Commit
·
a01c593
1
Parent(s):
7837edd
Upload 7 files
Browse files- config.json +43 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +508 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"LABEL_0": 0,
|
| 23 |
+
"LABEL_1": 1,
|
| 24 |
+
"LABEL_2": 2,
|
| 25 |
+
"LABEL_3": 3,
|
| 26 |
+
"LABEL_4": 4,
|
| 27 |
+
"LABEL_5": 5,
|
| 28 |
+
"LABEL_6": 6
|
| 29 |
+
},
|
| 30 |
+
"max_position_embeddings": 512,
|
| 31 |
+
"model_type": "distilbert",
|
| 32 |
+
"n_heads": 12,
|
| 33 |
+
"n_layers": 6,
|
| 34 |
+
"pad_token_id": 0,
|
| 35 |
+
"problem_type": "single_label_classification",
|
| 36 |
+
"qa_dropout": 0.1,
|
| 37 |
+
"seq_classif_dropout": 0.2,
|
| 38 |
+
"sinusoidal_pos_embds": false,
|
| 39 |
+
"tie_weights_": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.27.0",
|
| 42 |
+
"vocab_size": 30522
|
| 43 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9542a1b36c8829aa97a425b2fef358fdb68e7af80dae8a8051da030c3fbf595
|
| 3 |
+
size 174907141
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bde8ac586207088b3223274dd94a45a8beac9373d4ec102b5b4f217a0658d6f
|
| 3 |
+
size 267870893
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d317c176c78e97bb06fe124aa6169f1eeca412e67de36771fc16220a11e5fc5
|
| 3 |
+
size 17641
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c881b9118a40991c62ae6b40d94cda3edb966b4af52be92862889e5a3c47f0e5
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,508 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7987080812454224,
|
| 3 |
+
"best_model_checkpoint": "text3\\checkpoint-256",
|
| 4 |
+
"epoch": 2.9970731707317073,
|
| 5 |
+
"global_step": 768,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 2e-05,
|
| 13 |
+
"loss": 1.948,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.08,
|
| 18 |
+
"learning_rate": 4e-05,
|
| 19 |
+
"loss": 1.932,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.12,
|
| 24 |
+
"learning_rate": 6e-05,
|
| 25 |
+
"loss": 1.8378,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.16,
|
| 30 |
+
"learning_rate": 8e-05,
|
| 31 |
+
"loss": 1.6154,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.2,
|
| 36 |
+
"learning_rate": 0.0001,
|
| 37 |
+
"loss": 1.387,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.23,
|
| 42 |
+
"learning_rate": 0.00012,
|
| 43 |
+
"loss": 1.2299,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.27,
|
| 48 |
+
"learning_rate": 0.00014000000000000001,
|
| 49 |
+
"loss": 1.1199,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.31,
|
| 54 |
+
"learning_rate": 0.00016,
|
| 55 |
+
"loss": 1.0253,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.35,
|
| 60 |
+
"learning_rate": 0.00017999999999999998,
|
| 61 |
+
"loss": 1.062,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.39,
|
| 66 |
+
"learning_rate": 0.0002,
|
| 67 |
+
"loss": 0.9251,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.43,
|
| 72 |
+
"learning_rate": 0.00022,
|
| 73 |
+
"loss": 0.9046,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.47,
|
| 78 |
+
"learning_rate": 0.00024,
|
| 79 |
+
"loss": 0.8802,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.51,
|
| 84 |
+
"learning_rate": 0.00026000000000000003,
|
| 85 |
+
"loss": 0.9967,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.55,
|
| 90 |
+
"learning_rate": 0.00028000000000000003,
|
| 91 |
+
"loss": 0.8137,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.59,
|
| 96 |
+
"learning_rate": 0.0003,
|
| 97 |
+
"loss": 0.91,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.62,
|
| 102 |
+
"learning_rate": 0.00032,
|
| 103 |
+
"loss": 0.8306,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.66,
|
| 108 |
+
"learning_rate": 0.00034,
|
| 109 |
+
"loss": 0.8594,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.7,
|
| 114 |
+
"learning_rate": 0.00035999999999999997,
|
| 115 |
+
"loss": 0.928,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.74,
|
| 120 |
+
"learning_rate": 0.00038,
|
| 121 |
+
"loss": 0.8102,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.78,
|
| 126 |
+
"learning_rate": 0.0004,
|
| 127 |
+
"loss": 0.7926,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.82,
|
| 132 |
+
"learning_rate": 0.00042,
|
| 133 |
+
"loss": 0.7343,
|
| 134 |
+
"step": 210
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.86,
|
| 138 |
+
"learning_rate": 0.00044,
|
| 139 |
+
"loss": 0.8367,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.9,
|
| 144 |
+
"learning_rate": 0.00046,
|
| 145 |
+
"loss": 0.8216,
|
| 146 |
+
"step": 230
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.94,
|
| 150 |
+
"learning_rate": 0.00048,
|
| 151 |
+
"loss": 0.7632,
|
| 152 |
+
"step": 240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.98,
|
| 156 |
+
"learning_rate": 0.0005,
|
| 157 |
+
"loss": 0.818,
|
| 158 |
+
"step": 250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.0,
|
| 162 |
+
"eval_accuracy": 0.7320644216691069,
|
| 163 |
+
"eval_f1": 0.7317069643985404,
|
| 164 |
+
"eval_loss": 0.7987080812454224,
|
| 165 |
+
"eval_precision": 0.7374126435251394,
|
| 166 |
+
"eval_recall": 0.7320644216691069,
|
| 167 |
+
"eval_runtime": 28.883,
|
| 168 |
+
"eval_samples_per_second": 70.941,
|
| 169 |
+
"eval_steps_per_second": 4.466,
|
| 170 |
+
"step": 256
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.01,
|
| 174 |
+
"learning_rate": 0.0005200000000000001,
|
| 175 |
+
"loss": 0.7729,
|
| 176 |
+
"step": 260
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.05,
|
| 180 |
+
"learning_rate": 0.00054,
|
| 181 |
+
"loss": 0.8005,
|
| 182 |
+
"step": 270
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.09,
|
| 186 |
+
"learning_rate": 0.0005600000000000001,
|
| 187 |
+
"loss": 0.7229,
|
| 188 |
+
"step": 280
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.13,
|
| 192 |
+
"learning_rate": 0.00058,
|
| 193 |
+
"loss": 0.7439,
|
| 194 |
+
"step": 290
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.17,
|
| 198 |
+
"learning_rate": 0.0006,
|
| 199 |
+
"loss": 0.8348,
|
| 200 |
+
"step": 300
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.21,
|
| 204 |
+
"learning_rate": 0.00062,
|
| 205 |
+
"loss": 0.7075,
|
| 206 |
+
"step": 310
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.25,
|
| 210 |
+
"learning_rate": 0.00064,
|
| 211 |
+
"loss": 0.7768,
|
| 212 |
+
"step": 320
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.29,
|
| 216 |
+
"learning_rate": 0.00066,
|
| 217 |
+
"loss": 0.7575,
|
| 218 |
+
"step": 330
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.33,
|
| 222 |
+
"learning_rate": 0.00068,
|
| 223 |
+
"loss": 0.7574,
|
| 224 |
+
"step": 340
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.37,
|
| 228 |
+
"learning_rate": 0.0007,
|
| 229 |
+
"loss": 0.8399,
|
| 230 |
+
"step": 350
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.4,
|
| 234 |
+
"learning_rate": 0.0007199999999999999,
|
| 235 |
+
"loss": 0.8992,
|
| 236 |
+
"step": 360
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.44,
|
| 240 |
+
"learning_rate": 0.00074,
|
| 241 |
+
"loss": 0.8134,
|
| 242 |
+
"step": 370
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.48,
|
| 246 |
+
"learning_rate": 0.00076,
|
| 247 |
+
"loss": 0.8662,
|
| 248 |
+
"step": 380
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.52,
|
| 252 |
+
"learning_rate": 0.0007800000000000001,
|
| 253 |
+
"loss": 0.728,
|
| 254 |
+
"step": 390
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.56,
|
| 258 |
+
"learning_rate": 0.0008,
|
| 259 |
+
"loss": 0.8599,
|
| 260 |
+
"step": 400
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.6,
|
| 264 |
+
"learning_rate": 0.00082,
|
| 265 |
+
"loss": 0.8931,
|
| 266 |
+
"step": 410
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.64,
|
| 270 |
+
"learning_rate": 0.00084,
|
| 271 |
+
"loss": 0.8559,
|
| 272 |
+
"step": 420
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.68,
|
| 276 |
+
"learning_rate": 0.00086,
|
| 277 |
+
"loss": 0.918,
|
| 278 |
+
"step": 430
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.72,
|
| 282 |
+
"learning_rate": 0.00088,
|
| 283 |
+
"loss": 0.8785,
|
| 284 |
+
"step": 440
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.76,
|
| 288 |
+
"learning_rate": 0.0009000000000000001,
|
| 289 |
+
"loss": 0.7987,
|
| 290 |
+
"step": 450
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.8,
|
| 294 |
+
"learning_rate": 0.00092,
|
| 295 |
+
"loss": 0.7985,
|
| 296 |
+
"step": 460
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.83,
|
| 300 |
+
"learning_rate": 0.00094,
|
| 301 |
+
"loss": 0.82,
|
| 302 |
+
"step": 470
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.87,
|
| 306 |
+
"learning_rate": 0.00096,
|
| 307 |
+
"loss": 0.895,
|
| 308 |
+
"step": 480
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.91,
|
| 312 |
+
"learning_rate": 0.00098,
|
| 313 |
+
"loss": 0.9,
|
| 314 |
+
"step": 490
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.95,
|
| 318 |
+
"learning_rate": 0.001,
|
| 319 |
+
"loss": 0.7661,
|
| 320 |
+
"step": 500
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.99,
|
| 324 |
+
"learning_rate": 0.0009991869918699187,
|
| 325 |
+
"loss": 0.8573,
|
| 326 |
+
"step": 510
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.0,
|
| 330 |
+
"eval_accuracy": 0.7354807223035628,
|
| 331 |
+
"eval_f1": 0.7316570448238782,
|
| 332 |
+
"eval_loss": 0.8289155960083008,
|
| 333 |
+
"eval_precision": 0.7364917787903197,
|
| 334 |
+
"eval_recall": 0.7354807223035628,
|
| 335 |
+
"eval_runtime": 28.6407,
|
| 336 |
+
"eval_samples_per_second": 71.542,
|
| 337 |
+
"eval_steps_per_second": 4.504,
|
| 338 |
+
"step": 512
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.03,
|
| 342 |
+
"learning_rate": 0.0009983739837398375,
|
| 343 |
+
"loss": 0.7547,
|
| 344 |
+
"step": 520
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.07,
|
| 348 |
+
"learning_rate": 0.0009975609756097562,
|
| 349 |
+
"loss": 0.7428,
|
| 350 |
+
"step": 530
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.11,
|
| 354 |
+
"learning_rate": 0.0009967479674796748,
|
| 355 |
+
"loss": 0.7495,
|
| 356 |
+
"step": 540
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.15,
|
| 360 |
+
"learning_rate": 0.0009959349593495937,
|
| 361 |
+
"loss": 0.8956,
|
| 362 |
+
"step": 550
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.19,
|
| 366 |
+
"learning_rate": 0.0009951219512195123,
|
| 367 |
+
"loss": 0.7692,
|
| 368 |
+
"step": 560
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.22,
|
| 372 |
+
"learning_rate": 0.000994308943089431,
|
| 373 |
+
"loss": 0.802,
|
| 374 |
+
"step": 570
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.26,
|
| 378 |
+
"learning_rate": 0.0009934959349593496,
|
| 379 |
+
"loss": 0.8457,
|
| 380 |
+
"step": 580
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.3,
|
| 384 |
+
"learning_rate": 0.0009926829268292682,
|
| 385 |
+
"loss": 0.8257,
|
| 386 |
+
"step": 590
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.34,
|
| 390 |
+
"learning_rate": 0.0009918699186991869,
|
| 391 |
+
"loss": 0.8721,
|
| 392 |
+
"step": 600
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.38,
|
| 396 |
+
"learning_rate": 0.0009910569105691057,
|
| 397 |
+
"loss": 0.884,
|
| 398 |
+
"step": 610
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.42,
|
| 402 |
+
"learning_rate": 0.0009902439024390244,
|
| 403 |
+
"loss": 0.859,
|
| 404 |
+
"step": 620
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.46,
|
| 408 |
+
"learning_rate": 0.000989430894308943,
|
| 409 |
+
"loss": 0.7961,
|
| 410 |
+
"step": 630
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.5,
|
| 414 |
+
"learning_rate": 0.0009886178861788619,
|
| 415 |
+
"loss": 0.7881,
|
| 416 |
+
"step": 640
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.54,
|
| 420 |
+
"learning_rate": 0.0009878048780487805,
|
| 421 |
+
"loss": 0.7552,
|
| 422 |
+
"step": 650
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.58,
|
| 426 |
+
"learning_rate": 0.0009869918699186991,
|
| 427 |
+
"loss": 0.8331,
|
| 428 |
+
"step": 660
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.61,
|
| 432 |
+
"learning_rate": 0.000986178861788618,
|
| 433 |
+
"loss": 0.8285,
|
| 434 |
+
"step": 670
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.65,
|
| 438 |
+
"learning_rate": 0.0009853658536585366,
|
| 439 |
+
"loss": 0.8212,
|
| 440 |
+
"step": 680
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.69,
|
| 444 |
+
"learning_rate": 0.0009845528455284553,
|
| 445 |
+
"loss": 0.8296,
|
| 446 |
+
"step": 690
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.73,
|
| 450 |
+
"learning_rate": 0.0009837398373983741,
|
| 451 |
+
"loss": 0.8279,
|
| 452 |
+
"step": 700
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.77,
|
| 456 |
+
"learning_rate": 0.0009829268292682928,
|
| 457 |
+
"loss": 0.7799,
|
| 458 |
+
"step": 710
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.81,
|
| 462 |
+
"learning_rate": 0.0009821138211382114,
|
| 463 |
+
"loss": 0.7338,
|
| 464 |
+
"step": 720
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.85,
|
| 468 |
+
"learning_rate": 0.00098130081300813,
|
| 469 |
+
"loss": 0.691,
|
| 470 |
+
"step": 730
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.89,
|
| 474 |
+
"learning_rate": 0.0009804878048780487,
|
| 475 |
+
"loss": 0.84,
|
| 476 |
+
"step": 740
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.93,
|
| 480 |
+
"learning_rate": 0.0009796747967479673,
|
| 481 |
+
"loss": 0.7672,
|
| 482 |
+
"step": 750
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.97,
|
| 486 |
+
"learning_rate": 0.0009788617886178862,
|
| 487 |
+
"loss": 0.7583,
|
| 488 |
+
"step": 760
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 3.0,
|
| 492 |
+
"eval_accuracy": 0.7476817959980478,
|
| 493 |
+
"eval_f1": 0.7476581545903426,
|
| 494 |
+
"eval_loss": 0.8017462491989136,
|
| 495 |
+
"eval_precision": 0.7558306284443703,
|
| 496 |
+
"eval_recall": 0.7476817959980478,
|
| 497 |
+
"eval_runtime": 28.7319,
|
| 498 |
+
"eval_samples_per_second": 71.314,
|
| 499 |
+
"eval_steps_per_second": 4.49,
|
| 500 |
+
"step": 768
|
| 501 |
+
}
|
| 502 |
+
],
|
| 503 |
+
"max_steps": 12800,
|
| 504 |
+
"num_train_epochs": 50,
|
| 505 |
+
"total_flos": 1046595336611346.0,
|
| 506 |
+
"trial_name": null,
|
| 507 |
+
"trial_params": null
|
| 508 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cc263ddc7b49f2dc63ae9763300360620a2fd7b5a15deb4e6e9b39ed50be25f
|
| 3 |
+
size 3515
|