ZhangYunchenY
commited on
Commit
•
67969fa
1
Parent(s):
2d877cc
[Model] bert-base-uncased-qnli
Browse files- config.json +36 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.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 +496 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/mnt/lustre/weixiuying/transformer/pretrain_models/bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"finetuning_task": "qnli",
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "entailment",
|
| 15 |
+
"1": "not_entailment"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"entailment": 0,
|
| 21 |
+
"not_entailment": 1
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-12,
|
| 24 |
+
"max_position_embeddings": 512,
|
| 25 |
+
"model_type": "bert",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_hidden_layers": 12,
|
| 28 |
+
"pad_token_id": 0,
|
| 29 |
+
"position_embedding_type": "absolute",
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.13.0.dev0",
|
| 33 |
+
"type_vocab_size": 2,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4e0196c52812a4ce94c341e5c7bc3e504c8110615de60f69e67d1231b82d384
|
| 3 |
+
size 875997219
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddadbf21d0bbfcd4b01808adbafce8e94280d5b69cea09dc394c1e0f32bc1b2b
|
| 3 |
+
size 438024851
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3754ace772c031c64f8d8b832aa950e8b315075bf24b772118808283b3023e1
|
| 3 |
+
size 14659
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c4413974fc2480bc2f2f88428b7de420c76681d15e5bf178082904ab1a5ffb1
|
| 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, "special_tokens_map_file": null, "name_or_path": "/mnt/lustre/weixiuying/transformer/pretrain_models/bert-base-uncased", "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,496 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.22899456322193146,
|
| 3 |
+
"best_model_checkpoint": "output_dir/finetuned_best_qnli/checkpoint-5000",
|
| 4 |
+
"epoch": 4.886988393402565,
|
| 5 |
+
"global_step": 16000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.15,
|
| 12 |
+
"learning_rate": 1.938912645082468e-05,
|
| 13 |
+
"loss": 0.4392,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.15,
|
| 18 |
+
"eval_accuracy": 0.8553908109097565,
|
| 19 |
+
"eval_loss": 0.32711732387542725,
|
| 20 |
+
"eval_runtime": 26.9542,
|
| 21 |
+
"eval_samples_per_second": 202.677,
|
| 22 |
+
"eval_steps_per_second": 12.688,
|
| 23 |
+
"step": 500
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.31,
|
| 27 |
+
"learning_rate": 1.8778252901649362e-05,
|
| 28 |
+
"loss": 0.3536,
|
| 29 |
+
"step": 1000
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.31,
|
| 33 |
+
"eval_accuracy": 0.8828482518762585,
|
| 34 |
+
"eval_loss": 0.2784218490123749,
|
| 35 |
+
"eval_runtime": 28.1713,
|
| 36 |
+
"eval_samples_per_second": 193.921,
|
| 37 |
+
"eval_steps_per_second": 12.14,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.46,
|
| 42 |
+
"learning_rate": 1.816737935247404e-05,
|
| 43 |
+
"loss": 0.3288,
|
| 44 |
+
"step": 1500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.46,
|
| 48 |
+
"eval_accuracy": 0.8934651290499726,
|
| 49 |
+
"eval_loss": 0.2534938454627991,
|
| 50 |
+
"eval_runtime": 24.2891,
|
| 51 |
+
"eval_samples_per_second": 224.916,
|
| 52 |
+
"eval_steps_per_second": 14.08,
|
| 53 |
+
"step": 1500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.61,
|
| 57 |
+
"learning_rate": 1.755650580329872e-05,
|
| 58 |
+
"loss": 0.3105,
|
| 59 |
+
"step": 2000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.61,
|
| 63 |
+
"eval_accuracy": 0.9033498077979132,
|
| 64 |
+
"eval_loss": 0.24962939321994781,
|
| 65 |
+
"eval_runtime": 24.0235,
|
| 66 |
+
"eval_samples_per_second": 227.402,
|
| 67 |
+
"eval_steps_per_second": 14.236,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.76,
|
| 72 |
+
"learning_rate": 1.69456322541234e-05,
|
| 73 |
+
"loss": 0.3061,
|
| 74 |
+
"step": 2500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.76,
|
| 78 |
+
"eval_accuracy": 0.900604063701263,
|
| 79 |
+
"eval_loss": 0.24303048849105835,
|
| 80 |
+
"eval_runtime": 24.6661,
|
| 81 |
+
"eval_samples_per_second": 221.478,
|
| 82 |
+
"eval_steps_per_second": 13.865,
|
| 83 |
+
"step": 2500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.92,
|
| 87 |
+
"learning_rate": 1.6334758704948076e-05,
|
| 88 |
+
"loss": 0.2907,
|
| 89 |
+
"step": 3000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.92,
|
| 93 |
+
"eval_accuracy": 0.9029837085850265,
|
| 94 |
+
"eval_loss": 0.2454785704612732,
|
| 95 |
+
"eval_runtime": 25.5666,
|
| 96 |
+
"eval_samples_per_second": 213.677,
|
| 97 |
+
"eval_steps_per_second": 13.377,
|
| 98 |
+
"step": 3000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.07,
|
| 102 |
+
"learning_rate": 1.5723885155772757e-05,
|
| 103 |
+
"loss": 0.2484,
|
| 104 |
+
"step": 3500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.07,
|
| 108 |
+
"eval_accuracy": 0.9125022881200805,
|
| 109 |
+
"eval_loss": 0.24116584658622742,
|
| 110 |
+
"eval_runtime": 25.7855,
|
| 111 |
+
"eval_samples_per_second": 211.864,
|
| 112 |
+
"eval_steps_per_second": 13.263,
|
| 113 |
+
"step": 3500
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.22,
|
| 117 |
+
"learning_rate": 1.5113011606597437e-05,
|
| 118 |
+
"loss": 0.1937,
|
| 119 |
+
"step": 4000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 1.22,
|
| 123 |
+
"eval_accuracy": 0.9077429983525536,
|
| 124 |
+
"eval_loss": 0.25882598757743835,
|
| 125 |
+
"eval_runtime": 24.3945,
|
| 126 |
+
"eval_samples_per_second": 223.944,
|
| 127 |
+
"eval_steps_per_second": 14.02,
|
| 128 |
+
"step": 4000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.37,
|
| 132 |
+
"learning_rate": 1.4502138057422115e-05,
|
| 133 |
+
"loss": 0.1948,
|
| 134 |
+
"step": 4500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.37,
|
| 138 |
+
"eval_accuracy": 0.9134175361522973,
|
| 139 |
+
"eval_loss": 0.24079638719558716,
|
| 140 |
+
"eval_runtime": 25.609,
|
| 141 |
+
"eval_samples_per_second": 213.323,
|
| 142 |
+
"eval_steps_per_second": 13.355,
|
| 143 |
+
"step": 4500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.53,
|
| 147 |
+
"learning_rate": 1.3891264508246794e-05,
|
| 148 |
+
"loss": 0.1955,
|
| 149 |
+
"step": 5000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.53,
|
| 153 |
+
"eval_accuracy": 0.9126853377265239,
|
| 154 |
+
"eval_loss": 0.22899456322193146,
|
| 155 |
+
"eval_runtime": 25.5564,
|
| 156 |
+
"eval_samples_per_second": 213.763,
|
| 157 |
+
"eval_steps_per_second": 13.382,
|
| 158 |
+
"step": 5000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.68,
|
| 162 |
+
"learning_rate": 1.3280390959071474e-05,
|
| 163 |
+
"loss": 0.1869,
|
| 164 |
+
"step": 5500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.68,
|
| 168 |
+
"eval_accuracy": 0.9084751967783269,
|
| 169 |
+
"eval_loss": 0.2446000874042511,
|
| 170 |
+
"eval_runtime": 24.7359,
|
| 171 |
+
"eval_samples_per_second": 220.853,
|
| 172 |
+
"eval_steps_per_second": 13.826,
|
| 173 |
+
"step": 5500
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.83,
|
| 177 |
+
"learning_rate": 1.2669517409896153e-05,
|
| 178 |
+
"loss": 0.1883,
|
| 179 |
+
"step": 6000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.83,
|
| 183 |
+
"eval_accuracy": 0.9115870400878638,
|
| 184 |
+
"eval_loss": 0.23336854577064514,
|
| 185 |
+
"eval_runtime": 26.4848,
|
| 186 |
+
"eval_samples_per_second": 206.269,
|
| 187 |
+
"eval_steps_per_second": 12.913,
|
| 188 |
+
"step": 6000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.99,
|
| 192 |
+
"learning_rate": 1.2058643860720831e-05,
|
| 193 |
+
"loss": 0.1897,
|
| 194 |
+
"step": 6500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.99,
|
| 198 |
+
"eval_accuracy": 0.9084751967783269,
|
| 199 |
+
"eval_loss": 0.2398270219564438,
|
| 200 |
+
"eval_runtime": 26.0879,
|
| 201 |
+
"eval_samples_per_second": 209.407,
|
| 202 |
+
"eval_steps_per_second": 13.11,
|
| 203 |
+
"step": 6500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.14,
|
| 207 |
+
"learning_rate": 1.1447770311545512e-05,
|
| 208 |
+
"loss": 0.1169,
|
| 209 |
+
"step": 7000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.14,
|
| 213 |
+
"eval_accuracy": 0.9123192385136372,
|
| 214 |
+
"eval_loss": 0.30561476945877075,
|
| 215 |
+
"eval_runtime": 24.4434,
|
| 216 |
+
"eval_samples_per_second": 223.496,
|
| 217 |
+
"eval_steps_per_second": 13.992,
|
| 218 |
+
"step": 7000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.29,
|
| 222 |
+
"learning_rate": 1.083689676237019e-05,
|
| 223 |
+
"loss": 0.1069,
|
| 224 |
+
"step": 7500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.29,
|
| 228 |
+
"eval_accuracy": 0.9130514369394106,
|
| 229 |
+
"eval_loss": 0.295697420835495,
|
| 230 |
+
"eval_runtime": 25.6997,
|
| 231 |
+
"eval_samples_per_second": 212.571,
|
| 232 |
+
"eval_steps_per_second": 13.308,
|
| 233 |
+
"step": 7500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.44,
|
| 237 |
+
"learning_rate": 1.0226023213194869e-05,
|
| 238 |
+
"loss": 0.1079,
|
| 239 |
+
"step": 8000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.44,
|
| 243 |
+
"eval_accuracy": 0.9146988833974007,
|
| 244 |
+
"eval_loss": 0.31733793020248413,
|
| 245 |
+
"eval_runtime": 25.5822,
|
| 246 |
+
"eval_samples_per_second": 213.547,
|
| 247 |
+
"eval_steps_per_second": 13.369,
|
| 248 |
+
"step": 8000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.6,
|
| 252 |
+
"learning_rate": 9.615149664019549e-06,
|
| 253 |
+
"loss": 0.1132,
|
| 254 |
+
"step": 8500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.6,
|
| 258 |
+
"eval_accuracy": 0.9137836353651839,
|
| 259 |
+
"eval_loss": 0.3351670503616333,
|
| 260 |
+
"eval_runtime": 26.0424,
|
| 261 |
+
"eval_samples_per_second": 209.774,
|
| 262 |
+
"eval_steps_per_second": 13.132,
|
| 263 |
+
"step": 8500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 2.75,
|
| 267 |
+
"learning_rate": 9.004276114844227e-06,
|
| 268 |
+
"loss": 0.1141,
|
| 269 |
+
"step": 9000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.75,
|
| 273 |
+
"eval_accuracy": 0.9139666849716274,
|
| 274 |
+
"eval_loss": 0.3112892210483551,
|
| 275 |
+
"eval_runtime": 25.7504,
|
| 276 |
+
"eval_samples_per_second": 212.152,
|
| 277 |
+
"eval_steps_per_second": 13.281,
|
| 278 |
+
"step": 9000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.9,
|
| 282 |
+
"learning_rate": 8.393402565668908e-06,
|
| 283 |
+
"loss": 0.118,
|
| 284 |
+
"step": 9500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.9,
|
| 288 |
+
"eval_accuracy": 0.9178107267069375,
|
| 289 |
+
"eval_loss": 0.28728175163269043,
|
| 290 |
+
"eval_runtime": 24.7133,
|
| 291 |
+
"eval_samples_per_second": 221.055,
|
| 292 |
+
"eval_steps_per_second": 13.839,
|
| 293 |
+
"step": 9500
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.05,
|
| 297 |
+
"learning_rate": 7.782529016493586e-06,
|
| 298 |
+
"loss": 0.0918,
|
| 299 |
+
"step": 10000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.05,
|
| 303 |
+
"eval_accuracy": 0.9145158337909574,
|
| 304 |
+
"eval_loss": 0.4170892536640167,
|
| 305 |
+
"eval_runtime": 26.16,
|
| 306 |
+
"eval_samples_per_second": 208.83,
|
| 307 |
+
"eval_steps_per_second": 13.073,
|
| 308 |
+
"step": 10000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.21,
|
| 312 |
+
"learning_rate": 7.171655467318266e-06,
|
| 313 |
+
"loss": 0.0678,
|
| 314 |
+
"step": 10500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.21,
|
| 318 |
+
"eval_accuracy": 0.9112209408749771,
|
| 319 |
+
"eval_loss": 0.4185065031051636,
|
| 320 |
+
"eval_runtime": 24.3588,
|
| 321 |
+
"eval_samples_per_second": 224.272,
|
| 322 |
+
"eval_steps_per_second": 14.04,
|
| 323 |
+
"step": 10500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.36,
|
| 327 |
+
"learning_rate": 6.560781918142944e-06,
|
| 328 |
+
"loss": 0.0678,
|
| 329 |
+
"step": 11000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.36,
|
| 333 |
+
"eval_accuracy": 0.9112209408749771,
|
| 334 |
+
"eval_loss": 0.4082688093185425,
|
| 335 |
+
"eval_runtime": 24.7254,
|
| 336 |
+
"eval_samples_per_second": 220.947,
|
| 337 |
+
"eval_steps_per_second": 13.832,
|
| 338 |
+
"step": 11000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.51,
|
| 342 |
+
"learning_rate": 5.949908368967624e-06,
|
| 343 |
+
"loss": 0.0732,
|
| 344 |
+
"step": 11500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.51,
|
| 348 |
+
"eval_accuracy": 0.9146988833974007,
|
| 349 |
+
"eval_loss": 0.39638856053352356,
|
| 350 |
+
"eval_runtime": 25.9223,
|
| 351 |
+
"eval_samples_per_second": 210.746,
|
| 352 |
+
"eval_steps_per_second": 13.193,
|
| 353 |
+
"step": 11500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.67,
|
| 357 |
+
"learning_rate": 5.339034819792304e-06,
|
| 358 |
+
"loss": 0.0747,
|
| 359 |
+
"step": 12000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.67,
|
| 363 |
+
"eval_accuracy": 0.9154310818231741,
|
| 364 |
+
"eval_loss": 0.39597952365875244,
|
| 365 |
+
"eval_runtime": 25.8782,
|
| 366 |
+
"eval_samples_per_second": 211.104,
|
| 367 |
+
"eval_steps_per_second": 13.216,
|
| 368 |
+
"step": 12000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.82,
|
| 372 |
+
"learning_rate": 4.728161270616982e-06,
|
| 373 |
+
"loss": 0.0694,
|
| 374 |
+
"step": 12500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.82,
|
| 378 |
+
"eval_accuracy": 0.9167124290682775,
|
| 379 |
+
"eval_loss": 0.3776060938835144,
|
| 380 |
+
"eval_runtime": 25.8946,
|
| 381 |
+
"eval_samples_per_second": 210.97,
|
| 382 |
+
"eval_steps_per_second": 13.207,
|
| 383 |
+
"step": 12500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.97,
|
| 387 |
+
"learning_rate": 4.117287721441662e-06,
|
| 388 |
+
"loss": 0.0711,
|
| 389 |
+
"step": 13000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.97,
|
| 393 |
+
"eval_accuracy": 0.9154310818231741,
|
| 394 |
+
"eval_loss": 0.3837811052799225,
|
| 395 |
+
"eval_runtime": 24.4925,
|
| 396 |
+
"eval_samples_per_second": 223.048,
|
| 397 |
+
"eval_steps_per_second": 13.963,
|
| 398 |
+
"step": 13000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 4.12,
|
| 402 |
+
"learning_rate": 3.506414172266341e-06,
|
| 403 |
+
"loss": 0.0473,
|
| 404 |
+
"step": 13500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 4.12,
|
| 408 |
+
"eval_accuracy": 0.9146988833974007,
|
| 409 |
+
"eval_loss": 0.44068974256515503,
|
| 410 |
+
"eval_runtime": 26.0081,
|
| 411 |
+
"eval_samples_per_second": 210.05,
|
| 412 |
+
"eval_steps_per_second": 13.15,
|
| 413 |
+
"step": 13500
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 4.28,
|
| 417 |
+
"learning_rate": 2.8955406230910206e-06,
|
| 418 |
+
"loss": 0.043,
|
| 419 |
+
"step": 14000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 4.28,
|
| 423 |
+
"eval_accuracy": 0.9168954786747209,
|
| 424 |
+
"eval_loss": 0.4517548680305481,
|
| 425 |
+
"eval_runtime": 25.7888,
|
| 426 |
+
"eval_samples_per_second": 211.836,
|
| 427 |
+
"eval_steps_per_second": 13.262,
|
| 428 |
+
"step": 14000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.43,
|
| 432 |
+
"learning_rate": 2.2846670739156996e-06,
|
| 433 |
+
"loss": 0.0459,
|
| 434 |
+
"step": 14500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.43,
|
| 438 |
+
"eval_accuracy": 0.917993776313381,
|
| 439 |
+
"eval_loss": 0.43741610646247864,
|
| 440 |
+
"eval_runtime": 28.8351,
|
| 441 |
+
"eval_samples_per_second": 189.456,
|
| 442 |
+
"eval_steps_per_second": 11.861,
|
| 443 |
+
"step": 14500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 4.58,
|
| 447 |
+
"learning_rate": 1.6737935247403788e-06,
|
| 448 |
+
"loss": 0.043,
|
| 449 |
+
"step": 15000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 4.58,
|
| 453 |
+
"eval_accuracy": 0.9154310818231741,
|
| 454 |
+
"eval_loss": 0.4457714259624481,
|
| 455 |
+
"eval_runtime": 24.7472,
|
| 456 |
+
"eval_samples_per_second": 220.752,
|
| 457 |
+
"eval_steps_per_second": 13.82,
|
| 458 |
+
"step": 15000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 4.73,
|
| 462 |
+
"learning_rate": 1.0629199755650582e-06,
|
| 463 |
+
"loss": 0.0472,
|
| 464 |
+
"step": 15500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 4.73,
|
| 468 |
+
"eval_accuracy": 0.9183598755262676,
|
| 469 |
+
"eval_loss": 0.43522849678993225,
|
| 470 |
+
"eval_runtime": 25.0601,
|
| 471 |
+
"eval_samples_per_second": 217.996,
|
| 472 |
+
"eval_steps_per_second": 13.647,
|
| 473 |
+
"step": 15500
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 4.89,
|
| 477 |
+
"learning_rate": 4.5204642638973736e-07,
|
| 478 |
+
"loss": 0.041,
|
| 479 |
+
"step": 16000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 4.89,
|
| 483 |
+
"eval_accuracy": 0.9183598755262676,
|
| 484 |
+
"eval_loss": 0.44270119071006775,
|
| 485 |
+
"eval_runtime": 24.5695,
|
| 486 |
+
"eval_samples_per_second": 222.349,
|
| 487 |
+
"eval_steps_per_second": 13.92,
|
| 488 |
+
"step": 16000
|
| 489 |
+
}
|
| 490 |
+
],
|
| 491 |
+
"max_steps": 16370,
|
| 492 |
+
"num_train_epochs": 5,
|
| 493 |
+
"total_flos": 3.3671637309696e+16,
|
| 494 |
+
"trial_name": null,
|
| 495 |
+
"trial_params": null
|
| 496 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43c9a384de30e23b3c651ba43d6d0e0a0d37e4f6f791d549d8c6cb33ce56141d
|
| 3 |
+
size 2927
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|