Training in progress, epoch 9
Browse files- checkpoint-1467/optimizer.pt +2 -2
- checkpoint-1467/pytorch_model.bin +1 -1
- checkpoint-1467/rng_state.pth +1 -1
- checkpoint-1467/scheduler.pt +1 -1
- checkpoint-1467/trainer_state.json +77 -77
- checkpoint-1467/training_args.bin +1 -1
- checkpoint-1630/optimizer.pt +2 -2
- checkpoint-1630/pytorch_model.bin +1 -1
- checkpoint-1630/rng_state.pth +1 -1
- checkpoint-1630/scheduler.pt +1 -1
- checkpoint-1630/trainer_state.json +85 -85
- checkpoint-1630/training_args.bin +1 -1
- pytorch_model.bin +1 -1
checkpoint-1467/optimizer.pt
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 sha256:27ff37e113e06eff1db241a9c3d07e590a00e217cfcbb8577767c193b7941dd1
|
| 3 |
+
size 2681485310
|
checkpoint-1467/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1340743917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa59b62075ac20c4333b546c0b025606a618273ec6b78f95fe165738d3a0f2af
|
| 3 |
size 1340743917
|
checkpoint-1467/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e36b0f788cfae254f69b987374e8eb7dea9d5f493b9011eb51e4135cc476bfda
|
| 3 |
size 14503
|
checkpoint-1467/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96405c1f878387bb6d62cce12f08fc3133dfd93159844cc7dba9f524f0c58020
|
| 3 |
size 623
|
checkpoint-1467/trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-
|
| 4 |
"epoch": 8.997323135755257,
|
| 5 |
"global_step": 1467,
|
| 6 |
"is_hyper_param_search": false,
|
|
@@ -9,152 +9,152 @@
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 163
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
-
"eval_accuracy": 0.
|
| 19 |
-
"eval_f1": 0.
|
| 20 |
-
"eval_loss": 0.
|
| 21 |
-
"eval_runtime":
|
| 22 |
-
"eval_samples_per_second":
|
| 23 |
-
"eval_steps_per_second": 32.
|
| 24 |
"step": 163
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 326
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 2.0,
|
| 34 |
-
"eval_accuracy": 0.
|
| 35 |
-
"eval_f1": 0.
|
| 36 |
-
"eval_loss": 0.
|
| 37 |
-
"eval_runtime": 9.
|
| 38 |
-
"eval_samples_per_second":
|
| 39 |
-
"eval_steps_per_second":
|
| 40 |
"step": 326
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"epoch": 3.0,
|
| 44 |
-
"learning_rate":
|
| 45 |
-
"loss": 0.
|
| 46 |
"step": 489
|
| 47 |
},
|
| 48 |
{
|
| 49 |
"epoch": 3.0,
|
| 50 |
-
"eval_accuracy": 0.
|
| 51 |
-
"eval_f1": 0.
|
| 52 |
-
"eval_loss": 0.
|
| 53 |
-
"eval_runtime": 9.
|
| 54 |
-
"eval_samples_per_second":
|
| 55 |
-
"eval_steps_per_second":
|
| 56 |
"step": 489
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 4.0,
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 652
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 4.0,
|
| 66 |
-
"eval_accuracy": 0.
|
| 67 |
-
"eval_f1": 0.
|
| 68 |
-
"eval_loss": 0.
|
| 69 |
-
"eval_runtime": 9.
|
| 70 |
-
"eval_samples_per_second":
|
| 71 |
-
"eval_steps_per_second":
|
| 72 |
"step": 652
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 5.0,
|
| 76 |
-
"learning_rate":
|
| 77 |
-
"loss": 0.
|
| 78 |
"step": 815
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 5.0,
|
| 82 |
-
"eval_accuracy": 0.
|
| 83 |
-
"eval_f1": 0.
|
| 84 |
-
"eval_loss": 0.
|
| 85 |
-
"eval_runtime":
|
| 86 |
-
"eval_samples_per_second":
|
| 87 |
-
"eval_steps_per_second":
|
| 88 |
"step": 815
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 6.0,
|
| 92 |
-
"learning_rate":
|
| 93 |
-
"loss": 0.
|
| 94 |
"step": 978
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 6.0,
|
| 98 |
-
"eval_accuracy": 0.
|
| 99 |
-
"eval_f1": 0.
|
| 100 |
-
"eval_loss": 0.
|
| 101 |
-
"eval_runtime": 9.
|
| 102 |
-
"eval_samples_per_second":
|
| 103 |
-
"eval_steps_per_second":
|
| 104 |
"step": 978
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 7.0,
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss": 0.
|
| 110 |
"step": 1141
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 7.0,
|
| 114 |
-
"eval_accuracy": 0.
|
| 115 |
-
"eval_f1": 0.
|
| 116 |
-
"eval_loss": 0.
|
| 117 |
-
"eval_runtime":
|
| 118 |
-
"eval_samples_per_second":
|
| 119 |
-
"eval_steps_per_second":
|
| 120 |
"step": 1141
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 8.0,
|
| 124 |
-
"learning_rate":
|
| 125 |
-
"loss": 0.
|
| 126 |
"step": 1304
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 8.0,
|
| 130 |
-
"eval_accuracy": 0.
|
| 131 |
-
"eval_f1": 0.
|
| 132 |
-
"eval_loss": 0.
|
| 133 |
-
"eval_runtime": 9.
|
| 134 |
-
"eval_samples_per_second":
|
| 135 |
-
"eval_steps_per_second":
|
| 136 |
"step": 1304
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 9.0,
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 1467
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 9.0,
|
| 146 |
-
"eval_accuracy": 0.
|
| 147 |
-
"eval_f1": 0.
|
| 148 |
-
"eval_loss": 0.
|
| 149 |
-
"eval_runtime": 9.
|
| 150 |
-
"eval_samples_per_second":
|
| 151 |
-
"eval_steps_per_second":
|
| 152 |
"step": 1467
|
| 153 |
}
|
| 154 |
],
|
| 155 |
-
"max_steps":
|
| 156 |
-
"num_train_epochs":
|
| 157 |
-
"total_flos": 2.
|
| 158 |
"trial_name": null,
|
| 159 |
"trial_params": null
|
| 160 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.29900965094566345,
|
| 3 |
+
"best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-1467",
|
| 4 |
"epoch": 8.997323135755257,
|
| 5 |
"global_step": 1467,
|
| 6 |
"is_hyper_param_search": false,
|
|
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 9e-07,
|
| 13 |
+
"loss": 0.439,
|
| 14 |
"step": 163
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.745697074010327,
|
| 19 |
+
"eval_f1": 0.732240056847258,
|
| 20 |
+
"eval_loss": 0.3982622027397156,
|
| 21 |
+
"eval_runtime": 8.9237,
|
| 22 |
+
"eval_samples_per_second": 260.431,
|
| 23 |
+
"eval_steps_per_second": 32.61,
|
| 24 |
"step": 163
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
+
"learning_rate": 8e-07,
|
| 29 |
+
"loss": 0.3465,
|
| 30 |
"step": 326
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.7620481927710844,
|
| 35 |
+
"eval_f1": 0.750740067157349,
|
| 36 |
+
"eval_loss": 0.3448249399662018,
|
| 37 |
+
"eval_runtime": 9.0059,
|
| 38 |
+
"eval_samples_per_second": 258.053,
|
| 39 |
+
"eval_steps_per_second": 32.312,
|
| 40 |
"step": 326
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"epoch": 3.0,
|
| 44 |
+
"learning_rate": 7e-07,
|
| 45 |
+
"loss": 0.3089,
|
| 46 |
"step": 489
|
| 47 |
},
|
| 48 |
{
|
| 49 |
"epoch": 3.0,
|
| 50 |
+
"eval_accuracy": 0.7693631669535284,
|
| 51 |
+
"eval_f1": 0.7633651185887134,
|
| 52 |
+
"eval_loss": 0.3303545117378235,
|
| 53 |
+
"eval_runtime": 9.3737,
|
| 54 |
+
"eval_samples_per_second": 247.927,
|
| 55 |
+
"eval_steps_per_second": 31.044,
|
| 56 |
"step": 489
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 4.0,
|
| 60 |
+
"learning_rate": 6e-07,
|
| 61 |
+
"loss": 0.2916,
|
| 62 |
"step": 652
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 4.0,
|
| 66 |
+
"eval_accuracy": 0.7839931153184165,
|
| 67 |
+
"eval_f1": 0.7736843738845695,
|
| 68 |
+
"eval_loss": 0.30892524123191833,
|
| 69 |
+
"eval_runtime": 9.0737,
|
| 70 |
+
"eval_samples_per_second": 256.125,
|
| 71 |
+
"eval_steps_per_second": 32.071,
|
| 72 |
"step": 652
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 5.0,
|
| 76 |
+
"learning_rate": 5e-07,
|
| 77 |
+
"loss": 0.2826,
|
| 78 |
"step": 815
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 5.0,
|
| 82 |
+
"eval_accuracy": 0.7839931153184165,
|
| 83 |
+
"eval_f1": 0.7744514636272033,
|
| 84 |
+
"eval_loss": 0.3055116832256317,
|
| 85 |
+
"eval_runtime": 9.1262,
|
| 86 |
+
"eval_samples_per_second": 254.651,
|
| 87 |
+
"eval_steps_per_second": 31.886,
|
| 88 |
"step": 815
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 6.0,
|
| 92 |
+
"learning_rate": 4e-07,
|
| 93 |
+
"loss": 0.2747,
|
| 94 |
"step": 978
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 6.0,
|
| 98 |
+
"eval_accuracy": 0.7857142857142857,
|
| 99 |
+
"eval_f1": 0.7771340101366444,
|
| 100 |
+
"eval_loss": 0.30407363176345825,
|
| 101 |
+
"eval_runtime": 9.1656,
|
| 102 |
+
"eval_samples_per_second": 253.557,
|
| 103 |
+
"eval_steps_per_second": 31.749,
|
| 104 |
"step": 978
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 7.0,
|
| 108 |
+
"learning_rate": 3e-07,
|
| 109 |
+
"loss": 0.2678,
|
| 110 |
"step": 1141
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 7.0,
|
| 114 |
+
"eval_accuracy": 0.7865748709122203,
|
| 115 |
+
"eval_f1": 0.7768983029852594,
|
| 116 |
+
"eval_loss": 0.3031200170516968,
|
| 117 |
+
"eval_runtime": 9.6529,
|
| 118 |
+
"eval_samples_per_second": 240.756,
|
| 119 |
+
"eval_steps_per_second": 30.146,
|
| 120 |
"step": 1141
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 8.0,
|
| 124 |
+
"learning_rate": 2e-07,
|
| 125 |
+
"loss": 0.2641,
|
| 126 |
"step": 1304
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 8.0,
|
| 130 |
+
"eval_accuracy": 0.7874354561101549,
|
| 131 |
+
"eval_f1": 0.7772050769924619,
|
| 132 |
+
"eval_loss": 0.3010457754135132,
|
| 133 |
+
"eval_runtime": 9.1465,
|
| 134 |
+
"eval_samples_per_second": 254.087,
|
| 135 |
+
"eval_steps_per_second": 31.816,
|
| 136 |
"step": 1304
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 9.0,
|
| 140 |
+
"learning_rate": 1e-07,
|
| 141 |
+
"loss": 0.2631,
|
| 142 |
"step": 1467
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 9.0,
|
| 146 |
+
"eval_accuracy": 0.7917383820998278,
|
| 147 |
+
"eval_f1": 0.7830140707046156,
|
| 148 |
+
"eval_loss": 0.29900965094566345,
|
| 149 |
+
"eval_runtime": 9.9577,
|
| 150 |
+
"eval_samples_per_second": 233.387,
|
| 151 |
+
"eval_steps_per_second": 29.224,
|
| 152 |
"step": 1467
|
| 153 |
}
|
| 154 |
],
|
| 155 |
+
"max_steps": 1630,
|
| 156 |
+
"num_train_epochs": 10,
|
| 157 |
+
"total_flos": 2.739683604981792e+16,
|
| 158 |
"trial_name": null,
|
| 159 |
"trial_params": null
|
| 160 |
}
|
checkpoint-1467/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3119
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd48e93c542d5f8f840918341d20dc98e6dbd60ec7052cf9f5610075d1655eaf
|
| 3 |
size 3119
|
checkpoint-1630/optimizer.pt
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 sha256:58949addab61a91ba7273887e0d81fb845296dc8d00ee4a1d5f426047707bd55
|
| 3 |
+
size 2681485310
|
checkpoint-1630/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1340743917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a94b56e1da42f00703387b7c987adc79cef5d650801e77d14a802f4e92301a9c
|
| 3 |
size 1340743917
|
checkpoint-1630/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d895ad69969472b320a4216795557386f8649e29cb20bf0cdadbc0088844bdcb
|
| 3 |
size 14503
|
checkpoint-1630/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c3e7a1b845fb89890dfefde14b31ecc3084465b9c0621dd07e0fdee41ef59fc
|
| 3 |
size 623
|
checkpoint-1630/trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-
|
| 4 |
"epoch": 9.997323135755257,
|
| 5 |
"global_step": 1630,
|
| 6 |
"is_hyper_param_search": false,
|
|
@@ -9,168 +9,168 @@
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 163
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
-
"eval_accuracy": 0.
|
| 19 |
-
"eval_f1": 0.
|
| 20 |
-
"eval_loss": 0.
|
| 21 |
-
"eval_runtime":
|
| 22 |
-
"eval_samples_per_second":
|
| 23 |
-
"eval_steps_per_second": 32.
|
| 24 |
"step": 163
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 326
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 2.0,
|
| 34 |
-
"eval_accuracy": 0.
|
| 35 |
-
"eval_f1": 0.
|
| 36 |
-
"eval_loss": 0.
|
| 37 |
-
"eval_runtime": 9.
|
| 38 |
-
"eval_samples_per_second":
|
| 39 |
-
"eval_steps_per_second":
|
| 40 |
"step": 326
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"epoch": 3.0,
|
| 44 |
-
"learning_rate":
|
| 45 |
-
"loss": 0.
|
| 46 |
"step": 489
|
| 47 |
},
|
| 48 |
{
|
| 49 |
"epoch": 3.0,
|
| 50 |
-
"eval_accuracy": 0.
|
| 51 |
-
"eval_f1": 0.
|
| 52 |
-
"eval_loss": 0.
|
| 53 |
-
"eval_runtime": 9.
|
| 54 |
-
"eval_samples_per_second":
|
| 55 |
-
"eval_steps_per_second":
|
| 56 |
"step": 489
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 4.0,
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 652
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 4.0,
|
| 66 |
-
"eval_accuracy": 0.
|
| 67 |
-
"eval_f1": 0.
|
| 68 |
-
"eval_loss": 0.
|
| 69 |
-
"eval_runtime": 9.
|
| 70 |
-
"eval_samples_per_second":
|
| 71 |
-
"eval_steps_per_second":
|
| 72 |
"step": 652
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 5.0,
|
| 76 |
-
"learning_rate":
|
| 77 |
-
"loss": 0.
|
| 78 |
"step": 815
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 5.0,
|
| 82 |
-
"eval_accuracy": 0.
|
| 83 |
-
"eval_f1": 0.
|
| 84 |
-
"eval_loss": 0.
|
| 85 |
-
"eval_runtime":
|
| 86 |
-
"eval_samples_per_second":
|
| 87 |
-
"eval_steps_per_second":
|
| 88 |
"step": 815
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 6.0,
|
| 92 |
-
"learning_rate":
|
| 93 |
-
"loss": 0.
|
| 94 |
"step": 978
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 6.0,
|
| 98 |
-
"eval_accuracy": 0.
|
| 99 |
-
"eval_f1": 0.
|
| 100 |
-
"eval_loss": 0.
|
| 101 |
-
"eval_runtime": 9.
|
| 102 |
-
"eval_samples_per_second":
|
| 103 |
-
"eval_steps_per_second":
|
| 104 |
"step": 978
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 7.0,
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss": 0.
|
| 110 |
"step": 1141
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 7.0,
|
| 114 |
-
"eval_accuracy": 0.
|
| 115 |
-
"eval_f1": 0.
|
| 116 |
-
"eval_loss": 0.
|
| 117 |
-
"eval_runtime":
|
| 118 |
-
"eval_samples_per_second":
|
| 119 |
-
"eval_steps_per_second":
|
| 120 |
"step": 1141
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 8.0,
|
| 124 |
-
"learning_rate":
|
| 125 |
-
"loss": 0.
|
| 126 |
"step": 1304
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 8.0,
|
| 130 |
-
"eval_accuracy": 0.
|
| 131 |
-
"eval_f1": 0.
|
| 132 |
-
"eval_loss": 0.
|
| 133 |
-
"eval_runtime": 9.
|
| 134 |
-
"eval_samples_per_second":
|
| 135 |
-
"eval_steps_per_second":
|
| 136 |
"step": 1304
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 9.0,
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 1467
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 9.0,
|
| 146 |
-
"eval_accuracy": 0.
|
| 147 |
-
"eval_f1": 0.
|
| 148 |
-
"eval_loss": 0.
|
| 149 |
-
"eval_runtime": 9.
|
| 150 |
-
"eval_samples_per_second":
|
| 151 |
-
"eval_steps_per_second":
|
| 152 |
"step": 1467
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 10.0,
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 1630
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 10.0,
|
| 162 |
-
"eval_accuracy": 0.
|
| 163 |
-
"eval_f1": 0.
|
| 164 |
-
"eval_loss": 0.
|
| 165 |
-
"eval_runtime": 9.
|
| 166 |
-
"eval_samples_per_second":
|
| 167 |
-
"eval_steps_per_second": 31.
|
| 168 |
"step": 1630
|
| 169 |
}
|
| 170 |
],
|
| 171 |
-
"max_steps":
|
| 172 |
-
"num_train_epochs":
|
| 173 |
-
"total_flos": 3.
|
| 174 |
"trial_name": null,
|
| 175 |
"trial_params": null
|
| 176 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.29900965094566345,
|
| 3 |
+
"best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-1467",
|
| 4 |
"epoch": 9.997323135755257,
|
| 5 |
"global_step": 1630,
|
| 6 |
"is_hyper_param_search": false,
|
|
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 1.0,
|
| 12 |
+
"learning_rate": 9e-07,
|
| 13 |
+
"loss": 0.439,
|
| 14 |
"step": 163
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
+
"eval_accuracy": 0.745697074010327,
|
| 19 |
+
"eval_f1": 0.732240056847258,
|
| 20 |
+
"eval_loss": 0.3982622027397156,
|
| 21 |
+
"eval_runtime": 8.9237,
|
| 22 |
+
"eval_samples_per_second": 260.431,
|
| 23 |
+
"eval_steps_per_second": 32.61,
|
| 24 |
"step": 163
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
+
"learning_rate": 8e-07,
|
| 29 |
+
"loss": 0.3465,
|
| 30 |
"step": 326
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 2.0,
|
| 34 |
+
"eval_accuracy": 0.7620481927710844,
|
| 35 |
+
"eval_f1": 0.750740067157349,
|
| 36 |
+
"eval_loss": 0.3448249399662018,
|
| 37 |
+
"eval_runtime": 9.0059,
|
| 38 |
+
"eval_samples_per_second": 258.053,
|
| 39 |
+
"eval_steps_per_second": 32.312,
|
| 40 |
"step": 326
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"epoch": 3.0,
|
| 44 |
+
"learning_rate": 7e-07,
|
| 45 |
+
"loss": 0.3089,
|
| 46 |
"step": 489
|
| 47 |
},
|
| 48 |
{
|
| 49 |
"epoch": 3.0,
|
| 50 |
+
"eval_accuracy": 0.7693631669535284,
|
| 51 |
+
"eval_f1": 0.7633651185887134,
|
| 52 |
+
"eval_loss": 0.3303545117378235,
|
| 53 |
+
"eval_runtime": 9.3737,
|
| 54 |
+
"eval_samples_per_second": 247.927,
|
| 55 |
+
"eval_steps_per_second": 31.044,
|
| 56 |
"step": 489
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 4.0,
|
| 60 |
+
"learning_rate": 6e-07,
|
| 61 |
+
"loss": 0.2916,
|
| 62 |
"step": 652
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 4.0,
|
| 66 |
+
"eval_accuracy": 0.7839931153184165,
|
| 67 |
+
"eval_f1": 0.7736843738845695,
|
| 68 |
+
"eval_loss": 0.30892524123191833,
|
| 69 |
+
"eval_runtime": 9.0737,
|
| 70 |
+
"eval_samples_per_second": 256.125,
|
| 71 |
+
"eval_steps_per_second": 32.071,
|
| 72 |
"step": 652
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 5.0,
|
| 76 |
+
"learning_rate": 5e-07,
|
| 77 |
+
"loss": 0.2826,
|
| 78 |
"step": 815
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 5.0,
|
| 82 |
+
"eval_accuracy": 0.7839931153184165,
|
| 83 |
+
"eval_f1": 0.7744514636272033,
|
| 84 |
+
"eval_loss": 0.3055116832256317,
|
| 85 |
+
"eval_runtime": 9.1262,
|
| 86 |
+
"eval_samples_per_second": 254.651,
|
| 87 |
+
"eval_steps_per_second": 31.886,
|
| 88 |
"step": 815
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 6.0,
|
| 92 |
+
"learning_rate": 4e-07,
|
| 93 |
+
"loss": 0.2747,
|
| 94 |
"step": 978
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"epoch": 6.0,
|
| 98 |
+
"eval_accuracy": 0.7857142857142857,
|
| 99 |
+
"eval_f1": 0.7771340101366444,
|
| 100 |
+
"eval_loss": 0.30407363176345825,
|
| 101 |
+
"eval_runtime": 9.1656,
|
| 102 |
+
"eval_samples_per_second": 253.557,
|
| 103 |
+
"eval_steps_per_second": 31.749,
|
| 104 |
"step": 978
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 7.0,
|
| 108 |
+
"learning_rate": 3e-07,
|
| 109 |
+
"loss": 0.2678,
|
| 110 |
"step": 1141
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 7.0,
|
| 114 |
+
"eval_accuracy": 0.7865748709122203,
|
| 115 |
+
"eval_f1": 0.7768983029852594,
|
| 116 |
+
"eval_loss": 0.3031200170516968,
|
| 117 |
+
"eval_runtime": 9.6529,
|
| 118 |
+
"eval_samples_per_second": 240.756,
|
| 119 |
+
"eval_steps_per_second": 30.146,
|
| 120 |
"step": 1141
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 8.0,
|
| 124 |
+
"learning_rate": 2e-07,
|
| 125 |
+
"loss": 0.2641,
|
| 126 |
"step": 1304
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 8.0,
|
| 130 |
+
"eval_accuracy": 0.7874354561101549,
|
| 131 |
+
"eval_f1": 0.7772050769924619,
|
| 132 |
+
"eval_loss": 0.3010457754135132,
|
| 133 |
+
"eval_runtime": 9.1465,
|
| 134 |
+
"eval_samples_per_second": 254.087,
|
| 135 |
+
"eval_steps_per_second": 31.816,
|
| 136 |
"step": 1304
|
| 137 |
},
|
| 138 |
{
|
| 139 |
"epoch": 9.0,
|
| 140 |
+
"learning_rate": 1e-07,
|
| 141 |
+
"loss": 0.2631,
|
| 142 |
"step": 1467
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 9.0,
|
| 146 |
+
"eval_accuracy": 0.7917383820998278,
|
| 147 |
+
"eval_f1": 0.7830140707046156,
|
| 148 |
+
"eval_loss": 0.29900965094566345,
|
| 149 |
+
"eval_runtime": 9.9577,
|
| 150 |
+
"eval_samples_per_second": 233.387,
|
| 151 |
+
"eval_steps_per_second": 29.224,
|
| 152 |
"step": 1467
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 10.0,
|
| 156 |
+
"learning_rate": 0.0,
|
| 157 |
+
"loss": 0.2615,
|
| 158 |
"step": 1630
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 10.0,
|
| 162 |
+
"eval_accuracy": 0.7895869191049913,
|
| 163 |
+
"eval_f1": 0.7804941506557442,
|
| 164 |
+
"eval_loss": 0.3004284203052521,
|
| 165 |
+
"eval_runtime": 9.1779,
|
| 166 |
+
"eval_samples_per_second": 253.217,
|
| 167 |
+
"eval_steps_per_second": 31.707,
|
| 168 |
"step": 1630
|
| 169 |
}
|
| 170 |
],
|
| 171 |
+
"max_steps": 1630,
|
| 172 |
+
"num_train_epochs": 10,
|
| 173 |
+
"total_flos": 3.0430166394980544e+16,
|
| 174 |
"trial_name": null,
|
| 175 |
"trial_params": null
|
| 176 |
}
|
checkpoint-1630/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3119
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd48e93c542d5f8f840918341d20dc98e6dbd60ec7052cf9f5610075d1655eaf
|
| 3 |
size 3119
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1340743917
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a94b56e1da42f00703387b7c987adc79cef5d650801e77d14a802f4e92301a9c
|
| 3 |
size 1340743917
|