Shu Huang
commited on
Commit
路
10ccdcc
1
Parent(s):
bfd964d
best model for qa
Browse files- config.json +26 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +130 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/projects/SolarWindowsADSP/shu/models/revision/bert/batterybert-uncased/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForQuestionAnswering"
|
| 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": "4.17.0.dev0",
|
| 23 |
+
"type_vocab_size": 2,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 30522
|
| 26 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49d3e400fcbfc1ff4137977cbef8aab84909e0382d723460abc25d47b1e97f86
|
| 3 |
+
size 871270381
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a74a10d97b458d7fbf6a068839503fbafc177541083829b21d45458fe4cc6f9b
|
| 3 |
+
size 435661303
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0205e67e8e352dc6e570857d91d36d022bef4182ac03e6af9c550fc38d71d616
|
| 3 |
+
size 14657
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d5b6ed9cd004a3efe5cfb9678a485a92f5f0b15dff67e4c3e467ba37e9c9b22
|
| 3 |
+
size 14657
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49c50e6de254e9540e64a6bafc2994f79191038ebccec64aa1faf302cb816256
|
| 3 |
+
size 14657
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fd524db20c38e4e85d2ec522d1f908e140fcf3129773bb54e3caecd26979f87
|
| 3 |
+
size 14657
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b71abf5ffecb049013cf44c3e81123702c38f3da814939a9361f8ace4aceb746
|
| 3 |
+
size 14657
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee15d76d0f0279815f418ec9d410c0d307f07b7bd33213b44dc33b76be403a93
|
| 3 |
+
size 14657
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0746bc0f08d56c5ef1dad79fd699f7705b200a29ab33834f7b72926b7ae731e4
|
| 3 |
+
size 14657
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf5024ae9c1487c34f3887187a9b5a7fbc9bc053258baa4fb5bcb63093b95e80
|
| 3 |
+
size 14657
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d76a2ae72c909de0bf20a045aa9629e9f08ec33067dbaa2c8defe8ed942edad
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/projects/SolarWindowsADSP/shu/models/revision/bert/batterybert-uncased/", "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 8301,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.18,
|
| 12 |
+
"learning_rate": 2.8644741597397903e-05,
|
| 13 |
+
"loss": 2.0532,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.36,
|
| 18 |
+
"learning_rate": 2.728948319479581e-05,
|
| 19 |
+
"loss": 1.3426,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.54,
|
| 24 |
+
"learning_rate": 2.5934224792193712e-05,
|
| 25 |
+
"loss": 1.2121,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.72,
|
| 30 |
+
"learning_rate": 2.4578966389591615e-05,
|
| 31 |
+
"loss": 1.1652,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.9,
|
| 36 |
+
"learning_rate": 2.3223707986989517e-05,
|
| 37 |
+
"loss": 1.0871,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0,
|
| 42 |
+
"eval_exact_match": 79.35666982024598,
|
| 43 |
+
"eval_f1": 87.05079900714725,
|
| 44 |
+
"step": 2767
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.08,
|
| 48 |
+
"learning_rate": 2.1868449584387424e-05,
|
| 49 |
+
"loss": 0.9397,
|
| 50 |
+
"step": 3000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.26,
|
| 54 |
+
"learning_rate": 2.051319118178533e-05,
|
| 55 |
+
"loss": 0.8108,
|
| 56 |
+
"step": 3500
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.45,
|
| 60 |
+
"learning_rate": 1.9157932779183232e-05,
|
| 61 |
+
"loss": 0.8315,
|
| 62 |
+
"step": 4000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.63,
|
| 66 |
+
"learning_rate": 1.7802674376581135e-05,
|
| 67 |
+
"loss": 0.805,
|
| 68 |
+
"step": 4500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.81,
|
| 72 |
+
"learning_rate": 1.644741597397904e-05,
|
| 73 |
+
"loss": 0.8106,
|
| 74 |
+
"step": 5000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.99,
|
| 78 |
+
"learning_rate": 1.5092157571376944e-05,
|
| 79 |
+
"loss": 0.7997,
|
| 80 |
+
"step": 5500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 2.0,
|
| 84 |
+
"eval_exact_match": 80.13245033112582,
|
| 85 |
+
"eval_f1": 88.1743949836477,
|
| 86 |
+
"step": 5534
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 2.17,
|
| 90 |
+
"learning_rate": 1.3736899168774846e-05,
|
| 91 |
+
"loss": 0.5996,
|
| 92 |
+
"step": 6000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 2.35,
|
| 96 |
+
"learning_rate": 1.238164076617275e-05,
|
| 97 |
+
"loss": 0.589,
|
| 98 |
+
"step": 6500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.53,
|
| 102 |
+
"learning_rate": 1.1026382363570653e-05,
|
| 103 |
+
"loss": 0.5806,
|
| 104 |
+
"step": 7000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.71,
|
| 108 |
+
"learning_rate": 9.671123960968558e-06,
|
| 109 |
+
"loss": 0.5767,
|
| 110 |
+
"step": 7500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 2.89,
|
| 114 |
+
"learning_rate": 8.315865558366462e-06,
|
| 115 |
+
"loss": 0.5806,
|
| 116 |
+
"step": 8000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.0,
|
| 120 |
+
"eval_exact_match": 81.07852412488174,
|
| 121 |
+
"eval_f1": 88.40838871409778,
|
| 122 |
+
"step": 8301
|
| 123 |
+
}
|
| 124 |
+
],
|
| 125 |
+
"max_steps": 11068,
|
| 126 |
+
"num_train_epochs": 4,
|
| 127 |
+
"total_flos": 5.204717742535475e+16,
|
| 128 |
+
"trial_name": null,
|
| 129 |
+
"trial_params": null
|
| 130 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ecbc59331d565544c132f882489832eb4539898c3af1fb5e774d682015311f4
|
| 3 |
+
size 3183
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|