best albert-tiny model finetuned on ner
Browse files- all_results.json +13 -13
- eval_results.json +9 -9
- pytorch_model.bin +1 -1
- train_results.json +5 -5
- trainer_state.json +518 -20
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,17 +1,17 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime":
|
| 9 |
"eval_samples": 1916,
|
| 10 |
-
"eval_samples_per_second":
|
| 11 |
-
"eval_steps_per_second":
|
| 12 |
-
"train_loss": 0.
|
| 13 |
-
"train_runtime":
|
| 14 |
"train_samples": 8324,
|
| 15 |
-
"train_samples_per_second":
|
| 16 |
-
"train_steps_per_second":
|
| 17 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9473241942924933,
|
| 4 |
+
"eval_f1": 0.7241245438310427,
|
| 5 |
+
"eval_loss": 0.1745937019586563,
|
| 6 |
+
"eval_precision": 0.7045935327893623,
|
| 7 |
+
"eval_recall": 0.7447692061970931,
|
| 8 |
+
"eval_runtime": 1.4947,
|
| 9 |
"eval_samples": 1916,
|
| 10 |
+
"eval_samples_per_second": 1281.891,
|
| 11 |
+
"eval_steps_per_second": 80.285,
|
| 12 |
+
"train_loss": 0.1328041532904539,
|
| 13 |
+
"train_runtime": 90.5157,
|
| 14 |
"train_samples": 8324,
|
| 15 |
+
"train_samples_per_second": 367.848,
|
| 16 |
+
"train_steps_per_second": 23.024
|
| 17 |
}
|
eval_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime":
|
| 9 |
"eval_samples": 1916,
|
| 10 |
-
"eval_samples_per_second":
|
| 11 |
-
"eval_steps_per_second":
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"eval_accuracy": 0.9473241942924933,
|
| 4 |
+
"eval_f1": 0.7241245438310427,
|
| 5 |
+
"eval_loss": 0.1745937019586563,
|
| 6 |
+
"eval_precision": 0.7045935327893623,
|
| 7 |
+
"eval_recall": 0.7447692061970931,
|
| 8 |
+
"eval_runtime": 1.4947,
|
| 9 |
"eval_samples": 1916,
|
| 10 |
+
"eval_samples_per_second": 1281.891,
|
| 11 |
+
"eval_steps_per_second": 80.285
|
| 12 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 21011223
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ee5bc516deaa9037d742f40795bb6b274bd5ece153efe88ed66b62a57c9ff79
|
| 3 |
size 21011223
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 8324,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"train_loss": 0.1328041532904539,
|
| 4 |
+
"train_runtime": 90.5157,
|
| 5 |
"train_samples": 8324,
|
| 6 |
+
"train_samples_per_second": 367.848,
|
| 7 |
+
"train_steps_per_second": 23.024
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,43 +1,541 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_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": 0.96,
|
| 12 |
-
"learning_rate": 3.
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 500
|
| 15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
{
|
| 17 |
"epoch": 1.92,
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 1000
|
| 21 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
{
|
| 23 |
"epoch": 2.88,
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch":
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
}
|
| 37 |
],
|
| 38 |
-
"max_steps":
|
| 39 |
-
"num_train_epochs":
|
| 40 |
-
"total_flos":
|
| 41 |
"trial_name": null,
|
| 42 |
"trial_params": null
|
| 43 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.1745937019586563,
|
| 3 |
+
"best_model_checkpoint": "/home/sdonoso/data/all_results/ner-c/albert-tiny/epochs_4_bs_16_lr_5e-5/checkpoint-1400",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 2084,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"eval_accuracy": 0.863771172477427,
|
| 13 |
+
"eval_f1": 0.24746022618363045,
|
| 14 |
+
"eval_loss": 0.4690728187561035,
|
| 15 |
+
"eval_precision": 0.3093697579678888,
|
| 16 |
+
"eval_recall": 0.20619709311611564,
|
| 17 |
+
"eval_runtime": 1.4686,
|
| 18 |
+
"eval_samples_per_second": 1304.616,
|
| 19 |
+
"eval_steps_per_second": 81.709,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.19,
|
| 24 |
+
"eval_accuracy": 0.9084722862980293,
|
| 25 |
+
"eval_f1": 0.5024801196756161,
|
| 26 |
+
"eval_loss": 0.3399835526943207,
|
| 27 |
+
"eval_precision": 0.4954968944099379,
|
| 28 |
+
"eval_recall": 0.5096629931320875,
|
| 29 |
+
"eval_runtime": 1.4666,
|
| 30 |
+
"eval_samples_per_second": 1306.423,
|
| 31 |
+
"eval_steps_per_second": 81.822,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.29,
|
| 36 |
+
"eval_accuracy": 0.9171060436301325,
|
| 37 |
+
"eval_f1": 0.5566067486597288,
|
| 38 |
+
"eval_loss": 0.29001280665397644,
|
| 39 |
+
"eval_precision": 0.5495874202086253,
|
| 40 |
+
"eval_recall": 0.5638076984507268,
|
| 41 |
+
"eval_runtime": 1.5018,
|
| 42 |
+
"eval_samples_per_second": 1275.795,
|
| 43 |
+
"eval_steps_per_second": 79.904,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.38,
|
| 48 |
+
"eval_accuracy": 0.9215053054768338,
|
| 49 |
+
"eval_f1": 0.5868562353475006,
|
| 50 |
+
"eval_loss": 0.26263922452926636,
|
| 51 |
+
"eval_precision": 0.5573111174949728,
|
| 52 |
+
"eval_recall": 0.6197093116115636,
|
| 53 |
+
"eval_runtime": 1.4723,
|
| 54 |
+
"eval_samples_per_second": 1301.379,
|
| 55 |
+
"eval_steps_per_second": 81.506,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.48,
|
| 60 |
+
"eval_accuracy": 0.9255750346009358,
|
| 61 |
+
"eval_f1": 0.6203032300593275,
|
| 62 |
+
"eval_loss": 0.25319042801856995,
|
| 63 |
+
"eval_precision": 0.6406808510638298,
|
| 64 |
+
"eval_recall": 0.6011819198211148,
|
| 65 |
+
"eval_runtime": 1.469,
|
| 66 |
+
"eval_samples_per_second": 1304.326,
|
| 67 |
+
"eval_steps_per_second": 81.691,
|
| 68 |
+
"step": 250
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.58,
|
| 72 |
+
"eval_accuracy": 0.9309793712515653,
|
| 73 |
+
"eval_f1": 0.6298792914249882,
|
| 74 |
+
"eval_loss": 0.22614283859729767,
|
| 75 |
+
"eval_precision": 0.6184392796675389,
|
| 76 |
+
"eval_recall": 0.6417505190864079,
|
| 77 |
+
"eval_runtime": 1.4706,
|
| 78 |
+
"eval_samples_per_second": 1302.847,
|
| 79 |
+
"eval_steps_per_second": 81.598,
|
| 80 |
+
"step": 300
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.67,
|
| 84 |
+
"eval_accuracy": 0.9334838199433204,
|
| 85 |
+
"eval_f1": 0.6383647798742139,
|
| 86 |
+
"eval_loss": 0.21767833828926086,
|
| 87 |
+
"eval_precision": 0.6285802755844558,
|
| 88 |
+
"eval_recall": 0.6484587126657083,
|
| 89 |
+
"eval_runtime": 1.47,
|
| 90 |
+
"eval_samples_per_second": 1303.418,
|
| 91 |
+
"eval_steps_per_second": 81.634,
|
| 92 |
+
"step": 350
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.77,
|
| 96 |
+
"eval_accuracy": 0.9345383246556384,
|
| 97 |
+
"eval_f1": 0.6418154877953678,
|
| 98 |
+
"eval_loss": 0.21528242528438568,
|
| 99 |
+
"eval_precision": 0.6270953977445901,
|
| 100 |
+
"eval_recall": 0.657243251876697,
|
| 101 |
+
"eval_runtime": 1.5017,
|
| 102 |
+
"eval_samples_per_second": 1275.883,
|
| 103 |
+
"eval_steps_per_second": 79.909,
|
| 104 |
+
"step": 400
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.86,
|
| 108 |
+
"eval_accuracy": 0.9356422592763461,
|
| 109 |
+
"eval_f1": 0.6500153704272977,
|
| 110 |
+
"eval_loss": 0.21207766234874725,
|
| 111 |
+
"eval_precision": 0.626425714708932,
|
| 112 |
+
"eval_recall": 0.6754512058776553,
|
| 113 |
+
"eval_runtime": 1.4752,
|
| 114 |
+
"eval_samples_per_second": 1298.836,
|
| 115 |
+
"eval_steps_per_second": 81.347,
|
| 116 |
+
"step": 450
|
| 117 |
+
},
|
| 118 |
{
|
| 119 |
"epoch": 0.96,
|
| 120 |
+
"learning_rate": 3.807581573896353e-05,
|
| 121 |
+
"loss": 0.2732,
|
| 122 |
"step": 500
|
| 123 |
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.96,
|
| 126 |
+
"eval_accuracy": 0.9400415211230475,
|
| 127 |
+
"eval_f1": 0.6775403935982847,
|
| 128 |
+
"eval_loss": 0.19518034160137177,
|
| 129 |
+
"eval_precision": 0.6507796410709032,
|
| 130 |
+
"eval_recall": 0.7065963903529787,
|
| 131 |
+
"eval_runtime": 1.4979,
|
| 132 |
+
"eval_samples_per_second": 1279.083,
|
| 133 |
+
"eval_steps_per_second": 80.11,
|
| 134 |
+
"step": 500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.06,
|
| 138 |
+
"eval_accuracy": 0.9415738482831345,
|
| 139 |
+
"eval_f1": 0.68428873074216,
|
| 140 |
+
"eval_loss": 0.18678122758865356,
|
| 141 |
+
"eval_precision": 0.6703953417100827,
|
| 142 |
+
"eval_recall": 0.6987701645104616,
|
| 143 |
+
"eval_runtime": 1.473,
|
| 144 |
+
"eval_samples_per_second": 1300.753,
|
| 145 |
+
"eval_steps_per_second": 81.467,
|
| 146 |
+
"step": 550
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.15,
|
| 150 |
+
"eval_accuracy": 0.9421670071838133,
|
| 151 |
+
"eval_f1": 0.6916773778920309,
|
| 152 |
+
"eval_loss": 0.19731050729751587,
|
| 153 |
+
"eval_precision": 0.6958138031356069,
|
| 154 |
+
"eval_recall": 0.6875898418782942,
|
| 155 |
+
"eval_runtime": 1.4718,
|
| 156 |
+
"eval_samples_per_second": 1301.838,
|
| 157 |
+
"eval_steps_per_second": 81.535,
|
| 158 |
+
"step": 600
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.25,
|
| 162 |
+
"eval_accuracy": 0.9407500164766361,
|
| 163 |
+
"eval_f1": 0.6780254777070065,
|
| 164 |
+
"eval_loss": 0.1952008754014969,
|
| 165 |
+
"eval_precision": 0.6759803143356088,
|
| 166 |
+
"eval_recall": 0.6800830538252676,
|
| 167 |
+
"eval_runtime": 1.5038,
|
| 168 |
+
"eval_samples_per_second": 1274.147,
|
| 169 |
+
"eval_steps_per_second": 79.8,
|
| 170 |
+
"step": 650
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.34,
|
| 174 |
+
"eval_accuracy": 0.9399097080340078,
|
| 175 |
+
"eval_f1": 0.689172175007869,
|
| 176 |
+
"eval_loss": 0.19703227281570435,
|
| 177 |
+
"eval_precision": 0.679230649914689,
|
| 178 |
+
"eval_recall": 0.6994090400894426,
|
| 179 |
+
"eval_runtime": 1.4697,
|
| 180 |
+
"eval_samples_per_second": 1303.698,
|
| 181 |
+
"eval_steps_per_second": 81.651,
|
| 182 |
+
"step": 700
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.44,
|
| 186 |
+
"eval_accuracy": 0.9425789230870626,
|
| 187 |
+
"eval_f1": 0.697266881028939,
|
| 188 |
+
"eval_loss": 0.19310028851032257,
|
| 189 |
+
"eval_precision": 0.7018935102767438,
|
| 190 |
+
"eval_recall": 0.6927008465101422,
|
| 191 |
+
"eval_runtime": 1.4705,
|
| 192 |
+
"eval_samples_per_second": 1302.989,
|
| 193 |
+
"eval_steps_per_second": 81.607,
|
| 194 |
+
"step": 750
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.54,
|
| 198 |
+
"eval_accuracy": 0.9420351940947737,
|
| 199 |
+
"eval_f1": 0.689247483623582,
|
| 200 |
+
"eval_loss": 0.1976134181022644,
|
| 201 |
+
"eval_precision": 0.6894677960684034,
|
| 202 |
+
"eval_recall": 0.6890273119310014,
|
| 203 |
+
"eval_runtime": 1.4714,
|
| 204 |
+
"eval_samples_per_second": 1302.156,
|
| 205 |
+
"eval_steps_per_second": 81.555,
|
| 206 |
+
"step": 800
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.63,
|
| 210 |
+
"eval_accuracy": 0.9442265867000593,
|
| 211 |
+
"eval_f1": 0.6969575339166734,
|
| 212 |
+
"eval_loss": 0.18812265992164612,
|
| 213 |
+
"eval_precision": 0.7006132989025178,
|
| 214 |
+
"eval_recall": 0.6933397220891231,
|
| 215 |
+
"eval_runtime": 1.4736,
|
| 216 |
+
"eval_samples_per_second": 1300.193,
|
| 217 |
+
"eval_steps_per_second": 81.432,
|
| 218 |
+
"step": 850
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.73,
|
| 222 |
+
"eval_accuracy": 0.9432050352600013,
|
| 223 |
+
"eval_f1": 0.6990461049284578,
|
| 224 |
+
"eval_loss": 0.18850077688694,
|
| 225 |
+
"eval_precision": 0.69583794904257,
|
| 226 |
+
"eval_recall": 0.702283980194857,
|
| 227 |
+
"eval_runtime": 1.5056,
|
| 228 |
+
"eval_samples_per_second": 1272.624,
|
| 229 |
+
"eval_steps_per_second": 79.705,
|
| 230 |
+
"step": 900
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.82,
|
| 234 |
+
"eval_accuracy": 0.9444078296974889,
|
| 235 |
+
"eval_f1": 0.7056041617403641,
|
| 236 |
+
"eval_loss": 0.18260571360588074,
|
| 237 |
+
"eval_precision": 0.6965452847805789,
|
| 238 |
+
"eval_recall": 0.7149017728797317,
|
| 239 |
+
"eval_runtime": 1.4756,
|
| 240 |
+
"eval_samples_per_second": 1298.431,
|
| 241 |
+
"eval_steps_per_second": 81.321,
|
| 242 |
+
"step": 950
|
| 243 |
+
},
|
| 244 |
{
|
| 245 |
"epoch": 1.92,
|
| 246 |
+
"learning_rate": 2.607965451055662e-05,
|
| 247 |
+
"loss": 0.1235,
|
| 248 |
"step": 1000
|
| 249 |
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.92,
|
| 252 |
+
"eval_accuracy": 0.9451163250510776,
|
| 253 |
+
"eval_f1": 0.7066519546027743,
|
| 254 |
+
"eval_loss": 0.18071572482585907,
|
| 255 |
+
"eval_precision": 0.6975260619262487,
|
| 256 |
+
"eval_recall": 0.7160198051429484,
|
| 257 |
+
"eval_runtime": 1.4701,
|
| 258 |
+
"eval_samples_per_second": 1303.293,
|
| 259 |
+
"eval_steps_per_second": 81.626,
|
| 260 |
+
"step": 1000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.02,
|
| 264 |
+
"eval_accuracy": 0.9455282409543267,
|
| 265 |
+
"eval_f1": 0.7122369446609509,
|
| 266 |
+
"eval_loss": 0.17818446457386017,
|
| 267 |
+
"eval_precision": 0.6955396559598113,
|
| 268 |
+
"eval_recall": 0.7297556300910397,
|
| 269 |
+
"eval_runtime": 1.4738,
|
| 270 |
+
"eval_samples_per_second": 1300.036,
|
| 271 |
+
"eval_steps_per_second": 81.422,
|
| 272 |
+
"step": 1050
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.11,
|
| 276 |
+
"eval_accuracy": 0.9441277268832795,
|
| 277 |
+
"eval_f1": 0.7015257469802925,
|
| 278 |
+
"eval_loss": 0.18732576072216034,
|
| 279 |
+
"eval_precision": 0.6980863514154674,
|
| 280 |
+
"eval_recall": 0.7049992014055263,
|
| 281 |
+
"eval_runtime": 1.4745,
|
| 282 |
+
"eval_samples_per_second": 1299.388,
|
| 283 |
+
"eval_steps_per_second": 81.381,
|
| 284 |
+
"step": 1100
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.21,
|
| 288 |
+
"eval_accuracy": 0.9422493903644632,
|
| 289 |
+
"eval_f1": 0.6907414521705724,
|
| 290 |
+
"eval_loss": 0.19080577790737152,
|
| 291 |
+
"eval_precision": 0.6655315368670418,
|
| 292 |
+
"eval_recall": 0.7179364318798914,
|
| 293 |
+
"eval_runtime": 1.5005,
|
| 294 |
+
"eval_samples_per_second": 1276.934,
|
| 295 |
+
"eval_steps_per_second": 79.975,
|
| 296 |
+
"step": 1150
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.3,
|
| 300 |
+
"eval_accuracy": 0.945956633493706,
|
| 301 |
+
"eval_f1": 0.712525347059741,
|
| 302 |
+
"eval_loss": 0.181381955742836,
|
| 303 |
+
"eval_precision": 0.696235329980186,
|
| 304 |
+
"eval_recall": 0.7295959111962945,
|
| 305 |
+
"eval_runtime": 1.4739,
|
| 306 |
+
"eval_samples_per_second": 1299.963,
|
| 307 |
+
"eval_steps_per_second": 81.417,
|
| 308 |
+
"step": 1200
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.4,
|
| 312 |
+
"eval_accuracy": 0.9461873063995254,
|
| 313 |
+
"eval_f1": 0.7136230091232412,
|
| 314 |
+
"eval_loss": 0.17689131200313568,
|
| 315 |
+
"eval_precision": 0.6915929866626704,
|
| 316 |
+
"eval_recall": 0.7371026992493211,
|
| 317 |
+
"eval_runtime": 1.472,
|
| 318 |
+
"eval_samples_per_second": 1301.631,
|
| 319 |
+
"eval_steps_per_second": 81.522,
|
| 320 |
+
"step": 1250
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.5,
|
| 324 |
+
"eval_accuracy": 0.9468463718447242,
|
| 325 |
+
"eval_f1": 0.7252625760088447,
|
| 326 |
+
"eval_loss": 0.1800052374601364,
|
| 327 |
+
"eval_precision": 0.7172758512964699,
|
| 328 |
+
"eval_recall": 0.7334291646701805,
|
| 329 |
+
"eval_runtime": 1.4724,
|
| 330 |
+
"eval_samples_per_second": 1301.261,
|
| 331 |
+
"eval_steps_per_second": 81.499,
|
| 332 |
+
"step": 1300
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.59,
|
| 336 |
+
"eval_accuracy": 0.9469617082976339,
|
| 337 |
+
"eval_f1": 0.7245991396167384,
|
| 338 |
+
"eval_loss": 0.17777691781520844,
|
| 339 |
+
"eval_precision": 0.7099938687921521,
|
| 340 |
+
"eval_recall": 0.7398179204599904,
|
| 341 |
+
"eval_runtime": 1.4757,
|
| 342 |
+
"eval_samples_per_second": 1298.39,
|
| 343 |
+
"eval_steps_per_second": 81.319,
|
| 344 |
+
"step": 1350
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.69,
|
| 348 |
+
"eval_accuracy": 0.9473241942924933,
|
| 349 |
+
"eval_f1": 0.7241245438310427,
|
| 350 |
+
"eval_loss": 0.1745937019586563,
|
| 351 |
+
"eval_precision": 0.7045935327893623,
|
| 352 |
+
"eval_recall": 0.7447692061970931,
|
| 353 |
+
"eval_runtime": 1.5088,
|
| 354 |
+
"eval_samples_per_second": 1269.882,
|
| 355 |
+
"eval_steps_per_second": 79.533,
|
| 356 |
+
"step": 1400
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.78,
|
| 360 |
+
"eval_accuracy": 0.9480985961906018,
|
| 361 |
+
"eval_f1": 0.7267085687007716,
|
| 362 |
+
"eval_loss": 0.17996077239513397,
|
| 363 |
+
"eval_precision": 0.724001268230818,
|
| 364 |
+
"eval_recall": 0.7294361923015493,
|
| 365 |
+
"eval_runtime": 1.4708,
|
| 366 |
+
"eval_samples_per_second": 1302.711,
|
| 367 |
+
"eval_steps_per_second": 81.589,
|
| 368 |
+
"step": 1450
|
| 369 |
+
},
|
| 370 |
{
|
| 371 |
"epoch": 2.88,
|
| 372 |
+
"learning_rate": 1.4083493282149713e-05,
|
| 373 |
+
"loss": 0.083,
|
| 374 |
"step": 1500
|
| 375 |
},
|
| 376 |
{
|
| 377 |
+
"epoch": 2.88,
|
| 378 |
+
"eval_accuracy": 0.9467475120279444,
|
| 379 |
+
"eval_f1": 0.714475847490801,
|
| 380 |
+
"eval_loss": 0.1799446940422058,
|
| 381 |
+
"eval_precision": 0.7007063882063882,
|
| 382 |
+
"eval_recall": 0.7287973167225683,
|
| 383 |
+
"eval_runtime": 1.4712,
|
| 384 |
+
"eval_samples_per_second": 1302.299,
|
| 385 |
+
"eval_steps_per_second": 81.564,
|
| 386 |
+
"step": 1500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.98,
|
| 390 |
+
"eval_accuracy": 0.9470440914782838,
|
| 391 |
+
"eval_f1": 0.7189552956257009,
|
| 392 |
+
"eval_loss": 0.18403704464435577,
|
| 393 |
+
"eval_precision": 0.7212666773830574,
|
| 394 |
+
"eval_recall": 0.7166586807219294,
|
| 395 |
+
"eval_runtime": 1.4732,
|
| 396 |
+
"eval_samples_per_second": 1300.543,
|
| 397 |
+
"eval_steps_per_second": 81.454,
|
| 398 |
+
"step": 1550
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 3.07,
|
| 402 |
+
"eval_accuracy": 0.9481150728267317,
|
| 403 |
+
"eval_f1": 0.7218129404228059,
|
| 404 |
+
"eval_loss": 0.18616726994514465,
|
| 405 |
+
"eval_precision": 0.7237835233659868,
|
| 406 |
+
"eval_recall": 0.7198530586168344,
|
| 407 |
+
"eval_runtime": 1.4726,
|
| 408 |
+
"eval_samples_per_second": 1301.059,
|
| 409 |
+
"eval_steps_per_second": 81.486,
|
| 410 |
+
"step": 1600
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 3.17,
|
| 414 |
+
"eval_accuracy": 0.9484446055493311,
|
| 415 |
+
"eval_f1": 0.7236070954129874,
|
| 416 |
+
"eval_loss": 0.18031327426433563,
|
| 417 |
+
"eval_precision": 0.7083843329253366,
|
| 418 |
+
"eval_recall": 0.7394984826704999,
|
| 419 |
+
"eval_runtime": 1.5062,
|
| 420 |
+
"eval_samples_per_second": 1272.051,
|
| 421 |
+
"eval_steps_per_second": 79.669,
|
| 422 |
+
"step": 1650
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 3.26,
|
| 426 |
+
"eval_accuracy": 0.9472582877479734,
|
| 427 |
+
"eval_f1": 0.7165758509042092,
|
| 428 |
+
"eval_loss": 0.1847413182258606,
|
| 429 |
+
"eval_precision": 0.7086847860043737,
|
| 430 |
+
"eval_recall": 0.7246446254591918,
|
| 431 |
+
"eval_runtime": 1.4724,
|
| 432 |
+
"eval_samples_per_second": 1301.279,
|
| 433 |
+
"eval_steps_per_second": 81.5,
|
| 434 |
+
"step": 1700
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 3.36,
|
| 438 |
+
"eval_accuracy": 0.9482139326435115,
|
| 439 |
+
"eval_f1": 0.7222266150075118,
|
| 440 |
+
"eval_loss": 0.18235260248184204,
|
| 441 |
+
"eval_precision": 0.7151581584716568,
|
| 442 |
+
"eval_recall": 0.7294361923015493,
|
| 443 |
+
"eval_runtime": 1.4742,
|
| 444 |
+
"eval_samples_per_second": 1299.703,
|
| 445 |
+
"eval_steps_per_second": 81.401,
|
| 446 |
+
"step": 1750
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 3.45,
|
| 450 |
+
"eval_accuracy": 0.9486917550912806,
|
| 451 |
+
"eval_f1": 0.7286566227244193,
|
| 452 |
+
"eval_loss": 0.17917561531066895,
|
| 453 |
+
"eval_precision": 0.7161807805028536,
|
| 454 |
+
"eval_recall": 0.7415748283021881,
|
| 455 |
+
"eval_runtime": 1.4683,
|
| 456 |
+
"eval_samples_per_second": 1304.936,
|
| 457 |
+
"eval_steps_per_second": 81.729,
|
| 458 |
+
"step": 1800
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.55,
|
| 462 |
+
"eval_accuracy": 0.9481480260989916,
|
| 463 |
+
"eval_f1": 0.7228443887540136,
|
| 464 |
+
"eval_loss": 0.1824788898229599,
|
| 465 |
+
"eval_precision": 0.7091272280270436,
|
| 466 |
+
"eval_recall": 0.7371026992493211,
|
| 467 |
+
"eval_runtime": 1.471,
|
| 468 |
+
"eval_samples_per_second": 1302.492,
|
| 469 |
+
"eval_steps_per_second": 81.576,
|
| 470 |
+
"step": 1850
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 3.65,
|
| 474 |
+
"eval_accuracy": 0.9487411849996704,
|
| 475 |
+
"eval_f1": 0.7265369649805447,
|
| 476 |
+
"eval_loss": 0.17811530828475952,
|
| 477 |
+
"eval_precision": 0.708453483077857,
|
| 478 |
+
"eval_recall": 0.7455678006708194,
|
| 479 |
+
"eval_runtime": 1.5062,
|
| 480 |
+
"eval_samples_per_second": 1272.042,
|
| 481 |
+
"eval_steps_per_second": 79.669,
|
| 482 |
+
"step": 1900
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.74,
|
| 486 |
+
"eval_accuracy": 0.9482963158241613,
|
| 487 |
+
"eval_f1": 0.7255009823182711,
|
| 488 |
+
"eval_loss": 0.18192069232463837,
|
| 489 |
+
"eval_precision": 0.7141089108910891,
|
| 490 |
+
"eval_recall": 0.7372624181440665,
|
| 491 |
+
"eval_runtime": 1.4716,
|
| 492 |
+
"eval_samples_per_second": 1301.966,
|
| 493 |
+
"eval_steps_per_second": 81.543,
|
| 494 |
+
"step": 1950
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 3.84,
|
| 498 |
+
"learning_rate": 2.0873320537428026e-06,
|
| 499 |
+
"loss": 0.0639,
|
| 500 |
+
"step": 2000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.84,
|
| 504 |
+
"eval_accuracy": 0.9487576616358004,
|
| 505 |
+
"eval_f1": 0.7273722057214319,
|
| 506 |
+
"eval_loss": 0.17967551946640015,
|
| 507 |
+
"eval_precision": 0.7122302158273381,
|
| 508 |
+
"eval_recall": 0.7431720172496407,
|
| 509 |
+
"eval_runtime": 1.4718,
|
| 510 |
+
"eval_samples_per_second": 1301.808,
|
| 511 |
+
"eval_steps_per_second": 81.533,
|
| 512 |
+
"step": 2000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.93,
|
| 516 |
+
"eval_accuracy": 0.9482468859157714,
|
| 517 |
+
"eval_f1": 0.7234075810863619,
|
| 518 |
+
"eval_loss": 0.18143223226070404,
|
| 519 |
+
"eval_precision": 0.7082950719314356,
|
| 520 |
+
"eval_recall": 0.7391790448810094,
|
| 521 |
+
"eval_runtime": 1.4715,
|
| 522 |
+
"eval_samples_per_second": 1302.101,
|
| 523 |
+
"eval_steps_per_second": 81.551,
|
| 524 |
+
"step": 2050
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 4.0,
|
| 528 |
+
"step": 2084,
|
| 529 |
+
"total_flos": 20529237663360.0,
|
| 530 |
+
"train_loss": 0.1328041532904539,
|
| 531 |
+
"train_runtime": 90.5157,
|
| 532 |
+
"train_samples_per_second": 367.848,
|
| 533 |
+
"train_steps_per_second": 23.024
|
| 534 |
}
|
| 535 |
],
|
| 536 |
+
"max_steps": 2084,
|
| 537 |
+
"num_train_epochs": 4,
|
| 538 |
+
"total_flos": 20529237663360.0,
|
| 539 |
"trial_name": null,
|
| 540 |
"trial_params": null
|
| 541 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2863
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:415dd26e4c9bb86cdb797bec4f0ea4d492d7142400b45ffc20323abb9907ca27
|
| 3 |
size 2863
|