Training in progress, epoch 0
Browse files- all_results.json +2 -2
- pytorch_model.bin +1 -1
- test_results.json +2 -6
- trainer_state.json +468 -120
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 14.05,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss":
|
| 5 |
"eval_runtime": 44.2055,
|
| 6 |
"eval_samples_per_second": 0.724,
|
| 7 |
"eval_steps_per_second": 0.181
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 14.05,
|
| 3 |
+
"eval_accuracy": 0.75,
|
| 4 |
+
"eval_loss": 0.7047864198684692,
|
| 5 |
"eval_runtime": 44.2055,
|
| 6 |
"eval_samples_per_second": 0.724,
|
| 7 |
"eval_steps_per_second": 0.181
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 344991221
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48e143d40e68c068ea767c1097593f1eb66eb40b2e22e879162519301dafab74
|
| 3 |
size 344991221
|
test_results.json
CHANGED
|
@@ -1,8 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"eval_loss": 1.7664662599563599,
|
| 5 |
-
"eval_runtime": 44.2055,
|
| 6 |
-
"eval_samples_per_second": 0.724,
|
| 7 |
-
"eval_steps_per_second": 0.181
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"eval_accuracy": 0.75,
|
| 3 |
+
"eval_loss": 0.7047864198684692
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
}
|
trainer_state.json
CHANGED
|
@@ -1,202 +1,550 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "videomae-base-ipm_first_videos/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 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.
|
| 12 |
"eval_accuracy": 0.22857142857142856,
|
| 13 |
-
"eval_loss": 1.
|
| 14 |
-
"eval_runtime":
|
| 15 |
-
"eval_samples_per_second": 0.
|
| 16 |
-
"eval_steps_per_second": 0.
|
| 17 |
"step": 3
|
| 18 |
},
|
| 19 |
{
|
| 20 |
-
"epoch": 1.
|
| 21 |
-
"eval_accuracy": 0.
|
| 22 |
-
"eval_loss": 1.
|
| 23 |
-
"eval_runtime":
|
| 24 |
-
"eval_samples_per_second": 0.
|
| 25 |
-
"eval_steps_per_second": 0.
|
| 26 |
"step": 6
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 2.
|
| 30 |
-
"eval_accuracy": 0.
|
| 31 |
-
"eval_loss": 1.
|
| 32 |
-
"eval_runtime":
|
| 33 |
-
"eval_samples_per_second": 0.
|
| 34 |
-
"eval_steps_per_second": 0.
|
| 35 |
"step": 9
|
| 36 |
},
|
| 37 |
{
|
| 38 |
-
"epoch": 3.
|
| 39 |
-
"learning_rate":
|
| 40 |
-
"loss": 1.
|
| 41 |
"step": 10
|
| 42 |
},
|
| 43 |
{
|
| 44 |
-
"epoch": 3.
|
| 45 |
"eval_accuracy": 0.11428571428571428,
|
| 46 |
-
"eval_loss":
|
| 47 |
-
"eval_runtime":
|
| 48 |
-
"eval_samples_per_second": 0.
|
| 49 |
-
"eval_steps_per_second": 0.
|
| 50 |
"step": 12
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch": 4.
|
| 54 |
"eval_accuracy": 0.11428571428571428,
|
| 55 |
-
"eval_loss":
|
| 56 |
-
"eval_runtime":
|
| 57 |
-
"eval_samples_per_second": 0.
|
| 58 |
-
"eval_steps_per_second": 0.
|
| 59 |
"step": 15
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch": 5.
|
| 63 |
"eval_accuracy": 0.11428571428571428,
|
| 64 |
-
"eval_loss":
|
| 65 |
-
"eval_runtime":
|
| 66 |
-
"eval_samples_per_second": 0.
|
| 67 |
-
"eval_steps_per_second": 0.
|
| 68 |
"step": 18
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch": 6.
|
| 72 |
-
"learning_rate": 3.
|
| 73 |
-
"loss": 1.
|
| 74 |
"step": 20
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch": 6.
|
| 78 |
"eval_accuracy": 0.11428571428571428,
|
| 79 |
-
"eval_loss":
|
| 80 |
-
"eval_runtime":
|
| 81 |
-
"eval_samples_per_second": 0.
|
| 82 |
-
"eval_steps_per_second": 0.
|
| 83 |
"step": 21
|
| 84 |
},
|
| 85 |
{
|
| 86 |
-
"epoch": 7.
|
| 87 |
"eval_accuracy": 0.11428571428571428,
|
| 88 |
-
"eval_loss": 2.
|
| 89 |
-
"eval_runtime":
|
| 90 |
-
"eval_samples_per_second": 0.
|
| 91 |
-
"eval_steps_per_second": 0.
|
| 92 |
"step": 24
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch": 8.
|
| 96 |
"eval_accuracy": 0.11428571428571428,
|
| 97 |
-
"eval_loss": 2.
|
| 98 |
-
"eval_runtime":
|
| 99 |
-
"eval_samples_per_second": 0.
|
| 100 |
-
"eval_steps_per_second": 0.
|
| 101 |
"step": 27
|
| 102 |
},
|
| 103 |
{
|
| 104 |
-
"epoch": 9.
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 1.
|
| 107 |
"step": 30
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch": 9.
|
| 111 |
"eval_accuracy": 0.11428571428571428,
|
| 112 |
-
"eval_loss": 2.
|
| 113 |
-
"eval_runtime":
|
| 114 |
-
"eval_samples_per_second": 0.
|
| 115 |
-
"eval_steps_per_second": 0.
|
| 116 |
"step": 30
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch": 10.
|
| 120 |
-
"eval_accuracy": 0.
|
| 121 |
-
"eval_loss": 2.
|
| 122 |
-
"eval_runtime":
|
| 123 |
-
"eval_samples_per_second": 0.
|
| 124 |
-
"eval_steps_per_second": 0.
|
| 125 |
"step": 33
|
| 126 |
},
|
| 127 |
{
|
| 128 |
-
"epoch": 11.
|
| 129 |
-
"eval_accuracy": 0.
|
| 130 |
-
"eval_loss": 2.
|
| 131 |
-
"eval_runtime":
|
| 132 |
-
"eval_samples_per_second": 0.
|
| 133 |
-
"eval_steps_per_second": 0.
|
| 134 |
"step": 36
|
| 135 |
},
|
| 136 |
{
|
| 137 |
-
"epoch": 12.
|
| 138 |
-
"eval_accuracy": 0.
|
| 139 |
-
"eval_loss": 2.
|
| 140 |
-
"eval_runtime":
|
| 141 |
-
"eval_samples_per_second": 0.
|
| 142 |
-
"eval_steps_per_second": 0.
|
| 143 |
"step": 39
|
| 144 |
},
|
| 145 |
{
|
| 146 |
-
"epoch": 13.
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss": 1.
|
| 149 |
"step": 40
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch": 13.
|
| 153 |
-
"eval_accuracy": 0.
|
| 154 |
-
"eval_loss": 2.
|
| 155 |
-
"eval_runtime":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 156 |
"eval_samples_per_second": 0.631,
|
| 157 |
"eval_steps_per_second": 0.162,
|
| 158 |
-
"step":
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch":
|
| 162 |
-
"eval_accuracy": 0.
|
| 163 |
-
"eval_loss": 2.
|
| 164 |
-
"eval_runtime":
|
| 165 |
-
"eval_samples_per_second": 0.
|
| 166 |
-
"eval_steps_per_second": 0.
|
| 167 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 168 |
},
|
| 169 |
{
|
| 170 |
-
"epoch":
|
| 171 |
-
"
|
| 172 |
-
"
|
| 173 |
-
"
|
| 174 |
-
"train_runtime": 1281.9744,
|
| 175 |
-
"train_samples_per_second": 0.137,
|
| 176 |
-
"train_steps_per_second": 0.034
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"epoch":
|
| 180 |
-
"eval_accuracy": 0.
|
| 181 |
-
"eval_loss": 1.
|
| 182 |
-
"eval_runtime":
|
| 183 |
-
"eval_samples_per_second": 0.
|
| 184 |
-
"eval_steps_per_second": 0.
|
| 185 |
-
"step":
|
| 186 |
},
|
| 187 |
{
|
| 188 |
-
"epoch":
|
| 189 |
-
"eval_accuracy": 0.
|
| 190 |
-
"eval_loss": 1.
|
| 191 |
-
"eval_runtime":
|
| 192 |
-
"eval_samples_per_second": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 193 |
"eval_steps_per_second": 0.181,
|
| 194 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 195 |
}
|
| 196 |
],
|
| 197 |
-
"max_steps":
|
| 198 |
"num_train_epochs": 9223372036854775807,
|
| 199 |
-
"total_flos":
|
| 200 |
"trial_name": null,
|
| 201 |
"trial_params": null
|
| 202 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8,
|
| 3 |
+
"best_model_checkpoint": "videomae-base-ipm_first_videos/checkpoint-123",
|
| 4 |
+
"epoch": 48.00606060606061,
|
| 5 |
+
"global_step": 146,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
"eval_accuracy": 0.22857142857142856,
|
| 13 |
+
"eval_loss": 1.7709606885910034,
|
| 14 |
+
"eval_runtime": 56.0244,
|
| 15 |
+
"eval_samples_per_second": 0.625,
|
| 16 |
+
"eval_steps_per_second": 0.161,
|
| 17 |
"step": 3
|
| 18 |
},
|
| 19 |
{
|
| 20 |
+
"epoch": 1.01,
|
| 21 |
+
"eval_accuracy": 0.14285714285714285,
|
| 22 |
+
"eval_loss": 1.7788584232330322,
|
| 23 |
+
"eval_runtime": 54.8936,
|
| 24 |
+
"eval_samples_per_second": 0.638,
|
| 25 |
+
"eval_steps_per_second": 0.164,
|
| 26 |
"step": 6
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 2.01,
|
| 30 |
+
"eval_accuracy": 0.08571428571428572,
|
| 31 |
+
"eval_loss": 1.7939355373382568,
|
| 32 |
+
"eval_runtime": 57.093,
|
| 33 |
+
"eval_samples_per_second": 0.613,
|
| 34 |
+
"eval_steps_per_second": 0.158,
|
| 35 |
"step": 9
|
| 36 |
},
|
| 37 |
{
|
| 38 |
+
"epoch": 3.0,
|
| 39 |
+
"learning_rate": 1.5151515151515153e-05,
|
| 40 |
+
"loss": 1.7369,
|
| 41 |
"step": 10
|
| 42 |
},
|
| 43 |
{
|
| 44 |
+
"epoch": 3.01,
|
| 45 |
"eval_accuracy": 0.11428571428571428,
|
| 46 |
+
"eval_loss": 1.8259599208831787,
|
| 47 |
+
"eval_runtime": 49.6198,
|
| 48 |
+
"eval_samples_per_second": 0.705,
|
| 49 |
+
"eval_steps_per_second": 0.181,
|
| 50 |
"step": 12
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 4.01,
|
| 54 |
"eval_accuracy": 0.11428571428571428,
|
| 55 |
+
"eval_loss": 1.8636661767959595,
|
| 56 |
+
"eval_runtime": 47.6299,
|
| 57 |
+
"eval_samples_per_second": 0.735,
|
| 58 |
+
"eval_steps_per_second": 0.189,
|
| 59 |
"step": 15
|
| 60 |
},
|
| 61 |
{
|
| 62 |
+
"epoch": 5.01,
|
| 63 |
"eval_accuracy": 0.11428571428571428,
|
| 64 |
+
"eval_loss": 1.916202187538147,
|
| 65 |
+
"eval_runtime": 54.478,
|
| 66 |
+
"eval_samples_per_second": 0.642,
|
| 67 |
+
"eval_steps_per_second": 0.165,
|
| 68 |
"step": 18
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 6.01,
|
| 72 |
+
"learning_rate": 3.0303030303030306e-05,
|
| 73 |
+
"loss": 1.6934,
|
| 74 |
"step": 20
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 6.01,
|
| 78 |
"eval_accuracy": 0.11428571428571428,
|
| 79 |
+
"eval_loss": 1.979854702949524,
|
| 80 |
+
"eval_runtime": 47.3817,
|
| 81 |
+
"eval_samples_per_second": 0.739,
|
| 82 |
+
"eval_steps_per_second": 0.19,
|
| 83 |
"step": 21
|
| 84 |
},
|
| 85 |
{
|
| 86 |
+
"epoch": 7.01,
|
| 87 |
"eval_accuracy": 0.11428571428571428,
|
| 88 |
+
"eval_loss": 2.032222270965576,
|
| 89 |
+
"eval_runtime": 47.048,
|
| 90 |
+
"eval_samples_per_second": 0.744,
|
| 91 |
+
"eval_steps_per_second": 0.191,
|
| 92 |
"step": 24
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 8.01,
|
| 96 |
"eval_accuracy": 0.11428571428571428,
|
| 97 |
+
"eval_loss": 2.147186756134033,
|
| 98 |
+
"eval_runtime": 56.4896,
|
| 99 |
+
"eval_samples_per_second": 0.62,
|
| 100 |
+
"eval_steps_per_second": 0.159,
|
| 101 |
"step": 27
|
| 102 |
},
|
| 103 |
{
|
| 104 |
+
"epoch": 9.01,
|
| 105 |
+
"learning_rate": 4.545454545454546e-05,
|
| 106 |
+
"loss": 1.636,
|
| 107 |
"step": 30
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 9.01,
|
| 111 |
"eval_accuracy": 0.11428571428571428,
|
| 112 |
+
"eval_loss": 2.201059103012085,
|
| 113 |
+
"eval_runtime": 47.193,
|
| 114 |
+
"eval_samples_per_second": 0.742,
|
| 115 |
+
"eval_steps_per_second": 0.191,
|
| 116 |
"step": 30
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 10.01,
|
| 120 |
+
"eval_accuracy": 0.11428571428571428,
|
| 121 |
+
"eval_loss": 2.3041186332702637,
|
| 122 |
+
"eval_runtime": 49.6007,
|
| 123 |
+
"eval_samples_per_second": 0.706,
|
| 124 |
+
"eval_steps_per_second": 0.181,
|
| 125 |
"step": 33
|
| 126 |
},
|
| 127 |
{
|
| 128 |
+
"epoch": 11.01,
|
| 129 |
+
"eval_accuracy": 0.11428571428571428,
|
| 130 |
+
"eval_loss": 2.202650785446167,
|
| 131 |
+
"eval_runtime": 51.3674,
|
| 132 |
+
"eval_samples_per_second": 0.681,
|
| 133 |
+
"eval_steps_per_second": 0.175,
|
| 134 |
"step": 36
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"epoch": 12.01,
|
| 138 |
+
"eval_accuracy": 0.11428571428571428,
|
| 139 |
+
"eval_loss": 2.1011433601379395,
|
| 140 |
+
"eval_runtime": 47.3736,
|
| 141 |
+
"eval_samples_per_second": 0.739,
|
| 142 |
+
"eval_steps_per_second": 0.19,
|
| 143 |
"step": 39
|
| 144 |
},
|
| 145 |
{
|
| 146 |
+
"epoch": 13.0,
|
| 147 |
+
"learning_rate": 4.882154882154882e-05,
|
| 148 |
+
"loss": 1.6069,
|
| 149 |
"step": 40
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 13.01,
|
| 153 |
+
"eval_accuracy": 0.11428571428571428,
|
| 154 |
+
"eval_loss": 2.0470354557037354,
|
| 155 |
+
"eval_runtime": 52.7055,
|
| 156 |
+
"eval_samples_per_second": 0.664,
|
| 157 |
+
"eval_steps_per_second": 0.171,
|
| 158 |
+
"step": 42
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 14.01,
|
| 162 |
+
"eval_accuracy": 0.11428571428571428,
|
| 163 |
+
"eval_loss": 1.9688891172409058,
|
| 164 |
+
"eval_runtime": 46.2559,
|
| 165 |
+
"eval_samples_per_second": 0.757,
|
| 166 |
+
"eval_steps_per_second": 0.195,
|
| 167 |
+
"step": 45
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 15.01,
|
| 171 |
+
"eval_accuracy": 0.11428571428571428,
|
| 172 |
+
"eval_loss": 1.911560297012329,
|
| 173 |
+
"eval_runtime": 55.4227,
|
| 174 |
+
"eval_samples_per_second": 0.632,
|
| 175 |
+
"eval_steps_per_second": 0.162,
|
| 176 |
+
"step": 48
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 16.01,
|
| 180 |
+
"learning_rate": 4.713804713804714e-05,
|
| 181 |
+
"loss": 1.6509,
|
| 182 |
+
"step": 50
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 16.01,
|
| 186 |
+
"eval_accuracy": 0.11428571428571428,
|
| 187 |
+
"eval_loss": 1.9125531911849976,
|
| 188 |
+
"eval_runtime": 55.4531,
|
| 189 |
"eval_samples_per_second": 0.631,
|
| 190 |
"eval_steps_per_second": 0.162,
|
| 191 |
+
"step": 51
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 17.01,
|
| 195 |
+
"eval_accuracy": 0.11428571428571428,
|
| 196 |
+
"eval_loss": 2.038973808288574,
|
| 197 |
+
"eval_runtime": 47.6175,
|
| 198 |
+
"eval_samples_per_second": 0.735,
|
| 199 |
+
"eval_steps_per_second": 0.189,
|
| 200 |
+
"step": 54
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 18.01,
|
| 204 |
+
"eval_accuracy": 0.11428571428571428,
|
| 205 |
+
"eval_loss": 1.904532551765442,
|
| 206 |
+
"eval_runtime": 47.9854,
|
| 207 |
+
"eval_samples_per_second": 0.729,
|
| 208 |
+
"eval_steps_per_second": 0.188,
|
| 209 |
+
"step": 57
|
| 210 |
},
|
| 211 |
{
|
| 212 |
+
"epoch": 19.01,
|
| 213 |
+
"learning_rate": 4.545454545454546e-05,
|
| 214 |
+
"loss": 1.5023,
|
| 215 |
+
"step": 60
|
|
|
|
|
|
|
|
|
|
| 216 |
},
|
| 217 |
{
|
| 218 |
+
"epoch": 19.01,
|
| 219 |
+
"eval_accuracy": 0.11428571428571428,
|
| 220 |
+
"eval_loss": 1.796205759048462,
|
| 221 |
+
"eval_runtime": 51.1635,
|
| 222 |
+
"eval_samples_per_second": 0.684,
|
| 223 |
+
"eval_steps_per_second": 0.176,
|
| 224 |
+
"step": 60
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 20.01,
|
| 228 |
+
"eval_accuracy": 0.34285714285714286,
|
| 229 |
+
"eval_loss": 1.618465542793274,
|
| 230 |
+
"eval_runtime": 54.8541,
|
| 231 |
+
"eval_samples_per_second": 0.638,
|
| 232 |
+
"eval_steps_per_second": 0.164,
|
| 233 |
+
"step": 63
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 21.01,
|
| 237 |
+
"eval_accuracy": 0.34285714285714286,
|
| 238 |
+
"eval_loss": 1.4067193269729614,
|
| 239 |
+
"eval_runtime": 56.983,
|
| 240 |
+
"eval_samples_per_second": 0.614,
|
| 241 |
+
"eval_steps_per_second": 0.158,
|
| 242 |
+
"step": 66
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 22.01,
|
| 246 |
+
"eval_accuracy": 0.5142857142857142,
|
| 247 |
+
"eval_loss": 1.342714548110962,
|
| 248 |
+
"eval_runtime": 49.6455,
|
| 249 |
+
"eval_samples_per_second": 0.705,
|
| 250 |
"eval_steps_per_second": 0.181,
|
| 251 |
+
"step": 69
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 23.0,
|
| 255 |
+
"learning_rate": 4.3771043771043774e-05,
|
| 256 |
+
"loss": 1.2231,
|
| 257 |
+
"step": 70
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 23.01,
|
| 261 |
+
"eval_accuracy": 0.37142857142857144,
|
| 262 |
+
"eval_loss": 1.199639081954956,
|
| 263 |
+
"eval_runtime": 46.5204,
|
| 264 |
+
"eval_samples_per_second": 0.752,
|
| 265 |
+
"eval_steps_per_second": 0.193,
|
| 266 |
+
"step": 72
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 24.01,
|
| 270 |
+
"eval_accuracy": 0.5428571428571428,
|
| 271 |
+
"eval_loss": 1.067163348197937,
|
| 272 |
+
"eval_runtime": 47.5503,
|
| 273 |
+
"eval_samples_per_second": 0.736,
|
| 274 |
+
"eval_steps_per_second": 0.189,
|
| 275 |
+
"step": 75
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 25.01,
|
| 279 |
+
"eval_accuracy": 0.5142857142857142,
|
| 280 |
+
"eval_loss": 1.1605939865112305,
|
| 281 |
+
"eval_runtime": 46.8125,
|
| 282 |
+
"eval_samples_per_second": 0.748,
|
| 283 |
+
"eval_steps_per_second": 0.192,
|
| 284 |
+
"step": 78
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 26.01,
|
| 288 |
+
"learning_rate": 4.208754208754209e-05,
|
| 289 |
+
"loss": 1.086,
|
| 290 |
+
"step": 80
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 26.01,
|
| 294 |
+
"eval_accuracy": 0.5142857142857142,
|
| 295 |
+
"eval_loss": 1.0507373809814453,
|
| 296 |
+
"eval_runtime": 47.2904,
|
| 297 |
+
"eval_samples_per_second": 0.74,
|
| 298 |
+
"eval_steps_per_second": 0.19,
|
| 299 |
+
"step": 81
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 27.01,
|
| 303 |
+
"eval_accuracy": 0.6571428571428571,
|
| 304 |
+
"eval_loss": 0.8726997971534729,
|
| 305 |
+
"eval_runtime": 47.448,
|
| 306 |
+
"eval_samples_per_second": 0.738,
|
| 307 |
+
"eval_steps_per_second": 0.19,
|
| 308 |
+
"step": 84
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 28.01,
|
| 312 |
+
"eval_accuracy": 0.5714285714285714,
|
| 313 |
+
"eval_loss": 1.1010727882385254,
|
| 314 |
+
"eval_runtime": 46.68,
|
| 315 |
+
"eval_samples_per_second": 0.75,
|
| 316 |
+
"eval_steps_per_second": 0.193,
|
| 317 |
+
"step": 87
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 29.01,
|
| 321 |
+
"learning_rate": 4.0404040404040405e-05,
|
| 322 |
+
"loss": 1.1221,
|
| 323 |
+
"step": 90
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 29.01,
|
| 327 |
+
"eval_accuracy": 0.6285714285714286,
|
| 328 |
+
"eval_loss": 1.070949673652649,
|
| 329 |
+
"eval_runtime": 47.7392,
|
| 330 |
+
"eval_samples_per_second": 0.733,
|
| 331 |
+
"eval_steps_per_second": 0.189,
|
| 332 |
+
"step": 90
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 30.01,
|
| 336 |
+
"eval_accuracy": 0.34285714285714286,
|
| 337 |
+
"eval_loss": 1.2051596641540527,
|
| 338 |
+
"eval_runtime": 52.6759,
|
| 339 |
+
"eval_samples_per_second": 0.664,
|
| 340 |
+
"eval_steps_per_second": 0.171,
|
| 341 |
+
"step": 93
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 31.01,
|
| 345 |
+
"eval_accuracy": 0.3142857142857143,
|
| 346 |
+
"eval_loss": 1.1637940406799316,
|
| 347 |
+
"eval_runtime": 47.6299,
|
| 348 |
+
"eval_samples_per_second": 0.735,
|
| 349 |
+
"eval_steps_per_second": 0.189,
|
| 350 |
+
"step": 96
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 32.01,
|
| 354 |
+
"eval_accuracy": 0.5714285714285714,
|
| 355 |
+
"eval_loss": 1.0540904998779297,
|
| 356 |
+
"eval_runtime": 47.2579,
|
| 357 |
+
"eval_samples_per_second": 0.741,
|
| 358 |
+
"eval_steps_per_second": 0.19,
|
| 359 |
+
"step": 99
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 33.0,
|
| 363 |
+
"learning_rate": 3.872053872053872e-05,
|
| 364 |
+
"loss": 1.0483,
|
| 365 |
+
"step": 100
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 33.01,
|
| 369 |
+
"eval_accuracy": 0.5428571428571428,
|
| 370 |
+
"eval_loss": 0.9793229103088379,
|
| 371 |
+
"eval_runtime": 48.2595,
|
| 372 |
+
"eval_samples_per_second": 0.725,
|
| 373 |
+
"eval_steps_per_second": 0.186,
|
| 374 |
+
"step": 102
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 34.01,
|
| 378 |
+
"eval_accuracy": 0.7142857142857143,
|
| 379 |
+
"eval_loss": 0.9788510203361511,
|
| 380 |
+
"eval_runtime": 46.729,
|
| 381 |
+
"eval_samples_per_second": 0.749,
|
| 382 |
+
"eval_steps_per_second": 0.193,
|
| 383 |
+
"step": 105
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 35.01,
|
| 387 |
+
"eval_accuracy": 0.6285714285714286,
|
| 388 |
+
"eval_loss": 1.0231552124023438,
|
| 389 |
+
"eval_runtime": 47.7551,
|
| 390 |
+
"eval_samples_per_second": 0.733,
|
| 391 |
+
"eval_steps_per_second": 0.188,
|
| 392 |
+
"step": 108
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 36.01,
|
| 396 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 397 |
+
"loss": 0.8313,
|
| 398 |
+
"step": 110
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 36.01,
|
| 402 |
+
"eval_accuracy": 0.6857142857142857,
|
| 403 |
+
"eval_loss": 1.0134854316711426,
|
| 404 |
+
"eval_runtime": 50.8022,
|
| 405 |
+
"eval_samples_per_second": 0.689,
|
| 406 |
+
"eval_steps_per_second": 0.177,
|
| 407 |
+
"step": 111
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 37.01,
|
| 411 |
+
"eval_accuracy": 0.7142857142857143,
|
| 412 |
+
"eval_loss": 0.9512158036231995,
|
| 413 |
+
"eval_runtime": 47.6931,
|
| 414 |
+
"eval_samples_per_second": 0.734,
|
| 415 |
+
"eval_steps_per_second": 0.189,
|
| 416 |
+
"step": 114
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 38.01,
|
| 420 |
+
"eval_accuracy": 0.7428571428571429,
|
| 421 |
+
"eval_loss": 0.6964335441589355,
|
| 422 |
+
"eval_runtime": 48.6009,
|
| 423 |
+
"eval_samples_per_second": 0.72,
|
| 424 |
+
"eval_steps_per_second": 0.185,
|
| 425 |
+
"step": 117
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 39.01,
|
| 429 |
+
"learning_rate": 3.535353535353535e-05,
|
| 430 |
+
"loss": 0.9314,
|
| 431 |
+
"step": 120
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 39.01,
|
| 435 |
+
"eval_accuracy": 0.6,
|
| 436 |
+
"eval_loss": 0.7565953135490417,
|
| 437 |
+
"eval_runtime": 48.8407,
|
| 438 |
+
"eval_samples_per_second": 0.717,
|
| 439 |
+
"eval_steps_per_second": 0.184,
|
| 440 |
+
"step": 120
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 40.01,
|
| 444 |
+
"eval_accuracy": 0.8,
|
| 445 |
+
"eval_loss": 0.6933528184890747,
|
| 446 |
+
"eval_runtime": 46.6051,
|
| 447 |
+
"eval_samples_per_second": 0.751,
|
| 448 |
+
"eval_steps_per_second": 0.193,
|
| 449 |
+
"step": 123
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 41.01,
|
| 453 |
+
"eval_accuracy": 0.7714285714285715,
|
| 454 |
+
"eval_loss": 0.7758246064186096,
|
| 455 |
+
"eval_runtime": 46.5497,
|
| 456 |
+
"eval_samples_per_second": 0.752,
|
| 457 |
+
"eval_steps_per_second": 0.193,
|
| 458 |
+
"step": 126
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 42.01,
|
| 462 |
+
"eval_accuracy": 0.5714285714285714,
|
| 463 |
+
"eval_loss": 0.8644936084747314,
|
| 464 |
+
"eval_runtime": 47.6569,
|
| 465 |
+
"eval_samples_per_second": 0.734,
|
| 466 |
+
"eval_steps_per_second": 0.189,
|
| 467 |
+
"step": 129
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 43.0,
|
| 471 |
+
"learning_rate": 3.3670033670033675e-05,
|
| 472 |
+
"loss": 0.9863,
|
| 473 |
+
"step": 130
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 43.01,
|
| 477 |
+
"eval_accuracy": 0.7714285714285715,
|
| 478 |
+
"eval_loss": 0.8204832673072815,
|
| 479 |
+
"eval_runtime": 53.1222,
|
| 480 |
+
"eval_samples_per_second": 0.659,
|
| 481 |
+
"eval_steps_per_second": 0.169,
|
| 482 |
+
"step": 132
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 44.01,
|
| 486 |
+
"eval_accuracy": 0.7714285714285715,
|
| 487 |
+
"eval_loss": 0.7429643273353577,
|
| 488 |
+
"eval_runtime": 47.3081,
|
| 489 |
+
"eval_samples_per_second": 0.74,
|
| 490 |
+
"eval_steps_per_second": 0.19,
|
| 491 |
+
"step": 135
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 45.01,
|
| 495 |
+
"eval_accuracy": 0.6857142857142857,
|
| 496 |
+
"eval_loss": 0.7228943705558777,
|
| 497 |
+
"eval_runtime": 45.8699,
|
| 498 |
+
"eval_samples_per_second": 0.763,
|
| 499 |
+
"eval_steps_per_second": 0.196,
|
| 500 |
+
"step": 138
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 46.01,
|
| 504 |
+
"learning_rate": 3.198653198653199e-05,
|
| 505 |
+
"loss": 0.6828,
|
| 506 |
+
"step": 140
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 46.01,
|
| 510 |
+
"eval_accuracy": 0.6571428571428571,
|
| 511 |
+
"eval_loss": 0.684984028339386,
|
| 512 |
+
"eval_runtime": 52.7837,
|
| 513 |
+
"eval_samples_per_second": 0.663,
|
| 514 |
+
"eval_steps_per_second": 0.171,
|
| 515 |
+
"step": 141
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 47.01,
|
| 519 |
+
"eval_accuracy": 0.7714285714285715,
|
| 520 |
+
"eval_loss": 0.6505874395370483,
|
| 521 |
+
"eval_runtime": 47.1631,
|
| 522 |
+
"eval_samples_per_second": 0.742,
|
| 523 |
+
"eval_steps_per_second": 0.191,
|
| 524 |
+
"step": 144
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 48.01,
|
| 528 |
+
"eval_accuracy": 0.7894736842105263,
|
| 529 |
+
"eval_loss": 0.6245588660240173,
|
| 530 |
+
"eval_runtime": 50.9021,
|
| 531 |
+
"eval_samples_per_second": 0.747,
|
| 532 |
+
"eval_steps_per_second": 0.196,
|
| 533 |
+
"step": 146
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 48.01,
|
| 537 |
+
"eval_accuracy": 0.75,
|
| 538 |
+
"eval_loss": 0.7047864198684692,
|
| 539 |
+
"eval_runtime": 43.3232,
|
| 540 |
+
"eval_samples_per_second": 0.739,
|
| 541 |
+
"eval_steps_per_second": 0.185,
|
| 542 |
+
"step": 146
|
| 543 |
}
|
| 544 |
],
|
| 545 |
+
"max_steps": 330,
|
| 546 |
"num_train_epochs": 9223372036854775807,
|
| 547 |
+
"total_flos": 6.579455730080809e+17,
|
| 548 |
"trial_name": null,
|
| 549 |
"trial_params": null
|
| 550 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3963
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc0c9f2d3be88a3b16f882a91d47c15fad36dcba3504236baf70d3bf9a0d5f6e
|
| 3 |
size 3963
|