Upload folder using huggingface_hub
Browse files- config.json +29 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +445 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/codebert-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"output_past": true,
|
| 21 |
+
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
| 23 |
+
"problem_type": "single_label_classification",
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.35.2",
|
| 26 |
+
"type_vocab_size": 1,
|
| 27 |
+
"use_cache": true,
|
| 28 |
+
"vocab_size": 50265
|
| 29 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76be76a15eb7729f4b00b4f1d419d99293a80090099dc1e5fabd15af50a9baac
|
| 3 |
+
size 498612824
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2347bb36c75e36892183c95dce50a6b5615a6f578a2f69dc9fa44d40e4f2d99
|
| 3 |
+
size 118173498
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b92896732603661d06d166837c431b32c69a6df4f83079e8f3cf7091b113ad6a
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dcb5d1309ade11adef56b51bf410df7ad6a10fac32cf9fd0b45c0dab8f75032
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,445 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9870967741935484,
|
| 3 |
+
"best_model_checkpoint": "./php_cwe79_codebert_output\\checkpoint-1648",
|
| 4 |
+
"epoch": 16.99203640500569,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1867,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.46,
|
| 13 |
+
"learning_rate": 4.587155963302753e-06,
|
| 14 |
+
"loss": 0.7019,
|
| 15 |
+
"step": 50
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.91,
|
| 19 |
+
"learning_rate": 9.174311926605506e-06,
|
| 20 |
+
"loss": 0.6915,
|
| 21 |
+
"step": 100
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.99,
|
| 25 |
+
"eval_accuracy": 0.5532258064516129,
|
| 26 |
+
"eval_f1": 0.4822429906542056,
|
| 27 |
+
"eval_loss": 0.6805028915405273,
|
| 28 |
+
"eval_precision": 0.5733333333333334,
|
| 29 |
+
"eval_recall": 0.4161290322580645,
|
| 30 |
+
"eval_runtime": 19.9477,
|
| 31 |
+
"eval_samples_per_second": 62.162,
|
| 32 |
+
"eval_steps_per_second": 3.91,
|
| 33 |
+
"step": 109
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.37,
|
| 37 |
+
"learning_rate": 1.3761467889908258e-05,
|
| 38 |
+
"loss": 0.6774,
|
| 39 |
+
"step": 150
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.82,
|
| 43 |
+
"learning_rate": 1.834862385321101e-05,
|
| 44 |
+
"loss": 0.5408,
|
| 45 |
+
"step": 200
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.99,
|
| 49 |
+
"eval_accuracy": 0.8362903225806452,
|
| 50 |
+
"eval_f1": 0.8407843137254902,
|
| 51 |
+
"eval_loss": 0.35471096634864807,
|
| 52 |
+
"eval_precision": 0.8183206106870229,
|
| 53 |
+
"eval_recall": 0.864516129032258,
|
| 54 |
+
"eval_runtime": 20.4696,
|
| 55 |
+
"eval_samples_per_second": 60.578,
|
| 56 |
+
"eval_steps_per_second": 3.811,
|
| 57 |
+
"step": 219
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.28,
|
| 61 |
+
"learning_rate": 1.9673802242609582e-05,
|
| 62 |
+
"loss": 0.3461,
|
| 63 |
+
"step": 250
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.73,
|
| 67 |
+
"learning_rate": 1.9164118246687054e-05,
|
| 68 |
+
"loss": 0.2515,
|
| 69 |
+
"step": 300
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.99,
|
| 73 |
+
"eval_accuracy": 0.9185483870967742,
|
| 74 |
+
"eval_f1": 0.9144792548687553,
|
| 75 |
+
"eval_loss": 0.20694807171821594,
|
| 76 |
+
"eval_precision": 0.9625668449197861,
|
| 77 |
+
"eval_recall": 0.8709677419354839,
|
| 78 |
+
"eval_runtime": 31.9108,
|
| 79 |
+
"eval_samples_per_second": 38.858,
|
| 80 |
+
"eval_steps_per_second": 2.444,
|
| 81 |
+
"step": 329
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 3.19,
|
| 85 |
+
"learning_rate": 1.865443425076453e-05,
|
| 86 |
+
"loss": 0.211,
|
| 87 |
+
"step": 350
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 3.64,
|
| 91 |
+
"learning_rate": 1.8144750254841998e-05,
|
| 92 |
+
"loss": 0.1931,
|
| 93 |
+
"step": 400
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 4.0,
|
| 97 |
+
"eval_accuracy": 0.9314516129032258,
|
| 98 |
+
"eval_f1": 0.9280270956816258,
|
| 99 |
+
"eval_loss": 0.16265422105789185,
|
| 100 |
+
"eval_precision": 0.9768270944741533,
|
| 101 |
+
"eval_recall": 0.8838709677419355,
|
| 102 |
+
"eval_runtime": 36.5458,
|
| 103 |
+
"eval_samples_per_second": 33.93,
|
| 104 |
+
"eval_steps_per_second": 2.134,
|
| 105 |
+
"step": 439
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 4.1,
|
| 109 |
+
"learning_rate": 1.763506625891947e-05,
|
| 110 |
+
"loss": 0.1447,
|
| 111 |
+
"step": 450
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 4.55,
|
| 115 |
+
"learning_rate": 1.7125382262996945e-05,
|
| 116 |
+
"loss": 0.1335,
|
| 117 |
+
"step": 500
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 5.0,
|
| 121 |
+
"eval_accuracy": 0.9612903225806452,
|
| 122 |
+
"eval_f1": 0.9608482871125612,
|
| 123 |
+
"eval_loss": 0.09464450925588608,
|
| 124 |
+
"eval_precision": 0.971947194719472,
|
| 125 |
+
"eval_recall": 0.95,
|
| 126 |
+
"eval_runtime": 35.2367,
|
| 127 |
+
"eval_samples_per_second": 35.191,
|
| 128 |
+
"eval_steps_per_second": 2.214,
|
| 129 |
+
"step": 549
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 5.01,
|
| 133 |
+
"learning_rate": 1.6625891946992865e-05,
|
| 134 |
+
"loss": 0.1333,
|
| 135 |
+
"step": 550
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 5.46,
|
| 139 |
+
"learning_rate": 1.6116207951070337e-05,
|
| 140 |
+
"loss": 0.1043,
|
| 141 |
+
"step": 600
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 5.92,
|
| 145 |
+
"learning_rate": 1.560652395514781e-05,
|
| 146 |
+
"loss": 0.1057,
|
| 147 |
+
"step": 650
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 6.0,
|
| 151 |
+
"eval_accuracy": 0.9548387096774194,
|
| 152 |
+
"eval_f1": 0.9537953795379538,
|
| 153 |
+
"eval_loss": 0.09458089619874954,
|
| 154 |
+
"eval_precision": 0.9763513513513513,
|
| 155 |
+
"eval_recall": 0.932258064516129,
|
| 156 |
+
"eval_runtime": 36.0845,
|
| 157 |
+
"eval_samples_per_second": 34.364,
|
| 158 |
+
"eval_steps_per_second": 2.162,
|
| 159 |
+
"step": 659
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 6.37,
|
| 163 |
+
"learning_rate": 1.5096839959225283e-05,
|
| 164 |
+
"loss": 0.1046,
|
| 165 |
+
"step": 700
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 6.83,
|
| 169 |
+
"learning_rate": 1.4587155963302753e-05,
|
| 170 |
+
"loss": 0.0887,
|
| 171 |
+
"step": 750
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 7.0,
|
| 175 |
+
"eval_accuracy": 0.9701612903225807,
|
| 176 |
+
"eval_f1": 0.9699918896999189,
|
| 177 |
+
"eval_loss": 0.07421040534973145,
|
| 178 |
+
"eval_precision": 0.9755301794453507,
|
| 179 |
+
"eval_recall": 0.964516129032258,
|
| 180 |
+
"eval_runtime": 37.4354,
|
| 181 |
+
"eval_samples_per_second": 33.124,
|
| 182 |
+
"eval_steps_per_second": 2.084,
|
| 183 |
+
"step": 769
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 7.28,
|
| 187 |
+
"learning_rate": 1.4077471967380225e-05,
|
| 188 |
+
"loss": 0.0763,
|
| 189 |
+
"step": 800
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 7.74,
|
| 193 |
+
"learning_rate": 1.3567787971457698e-05,
|
| 194 |
+
"loss": 0.0916,
|
| 195 |
+
"step": 850
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 8.0,
|
| 199 |
+
"eval_accuracy": 0.9733870967741935,
|
| 200 |
+
"eval_f1": 0.9734085414987913,
|
| 201 |
+
"eval_loss": 0.05636864900588989,
|
| 202 |
+
"eval_precision": 0.9726247987117552,
|
| 203 |
+
"eval_recall": 0.9741935483870968,
|
| 204 |
+
"eval_runtime": 37.5471,
|
| 205 |
+
"eval_samples_per_second": 33.025,
|
| 206 |
+
"eval_steps_per_second": 2.077,
|
| 207 |
+
"step": 879
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 8.19,
|
| 211 |
+
"learning_rate": 1.305810397553517e-05,
|
| 212 |
+
"loss": 0.0858,
|
| 213 |
+
"step": 900
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 8.65,
|
| 217 |
+
"learning_rate": 1.254841997961264e-05,
|
| 218 |
+
"loss": 0.0716,
|
| 219 |
+
"step": 950
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 8.99,
|
| 223 |
+
"eval_accuracy": 0.9790322580645161,
|
| 224 |
+
"eval_f1": 0.9790996784565916,
|
| 225 |
+
"eval_loss": 0.049785859882831573,
|
| 226 |
+
"eval_precision": 0.9759615384615384,
|
| 227 |
+
"eval_recall": 0.9822580645161291,
|
| 228 |
+
"eval_runtime": 39.3971,
|
| 229 |
+
"eval_samples_per_second": 31.474,
|
| 230 |
+
"eval_steps_per_second": 1.98,
|
| 231 |
+
"step": 988
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 9.1,
|
| 235 |
+
"learning_rate": 1.2038735983690114e-05,
|
| 236 |
+
"loss": 0.0686,
|
| 237 |
+
"step": 1000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 9.56,
|
| 241 |
+
"learning_rate": 1.1529051987767585e-05,
|
| 242 |
+
"loss": 0.0673,
|
| 243 |
+
"step": 1050
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 9.99,
|
| 247 |
+
"eval_accuracy": 0.9798387096774194,
|
| 248 |
+
"eval_f1": 0.9799518845228549,
|
| 249 |
+
"eval_loss": 0.046214405447244644,
|
| 250 |
+
"eval_precision": 0.9744816586921851,
|
| 251 |
+
"eval_recall": 0.9854838709677419,
|
| 252 |
+
"eval_runtime": 29.0256,
|
| 253 |
+
"eval_samples_per_second": 42.721,
|
| 254 |
+
"eval_steps_per_second": 2.687,
|
| 255 |
+
"step": 1098
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 10.01,
|
| 259 |
+
"learning_rate": 1.1019367991845057e-05,
|
| 260 |
+
"loss": 0.0577,
|
| 261 |
+
"step": 1100
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 10.47,
|
| 265 |
+
"learning_rate": 1.0509683995922529e-05,
|
| 266 |
+
"loss": 0.0533,
|
| 267 |
+
"step": 1150
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 10.92,
|
| 271 |
+
"learning_rate": 1e-05,
|
| 272 |
+
"loss": 0.0569,
|
| 273 |
+
"step": 1200
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 10.99,
|
| 277 |
+
"eval_accuracy": 0.9846774193548387,
|
| 278 |
+
"eval_f1": 0.9847144006436042,
|
| 279 |
+
"eval_loss": 0.039788804948329926,
|
| 280 |
+
"eval_precision": 0.9823434991974318,
|
| 281 |
+
"eval_recall": 0.9870967741935484,
|
| 282 |
+
"eval_runtime": 29.3619,
|
| 283 |
+
"eval_samples_per_second": 42.232,
|
| 284 |
+
"eval_steps_per_second": 2.657,
|
| 285 |
+
"step": 1208
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 11.38,
|
| 289 |
+
"learning_rate": 9.490316004077473e-06,
|
| 290 |
+
"loss": 0.0497,
|
| 291 |
+
"step": 1250
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 11.83,
|
| 295 |
+
"learning_rate": 8.980632008154944e-06,
|
| 296 |
+
"loss": 0.0532,
|
| 297 |
+
"step": 1300
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 12.0,
|
| 301 |
+
"eval_accuracy": 0.9854838709677419,
|
| 302 |
+
"eval_f1": 0.9854604200323102,
|
| 303 |
+
"eval_loss": 0.034001607447862625,
|
| 304 |
+
"eval_precision": 0.9870550161812298,
|
| 305 |
+
"eval_recall": 0.9838709677419355,
|
| 306 |
+
"eval_runtime": 35.9784,
|
| 307 |
+
"eval_samples_per_second": 34.465,
|
| 308 |
+
"eval_steps_per_second": 2.168,
|
| 309 |
+
"step": 1318
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 12.29,
|
| 313 |
+
"learning_rate": 8.470948012232416e-06,
|
| 314 |
+
"loss": 0.0517,
|
| 315 |
+
"step": 1350
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 12.74,
|
| 319 |
+
"learning_rate": 7.961264016309888e-06,
|
| 320 |
+
"loss": 0.0382,
|
| 321 |
+
"step": 1400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 13.0,
|
| 325 |
+
"eval_accuracy": 0.9854838709677419,
|
| 326 |
+
"eval_f1": 0.9855072463768116,
|
| 327 |
+
"eval_loss": 0.02894522435963154,
|
| 328 |
+
"eval_precision": 0.9839228295819936,
|
| 329 |
+
"eval_recall": 0.9870967741935484,
|
| 330 |
+
"eval_runtime": 37.3704,
|
| 331 |
+
"eval_samples_per_second": 33.181,
|
| 332 |
+
"eval_steps_per_second": 2.087,
|
| 333 |
+
"step": 1428
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 13.2,
|
| 337 |
+
"learning_rate": 7.45158002038736e-06,
|
| 338 |
+
"loss": 0.0333,
|
| 339 |
+
"step": 1450
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 13.65,
|
| 343 |
+
"learning_rate": 6.941896024464833e-06,
|
| 344 |
+
"loss": 0.0338,
|
| 345 |
+
"step": 1500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 14.0,
|
| 349 |
+
"eval_accuracy": 0.9854838709677419,
|
| 350 |
+
"eval_f1": 0.9854838709677419,
|
| 351 |
+
"eval_loss": 0.028582246974110603,
|
| 352 |
+
"eval_precision": 0.9854838709677419,
|
| 353 |
+
"eval_recall": 0.9854838709677419,
|
| 354 |
+
"eval_runtime": 34.3893,
|
| 355 |
+
"eval_samples_per_second": 36.058,
|
| 356 |
+
"eval_steps_per_second": 2.268,
|
| 357 |
+
"step": 1538
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 14.11,
|
| 361 |
+
"learning_rate": 6.432212028542304e-06,
|
| 362 |
+
"loss": 0.0365,
|
| 363 |
+
"step": 1550
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 14.56,
|
| 367 |
+
"learning_rate": 5.922528032619776e-06,
|
| 368 |
+
"loss": 0.0332,
|
| 369 |
+
"step": 1600
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 15.0,
|
| 373 |
+
"eval_accuracy": 0.9870967741935484,
|
| 374 |
+
"eval_f1": 0.9870967741935484,
|
| 375 |
+
"eval_loss": 0.02915828675031662,
|
| 376 |
+
"eval_precision": 0.9870967741935484,
|
| 377 |
+
"eval_recall": 0.9870967741935484,
|
| 378 |
+
"eval_runtime": 24.73,
|
| 379 |
+
"eval_samples_per_second": 50.141,
|
| 380 |
+
"eval_steps_per_second": 3.154,
|
| 381 |
+
"step": 1648
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 15.02,
|
| 385 |
+
"learning_rate": 5.412844036697248e-06,
|
| 386 |
+
"loss": 0.0329,
|
| 387 |
+
"step": 1650
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 15.47,
|
| 391 |
+
"learning_rate": 4.90316004077472e-06,
|
| 392 |
+
"loss": 0.029,
|
| 393 |
+
"step": 1700
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 15.93,
|
| 397 |
+
"learning_rate": 4.393476044852192e-06,
|
| 398 |
+
"loss": 0.0271,
|
| 399 |
+
"step": 1750
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 16.0,
|
| 403 |
+
"eval_accuracy": 0.9854838709677419,
|
| 404 |
+
"eval_f1": 0.9855072463768116,
|
| 405 |
+
"eval_loss": 0.02873540110886097,
|
| 406 |
+
"eval_precision": 0.9839228295819936,
|
| 407 |
+
"eval_recall": 0.9870967741935484,
|
| 408 |
+
"eval_runtime": 24.9886,
|
| 409 |
+
"eval_samples_per_second": 49.623,
|
| 410 |
+
"eval_steps_per_second": 3.121,
|
| 411 |
+
"step": 1758
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 16.38,
|
| 415 |
+
"learning_rate": 3.8837920489296635e-06,
|
| 416 |
+
"loss": 0.0233,
|
| 417 |
+
"step": 1800
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 16.84,
|
| 421 |
+
"learning_rate": 3.3741080530071357e-06,
|
| 422 |
+
"loss": 0.0264,
|
| 423 |
+
"step": 1850
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 16.99,
|
| 427 |
+
"eval_accuracy": 0.9854838709677419,
|
| 428 |
+
"eval_f1": 0.9854838709677419,
|
| 429 |
+
"eval_loss": 0.026798125356435776,
|
| 430 |
+
"eval_precision": 0.9854838709677419,
|
| 431 |
+
"eval_recall": 0.9854838709677419,
|
| 432 |
+
"eval_runtime": 35.295,
|
| 433 |
+
"eval_samples_per_second": 35.132,
|
| 434 |
+
"eval_steps_per_second": 2.21,
|
| 435 |
+
"step": 1867
|
| 436 |
+
}
|
| 437 |
+
],
|
| 438 |
+
"logging_steps": 50,
|
| 439 |
+
"max_steps": 2180,
|
| 440 |
+
"num_train_epochs": 20,
|
| 441 |
+
"save_steps": 500,
|
| 442 |
+
"total_flos": 3.1422037786368e+16,
|
| 443 |
+
"trial_name": null,
|
| 444 |
+
"trial_params": null
|
| 445 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a57b4d693922248abedb2c0d9ab60786de92600c7d03e067f28731e3896c892
|
| 3 |
+
size 4600
|