End of training
Browse files- README.md +2 -2
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Apr24_21-59-22_47b2fe407df5/events.out.tfevents.1713997700.47b2fe407df5.3334.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +575 -0
README.md
CHANGED
|
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss:
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.5797
|
| 21 |
+
- Accuracy: 0.8333
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 37.935483870967744,
|
| 3 |
+
"eval_accuracy": 0.8333333333333334,
|
| 4 |
+
"eval_loss": 0.5796787142753601,
|
| 5 |
+
"eval_runtime": 1.6435,
|
| 6 |
+
"eval_samples_per_second": 36.507,
|
| 7 |
+
"eval_steps_per_second": 1.217,
|
| 8 |
+
"total_flos": 2.8633958865108173e+18,
|
| 9 |
+
"train_loss": 0.24709520539661653,
|
| 10 |
+
"train_runtime": 1707.2205,
|
| 11 |
+
"train_samples_per_second": 23.962,
|
| 12 |
+
"train_steps_per_second": 0.172
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 37.935483870967744,
|
| 3 |
+
"eval_accuracy": 0.8333333333333334,
|
| 4 |
+
"eval_loss": 0.5796787142753601,
|
| 5 |
+
"eval_runtime": 1.6435,
|
| 6 |
+
"eval_samples_per_second": 36.507,
|
| 7 |
+
"eval_steps_per_second": 1.217
|
| 8 |
+
}
|
runs/Apr24_21-59-22_47b2fe407df5/events.out.tfevents.1713997700.47b2fe407df5.3334.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9667b26392f25d89f63843c42b5b824e717f4d4a661b65d69f563c96662e623a
|
| 3 |
+
size 411
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 37.935483870967744,
|
| 3 |
+
"total_flos": 2.8633958865108173e+18,
|
| 4 |
+
"train_loss": 0.24709520539661653,
|
| 5 |
+
"train_runtime": 1707.2205,
|
| 6 |
+
"train_samples_per_second": 23.962,
|
| 7 |
+
"train_steps_per_second": 0.172
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,575 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8333333333333334,
|
| 3 |
+
"best_model_checkpoint": "beit-base-patch16-224-dmae-va-U5-42E/checkpoint-38",
|
| 4 |
+
"epoch": 37.935483870967744,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 294,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.9032258064516129,
|
| 13 |
+
"eval_accuracy": 0.55,
|
| 14 |
+
"eval_loss": 1.2065638303756714,
|
| 15 |
+
"eval_runtime": 1.625,
|
| 16 |
+
"eval_samples_per_second": 36.924,
|
| 17 |
+
"eval_steps_per_second": 1.231,
|
| 18 |
+
"step": 7
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.2903225806451613,
|
| 22 |
+
"grad_norm": 10.190420150756836,
|
| 23 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 24 |
+
"loss": 1.5038,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.935483870967742,
|
| 29 |
+
"eval_accuracy": 0.4166666666666667,
|
| 30 |
+
"eval_loss": 1.2166622877120972,
|
| 31 |
+
"eval_runtime": 1.5799,
|
| 32 |
+
"eval_samples_per_second": 37.978,
|
| 33 |
+
"eval_steps_per_second": 1.266,
|
| 34 |
+
"step": 15
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 2.5806451612903225,
|
| 38 |
+
"grad_norm": 8.352402687072754,
|
| 39 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 40 |
+
"loss": 1.1504,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 2.967741935483871,
|
| 45 |
+
"eval_accuracy": 0.65,
|
| 46 |
+
"eval_loss": 0.8820936679840088,
|
| 47 |
+
"eval_runtime": 1.6273,
|
| 48 |
+
"eval_samples_per_second": 36.871,
|
| 49 |
+
"eval_steps_per_second": 1.229,
|
| 50 |
+
"step": 23
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.870967741935484,
|
| 54 |
+
"grad_norm": 8.781105041503906,
|
| 55 |
+
"learning_rate": 4e-05,
|
| 56 |
+
"loss": 0.8299,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.0,
|
| 61 |
+
"eval_accuracy": 0.7666666666666667,
|
| 62 |
+
"eval_loss": 0.6488708853721619,
|
| 63 |
+
"eval_runtime": 1.6663,
|
| 64 |
+
"eval_samples_per_second": 36.008,
|
| 65 |
+
"eval_steps_per_second": 1.2,
|
| 66 |
+
"step": 31
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 4.903225806451613,
|
| 70 |
+
"eval_accuracy": 0.8333333333333334,
|
| 71 |
+
"eval_loss": 0.5796787142753601,
|
| 72 |
+
"eval_runtime": 1.6444,
|
| 73 |
+
"eval_samples_per_second": 36.488,
|
| 74 |
+
"eval_steps_per_second": 1.216,
|
| 75 |
+
"step": 38
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.161290322580645,
|
| 79 |
+
"grad_norm": 17.170116424560547,
|
| 80 |
+
"learning_rate": 3.848484848484849e-05,
|
| 81 |
+
"loss": 0.5887,
|
| 82 |
+
"step": 40
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 5.935483870967742,
|
| 86 |
+
"eval_accuracy": 0.75,
|
| 87 |
+
"eval_loss": 0.6618198752403259,
|
| 88 |
+
"eval_runtime": 1.6267,
|
| 89 |
+
"eval_samples_per_second": 36.884,
|
| 90 |
+
"eval_steps_per_second": 1.229,
|
| 91 |
+
"step": 46
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 6.451612903225806,
|
| 95 |
+
"grad_norm": 8.946195602416992,
|
| 96 |
+
"learning_rate": 3.6969696969696974e-05,
|
| 97 |
+
"loss": 0.3965,
|
| 98 |
+
"step": 50
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.967741935483871,
|
| 102 |
+
"eval_accuracy": 0.7833333333333333,
|
| 103 |
+
"eval_loss": 0.6530690789222717,
|
| 104 |
+
"eval_runtime": 1.6436,
|
| 105 |
+
"eval_samples_per_second": 36.505,
|
| 106 |
+
"eval_steps_per_second": 1.217,
|
| 107 |
+
"step": 54
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 7.741935483870968,
|
| 111 |
+
"grad_norm": 10.897398948669434,
|
| 112 |
+
"learning_rate": 3.545454545454546e-05,
|
| 113 |
+
"loss": 0.3089,
|
| 114 |
+
"step": 60
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 8.0,
|
| 118 |
+
"eval_accuracy": 0.7,
|
| 119 |
+
"eval_loss": 0.7609087824821472,
|
| 120 |
+
"eval_runtime": 1.6283,
|
| 121 |
+
"eval_samples_per_second": 36.849,
|
| 122 |
+
"eval_steps_per_second": 1.228,
|
| 123 |
+
"step": 62
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 8.903225806451612,
|
| 127 |
+
"eval_accuracy": 0.6833333333333333,
|
| 128 |
+
"eval_loss": 0.8608618378639221,
|
| 129 |
+
"eval_runtime": 1.8859,
|
| 130 |
+
"eval_samples_per_second": 31.815,
|
| 131 |
+
"eval_steps_per_second": 1.06,
|
| 132 |
+
"step": 69
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 9.03225806451613,
|
| 136 |
+
"grad_norm": 8.992852210998535,
|
| 137 |
+
"learning_rate": 3.3939393939393945e-05,
|
| 138 |
+
"loss": 0.2393,
|
| 139 |
+
"step": 70
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 9.935483870967742,
|
| 143 |
+
"eval_accuracy": 0.7833333333333333,
|
| 144 |
+
"eval_loss": 0.6909741759300232,
|
| 145 |
+
"eval_runtime": 1.6359,
|
| 146 |
+
"eval_samples_per_second": 36.678,
|
| 147 |
+
"eval_steps_per_second": 1.223,
|
| 148 |
+
"step": 77
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 10.32258064516129,
|
| 152 |
+
"grad_norm": 8.585020065307617,
|
| 153 |
+
"learning_rate": 3.2424242424242423e-05,
|
| 154 |
+
"loss": 0.1928,
|
| 155 |
+
"step": 80
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 10.967741935483872,
|
| 159 |
+
"eval_accuracy": 0.8,
|
| 160 |
+
"eval_loss": 0.7773979902267456,
|
| 161 |
+
"eval_runtime": 1.636,
|
| 162 |
+
"eval_samples_per_second": 36.675,
|
| 163 |
+
"eval_steps_per_second": 1.222,
|
| 164 |
+
"step": 85
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 11.612903225806452,
|
| 168 |
+
"grad_norm": 8.469679832458496,
|
| 169 |
+
"learning_rate": 3.090909090909091e-05,
|
| 170 |
+
"loss": 0.1993,
|
| 171 |
+
"step": 90
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 12.0,
|
| 175 |
+
"eval_accuracy": 0.7833333333333333,
|
| 176 |
+
"eval_loss": 0.8423529863357544,
|
| 177 |
+
"eval_runtime": 1.6346,
|
| 178 |
+
"eval_samples_per_second": 36.707,
|
| 179 |
+
"eval_steps_per_second": 1.224,
|
| 180 |
+
"step": 93
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 12.903225806451612,
|
| 184 |
+
"grad_norm": 5.69382381439209,
|
| 185 |
+
"learning_rate": 2.9393939393939398e-05,
|
| 186 |
+
"loss": 0.165,
|
| 187 |
+
"step": 100
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 12.903225806451612,
|
| 191 |
+
"eval_accuracy": 0.7666666666666667,
|
| 192 |
+
"eval_loss": 0.7478328347206116,
|
| 193 |
+
"eval_runtime": 1.6366,
|
| 194 |
+
"eval_samples_per_second": 36.661,
|
| 195 |
+
"eval_steps_per_second": 1.222,
|
| 196 |
+
"step": 100
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 13.935483870967742,
|
| 200 |
+
"eval_accuracy": 0.75,
|
| 201 |
+
"eval_loss": 0.757307231426239,
|
| 202 |
+
"eval_runtime": 1.6144,
|
| 203 |
+
"eval_samples_per_second": 37.166,
|
| 204 |
+
"eval_steps_per_second": 1.239,
|
| 205 |
+
"step": 108
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 14.193548387096774,
|
| 209 |
+
"grad_norm": 5.3613386154174805,
|
| 210 |
+
"learning_rate": 2.7878787878787883e-05,
|
| 211 |
+
"loss": 0.1117,
|
| 212 |
+
"step": 110
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 14.967741935483872,
|
| 216 |
+
"eval_accuracy": 0.8166666666666667,
|
| 217 |
+
"eval_loss": 0.8059377074241638,
|
| 218 |
+
"eval_runtime": 1.6456,
|
| 219 |
+
"eval_samples_per_second": 36.46,
|
| 220 |
+
"eval_steps_per_second": 1.215,
|
| 221 |
+
"step": 116
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 15.483870967741936,
|
| 225 |
+
"grad_norm": 6.849861145019531,
|
| 226 |
+
"learning_rate": 2.6363636363636365e-05,
|
| 227 |
+
"loss": 0.1171,
|
| 228 |
+
"step": 120
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 16.0,
|
| 232 |
+
"eval_accuracy": 0.7666666666666667,
|
| 233 |
+
"eval_loss": 0.8982041478157043,
|
| 234 |
+
"eval_runtime": 1.6378,
|
| 235 |
+
"eval_samples_per_second": 36.635,
|
| 236 |
+
"eval_steps_per_second": 1.221,
|
| 237 |
+
"step": 124
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 16.774193548387096,
|
| 241 |
+
"grad_norm": 4.013183116912842,
|
| 242 |
+
"learning_rate": 2.484848484848485e-05,
|
| 243 |
+
"loss": 0.0961,
|
| 244 |
+
"step": 130
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 16.903225806451612,
|
| 248 |
+
"eval_accuracy": 0.8,
|
| 249 |
+
"eval_loss": 0.9133464097976685,
|
| 250 |
+
"eval_runtime": 1.8779,
|
| 251 |
+
"eval_samples_per_second": 31.951,
|
| 252 |
+
"eval_steps_per_second": 1.065,
|
| 253 |
+
"step": 131
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 17.93548387096774,
|
| 257 |
+
"eval_accuracy": 0.7666666666666667,
|
| 258 |
+
"eval_loss": 0.912105917930603,
|
| 259 |
+
"eval_runtime": 1.6239,
|
| 260 |
+
"eval_samples_per_second": 36.949,
|
| 261 |
+
"eval_steps_per_second": 1.232,
|
| 262 |
+
"step": 139
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 18.06451612903226,
|
| 266 |
+
"grad_norm": 6.759372711181641,
|
| 267 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 268 |
+
"loss": 0.1359,
|
| 269 |
+
"step": 140
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 18.967741935483872,
|
| 273 |
+
"eval_accuracy": 0.8,
|
| 274 |
+
"eval_loss": 0.9297049045562744,
|
| 275 |
+
"eval_runtime": 1.7996,
|
| 276 |
+
"eval_samples_per_second": 33.341,
|
| 277 |
+
"eval_steps_per_second": 1.111,
|
| 278 |
+
"step": 147
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 19.35483870967742,
|
| 282 |
+
"grad_norm": 6.179893970489502,
|
| 283 |
+
"learning_rate": 2.1818181818181818e-05,
|
| 284 |
+
"loss": 0.0981,
|
| 285 |
+
"step": 150
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 20.0,
|
| 289 |
+
"eval_accuracy": 0.7333333333333333,
|
| 290 |
+
"eval_loss": 1.012387990951538,
|
| 291 |
+
"eval_runtime": 2.1389,
|
| 292 |
+
"eval_samples_per_second": 28.052,
|
| 293 |
+
"eval_steps_per_second": 0.935,
|
| 294 |
+
"step": 155
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 20.64516129032258,
|
| 298 |
+
"grad_norm": 5.074409484863281,
|
| 299 |
+
"learning_rate": 2.0303030303030303e-05,
|
| 300 |
+
"loss": 0.0817,
|
| 301 |
+
"step": 160
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 20.903225806451612,
|
| 305 |
+
"eval_accuracy": 0.75,
|
| 306 |
+
"eval_loss": 0.9627708196640015,
|
| 307 |
+
"eval_runtime": 1.827,
|
| 308 |
+
"eval_samples_per_second": 32.841,
|
| 309 |
+
"eval_steps_per_second": 1.095,
|
| 310 |
+
"step": 162
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 21.93548387096774,
|
| 314 |
+
"grad_norm": 5.621190547943115,
|
| 315 |
+
"learning_rate": 1.8787878787878792e-05,
|
| 316 |
+
"loss": 0.0976,
|
| 317 |
+
"step": 170
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 21.93548387096774,
|
| 321 |
+
"eval_accuracy": 0.7666666666666667,
|
| 322 |
+
"eval_loss": 0.9663652777671814,
|
| 323 |
+
"eval_runtime": 1.6503,
|
| 324 |
+
"eval_samples_per_second": 36.358,
|
| 325 |
+
"eval_steps_per_second": 1.212,
|
| 326 |
+
"step": 170
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 22.967741935483872,
|
| 330 |
+
"eval_accuracy": 0.8166666666666667,
|
| 331 |
+
"eval_loss": 0.7979750037193298,
|
| 332 |
+
"eval_runtime": 1.6343,
|
| 333 |
+
"eval_samples_per_second": 36.714,
|
| 334 |
+
"eval_steps_per_second": 1.224,
|
| 335 |
+
"step": 178
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 23.225806451612904,
|
| 339 |
+
"grad_norm": 4.8617706298828125,
|
| 340 |
+
"learning_rate": 1.7272727272727274e-05,
|
| 341 |
+
"loss": 0.0899,
|
| 342 |
+
"step": 180
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 24.0,
|
| 346 |
+
"eval_accuracy": 0.7666666666666667,
|
| 347 |
+
"eval_loss": 0.8365867733955383,
|
| 348 |
+
"eval_runtime": 2.8201,
|
| 349 |
+
"eval_samples_per_second": 21.276,
|
| 350 |
+
"eval_steps_per_second": 0.709,
|
| 351 |
+
"step": 186
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 24.516129032258064,
|
| 355 |
+
"grad_norm": 5.400606155395508,
|
| 356 |
+
"learning_rate": 1.575757575757576e-05,
|
| 357 |
+
"loss": 0.1052,
|
| 358 |
+
"step": 190
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 24.903225806451612,
|
| 362 |
+
"eval_accuracy": 0.7666666666666667,
|
| 363 |
+
"eval_loss": 0.9160324335098267,
|
| 364 |
+
"eval_runtime": 1.643,
|
| 365 |
+
"eval_samples_per_second": 36.519,
|
| 366 |
+
"eval_steps_per_second": 1.217,
|
| 367 |
+
"step": 193
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 25.806451612903224,
|
| 371 |
+
"grad_norm": 3.636944055557251,
|
| 372 |
+
"learning_rate": 1.4242424242424245e-05,
|
| 373 |
+
"loss": 0.0817,
|
| 374 |
+
"step": 200
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 25.93548387096774,
|
| 378 |
+
"eval_accuracy": 0.7666666666666667,
|
| 379 |
+
"eval_loss": 0.970082700252533,
|
| 380 |
+
"eval_runtime": 2.149,
|
| 381 |
+
"eval_samples_per_second": 27.92,
|
| 382 |
+
"eval_steps_per_second": 0.931,
|
| 383 |
+
"step": 201
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 26.967741935483872,
|
| 387 |
+
"eval_accuracy": 0.75,
|
| 388 |
+
"eval_loss": 0.9995465874671936,
|
| 389 |
+
"eval_runtime": 1.6532,
|
| 390 |
+
"eval_samples_per_second": 36.292,
|
| 391 |
+
"eval_steps_per_second": 1.21,
|
| 392 |
+
"step": 209
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 27.096774193548388,
|
| 396 |
+
"grad_norm": 10.176094055175781,
|
| 397 |
+
"learning_rate": 1.2727272727272728e-05,
|
| 398 |
+
"loss": 0.0886,
|
| 399 |
+
"step": 210
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 28.0,
|
| 403 |
+
"eval_accuracy": 0.8,
|
| 404 |
+
"eval_loss": 0.8483232855796814,
|
| 405 |
+
"eval_runtime": 1.6529,
|
| 406 |
+
"eval_samples_per_second": 36.3,
|
| 407 |
+
"eval_steps_per_second": 1.21,
|
| 408 |
+
"step": 217
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 28.387096774193548,
|
| 412 |
+
"grad_norm": 4.629071235656738,
|
| 413 |
+
"learning_rate": 1.1212121212121212e-05,
|
| 414 |
+
"loss": 0.0766,
|
| 415 |
+
"step": 220
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 28.903225806451612,
|
| 419 |
+
"eval_accuracy": 0.7833333333333333,
|
| 420 |
+
"eval_loss": 0.89542156457901,
|
| 421 |
+
"eval_runtime": 1.758,
|
| 422 |
+
"eval_samples_per_second": 34.129,
|
| 423 |
+
"eval_steps_per_second": 1.138,
|
| 424 |
+
"step": 224
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 29.677419354838708,
|
| 428 |
+
"grad_norm": 9.337085723876953,
|
| 429 |
+
"learning_rate": 9.696969696969698e-06,
|
| 430 |
+
"loss": 0.0923,
|
| 431 |
+
"step": 230
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 29.93548387096774,
|
| 435 |
+
"eval_accuracy": 0.7833333333333333,
|
| 436 |
+
"eval_loss": 0.9605885744094849,
|
| 437 |
+
"eval_runtime": 1.6458,
|
| 438 |
+
"eval_samples_per_second": 36.456,
|
| 439 |
+
"eval_steps_per_second": 1.215,
|
| 440 |
+
"step": 232
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 30.967741935483872,
|
| 444 |
+
"grad_norm": 4.47194242477417,
|
| 445 |
+
"learning_rate": 8.181818181818183e-06,
|
| 446 |
+
"loss": 0.0579,
|
| 447 |
+
"step": 240
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 30.967741935483872,
|
| 451 |
+
"eval_accuracy": 0.75,
|
| 452 |
+
"eval_loss": 0.9958234429359436,
|
| 453 |
+
"eval_runtime": 1.8682,
|
| 454 |
+
"eval_samples_per_second": 32.116,
|
| 455 |
+
"eval_steps_per_second": 1.071,
|
| 456 |
+
"step": 240
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 32.0,
|
| 460 |
+
"eval_accuracy": 0.7833333333333333,
|
| 461 |
+
"eval_loss": 0.9665268063545227,
|
| 462 |
+
"eval_runtime": 1.6466,
|
| 463 |
+
"eval_samples_per_second": 36.439,
|
| 464 |
+
"eval_steps_per_second": 1.215,
|
| 465 |
+
"step": 248
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 32.25806451612903,
|
| 469 |
+
"grad_norm": 3.8999428749084473,
|
| 470 |
+
"learning_rate": 6.666666666666667e-06,
|
| 471 |
+
"loss": 0.0707,
|
| 472 |
+
"step": 250
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 32.903225806451616,
|
| 476 |
+
"eval_accuracy": 0.7666666666666667,
|
| 477 |
+
"eval_loss": 1.0259429216384888,
|
| 478 |
+
"eval_runtime": 1.7687,
|
| 479 |
+
"eval_samples_per_second": 33.923,
|
| 480 |
+
"eval_steps_per_second": 1.131,
|
| 481 |
+
"step": 255
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 33.54838709677419,
|
| 485 |
+
"grad_norm": 3.87837815284729,
|
| 486 |
+
"learning_rate": 5.151515151515152e-06,
|
| 487 |
+
"loss": 0.0756,
|
| 488 |
+
"step": 260
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 33.935483870967744,
|
| 492 |
+
"eval_accuracy": 0.75,
|
| 493 |
+
"eval_loss": 1.0626757144927979,
|
| 494 |
+
"eval_runtime": 2.1538,
|
| 495 |
+
"eval_samples_per_second": 27.858,
|
| 496 |
+
"eval_steps_per_second": 0.929,
|
| 497 |
+
"step": 263
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 34.83870967741935,
|
| 501 |
+
"grad_norm": 7.991878986358643,
|
| 502 |
+
"learning_rate": 3.6363636363636366e-06,
|
| 503 |
+
"loss": 0.0528,
|
| 504 |
+
"step": 270
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 34.96774193548387,
|
| 508 |
+
"eval_accuracy": 0.7666666666666667,
|
| 509 |
+
"eval_loss": 1.050768256187439,
|
| 510 |
+
"eval_runtime": 1.6273,
|
| 511 |
+
"eval_samples_per_second": 36.87,
|
| 512 |
+
"eval_steps_per_second": 1.229,
|
| 513 |
+
"step": 271
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 36.0,
|
| 517 |
+
"eval_accuracy": 0.7666666666666667,
|
| 518 |
+
"eval_loss": 1.099774718284607,
|
| 519 |
+
"eval_runtime": 1.6638,
|
| 520 |
+
"eval_samples_per_second": 36.062,
|
| 521 |
+
"eval_steps_per_second": 1.202,
|
| 522 |
+
"step": 279
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 36.12903225806452,
|
| 526 |
+
"grad_norm": 5.349879741668701,
|
| 527 |
+
"learning_rate": 2.1212121212121216e-06,
|
| 528 |
+
"loss": 0.0706,
|
| 529 |
+
"step": 280
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 36.903225806451616,
|
| 533 |
+
"eval_accuracy": 0.75,
|
| 534 |
+
"eval_loss": 1.0693951845169067,
|
| 535 |
+
"eval_runtime": 1.675,
|
| 536 |
+
"eval_samples_per_second": 35.82,
|
| 537 |
+
"eval_steps_per_second": 1.194,
|
| 538 |
+
"step": 286
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 37.41935483870968,
|
| 542 |
+
"grad_norm": 6.116847038269043,
|
| 543 |
+
"learning_rate": 6.060606060606061e-07,
|
| 544 |
+
"loss": 0.0658,
|
| 545 |
+
"step": 290
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 37.935483870967744,
|
| 549 |
+
"eval_accuracy": 0.7666666666666667,
|
| 550 |
+
"eval_loss": 1.0560951232910156,
|
| 551 |
+
"eval_runtime": 1.6581,
|
| 552 |
+
"eval_samples_per_second": 36.187,
|
| 553 |
+
"eval_steps_per_second": 1.206,
|
| 554 |
+
"step": 294
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 37.935483870967744,
|
| 558 |
+
"step": 294,
|
| 559 |
+
"total_flos": 2.8633958865108173e+18,
|
| 560 |
+
"train_loss": 0.24709520539661653,
|
| 561 |
+
"train_runtime": 1707.2205,
|
| 562 |
+
"train_samples_per_second": 23.962,
|
| 563 |
+
"train_steps_per_second": 0.172
|
| 564 |
+
}
|
| 565 |
+
],
|
| 566 |
+
"logging_steps": 10,
|
| 567 |
+
"max_steps": 294,
|
| 568 |
+
"num_input_tokens_seen": 0,
|
| 569 |
+
"num_train_epochs": 42,
|
| 570 |
+
"save_steps": 500,
|
| 571 |
+
"total_flos": 2.8633958865108173e+18,
|
| 572 |
+
"train_batch_size": 32,
|
| 573 |
+
"trial_name": null,
|
| 574 |
+
"trial_params": null
|
| 575 |
+
}
|