End of training
Browse files- README.md +2 -2
- all_results.json +8 -0
- runs/May03_12-32-43_Hardik/events.out.tfevents.1746322343.Hardik.29964.3 +2 -2
- test_results.json +8 -0
- trainer_state.json +500 -0
README.md
CHANGED
|
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- Accuracy: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.7002
|
| 22 |
+
- Accuracy: 0.7887
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.157608695652174,
|
| 3 |
+
"eval_accuracy": 0.78867879652753,
|
| 4 |
+
"eval_loss": 0.7002037763595581,
|
| 5 |
+
"eval_runtime": 1290.721,
|
| 6 |
+
"eval_samples_per_second": 6.515,
|
| 7 |
+
"eval_steps_per_second": 1.629
|
| 8 |
+
}
|
runs/May03_12-32-43_Hardik/events.out.tfevents.1746322343.Hardik.29964.3
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 sha256:41157cd838f120d9a9455c2225f74c3eb8e189399c6a547e5dc086f9f10e7b3c
|
| 3 |
+
size 686
|
test_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.157608695652174,
|
| 3 |
+
"eval_accuracy": 0.78867879652753,
|
| 4 |
+
"eval_loss": 0.7002037763595581,
|
| 5 |
+
"eval_runtime": 1290.721,
|
| 6 |
+
"eval_samples_per_second": 6.515,
|
| 7 |
+
"eval_steps_per_second": 1.629
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,500 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 552,
|
| 3 |
+
"best_metric": 0.758873745694174,
|
| 4 |
+
"best_model_checkpoint": "abcd\\checkpoint-552",
|
| 5 |
+
"epoch": 5.157608695652174,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 552,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.018115942028985508,
|
| 14 |
+
"grad_norm": 13.317688941955566,
|
| 15 |
+
"learning_rate": 8.035714285714286e-06,
|
| 16 |
+
"loss": 0.8905,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.036231884057971016,
|
| 21 |
+
"grad_norm": 12.00970458984375,
|
| 22 |
+
"learning_rate": 1.6964285714285715e-05,
|
| 23 |
+
"loss": 0.7819,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.05434782608695652,
|
| 28 |
+
"grad_norm": 14.536447525024414,
|
| 29 |
+
"learning_rate": 2.5892857142857148e-05,
|
| 30 |
+
"loss": 0.9766,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.07246376811594203,
|
| 35 |
+
"grad_norm": 15.37159252166748,
|
| 36 |
+
"learning_rate": 3.4821428571428574e-05,
|
| 37 |
+
"loss": 0.8572,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09057971014492754,
|
| 42 |
+
"grad_norm": 20.875459671020508,
|
| 43 |
+
"learning_rate": 4.375e-05,
|
| 44 |
+
"loss": 1.0996,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.10869565217391304,
|
| 49 |
+
"grad_norm": 13.146461486816406,
|
| 50 |
+
"learning_rate": 4.969758064516129e-05,
|
| 51 |
+
"loss": 0.9429,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.12681159420289856,
|
| 56 |
+
"grad_norm": 20.685447692871094,
|
| 57 |
+
"learning_rate": 4.868951612903226e-05,
|
| 58 |
+
"loss": 1.1377,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14492753623188406,
|
| 63 |
+
"grad_norm": 16.825111389160156,
|
| 64 |
+
"learning_rate": 4.768145161290323e-05,
|
| 65 |
+
"loss": 1.0243,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.16304347826086957,
|
| 70 |
+
"grad_norm": 19.70474624633789,
|
| 71 |
+
"learning_rate": 4.6673387096774196e-05,
|
| 72 |
+
"loss": 1.1325,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.16847826086956522,
|
| 77 |
+
"eval_accuracy": 0.556836902800659,
|
| 78 |
+
"eval_loss": 1.0675878524780273,
|
| 79 |
+
"eval_runtime": 1853.5174,
|
| 80 |
+
"eval_samples_per_second": 7.205,
|
| 81 |
+
"eval_steps_per_second": 1.801,
|
| 82 |
+
"step": 93
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.0126811594202898,
|
| 86 |
+
"grad_norm": 11.140310287475586,
|
| 87 |
+
"learning_rate": 4.566532258064516e-05,
|
| 88 |
+
"loss": 0.8952,
|
| 89 |
+
"step": 100
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.0307971014492754,
|
| 93 |
+
"grad_norm": 6.155562877655029,
|
| 94 |
+
"learning_rate": 4.465725806451613e-05,
|
| 95 |
+
"loss": 0.8204,
|
| 96 |
+
"step": 110
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.048913043478261,
|
| 100 |
+
"grad_norm": 9.62833023071289,
|
| 101 |
+
"learning_rate": 4.36491935483871e-05,
|
| 102 |
+
"loss": 0.8178,
|
| 103 |
+
"step": 120
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.0670289855072463,
|
| 107 |
+
"grad_norm": 14.596573829650879,
|
| 108 |
+
"learning_rate": 4.2641129032258064e-05,
|
| 109 |
+
"loss": 0.9171,
|
| 110 |
+
"step": 130
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.085144927536232,
|
| 114 |
+
"grad_norm": 14.76526927947998,
|
| 115 |
+
"learning_rate": 4.163306451612903e-05,
|
| 116 |
+
"loss": 0.781,
|
| 117 |
+
"step": 140
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.1032608695652173,
|
| 121 |
+
"grad_norm": 21.03084945678711,
|
| 122 |
+
"learning_rate": 4.0625000000000005e-05,
|
| 123 |
+
"loss": 0.7955,
|
| 124 |
+
"step": 150
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.1213768115942029,
|
| 128 |
+
"grad_norm": 18.31418800354004,
|
| 129 |
+
"learning_rate": 3.961693548387097e-05,
|
| 130 |
+
"loss": 1.1034,
|
| 131 |
+
"step": 160
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.1394927536231885,
|
| 135 |
+
"grad_norm": 17.097795486450195,
|
| 136 |
+
"learning_rate": 3.860887096774194e-05,
|
| 137 |
+
"loss": 0.8052,
|
| 138 |
+
"step": 170
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.1576086956521738,
|
| 142 |
+
"grad_norm": 15.764641761779785,
|
| 143 |
+
"learning_rate": 3.7600806451612906e-05,
|
| 144 |
+
"loss": 0.738,
|
| 145 |
+
"step": 180
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.1684782608695652,
|
| 149 |
+
"eval_accuracy": 0.549947581249064,
|
| 150 |
+
"eval_loss": 1.2091021537780762,
|
| 151 |
+
"eval_runtime": 1866.8421,
|
| 152 |
+
"eval_samples_per_second": 7.153,
|
| 153 |
+
"eval_steps_per_second": 1.789,
|
| 154 |
+
"step": 186
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.0072463768115942,
|
| 158 |
+
"grad_norm": 6.231867790222168,
|
| 159 |
+
"learning_rate": 3.659274193548387e-05,
|
| 160 |
+
"loss": 0.4987,
|
| 161 |
+
"step": 190
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.0253623188405796,
|
| 165 |
+
"grad_norm": 7.453345775604248,
|
| 166 |
+
"learning_rate": 3.558467741935484e-05,
|
| 167 |
+
"loss": 0.3465,
|
| 168 |
+
"step": 200
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.0434782608695654,
|
| 172 |
+
"grad_norm": 21.0439453125,
|
| 173 |
+
"learning_rate": 3.457661290322581e-05,
|
| 174 |
+
"loss": 0.3425,
|
| 175 |
+
"step": 210
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 2.0615942028985508,
|
| 179 |
+
"grad_norm": 18.279014587402344,
|
| 180 |
+
"learning_rate": 3.3568548387096774e-05,
|
| 181 |
+
"loss": 0.6557,
|
| 182 |
+
"step": 220
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.079710144927536,
|
| 186 |
+
"grad_norm": 27.888294219970703,
|
| 187 |
+
"learning_rate": 3.256048387096775e-05,
|
| 188 |
+
"loss": 0.8808,
|
| 189 |
+
"step": 230
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.097826086956522,
|
| 193 |
+
"grad_norm": 16.571508407592773,
|
| 194 |
+
"learning_rate": 3.1552419354838715e-05,
|
| 195 |
+
"loss": 0.49,
|
| 196 |
+
"step": 240
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 2.1159420289855073,
|
| 200 |
+
"grad_norm": 23.84330177307129,
|
| 201 |
+
"learning_rate": 3.0544354838709676e-05,
|
| 202 |
+
"loss": 0.6079,
|
| 203 |
+
"step": 250
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 2.1340579710144927,
|
| 207 |
+
"grad_norm": 13.54464340209961,
|
| 208 |
+
"learning_rate": 2.9536290322580646e-05,
|
| 209 |
+
"loss": 0.4746,
|
| 210 |
+
"step": 260
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.1521739130434785,
|
| 214 |
+
"grad_norm": 22.121822357177734,
|
| 215 |
+
"learning_rate": 2.8528225806451613e-05,
|
| 216 |
+
"loss": 0.6397,
|
| 217 |
+
"step": 270
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 2.1684782608695654,
|
| 221 |
+
"eval_accuracy": 0.611577055563876,
|
| 222 |
+
"eval_loss": 1.2484452724456787,
|
| 223 |
+
"eval_runtime": 1864.5566,
|
| 224 |
+
"eval_samples_per_second": 7.162,
|
| 225 |
+
"eval_steps_per_second": 1.791,
|
| 226 |
+
"step": 279
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 3.0018115942028984,
|
| 230 |
+
"grad_norm": 16.256120681762695,
|
| 231 |
+
"learning_rate": 2.7520161290322584e-05,
|
| 232 |
+
"loss": 0.473,
|
| 233 |
+
"step": 280
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.0199275362318843,
|
| 237 |
+
"grad_norm": 7.968146324157715,
|
| 238 |
+
"learning_rate": 2.651209677419355e-05,
|
| 239 |
+
"loss": 0.3852,
|
| 240 |
+
"step": 290
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.0380434782608696,
|
| 244 |
+
"grad_norm": 21.890714645385742,
|
| 245 |
+
"learning_rate": 2.550403225806452e-05,
|
| 246 |
+
"loss": 0.4942,
|
| 247 |
+
"step": 300
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 3.056159420289855,
|
| 251 |
+
"grad_norm": 14.216273307800293,
|
| 252 |
+
"learning_rate": 2.4495967741935485e-05,
|
| 253 |
+
"loss": 0.3557,
|
| 254 |
+
"step": 310
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.074275362318841,
|
| 258 |
+
"grad_norm": 2.547912836074829,
|
| 259 |
+
"learning_rate": 2.3487903225806455e-05,
|
| 260 |
+
"loss": 0.3706,
|
| 261 |
+
"step": 320
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.092391304347826,
|
| 265 |
+
"grad_norm": 16.752574920654297,
|
| 266 |
+
"learning_rate": 2.247983870967742e-05,
|
| 267 |
+
"loss": 0.444,
|
| 268 |
+
"step": 330
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.1105072463768115,
|
| 272 |
+
"grad_norm": 15.96899127960205,
|
| 273 |
+
"learning_rate": 2.147177419354839e-05,
|
| 274 |
+
"loss": 0.4921,
|
| 275 |
+
"step": 340
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.128623188405797,
|
| 279 |
+
"grad_norm": 11.133148193359375,
|
| 280 |
+
"learning_rate": 2.0463709677419356e-05,
|
| 281 |
+
"loss": 0.3874,
|
| 282 |
+
"step": 350
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.1467391304347827,
|
| 286 |
+
"grad_norm": 6.035247802734375,
|
| 287 |
+
"learning_rate": 1.9455645161290323e-05,
|
| 288 |
+
"loss": 0.5042,
|
| 289 |
+
"step": 360
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.164855072463768,
|
| 293 |
+
"grad_norm": 4.174564361572266,
|
| 294 |
+
"learning_rate": 1.844758064516129e-05,
|
| 295 |
+
"loss": 0.4395,
|
| 296 |
+
"step": 370
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.1684782608695654,
|
| 300 |
+
"eval_accuracy": 0.642728770405871,
|
| 301 |
+
"eval_loss": 1.0139626264572144,
|
| 302 |
+
"eval_runtime": 1859.3799,
|
| 303 |
+
"eval_samples_per_second": 7.182,
|
| 304 |
+
"eval_steps_per_second": 1.796,
|
| 305 |
+
"step": 372
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 4.0144927536231885,
|
| 309 |
+
"grad_norm": 3.096120595932007,
|
| 310 |
+
"learning_rate": 1.743951612903226e-05,
|
| 311 |
+
"loss": 0.2476,
|
| 312 |
+
"step": 380
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 4.032608695652174,
|
| 316 |
+
"grad_norm": 17.17482566833496,
|
| 317 |
+
"learning_rate": 1.6431451612903225e-05,
|
| 318 |
+
"loss": 0.324,
|
| 319 |
+
"step": 390
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 4.050724637681159,
|
| 323 |
+
"grad_norm": 4.938539505004883,
|
| 324 |
+
"learning_rate": 1.5423387096774195e-05,
|
| 325 |
+
"loss": 0.2958,
|
| 326 |
+
"step": 400
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.068840579710145,
|
| 330 |
+
"grad_norm": 4.778896808624268,
|
| 331 |
+
"learning_rate": 1.4415322580645164e-05,
|
| 332 |
+
"loss": 0.284,
|
| 333 |
+
"step": 410
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 4.086956521739131,
|
| 337 |
+
"grad_norm": 20.58946418762207,
|
| 338 |
+
"learning_rate": 1.340725806451613e-05,
|
| 339 |
+
"loss": 0.4622,
|
| 340 |
+
"step": 420
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 4.105072463768116,
|
| 344 |
+
"grad_norm": 0.7577747702598572,
|
| 345 |
+
"learning_rate": 1.2399193548387098e-05,
|
| 346 |
+
"loss": 0.2173,
|
| 347 |
+
"step": 430
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 4.1231884057971016,
|
| 351 |
+
"grad_norm": 0.33162328600883484,
|
| 352 |
+
"learning_rate": 1.1391129032258065e-05,
|
| 353 |
+
"loss": 0.2307,
|
| 354 |
+
"step": 440
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 4.141304347826087,
|
| 358 |
+
"grad_norm": 4.827192783355713,
|
| 359 |
+
"learning_rate": 1.0383064516129034e-05,
|
| 360 |
+
"loss": 0.3314,
|
| 361 |
+
"step": 450
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 4.159420289855072,
|
| 365 |
+
"grad_norm": 2.6278650760650635,
|
| 366 |
+
"learning_rate": 9.375000000000001e-06,
|
| 367 |
+
"loss": 0.3098,
|
| 368 |
+
"step": 460
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.168478260869565,
|
| 372 |
+
"eval_accuracy": 0.6830163246967201,
|
| 373 |
+
"eval_loss": 0.9756622910499573,
|
| 374 |
+
"eval_runtime": 1864.2768,
|
| 375 |
+
"eval_samples_per_second": 7.163,
|
| 376 |
+
"eval_steps_per_second": 1.791,
|
| 377 |
+
"step": 465
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 5.009057971014493,
|
| 381 |
+
"grad_norm": 12.96372127532959,
|
| 382 |
+
"learning_rate": 8.366935483870968e-06,
|
| 383 |
+
"loss": 0.4201,
|
| 384 |
+
"step": 470
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 5.0271739130434785,
|
| 388 |
+
"grad_norm": 17.302637100219727,
|
| 389 |
+
"learning_rate": 7.358870967741936e-06,
|
| 390 |
+
"loss": 0.3379,
|
| 391 |
+
"step": 480
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 5.045289855072464,
|
| 395 |
+
"grad_norm": 4.884481906890869,
|
| 396 |
+
"learning_rate": 6.350806451612904e-06,
|
| 397 |
+
"loss": 0.3286,
|
| 398 |
+
"step": 490
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 5.063405797101449,
|
| 402 |
+
"grad_norm": 18.058940887451172,
|
| 403 |
+
"learning_rate": 5.342741935483872e-06,
|
| 404 |
+
"loss": 0.258,
|
| 405 |
+
"step": 500
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 5.081521739130435,
|
| 409 |
+
"grad_norm": 1.203333854675293,
|
| 410 |
+
"learning_rate": 4.33467741935484e-06,
|
| 411 |
+
"loss": 0.1982,
|
| 412 |
+
"step": 510
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 5.09963768115942,
|
| 416 |
+
"grad_norm": 21.148109436035156,
|
| 417 |
+
"learning_rate": 3.3266129032258062e-06,
|
| 418 |
+
"loss": 0.2102,
|
| 419 |
+
"step": 520
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 5.117753623188406,
|
| 423 |
+
"grad_norm": 1.2070428133010864,
|
| 424 |
+
"learning_rate": 2.318548387096774e-06,
|
| 425 |
+
"loss": 0.2017,
|
| 426 |
+
"step": 530
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 5.135869565217392,
|
| 430 |
+
"grad_norm": 1.2308259010314941,
|
| 431 |
+
"learning_rate": 1.310483870967742e-06,
|
| 432 |
+
"loss": 0.1859,
|
| 433 |
+
"step": 540
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 5.153985507246377,
|
| 437 |
+
"grad_norm": 22.218280792236328,
|
| 438 |
+
"learning_rate": 3.024193548387097e-07,
|
| 439 |
+
"loss": 0.1016,
|
| 440 |
+
"step": 550
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 5.157608695652174,
|
| 444 |
+
"eval_accuracy": 0.758873745694174,
|
| 445 |
+
"eval_loss": 0.7178874611854553,
|
| 446 |
+
"eval_runtime": 1859.6371,
|
| 447 |
+
"eval_samples_per_second": 7.181,
|
| 448 |
+
"eval_steps_per_second": 1.796,
|
| 449 |
+
"step": 552
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 5.157608695652174,
|
| 453 |
+
"step": 552,
|
| 454 |
+
"total_flos": 1.9302137237930803e+18,
|
| 455 |
+
"train_loss": 0.5571505176848259,
|
| 456 |
+
"train_runtime": 11844.7659,
|
| 457 |
+
"train_samples_per_second": 0.186,
|
| 458 |
+
"train_steps_per_second": 0.047
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 5.157608695652174,
|
| 462 |
+
"eval_accuracy": 0.7891051507239497,
|
| 463 |
+
"eval_loss": 0.6989445090293884,
|
| 464 |
+
"eval_runtime": 1206.5933,
|
| 465 |
+
"eval_samples_per_second": 6.983,
|
| 466 |
+
"eval_steps_per_second": 1.746,
|
| 467 |
+
"step": 552
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5.157608695652174,
|
| 471 |
+
"eval_accuracy": 0.78867879652753,
|
| 472 |
+
"eval_loss": 0.7002037763595581,
|
| 473 |
+
"eval_runtime": 1290.721,
|
| 474 |
+
"eval_samples_per_second": 6.515,
|
| 475 |
+
"eval_steps_per_second": 1.629,
|
| 476 |
+
"step": 552
|
| 477 |
+
}
|
| 478 |
+
],
|
| 479 |
+
"logging_steps": 10,
|
| 480 |
+
"max_steps": 552,
|
| 481 |
+
"num_input_tokens_seen": 0,
|
| 482 |
+
"num_train_epochs": 9223372036854775807,
|
| 483 |
+
"save_steps": 500,
|
| 484 |
+
"stateful_callbacks": {
|
| 485 |
+
"TrainerControl": {
|
| 486 |
+
"args": {
|
| 487 |
+
"should_epoch_stop": false,
|
| 488 |
+
"should_evaluate": false,
|
| 489 |
+
"should_log": false,
|
| 490 |
+
"should_save": true,
|
| 491 |
+
"should_training_stop": true
|
| 492 |
+
},
|
| 493 |
+
"attributes": {}
|
| 494 |
+
}
|
| 495 |
+
},
|
| 496 |
+
"total_flos": 1.9302137237930803e+18,
|
| 497 |
+
"train_batch_size": 4,
|
| 498 |
+
"trial_name": null,
|
| 499 |
+
"trial_params": null
|
| 500 |
+
}
|