_batch_size": 16,
|
120 |
+
"trial_name": null,
|
121 |
+
"trial_params": {
|
122 |
+
"learning_rate": 6.272915310691983e-06,
|
123 |
+
"per_device_train_batch_size": 16
|
124 |
+
}
|
125 |
+
}
|
run-19/checkpoint-4000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6269efce6728cb9542ef42bc90bc2ea1d4e3e7c322bfd020bf22664d6b551f94
|
3 |
+
size 5048
|
run-19/checkpoint-4000/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-19/checkpoint-4500/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-19/checkpoint-4500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d652f8d231b8971668f5e3fb86f9ca85c822439006a926d7aa2ec2ef8c1b86e1
|
3 |
+
size 1340618660
|
run-19/checkpoint-4500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49f8044e48ddae671d05900c6f5fef2785741cb00d8b74d931112d530c435d3f
|
3 |
+
size 2681472237
|
run-19/checkpoint-4500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c65c81fd3021fa5a65673197784a1bfa7af04999304bdf6b50fc4ee0d7de006
|
3 |
+
size 14244
|
run-19/checkpoint-4500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5eaf982abcbdd4552dc43a111b6674b60294be1163d73803906351e1150045e8
|
3 |
+
size 1064
|
run-19/checkpoint-4500/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-19/checkpoint-4500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-19/checkpoint-4500/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-19/checkpoint-4500/trainer_state.json
ADDED
@@ -0,0 +1,141 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.032171581769437,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 4500,
|
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": 12.96187973022461,
|
14 |
+
"learning_rate": 5.852478627669732e-06,
|
15 |
+
"loss": 0.5779,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7619845867156982,
|
21 |
+
"eval_loss": 0.48268476128578186,
|
22 |
+
"eval_runtime": 9.469,
|
23 |
+
"eval_samples_per_second": 315.027,
|
24 |
+
"eval_steps_per_second": 19.749,
|
25 |
+
"step": 746
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.3404825737265416,
|
29 |
+
"grad_norm": 19.64900779724121,
|
30 |
+
"learning_rate": 5.432041944647482e-06,
|
31 |
+
"loss": 0.464,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.7680187821388245,
|
37 |
+
"eval_loss": 0.5030698180198669,
|
38 |
+
"eval_runtime": 9.5015,
|
39 |
+
"eval_samples_per_second": 313.951,
|
40 |
+
"eval_steps_per_second": 19.681,
|
41 |
+
"step": 1492
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.0107238605898123,
|
45 |
+
"grad_norm": 9.11796760559082,
|
46 |
+
"learning_rate": 5.0116052616252305e-06,
|
47 |
+
"loss": 0.4025,
|
48 |
+
"step": 1500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.680965147453083,
|
52 |
+
"grad_norm": 11.002016067504883,
|
53 |
+
"learning_rate": 4.59116857860298e-06,
|
54 |
+
"loss": 0.2688,
|
55 |
+
"step": 2000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 3.0,
|
59 |
+
"eval_accuracy": 0.7747234106063843,
|
60 |
+
"eval_loss": 0.5899690389633179,
|
61 |
+
"eval_runtime": 9.4806,
|
62 |
+
"eval_samples_per_second": 314.643,
|
63 |
+
"eval_steps_per_second": 19.725,
|
64 |
+
"step": 2238
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 3.351206434316354,
|
68 |
+
"grad_norm": 3.2045211791992188,
|
69 |
+
"learning_rate": 4.170731895580729e-06,
|
70 |
+
"loss": 0.2182,
|
71 |
+
"step": 2500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 4.0,
|
75 |
+
"eval_accuracy": 0.7673482894897461,
|
76 |
+
"eval_loss": 0.7394132614135742,
|
77 |
+
"eval_runtime": 9.6202,
|
78 |
+
"eval_samples_per_second": 310.077,
|
79 |
+
"eval_steps_per_second": 19.438,
|
80 |
+
"step": 2984
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 4.021447721179625,
|
84 |
+
"grad_norm": 0.5618192553520203,
|
85 |
+
"learning_rate": 3.7502952125584775e-06,
|
86 |
+
"loss": 0.1644,
|
87 |
+
"step": 3000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 4.6916890080428955,
|
91 |
+
"grad_norm": 19.86639976501465,
|
92 |
+
"learning_rate": 3.3298585295362272e-06,
|
93 |
+
"loss": 0.1173,
|
94 |
+
"step": 3500
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 5.0,
|
98 |
+
"eval_accuracy": 0.7646664381027222,
|
99 |
+
"eval_loss": 0.7920505404472351,
|
100 |
+
"eval_runtime": 9.4974,
|
101 |
+
"eval_samples_per_second": 314.085,
|
102 |
+
"eval_steps_per_second": 19.69,
|
103 |
+
"step": 3730
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 5.361930294906166,
|
107 |
+
"grad_norm": 7.497531414031982,
|
108 |
+
"learning_rate": 2.909421846513976e-06,
|
109 |
+
"loss": 0.1026,
|
110 |
+
"step": 4000
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 6.0,
|
114 |
+
"eval_accuracy": 0.7740529775619507,
|
115 |
+
"eval_loss": 0.9123848676681519,
|
116 |
+
"eval_runtime": 9.4955,
|
117 |
+
"eval_samples_per_second": 314.147,
|
118 |
+
"eval_steps_per_second": 19.693,
|
119 |
+
"step": 4476
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 6.032171581769437,
|
123 |
+
"grad_norm": 21.95626449584961,
|
124 |
+
"learning_rate": 2.488985163491725e-06,
|
125 |
+
"loss": 0.082,
|
126 |
+
"step": 4500
|
127 |
+
}
|
128 |
+
],
|
129 |
+
"logging_steps": 500,
|
130 |
+
"max_steps": 7460,
|
131 |
+
"num_input_tokens_seen": 0,
|
132 |
+
"num_train_epochs": 10,
|
133 |
+
"save_steps": 500,
|
134 |
+
"total_flos": 1.2362610220848e+16,
|
135 |
+
"train_batch_size": 16,
|
136 |
+
"trial_name": null,
|
137 |
+
"trial_params": {
|
138 |
+
"learning_rate": 6.272915310691983e-06,
|
139 |
+
"per_device_train_batch_size": 16
|
140 |
+
}
|
141 |
+
}
|
run-19/checkpoint-4500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6269efce6728cb9542ef42bc90bc2ea1d4e3e7c322bfd020bf22664d6b551f94
|
3 |
+
size 5048
|
run-19/checkpoint-4500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-19/checkpoint-5000/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-19/checkpoint-5000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7072d8120c383505bffa543bbf63c1edbb6dbc90885dff5e685598df808a33ba
|
3 |
+
size 1340618660
|
run-19/checkpoint-5000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6aaa86f26d3e8b515f8215f889a7c69e24a60e321999a60b83e5b8aec94bbdf6
|
3 |
+
size 2681472237
|
run-19/checkpoint-5000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee6e7b4445fde26e96fc3b984ba0d561dd1184ebbc74ec417e69ac27afee388f
|
3 |
+
size 14244
|
run-19/checkpoint-5000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e86338e9094b0919b9dac730a6eb7371c4cbc31ee8f821ad4537edcd27d946ff
|
3 |
+
size 1064
|
run-19/checkpoint-5000/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-19/checkpoint-5000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-19/checkpoint-5000/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-19/checkpoint-5000/trainer_state.json
ADDED
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 6.702412868632708,
|
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": 0.6702412868632708,
|
13 |
+
"grad_norm": 12.96187973022461,
|
14 |
+
"learning_rate": 5.852478627669732e-06,
|
15 |
+
"loss": 0.5779,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7619845867156982,
|
21 |
+
"eval_loss": 0.48268476128578186,
|
22 |
+
"eval_runtime": 9.469,
|
23 |
+
"eval_samples_per_second": 315.027,
|
24 |
+
"eval_steps_per_second": 19.749,
|
25 |
+
"step": 746
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.3404825737265416,
|
29 |
+
"grad_norm": 19.64900779724121,
|
30 |
+
"learning_rate": 5.432041944647482e-06,
|
31 |
+
"loss": 0.464,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.7680187821388245,
|
37 |
+
"eval_loss": 0.5030698180198669,
|
38 |
+
"eval_runtime": 9.5015,
|
39 |
+
"eval_samples_per_second": 313.951,
|
40 |
+
"eval_steps_per_second": 19.681,
|
41 |
+
"step": 1492
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.0107238605898123,
|
45 |
+
"grad_norm": 9.11796760559082,
|
46 |
+
"learning_rate": 5.0116052616252305e-06,
|
47 |
+
"loss": 0.4025,
|
48 |
+
"step": 1500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.680965147453083,
|
52 |
+
"grad_norm": 11.002016067504883,
|
53 |
+
"learning_rate": 4.59116857860298e-06,
|
54 |
+
"loss": 0.2688,
|
55 |
+
"step": 2000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 3.0,
|
59 |
+
"eval_accuracy": 0.7747234106063843,
|
60 |
+
"eval_loss": 0.5899690389633179,
|
61 |
+
"eval_runtime": 9.4806,
|
62 |
+
"eval_samples_per_second": 314.643,
|
63 |
+
"eval_steps_per_second": 19.725,
|
64 |
+
"step": 2238
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 3.351206434316354,
|
68 |
+
"grad_norm": 3.2045211791992188,
|
69 |
+
"learning_rate": 4.170731895580729e-06,
|
70 |
+
"loss": 0.2182,
|
71 |
+
"step": 2500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 4.0,
|
75 |
+
"eval_accuracy": 0.7673482894897461,
|
76 |
+
"eval_loss": 0.7394132614135742,
|
77 |
+
"eval_runtime": 9.6202,
|
78 |
+
"eval_samples_per_second": 310.077,
|
79 |
+
"eval_steps_per_second": 19.438,
|
80 |
+
"step": 2984
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 4.021447721179625,
|
84 |
+
"grad_norm": 0.5618192553520203,
|
85 |
+
"learning_rate": 3.7502952125584775e-06,
|
86 |
+
"loss": 0.1644,
|
87 |
+
"step": 3000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 4.6916890080428955,
|
91 |
+
"grad_norm": 19.86639976501465,
|
92 |
+
"learning_rate": 3.3298585295362272e-06,
|
93 |
+
"loss": 0.1173,
|
94 |
+
"step": 3500
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 5.0,
|
98 |
+
"eval_accuracy": 0.7646664381027222,
|
99 |
+
"eval_loss": 0.7920505404472351,
|
100 |
+
"eval_runtime": 9.4974,
|
101 |
+
"eval_samples_per_second": 314.085,
|
102 |
+
"eval_steps_per_second": 19.69,
|
103 |
+
"step": 3730
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 5.361930294906166,
|
107 |
+
"grad_norm": 7.497531414031982,
|
108 |
+
"learning_rate": 2.909421846513976e-06,
|
109 |
+
"loss": 0.1026,
|
110 |
+
"step": 4000
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 6.0,
|
114 |
+
"eval_accuracy": 0.7740529775619507,
|
115 |
+
"eval_loss": 0.9123848676681519,
|
116 |
+
"eval_runtime": 9.4955,
|
117 |
+
"eval_samples_per_second": 314.147,
|
118 |
+
"eval_steps_per_second": 19.693,
|
119 |
+
"step": 4476
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 6.032171581769437,
|
123 |
+
"grad_norm": 21.95626449584961,
|
124 |
+
"learning_rate": 2.488985163491725e-06,
|
125 |
+
"loss": 0.082,
|
126 |
+
"step": 4500
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 6.702412868632708,
|
130 |
+
"grad_norm": 0.22410695254802704,
|
131 |
+
"learning_rate": 2.0685484804694742e-06,
|
132 |
+
"loss": 0.065,
|
133 |
+
"step": 5000
|
134 |
+
}
|
135 |
+
],
|
136 |
+
"logging_steps": 500,
|
137 |
+
"max_steps": 7460,
|
138 |
+
"num_input_tokens_seen": 0,
|
139 |
+
"num_train_epochs": 10,
|
140 |
+
"save_steps": 500,
|
141 |
+
"total_flos": 1.366556235578496e+16,
|
142 |
+
"train_batch_size": 16,
|
143 |
+
"trial_name": null,
|
144 |
+
"trial_params": {
|
145 |
+
"learning_rate": 6.272915310691983e-06,
|
146 |
+
"per_device_train_batch_size": 16
|
147 |
+
}
|
148 |
+
}
|
run-19/checkpoint-5000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6269efce6728cb9542ef42bc90bc2ea1d4e3e7c322bfd020bf22664d6b551f94
|
3 |
+
size 5048
|
run-19/checkpoint-5000/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-19/checkpoint-5500/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-19/checkpoint-5500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b8ae85a05964de0f4a2ef88835626a7a850c2e6af594e1b0e52678abdfb1a99
|
3 |
+
size 1340618660
|
run-19/checkpoint-5500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cbdf90f670dcd79e231b6dd10918a8d709bc52d6b561859c84cf0da719c71e9
|
3 |
+
size 2681472237
|
run-19/checkpoint-5500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd4bd4443156419aea67e93c5b42b9fa93aaa633686043f4ecd36cb3df827a6e
|
3 |
+
size 14244
|
run-19/checkpoint-5500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32c407b012ab8de6d0ec8dc9ec2f22225726fa649291914e1cf1b72410bee98c
|
3 |
+
size 1064
|
run-19/checkpoint-5500/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-19/checkpoint-5500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-19/checkpoint-5500/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-19/checkpoint-5500/trainer_state.json
ADDED
@@ -0,0 +1,164 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.372654155495979,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 5500,
|
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": 12.96187973022461,
|
14 |
+
"learning_rate": 5.852478627669732e-06,
|
15 |
+
"loss": 0.5779,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7619845867156982,
|
21 |
+
"eval_loss": 0.48268476128578186,
|
22 |
+
"eval_runtime": 9.469,
|
23 |
+
"eval_samples_per_second": 315.027,
|
24 |
+
"eval_steps_per_second": 19.749,
|
25 |
+
"step": 746
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.3404825737265416,
|
29 |
+
"grad_norm": 19.64900779724121,
|
30 |
+
"learning_rate": 5.432041944647482e-06,
|
31 |
+
"loss": 0.464,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.7680187821388245,
|
37 |
+
"eval_loss": 0.5030698180198669,
|
38 |
+
"eval_runtime": 9.5015,
|
39 |
+
"eval_samples_per_second": 313.951,
|
40 |
+
"eval_steps_per_second": 19.681,
|
41 |
+
"step": 1492
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.0107238605898123,
|
45 |
+
"grad_norm": 9.11796760559082,
|
46 |
+
"learning_rate": 5.0116052616252305e-06,
|
47 |
+
"loss": 0.4025,
|
48 |
+
"step": 1500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.680965147453083,
|
52 |
+
"grad_norm": 11.002016067504883,
|
53 |
+
"learning_rate": 4.59116857860298e-06,
|
54 |
+
"loss": 0.2688,
|
55 |
+
"step": 2000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 3.0,
|
59 |
+
"eval_accuracy": 0.7747234106063843,
|
60 |
+
"eval_loss": 0.5899690389633179,
|
61 |
+
"eval_runtime": 9.4806,
|
62 |
+
"eval_samples_per_second": 314.643,
|
63 |
+
"eval_steps_per_second": 19.725,
|
64 |
+
"step": 2238
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 3.351206434316354,
|
68 |
+
"grad_norm": 3.2045211791992188,
|
69 |
+
"learning_rate": 4.170731895580729e-06,
|
70 |
+
"loss": 0.2182,
|
71 |
+
"step": 2500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 4.0,
|
75 |
+
"eval_accuracy": 0.7673482894897461,
|
76 |
+
"eval_loss": 0.7394132614135742,
|
77 |
+
"eval_runtime": 9.6202,
|
78 |
+
"eval_samples_per_second": 310.077,
|
79 |
+
"eval_steps_per_second": 19.438,
|
80 |
+
"step": 2984
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 4.021447721179625,
|
84 |
+
"grad_norm": 0.5618192553520203,
|
85 |
+
"learning_rate": 3.7502952125584775e-06,
|
86 |
+
"loss": 0.1644,
|
87 |
+
"step": 3000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 4.6916890080428955,
|
91 |
+
"grad_norm": 19.86639976501465,
|
92 |
+
"learning_rate": 3.3298585295362272e-06,
|
93 |
+
"loss": 0.1173,
|
94 |
+
"step": 3500
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 5.0,
|
98 |
+
"eval_accuracy": 0.7646664381027222,
|
99 |
+
"eval_loss": 0.7920505404472351,
|
100 |
+
"eval_runtime": 9.4974,
|
101 |
+
"eval_samples_per_second": 314.085,
|
102 |
+
"eval_steps_per_second": 19.69,
|
103 |
+
"step": 3730
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 5.361930294906166,
|
107 |
+
"grad_norm": 7.497531414031982,
|
108 |
+
"learning_rate": 2.909421846513976e-06,
|
109 |
+
"loss": 0.1026,
|
110 |
+
"step": 4000
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 6.0,
|
114 |
+
"eval_accuracy": 0.7740529775619507,
|
115 |
+
"eval_loss": 0.9123848676681519,
|
116 |
+
"eval_runtime": 9.4955,
|
117 |
+
"eval_samples_per_second": 314.147,
|
118 |
+
"eval_steps_per_second": 19.693,
|
119 |
+
"step": 4476
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 6.032171581769437,
|
123 |
+
"grad_norm": 21.95626449584961,
|
124 |
+
"learning_rate": 2.488985163491725e-06,
|
125 |
+
"loss": 0.082,
|
126 |
+
"step": 4500
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 6.702412868632708,
|
130 |
+
"grad_norm": 0.22410695254802704,
|
131 |
+
"learning_rate": 2.0685484804694742e-06,
|
132 |
+
"loss": 0.065,
|
133 |
+
"step": 5000
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 7.0,
|
137 |
+
"eval_accuracy": 0.7720415592193604,
|
138 |
+
"eval_loss": 0.9457674026489258,
|
139 |
+
"eval_runtime": 9.4723,
|
140 |
+
"eval_samples_per_second": 314.918,
|
141 |
+
"eval_steps_per_second": 19.742,
|
142 |
+
"step": 5222
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 7.372654155495979,
|
146 |
+
"grad_norm": 53.26298904418945,
|
147 |
+
"learning_rate": 1.6481117974472235e-06,
|
148 |
+
"loss": 0.0629,
|
149 |
+
"step": 5500
|
150 |
+
}
|
151 |
+
],
|
152 |
+
"logging_steps": 500,
|
153 |
+
"max_steps": 7460,
|
154 |
+
"num_input_tokens_seen": 0,
|
155 |
+
"num_train_epochs": 10,
|
156 |
+
"save_steps": 500,
|
157 |
+
"total_flos": 1.4966570546711928e+16,
|
158 |
+
"train_batch_size": 16,
|
159 |
+
"trial_name": null,
|
160 |
+
"trial_params": {
|
161 |
+
"learning_rate": 6.272915310691983e-06,
|
162 |
+
"per_device_train_batch_size": 16
|
163 |
+
}
|
164 |
+
}
|
run-19/checkpoint-5500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6269efce6728cb9542ef42bc90bc2ea1d4e3e7c322bfd020bf22664d6b551f94
|
3 |
+
size 5048
|
run-19/checkpoint-5500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-19/checkpoint-6000/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-19/checkpoint-6000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:222c337855cb5af036286792a98d51327d23a50c06898ad8974652081a61acdf
|
3 |
+
size 1340618660
|
run-19/checkpoint-6000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c806ab7d1a3035af670a69dc57e95340e6779d352cf26af33ca6372f7dde2c4e
|
3 |
+
size 2681472237
|
run-19/checkpoint-6000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cb6c601562c14fd8f3b9d6b06f08a1bb52309eabe2bb4d684114b4d7a5fe8dc
|
3 |
+
size 14244
|
run-19/checkpoint-6000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6beb9b3c5de11cfa1655c4d50cc3169e519e7e84211bc73bd03d5f87551c103
|
3 |
+
size 1064
|