End of training
Browse files- all_results.json +14 -14
- eval_results.json +10 -10
- runs/Sep04_12-03-40_data-science-wbi/events.out.tfevents.1725464007.data-science-wbi +2 -2
- train_results.json +5 -9
- trainer_state.json +279 -105
all_results.json
CHANGED
|
@@ -1,22 +1,22 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 6.885245901639344,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_auc_class_0": 0.
|
| 5 |
-
"eval_auc_class_1": 0.
|
| 6 |
-
"eval_auc_class_2":
|
| 7 |
-
"eval_auc_overall": 0.
|
| 8 |
-
"eval_loss": 0.
|
| 9 |
-
"eval_runtime":
|
| 10 |
-
"eval_samples_per_second":
|
| 11 |
-
"eval_steps_per_second":
|
| 12 |
-
"total_flos":
|
| 13 |
"train_accuracy": 0.8871655680496316,
|
| 14 |
"train_auc_class_0": 0.9601424899214485,
|
| 15 |
"train_auc_class_1": 0.968345723853034,
|
| 16 |
"train_auc_class_2": 0.9621813081120092,
|
| 17 |
"train_auc_overall": 0.9635565072954971,
|
| 18 |
-
"train_loss": 0.
|
| 19 |
-
"train_runtime":
|
| 20 |
-
"train_samples_per_second":
|
| 21 |
-
"train_steps_per_second": 0.
|
| 22 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 6.885245901639344,
|
| 3 |
+
"eval_accuracy": 0.8819264629725531,
|
| 4 |
+
"eval_auc_class_0": 0.9495999423161078,
|
| 5 |
+
"eval_auc_class_1": 0.9589146175353072,
|
| 6 |
+
"eval_auc_class_2": 0.9645625643801177,
|
| 7 |
+
"eval_auc_overall": 0.9576923747438442,
|
| 8 |
+
"eval_loss": 0.3063272535800934,
|
| 9 |
+
"eval_runtime": 213.6843,
|
| 10 |
+
"eval_samples_per_second": 9.037,
|
| 11 |
+
"eval_steps_per_second": 0.075,
|
| 12 |
+
"total_flos": 4.1785312376666235e+18,
|
| 13 |
"train_accuracy": 0.8871655680496316,
|
| 14 |
"train_auc_class_0": 0.9601424899214485,
|
| 15 |
"train_auc_class_1": 0.968345723853034,
|
| 16 |
"train_auc_class_2": 0.9621813081120092,
|
| 17 |
"train_auc_overall": 0.9635565072954971,
|
| 18 |
+
"train_loss": 0.4226800623394194,
|
| 19 |
+
"train_runtime": 11867.0985,
|
| 20 |
+
"train_samples_per_second": 4.564,
|
| 21 |
+
"train_steps_per_second": 0.009
|
| 22 |
}
|
eval_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_auc_class_0": 0.
|
| 5 |
-
"eval_auc_class_1": 0.
|
| 6 |
-
"eval_auc_class_2":
|
| 7 |
-
"eval_auc_overall": 0.
|
| 8 |
-
"eval_loss": 0.
|
| 9 |
-
"eval_runtime":
|
| 10 |
-
"eval_samples_per_second":
|
| 11 |
-
"eval_steps_per_second":
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 6.885245901639344,
|
| 3 |
+
"eval_accuracy": 0.8819264629725531,
|
| 4 |
+
"eval_auc_class_0": 0.9495999423161078,
|
| 5 |
+
"eval_auc_class_1": 0.9589146175353072,
|
| 6 |
+
"eval_auc_class_2": 0.9645625643801177,
|
| 7 |
+
"eval_auc_overall": 0.9576923747438442,
|
| 8 |
+
"eval_loss": 0.3063272535800934,
|
| 9 |
+
"eval_runtime": 213.6843,
|
| 10 |
+
"eval_samples_per_second": 9.037,
|
| 11 |
+
"eval_steps_per_second": 0.075
|
| 12 |
}
|
runs/Sep04_12-03-40_data-science-wbi/events.out.tfevents.1725464007.data-science-wbi
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 sha256:2716d150ddc47634cbe1e3edff13dc15faec299b9ab04762924abf3f290e83e1
|
| 3 |
+
size 636
|
train_results.json
CHANGED
|
@@ -1,12 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 6.885245901639344,
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"
|
| 8 |
-
"train_loss": 0.2833240032196045,
|
| 9 |
-
"train_runtime": 718.0615,
|
| 10 |
-
"train_samples_per_second": 10.775,
|
| 11 |
-
"train_steps_per_second": 0.085
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 6.885245901639344,
|
| 3 |
+
"total_flos": 4.1785312376666235e+18,
|
| 4 |
+
"train_loss": 0.4226800623394194,
|
| 5 |
+
"train_runtime": 11867.0985,
|
| 6 |
+
"train_samples_per_second": 4.564,
|
| 7 |
+
"train_steps_per_second": 0.009
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,118 +1,292 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "swin-base-patch4-window7-224-in22k-cons_Classification_base_V10/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":
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
|
| 18 |
-
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
"
|
| 26 |
-
"
|
| 27 |
-
"
|
| 28 |
-
"
|
| 29 |
-
"
|
| 30 |
-
|
| 31 |
-
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
"
|
| 39 |
-
"
|
| 40 |
-
"
|
| 41 |
-
"
|
| 42 |
-
"
|
| 43 |
-
|
| 44 |
-
|
| 45 |
-
"
|
| 46 |
-
"
|
| 47 |
-
"
|
| 48 |
-
"
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
"
|
| 53 |
-
"
|
| 54 |
-
"
|
| 55 |
-
"
|
| 56 |
-
"
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
"
|
| 60 |
-
"
|
| 61 |
-
"
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
"
|
| 65 |
-
"
|
| 66 |
-
"
|
| 67 |
-
"
|
| 68 |
-
"
|
| 69 |
-
"
|
| 70 |
-
|
| 71 |
-
|
| 72 |
-
"
|
| 73 |
-
"
|
| 74 |
-
"
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
"
|
| 78 |
-
"
|
| 79 |
-
"
|
| 80 |
-
"
|
| 81 |
-
"
|
| 82 |
-
"
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
"
|
| 86 |
-
"
|
| 87 |
-
"
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
"
|
| 93 |
-
"
|
| 94 |
-
"
|
| 95 |
-
"
|
| 96 |
-
"
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
"
|
| 100 |
-
"
|
| 101 |
-
"
|
| 102 |
-
"
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
"
|
| 106 |
-
"
|
| 107 |
-
"
|
| 108 |
-
"
|
| 109 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 110 |
}
|
| 111 |
],
|
| 112 |
"logging_steps": 10,
|
| 113 |
-
"max_steps":
|
| 114 |
"num_input_tokens_seen": 0,
|
| 115 |
-
"num_train_epochs":
|
| 116 |
"save_steps": 500,
|
| 117 |
"stateful_callbacks": {
|
| 118 |
"TrainerControl": {
|
|
@@ -126,7 +300,7 @@
|
|
| 126 |
"attributes": {}
|
| 127 |
}
|
| 128 |
},
|
| 129 |
-
"total_flos":
|
| 130 |
"train_batch_size": 128,
|
| 131 |
"trial_name": null,
|
| 132 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8819264629725531,
|
| 3 |
+
"best_model_checkpoint": "swin-base-patch4-window7-224-in22k-cons_Classification_base_V10/checkpoint-105",
|
| 4 |
+
"epoch": 6.885245901639344,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 105,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.6557377049180327,
|
| 13 |
+
"grad_norm": 3.7154650688171387,
|
| 14 |
+
"learning_rate": 4.545454545454546e-05,
|
| 15 |
+
"loss": 1.0279,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.9836065573770492,
|
| 20 |
+
"step": 15,
|
| 21 |
+
"train_accuracy": 0.7968204730515703,
|
| 22 |
+
"train_auc_class_0": 0.8674857214060812,
|
| 23 |
+
"train_auc_class_1": 0.9047321713989991,
|
| 24 |
+
"train_auc_class_2": 0.8256152717071332,
|
| 25 |
+
"train_auc_overall": 0.8659443881707377,
|
| 26 |
+
"train_loss": 0.5398309230804443,
|
| 27 |
+
"train_runtime": 704.5916,
|
| 28 |
+
"train_samples_per_second": 10.981,
|
| 29 |
+
"train_steps_per_second": 0.087
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.9836065573770492,
|
| 33 |
+
"eval_accuracy": 0.8234075608493009,
|
| 34 |
+
"eval_auc_class_0": 0.8869781099574333,
|
| 35 |
+
"eval_auc_class_1": 0.9183382321313357,
|
| 36 |
+
"eval_auc_class_2": 0.8605897655254291,
|
| 37 |
+
"eval_auc_overall": 0.8886353692047327,
|
| 38 |
+
"eval_loss": 0.4998205900192261,
|
| 39 |
+
"eval_runtime": 206.129,
|
| 40 |
+
"eval_samples_per_second": 9.368,
|
| 41 |
+
"eval_steps_per_second": 0.078,
|
| 42 |
+
"step": 15
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.3114754098360657,
|
| 46 |
+
"grad_norm": 1.7328158617019653,
|
| 47 |
+
"learning_rate": 4.5212765957446815e-05,
|
| 48 |
+
"loss": 0.5553,
|
| 49 |
+
"step": 20
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 1.9672131147540983,
|
| 53 |
+
"grad_norm": 2.4891183376312256,
|
| 54 |
+
"learning_rate": 3.9893617021276594e-05,
|
| 55 |
+
"loss": 0.428,
|
| 56 |
+
"step": 30
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.9672131147540983,
|
| 60 |
+
"step": 30,
|
| 61 |
+
"train_accuracy": 0.8445133772780148,
|
| 62 |
+
"train_auc_class_0": 0.9255038035954841,
|
| 63 |
+
"train_auc_class_1": 0.9439145849287703,
|
| 64 |
+
"train_auc_class_2": 0.9234406921755834,
|
| 65 |
+
"train_auc_overall": 0.930953026899946,
|
| 66 |
+
"train_loss": 0.38005331158638,
|
| 67 |
+
"train_runtime": 696.7728,
|
| 68 |
+
"train_samples_per_second": 11.104,
|
| 69 |
+
"train_steps_per_second": 0.088
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.9672131147540983,
|
| 73 |
+
"eval_accuracy": 0.8493008803728638,
|
| 74 |
+
"eval_auc_class_0": 0.9309048911962445,
|
| 75 |
+
"eval_auc_class_1": 0.9438927521686142,
|
| 76 |
+
"eval_auc_class_2": 0.9451350454807339,
|
| 77 |
+
"eval_auc_overall": 0.9399775629485309,
|
| 78 |
+
"eval_loss": 0.373575896024704,
|
| 79 |
+
"eval_runtime": 206.7801,
|
| 80 |
+
"eval_samples_per_second": 9.338,
|
| 81 |
+
"eval_steps_per_second": 0.077,
|
| 82 |
+
"step": 30
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 2.6229508196721314,
|
| 86 |
+
"grad_norm": 1.9731707572937012,
|
| 87 |
+
"learning_rate": 3.4574468085106386e-05,
|
| 88 |
+
"loss": 0.3805,
|
| 89 |
+
"step": 40
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.9508196721311473,
|
| 93 |
+
"step": 45,
|
| 94 |
+
"train_accuracy": 0.8635129895308259,
|
| 95 |
+
"train_auc_class_0": 0.9433487526029413,
|
| 96 |
+
"train_auc_class_1": 0.9545073030991414,
|
| 97 |
+
"train_auc_class_2": 0.9527349780371537,
|
| 98 |
+
"train_auc_overall": 0.9501970112464121,
|
| 99 |
+
"train_loss": 0.33183473348617554,
|
| 100 |
+
"train_runtime": 694.8396,
|
| 101 |
+
"train_samples_per_second": 11.135,
|
| 102 |
+
"train_steps_per_second": 0.088
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 2.9508196721311473,
|
| 106 |
+
"eval_accuracy": 0.8638011393060591,
|
| 107 |
+
"eval_auc_class_0": 0.9430968293750248,
|
| 108 |
+
"eval_auc_class_1": 0.9533629650871029,
|
| 109 |
+
"eval_auc_class_2": 0.9590411508982662,
|
| 110 |
+
"eval_auc_overall": 0.9518336484534647,
|
| 111 |
+
"eval_loss": 0.3269486129283905,
|
| 112 |
+
"eval_runtime": 209.5765,
|
| 113 |
+
"eval_samples_per_second": 9.214,
|
| 114 |
+
"eval_steps_per_second": 0.076,
|
| 115 |
+
"step": 45
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 3.278688524590164,
|
| 119 |
+
"grad_norm": 2.599257469177246,
|
| 120 |
+
"learning_rate": 2.925531914893617e-05,
|
| 121 |
+
"loss": 0.338,
|
| 122 |
+
"step": 50
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 3.9344262295081966,
|
| 126 |
+
"grad_norm": 2.2009198665618896,
|
| 127 |
+
"learning_rate": 2.393617021276596e-05,
|
| 128 |
+
"loss": 0.3305,
|
| 129 |
+
"step": 60
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.0,
|
| 133 |
+
"step": 61,
|
| 134 |
+
"train_accuracy": 0.8725604239369265,
|
| 135 |
+
"train_auc_class_0": 0.948471525573143,
|
| 136 |
+
"train_auc_class_1": 0.9603955056035058,
|
| 137 |
+
"train_auc_class_2": 0.9486343423490885,
|
| 138 |
+
"train_auc_overall": 0.9525004578419124,
|
| 139 |
+
"train_loss": 0.31600990891456604,
|
| 140 |
+
"train_runtime": 726.5744,
|
| 141 |
+
"train_samples_per_second": 10.649,
|
| 142 |
+
"train_steps_per_second": 0.084
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 4.0,
|
| 146 |
+
"eval_accuracy": 0.8762299326773693,
|
| 147 |
+
"eval_auc_class_0": 0.9471881588892868,
|
| 148 |
+
"eval_auc_class_1": 0.9563538604917915,
|
| 149 |
+
"eval_auc_class_2": 0.9630043472947257,
|
| 150 |
+
"eval_auc_overall": 0.9555154555586013,
|
| 151 |
+
"eval_loss": 0.3176056146621704,
|
| 152 |
+
"eval_runtime": 216.0268,
|
| 153 |
+
"eval_samples_per_second": 8.939,
|
| 154 |
+
"eval_steps_per_second": 0.074,
|
| 155 |
+
"step": 61
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 4.590163934426229,
|
| 159 |
+
"grad_norm": 2.0908782482147217,
|
| 160 |
+
"learning_rate": 1.8617021276595745e-05,
|
| 161 |
+
"loss": 0.3332,
|
| 162 |
+
"step": 70
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 4.983606557377049,
|
| 166 |
+
"step": 76,
|
| 167 |
+
"train_accuracy": 0.8768256430140882,
|
| 168 |
+
"train_auc_class_0": 0.9538384356872789,
|
| 169 |
+
"train_auc_class_1": 0.963852382784682,
|
| 170 |
+
"train_auc_class_2": 0.9602902514264319,
|
| 171 |
+
"train_auc_overall": 0.9593270232994642,
|
| 172 |
+
"train_loss": 0.30048099160194397,
|
| 173 |
+
"train_runtime": 713.1172,
|
| 174 |
+
"train_samples_per_second": 10.85,
|
| 175 |
+
"train_steps_per_second": 0.086
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 4.983606557377049,
|
| 179 |
+
"eval_accuracy": 0.8741584671154842,
|
| 180 |
+
"eval_auc_class_0": 0.946992978477941,
|
| 181 |
+
"eval_auc_class_1": 0.9557961144168041,
|
| 182 |
+
"eval_auc_class_2": 0.9635150234823752,
|
| 183 |
+
"eval_auc_overall": 0.9554347054590401,
|
| 184 |
+
"eval_loss": 0.31987833976745605,
|
| 185 |
+
"eval_runtime": 212.2374,
|
| 186 |
+
"eval_samples_per_second": 9.098,
|
| 187 |
+
"eval_steps_per_second": 0.075,
|
| 188 |
+
"step": 76
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 5.245901639344262,
|
| 192 |
+
"grad_norm": 2.1055748462677,
|
| 193 |
+
"learning_rate": 1.3297872340425532e-05,
|
| 194 |
+
"loss": 0.3097,
|
| 195 |
+
"step": 80
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 5.901639344262295,
|
| 199 |
+
"grad_norm": 1.8331685066223145,
|
| 200 |
+
"learning_rate": 7.97872340425532e-06,
|
| 201 |
+
"loss": 0.2986,
|
| 202 |
+
"step": 90
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 5.967213114754099,
|
| 206 |
+
"step": 91,
|
| 207 |
+
"train_accuracy": 0.8836758433501357,
|
| 208 |
+
"train_auc_class_0": 0.9567022523385401,
|
| 209 |
+
"train_auc_class_1": 0.9669396820592466,
|
| 210 |
+
"train_auc_class_2": 0.9649150652373859,
|
| 211 |
+
"train_auc_overall": 0.9628523332117241,
|
| 212 |
+
"train_loss": 0.2871149480342865,
|
| 213 |
+
"train_runtime": 707.266,
|
| 214 |
+
"train_samples_per_second": 10.939,
|
| 215 |
+
"train_steps_per_second": 0.086
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 5.967213114754099,
|
| 219 |
+
"eval_accuracy": 0.8767477990678405,
|
| 220 |
+
"eval_auc_class_0": 0.9486936587500497,
|
| 221 |
+
"eval_auc_class_1": 0.9580586421965732,
|
| 222 |
+
"eval_auc_class_2": 0.9654660684044206,
|
| 223 |
+
"eval_auc_overall": 0.9574061231170146,
|
| 224 |
+
"eval_loss": 0.3098297417163849,
|
| 225 |
+
"eval_runtime": 211.4462,
|
| 226 |
+
"eval_samples_per_second": 9.132,
|
| 227 |
+
"eval_steps_per_second": 0.076,
|
| 228 |
+
"step": 91
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 6.557377049180328,
|
| 232 |
+
"grad_norm": 1.698627233505249,
|
| 233 |
+
"learning_rate": 2.6595744680851065e-06,
|
| 234 |
+
"loss": 0.2891,
|
| 235 |
+
"step": 100
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 6.885245901639344,
|
| 239 |
+
"step": 105,
|
| 240 |
+
"train_accuracy": 0.8938865193227349,
|
| 241 |
+
"train_auc_class_0": 0.9620290605729788,
|
| 242 |
+
"train_auc_class_1": 0.9704803672023041,
|
| 243 |
+
"train_auc_class_2": 0.967734557500875,
|
| 244 |
+
"train_auc_overall": 0.9667479950920526,
|
| 245 |
+
"train_loss": 0.2710348963737488,
|
| 246 |
+
"train_runtime": 695.2399,
|
| 247 |
+
"train_samples_per_second": 11.129,
|
| 248 |
+
"train_steps_per_second": 0.088
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 6.885245901639344,
|
| 252 |
+
"eval_accuracy": 0.8819264629725531,
|
| 253 |
+
"eval_auc_class_0": 0.9495999423161078,
|
| 254 |
+
"eval_auc_class_1": 0.9589146175353072,
|
| 255 |
+
"eval_auc_class_2": 0.9645625643801177,
|
| 256 |
+
"eval_auc_overall": 0.9576923747438442,
|
| 257 |
+
"eval_loss": 0.3063272535800934,
|
| 258 |
+
"eval_runtime": 210.6714,
|
| 259 |
+
"eval_samples_per_second": 9.166,
|
| 260 |
+
"eval_steps_per_second": 0.076,
|
| 261 |
+
"step": 105
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 6.885245901639344,
|
| 265 |
+
"step": 105,
|
| 266 |
+
"total_flos": 4.1785312376666235e+18,
|
| 267 |
+
"train_loss": 0.4226800623394194,
|
| 268 |
+
"train_runtime": 11867.0985,
|
| 269 |
+
"train_samples_per_second": 4.564,
|
| 270 |
+
"train_steps_per_second": 0.009
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 6.885245901639344,
|
| 274 |
+
"step": 105,
|
| 275 |
+
"train_accuracy": 0.8871655680496316,
|
| 276 |
+
"train_auc_class_0": 0.9601424899214485,
|
| 277 |
+
"train_auc_class_1": 0.968345723853034,
|
| 278 |
+
"train_auc_class_2": 0.9621813081120092,
|
| 279 |
+
"train_auc_overall": 0.9635565072954971,
|
| 280 |
+
"train_loss": 0.2833240032196045,
|
| 281 |
+
"train_runtime": 718.0615,
|
| 282 |
+
"train_samples_per_second": 10.775,
|
| 283 |
+
"train_steps_per_second": 0.085
|
| 284 |
}
|
| 285 |
],
|
| 286 |
"logging_steps": 10,
|
| 287 |
+
"max_steps": 105,
|
| 288 |
"num_input_tokens_seen": 0,
|
| 289 |
+
"num_train_epochs": 7,
|
| 290 |
"save_steps": 500,
|
| 291 |
"stateful_callbacks": {
|
| 292 |
"TrainerControl": {
|
|
|
|
| 300 |
"attributes": {}
|
| 301 |
}
|
| 302 |
},
|
| 303 |
+
"total_flos": 4.1785312376666235e+18,
|
| 304 |
"train_batch_size": 128,
|
| 305 |
"trial_name": null,
|
| 306 |
"trial_params": null
|