Commit
•
aba047d
1
Parent(s):
cdd4b20
Training in progress, step 200
Browse files- all_results.json +14 -14
- eval_results.json +5 -5
- pytorch_model.bin +2 -2
- runs/Feb01_08-47-59_node1/events.out.tfevents.1643676640.node1 +2 -2
- runs/Feb01_08-47-59_node1/events.out.tfevents.1643680170.node1 +3 -0
- runs/Feb02_20-38-16_node1/1643805565.1931665/events.out.tfevents.1643805565.node1 +3 -0
- runs/Feb02_20-38-16_node1/events.out.tfevents.1643805565.node1 +3 -0
- test_results.json +5 -5
- tokenizer.json +0 -0
- train_results.json +4 -4
- trainer_state.json +522 -66
- training_args.bin +1 -1
- training_config.json +1 -1
all_results.json
CHANGED
|
@@ -1,18 +1,18 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"eval_accuracy":
|
| 4 |
-
"eval_average_metrics":
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_runtime":
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"test_accuracy":
|
| 9 |
-
"test_average_metrics":
|
| 10 |
-
"test_loss": 0.
|
| 11 |
-
"test_runtime":
|
| 12 |
-
"test_samples_per_second":
|
| 13 |
-
"train_loss": 0.
|
| 14 |
-
"train_runtime":
|
| 15 |
"train_samples": 103743,
|
| 16 |
-
"train_samples_per_second":
|
| 17 |
-
"train_steps_per_second": 2.
|
| 18 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 96.2,
|
| 4 |
+
"eval_average_metrics": 96.2,
|
| 5 |
+
"eval_loss": 0.04570974037051201,
|
| 6 |
+
"eval_runtime": 4.807,
|
| 7 |
+
"eval_samples_per_second": 208.03,
|
| 8 |
+
"test_accuracy": 93.3919092073952,
|
| 9 |
+
"test_average_metrics": 93.3919092073952,
|
| 10 |
+
"test_loss": 0.07689828425645828,
|
| 11 |
+
"test_runtime": 25.7399,
|
| 12 |
+
"test_samples_per_second": 212.239,
|
| 13 |
+
"train_loss": 0.07298248127461363,
|
| 14 |
+
"train_runtime": 3523.2101,
|
| 15 |
"train_samples": 103743,
|
| 16 |
+
"train_samples_per_second": 88.337,
|
| 17 |
+
"train_steps_per_second": 2.761
|
| 18 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"eval_accuracy":
|
| 4 |
-
"eval_average_metrics":
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_runtime":
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 96.2,
|
| 4 |
+
"eval_average_metrics": 96.2,
|
| 5 |
+
"eval_loss": 0.04570974037051201,
|
| 6 |
+
"eval_runtime": 4.807,
|
| 7 |
+
"eval_samples_per_second": 208.03
|
| 8 |
}
|
pytorch_model.bin
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:cd19e856e1aefcbf9ed4b1513419438eafbc64487e86b5f609b575c26a62ea99
|
| 3 |
+
size 2631685
|
runs/Feb01_08-47-59_node1/events.out.tfevents.1643676640.node1
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:fe30d35e85f7789e8a82da85027e4c3e3566db9ff52eb807ab4a744eb2e78ac6
|
| 3 |
+
size 23092
|
runs/Feb01_08-47-59_node1/events.out.tfevents.1643680170.node1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:988efc3b4fd1f973bab61e956c2dc54f12532327e753d927358aff8339073477
|
| 3 |
+
size 684
|
runs/Feb02_20-38-16_node1/1643805565.1931665/events.out.tfevents.1643805565.node1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96584d0bf4cce8fa40154c17140bbc17bedad015383bdd018292c47d60839902
|
| 3 |
+
size 5011
|
runs/Feb02_20-38-16_node1/events.out.tfevents.1643805565.node1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca11303ef6d642df6cd23e2fceffa7c8d62f2276a9278bed8a00eadec386cebd
|
| 3 |
+
size 4299
|
test_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"test_accuracy":
|
| 4 |
-
"test_average_metrics":
|
| 5 |
-
"test_loss": 0.
|
| 6 |
-
"test_runtime":
|
| 7 |
-
"test_samples_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"test_accuracy": 93.3919092073952,
|
| 4 |
+
"test_average_metrics": 93.3919092073952,
|
| 5 |
+
"test_loss": 0.07689828425645828,
|
| 6 |
+
"test_runtime": 25.7399,
|
| 7 |
+
"test_samples_per_second": 212.239
|
| 8 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 103743,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 2.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.07298248127461363,
|
| 4 |
+
"train_runtime": 3523.2101,
|
| 5 |
"train_samples": 103743,
|
| 6 |
+
"train_samples_per_second": 88.337,
|
| 7 |
+
"train_steps_per_second": 2.761
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,115 +1,571 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "outputs/bitfit/t5-base/qnli/checkpoint-
|
| 4 |
"epoch": 3.0,
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch": 0.
|
| 12 |
-
"
|
| 13 |
-
"
|
| 14 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"
|
| 19 |
-
"
|
| 20 |
-
"eval_loss": 0.06821990013122559,
|
| 21 |
-
"eval_runtime": 3.2581,
|
| 22 |
-
"eval_samples_per_second": 306.927,
|
| 23 |
"step": 500
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"
|
| 28 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
"step": 1000
|
| 30 |
},
|
| 31 |
{
|
| 32 |
-
"epoch": 0.
|
| 33 |
-
"eval_accuracy":
|
| 34 |
-
"eval_average_metrics":
|
| 35 |
-
"eval_loss": 0.
|
| 36 |
-
"eval_runtime":
|
| 37 |
-
"eval_samples_per_second":
|
| 38 |
"step": 1000
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"
|
| 43 |
-
"
|
| 44 |
-
"
|
|
|
|
|
|
|
|
|
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"eval_accuracy": 95.
|
| 49 |
-
"eval_average_metrics": 95.
|
| 50 |
-
"eval_loss": 0.
|
| 51 |
-
"eval_runtime":
|
| 52 |
-
"eval_samples_per_second":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
"step": 1500
|
| 54 |
},
|
| 55 |
{
|
| 56 |
-
"epoch":
|
| 57 |
-
"
|
| 58 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
"step": 2000
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch":
|
| 63 |
-
"eval_accuracy":
|
| 64 |
-
"eval_average_metrics":
|
| 65 |
-
"eval_loss": 0.
|
| 66 |
-
"eval_runtime":
|
| 67 |
-
"eval_samples_per_second":
|
| 68 |
"step": 2000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch":
|
| 72 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
"loss": 0.0742,
|
| 74 |
"step": 2500
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch":
|
| 78 |
-
"eval_accuracy": 95.
|
| 79 |
-
"eval_average_metrics": 95.
|
| 80 |
-
"eval_loss": 0.
|
| 81 |
-
"eval_runtime":
|
| 82 |
-
"eval_samples_per_second":
|
| 83 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
},
|
| 85 |
{
|
| 86 |
-
"epoch":
|
| 87 |
-
"
|
| 88 |
-
"
|
|
|
|
|
|
|
|
|
|
| 89 |
"step": 3000
|
| 90 |
},
|
| 91 |
{
|
| 92 |
-
"epoch":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
"eval_accuracy": 95.5,
|
| 94 |
"eval_average_metrics": 95.5,
|
| 95 |
-
"eval_loss": 0.
|
| 96 |
-
"eval_runtime":
|
| 97 |
-
"eval_samples_per_second":
|
| 98 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 3.0,
|
| 102 |
-
"step":
|
| 103 |
-
"total_flos": 4.
|
| 104 |
-
"train_loss": 0.
|
| 105 |
-
"train_runtime":
|
| 106 |
-
"train_samples_per_second":
|
| 107 |
-
"train_steps_per_second": 2.
|
| 108 |
}
|
| 109 |
],
|
| 110 |
-
"max_steps":
|
| 111 |
"num_train_epochs": 3,
|
| 112 |
-
"total_flos": 4.
|
| 113 |
"trial_name": null,
|
| 114 |
"trial_params": null
|
| 115 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 96.2,
|
| 3 |
+
"best_model_checkpoint": "outputs/bitfit/t5-base/qnli/checkpoint-3800",
|
| 4 |
"epoch": 3.0,
|
| 5 |
+
"global_step": 9726,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"eval_accuracy": 92.5,
|
| 13 |
+
"eval_average_metrics": 92.5,
|
| 14 |
+
"eval_loss": 0.07770004123449326,
|
| 15 |
+
"eval_runtime": 4.8406,
|
| 16 |
+
"eval_samples_per_second": 206.585,
|
| 17 |
+
"step": 200
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.12,
|
| 21 |
+
"eval_accuracy": 94.89999999999999,
|
| 22 |
+
"eval_average_metrics": 94.89999999999999,
|
| 23 |
+
"eval_loss": 0.05564185231924057,
|
| 24 |
+
"eval_runtime": 4.8573,
|
| 25 |
+
"eval_samples_per_second": 205.876,
|
| 26 |
+
"step": 400
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.15,
|
| 30 |
+
"learning_rate": 0.0002845774213448488,
|
| 31 |
+
"loss": 0.1452,
|
|
|
|
|
|
|
|
|
|
| 32 |
"step": 500
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.19,
|
| 36 |
+
"eval_accuracy": 94.89999999999999,
|
| 37 |
+
"eval_average_metrics": 94.89999999999999,
|
| 38 |
+
"eval_loss": 0.058011941611766815,
|
| 39 |
+
"eval_runtime": 4.8049,
|
| 40 |
+
"eval_samples_per_second": 208.12,
|
| 41 |
+
"step": 600
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.25,
|
| 45 |
+
"eval_accuracy": 94.69999999999999,
|
| 46 |
+
"eval_average_metrics": 94.69999999999999,
|
| 47 |
+
"eval_loss": 0.054659225046634674,
|
| 48 |
+
"eval_runtime": 4.7475,
|
| 49 |
+
"eval_samples_per_second": 210.637,
|
| 50 |
+
"step": 800
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.31,
|
| 54 |
+
"learning_rate": 0.0002691548426896977,
|
| 55 |
+
"loss": 0.0755,
|
| 56 |
"step": 1000
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 0.31,
|
| 60 |
+
"eval_accuracy": 95.5,
|
| 61 |
+
"eval_average_metrics": 95.5,
|
| 62 |
+
"eval_loss": 0.050559960305690765,
|
| 63 |
+
"eval_runtime": 4.7617,
|
| 64 |
+
"eval_samples_per_second": 210.008,
|
| 65 |
"step": 1000
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.37,
|
| 69 |
+
"eval_accuracy": 95.1,
|
| 70 |
+
"eval_average_metrics": 95.1,
|
| 71 |
+
"eval_loss": 0.05192100629210472,
|
| 72 |
+
"eval_runtime": 4.7418,
|
| 73 |
+
"eval_samples_per_second": 210.892,
|
| 74 |
+
"step": 1200
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 0.43,
|
| 78 |
+
"eval_accuracy": 95.1,
|
| 79 |
+
"eval_average_metrics": 95.1,
|
| 80 |
+
"eval_loss": 0.05229589715600014,
|
| 81 |
+
"eval_runtime": 4.8058,
|
| 82 |
+
"eval_samples_per_second": 208.082,
|
| 83 |
+
"step": 1400
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.46,
|
| 87 |
+
"learning_rate": 0.00025373226403454656,
|
| 88 |
+
"loss": 0.0741,
|
| 89 |
"step": 1500
|
| 90 |
},
|
| 91 |
{
|
| 92 |
+
"epoch": 0.49,
|
| 93 |
+
"eval_accuracy": 95.0,
|
| 94 |
+
"eval_average_metrics": 95.0,
|
| 95 |
+
"eval_loss": 0.054607994854450226,
|
| 96 |
+
"eval_runtime": 4.7778,
|
| 97 |
+
"eval_samples_per_second": 209.3,
|
| 98 |
+
"step": 1600
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.56,
|
| 102 |
+
"eval_accuracy": 94.5,
|
| 103 |
+
"eval_average_metrics": 94.5,
|
| 104 |
+
"eval_loss": 0.061842530965805054,
|
| 105 |
+
"eval_runtime": 4.6161,
|
| 106 |
+
"eval_samples_per_second": 216.634,
|
| 107 |
+
"step": 1800
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.62,
|
| 111 |
+
"learning_rate": 0.0002383096853793954,
|
| 112 |
+
"loss": 0.0767,
|
| 113 |
"step": 2000
|
| 114 |
},
|
| 115 |
{
|
| 116 |
+
"epoch": 0.62,
|
| 117 |
+
"eval_accuracy": 95.19999999999999,
|
| 118 |
+
"eval_average_metrics": 95.19999999999999,
|
| 119 |
+
"eval_loss": 0.05252940207719803,
|
| 120 |
+
"eval_runtime": 4.9106,
|
| 121 |
+
"eval_samples_per_second": 203.642,
|
| 122 |
"step": 2000
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 0.68,
|
| 126 |
+
"eval_accuracy": 95.5,
|
| 127 |
+
"eval_average_metrics": 95.5,
|
| 128 |
+
"eval_loss": 0.05460799112915993,
|
| 129 |
+
"eval_runtime": 4.7646,
|
| 130 |
+
"eval_samples_per_second": 209.881,
|
| 131 |
+
"step": 2200
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.74,
|
| 135 |
+
"eval_accuracy": 95.89999999999999,
|
| 136 |
+
"eval_average_metrics": 95.89999999999999,
|
| 137 |
+
"eval_loss": 0.05030712112784386,
|
| 138 |
+
"eval_runtime": 4.7399,
|
| 139 |
+
"eval_samples_per_second": 210.974,
|
| 140 |
+
"step": 2400
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.77,
|
| 144 |
+
"learning_rate": 0.00022288710672424428,
|
| 145 |
"loss": 0.0742,
|
| 146 |
"step": 2500
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"epoch": 0.8,
|
| 150 |
+
"eval_accuracy": 95.8,
|
| 151 |
+
"eval_average_metrics": 95.8,
|
| 152 |
+
"eval_loss": 0.048599060624837875,
|
| 153 |
+
"eval_runtime": 4.7193,
|
| 154 |
+
"eval_samples_per_second": 211.896,
|
| 155 |
+
"step": 2600
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 0.86,
|
| 159 |
+
"eval_accuracy": 95.6,
|
| 160 |
+
"eval_average_metrics": 95.6,
|
| 161 |
+
"eval_loss": 0.05030570924282074,
|
| 162 |
+
"eval_runtime": 4.7668,
|
| 163 |
+
"eval_samples_per_second": 209.784,
|
| 164 |
+
"step": 2800
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.93,
|
| 168 |
+
"learning_rate": 0.00020746452806909312,
|
| 169 |
+
"loss": 0.075,
|
| 170 |
+
"step": 3000
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.93,
|
| 174 |
+
"eval_accuracy": 95.8,
|
| 175 |
+
"eval_average_metrics": 95.8,
|
| 176 |
+
"eval_loss": 0.047494787722826004,
|
| 177 |
+
"eval_runtime": 4.7477,
|
| 178 |
+
"eval_samples_per_second": 210.63,
|
| 179 |
"step": 3000
|
| 180 |
},
|
| 181 |
{
|
| 182 |
+
"epoch": 0.99,
|
| 183 |
+
"eval_accuracy": 95.19999999999999,
|
| 184 |
+
"eval_average_metrics": 95.19999999999999,
|
| 185 |
+
"eval_loss": 0.04927437752485275,
|
| 186 |
+
"eval_runtime": 4.7206,
|
| 187 |
+
"eval_samples_per_second": 211.839,
|
| 188 |
+
"step": 3200
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.05,
|
| 192 |
+
"eval_accuracy": 95.6,
|
| 193 |
+
"eval_average_metrics": 95.6,
|
| 194 |
+
"eval_loss": 0.05033966153860092,
|
| 195 |
+
"eval_runtime": 4.6755,
|
| 196 |
+
"eval_samples_per_second": 213.88,
|
| 197 |
+
"step": 3400
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.08,
|
| 201 |
+
"learning_rate": 0.000192041949413942,
|
| 202 |
+
"loss": 0.0715,
|
| 203 |
+
"step": 3500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.11,
|
| 207 |
+
"eval_accuracy": 95.0,
|
| 208 |
+
"eval_average_metrics": 95.0,
|
| 209 |
+
"eval_loss": 0.05600408464670181,
|
| 210 |
+
"eval_runtime": 4.8028,
|
| 211 |
+
"eval_samples_per_second": 208.211,
|
| 212 |
+
"step": 3600
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.17,
|
| 216 |
+
"eval_accuracy": 96.2,
|
| 217 |
+
"eval_average_metrics": 96.2,
|
| 218 |
+
"eval_loss": 0.04570974037051201,
|
| 219 |
+
"eval_runtime": 4.76,
|
| 220 |
+
"eval_samples_per_second": 210.082,
|
| 221 |
+
"step": 3800
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.23,
|
| 225 |
+
"learning_rate": 0.00017661937075879084,
|
| 226 |
+
"loss": 0.0709,
|
| 227 |
+
"step": 4000
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.23,
|
| 231 |
+
"eval_accuracy": 95.7,
|
| 232 |
+
"eval_average_metrics": 95.7,
|
| 233 |
+
"eval_loss": 0.04873451963067055,
|
| 234 |
+
"eval_runtime": 4.7588,
|
| 235 |
+
"eval_samples_per_second": 210.137,
|
| 236 |
+
"step": 4000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.3,
|
| 240 |
+
"eval_accuracy": 95.7,
|
| 241 |
+
"eval_average_metrics": 95.7,
|
| 242 |
+
"eval_loss": 0.04785784333944321,
|
| 243 |
+
"eval_runtime": 4.7192,
|
| 244 |
+
"eval_samples_per_second": 211.9,
|
| 245 |
+
"step": 4200
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.36,
|
| 249 |
+
"eval_accuracy": 95.89999999999999,
|
| 250 |
+
"eval_average_metrics": 95.89999999999999,
|
| 251 |
+
"eval_loss": 0.05093304440379143,
|
| 252 |
+
"eval_runtime": 4.68,
|
| 253 |
+
"eval_samples_per_second": 213.674,
|
| 254 |
+
"step": 4400
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.39,
|
| 258 |
+
"learning_rate": 0.0001611967921036397,
|
| 259 |
+
"loss": 0.0693,
|
| 260 |
+
"step": 4500
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.42,
|
| 264 |
+
"eval_accuracy": 95.19999999999999,
|
| 265 |
+
"eval_average_metrics": 95.19999999999999,
|
| 266 |
+
"eval_loss": 0.05333869531750679,
|
| 267 |
+
"eval_runtime": 4.6769,
|
| 268 |
+
"eval_samples_per_second": 213.817,
|
| 269 |
+
"step": 4600
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.48,
|
| 273 |
+
"eval_accuracy": 95.19999999999999,
|
| 274 |
+
"eval_average_metrics": 95.19999999999999,
|
| 275 |
+
"eval_loss": 0.05299631133675575,
|
| 276 |
+
"eval_runtime": 4.8038,
|
| 277 |
+
"eval_samples_per_second": 208.169,
|
| 278 |
+
"step": 4800
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.54,
|
| 282 |
+
"learning_rate": 0.00014577421344848858,
|
| 283 |
+
"loss": 0.0701,
|
| 284 |
+
"step": 5000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.54,
|
| 288 |
+
"eval_accuracy": 95.39999999999999,
|
| 289 |
+
"eval_average_metrics": 95.39999999999999,
|
| 290 |
+
"eval_loss": 0.049973100423812866,
|
| 291 |
+
"eval_runtime": 4.7662,
|
| 292 |
+
"eval_samples_per_second": 209.812,
|
| 293 |
+
"step": 5000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.6,
|
| 297 |
+
"eval_accuracy": 95.39999999999999,
|
| 298 |
+
"eval_average_metrics": 95.39999999999999,
|
| 299 |
+
"eval_loss": 0.04949893057346344,
|
| 300 |
+
"eval_runtime": 3.1699,
|
| 301 |
+
"eval_samples_per_second": 315.466,
|
| 302 |
+
"step": 5200
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.67,
|
| 306 |
+
"eval_accuracy": 95.39999999999999,
|
| 307 |
+
"eval_average_metrics": 95.39999999999999,
|
| 308 |
+
"eval_loss": 0.0472724474966526,
|
| 309 |
+
"eval_runtime": 4.7592,
|
| 310 |
+
"eval_samples_per_second": 210.12,
|
| 311 |
+
"step": 5400
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.7,
|
| 315 |
+
"learning_rate": 0.00013035163479333743,
|
| 316 |
+
"loss": 0.0701,
|
| 317 |
+
"step": 5500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.73,
|
| 321 |
+
"eval_accuracy": 95.7,
|
| 322 |
+
"eval_average_metrics": 95.7,
|
| 323 |
+
"eval_loss": 0.04894798621535301,
|
| 324 |
+
"eval_runtime": 4.9844,
|
| 325 |
+
"eval_samples_per_second": 200.627,
|
| 326 |
+
"step": 5600
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.79,
|
| 330 |
+
"eval_accuracy": 95.39999999999999,
|
| 331 |
+
"eval_average_metrics": 95.39999999999999,
|
| 332 |
+
"eval_loss": 0.046521034091711044,
|
| 333 |
+
"eval_runtime": 4.8064,
|
| 334 |
+
"eval_samples_per_second": 208.058,
|
| 335 |
+
"step": 5800
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.85,
|
| 339 |
+
"learning_rate": 0.0001149290561381863,
|
| 340 |
+
"loss": 0.0703,
|
| 341 |
+
"step": 6000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.85,
|
| 345 |
+
"eval_accuracy": 95.89999999999999,
|
| 346 |
+
"eval_average_metrics": 95.89999999999999,
|
| 347 |
+
"eval_loss": 0.04965585470199585,
|
| 348 |
+
"eval_runtime": 4.7332,
|
| 349 |
+
"eval_samples_per_second": 211.272,
|
| 350 |
+
"step": 6000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.91,
|
| 354 |
+
"eval_accuracy": 95.7,
|
| 355 |
+
"eval_average_metrics": 95.7,
|
| 356 |
+
"eval_loss": 0.04986129701137543,
|
| 357 |
+
"eval_runtime": 4.7614,
|
| 358 |
+
"eval_samples_per_second": 210.02,
|
| 359 |
+
"step": 6200
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.97,
|
| 363 |
+
"eval_accuracy": 95.39999999999999,
|
| 364 |
+
"eval_average_metrics": 95.39999999999999,
|
| 365 |
+
"eval_loss": 0.04970705509185791,
|
| 366 |
+
"eval_runtime": 4.7354,
|
| 367 |
+
"eval_samples_per_second": 211.177,
|
| 368 |
+
"step": 6400
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.0,
|
| 372 |
+
"learning_rate": 9.950647748303516e-05,
|
| 373 |
+
"loss": 0.0683,
|
| 374 |
+
"step": 6500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.04,
|
| 378 |
"eval_accuracy": 95.5,
|
| 379 |
"eval_average_metrics": 95.5,
|
| 380 |
+
"eval_loss": 0.05166413262486458,
|
| 381 |
+
"eval_runtime": 4.7531,
|
| 382 |
+
"eval_samples_per_second": 210.389,
|
| 383 |
+
"step": 6600
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.1,
|
| 387 |
+
"eval_accuracy": 95.6,
|
| 388 |
+
"eval_average_metrics": 95.6,
|
| 389 |
+
"eval_loss": 0.04985863342881203,
|
| 390 |
+
"eval_runtime": 4.6875,
|
| 391 |
+
"eval_samples_per_second": 213.333,
|
| 392 |
+
"step": 6800
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.16,
|
| 396 |
+
"learning_rate": 8.408389882788402e-05,
|
| 397 |
+
"loss": 0.0639,
|
| 398 |
+
"step": 7000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.16,
|
| 402 |
+
"eval_accuracy": 95.6,
|
| 403 |
+
"eval_average_metrics": 95.6,
|
| 404 |
+
"eval_loss": 0.04906700178980827,
|
| 405 |
+
"eval_runtime": 4.7251,
|
| 406 |
+
"eval_samples_per_second": 211.637,
|
| 407 |
+
"step": 7000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 2.22,
|
| 411 |
+
"eval_accuracy": 95.39999999999999,
|
| 412 |
+
"eval_average_metrics": 95.39999999999999,
|
| 413 |
+
"eval_loss": 0.05032121390104294,
|
| 414 |
+
"eval_runtime": 4.6901,
|
| 415 |
+
"eval_samples_per_second": 213.216,
|
| 416 |
+
"step": 7200
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.28,
|
| 420 |
+
"eval_accuracy": 95.6,
|
| 421 |
+
"eval_average_metrics": 95.6,
|
| 422 |
+
"eval_loss": 0.049571845680475235,
|
| 423 |
+
"eval_runtime": 4.7849,
|
| 424 |
+
"eval_samples_per_second": 208.989,
|
| 425 |
+
"step": 7400
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.31,
|
| 429 |
+
"learning_rate": 6.866132017273288e-05,
|
| 430 |
+
"loss": 0.0628,
|
| 431 |
+
"step": 7500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.34,
|
| 435 |
+
"eval_accuracy": 95.7,
|
| 436 |
+
"eval_average_metrics": 95.7,
|
| 437 |
+
"eval_loss": 0.05029569938778877,
|
| 438 |
+
"eval_runtime": 4.7631,
|
| 439 |
+
"eval_samples_per_second": 209.949,
|
| 440 |
+
"step": 7600
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.41,
|
| 444 |
+
"eval_accuracy": 95.39999999999999,
|
| 445 |
+
"eval_average_metrics": 95.39999999999999,
|
| 446 |
+
"eval_loss": 0.05099053308367729,
|
| 447 |
+
"eval_runtime": 4.6959,
|
| 448 |
+
"eval_samples_per_second": 212.954,
|
| 449 |
+
"step": 7800
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.47,
|
| 453 |
+
"learning_rate": 5.323874151758173e-05,
|
| 454 |
+
"loss": 0.0629,
|
| 455 |
+
"step": 8000
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 2.47,
|
| 459 |
+
"eval_accuracy": 95.7,
|
| 460 |
+
"eval_average_metrics": 95.7,
|
| 461 |
+
"eval_loss": 0.04943836107850075,
|
| 462 |
+
"eval_runtime": 4.8312,
|
| 463 |
+
"eval_samples_per_second": 206.989,
|
| 464 |
+
"step": 8000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.53,
|
| 468 |
+
"eval_accuracy": 95.39999999999999,
|
| 469 |
+
"eval_average_metrics": 95.39999999999999,
|
| 470 |
+
"eval_loss": 0.04987151920795441,
|
| 471 |
+
"eval_runtime": 4.7857,
|
| 472 |
+
"eval_samples_per_second": 208.955,
|
| 473 |
+
"step": 8200
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.59,
|
| 477 |
+
"eval_accuracy": 95.89999999999999,
|
| 478 |
+
"eval_average_metrics": 95.89999999999999,
|
| 479 |
+
"eval_loss": 0.04786397144198418,
|
| 480 |
+
"eval_runtime": 4.6689,
|
| 481 |
+
"eval_samples_per_second": 214.182,
|
| 482 |
+
"step": 8400
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.62,
|
| 486 |
+
"learning_rate": 3.781616286243059e-05,
|
| 487 |
+
"loss": 0.0644,
|
| 488 |
+
"step": 8500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.65,
|
| 492 |
+
"eval_accuracy": 96.0,
|
| 493 |
+
"eval_average_metrics": 96.0,
|
| 494 |
+
"eval_loss": 0.04664640501141548,
|
| 495 |
+
"eval_runtime": 4.8983,
|
| 496 |
+
"eval_samples_per_second": 204.153,
|
| 497 |
+
"step": 8600
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 2.71,
|
| 501 |
+
"eval_accuracy": 95.89999999999999,
|
| 502 |
+
"eval_average_metrics": 95.89999999999999,
|
| 503 |
+
"eval_loss": 0.04768410325050354,
|
| 504 |
+
"eval_runtime": 4.7197,
|
| 505 |
+
"eval_samples_per_second": 211.878,
|
| 506 |
+
"step": 8800
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.78,
|
| 510 |
+
"learning_rate": 2.2393584207279457e-05,
|
| 511 |
+
"loss": 0.0654,
|
| 512 |
+
"step": 9000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.78,
|
| 516 |
+
"eval_accuracy": 95.8,
|
| 517 |
+
"eval_average_metrics": 95.8,
|
| 518 |
+
"eval_loss": 0.04792344942688942,
|
| 519 |
+
"eval_runtime": 4.8006,
|
| 520 |
+
"eval_samples_per_second": 208.308,
|
| 521 |
+
"step": 9000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.84,
|
| 525 |
+
"eval_accuracy": 95.6,
|
| 526 |
+
"eval_average_metrics": 95.6,
|
| 527 |
+
"eval_loss": 0.04864838346838951,
|
| 528 |
+
"eval_runtime": 4.7035,
|
| 529 |
+
"eval_samples_per_second": 212.608,
|
| 530 |
+
"step": 9200
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 2.9,
|
| 534 |
+
"eval_accuracy": 95.89999999999999,
|
| 535 |
+
"eval_average_metrics": 95.89999999999999,
|
| 536 |
+
"eval_loss": 0.0480988509953022,
|
| 537 |
+
"eval_runtime": 4.7424,
|
| 538 |
+
"eval_samples_per_second": 210.863,
|
| 539 |
+
"step": 9400
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.93,
|
| 543 |
+
"learning_rate": 6.971005552128316e-06,
|
| 544 |
+
"loss": 0.0601,
|
| 545 |
+
"step": 9500
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 2.96,
|
| 549 |
+
"eval_accuracy": 95.89999999999999,
|
| 550 |
+
"eval_average_metrics": 95.89999999999999,
|
| 551 |
+
"eval_loss": 0.04831766337156296,
|
| 552 |
+
"eval_runtime": 4.7844,
|
| 553 |
+
"eval_samples_per_second": 209.012,
|
| 554 |
+
"step": 9600
|
| 555 |
},
|
| 556 |
{
|
| 557 |
"epoch": 3.0,
|
| 558 |
+
"step": 9726,
|
| 559 |
+
"total_flos": 4.195152360543514e+16,
|
| 560 |
+
"train_loss": 0.07298248127461363,
|
| 561 |
+
"train_runtime": 3523.2101,
|
| 562 |
+
"train_samples_per_second": 88.337,
|
| 563 |
+
"train_steps_per_second": 2.761
|
| 564 |
}
|
| 565 |
],
|
| 566 |
+
"max_steps": 9726,
|
| 567 |
"num_train_epochs": 3,
|
| 568 |
+
"total_flos": 4.195152360543514e+16,
|
| 569 |
"trial_name": null,
|
| 570 |
"trial_params": null
|
| 571 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3183
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa2c74f82503d69a25e90e8b4d0c21500ef081800a6efcbd1692b97c957aa724
|
| 3 |
size 3183
|
training_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"
|
|
|
|
| 1 |
+
{"dataset_config_name": ["en"], "delta_type": "lora", "do_eval": true, "do_test": true, "do_train": true, "eval_dataset_config_name": ["en"], "eval_dataset_name": "qnli", "eval_steps": 200, "evaluation_strategy": "steps", "greater_is_better": true, "learning_rate": 0.0003, "load_best_model_at_end": true, "lora_r": 8, "max_source_length": 128, "metric_for_best_model": "average_metrics", "model_name_or_path": "../../../../plm_cache/t5-base", "num_train_epochs": 3, "output_dir": "outputs/bitfit/t5-base/qnli", "overwrite_output_dir": true, "per_device_eval_batch_size": 32, "per_device_train_batch_size": 32, "predict_with_generate": true, "push_to_hub": true, "save_steps": 200, "save_strategy": "steps", "save_total_limit": 1, "seed": 42, "split_validation_test": true, "task_name": "qnli", "test_dataset_config_name": ["en"], "test_dataset_name": "qnli", "tokenizer_name": "../../../../plm_cache/t5-base", "unfrozen_modules": ["deltas", "layer_norm", "final_layer_norm"], "warmup_steps": 0}
|