Instructions to use cbrew475/mpnet-metric with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cbrew475/mpnet-metric with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="cbrew475/mpnet-metric")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("cbrew475/mpnet-metric") model = AutoModelForSequenceClassification.from_pretrained("cbrew475/mpnet-metric", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 200
Browse files- checkpoint-1200/optimizer.pt +1 -1
- checkpoint-1200/pytorch_model.bin +1 -1
- checkpoint-1200/scheduler.pt +1 -1
- checkpoint-1200/trainer_state.json +90 -90
- checkpoint-1200/training_args.bin +1 -1
- checkpoint-1400/optimizer.pt +1 -1
- checkpoint-1400/pytorch_model.bin +1 -1
- checkpoint-1400/scheduler.pt +1 -1
- checkpoint-1400/trainer_state.json +104 -104
- checkpoint-1400/training_args.bin +1 -1
- checkpoint-1600/optimizer.pt +1 -1
- checkpoint-1600/pytorch_model.bin +1 -1
- checkpoint-1600/scheduler.pt +1 -1
- checkpoint-1600/trainer_state.json +119 -119
- checkpoint-1600/training_args.bin +1 -1
- checkpoint-200/optimizer.pt +1 -1
- checkpoint-200/pytorch_model.bin +1 -1
- checkpoint-200/scheduler.pt +1 -1
- checkpoint-200/trainer_state.json +15 -15
- checkpoint-200/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
checkpoint-1200/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1762416361
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdfb14de85c5a258222b317f882a80b663ca21db65e33292ccec29d015530a52
|
| 3 |
size 1762416361
|
checkpoint-1200/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 440628841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e819bb724d3f1dbffdfc7ff2bc1757fa81edc40e914e82fc310574bef5a378b8
|
| 3 |
size 440628841
|
checkpoint-1200/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:fc218f9cd629f09ca27567dea3c1e1f10201cc0fa616e70f2ba55db610c4356f
|
| 3 |
size 623
|
checkpoint-1200/trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "mpnet-metric/checkpoint-
|
| 4 |
"epoch": 27.272727272727273,
|
| 5 |
"global_step": 1200,
|
| 6 |
"is_hyper_param_search": false,
|
|
@@ -9,146 +9,146 @@
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 2.27,
|
| 12 |
-
"eval_accuracy": 0.
|
| 13 |
-
"eval_f1": 0.
|
| 14 |
-
"eval_loss": 1.
|
| 15 |
-
"eval_matthews_correlation": 0.
|
| 16 |
-
"eval_runtime": 2.
|
| 17 |
-
"eval_samples_per_second":
|
| 18 |
-
"eval_steps_per_second":
|
| 19 |
"step": 100
|
| 20 |
},
|
| 21 |
{
|
| 22 |
"epoch": 4.55,
|
| 23 |
-
"eval_accuracy": 0.
|
| 24 |
-
"eval_f1": 0.
|
| 25 |
-
"eval_loss": 1.
|
| 26 |
-
"eval_matthews_correlation": 0.
|
| 27 |
-
"eval_runtime": 2.
|
| 28 |
-
"eval_samples_per_second":
|
| 29 |
-
"eval_steps_per_second":
|
| 30 |
"step": 200
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 6.82,
|
| 34 |
-
"eval_accuracy": 0.
|
| 35 |
-
"eval_f1": 0.
|
| 36 |
-
"eval_loss": 1.
|
| 37 |
-
"eval_matthews_correlation": 0.
|
| 38 |
-
"eval_runtime": 2.
|
| 39 |
-
"eval_samples_per_second":
|
| 40 |
-
"eval_steps_per_second":
|
| 41 |
"step": 300
|
| 42 |
},
|
| 43 |
{
|
| 44 |
"epoch": 9.09,
|
| 45 |
-
"eval_accuracy": 0.
|
| 46 |
-
"eval_f1": 0.
|
| 47 |
-
"eval_loss": 1.
|
| 48 |
-
"eval_matthews_correlation": 0.
|
| 49 |
-
"eval_runtime": 2.
|
| 50 |
-
"eval_samples_per_second":
|
| 51 |
-
"eval_steps_per_second": 9.
|
| 52 |
"step": 400
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 11.36,
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 1.
|
| 58 |
"step": 500
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 11.36,
|
| 62 |
-
"eval_accuracy": 0.
|
| 63 |
-
"eval_f1": 0.
|
| 64 |
-
"eval_loss": 1.
|
| 65 |
-
"eval_matthews_correlation": 0.
|
| 66 |
-
"eval_runtime": 2.
|
| 67 |
-
"eval_samples_per_second":
|
| 68 |
-
"eval_steps_per_second": 9.
|
| 69 |
"step": 500
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 13.64,
|
| 73 |
-
"eval_accuracy": 0.
|
| 74 |
-
"eval_f1": 0.
|
| 75 |
-
"eval_loss": 1.
|
| 76 |
-
"eval_matthews_correlation": 0.
|
| 77 |
-
"eval_runtime": 2.
|
| 78 |
-
"eval_samples_per_second":
|
| 79 |
-
"eval_steps_per_second": 9.
|
| 80 |
"step": 600
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 15.91,
|
| 84 |
-
"eval_accuracy": 0.
|
| 85 |
-
"eval_f1": 0.
|
| 86 |
-
"eval_loss": 1.
|
| 87 |
-
"eval_matthews_correlation": 0.
|
| 88 |
-
"eval_runtime": 2.
|
| 89 |
-
"eval_samples_per_second":
|
| 90 |
-
"eval_steps_per_second":
|
| 91 |
"step": 700
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 18.18,
|
| 95 |
-
"eval_accuracy": 0.
|
| 96 |
-
"eval_f1": 0.
|
| 97 |
-
"eval_loss": 1.
|
| 98 |
-
"eval_matthews_correlation": 0.
|
| 99 |
-
"eval_runtime": 2.
|
| 100 |
-
"eval_samples_per_second": 1416.
|
| 101 |
-
"eval_steps_per_second": 9.
|
| 102 |
"step": 800
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 20.45,
|
| 106 |
-
"eval_accuracy": 0.
|
| 107 |
-
"eval_f1": 0.
|
| 108 |
-
"eval_loss": 1.
|
| 109 |
-
"eval_matthews_correlation": 0.
|
| 110 |
-
"eval_runtime": 2.
|
| 111 |
-
"eval_samples_per_second":
|
| 112 |
-
"eval_steps_per_second": 9.
|
| 113 |
"step": 900
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 22.73,
|
| 117 |
-
"learning_rate":
|
| 118 |
-
"loss": 0.
|
| 119 |
"step": 1000
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 22.73,
|
| 123 |
-
"eval_accuracy": 0.
|
| 124 |
-
"eval_f1": 0.
|
| 125 |
-
"eval_loss": 1.
|
| 126 |
-
"eval_matthews_correlation": 0.
|
| 127 |
-
"eval_runtime": 2.
|
| 128 |
-
"eval_samples_per_second":
|
| 129 |
-
"eval_steps_per_second": 9.
|
| 130 |
"step": 1000
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 25.0,
|
| 134 |
-
"eval_accuracy": 0.
|
| 135 |
-
"eval_f1": 0.
|
| 136 |
-
"eval_loss": 1.
|
| 137 |
-
"eval_matthews_correlation": 0.
|
| 138 |
-
"eval_runtime": 2.
|
| 139 |
-
"eval_samples_per_second":
|
| 140 |
-
"eval_steps_per_second":
|
| 141 |
"step": 1100
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 27.27,
|
| 145 |
-
"eval_accuracy": 0.
|
| 146 |
-
"eval_f1": 0.
|
| 147 |
-
"eval_loss": 1.
|
| 148 |
-
"eval_matthews_correlation": 0.
|
| 149 |
-
"eval_runtime": 2.
|
| 150 |
-
"eval_samples_per_second":
|
| 151 |
-
"eval_steps_per_second": 9.
|
| 152 |
"step": 1200
|
| 153 |
}
|
| 154 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9256493506493506,
|
| 3 |
+
"best_model_checkpoint": "mpnet-metric/checkpoint-1000",
|
| 4 |
"epoch": 27.272727272727273,
|
| 5 |
"global_step": 1200,
|
| 6 |
"is_hyper_param_search": false,
|
|
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 2.27,
|
| 12 |
+
"eval_accuracy": 0.8168831168831169,
|
| 13 |
+
"eval_f1": 0.7526160112915868,
|
| 14 |
+
"eval_loss": 1.6600779294967651,
|
| 15 |
+
"eval_matthews_correlation": 0.8152410229901306,
|
| 16 |
+
"eval_runtime": 2.4316,
|
| 17 |
+
"eval_samples_per_second": 1266.672,
|
| 18 |
+
"eval_steps_per_second": 8.225,
|
| 19 |
"step": 100
|
| 20 |
},
|
| 21 |
{
|
| 22 |
"epoch": 4.55,
|
| 23 |
+
"eval_accuracy": 0.897077922077922,
|
| 24 |
+
"eval_f1": 0.8856257075703299,
|
| 25 |
+
"eval_loss": 1.4927222728729248,
|
| 26 |
+
"eval_matthews_correlation": 0.8957943237010111,
|
| 27 |
+
"eval_runtime": 2.2227,
|
| 28 |
+
"eval_samples_per_second": 1385.731,
|
| 29 |
+
"eval_steps_per_second": 8.998,
|
| 30 |
"step": 200
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 6.82,
|
| 34 |
+
"eval_accuracy": 0.9201298701298701,
|
| 35 |
+
"eval_f1": 0.9205225631693909,
|
| 36 |
+
"eval_loss": 1.5566294193267822,
|
| 37 |
+
"eval_matthews_correlation": 0.9190320812070084,
|
| 38 |
+
"eval_runtime": 2.1905,
|
| 39 |
+
"eval_samples_per_second": 1406.054,
|
| 40 |
+
"eval_steps_per_second": 9.13,
|
| 41 |
"step": 300
|
| 42 |
},
|
| 43 |
{
|
| 44 |
"epoch": 9.09,
|
| 45 |
+
"eval_accuracy": 0.912012987012987,
|
| 46 |
+
"eval_f1": 0.9120652244039835,
|
| 47 |
+
"eval_loss": 1.5064270496368408,
|
| 48 |
+
"eval_matthews_correlation": 0.910845237954562,
|
| 49 |
+
"eval_runtime": 2.0804,
|
| 50 |
+
"eval_samples_per_second": 1480.451,
|
| 51 |
+
"eval_steps_per_second": 9.613,
|
| 52 |
"step": 400
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 11.36,
|
| 56 |
+
"learning_rate": 7.143981790504036e-05,
|
| 57 |
+
"loss": 1.1713,
|
| 58 |
"step": 500
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 11.36,
|
| 62 |
+
"eval_accuracy": 0.9214285714285714,
|
| 63 |
+
"eval_f1": 0.9209415679460552,
|
| 64 |
+
"eval_loss": 1.6870453357696533,
|
| 65 |
+
"eval_matthews_correlation": 0.920369186542805,
|
| 66 |
+
"eval_runtime": 2.1662,
|
| 67 |
+
"eval_samples_per_second": 1421.817,
|
| 68 |
+
"eval_steps_per_second": 9.233,
|
| 69 |
"step": 500
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 13.64,
|
| 73 |
+
"eval_accuracy": 0.9198051948051948,
|
| 74 |
+
"eval_f1": 0.9197304127364558,
|
| 75 |
+
"eval_loss": 1.6187154054641724,
|
| 76 |
+
"eval_matthews_correlation": 0.918700976641645,
|
| 77 |
+
"eval_runtime": 2.0584,
|
| 78 |
+
"eval_samples_per_second": 1496.322,
|
| 79 |
+
"eval_steps_per_second": 9.716,
|
| 80 |
"step": 600
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 15.91,
|
| 84 |
+
"eval_accuracy": 0.9159090909090909,
|
| 85 |
+
"eval_f1": 0.9164948773151114,
|
| 86 |
+
"eval_loss": 1.6880903244018555,
|
| 87 |
+
"eval_matthews_correlation": 0.9148059546508341,
|
| 88 |
+
"eval_runtime": 2.255,
|
| 89 |
+
"eval_samples_per_second": 1365.875,
|
| 90 |
+
"eval_steps_per_second": 8.869,
|
| 91 |
"step": 700
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 18.18,
|
| 95 |
+
"eval_accuracy": 0.9172077922077922,
|
| 96 |
+
"eval_f1": 0.9171466545500319,
|
| 97 |
+
"eval_loss": 1.6939719915390015,
|
| 98 |
+
"eval_matthews_correlation": 0.9160846990725676,
|
| 99 |
+
"eval_runtime": 2.1751,
|
| 100 |
+
"eval_samples_per_second": 1416.047,
|
| 101 |
+
"eval_steps_per_second": 9.195,
|
| 102 |
"step": 800
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 20.45,
|
| 106 |
+
"eval_accuracy": 0.9237012987012987,
|
| 107 |
+
"eval_f1": 0.9228068483209093,
|
| 108 |
+
"eval_loss": 1.827225685119629,
|
| 109 |
+
"eval_matthews_correlation": 0.9226697076696465,
|
| 110 |
+
"eval_runtime": 2.0546,
|
| 111 |
+
"eval_samples_per_second": 1499.088,
|
| 112 |
+
"eval_steps_per_second": 9.734,
|
| 113 |
"step": 900
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 22.73,
|
| 117 |
+
"learning_rate": 4.309068381573863e-05,
|
| 118 |
+
"loss": 0.3851,
|
| 119 |
"step": 1000
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 22.73,
|
| 123 |
+
"eval_accuracy": 0.9256493506493506,
|
| 124 |
+
"eval_f1": 0.924610487019518,
|
| 125 |
+
"eval_loss": 1.752126932144165,
|
| 126 |
+
"eval_matthews_correlation": 0.9246248223527813,
|
| 127 |
+
"eval_runtime": 2.1963,
|
| 128 |
+
"eval_samples_per_second": 1402.379,
|
| 129 |
+
"eval_steps_per_second": 9.106,
|
| 130 |
"step": 1000
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 25.0,
|
| 134 |
+
"eval_accuracy": 0.9227272727272727,
|
| 135 |
+
"eval_f1": 0.9224489868001543,
|
| 136 |
+
"eval_loss": 1.8111803531646729,
|
| 137 |
+
"eval_matthews_correlation": 0.9216666198601385,
|
| 138 |
+
"eval_runtime": 2.2202,
|
| 139 |
+
"eval_samples_per_second": 1387.252,
|
| 140 |
+
"eval_steps_per_second": 9.008,
|
| 141 |
"step": 1100
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 27.27,
|
| 145 |
+
"eval_accuracy": 0.924025974025974,
|
| 146 |
+
"eval_f1": 0.9235055742877311,
|
| 147 |
+
"eval_loss": 1.8154934644699097,
|
| 148 |
+
"eval_matthews_correlation": 0.9229953706448562,
|
| 149 |
+
"eval_runtime": 2.1795,
|
| 150 |
+
"eval_samples_per_second": 1413.141,
|
| 151 |
+
"eval_steps_per_second": 9.176,
|
| 152 |
"step": 1200
|
| 153 |
}
|
| 154 |
],
|
checkpoint-1200/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2927
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fe18383a394371aab9808aba1f4950c63c76fd24cef71575ffa768824cc29b5
|
| 3 |
size 2927
|
checkpoint-1400/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1762416361
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc72dc678da0d7aeedd1429a7c22438d98743d42aded82b7477273ae0890204d
|
| 3 |
size 1762416361
|
checkpoint-1400/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 440628841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:448231487e8e885b9da0faf94b2c744c8a7750fe206d64573875c2a4fa87488c
|
| 3 |
size 440628841
|
checkpoint-1400/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 sha256:5e0433ac814c8e490bc1cba0907fa3d6e23d0cc5bb6b5d5182479419d1d89fae
|
| 3 |
size 623
|
checkpoint-1400/trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "mpnet-metric/checkpoint-
|
| 4 |
"epoch": 31.818181818181817,
|
| 5 |
"global_step": 1400,
|
| 6 |
"is_hyper_param_search": false,
|
|
@@ -9,168 +9,168 @@
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 2.27,
|
| 12 |
-
"eval_accuracy": 0.
|
| 13 |
-
"eval_f1": 0.
|
| 14 |
-
"eval_loss": 1.
|
| 15 |
-
"eval_matthews_correlation": 0.
|
| 16 |
-
"eval_runtime": 2.
|
| 17 |
-
"eval_samples_per_second":
|
| 18 |
-
"eval_steps_per_second":
|
| 19 |
"step": 100
|
| 20 |
},
|
| 21 |
{
|
| 22 |
"epoch": 4.55,
|
| 23 |
-
"eval_accuracy": 0.
|
| 24 |
-
"eval_f1": 0.
|
| 25 |
-
"eval_loss": 1.
|
| 26 |
-
"eval_matthews_correlation": 0.
|
| 27 |
-
"eval_runtime": 2.
|
| 28 |
-
"eval_samples_per_second":
|
| 29 |
-
"eval_steps_per_second":
|
| 30 |
"step": 200
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 6.82,
|
| 34 |
-
"eval_accuracy": 0.
|
| 35 |
-
"eval_f1": 0.
|
| 36 |
-
"eval_loss": 1.
|
| 37 |
-
"eval_matthews_correlation": 0.
|
| 38 |
-
"eval_runtime": 2.
|
| 39 |
-
"eval_samples_per_second":
|
| 40 |
-
"eval_steps_per_second":
|
| 41 |
"step": 300
|
| 42 |
},
|
| 43 |
{
|
| 44 |
"epoch": 9.09,
|
| 45 |
-
"eval_accuracy": 0.
|
| 46 |
-
"eval_f1": 0.
|
| 47 |
-
"eval_loss": 1.
|
| 48 |
-
"eval_matthews_correlation": 0.
|
| 49 |
-
"eval_runtime": 2.
|
| 50 |
-
"eval_samples_per_second":
|
| 51 |
-
"eval_steps_per_second": 9.
|
| 52 |
"step": 400
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 11.36,
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 1.
|
| 58 |
"step": 500
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 11.36,
|
| 62 |
-
"eval_accuracy": 0.
|
| 63 |
-
"eval_f1": 0.
|
| 64 |
-
"eval_loss": 1.
|
| 65 |
-
"eval_matthews_correlation": 0.
|
| 66 |
-
"eval_runtime": 2.
|
| 67 |
-
"eval_samples_per_second":
|
| 68 |
-
"eval_steps_per_second": 9.
|
| 69 |
"step": 500
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 13.64,
|
| 73 |
-
"eval_accuracy": 0.
|
| 74 |
-
"eval_f1": 0.
|
| 75 |
-
"eval_loss": 1.
|
| 76 |
-
"eval_matthews_correlation": 0.
|
| 77 |
-
"eval_runtime": 2.
|
| 78 |
-
"eval_samples_per_second":
|
| 79 |
-
"eval_steps_per_second": 9.
|
| 80 |
"step": 600
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 15.91,
|
| 84 |
-
"eval_accuracy": 0.
|
| 85 |
-
"eval_f1": 0.
|
| 86 |
-
"eval_loss": 1.
|
| 87 |
-
"eval_matthews_correlation": 0.
|
| 88 |
-
"eval_runtime": 2.
|
| 89 |
-
"eval_samples_per_second":
|
| 90 |
-
"eval_steps_per_second":
|
| 91 |
"step": 700
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 18.18,
|
| 95 |
-
"eval_accuracy": 0.
|
| 96 |
-
"eval_f1": 0.
|
| 97 |
-
"eval_loss": 1.
|
| 98 |
-
"eval_matthews_correlation": 0.
|
| 99 |
-
"eval_runtime": 2.
|
| 100 |
-
"eval_samples_per_second": 1416.
|
| 101 |
-
"eval_steps_per_second": 9.
|
| 102 |
"step": 800
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 20.45,
|
| 106 |
-
"eval_accuracy": 0.
|
| 107 |
-
"eval_f1": 0.
|
| 108 |
-
"eval_loss": 1.
|
| 109 |
-
"eval_matthews_correlation": 0.
|
| 110 |
-
"eval_runtime": 2.
|
| 111 |
-
"eval_samples_per_second":
|
| 112 |
-
"eval_steps_per_second": 9.
|
| 113 |
"step": 900
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 22.73,
|
| 117 |
-
"learning_rate":
|
| 118 |
-
"loss": 0.
|
| 119 |
"step": 1000
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 22.73,
|
| 123 |
-
"eval_accuracy": 0.
|
| 124 |
-
"eval_f1": 0.
|
| 125 |
-
"eval_loss": 1.
|
| 126 |
-
"eval_matthews_correlation": 0.
|
| 127 |
-
"eval_runtime": 2.
|
| 128 |
-
"eval_samples_per_second":
|
| 129 |
-
"eval_steps_per_second": 9.
|
| 130 |
"step": 1000
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 25.0,
|
| 134 |
-
"eval_accuracy": 0.
|
| 135 |
-
"eval_f1": 0.
|
| 136 |
-
"eval_loss": 1.
|
| 137 |
-
"eval_matthews_correlation": 0.
|
| 138 |
-
"eval_runtime": 2.
|
| 139 |
-
"eval_samples_per_second":
|
| 140 |
-
"eval_steps_per_second":
|
| 141 |
"step": 1100
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 27.27,
|
| 145 |
-
"eval_accuracy": 0.
|
| 146 |
-
"eval_f1": 0.
|
| 147 |
-
"eval_loss": 1.
|
| 148 |
-
"eval_matthews_correlation": 0.
|
| 149 |
-
"eval_runtime": 2.
|
| 150 |
-
"eval_samples_per_second":
|
| 151 |
-
"eval_steps_per_second": 9.
|
| 152 |
"step": 1200
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 29.55,
|
| 156 |
-
"eval_accuracy": 0.
|
| 157 |
-
"eval_f1": 0.
|
| 158 |
-
"eval_loss": 1.
|
| 159 |
-
"eval_matthews_correlation": 0.
|
| 160 |
-
"eval_runtime": 2.
|
| 161 |
-
"eval_samples_per_second":
|
| 162 |
-
"eval_steps_per_second": 9.
|
| 163 |
"step": 1300
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 31.82,
|
| 167 |
-
"eval_accuracy": 0.
|
| 168 |
-
"eval_f1": 0.
|
| 169 |
-
"eval_loss": 1.
|
| 170 |
-
"eval_matthews_correlation": 0.
|
| 171 |
-
"eval_runtime": 2.
|
| 172 |
-
"eval_samples_per_second":
|
| 173 |
-
"eval_steps_per_second": 9.
|
| 174 |
"step": 1400
|
| 175 |
}
|
| 176 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.926948051948052,
|
| 3 |
+
"best_model_checkpoint": "mpnet-metric/checkpoint-1400",
|
| 4 |
"epoch": 31.818181818181817,
|
| 5 |
"global_step": 1400,
|
| 6 |
"is_hyper_param_search": false,
|
|
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 2.27,
|
| 12 |
+
"eval_accuracy": 0.8168831168831169,
|
| 13 |
+
"eval_f1": 0.7526160112915868,
|
| 14 |
+
"eval_loss": 1.6600779294967651,
|
| 15 |
+
"eval_matthews_correlation": 0.8152410229901306,
|
| 16 |
+
"eval_runtime": 2.4316,
|
| 17 |
+
"eval_samples_per_second": 1266.672,
|
| 18 |
+
"eval_steps_per_second": 8.225,
|
| 19 |
"step": 100
|
| 20 |
},
|
| 21 |
{
|
| 22 |
"epoch": 4.55,
|
| 23 |
+
"eval_accuracy": 0.897077922077922,
|
| 24 |
+
"eval_f1": 0.8856257075703299,
|
| 25 |
+
"eval_loss": 1.4927222728729248,
|
| 26 |
+
"eval_matthews_correlation": 0.8957943237010111,
|
| 27 |
+
"eval_runtime": 2.2227,
|
| 28 |
+
"eval_samples_per_second": 1385.731,
|
| 29 |
+
"eval_steps_per_second": 8.998,
|
| 30 |
"step": 200
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 6.82,
|
| 34 |
+
"eval_accuracy": 0.9201298701298701,
|
| 35 |
+
"eval_f1": 0.9205225631693909,
|
| 36 |
+
"eval_loss": 1.5566294193267822,
|
| 37 |
+
"eval_matthews_correlation": 0.9190320812070084,
|
| 38 |
+
"eval_runtime": 2.1905,
|
| 39 |
+
"eval_samples_per_second": 1406.054,
|
| 40 |
+
"eval_steps_per_second": 9.13,
|
| 41 |
"step": 300
|
| 42 |
},
|
| 43 |
{
|
| 44 |
"epoch": 9.09,
|
| 45 |
+
"eval_accuracy": 0.912012987012987,
|
| 46 |
+
"eval_f1": 0.9120652244039835,
|
| 47 |
+
"eval_loss": 1.5064270496368408,
|
| 48 |
+
"eval_matthews_correlation": 0.910845237954562,
|
| 49 |
+
"eval_runtime": 2.0804,
|
| 50 |
+
"eval_samples_per_second": 1480.451,
|
| 51 |
+
"eval_steps_per_second": 9.613,
|
| 52 |
"step": 400
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 11.36,
|
| 56 |
+
"learning_rate": 7.143981790504036e-05,
|
| 57 |
+
"loss": 1.1713,
|
| 58 |
"step": 500
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 11.36,
|
| 62 |
+
"eval_accuracy": 0.9214285714285714,
|
| 63 |
+
"eval_f1": 0.9209415679460552,
|
| 64 |
+
"eval_loss": 1.6870453357696533,
|
| 65 |
+
"eval_matthews_correlation": 0.920369186542805,
|
| 66 |
+
"eval_runtime": 2.1662,
|
| 67 |
+
"eval_samples_per_second": 1421.817,
|
| 68 |
+
"eval_steps_per_second": 9.233,
|
| 69 |
"step": 500
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 13.64,
|
| 73 |
+
"eval_accuracy": 0.9198051948051948,
|
| 74 |
+
"eval_f1": 0.9197304127364558,
|
| 75 |
+
"eval_loss": 1.6187154054641724,
|
| 76 |
+
"eval_matthews_correlation": 0.918700976641645,
|
| 77 |
+
"eval_runtime": 2.0584,
|
| 78 |
+
"eval_samples_per_second": 1496.322,
|
| 79 |
+
"eval_steps_per_second": 9.716,
|
| 80 |
"step": 600
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 15.91,
|
| 84 |
+
"eval_accuracy": 0.9159090909090909,
|
| 85 |
+
"eval_f1": 0.9164948773151114,
|
| 86 |
+
"eval_loss": 1.6880903244018555,
|
| 87 |
+
"eval_matthews_correlation": 0.9148059546508341,
|
| 88 |
+
"eval_runtime": 2.255,
|
| 89 |
+
"eval_samples_per_second": 1365.875,
|
| 90 |
+
"eval_steps_per_second": 8.869,
|
| 91 |
"step": 700
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 18.18,
|
| 95 |
+
"eval_accuracy": 0.9172077922077922,
|
| 96 |
+
"eval_f1": 0.9171466545500319,
|
| 97 |
+
"eval_loss": 1.6939719915390015,
|
| 98 |
+
"eval_matthews_correlation": 0.9160846990725676,
|
| 99 |
+
"eval_runtime": 2.1751,
|
| 100 |
+
"eval_samples_per_second": 1416.047,
|
| 101 |
+
"eval_steps_per_second": 9.195,
|
| 102 |
"step": 800
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 20.45,
|
| 106 |
+
"eval_accuracy": 0.9237012987012987,
|
| 107 |
+
"eval_f1": 0.9228068483209093,
|
| 108 |
+
"eval_loss": 1.827225685119629,
|
| 109 |
+
"eval_matthews_correlation": 0.9226697076696465,
|
| 110 |
+
"eval_runtime": 2.0546,
|
| 111 |
+
"eval_samples_per_second": 1499.088,
|
| 112 |
+
"eval_steps_per_second": 9.734,
|
| 113 |
"step": 900
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 22.73,
|
| 117 |
+
"learning_rate": 4.309068381573863e-05,
|
| 118 |
+
"loss": 0.3851,
|
| 119 |
"step": 1000
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 22.73,
|
| 123 |
+
"eval_accuracy": 0.9256493506493506,
|
| 124 |
+
"eval_f1": 0.924610487019518,
|
| 125 |
+
"eval_loss": 1.752126932144165,
|
| 126 |
+
"eval_matthews_correlation": 0.9246248223527813,
|
| 127 |
+
"eval_runtime": 2.1963,
|
| 128 |
+
"eval_samples_per_second": 1402.379,
|
| 129 |
+
"eval_steps_per_second": 9.106,
|
| 130 |
"step": 1000
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 25.0,
|
| 134 |
+
"eval_accuracy": 0.9227272727272727,
|
| 135 |
+
"eval_f1": 0.9224489868001543,
|
| 136 |
+
"eval_loss": 1.8111803531646729,
|
| 137 |
+
"eval_matthews_correlation": 0.9216666198601385,
|
| 138 |
+
"eval_runtime": 2.2202,
|
| 139 |
+
"eval_samples_per_second": 1387.252,
|
| 140 |
+
"eval_steps_per_second": 9.008,
|
| 141 |
"step": 1100
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 27.27,
|
| 145 |
+
"eval_accuracy": 0.924025974025974,
|
| 146 |
+
"eval_f1": 0.9235055742877311,
|
| 147 |
+
"eval_loss": 1.8154934644699097,
|
| 148 |
+
"eval_matthews_correlation": 0.9229953706448562,
|
| 149 |
+
"eval_runtime": 2.1795,
|
| 150 |
+
"eval_samples_per_second": 1413.141,
|
| 151 |
+
"eval_steps_per_second": 9.176,
|
| 152 |
"step": 1200
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 29.55,
|
| 156 |
+
"eval_accuracy": 0.925974025974026,
|
| 157 |
+
"eval_f1": 0.9250491597779087,
|
| 158 |
+
"eval_loss": 1.8494137525558472,
|
| 159 |
+
"eval_matthews_correlation": 0.9249617346684725,
|
| 160 |
+
"eval_runtime": 2.1532,
|
| 161 |
+
"eval_samples_per_second": 1430.445,
|
| 162 |
+
"eval_steps_per_second": 9.289,
|
| 163 |
"step": 1300
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 31.82,
|
| 167 |
+
"eval_accuracy": 0.926948051948052,
|
| 168 |
+
"eval_f1": 0.9263712922428582,
|
| 169 |
+
"eval_loss": 1.845504641532898,
|
| 170 |
+
"eval_matthews_correlation": 0.925946513781978,
|
| 171 |
+
"eval_runtime": 2.0321,
|
| 172 |
+
"eval_samples_per_second": 1515.7,
|
| 173 |
+
"eval_steps_per_second": 9.842,
|
| 174 |
"step": 1400
|
| 175 |
}
|
| 176 |
],
|
checkpoint-1400/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2927
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fe18383a394371aab9808aba1f4950c63c76fd24cef71575ffa768824cc29b5
|
| 3 |
size 2927
|
checkpoint-1600/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1762416361
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f67a75074cf83a02b5c28f5dd1893c75a67db34abb973c2f381df508be1b19f
|
| 3 |
size 1762416361
|
checkpoint-1600/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 440628841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2955a53f1f98b08cdd7181fd3a3127a37549e31bf31592b14205f5a01e0a0b7b
|
| 3 |
size 440628841
|
checkpoint-1600/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:cf9a234b21a74bb8cab1c8ff195279b444caa9b2dcd39b87cf49e883531ecfe1
|
| 3 |
size 623
|
checkpoint-1600/trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "mpnet-metric/checkpoint-
|
| 4 |
"epoch": 36.36363636363637,
|
| 5 |
"global_step": 1600,
|
| 6 |
"is_hyper_param_search": false,
|
|
@@ -9,196 +9,196 @@
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 2.27,
|
| 12 |
-
"eval_accuracy": 0.
|
| 13 |
-
"eval_f1": 0.
|
| 14 |
-
"eval_loss": 1.
|
| 15 |
-
"eval_matthews_correlation": 0.
|
| 16 |
-
"eval_runtime": 2.
|
| 17 |
-
"eval_samples_per_second":
|
| 18 |
-
"eval_steps_per_second":
|
| 19 |
"step": 100
|
| 20 |
},
|
| 21 |
{
|
| 22 |
"epoch": 4.55,
|
| 23 |
-
"eval_accuracy": 0.
|
| 24 |
-
"eval_f1": 0.
|
| 25 |
-
"eval_loss": 1.
|
| 26 |
-
"eval_matthews_correlation": 0.
|
| 27 |
-
"eval_runtime": 2.
|
| 28 |
-
"eval_samples_per_second":
|
| 29 |
-
"eval_steps_per_second":
|
| 30 |
"step": 200
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 6.82,
|
| 34 |
-
"eval_accuracy": 0.
|
| 35 |
-
"eval_f1": 0.
|
| 36 |
-
"eval_loss": 1.
|
| 37 |
-
"eval_matthews_correlation": 0.
|
| 38 |
-
"eval_runtime": 2.
|
| 39 |
-
"eval_samples_per_second":
|
| 40 |
-
"eval_steps_per_second":
|
| 41 |
"step": 300
|
| 42 |
},
|
| 43 |
{
|
| 44 |
"epoch": 9.09,
|
| 45 |
-
"eval_accuracy": 0.
|
| 46 |
-
"eval_f1": 0.
|
| 47 |
-
"eval_loss": 1.
|
| 48 |
-
"eval_matthews_correlation": 0.
|
| 49 |
-
"eval_runtime": 2.
|
| 50 |
-
"eval_samples_per_second":
|
| 51 |
-
"eval_steps_per_second": 9.
|
| 52 |
"step": 400
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 11.36,
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 1.
|
| 58 |
"step": 500
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 11.36,
|
| 62 |
-
"eval_accuracy": 0.
|
| 63 |
-
"eval_f1": 0.
|
| 64 |
-
"eval_loss": 1.
|
| 65 |
-
"eval_matthews_correlation": 0.
|
| 66 |
-
"eval_runtime": 2.
|
| 67 |
-
"eval_samples_per_second":
|
| 68 |
-
"eval_steps_per_second": 9.
|
| 69 |
"step": 500
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 13.64,
|
| 73 |
-
"eval_accuracy": 0.
|
| 74 |
-
"eval_f1": 0.
|
| 75 |
-
"eval_loss": 1.
|
| 76 |
-
"eval_matthews_correlation": 0.
|
| 77 |
-
"eval_runtime": 2.
|
| 78 |
-
"eval_samples_per_second":
|
| 79 |
-
"eval_steps_per_second": 9.
|
| 80 |
"step": 600
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 15.91,
|
| 84 |
-
"eval_accuracy": 0.
|
| 85 |
-
"eval_f1": 0.
|
| 86 |
-
"eval_loss": 1.
|
| 87 |
-
"eval_matthews_correlation": 0.
|
| 88 |
-
"eval_runtime": 2.
|
| 89 |
-
"eval_samples_per_second":
|
| 90 |
-
"eval_steps_per_second":
|
| 91 |
"step": 700
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 18.18,
|
| 95 |
-
"eval_accuracy": 0.
|
| 96 |
-
"eval_f1": 0.
|
| 97 |
-
"eval_loss": 1.
|
| 98 |
-
"eval_matthews_correlation": 0.
|
| 99 |
-
"eval_runtime": 2.
|
| 100 |
-
"eval_samples_per_second": 1416.
|
| 101 |
-
"eval_steps_per_second": 9.
|
| 102 |
"step": 800
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 20.45,
|
| 106 |
-
"eval_accuracy": 0.
|
| 107 |
-
"eval_f1": 0.
|
| 108 |
-
"eval_loss": 1.
|
| 109 |
-
"eval_matthews_correlation": 0.
|
| 110 |
-
"eval_runtime": 2.
|
| 111 |
-
"eval_samples_per_second":
|
| 112 |
-
"eval_steps_per_second": 9.
|
| 113 |
"step": 900
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 22.73,
|
| 117 |
-
"learning_rate":
|
| 118 |
-
"loss": 0.
|
| 119 |
"step": 1000
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 22.73,
|
| 123 |
-
"eval_accuracy": 0.
|
| 124 |
-
"eval_f1": 0.
|
| 125 |
-
"eval_loss": 1.
|
| 126 |
-
"eval_matthews_correlation": 0.
|
| 127 |
-
"eval_runtime": 2.
|
| 128 |
-
"eval_samples_per_second":
|
| 129 |
-
"eval_steps_per_second": 9.
|
| 130 |
"step": 1000
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 25.0,
|
| 134 |
-
"eval_accuracy": 0.
|
| 135 |
-
"eval_f1": 0.
|
| 136 |
-
"eval_loss": 1.
|
| 137 |
-
"eval_matthews_correlation": 0.
|
| 138 |
-
"eval_runtime": 2.
|
| 139 |
-
"eval_samples_per_second":
|
| 140 |
-
"eval_steps_per_second":
|
| 141 |
"step": 1100
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 27.27,
|
| 145 |
-
"eval_accuracy": 0.
|
| 146 |
-
"eval_f1": 0.
|
| 147 |
-
"eval_loss": 1.
|
| 148 |
-
"eval_matthews_correlation": 0.
|
| 149 |
-
"eval_runtime": 2.
|
| 150 |
-
"eval_samples_per_second":
|
| 151 |
-
"eval_steps_per_second": 9.
|
| 152 |
"step": 1200
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 29.55,
|
| 156 |
-
"eval_accuracy": 0.
|
| 157 |
-
"eval_f1": 0.
|
| 158 |
-
"eval_loss": 1.
|
| 159 |
-
"eval_matthews_correlation": 0.
|
| 160 |
-
"eval_runtime": 2.
|
| 161 |
-
"eval_samples_per_second":
|
| 162 |
-
"eval_steps_per_second": 9.
|
| 163 |
"step": 1300
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 31.82,
|
| 167 |
-
"eval_accuracy": 0.
|
| 168 |
-
"eval_f1": 0.
|
| 169 |
-
"eval_loss": 1.
|
| 170 |
-
"eval_matthews_correlation": 0.
|
| 171 |
-
"eval_runtime": 2.
|
| 172 |
-
"eval_samples_per_second":
|
| 173 |
-
"eval_steps_per_second": 9.
|
| 174 |
"step": 1400
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 34.09,
|
| 178 |
-
"learning_rate":
|
| 179 |
-
"loss": 0.
|
| 180 |
"step": 1500
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 34.09,
|
| 184 |
"eval_accuracy": 0.9256493506493506,
|
| 185 |
-
"eval_f1": 0.
|
| 186 |
-
"eval_loss": 1.
|
| 187 |
-
"eval_matthews_correlation": 0.
|
| 188 |
-
"eval_runtime": 2.
|
| 189 |
-
"eval_samples_per_second":
|
| 190 |
-
"eval_steps_per_second": 9.
|
| 191 |
"step": 1500
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 36.36,
|
| 195 |
-
"eval_accuracy": 0.
|
| 196 |
-
"eval_f1": 0.
|
| 197 |
-
"eval_loss": 1.
|
| 198 |
-
"eval_matthews_correlation": 0.
|
| 199 |
-
"eval_runtime": 2.
|
| 200 |
-
"eval_samples_per_second":
|
| 201 |
-
"eval_steps_per_second":
|
| 202 |
"step": 1600
|
| 203 |
}
|
| 204 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.926948051948052,
|
| 3 |
+
"best_model_checkpoint": "mpnet-metric/checkpoint-1400",
|
| 4 |
"epoch": 36.36363636363637,
|
| 5 |
"global_step": 1600,
|
| 6 |
"is_hyper_param_search": false,
|
|
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 2.27,
|
| 12 |
+
"eval_accuracy": 0.8168831168831169,
|
| 13 |
+
"eval_f1": 0.7526160112915868,
|
| 14 |
+
"eval_loss": 1.6600779294967651,
|
| 15 |
+
"eval_matthews_correlation": 0.8152410229901306,
|
| 16 |
+
"eval_runtime": 2.4316,
|
| 17 |
+
"eval_samples_per_second": 1266.672,
|
| 18 |
+
"eval_steps_per_second": 8.225,
|
| 19 |
"step": 100
|
| 20 |
},
|
| 21 |
{
|
| 22 |
"epoch": 4.55,
|
| 23 |
+
"eval_accuracy": 0.897077922077922,
|
| 24 |
+
"eval_f1": 0.8856257075703299,
|
| 25 |
+
"eval_loss": 1.4927222728729248,
|
| 26 |
+
"eval_matthews_correlation": 0.8957943237010111,
|
| 27 |
+
"eval_runtime": 2.2227,
|
| 28 |
+
"eval_samples_per_second": 1385.731,
|
| 29 |
+
"eval_steps_per_second": 8.998,
|
| 30 |
"step": 200
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 6.82,
|
| 34 |
+
"eval_accuracy": 0.9201298701298701,
|
| 35 |
+
"eval_f1": 0.9205225631693909,
|
| 36 |
+
"eval_loss": 1.5566294193267822,
|
| 37 |
+
"eval_matthews_correlation": 0.9190320812070084,
|
| 38 |
+
"eval_runtime": 2.1905,
|
| 39 |
+
"eval_samples_per_second": 1406.054,
|
| 40 |
+
"eval_steps_per_second": 9.13,
|
| 41 |
"step": 300
|
| 42 |
},
|
| 43 |
{
|
| 44 |
"epoch": 9.09,
|
| 45 |
+
"eval_accuracy": 0.912012987012987,
|
| 46 |
+
"eval_f1": 0.9120652244039835,
|
| 47 |
+
"eval_loss": 1.5064270496368408,
|
| 48 |
+
"eval_matthews_correlation": 0.910845237954562,
|
| 49 |
+
"eval_runtime": 2.0804,
|
| 50 |
+
"eval_samples_per_second": 1480.451,
|
| 51 |
+
"eval_steps_per_second": 9.613,
|
| 52 |
"step": 400
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 11.36,
|
| 56 |
+
"learning_rate": 7.143981790504036e-05,
|
| 57 |
+
"loss": 1.1713,
|
| 58 |
"step": 500
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 11.36,
|
| 62 |
+
"eval_accuracy": 0.9214285714285714,
|
| 63 |
+
"eval_f1": 0.9209415679460552,
|
| 64 |
+
"eval_loss": 1.6870453357696533,
|
| 65 |
+
"eval_matthews_correlation": 0.920369186542805,
|
| 66 |
+
"eval_runtime": 2.1662,
|
| 67 |
+
"eval_samples_per_second": 1421.817,
|
| 68 |
+
"eval_steps_per_second": 9.233,
|
| 69 |
"step": 500
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 13.64,
|
| 73 |
+
"eval_accuracy": 0.9198051948051948,
|
| 74 |
+
"eval_f1": 0.9197304127364558,
|
| 75 |
+
"eval_loss": 1.6187154054641724,
|
| 76 |
+
"eval_matthews_correlation": 0.918700976641645,
|
| 77 |
+
"eval_runtime": 2.0584,
|
| 78 |
+
"eval_samples_per_second": 1496.322,
|
| 79 |
+
"eval_steps_per_second": 9.716,
|
| 80 |
"step": 600
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 15.91,
|
| 84 |
+
"eval_accuracy": 0.9159090909090909,
|
| 85 |
+
"eval_f1": 0.9164948773151114,
|
| 86 |
+
"eval_loss": 1.6880903244018555,
|
| 87 |
+
"eval_matthews_correlation": 0.9148059546508341,
|
| 88 |
+
"eval_runtime": 2.255,
|
| 89 |
+
"eval_samples_per_second": 1365.875,
|
| 90 |
+
"eval_steps_per_second": 8.869,
|
| 91 |
"step": 700
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 18.18,
|
| 95 |
+
"eval_accuracy": 0.9172077922077922,
|
| 96 |
+
"eval_f1": 0.9171466545500319,
|
| 97 |
+
"eval_loss": 1.6939719915390015,
|
| 98 |
+
"eval_matthews_correlation": 0.9160846990725676,
|
| 99 |
+
"eval_runtime": 2.1751,
|
| 100 |
+
"eval_samples_per_second": 1416.047,
|
| 101 |
+
"eval_steps_per_second": 9.195,
|
| 102 |
"step": 800
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 20.45,
|
| 106 |
+
"eval_accuracy": 0.9237012987012987,
|
| 107 |
+
"eval_f1": 0.9228068483209093,
|
| 108 |
+
"eval_loss": 1.827225685119629,
|
| 109 |
+
"eval_matthews_correlation": 0.9226697076696465,
|
| 110 |
+
"eval_runtime": 2.0546,
|
| 111 |
+
"eval_samples_per_second": 1499.088,
|
| 112 |
+
"eval_steps_per_second": 9.734,
|
| 113 |
"step": 900
|
| 114 |
},
|
| 115 |
{
|
| 116 |
"epoch": 22.73,
|
| 117 |
+
"learning_rate": 4.309068381573863e-05,
|
| 118 |
+
"loss": 0.3851,
|
| 119 |
"step": 1000
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 22.73,
|
| 123 |
+
"eval_accuracy": 0.9256493506493506,
|
| 124 |
+
"eval_f1": 0.924610487019518,
|
| 125 |
+
"eval_loss": 1.752126932144165,
|
| 126 |
+
"eval_matthews_correlation": 0.9246248223527813,
|
| 127 |
+
"eval_runtime": 2.1963,
|
| 128 |
+
"eval_samples_per_second": 1402.379,
|
| 129 |
+
"eval_steps_per_second": 9.106,
|
| 130 |
"step": 1000
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 25.0,
|
| 134 |
+
"eval_accuracy": 0.9227272727272727,
|
| 135 |
+
"eval_f1": 0.9224489868001543,
|
| 136 |
+
"eval_loss": 1.8111803531646729,
|
| 137 |
+
"eval_matthews_correlation": 0.9216666198601385,
|
| 138 |
+
"eval_runtime": 2.2202,
|
| 139 |
+
"eval_samples_per_second": 1387.252,
|
| 140 |
+
"eval_steps_per_second": 9.008,
|
| 141 |
"step": 1100
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 27.27,
|
| 145 |
+
"eval_accuracy": 0.924025974025974,
|
| 146 |
+
"eval_f1": 0.9235055742877311,
|
| 147 |
+
"eval_loss": 1.8154934644699097,
|
| 148 |
+
"eval_matthews_correlation": 0.9229953706448562,
|
| 149 |
+
"eval_runtime": 2.1795,
|
| 150 |
+
"eval_samples_per_second": 1413.141,
|
| 151 |
+
"eval_steps_per_second": 9.176,
|
| 152 |
"step": 1200
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 29.55,
|
| 156 |
+
"eval_accuracy": 0.925974025974026,
|
| 157 |
+
"eval_f1": 0.9250491597779087,
|
| 158 |
+
"eval_loss": 1.8494137525558472,
|
| 159 |
+
"eval_matthews_correlation": 0.9249617346684725,
|
| 160 |
+
"eval_runtime": 2.1532,
|
| 161 |
+
"eval_samples_per_second": 1430.445,
|
| 162 |
+
"eval_steps_per_second": 9.289,
|
| 163 |
"step": 1300
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 31.82,
|
| 167 |
+
"eval_accuracy": 0.926948051948052,
|
| 168 |
+
"eval_f1": 0.9263712922428582,
|
| 169 |
+
"eval_loss": 1.845504641532898,
|
| 170 |
+
"eval_matthews_correlation": 0.925946513781978,
|
| 171 |
+
"eval_runtime": 2.0321,
|
| 172 |
+
"eval_samples_per_second": 1515.7,
|
| 173 |
+
"eval_steps_per_second": 9.842,
|
| 174 |
"step": 1400
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 34.09,
|
| 178 |
+
"learning_rate": 1.4741549726436899e-05,
|
| 179 |
+
"loss": 0.0405,
|
| 180 |
"step": 1500
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 34.09,
|
| 184 |
"eval_accuracy": 0.9256493506493506,
|
| 185 |
+
"eval_f1": 0.925144415860077,
|
| 186 |
+
"eval_loss": 1.8381743431091309,
|
| 187 |
+
"eval_matthews_correlation": 0.9246323973685248,
|
| 188 |
+
"eval_runtime": 2.1091,
|
| 189 |
+
"eval_samples_per_second": 1460.352,
|
| 190 |
+
"eval_steps_per_second": 9.483,
|
| 191 |
"step": 1500
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 36.36,
|
| 195 |
+
"eval_accuracy": 0.925,
|
| 196 |
+
"eval_f1": 0.9246946976864899,
|
| 197 |
+
"eval_loss": 1.8348827362060547,
|
| 198 |
+
"eval_matthews_correlation": 0.9239766342788056,
|
| 199 |
+
"eval_runtime": 2.1159,
|
| 200 |
+
"eval_samples_per_second": 1455.631,
|
| 201 |
+
"eval_steps_per_second": 9.452,
|
| 202 |
"step": 1600
|
| 203 |
}
|
| 204 |
],
|
checkpoint-1600/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2927
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fe18383a394371aab9808aba1f4950c63c76fd24cef71575ffa768824cc29b5
|
| 3 |
size 2927
|
checkpoint-200/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1762415977
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9439c182b3e4ea5d09e5cc1d51b0c801ca318a212f5674eb7ca73a359fa977b
|
| 3 |
size 1762415977
|
checkpoint-200/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 440628841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c01622af90baa3d74c8ca0fc35f5f9f3d2a878e3df5bb273eed362255909c0b
|
| 3 |
size 440628841
|
checkpoint-200/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:c5acf53d8795047ae3fb8c3d053417580641d9bd9c3b7986b26e1e96100587dc
|
| 3 |
size 623
|
checkpoint-200/trainer_state.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
"best_model_checkpoint": "mpnet-metric/checkpoint-200",
|
| 4 |
"epoch": 4.545454545454545,
|
| 5 |
"global_step": 200,
|
|
@@ -9,24 +9,24 @@
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 2.27,
|
| 12 |
-
"eval_accuracy": 0.
|
| 13 |
-
"eval_f1": 0.
|
| 14 |
-
"eval_loss": 1.
|
| 15 |
-
"eval_matthews_correlation": 0.
|
| 16 |
-
"eval_runtime": 2.
|
| 17 |
-
"eval_samples_per_second":
|
| 18 |
-
"eval_steps_per_second": 8.
|
| 19 |
"step": 100
|
| 20 |
},
|
| 21 |
{
|
| 22 |
"epoch": 4.55,
|
| 23 |
-
"eval_accuracy": 0.
|
| 24 |
-
"eval_f1": 0.
|
| 25 |
-
"eval_loss": 1.
|
| 26 |
-
"eval_matthews_correlation": 0.
|
| 27 |
-
"eval_runtime": 2.
|
| 28 |
-
"eval_samples_per_second":
|
| 29 |
-
"eval_steps_per_second":
|
| 30 |
"step": 200
|
| 31 |
}
|
| 32 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8948051948051948,
|
| 3 |
"best_model_checkpoint": "mpnet-metric/checkpoint-200",
|
| 4 |
"epoch": 4.545454545454545,
|
| 5 |
"global_step": 200,
|
|
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 2.27,
|
| 12 |
+
"eval_accuracy": 0.8142857142857143,
|
| 13 |
+
"eval_f1": 0.7571139466171084,
|
| 14 |
+
"eval_loss": 1.6553083658218384,
|
| 15 |
+
"eval_matthews_correlation": 0.8128010374008804,
|
| 16 |
+
"eval_runtime": 2.3607,
|
| 17 |
+
"eval_samples_per_second": 1304.725,
|
| 18 |
+
"eval_steps_per_second": 8.472,
|
| 19 |
"step": 100
|
| 20 |
},
|
| 21 |
{
|
| 22 |
"epoch": 4.55,
|
| 23 |
+
"eval_accuracy": 0.8948051948051948,
|
| 24 |
+
"eval_f1": 0.8619038692930777,
|
| 25 |
+
"eval_loss": 1.4167946577072144,
|
| 26 |
+
"eval_matthews_correlation": 0.8934693025227957,
|
| 27 |
+
"eval_runtime": 2.1743,
|
| 28 |
+
"eval_samples_per_second": 1416.55,
|
| 29 |
+
"eval_steps_per_second": 9.198,
|
| 30 |
"step": 200
|
| 31 |
}
|
| 32 |
],
|
checkpoint-200/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2927
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1912ec144e9e5b98372a9c9abb72fc7763e9904e5599699afcdc707da8bc9dc5
|
| 3 |
size 2927
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 440628841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c01622af90baa3d74c8ca0fc35f5f9f3d2a878e3df5bb273eed362255909c0b
|
| 3 |
size 440628841
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2927
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1912ec144e9e5b98372a9c9abb72fc7763e9904e5599699afcdc707da8bc9dc5
|
| 3 |
size 2927
|