End of training
Browse files
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second": 5.
|
| 7 |
-
"eval_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.2,
|
| 3 |
+
"eval_accuracy": 0.9161290322580645,
|
| 4 |
+
"eval_loss": 0.25597548484802246,
|
| 5 |
+
"eval_runtime": 28.3145,
|
| 6 |
+
"eval_samples_per_second": 5.474,
|
| 7 |
+
"eval_steps_per_second": 1.377
|
| 8 |
}
|
runs/May22_15-06-40_b08fa7a48520/events.out.tfevents.1716391081.b08fa7a48520.34.1
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:bf9f028c60e87fc04b88609ab05066e0d4b6d5287eee967000126c02f4c0a474
|
| 3 |
+
size 734
|
test_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second": 5.
|
| 7 |
-
"eval_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.2,
|
| 3 |
+
"eval_accuracy": 0.9161290322580645,
|
| 4 |
+
"eval_loss": 0.25597548484802246,
|
| 5 |
+
"eval_runtime": 28.3145,
|
| 6 |
+
"eval_samples_per_second": 5.474,
|
| 7 |
+
"eval_steps_per_second": 1.377
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,105 +1,351 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 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.
|
| 13 |
-
"grad_norm": 10.
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss":
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss":
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate": 3.
|
| 29 |
-
"loss":
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss":
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss":
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch":
|
| 62 |
-
"eval_accuracy": 0.
|
| 63 |
-
"eval_loss":
|
| 64 |
-
"eval_runtime":
|
| 65 |
-
"eval_samples_per_second": 5.
|
| 66 |
-
"eval_steps_per_second": 1.
|
| 67 |
"step": 75
|
| 68 |
},
|
| 69 |
{
|
| 70 |
-
"epoch": 1.
|
| 71 |
-
"
|
| 72 |
-
"
|
| 73 |
-
"
|
| 74 |
-
"
|
| 75 |
-
"train_samples_per_second": 2.611,
|
| 76 |
-
"train_steps_per_second": 0.653
|
| 77 |
},
|
| 78 |
{
|
| 79 |
-
"epoch": 1.
|
| 80 |
-
"
|
| 81 |
-
"
|
| 82 |
-
"
|
| 83 |
-
"
|
| 84 |
-
"eval_steps_per_second": 1.372,
|
| 85 |
-
"step": 75
|
| 86 |
},
|
| 87 |
{
|
| 88 |
-
"epoch": 1.
|
| 89 |
-
"
|
| 90 |
-
"
|
| 91 |
-
"
|
| 92 |
-
"
|
| 93 |
-
|
| 94 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 95 |
}
|
| 96 |
],
|
| 97 |
"logging_steps": 10,
|
| 98 |
-
"max_steps":
|
| 99 |
"num_input_tokens_seen": 0,
|
| 100 |
"num_train_epochs": 9223372036854775807,
|
| 101 |
"save_steps": 500,
|
| 102 |
-
"total_flos":
|
| 103 |
"train_batch_size": 4,
|
| 104 |
"trial_name": null,
|
| 105 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-375",
|
| 4 |
+
"epoch": 4.2,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 375,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"grad_norm": 10.424443244934082,
|
| 14 |
+
"learning_rate": 1.3157894736842106e-05,
|
| 15 |
+
"loss": 2.3451,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 9.281598091125488,
|
| 21 |
+
"learning_rate": 2.6315789473684212e-05,
|
| 22 |
+
"loss": 2.3445,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.08,
|
| 27 |
+
"grad_norm": 9.415879249572754,
|
| 28 |
+
"learning_rate": 3.9473684210526316e-05,
|
| 29 |
+
"loss": 2.234,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.11,
|
| 34 |
+
"grad_norm": 9.546265602111816,
|
| 35 |
+
"learning_rate": 4.9703264094955494e-05,
|
| 36 |
+
"loss": 2.1348,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.13,
|
| 41 |
+
"grad_norm": 12.744800567626953,
|
| 42 |
+
"learning_rate": 4.821958456973294e-05,
|
| 43 |
+
"loss": 2.0604,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.16,
|
| 48 |
+
"grad_norm": 9.805941581726074,
|
| 49 |
+
"learning_rate": 4.673590504451038e-05,
|
| 50 |
+
"loss": 1.8655,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.19,
|
| 55 |
+
"grad_norm": 15.323193550109863,
|
| 56 |
+
"learning_rate": 4.525222551928784e-05,
|
| 57 |
+
"loss": 1.9591,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.2,
|
| 62 |
+
"eval_accuracy": 0.42857142857142855,
|
| 63 |
+
"eval_loss": 1.6628010272979736,
|
| 64 |
+
"eval_runtime": 13.2129,
|
| 65 |
+
"eval_samples_per_second": 5.298,
|
| 66 |
+
"eval_steps_per_second": 1.362,
|
| 67 |
"step": 75
|
| 68 |
},
|
| 69 |
{
|
| 70 |
+
"epoch": 1.01,
|
| 71 |
+
"grad_norm": 11.818169593811035,
|
| 72 |
+
"learning_rate": 4.3768545994065286e-05,
|
| 73 |
+
"loss": 1.482,
|
| 74 |
+
"step": 80
|
|
|
|
|
|
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 1.04,
|
| 78 |
+
"grad_norm": 12.213088035583496,
|
| 79 |
+
"learning_rate": 4.228486646884273e-05,
|
| 80 |
+
"loss": 1.2242,
|
| 81 |
+
"step": 90
|
|
|
|
|
|
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 1.07,
|
| 85 |
+
"grad_norm": 18.863269805908203,
|
| 86 |
+
"learning_rate": 4.080118694362018e-05,
|
| 87 |
+
"loss": 1.0472,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.09,
|
| 92 |
+
"grad_norm": 10.183364868164062,
|
| 93 |
+
"learning_rate": 3.9317507418397627e-05,
|
| 94 |
+
"loss": 0.7998,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.12,
|
| 99 |
+
"grad_norm": 9.917871475219727,
|
| 100 |
+
"learning_rate": 3.783382789317508e-05,
|
| 101 |
+
"loss": 0.837,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.15,
|
| 106 |
+
"grad_norm": 15.699859619140625,
|
| 107 |
+
"learning_rate": 3.635014836795252e-05,
|
| 108 |
+
"loss": 0.6737,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.17,
|
| 113 |
+
"grad_norm": 11.725618362426758,
|
| 114 |
+
"learning_rate": 3.4866468842729974e-05,
|
| 115 |
+
"loss": 0.6864,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.2,
|
| 120 |
+
"grad_norm": 65.09258270263672,
|
| 121 |
+
"learning_rate": 3.338278931750742e-05,
|
| 122 |
+
"loss": 0.9775,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.2,
|
| 127 |
+
"eval_accuracy": 0.7285714285714285,
|
| 128 |
+
"eval_loss": 0.9276337623596191,
|
| 129 |
+
"eval_runtime": 12.7097,
|
| 130 |
+
"eval_samples_per_second": 5.508,
|
| 131 |
+
"eval_steps_per_second": 1.416,
|
| 132 |
+
"step": 150
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.03,
|
| 136 |
+
"grad_norm": 11.323193550109863,
|
| 137 |
+
"learning_rate": 3.189910979228487e-05,
|
| 138 |
+
"loss": 0.4997,
|
| 139 |
+
"step": 160
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 2.05,
|
| 143 |
+
"grad_norm": 34.906097412109375,
|
| 144 |
+
"learning_rate": 3.0415430267062318e-05,
|
| 145 |
+
"loss": 0.5372,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.08,
|
| 150 |
+
"grad_norm": 4.410595893859863,
|
| 151 |
+
"learning_rate": 2.8931750741839762e-05,
|
| 152 |
+
"loss": 0.5236,
|
| 153 |
+
"step": 180
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.11,
|
| 157 |
+
"grad_norm": 11.69422721862793,
|
| 158 |
+
"learning_rate": 2.744807121661721e-05,
|
| 159 |
+
"loss": 0.3245,
|
| 160 |
+
"step": 190
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.13,
|
| 164 |
+
"grad_norm": 16.422433853149414,
|
| 165 |
+
"learning_rate": 2.5964391691394662e-05,
|
| 166 |
+
"loss": 0.4124,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.16,
|
| 171 |
+
"grad_norm": 5.309849739074707,
|
| 172 |
+
"learning_rate": 2.4480712166172106e-05,
|
| 173 |
+
"loss": 0.4554,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.19,
|
| 178 |
+
"grad_norm": 1.0133864879608154,
|
| 179 |
+
"learning_rate": 2.2997032640949558e-05,
|
| 180 |
+
"loss": 0.2693,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.2,
|
| 185 |
+
"eval_accuracy": 0.7428571428571429,
|
| 186 |
+
"eval_loss": 0.4798918664455414,
|
| 187 |
+
"eval_runtime": 12.6824,
|
| 188 |
+
"eval_samples_per_second": 5.519,
|
| 189 |
+
"eval_steps_per_second": 1.419,
|
| 190 |
+
"step": 225
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.01,
|
| 194 |
+
"grad_norm": 1.2999351024627686,
|
| 195 |
+
"learning_rate": 2.1513353115727002e-05,
|
| 196 |
+
"loss": 0.2994,
|
| 197 |
+
"step": 230
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.04,
|
| 201 |
+
"grad_norm": 0.5214590430259705,
|
| 202 |
+
"learning_rate": 2.0029673590504454e-05,
|
| 203 |
+
"loss": 0.0871,
|
| 204 |
+
"step": 240
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.07,
|
| 208 |
+
"grad_norm": 22.973987579345703,
|
| 209 |
+
"learning_rate": 1.85459940652819e-05,
|
| 210 |
+
"loss": 0.1398,
|
| 211 |
+
"step": 250
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 3.09,
|
| 215 |
+
"grad_norm": 0.22316251695156097,
|
| 216 |
+
"learning_rate": 1.706231454005935e-05,
|
| 217 |
+
"loss": 0.0745,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.12,
|
| 222 |
+
"grad_norm": 1.7083332538604736,
|
| 223 |
+
"learning_rate": 1.5578635014836794e-05,
|
| 224 |
+
"loss": 0.2018,
|
| 225 |
+
"step": 270
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 3.15,
|
| 229 |
+
"grad_norm": 0.34350940585136414,
|
| 230 |
+
"learning_rate": 1.4094955489614246e-05,
|
| 231 |
+
"loss": 0.282,
|
| 232 |
+
"step": 280
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 3.17,
|
| 236 |
+
"grad_norm": 2.1111364364624023,
|
| 237 |
+
"learning_rate": 1.2611275964391692e-05,
|
| 238 |
+
"loss": 0.2336,
|
| 239 |
+
"step": 290
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 3.2,
|
| 243 |
+
"grad_norm": 2.993694305419922,
|
| 244 |
+
"learning_rate": 1.112759643916914e-05,
|
| 245 |
+
"loss": 0.2194,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.2,
|
| 250 |
+
"eval_accuracy": 0.8285714285714286,
|
| 251 |
+
"eval_loss": 0.43333032727241516,
|
| 252 |
+
"eval_runtime": 12.7052,
|
| 253 |
+
"eval_samples_per_second": 5.51,
|
| 254 |
+
"eval_steps_per_second": 1.417,
|
| 255 |
+
"step": 300
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 4.03,
|
| 259 |
+
"grad_norm": 0.44264498353004456,
|
| 260 |
+
"learning_rate": 9.643916913946588e-06,
|
| 261 |
+
"loss": 0.0751,
|
| 262 |
+
"step": 310
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 4.05,
|
| 266 |
+
"grad_norm": 8.502839088439941,
|
| 267 |
+
"learning_rate": 8.160237388724036e-06,
|
| 268 |
+
"loss": 0.2655,
|
| 269 |
+
"step": 320
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 4.08,
|
| 273 |
+
"grad_norm": 11.5534086227417,
|
| 274 |
+
"learning_rate": 6.676557863501484e-06,
|
| 275 |
+
"loss": 0.2037,
|
| 276 |
+
"step": 330
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 4.11,
|
| 280 |
+
"grad_norm": 1.2078895568847656,
|
| 281 |
+
"learning_rate": 5.192878338278932e-06,
|
| 282 |
+
"loss": 0.0657,
|
| 283 |
+
"step": 340
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 4.13,
|
| 287 |
+
"grad_norm": 0.2843732535839081,
|
| 288 |
+
"learning_rate": 3.7091988130563796e-06,
|
| 289 |
+
"loss": 0.1069,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.16,
|
| 294 |
+
"grad_norm": 0.15084530413150787,
|
| 295 |
+
"learning_rate": 2.225519287833828e-06,
|
| 296 |
+
"loss": 0.073,
|
| 297 |
+
"step": 360
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.19,
|
| 301 |
+
"grad_norm": 0.18272823095321655,
|
| 302 |
+
"learning_rate": 7.41839762611276e-07,
|
| 303 |
+
"loss": 0.0873,
|
| 304 |
+
"step": 370
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 4.2,
|
| 308 |
+
"eval_accuracy": 0.9,
|
| 309 |
+
"eval_loss": 0.31446826457977295,
|
| 310 |
+
"eval_runtime": 12.7219,
|
| 311 |
+
"eval_samples_per_second": 5.502,
|
| 312 |
+
"eval_steps_per_second": 1.415,
|
| 313 |
+
"step": 375
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 4.2,
|
| 317 |
+
"step": 375,
|
| 318 |
+
"total_flos": 1.86923023515648e+18,
|
| 319 |
+
"train_loss": 0.7497338762482008,
|
| 320 |
+
"train_runtime": 612.0494,
|
| 321 |
+
"train_samples_per_second": 2.451,
|
| 322 |
+
"train_steps_per_second": 0.613
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 4.2,
|
| 326 |
+
"eval_accuracy": 0.9161290322580645,
|
| 327 |
+
"eval_loss": 0.25597551465034485,
|
| 328 |
+
"eval_runtime": 29.0097,
|
| 329 |
+
"eval_samples_per_second": 5.343,
|
| 330 |
+
"eval_steps_per_second": 1.344,
|
| 331 |
+
"step": 375
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.2,
|
| 335 |
+
"eval_accuracy": 0.9161290322580645,
|
| 336 |
+
"eval_loss": 0.25597548484802246,
|
| 337 |
+
"eval_runtime": 28.3145,
|
| 338 |
+
"eval_samples_per_second": 5.474,
|
| 339 |
+
"eval_steps_per_second": 1.377,
|
| 340 |
+
"step": 375
|
| 341 |
}
|
| 342 |
],
|
| 343 |
"logging_steps": 10,
|
| 344 |
+
"max_steps": 375,
|
| 345 |
"num_input_tokens_seen": 0,
|
| 346 |
"num_train_epochs": 9223372036854775807,
|
| 347 |
"save_steps": 500,
|
| 348 |
+
"total_flos": 1.86923023515648e+18,
|
| 349 |
"train_batch_size": 4,
|
| 350 |
"trial_name": null,
|
| 351 |
"trial_params": null
|