Commit ·
fb19ea9
1
Parent(s): 0ed263a
Added the model
Browse files- config.json +48 -0
- model.safetensors +3 -0
- trainer_state.json +371 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "0",
|
| 13 |
+
"1": "1",
|
| 14 |
+
"2": "2",
|
| 15 |
+
"3": "3",
|
| 16 |
+
"4": "4",
|
| 17 |
+
"5": "5",
|
| 18 |
+
"6": "6",
|
| 19 |
+
"7": "7",
|
| 20 |
+
"8": "8",
|
| 21 |
+
"9": "9"
|
| 22 |
+
},
|
| 23 |
+
"image_size": 224,
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 3072,
|
| 26 |
+
"label2id": {
|
| 27 |
+
"0": 0,
|
| 28 |
+
"1": 1,
|
| 29 |
+
"2": 2,
|
| 30 |
+
"3": 3,
|
| 31 |
+
"4": 4,
|
| 32 |
+
"5": 5,
|
| 33 |
+
"6": 6,
|
| 34 |
+
"7": 7,
|
| 35 |
+
"8": 8,
|
| 36 |
+
"9": 9
|
| 37 |
+
},
|
| 38 |
+
"layer_norm_eps": 1e-12,
|
| 39 |
+
"model_type": "vit",
|
| 40 |
+
"num_attention_heads": 12,
|
| 41 |
+
"num_channels": 3,
|
| 42 |
+
"num_hidden_layers": 12,
|
| 43 |
+
"patch_size": 16,
|
| 44 |
+
"problem_type": "single_label_classification",
|
| 45 |
+
"qkv_bias": true,
|
| 46 |
+
"torch_dtype": "float32",
|
| 47 |
+
"transformers_version": "4.41.2"
|
| 48 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e751a773d611bfdcaba4f090d670e9260d9df128f5411012a500c4cec1499c2c
|
| 3 |
+
size 343248584
|
trainer_state.json
ADDED
|
@@ -0,0 +1,371 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.013251620344817638,
|
| 3 |
+
"best_model_checkpoint": "./trained_model/checkpoint-1140",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1140,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 14.846182823181152,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 2.1891,
|
| 16 |
+
"step": 57
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_f1": 0.4889426173016636,
|
| 21 |
+
"eval_loss": 1.8956528902053833,
|
| 22 |
+
"eval_runtime": 2.655,
|
| 23 |
+
"eval_samples_per_second": 37.664,
|
| 24 |
+
"eval_steps_per_second": 0.753,
|
| 25 |
+
"step": 57
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"grad_norm": 12.204806327819824,
|
| 30 |
+
"learning_rate": 1e-05,
|
| 31 |
+
"loss": 1.3658,
|
| 32 |
+
"step": 114
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_f1": 0.8423279606641237,
|
| 37 |
+
"eval_loss": 0.9139096140861511,
|
| 38 |
+
"eval_runtime": 5.6535,
|
| 39 |
+
"eval_samples_per_second": 17.688,
|
| 40 |
+
"eval_steps_per_second": 0.354,
|
| 41 |
+
"step": 114
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 3.0,
|
| 45 |
+
"grad_norm": 4.8677287101745605,
|
| 46 |
+
"learning_rate": 9.444444444444445e-06,
|
| 47 |
+
"loss": 0.4966,
|
| 48 |
+
"step": 171
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 3.0,
|
| 52 |
+
"eval_f1": 0.9318143553848225,
|
| 53 |
+
"eval_loss": 0.3583294749259949,
|
| 54 |
+
"eval_runtime": 3.8044,
|
| 55 |
+
"eval_samples_per_second": 26.285,
|
| 56 |
+
"eval_steps_per_second": 0.526,
|
| 57 |
+
"step": 171
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.0,
|
| 61 |
+
"grad_norm": 6.852542877197266,
|
| 62 |
+
"learning_rate": 8.888888888888888e-06,
|
| 63 |
+
"loss": 0.1752,
|
| 64 |
+
"step": 228
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 4.0,
|
| 68 |
+
"eval_f1": 0.9814364876385337,
|
| 69 |
+
"eval_loss": 0.12476889789104462,
|
| 70 |
+
"eval_runtime": 4.5818,
|
| 71 |
+
"eval_samples_per_second": 21.825,
|
| 72 |
+
"eval_steps_per_second": 0.437,
|
| 73 |
+
"step": 228
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 5.0,
|
| 77 |
+
"grad_norm": 0.4434330463409424,
|
| 78 |
+
"learning_rate": 8.333333333333334e-06,
|
| 79 |
+
"loss": 0.0727,
|
| 80 |
+
"step": 285
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 5.0,
|
| 84 |
+
"eval_f1": 1.0,
|
| 85 |
+
"eval_loss": 0.0717741921544075,
|
| 86 |
+
"eval_runtime": 4.907,
|
| 87 |
+
"eval_samples_per_second": 20.379,
|
| 88 |
+
"eval_steps_per_second": 0.408,
|
| 89 |
+
"step": 285
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 6.0,
|
| 93 |
+
"grad_norm": 0.28406473994255066,
|
| 94 |
+
"learning_rate": 7.77777777777778e-06,
|
| 95 |
+
"loss": 0.0273,
|
| 96 |
+
"step": 342
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 6.0,
|
| 100 |
+
"eval_f1": 1.0,
|
| 101 |
+
"eval_loss": 0.03775007277727127,
|
| 102 |
+
"eval_runtime": 4.871,
|
| 103 |
+
"eval_samples_per_second": 20.53,
|
| 104 |
+
"eval_steps_per_second": 0.411,
|
| 105 |
+
"step": 342
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 7.0,
|
| 109 |
+
"grad_norm": 0.2636268436908722,
|
| 110 |
+
"learning_rate": 7.222222222222223e-06,
|
| 111 |
+
"loss": 0.0122,
|
| 112 |
+
"step": 399
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 7.0,
|
| 116 |
+
"eval_f1": 0.9879598662207357,
|
| 117 |
+
"eval_loss": 0.028589317575097084,
|
| 118 |
+
"eval_runtime": 4.85,
|
| 119 |
+
"eval_samples_per_second": 20.619,
|
| 120 |
+
"eval_steps_per_second": 0.412,
|
| 121 |
+
"step": 399
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 8.0,
|
| 125 |
+
"grad_norm": 0.20097118616104126,
|
| 126 |
+
"learning_rate": 6.666666666666667e-06,
|
| 127 |
+
"loss": 0.0066,
|
| 128 |
+
"step": 456
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.0,
|
| 132 |
+
"eval_f1": 0.9879598662207357,
|
| 133 |
+
"eval_loss": 0.02147584594786167,
|
| 134 |
+
"eval_runtime": 4.6,
|
| 135 |
+
"eval_samples_per_second": 21.739,
|
| 136 |
+
"eval_steps_per_second": 0.435,
|
| 137 |
+
"step": 456
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 9.0,
|
| 141 |
+
"grad_norm": 0.07710137218236923,
|
| 142 |
+
"learning_rate": 6.111111111111112e-06,
|
| 143 |
+
"loss": 0.0045,
|
| 144 |
+
"step": 513
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 9.0,
|
| 148 |
+
"eval_f1": 0.9879598662207357,
|
| 149 |
+
"eval_loss": 0.018611174076795578,
|
| 150 |
+
"eval_runtime": 4.3657,
|
| 151 |
+
"eval_samples_per_second": 22.906,
|
| 152 |
+
"eval_steps_per_second": 0.458,
|
| 153 |
+
"step": 513
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 10.0,
|
| 157 |
+
"grad_norm": 0.1254049688577652,
|
| 158 |
+
"learning_rate": 5.555555555555557e-06,
|
| 159 |
+
"loss": 0.0036,
|
| 160 |
+
"step": 570
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 10.0,
|
| 164 |
+
"eval_f1": 0.9879598662207357,
|
| 165 |
+
"eval_loss": 0.016895567998290062,
|
| 166 |
+
"eval_runtime": 4.619,
|
| 167 |
+
"eval_samples_per_second": 21.65,
|
| 168 |
+
"eval_steps_per_second": 0.433,
|
| 169 |
+
"step": 570
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 11.0,
|
| 173 |
+
"grad_norm": 0.22337734699249268,
|
| 174 |
+
"learning_rate": 5e-06,
|
| 175 |
+
"loss": 0.0031,
|
| 176 |
+
"step": 627
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 11.0,
|
| 180 |
+
"eval_f1": 0.9879598662207357,
|
| 181 |
+
"eval_loss": 0.016244541853666306,
|
| 182 |
+
"eval_runtime": 4.4069,
|
| 183 |
+
"eval_samples_per_second": 22.692,
|
| 184 |
+
"eval_steps_per_second": 0.454,
|
| 185 |
+
"step": 627
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 12.0,
|
| 189 |
+
"grad_norm": 0.1756511926651001,
|
| 190 |
+
"learning_rate": 4.444444444444444e-06,
|
| 191 |
+
"loss": 0.0027,
|
| 192 |
+
"step": 684
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 12.0,
|
| 196 |
+
"eval_f1": 0.9879598662207357,
|
| 197 |
+
"eval_loss": 0.015648650005459785,
|
| 198 |
+
"eval_runtime": 4.7525,
|
| 199 |
+
"eval_samples_per_second": 21.042,
|
| 200 |
+
"eval_steps_per_second": 0.421,
|
| 201 |
+
"step": 684
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 13.0,
|
| 205 |
+
"grad_norm": 0.13555917143821716,
|
| 206 |
+
"learning_rate": 3.88888888888889e-06,
|
| 207 |
+
"loss": 0.0024,
|
| 208 |
+
"step": 741
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 13.0,
|
| 212 |
+
"eval_f1": 0.9879598662207357,
|
| 213 |
+
"eval_loss": 0.01482668612152338,
|
| 214 |
+
"eval_runtime": 5.1927,
|
| 215 |
+
"eval_samples_per_second": 19.258,
|
| 216 |
+
"eval_steps_per_second": 0.385,
|
| 217 |
+
"step": 741
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 14.0,
|
| 221 |
+
"grad_norm": 0.03623472899198532,
|
| 222 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 223 |
+
"loss": 0.0022,
|
| 224 |
+
"step": 798
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 14.0,
|
| 228 |
+
"eval_f1": 0.9879598662207357,
|
| 229 |
+
"eval_loss": 0.014521930366754532,
|
| 230 |
+
"eval_runtime": 6.2096,
|
| 231 |
+
"eval_samples_per_second": 16.104,
|
| 232 |
+
"eval_steps_per_second": 0.322,
|
| 233 |
+
"step": 798
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 15.0,
|
| 237 |
+
"grad_norm": 0.08643201738595963,
|
| 238 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 239 |
+
"loss": 0.002,
|
| 240 |
+
"step": 855
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 15.0,
|
| 244 |
+
"eval_f1": 0.9879598662207357,
|
| 245 |
+
"eval_loss": 0.01371282059699297,
|
| 246 |
+
"eval_runtime": 2.6098,
|
| 247 |
+
"eval_samples_per_second": 38.317,
|
| 248 |
+
"eval_steps_per_second": 0.766,
|
| 249 |
+
"step": 855
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 16.0,
|
| 253 |
+
"grad_norm": 0.026679443195462227,
|
| 254 |
+
"learning_rate": 2.222222222222222e-06,
|
| 255 |
+
"loss": 0.0019,
|
| 256 |
+
"step": 912
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 16.0,
|
| 260 |
+
"eval_f1": 0.9879598662207357,
|
| 261 |
+
"eval_loss": 0.013448533602058887,
|
| 262 |
+
"eval_runtime": 6.11,
|
| 263 |
+
"eval_samples_per_second": 16.367,
|
| 264 |
+
"eval_steps_per_second": 0.327,
|
| 265 |
+
"step": 912
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 17.0,
|
| 269 |
+
"grad_norm": 0.04731046035885811,
|
| 270 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 271 |
+
"loss": 0.0018,
|
| 272 |
+
"step": 969
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 17.0,
|
| 276 |
+
"eval_f1": 0.9879598662207357,
|
| 277 |
+
"eval_loss": 0.013340299017727375,
|
| 278 |
+
"eval_runtime": 4.7908,
|
| 279 |
+
"eval_samples_per_second": 20.873,
|
| 280 |
+
"eval_steps_per_second": 0.417,
|
| 281 |
+
"step": 969
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 18.0,
|
| 285 |
+
"grad_norm": 0.019874220713973045,
|
| 286 |
+
"learning_rate": 1.111111111111111e-06,
|
| 287 |
+
"loss": 0.0017,
|
| 288 |
+
"step": 1026
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 18.0,
|
| 292 |
+
"eval_f1": 0.9879598662207357,
|
| 293 |
+
"eval_loss": 0.01337173581123352,
|
| 294 |
+
"eval_runtime": 4.6064,
|
| 295 |
+
"eval_samples_per_second": 21.709,
|
| 296 |
+
"eval_steps_per_second": 0.434,
|
| 297 |
+
"step": 1026
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 19.0,
|
| 301 |
+
"grad_norm": 0.022309044376015663,
|
| 302 |
+
"learning_rate": 5.555555555555555e-07,
|
| 303 |
+
"loss": 0.0017,
|
| 304 |
+
"step": 1083
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 19.0,
|
| 308 |
+
"eval_f1": 0.9879598662207357,
|
| 309 |
+
"eval_loss": 0.013301899656653404,
|
| 310 |
+
"eval_runtime": 3.5693,
|
| 311 |
+
"eval_samples_per_second": 28.017,
|
| 312 |
+
"eval_steps_per_second": 0.56,
|
| 313 |
+
"step": 1083
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 20.0,
|
| 317 |
+
"grad_norm": 0.03687524050474167,
|
| 318 |
+
"learning_rate": 0.0,
|
| 319 |
+
"loss": 0.0017,
|
| 320 |
+
"step": 1140
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 20.0,
|
| 324 |
+
"eval_f1": 0.9879598662207357,
|
| 325 |
+
"eval_loss": 0.013251620344817638,
|
| 326 |
+
"eval_runtime": 3.8862,
|
| 327 |
+
"eval_samples_per_second": 25.732,
|
| 328 |
+
"eval_steps_per_second": 0.515,
|
| 329 |
+
"step": 1140
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 20.0,
|
| 333 |
+
"step": 1140,
|
| 334 |
+
"total_flos": 1.394955826274304e+18,
|
| 335 |
+
"train_loss": 0.21872812718675846,
|
| 336 |
+
"train_runtime": 2803.2829,
|
| 337 |
+
"train_samples_per_second": 6.421,
|
| 338 |
+
"train_steps_per_second": 0.407
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 20.0,
|
| 342 |
+
"eval_f1": 0.9879598662207357,
|
| 343 |
+
"eval_loss": 0.013251620344817638,
|
| 344 |
+
"eval_runtime": 3.382,
|
| 345 |
+
"eval_samples_per_second": 29.568,
|
| 346 |
+
"eval_steps_per_second": 0.591,
|
| 347 |
+
"step": 1140
|
| 348 |
+
}
|
| 349 |
+
],
|
| 350 |
+
"logging_steps": 500,
|
| 351 |
+
"max_steps": 1140,
|
| 352 |
+
"num_input_tokens_seen": 0,
|
| 353 |
+
"num_train_epochs": 20,
|
| 354 |
+
"save_steps": 500,
|
| 355 |
+
"stateful_callbacks": {
|
| 356 |
+
"TrainerControl": {
|
| 357 |
+
"args": {
|
| 358 |
+
"should_epoch_stop": false,
|
| 359 |
+
"should_evaluate": false,
|
| 360 |
+
"should_log": false,
|
| 361 |
+
"should_save": true,
|
| 362 |
+
"should_training_stop": true
|
| 363 |
+
},
|
| 364 |
+
"attributes": {}
|
| 365 |
+
}
|
| 366 |
+
},
|
| 367 |
+
"total_flos": 1.394955826274304e+18,
|
| 368 |
+
"train_batch_size": 16,
|
| 369 |
+
"trial_name": null,
|
| 370 |
+
"trial_params": null
|
| 371 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdb17181f51b485d04172d246a60053b7b83c9b97c09d0f8abe1d7df7daa6f87
|
| 3 |
+
size 5048
|