Upload final best ARBERT sub-meter classifier
Browse files- README.md +98 -0
- all_results.json +8 -0
- model.safetensors +1 -1
- train_results.json +8 -0
- trainer_state.json +655 -0
README.md
ADDED
|
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
base_model: UBC-NLP/ARBERT
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: ARBERT-base-submeter-classifier
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# ARBERT-base-submeter-classifier
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [UBC-NLP/ARBERT](https://huggingface.co/UBC-NLP/ARBERT) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.1113
|
| 21 |
+
- Accuracy: 0.9709
|
| 22 |
+
- Macro F1: 0.6021
|
| 23 |
+
- Weighted F1: 0.9654
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 5e-05
|
| 43 |
+
- train_batch_size: 128
|
| 44 |
+
- eval_batch_size: 256
|
| 45 |
+
- seed: 42
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 256
|
| 48 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- num_epochs: 3
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Macro F1 | Weighted F1 |
|
| 56 |
+
|:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:|:-----------:|
|
| 57 |
+
| 1.2986 | 0.0865 | 500 | 0.7567 | 0.7652 | 0.2987 | 0.7566 |
|
| 58 |
+
| 0.5963 | 0.1730 | 1000 | 0.4073 | 0.8766 | 0.4198 | 0.8677 |
|
| 59 |
+
| 0.3789 | 0.2594 | 1500 | 0.2946 | 0.9137 | 0.4782 | 0.9067 |
|
| 60 |
+
| 0.2838 | 0.3459 | 2000 | 0.2346 | 0.9315 | 0.5072 | 0.9263 |
|
| 61 |
+
| 0.2401 | 0.4324 | 2500 | 0.2036 | 0.9422 | 0.5251 | 0.9357 |
|
| 62 |
+
| 0.2168 | 0.5189 | 3000 | 0.1820 | 0.9480 | 0.5299 | 0.9418 |
|
| 63 |
+
| 0.1955 | 0.6054 | 3500 | 0.1703 | 0.9519 | 0.5376 | 0.9455 |
|
| 64 |
+
| 0.1782 | 0.6919 | 4000 | 0.1578 | 0.9557 | 0.5499 | 0.9496 |
|
| 65 |
+
| 0.1699 | 0.7783 | 4500 | 0.1534 | 0.9571 | 0.5466 | 0.9508 |
|
| 66 |
+
| 0.1622 | 0.8648 | 5000 | 0.1496 | 0.9585 | 0.5579 | 0.9523 |
|
| 67 |
+
| 0.1569 | 0.9513 | 5500 | 0.1450 | 0.9602 | 0.5472 | 0.9537 |
|
| 68 |
+
| 0.1422 | 1.0377 | 6000 | 0.1469 | 0.9593 | 0.5690 | 0.9533 |
|
| 69 |
+
| 0.1251 | 1.1242 | 6500 | 0.1369 | 0.9628 | 0.5801 | 0.9568 |
|
| 70 |
+
| 0.123 | 1.2107 | 7000 | 0.1349 | 0.9632 | 0.5686 | 0.9571 |
|
| 71 |
+
| 0.1208 | 1.2972 | 7500 | 0.1337 | 0.9639 | 0.5747 | 0.9577 |
|
| 72 |
+
| 0.1188 | 1.3836 | 8000 | 0.1307 | 0.9645 | 0.5725 | 0.9581 |
|
| 73 |
+
| 0.1201 | 1.4701 | 8500 | 0.1295 | 0.9651 | 0.5705 | 0.9588 |
|
| 74 |
+
| 0.118 | 1.5566 | 9000 | 0.1271 | 0.9657 | 0.5692 | 0.9594 |
|
| 75 |
+
| 0.1167 | 1.6431 | 9500 | 0.1259 | 0.9662 | 0.5795 | 0.9600 |
|
| 76 |
+
| 0.1133 | 1.7296 | 10000 | 0.1220 | 0.9671 | 0.5803 | 0.9609 |
|
| 77 |
+
| 0.1116 | 1.8161 | 10500 | 0.1210 | 0.9674 | 0.5835 | 0.9612 |
|
| 78 |
+
| 0.1103 | 1.9025 | 11000 | 0.1165 | 0.9685 | 0.5836 | 0.9623 |
|
| 79 |
+
| 0.1093 | 1.9890 | 11500 | 0.1172 | 0.9683 | 0.5835 | 0.9623 |
|
| 80 |
+
| 0.0899 | 2.0754 | 12000 | 0.1174 | 0.9689 | 0.5972 | 0.9632 |
|
| 81 |
+
| 0.0851 | 2.1619 | 12500 | 0.1171 | 0.9692 | 0.5858 | 0.9632 |
|
| 82 |
+
| 0.0862 | 2.2484 | 13000 | 0.1172 | 0.9688 | 0.5902 | 0.9635 |
|
| 83 |
+
| 0.0835 | 2.3349 | 13500 | 0.1162 | 0.9696 | 0.5970 | 0.9638 |
|
| 84 |
+
| 0.0854 | 2.4213 | 14000 | 0.1159 | 0.9694 | 0.5925 | 0.9639 |
|
| 85 |
+
| 0.0797 | 2.5078 | 14500 | 0.1157 | 0.9698 | 0.5934 | 0.9640 |
|
| 86 |
+
| 0.0819 | 2.5943 | 15000 | 0.1152 | 0.9698 | 0.6004 | 0.9643 |
|
| 87 |
+
| 0.0813 | 2.6808 | 15500 | 0.1135 | 0.9703 | 0.5964 | 0.9646 |
|
| 88 |
+
| 0.0792 | 2.7673 | 16000 | 0.1120 | 0.9706 | 0.6000 | 0.9649 |
|
| 89 |
+
| 0.0786 | 2.8538 | 16500 | 0.1116 | 0.9707 | 0.6010 | 0.9653 |
|
| 90 |
+
| 0.0789 | 2.9402 | 17000 | 0.1113 | 0.9709 | 0.6021 | 0.9654 |
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
### Framework versions
|
| 94 |
+
|
| 95 |
+
- Transformers 4.57.6
|
| 96 |
+
- Pytorch 2.10.0+cu128
|
| 97 |
+
- Datasets 3.6.0
|
| 98 |
+
- Tokenizers 0.22.2
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 7.302829698913882e+16,
|
| 4 |
+
"train_loss": 0.18075496944522934,
|
| 5 |
+
"train_runtime": 31524.4633,
|
| 6 |
+
"train_samples_per_second": 140.843,
|
| 7 |
+
"train_steps_per_second": 0.55
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 651465828
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a50330db4c30408b0d667e66275ea8ddd76919ff801ccbdb36b76b7033c822f
|
| 3 |
size 651465828
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 7.302829698913882e+16,
|
| 4 |
+
"train_loss": 0.18075496944522934,
|
| 5 |
+
"train_runtime": 31524.4633,
|
| 6 |
+
"train_samples_per_second": 140.843,
|
| 7 |
+
"train_steps_per_second": 0.55
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,655 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 17000,
|
| 3 |
+
"best_metric": 0.9708837837837838,
|
| 4 |
+
"best_model_checkpoint": "/kaggle/working/arbert_submeter_training/checkpoints/checkpoint-17000",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 17346,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.08648274669203494,
|
| 14 |
+
"grad_norm": 25.747224807739258,
|
| 15 |
+
"learning_rate": 4.856162804104693e-05,
|
| 16 |
+
"loss": 1.2986,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.08648274669203494,
|
| 21 |
+
"eval_accuracy": 0.765245945945946,
|
| 22 |
+
"eval_loss": 0.756655216217041,
|
| 23 |
+
"eval_macro_f1": 0.2987486877044399,
|
| 24 |
+
"eval_runtime": 418.3804,
|
| 25 |
+
"eval_samples_per_second": 884.363,
|
| 26 |
+
"eval_steps_per_second": 3.456,
|
| 27 |
+
"eval_weighted_f1": 0.7565798837380349,
|
| 28 |
+
"step": 500
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.17296549338406988,
|
| 32 |
+
"grad_norm": 7.156609535217285,
|
| 33 |
+
"learning_rate": 4.7120373573158074e-05,
|
| 34 |
+
"loss": 0.5963,
|
| 35 |
+
"step": 1000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.17296549338406988,
|
| 39 |
+
"eval_accuracy": 0.8766405405405405,
|
| 40 |
+
"eval_loss": 0.40730020403862,
|
| 41 |
+
"eval_macro_f1": 0.4197539556932673,
|
| 42 |
+
"eval_runtime": 418.1054,
|
| 43 |
+
"eval_samples_per_second": 884.944,
|
| 44 |
+
"eval_steps_per_second": 3.458,
|
| 45 |
+
"eval_weighted_f1": 0.8676584583901654,
|
| 46 |
+
"step": 1000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.25944824007610484,
|
| 50 |
+
"grad_norm": 6.3231658935546875,
|
| 51 |
+
"learning_rate": 4.567911910526923e-05,
|
| 52 |
+
"loss": 0.3789,
|
| 53 |
+
"step": 1500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.25944824007610484,
|
| 57 |
+
"eval_accuracy": 0.9137351351351352,
|
| 58 |
+
"eval_loss": 0.2946445643901825,
|
| 59 |
+
"eval_macro_f1": 0.47816321808462303,
|
| 60 |
+
"eval_runtime": 418.8729,
|
| 61 |
+
"eval_samples_per_second": 883.323,
|
| 62 |
+
"eval_steps_per_second": 3.452,
|
| 63 |
+
"eval_weighted_f1": 0.9066607985127312,
|
| 64 |
+
"step": 1500
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.34593098676813977,
|
| 68 |
+
"grad_norm": 9.21304988861084,
|
| 69 |
+
"learning_rate": 4.423786463738038e-05,
|
| 70 |
+
"loss": 0.2838,
|
| 71 |
+
"step": 2000
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.34593098676813977,
|
| 75 |
+
"eval_accuracy": 0.9314702702702703,
|
| 76 |
+
"eval_loss": 0.23459294438362122,
|
| 77 |
+
"eval_macro_f1": 0.5072222949676094,
|
| 78 |
+
"eval_runtime": 418.1997,
|
| 79 |
+
"eval_samples_per_second": 884.745,
|
| 80 |
+
"eval_steps_per_second": 3.458,
|
| 81 |
+
"eval_weighted_f1": 0.9263247220377161,
|
| 82 |
+
"step": 2000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.4324137334601747,
|
| 86 |
+
"grad_norm": 6.399903297424316,
|
| 87 |
+
"learning_rate": 4.279661016949153e-05,
|
| 88 |
+
"loss": 0.2401,
|
| 89 |
+
"step": 2500
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.4324137334601747,
|
| 93 |
+
"eval_accuracy": 0.9421918918918919,
|
| 94 |
+
"eval_loss": 0.20360097289085388,
|
| 95 |
+
"eval_macro_f1": 0.5251223211604551,
|
| 96 |
+
"eval_runtime": 418.9782,
|
| 97 |
+
"eval_samples_per_second": 883.101,
|
| 98 |
+
"eval_steps_per_second": 3.451,
|
| 99 |
+
"eval_weighted_f1": 0.9356836777939385,
|
| 100 |
+
"step": 2500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5188964801522097,
|
| 104 |
+
"grad_norm": 7.528863906860352,
|
| 105 |
+
"learning_rate": 4.135535570160268e-05,
|
| 106 |
+
"loss": 0.2168,
|
| 107 |
+
"step": 3000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5188964801522097,
|
| 111 |
+
"eval_accuracy": 0.947972972972973,
|
| 112 |
+
"eval_loss": 0.1820368617773056,
|
| 113 |
+
"eval_macro_f1": 0.5299222018041627,
|
| 114 |
+
"eval_runtime": 418.5666,
|
| 115 |
+
"eval_samples_per_second": 883.969,
|
| 116 |
+
"eval_steps_per_second": 3.455,
|
| 117 |
+
"eval_weighted_f1": 0.9417715175152749,
|
| 118 |
+
"step": 3000
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.6053792268442446,
|
| 122 |
+
"grad_norm": 3.640698194503784,
|
| 123 |
+
"learning_rate": 3.9914101233713826e-05,
|
| 124 |
+
"loss": 0.1955,
|
| 125 |
+
"step": 3500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.6053792268442446,
|
| 129 |
+
"eval_accuracy": 0.9518621621621621,
|
| 130 |
+
"eval_loss": 0.17032282054424286,
|
| 131 |
+
"eval_macro_f1": 0.5375603114820035,
|
| 132 |
+
"eval_runtime": 418.6948,
|
| 133 |
+
"eval_samples_per_second": 883.699,
|
| 134 |
+
"eval_steps_per_second": 3.454,
|
| 135 |
+
"eval_weighted_f1": 0.9454971013709563,
|
| 136 |
+
"step": 3500
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.6918619735362795,
|
| 140 |
+
"grad_norm": 5.204596996307373,
|
| 141 |
+
"learning_rate": 3.847284676582498e-05,
|
| 142 |
+
"loss": 0.1782,
|
| 143 |
+
"step": 4000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.6918619735362795,
|
| 147 |
+
"eval_accuracy": 0.9557081081081081,
|
| 148 |
+
"eval_loss": 0.15780550241470337,
|
| 149 |
+
"eval_macro_f1": 0.5498663380782979,
|
| 150 |
+
"eval_runtime": 418.4036,
|
| 151 |
+
"eval_samples_per_second": 884.314,
|
| 152 |
+
"eval_steps_per_second": 3.456,
|
| 153 |
+
"eval_weighted_f1": 0.9495774047836557,
|
| 154 |
+
"step": 4000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.7783447202283145,
|
| 158 |
+
"grad_norm": 2.9452965259552,
|
| 159 |
+
"learning_rate": 3.7031592297936126e-05,
|
| 160 |
+
"loss": 0.1699,
|
| 161 |
+
"step": 4500
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.7783447202283145,
|
| 165 |
+
"eval_accuracy": 0.9571459459459459,
|
| 166 |
+
"eval_loss": 0.15344275534152985,
|
| 167 |
+
"eval_macro_f1": 0.5465995200000592,
|
| 168 |
+
"eval_runtime": 418.0876,
|
| 169 |
+
"eval_samples_per_second": 884.982,
|
| 170 |
+
"eval_steps_per_second": 3.459,
|
| 171 |
+
"eval_weighted_f1": 0.9507761247869798,
|
| 172 |
+
"step": 4500
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.8648274669203494,
|
| 176 |
+
"grad_norm": 5.704383850097656,
|
| 177 |
+
"learning_rate": 3.559033783004728e-05,
|
| 178 |
+
"loss": 0.1622,
|
| 179 |
+
"step": 5000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.8648274669203494,
|
| 183 |
+
"eval_accuracy": 0.9585405405405405,
|
| 184 |
+
"eval_loss": 0.1496480107307434,
|
| 185 |
+
"eval_macro_f1": 0.5578920159472586,
|
| 186 |
+
"eval_runtime": 418.0713,
|
| 187 |
+
"eval_samples_per_second": 885.017,
|
| 188 |
+
"eval_steps_per_second": 3.459,
|
| 189 |
+
"eval_weighted_f1": 0.9523043519198916,
|
| 190 |
+
"step": 5000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.9513102136123843,
|
| 194 |
+
"grad_norm": 3.2097666263580322,
|
| 195 |
+
"learning_rate": 3.4149083362158425e-05,
|
| 196 |
+
"loss": 0.1569,
|
| 197 |
+
"step": 5500
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.9513102136123843,
|
| 201 |
+
"eval_accuracy": 0.9602459459459459,
|
| 202 |
+
"eval_loss": 0.14497891068458557,
|
| 203 |
+
"eval_macro_f1": 0.5471822620722766,
|
| 204 |
+
"eval_runtime": 418.9758,
|
| 205 |
+
"eval_samples_per_second": 883.106,
|
| 206 |
+
"eval_steps_per_second": 3.451,
|
| 207 |
+
"eval_weighted_f1": 0.9536733224654437,
|
| 208 |
+
"step": 5500
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.0377064775577272,
|
| 212 |
+
"grad_norm": 4.706158638000488,
|
| 213 |
+
"learning_rate": 3.270782889426958e-05,
|
| 214 |
+
"loss": 0.1422,
|
| 215 |
+
"step": 6000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.0377064775577272,
|
| 219 |
+
"eval_accuracy": 0.9593081081081081,
|
| 220 |
+
"eval_loss": 0.1468845158815384,
|
| 221 |
+
"eval_macro_f1": 0.5689795604124087,
|
| 222 |
+
"eval_runtime": 420.1108,
|
| 223 |
+
"eval_samples_per_second": 880.72,
|
| 224 |
+
"eval_steps_per_second": 3.442,
|
| 225 |
+
"eval_weighted_f1": 0.9533441467822756,
|
| 226 |
+
"step": 6000
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.1241892242497622,
|
| 230 |
+
"grad_norm": 3.167544364929199,
|
| 231 |
+
"learning_rate": 3.1266574426380724e-05,
|
| 232 |
+
"loss": 0.1251,
|
| 233 |
+
"step": 6500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.1241892242497622,
|
| 237 |
+
"eval_accuracy": 0.9628189189189189,
|
| 238 |
+
"eval_loss": 0.13693760335445404,
|
| 239 |
+
"eval_macro_f1": 0.5800974551510764,
|
| 240 |
+
"eval_runtime": 420.0357,
|
| 241 |
+
"eval_samples_per_second": 880.877,
|
| 242 |
+
"eval_steps_per_second": 3.443,
|
| 243 |
+
"eval_weighted_f1": 0.9568010100001315,
|
| 244 |
+
"step": 6500
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.210671970941797,
|
| 248 |
+
"grad_norm": 2.2167930603027344,
|
| 249 |
+
"learning_rate": 2.982531995849187e-05,
|
| 250 |
+
"loss": 0.123,
|
| 251 |
+
"step": 7000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.210671970941797,
|
| 255 |
+
"eval_accuracy": 0.9632054054054054,
|
| 256 |
+
"eval_loss": 0.1349489837884903,
|
| 257 |
+
"eval_macro_f1": 0.5686206184279916,
|
| 258 |
+
"eval_runtime": 419.1921,
|
| 259 |
+
"eval_samples_per_second": 882.65,
|
| 260 |
+
"eval_steps_per_second": 3.449,
|
| 261 |
+
"eval_weighted_f1": 0.9570982563798056,
|
| 262 |
+
"step": 7000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.297154717633832,
|
| 266 |
+
"grad_norm": 3.8189609050750732,
|
| 267 |
+
"learning_rate": 2.8384065490603024e-05,
|
| 268 |
+
"loss": 0.1208,
|
| 269 |
+
"step": 7500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.297154717633832,
|
| 273 |
+
"eval_accuracy": 0.963927027027027,
|
| 274 |
+
"eval_loss": 0.13370193541049957,
|
| 275 |
+
"eval_macro_f1": 0.5746596478621987,
|
| 276 |
+
"eval_runtime": 418.7013,
|
| 277 |
+
"eval_samples_per_second": 883.685,
|
| 278 |
+
"eval_steps_per_second": 3.454,
|
| 279 |
+
"eval_weighted_f1": 0.9576970198616988,
|
| 280 |
+
"step": 7500
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.3836374643258669,
|
| 284 |
+
"grad_norm": 4.8342461585998535,
|
| 285 |
+
"learning_rate": 2.694281102271417e-05,
|
| 286 |
+
"loss": 0.1188,
|
| 287 |
+
"step": 8000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.3836374643258669,
|
| 291 |
+
"eval_accuracy": 0.964472972972973,
|
| 292 |
+
"eval_loss": 0.13066376745700836,
|
| 293 |
+
"eval_macro_f1": 0.5725448949887878,
|
| 294 |
+
"eval_runtime": 418.7971,
|
| 295 |
+
"eval_samples_per_second": 883.483,
|
| 296 |
+
"eval_steps_per_second": 3.453,
|
| 297 |
+
"eval_weighted_f1": 0.9581300625445718,
|
| 298 |
+
"step": 8000
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.470120211017902,
|
| 302 |
+
"grad_norm": 3.3662569522857666,
|
| 303 |
+
"learning_rate": 2.5501556554825323e-05,
|
| 304 |
+
"loss": 0.1201,
|
| 305 |
+
"step": 8500
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.470120211017902,
|
| 309 |
+
"eval_accuracy": 0.9651378378378378,
|
| 310 |
+
"eval_loss": 0.12952136993408203,
|
| 311 |
+
"eval_macro_f1": 0.5705480082509794,
|
| 312 |
+
"eval_runtime": 418.5068,
|
| 313 |
+
"eval_samples_per_second": 884.095,
|
| 314 |
+
"eval_steps_per_second": 3.455,
|
| 315 |
+
"eval_weighted_f1": 0.9587555599089429,
|
| 316 |
+
"step": 8500
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.556602957709937,
|
| 320 |
+
"grad_norm": 3.425612211227417,
|
| 321 |
+
"learning_rate": 2.406030208693647e-05,
|
| 322 |
+
"loss": 0.118,
|
| 323 |
+
"step": 9000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.556602957709937,
|
| 327 |
+
"eval_accuracy": 0.965654054054054,
|
| 328 |
+
"eval_loss": 0.1270706057548523,
|
| 329 |
+
"eval_macro_f1": 0.5691587584053437,
|
| 330 |
+
"eval_runtime": 419.0634,
|
| 331 |
+
"eval_samples_per_second": 882.921,
|
| 332 |
+
"eval_steps_per_second": 3.451,
|
| 333 |
+
"eval_weighted_f1": 0.9593746302255395,
|
| 334 |
+
"step": 9000
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.6430857044019718,
|
| 338 |
+
"grad_norm": 1.4031856060028076,
|
| 339 |
+
"learning_rate": 2.261904761904762e-05,
|
| 340 |
+
"loss": 0.1167,
|
| 341 |
+
"step": 9500
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.6430857044019718,
|
| 345 |
+
"eval_accuracy": 0.9661621621621621,
|
| 346 |
+
"eval_loss": 0.125877246260643,
|
| 347 |
+
"eval_macro_f1": 0.5795209016258601,
|
| 348 |
+
"eval_runtime": 418.9995,
|
| 349 |
+
"eval_samples_per_second": 883.056,
|
| 350 |
+
"eval_steps_per_second": 3.451,
|
| 351 |
+
"eval_weighted_f1": 0.9600300931445321,
|
| 352 |
+
"step": 9500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.7295684510940066,
|
| 356 |
+
"grad_norm": 2.918519973754883,
|
| 357 |
+
"learning_rate": 2.117779315115877e-05,
|
| 358 |
+
"loss": 0.1133,
|
| 359 |
+
"step": 10000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.7295684510940066,
|
| 363 |
+
"eval_accuracy": 0.9670945945945946,
|
| 364 |
+
"eval_loss": 0.12201372534036636,
|
| 365 |
+
"eval_macro_f1": 0.5803247802424795,
|
| 366 |
+
"eval_runtime": 418.9179,
|
| 367 |
+
"eval_samples_per_second": 883.228,
|
| 368 |
+
"eval_steps_per_second": 3.452,
|
| 369 |
+
"eval_weighted_f1": 0.9608891715468071,
|
| 370 |
+
"step": 10000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.8160511977860416,
|
| 374 |
+
"grad_norm": 2.741220712661743,
|
| 375 |
+
"learning_rate": 1.973653868326992e-05,
|
| 376 |
+
"loss": 0.1116,
|
| 377 |
+
"step": 10500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.8160511977860416,
|
| 381 |
+
"eval_accuracy": 0.9673864864864865,
|
| 382 |
+
"eval_loss": 0.12097315490245819,
|
| 383 |
+
"eval_macro_f1": 0.5834823701825592,
|
| 384 |
+
"eval_runtime": 418.7157,
|
| 385 |
+
"eval_samples_per_second": 883.654,
|
| 386 |
+
"eval_steps_per_second": 3.453,
|
| 387 |
+
"eval_weighted_f1": 0.9612394940368674,
|
| 388 |
+
"step": 10500
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.9025339444780767,
|
| 392 |
+
"grad_norm": 2.6713507175445557,
|
| 393 |
+
"learning_rate": 1.8295284215381068e-05,
|
| 394 |
+
"loss": 0.1103,
|
| 395 |
+
"step": 11000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.9025339444780767,
|
| 399 |
+
"eval_accuracy": 0.9684972972972973,
|
| 400 |
+
"eval_loss": 0.11646272242069244,
|
| 401 |
+
"eval_macro_f1": 0.5835802563966344,
|
| 402 |
+
"eval_runtime": 418.3811,
|
| 403 |
+
"eval_samples_per_second": 884.361,
|
| 404 |
+
"eval_steps_per_second": 3.456,
|
| 405 |
+
"eval_weighted_f1": 0.9622871010076606,
|
| 406 |
+
"step": 11000
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.9890166911701117,
|
| 410 |
+
"grad_norm": 2.58137845993042,
|
| 411 |
+
"learning_rate": 1.6854029747492218e-05,
|
| 412 |
+
"loss": 0.1093,
|
| 413 |
+
"step": 11500
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.9890166911701117,
|
| 417 |
+
"eval_accuracy": 0.9683432432432433,
|
| 418 |
+
"eval_loss": 0.11723459511995316,
|
| 419 |
+
"eval_macro_f1": 0.5835321485745915,
|
| 420 |
+
"eval_runtime": 419.3158,
|
| 421 |
+
"eval_samples_per_second": 882.39,
|
| 422 |
+
"eval_steps_per_second": 3.448,
|
| 423 |
+
"eval_weighted_f1": 0.9623140045622489,
|
| 424 |
+
"step": 11500
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 2.0754129551154543,
|
| 428 |
+
"grad_norm": 3.1163055896759033,
|
| 429 |
+
"learning_rate": 1.5412775279603368e-05,
|
| 430 |
+
"loss": 0.0899,
|
| 431 |
+
"step": 12000
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.0754129551154543,
|
| 435 |
+
"eval_accuracy": 0.9689324324324324,
|
| 436 |
+
"eval_loss": 0.11741844564676285,
|
| 437 |
+
"eval_macro_f1": 0.5972224837605217,
|
| 438 |
+
"eval_runtime": 419.245,
|
| 439 |
+
"eval_samples_per_second": 882.539,
|
| 440 |
+
"eval_steps_per_second": 3.449,
|
| 441 |
+
"eval_weighted_f1": 0.9632448268921581,
|
| 442 |
+
"step": 12000
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 2.1618957018074894,
|
| 446 |
+
"grad_norm": 2.067152738571167,
|
| 447 |
+
"learning_rate": 1.3971520811714517e-05,
|
| 448 |
+
"loss": 0.0851,
|
| 449 |
+
"step": 12500
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.1618957018074894,
|
| 453 |
+
"eval_accuracy": 0.9692378378378378,
|
| 454 |
+
"eval_loss": 0.11705382913351059,
|
| 455 |
+
"eval_macro_f1": 0.5857631212432319,
|
| 456 |
+
"eval_runtime": 419.6262,
|
| 457 |
+
"eval_samples_per_second": 881.737,
|
| 458 |
+
"eval_steps_per_second": 3.446,
|
| 459 |
+
"eval_weighted_f1": 0.9632093509253533,
|
| 460 |
+
"step": 12500
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 2.2483784484995244,
|
| 464 |
+
"grad_norm": 1.862592339515686,
|
| 465 |
+
"learning_rate": 1.2530266343825667e-05,
|
| 466 |
+
"loss": 0.0862,
|
| 467 |
+
"step": 13000
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 2.2483784484995244,
|
| 471 |
+
"eval_accuracy": 0.9688189189189189,
|
| 472 |
+
"eval_loss": 0.11716984957456589,
|
| 473 |
+
"eval_macro_f1": 0.590216690584949,
|
| 474 |
+
"eval_runtime": 418.913,
|
| 475 |
+
"eval_samples_per_second": 883.238,
|
| 476 |
+
"eval_steps_per_second": 3.452,
|
| 477 |
+
"eval_weighted_f1": 0.9634743085321129,
|
| 478 |
+
"step": 13000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.3348611951915594,
|
| 482 |
+
"grad_norm": 2.883910655975342,
|
| 483 |
+
"learning_rate": 1.1089011875936815e-05,
|
| 484 |
+
"loss": 0.0835,
|
| 485 |
+
"step": 13500
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.3348611951915594,
|
| 489 |
+
"eval_accuracy": 0.9696405405405405,
|
| 490 |
+
"eval_loss": 0.11618903279304504,
|
| 491 |
+
"eval_macro_f1": 0.5970308633746413,
|
| 492 |
+
"eval_runtime": 418.887,
|
| 493 |
+
"eval_samples_per_second": 883.293,
|
| 494 |
+
"eval_steps_per_second": 3.452,
|
| 495 |
+
"eval_weighted_f1": 0.9638159327084403,
|
| 496 |
+
"step": 13500
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.421343941883594,
|
| 500 |
+
"grad_norm": 0.7860650420188904,
|
| 501 |
+
"learning_rate": 9.647757408047965e-06,
|
| 502 |
+
"loss": 0.0854,
|
| 503 |
+
"step": 14000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.421343941883594,
|
| 507 |
+
"eval_accuracy": 0.9694459459459459,
|
| 508 |
+
"eval_loss": 0.1158711388707161,
|
| 509 |
+
"eval_macro_f1": 0.592536606494846,
|
| 510 |
+
"eval_runtime": 419.3296,
|
| 511 |
+
"eval_samples_per_second": 882.361,
|
| 512 |
+
"eval_steps_per_second": 3.448,
|
| 513 |
+
"eval_weighted_f1": 0.9638996969783739,
|
| 514 |
+
"step": 14000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.507826688575629,
|
| 518 |
+
"grad_norm": 3.2249786853790283,
|
| 519 |
+
"learning_rate": 8.206502940159114e-06,
|
| 520 |
+
"loss": 0.0797,
|
| 521 |
+
"step": 14500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 2.507826688575629,
|
| 525 |
+
"eval_accuracy": 0.9697621621621622,
|
| 526 |
+
"eval_loss": 0.11566793918609619,
|
| 527 |
+
"eval_macro_f1": 0.5934226559634111,
|
| 528 |
+
"eval_runtime": 420.7367,
|
| 529 |
+
"eval_samples_per_second": 879.41,
|
| 530 |
+
"eval_steps_per_second": 3.437,
|
| 531 |
+
"eval_weighted_f1": 0.964013311849684,
|
| 532 |
+
"step": 14500
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.594309435267664,
|
| 536 |
+
"grad_norm": 4.085644245147705,
|
| 537 |
+
"learning_rate": 6.765248472270265e-06,
|
| 538 |
+
"loss": 0.0819,
|
| 539 |
+
"step": 15000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.594309435267664,
|
| 543 |
+
"eval_accuracy": 0.9698027027027027,
|
| 544 |
+
"eval_loss": 0.1152041032910347,
|
| 545 |
+
"eval_macro_f1": 0.6003991642644262,
|
| 546 |
+
"eval_runtime": 419.1122,
|
| 547 |
+
"eval_samples_per_second": 882.818,
|
| 548 |
+
"eval_steps_per_second": 3.45,
|
| 549 |
+
"eval_weighted_f1": 0.9643335590541979,
|
| 550 |
+
"step": 15000
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.680792181959699,
|
| 554 |
+
"grad_norm": 2.286464214324951,
|
| 555 |
+
"learning_rate": 5.323994004381414e-06,
|
| 556 |
+
"loss": 0.0813,
|
| 557 |
+
"step": 15500
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.680792181959699,
|
| 561 |
+
"eval_accuracy": 0.9702864864864865,
|
| 562 |
+
"eval_loss": 0.1135055348277092,
|
| 563 |
+
"eval_macro_f1": 0.5963674935323597,
|
| 564 |
+
"eval_runtime": 419.7981,
|
| 565 |
+
"eval_samples_per_second": 881.376,
|
| 566 |
+
"eval_steps_per_second": 3.445,
|
| 567 |
+
"eval_weighted_f1": 0.9645615895626319,
|
| 568 |
+
"step": 15500
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 2.7672749286517337,
|
| 572 |
+
"grad_norm": 2.7449326515197754,
|
| 573 |
+
"learning_rate": 3.882739536492564e-06,
|
| 574 |
+
"loss": 0.0792,
|
| 575 |
+
"step": 16000
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 2.7672749286517337,
|
| 579 |
+
"eval_accuracy": 0.9706054054054054,
|
| 580 |
+
"eval_loss": 0.1119714081287384,
|
| 581 |
+
"eval_macro_f1": 0.6000477857320852,
|
| 582 |
+
"eval_runtime": 419.5757,
|
| 583 |
+
"eval_samples_per_second": 881.843,
|
| 584 |
+
"eval_steps_per_second": 3.446,
|
| 585 |
+
"eval_weighted_f1": 0.9649497278700637,
|
| 586 |
+
"step": 16000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.853757675343769,
|
| 590 |
+
"grad_norm": 1.0509530305862427,
|
| 591 |
+
"learning_rate": 2.441485068603713e-06,
|
| 592 |
+
"loss": 0.0786,
|
| 593 |
+
"step": 16500
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 2.853757675343769,
|
| 597 |
+
"eval_accuracy": 0.9707135135135135,
|
| 598 |
+
"eval_loss": 0.11158089339733124,
|
| 599 |
+
"eval_macro_f1": 0.6009545374695694,
|
| 600 |
+
"eval_runtime": 418.9418,
|
| 601 |
+
"eval_samples_per_second": 883.178,
|
| 602 |
+
"eval_steps_per_second": 3.452,
|
| 603 |
+
"eval_weighted_f1": 0.9653056586898462,
|
| 604 |
+
"step": 16500
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.940240422035804,
|
| 608 |
+
"grad_norm": 0.9345380663871765,
|
| 609 |
+
"learning_rate": 1.0002306007148624e-06,
|
| 610 |
+
"loss": 0.0789,
|
| 611 |
+
"step": 17000
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 2.940240422035804,
|
| 615 |
+
"eval_accuracy": 0.9708837837837838,
|
| 616 |
+
"eval_loss": 0.11126039922237396,
|
| 617 |
+
"eval_macro_f1": 0.6020869942813024,
|
| 618 |
+
"eval_runtime": 419.4331,
|
| 619 |
+
"eval_samples_per_second": 882.143,
|
| 620 |
+
"eval_steps_per_second": 3.448,
|
| 621 |
+
"eval_weighted_f1": 0.9654166847298334,
|
| 622 |
+
"step": 17000
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 3.0,
|
| 626 |
+
"step": 17346,
|
| 627 |
+
"total_flos": 7.302829698913882e+16,
|
| 628 |
+
"train_loss": 0.18075496944522934,
|
| 629 |
+
"train_runtime": 31524.4633,
|
| 630 |
+
"train_samples_per_second": 140.843,
|
| 631 |
+
"train_steps_per_second": 0.55
|
| 632 |
+
}
|
| 633 |
+
],
|
| 634 |
+
"logging_steps": 500,
|
| 635 |
+
"max_steps": 17346,
|
| 636 |
+
"num_input_tokens_seen": 0,
|
| 637 |
+
"num_train_epochs": 3,
|
| 638 |
+
"save_steps": 500,
|
| 639 |
+
"stateful_callbacks": {
|
| 640 |
+
"TrainerControl": {
|
| 641 |
+
"args": {
|
| 642 |
+
"should_epoch_stop": false,
|
| 643 |
+
"should_evaluate": false,
|
| 644 |
+
"should_log": false,
|
| 645 |
+
"should_save": true,
|
| 646 |
+
"should_training_stop": true
|
| 647 |
+
},
|
| 648 |
+
"attributes": {}
|
| 649 |
+
}
|
| 650 |
+
},
|
| 651 |
+
"total_flos": 7.302829698913882e+16,
|
| 652 |
+
"train_batch_size": 128,
|
| 653 |
+
"trial_name": null,
|
| 654 |
+
"trial_params": null
|
| 655 |
+
}
|