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 1000
Browse files- checkpoint-1000/optimizer.pt +1 -1
- checkpoint-1000/pytorch_model.bin +1 -1
- checkpoint-1000/scheduler.pt +1 -1
- checkpoint-1000/trainer_state.json +75 -75
- checkpoint-1000/training_args.bin +1 -1
- checkpoint-400/optimizer.pt +1 -1
- checkpoint-400/pytorch_model.bin +1 -1
- checkpoint-400/scheduler.pt +1 -1
- checkpoint-400/trainer_state.json +29 -29
- checkpoint-400/training_args.bin +1 -1
- checkpoint-600/optimizer.pt +1 -1
- checkpoint-600/pytorch_model.bin +1 -1
- checkpoint-600/scheduler.pt +1 -1
- checkpoint-600/trainer_state.json +45 -45
- checkpoint-600/training_args.bin +1 -1
- checkpoint-800/optimizer.pt +1 -1
- checkpoint-800/pytorch_model.bin +1 -1
- checkpoint-800/scheduler.pt +1 -1
- checkpoint-800/trainer_state.json +59 -59
- checkpoint-800/training_args.bin +1 -1
- pytorch_model.bin +1 -1
checkpoint-1000/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:e1ebb8e6ec60ec6997dfcd1f3612ce611dae5f758d2a7038bd7d80b3a3382418
|
| 3 |
size 1762416361
|
checkpoint-1000/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 sha256:043f5c480bedb53f96a633d0ca2d65dd6f5fc6adc2af5fd6892dc7afa7e84dcb
|
| 3 |
size 440628841
|
checkpoint-1000/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 sha256:630e80d2d18164c1a0800c0b398fa7ab45c2ec704efd3a848e0a7efd179ea55b
|
| 3 |
size 623
|
checkpoint-1000/trainer_state.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
"best_model_checkpoint": "mpnet-metric/checkpoint-1000",
|
| 4 |
"epoch": 22.727272727272727,
|
| 5 |
"global_step": 1000,
|
|
@@ -9,124 +9,124 @@
|
|
| 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 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9256493506493506,
|
| 3 |
"best_model_checkpoint": "mpnet-metric/checkpoint-1000",
|
| 4 |
"epoch": 22.727272727272727,
|
| 5 |
"global_step": 1000,
|
|
|
|
| 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 |
],
|
checkpoint-1000/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-400/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 sha256:07952d7fd0611d3373f712ef0a2d5e391a61fb01b0d4b3cf3b9ec9dee2d6f09c
|
| 3 |
size 1762416361
|
checkpoint-400/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:f1c32389edc5e42fcac63f14a14276fefd1f59e2d32710432fd290872df53244
|
| 3 |
size 440628841
|
checkpoint-400/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 sha256:5e1c57e8f93b3d7f48d2ed0330591daa53d6f47fe0277b5b8df6de1eda873882
|
| 3 |
size 623
|
checkpoint-400/trainer_state.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
"best_model_checkpoint": "mpnet-metric/checkpoint-400",
|
| 4 |
"epoch": 9.090909090909092,
|
| 5 |
"global_step": 400,
|
|
@@ -9,46 +9,46 @@
|
|
| 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 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.912012987012987,
|
| 3 |
"best_model_checkpoint": "mpnet-metric/checkpoint-400",
|
| 4 |
"epoch": 9.090909090909092,
|
| 5 |
"global_step": 400,
|
|
|
|
| 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 |
],
|
checkpoint-400/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-600/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:e7b745b9b72b63e00e2e8d416afa8ca9f9bbd45f1d5585ac4f7e9c352fded614
|
| 3 |
size 1762416361
|
checkpoint-600/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 sha256:8c1897bd6b13f7cc3cc8dcbee8cd65463b17a4abc4cc2d41c704f1d93f5d91f4
|
| 3 |
size 440628841
|
checkpoint-600/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 sha256:439efae2d494351e783e08f2ec1c0f71e2966b0eaef2708b6549ccacee842193
|
| 3 |
size 623
|
checkpoint-600/trainer_state.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
"best_model_checkpoint": "mpnet-metric/checkpoint-600",
|
| 4 |
"epoch": 13.636363636363637,
|
| 5 |
"global_step": 600,
|
|
@@ -9,74 +9,74 @@
|
|
| 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 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9198051948051948,
|
| 3 |
"best_model_checkpoint": "mpnet-metric/checkpoint-600",
|
| 4 |
"epoch": 13.636363636363637,
|
| 5 |
"global_step": 600,
|
|
|
|
| 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 |
],
|
checkpoint-600/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-800/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 sha256:04b8caca37ff4a7615f185fc2afadf415cd025d4419cf30f0fb436b67f773c1a
|
| 3 |
size 1762416361
|
checkpoint-800/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:e8ae07fa103386886dd4a39a02e6356ccdccf33891080467170a9b55f082732d
|
| 3 |
size 440628841
|
checkpoint-800/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 sha256:7e08fbce60fb739ae75a55db7d1eb039943cff968e32c13837eda1ebdd61867a
|
| 3 |
size 623
|
checkpoint-800/trainer_state.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
"best_model_checkpoint": "mpnet-metric/checkpoint-600",
|
| 4 |
"epoch": 18.181818181818183,
|
| 5 |
"global_step": 800,
|
|
@@ -9,96 +9,96 @@
|
|
| 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 |
],
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9198051948051948,
|
| 3 |
"best_model_checkpoint": "mpnet-metric/checkpoint-600",
|
| 4 |
"epoch": 18.181818181818183,
|
| 5 |
"global_step": 800,
|
|
|
|
| 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 |
],
|
checkpoint-800/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
|
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 sha256:043f5c480bedb53f96a633d0ca2d65dd6f5fc6adc2af5fd6892dc7afa7e84dcb
|
| 3 |
size 440628841
|