End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.2439999999999998,
|
| 3 |
+
"eval_accuracy": 0.7586206896551724,
|
| 4 |
+
"eval_loss": 0.8059644103050232,
|
| 5 |
+
"eval_runtime": 62.6184,
|
| 6 |
+
"eval_samples_per_second": 0.926,
|
| 7 |
+
"eval_steps_per_second": 0.064
|
| 8 |
+
}
|
runs/Sep28_19-47-20_602ba6f27d79/events.out.tfevents.1727558261.602ba6f27d79.31.1
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dfcb22a57eb377196ca671d27371b35d547c57b65e7e1bad37d24bd0487079a7
|
| 3 |
+
size 734
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.2439999999999998,
|
| 3 |
+
"eval_accuracy": 0.7586206896551724,
|
| 4 |
+
"eval_loss": 0.8059644103050232,
|
| 5 |
+
"eval_runtime": 62.6184,
|
| 6 |
+
"eval_samples_per_second": 0.926,
|
| 7 |
+
"eval_steps_per_second": 0.064
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,271 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6818181818181818,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-Custom_Dataset_Finetune/checkpoint-126",
|
| 4 |
+
"epoch": 3.2439999999999998,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.04,
|
| 13 |
+
"grad_norm": 4.941892147064209,
|
| 14 |
+
"learning_rate": 2.4e-05,
|
| 15 |
+
"loss": 1.8353,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.08,
|
| 20 |
+
"grad_norm": 6.511570453643799,
|
| 21 |
+
"learning_rate": 4.8e-05,
|
| 22 |
+
"loss": 1.7037,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.12,
|
| 27 |
+
"grad_norm": 5.7441301345825195,
|
| 28 |
+
"learning_rate": 5.8666666666666665e-05,
|
| 29 |
+
"loss": 1.4799,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.16,
|
| 34 |
+
"grad_norm": 6.4645514488220215,
|
| 35 |
+
"learning_rate": 5.6e-05,
|
| 36 |
+
"loss": 1.2797,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2,
|
| 41 |
+
"grad_norm": 6.132994651794434,
|
| 42 |
+
"learning_rate": 5.333333333333333e-05,
|
| 43 |
+
"loss": 1.1603,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24,
|
| 48 |
+
"grad_norm": 4.506332874298096,
|
| 49 |
+
"learning_rate": 5.066666666666667e-05,
|
| 50 |
+
"loss": 0.9284,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.252,
|
| 55 |
+
"eval_accuracy": 0.5151515151515151,
|
| 56 |
+
"eval_loss": 0.9844135046005249,
|
| 57 |
+
"eval_runtime": 60.7277,
|
| 58 |
+
"eval_samples_per_second": 1.087,
|
| 59 |
+
"eval_steps_per_second": 0.082,
|
| 60 |
+
"step": 63
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.028,
|
| 64 |
+
"grad_norm": 6.4644880294799805,
|
| 65 |
+
"learning_rate": 4.8e-05,
|
| 66 |
+
"loss": 0.918,
|
| 67 |
+
"step": 70
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.068,
|
| 71 |
+
"grad_norm": 10.729351997375488,
|
| 72 |
+
"learning_rate": 4.5333333333333335e-05,
|
| 73 |
+
"loss": 0.9294,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.108,
|
| 78 |
+
"grad_norm": 8.79098129272461,
|
| 79 |
+
"learning_rate": 4.266666666666667e-05,
|
| 80 |
+
"loss": 0.9386,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.148,
|
| 85 |
+
"grad_norm": 4.564964294433594,
|
| 86 |
+
"learning_rate": 3.9999999999999996e-05,
|
| 87 |
+
"loss": 1.0353,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.188,
|
| 92 |
+
"grad_norm": 6.161099433898926,
|
| 93 |
+
"learning_rate": 3.733333333333334e-05,
|
| 94 |
+
"loss": 0.9968,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.228,
|
| 99 |
+
"grad_norm": 4.650356292724609,
|
| 100 |
+
"learning_rate": 3.4666666666666665e-05,
|
| 101 |
+
"loss": 0.9402,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.252,
|
| 106 |
+
"eval_accuracy": 0.6818181818181818,
|
| 107 |
+
"eval_loss": 0.9521052241325378,
|
| 108 |
+
"eval_runtime": 62.8381,
|
| 109 |
+
"eval_samples_per_second": 1.05,
|
| 110 |
+
"eval_steps_per_second": 0.08,
|
| 111 |
+
"step": 126
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.016,
|
| 115 |
+
"grad_norm": 3.565009117126465,
|
| 116 |
+
"learning_rate": 3.2e-05,
|
| 117 |
+
"loss": 0.8584,
|
| 118 |
+
"step": 130
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.056,
|
| 122 |
+
"grad_norm": 5.3584489822387695,
|
| 123 |
+
"learning_rate": 2.9333333333333333e-05,
|
| 124 |
+
"loss": 0.8446,
|
| 125 |
+
"step": 140
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.096,
|
| 129 |
+
"grad_norm": 9.390802383422852,
|
| 130 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 131 |
+
"loss": 0.8279,
|
| 132 |
+
"step": 150
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.136,
|
| 136 |
+
"grad_norm": 7.512342929840088,
|
| 137 |
+
"learning_rate": 2.4e-05,
|
| 138 |
+
"loss": 0.8049,
|
| 139 |
+
"step": 160
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.176,
|
| 143 |
+
"grad_norm": 4.40623664855957,
|
| 144 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 145 |
+
"loss": 0.8291,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.216,
|
| 150 |
+
"grad_norm": 6.4893059730529785,
|
| 151 |
+
"learning_rate": 1.866666666666667e-05,
|
| 152 |
+
"loss": 0.8639,
|
| 153 |
+
"step": 180
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.252,
|
| 157 |
+
"eval_accuracy": 0.6060606060606061,
|
| 158 |
+
"eval_loss": 0.7931472063064575,
|
| 159 |
+
"eval_runtime": 63.7339,
|
| 160 |
+
"eval_samples_per_second": 1.036,
|
| 161 |
+
"eval_steps_per_second": 0.078,
|
| 162 |
+
"step": 189
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.004,
|
| 166 |
+
"grad_norm": 5.078976154327393,
|
| 167 |
+
"learning_rate": 1.6e-05,
|
| 168 |
+
"loss": 0.7345,
|
| 169 |
+
"step": 190
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 3.044,
|
| 173 |
+
"grad_norm": 2.724031925201416,
|
| 174 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 175 |
+
"loss": 0.7462,
|
| 176 |
+
"step": 200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.084,
|
| 180 |
+
"grad_norm": 3.8141984939575195,
|
| 181 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 182 |
+
"loss": 0.7004,
|
| 183 |
+
"step": 210
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.124,
|
| 187 |
+
"grad_norm": 3.8294148445129395,
|
| 188 |
+
"learning_rate": 8e-06,
|
| 189 |
+
"loss": 0.7095,
|
| 190 |
+
"step": 220
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.164,
|
| 194 |
+
"grad_norm": 5.064866065979004,
|
| 195 |
+
"learning_rate": 5.333333333333334e-06,
|
| 196 |
+
"loss": 0.7274,
|
| 197 |
+
"step": 230
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.204,
|
| 201 |
+
"grad_norm": 3.320218801498413,
|
| 202 |
+
"learning_rate": 2.666666666666667e-06,
|
| 203 |
+
"loss": 0.6674,
|
| 204 |
+
"step": 240
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.2439999999999998,
|
| 208 |
+
"grad_norm": 3.968177080154419,
|
| 209 |
+
"learning_rate": 0.0,
|
| 210 |
+
"loss": 0.6195,
|
| 211 |
+
"step": 250
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 3.2439999999999998,
|
| 215 |
+
"eval_accuracy": 0.6363636363636364,
|
| 216 |
+
"eval_loss": 0.910934329032898,
|
| 217 |
+
"eval_runtime": 73.6738,
|
| 218 |
+
"eval_samples_per_second": 0.896,
|
| 219 |
+
"eval_steps_per_second": 0.068,
|
| 220 |
+
"step": 250
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 3.2439999999999998,
|
| 224 |
+
"step": 250,
|
| 225 |
+
"total_flos": 4.9769595049134e+18,
|
| 226 |
+
"train_loss": 0.9631701583862304,
|
| 227 |
+
"train_runtime": 5330.9549,
|
| 228 |
+
"train_samples_per_second": 0.75,
|
| 229 |
+
"train_steps_per_second": 0.047
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 3.2439999999999998,
|
| 233 |
+
"eval_accuracy": 0.7586206896551724,
|
| 234 |
+
"eval_loss": 0.8059645295143127,
|
| 235 |
+
"eval_runtime": 63.0154,
|
| 236 |
+
"eval_samples_per_second": 0.92,
|
| 237 |
+
"eval_steps_per_second": 0.063,
|
| 238 |
+
"step": 250
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 3.2439999999999998,
|
| 242 |
+
"eval_accuracy": 0.7586206896551724,
|
| 243 |
+
"eval_loss": 0.8059644103050232,
|
| 244 |
+
"eval_runtime": 62.6184,
|
| 245 |
+
"eval_samples_per_second": 0.926,
|
| 246 |
+
"eval_steps_per_second": 0.064,
|
| 247 |
+
"step": 250
|
| 248 |
+
}
|
| 249 |
+
],
|
| 250 |
+
"logging_steps": 10,
|
| 251 |
+
"max_steps": 250,
|
| 252 |
+
"num_input_tokens_seen": 0,
|
| 253 |
+
"num_train_epochs": 9223372036854775807,
|
| 254 |
+
"save_steps": 500,
|
| 255 |
+
"stateful_callbacks": {
|
| 256 |
+
"TrainerControl": {
|
| 257 |
+
"args": {
|
| 258 |
+
"should_epoch_stop": false,
|
| 259 |
+
"should_evaluate": false,
|
| 260 |
+
"should_log": false,
|
| 261 |
+
"should_save": true,
|
| 262 |
+
"should_training_stop": true
|
| 263 |
+
},
|
| 264 |
+
"attributes": {}
|
| 265 |
+
}
|
| 266 |
+
},
|
| 267 |
+
"total_flos": 4.9769595049134e+18,
|
| 268 |
+
"train_batch_size": 16,
|
| 269 |
+
"trial_name": null,
|
| 270 |
+
"trial_params": null
|
| 271 |
+
}
|