Upload 18 files
Browse files- README.md +158 -1
- logs/events.out.tfevents.1709072051.serv-9216.749410.0 +3 -0
- logs/events.out.tfevents.1709072142.serv-9216.750111.0 +3 -0
- logs/events.out.tfevents.1709074878.serv-9216.750111.1 +3 -0
- logs/mt_cn_lang_adapter.png +0 -0
- mlm/adapter_config.json +41 -0
- mlm/head_config.json +14 -0
- mlm/pytorch_adapter.bin +3 -0
- mlm/pytorch_model_head.bin +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- trainer_state.json +1219 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
CHANGED
|
@@ -1,3 +1,160 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: bert-base-multilingual-cased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: mt
|
| 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 |
+
# mt
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.8117
|
| 21 |
+
- Accuracy: 0.8590
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 16
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- training_steps: 50000
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
+
|:-------------:|:------:|:-----:|:---------------:|:--------:|
|
| 53 |
+
| 2.6689 | 1.04 | 500 | 2.1345 | 0.6677 |
|
| 54 |
+
| 2.1415 | 2.07 | 1000 | 1.8436 | 0.6926 |
|
| 55 |
+
| 1.9421 | 3.11 | 1500 | 1.7874 | 0.6907 |
|
| 56 |
+
| 1.7588 | 4.14 | 2000 | 1.7605 | 0.7013 |
|
| 57 |
+
| 1.6729 | 5.18 | 2500 | 1.7568 | 0.6957 |
|
| 58 |
+
| 1.596 | 6.21 | 3000 | 1.5006 | 0.7273 |
|
| 59 |
+
| 1.5778 | 7.25 | 3500 | 1.3924 | 0.7451 |
|
| 60 |
+
| 1.4821 | 8.28 | 4000 | 1.6097 | 0.7099 |
|
| 61 |
+
| 1.4183 | 9.32 | 4500 | 1.3552 | 0.7491 |
|
| 62 |
+
| 1.4197 | 10.35 | 5000 | 1.2847 | 0.7513 |
|
| 63 |
+
| 1.3156 | 11.39 | 5500 | 1.3173 | 0.7496 |
|
| 64 |
+
| 1.2882 | 12.42 | 6000 | 1.2817 | 0.7738 |
|
| 65 |
+
| 1.2692 | 13.46 | 6500 | 1.1892 | 0.7751 |
|
| 66 |
+
| 1.2368 | 14.49 | 7000 | 1.2363 | 0.7816 |
|
| 67 |
+
| 1.1975 | 15.53 | 7500 | 1.2442 | 0.7700 |
|
| 68 |
+
| 1.1907 | 16.56 | 8000 | 1.2569 | 0.7720 |
|
| 69 |
+
| 1.1231 | 17.6 | 8500 | 1.1386 | 0.7761 |
|
| 70 |
+
| 1.0873 | 18.63 | 9000 | 1.2105 | 0.7856 |
|
| 71 |
+
| 1.1242 | 19.67 | 9500 | 1.2142 | 0.7738 |
|
| 72 |
+
| 1.0367 | 20.7 | 10000 | 1.2121 | 0.7712 |
|
| 73 |
+
| 1.0869 | 21.74 | 10500 | 1.0782 | 0.7955 |
|
| 74 |
+
| 1.0353 | 22.77 | 11000 | 0.9918 | 0.8069 |
|
| 75 |
+
| 1.0324 | 23.81 | 11500 | 1.0908 | 0.7971 |
|
| 76 |
+
| 1.0145 | 24.84 | 12000 | 1.0945 | 0.7975 |
|
| 77 |
+
| 0.9951 | 25.88 | 12500 | 1.0005 | 0.8028 |
|
| 78 |
+
| 0.9483 | 26.92 | 13000 | 0.9638 | 0.8187 |
|
| 79 |
+
| 0.9304 | 27.95 | 13500 | 0.9761 | 0.8205 |
|
| 80 |
+
| 0.8835 | 28.99 | 14000 | 1.0620 | 0.8046 |
|
| 81 |
+
| 0.9097 | 30.02 | 14500 | 0.9138 | 0.8060 |
|
| 82 |
+
| 0.9293 | 31.06 | 15000 | 0.9180 | 0.8176 |
|
| 83 |
+
| 0.9043 | 32.09 | 15500 | 0.9215 | 0.8208 |
|
| 84 |
+
| 0.8581 | 33.13 | 16000 | 0.9625 | 0.8225 |
|
| 85 |
+
| 0.8638 | 34.16 | 16500 | 0.8586 | 0.8368 |
|
| 86 |
+
| 0.874 | 35.2 | 17000 | 1.0044 | 0.8135 |
|
| 87 |
+
| 0.8235 | 36.23 | 17500 | 0.9755 | 0.8184 |
|
| 88 |
+
| 0.8589 | 37.27 | 18000 | 0.9042 | 0.8292 |
|
| 89 |
+
| 0.8107 | 38.3 | 18500 | 0.8821 | 0.8272 |
|
| 90 |
+
| 0.8346 | 39.34 | 19000 | 0.9061 | 0.8248 |
|
| 91 |
+
| 0.8393 | 40.37 | 19500 | 0.9796 | 0.8235 |
|
| 92 |
+
| 0.789 | 41.41 | 20000 | 0.9015 | 0.8331 |
|
| 93 |
+
| 0.8121 | 42.44 | 20500 | 0.8589 | 0.8386 |
|
| 94 |
+
| 0.7709 | 43.48 | 21000 | 0.8836 | 0.8351 |
|
| 95 |
+
| 0.7922 | 44.51 | 21500 | 0.9524 | 0.8180 |
|
| 96 |
+
| 0.7457 | 45.55 | 22000 | 0.8350 | 0.8364 |
|
| 97 |
+
| 0.7386 | 46.58 | 22500 | 0.9025 | 0.8341 |
|
| 98 |
+
| 0.7515 | 47.62 | 23000 | 0.9092 | 0.8390 |
|
| 99 |
+
| 0.7324 | 48.65 | 23500 | 0.8322 | 0.8421 |
|
| 100 |
+
| 0.7314 | 49.69 | 24000 | 0.7968 | 0.8477 |
|
| 101 |
+
| 0.7442 | 50.72 | 24500 | 0.9305 | 0.8324 |
|
| 102 |
+
| 0.7074 | 51.76 | 25000 | 1.0011 | 0.8208 |
|
| 103 |
+
| 0.739 | 52.8 | 25500 | 0.8732 | 0.8331 |
|
| 104 |
+
| 0.7243 | 53.83 | 26000 | 0.7857 | 0.8480 |
|
| 105 |
+
| 0.6842 | 54.87 | 26500 | 0.7945 | 0.8377 |
|
| 106 |
+
| 0.6991 | 55.9 | 27000 | 0.9628 | 0.8275 |
|
| 107 |
+
| 0.6896 | 56.94 | 27500 | 0.8363 | 0.8410 |
|
| 108 |
+
| 0.6925 | 57.97 | 28000 | 0.8433 | 0.8392 |
|
| 109 |
+
| 0.7081 | 59.01 | 28500 | 1.0086 | 0.8223 |
|
| 110 |
+
| 0.6598 | 60.04 | 29000 | 0.9251 | 0.8333 |
|
| 111 |
+
| 0.6677 | 61.08 | 29500 | 0.8823 | 0.8437 |
|
| 112 |
+
| 0.695 | 62.11 | 30000 | 0.7751 | 0.8560 |
|
| 113 |
+
| 0.7108 | 63.15 | 30500 | 0.8452 | 0.8481 |
|
| 114 |
+
| 0.6721 | 64.18 | 31000 | 0.8560 | 0.8413 |
|
| 115 |
+
| 0.6571 | 65.22 | 31500 | 0.9800 | 0.8163 |
|
| 116 |
+
| 0.6891 | 66.25 | 32000 | 0.8106 | 0.8457 |
|
| 117 |
+
| 0.6541 | 67.29 | 32500 | 0.8197 | 0.8430 |
|
| 118 |
+
| 0.6559 | 68.32 | 33000 | 0.8678 | 0.8388 |
|
| 119 |
+
| 0.6554 | 69.36 | 33500 | 0.7396 | 0.8662 |
|
| 120 |
+
| 0.618 | 70.39 | 34000 | 0.8518 | 0.8376 |
|
| 121 |
+
| 0.6558 | 71.43 | 34500 | 0.7706 | 0.8409 |
|
| 122 |
+
| 0.6034 | 72.46 | 35000 | 0.7829 | 0.8518 |
|
| 123 |
+
| 0.6336 | 73.5 | 35500 | 0.7835 | 0.8591 |
|
| 124 |
+
| 0.6287 | 74.53 | 36000 | 0.7548 | 0.8575 |
|
| 125 |
+
| 0.6065 | 75.57 | 36500 | 0.8542 | 0.8508 |
|
| 126 |
+
| 0.6029 | 76.6 | 37000 | 0.8203 | 0.8405 |
|
| 127 |
+
| 0.6208 | 77.64 | 37500 | 0.7082 | 0.8661 |
|
| 128 |
+
| 0.64 | 78.67 | 38000 | 0.8505 | 0.8410 |
|
| 129 |
+
| 0.6144 | 79.71 | 38500 | 0.7246 | 0.8604 |
|
| 130 |
+
| 0.6507 | 80.75 | 39000 | 0.7150 | 0.8611 |
|
| 131 |
+
| 0.6177 | 81.78 | 39500 | 0.9332 | 0.84 |
|
| 132 |
+
| 0.6159 | 82.82 | 40000 | 0.6427 | 0.8733 |
|
| 133 |
+
| 0.5944 | 83.85 | 40500 | 0.7721 | 0.8411 |
|
| 134 |
+
| 0.6044 | 84.89 | 41000 | 0.8968 | 0.8449 |
|
| 135 |
+
| 0.6 | 85.92 | 41500 | 0.7673 | 0.8538 |
|
| 136 |
+
| 0.5899 | 86.96 | 42000 | 0.8039 | 0.8505 |
|
| 137 |
+
| 0.5812 | 87.99 | 42500 | 0.7467 | 0.8567 |
|
| 138 |
+
| 0.5977 | 89.03 | 43000 | 0.9534 | 0.8316 |
|
| 139 |
+
| 0.6019 | 90.06 | 43500 | 0.9170 | 0.8316 |
|
| 140 |
+
| 0.563 | 91.1 | 44000 | 0.7761 | 0.8569 |
|
| 141 |
+
| 0.6347 | 92.13 | 44500 | 0.7811 | 0.8577 |
|
| 142 |
+
| 0.5855 | 93.17 | 45000 | 0.7562 | 0.8606 |
|
| 143 |
+
| 0.6026 | 94.2 | 45500 | 0.7490 | 0.8636 |
|
| 144 |
+
| 0.5846 | 95.24 | 46000 | 0.7456 | 0.8487 |
|
| 145 |
+
| 0.5635 | 96.27 | 46500 | 0.8115 | 0.8495 |
|
| 146 |
+
| 0.5903 | 97.31 | 47000 | 0.8137 | 0.8448 |
|
| 147 |
+
| 0.576 | 98.34 | 47500 | 0.8441 | 0.8424 |
|
| 148 |
+
| 0.5745 | 99.38 | 48000 | 0.7266 | 0.8609 |
|
| 149 |
+
| 0.5915 | 100.41 | 48500 | 0.9169 | 0.8446 |
|
| 150 |
+
| 0.601 | 101.45 | 49000 | 0.7671 | 0.8576 |
|
| 151 |
+
| 0.5713 | 102.48 | 49500 | 0.7868 | 0.8487 |
|
| 152 |
+
| 0.5541 | 103.52 | 50000 | 0.7907 | 0.8569 |
|
| 153 |
+
|
| 154 |
+
|
| 155 |
+
### Framework versions
|
| 156 |
+
|
| 157 |
+
- Transformers 4.35.2
|
| 158 |
+
- Pytorch 2.0.0
|
| 159 |
+
- Datasets 2.15.0
|
| 160 |
+
- Tokenizers 0.15.0
|
logs/events.out.tfevents.1709072051.serv-9216.749410.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddaec0ad57b7075839c79282f1d002e7aa290d85bb49e5bf3d69f8f197d2ae3a
|
| 3 |
+
size 4329
|
logs/events.out.tfevents.1709072142.serv-9216.750111.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e6a37360b015f0683eb910f09c1f5a1ece82ca6586f31e930ae5f0ba705669c
|
| 3 |
+
size 53301
|
logs/events.out.tfevents.1709074878.serv-9216.750111.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e10e179d23b81bdc9f9927bf3b6fceadd28fa9097939aa5c6f762b6ccaf97d3
|
| 3 |
+
size 369
|
logs/mt_cn_lang_adapter.png
ADDED
|
mlm/adapter_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"adapter_residual_before_ln": false,
|
| 4 |
+
"cross_adapter": false,
|
| 5 |
+
"factorized_phm_W": true,
|
| 6 |
+
"factorized_phm_rule": false,
|
| 7 |
+
"hypercomplex_nonlinearity": "glorot-uniform",
|
| 8 |
+
"init_weights": "bert",
|
| 9 |
+
"inv_adapter": null,
|
| 10 |
+
"inv_adapter_reduction_factor": null,
|
| 11 |
+
"is_parallel": false,
|
| 12 |
+
"learn_phm": true,
|
| 13 |
+
"leave_out": [],
|
| 14 |
+
"ln_after": false,
|
| 15 |
+
"ln_before": false,
|
| 16 |
+
"mh_adapter": false,
|
| 17 |
+
"non_linearity": "relu",
|
| 18 |
+
"original_ln_after": true,
|
| 19 |
+
"original_ln_before": true,
|
| 20 |
+
"output_adapter": true,
|
| 21 |
+
"phm_bias": true,
|
| 22 |
+
"phm_c_init": "normal",
|
| 23 |
+
"phm_dim": 4,
|
| 24 |
+
"phm_init_range": 0.0001,
|
| 25 |
+
"phm_layer": false,
|
| 26 |
+
"phm_rank": 1,
|
| 27 |
+
"reduction_factor": 16,
|
| 28 |
+
"residual_before_ln": true,
|
| 29 |
+
"scaling": 1.0,
|
| 30 |
+
"shared_W_phm": false,
|
| 31 |
+
"shared_phm_rule": true,
|
| 32 |
+
"use_gating": false
|
| 33 |
+
},
|
| 34 |
+
"config_id": "9076f36a74755ac4",
|
| 35 |
+
"hidden_size": 768,
|
| 36 |
+
"model_class": "BertForMaskedLM",
|
| 37 |
+
"model_name": "bert-base-multilingual-cased",
|
| 38 |
+
"model_type": "bert",
|
| 39 |
+
"name": "mlm",
|
| 40 |
+
"version": "0.1.1"
|
| 41 |
+
}
|
mlm/head_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": null,
|
| 3 |
+
"hidden_size": 768,
|
| 4 |
+
"label2id": {
|
| 5 |
+
"LABEL_0": 0,
|
| 6 |
+
"LABEL_1": 1
|
| 7 |
+
},
|
| 8 |
+
"model_class": "BertForMaskedLM",
|
| 9 |
+
"model_name": "bert-base-multilingual-cased",
|
| 10 |
+
"model_type": "bert",
|
| 11 |
+
"name": null,
|
| 12 |
+
"num_labels": 2,
|
| 13 |
+
"version": "0.1.1"
|
| 14 |
+
}
|
mlm/pytorch_adapter.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a77f9e21137b7aacd782b79dcf7af527615eefa4cd69bdf8b41385f3b4da3e81
|
| 3 |
+
size 3594917
|
mlm/pytorch_model_head.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad4d635f02fc17009f80b4a4372a46dc2e948966597fa74cd2facd69fbb75139
|
| 3 |
+
size 370097519
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8245911fe34ac3e760ee802b087864bb19b4cd1900156cdbbe03d5bcb3c4cbfd
|
| 3 |
+
size 11936581
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b634be18e10c459815918b699c7ee3f3bd71eb974625fdddbaac9be32efcbfc0
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45ac04db287f65dfb1b249a2c231138e4e9cf7b14bf5ff37aea1e4cda5391828
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "BertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6427481174468994,
|
| 3 |
+
"best_model_checkpoint": "./models/adapters_mlm_cn/mt/checkpoint-40000",
|
| 4 |
+
"epoch": 82.81573498964804,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 40000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.04,
|
| 13 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 14 |
+
"loss": 2.6689,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.04,
|
| 19 |
+
"eval_accuracy": 0.6676783004552352,
|
| 20 |
+
"eval_loss": 2.1344573497772217,
|
| 21 |
+
"eval_runtime": 1.6941,
|
| 22 |
+
"eval_samples_per_second": 506.449,
|
| 23 |
+
"eval_steps_per_second": 31.874,
|
| 24 |
+
"step": 500
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 2.07,
|
| 28 |
+
"learning_rate": 4.9e-05,
|
| 29 |
+
"loss": 2.1415,
|
| 30 |
+
"step": 1000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.07,
|
| 34 |
+
"eval_accuracy": 0.6926470588235294,
|
| 35 |
+
"eval_loss": 1.8435733318328857,
|
| 36 |
+
"eval_runtime": 1.6896,
|
| 37 |
+
"eval_samples_per_second": 507.824,
|
| 38 |
+
"eval_steps_per_second": 31.961,
|
| 39 |
+
"step": 1000
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.11,
|
| 43 |
+
"learning_rate": 4.85e-05,
|
| 44 |
+
"loss": 1.9421,
|
| 45 |
+
"step": 1500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.11,
|
| 49 |
+
"eval_accuracy": 0.690674753601213,
|
| 50 |
+
"eval_loss": 1.787391185760498,
|
| 51 |
+
"eval_runtime": 1.6956,
|
| 52 |
+
"eval_samples_per_second": 506.016,
|
| 53 |
+
"eval_steps_per_second": 31.847,
|
| 54 |
+
"step": 1500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 4.14,
|
| 58 |
+
"learning_rate": 4.8e-05,
|
| 59 |
+
"loss": 1.7588,
|
| 60 |
+
"step": 2000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 4.14,
|
| 64 |
+
"eval_accuracy": 0.7012509197939661,
|
| 65 |
+
"eval_loss": 1.760498285293579,
|
| 66 |
+
"eval_runtime": 1.6894,
|
| 67 |
+
"eval_samples_per_second": 507.882,
|
| 68 |
+
"eval_steps_per_second": 31.965,
|
| 69 |
+
"step": 2000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 5.18,
|
| 73 |
+
"learning_rate": 4.75e-05,
|
| 74 |
+
"loss": 1.6729,
|
| 75 |
+
"step": 2500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.18,
|
| 79 |
+
"eval_accuracy": 0.6956845238095238,
|
| 80 |
+
"eval_loss": 1.7567747831344604,
|
| 81 |
+
"eval_runtime": 1.6937,
|
| 82 |
+
"eval_samples_per_second": 506.597,
|
| 83 |
+
"eval_steps_per_second": 31.884,
|
| 84 |
+
"step": 2500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.21,
|
| 88 |
+
"learning_rate": 4.7e-05,
|
| 89 |
+
"loss": 1.596,
|
| 90 |
+
"step": 3000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 6.21,
|
| 94 |
+
"eval_accuracy": 0.7272727272727273,
|
| 95 |
+
"eval_loss": 1.5006115436553955,
|
| 96 |
+
"eval_runtime": 1.6969,
|
| 97 |
+
"eval_samples_per_second": 505.627,
|
| 98 |
+
"eval_steps_per_second": 31.823,
|
| 99 |
+
"step": 3000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 7.25,
|
| 103 |
+
"learning_rate": 4.6500000000000005e-05,
|
| 104 |
+
"loss": 1.5778,
|
| 105 |
+
"step": 3500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 7.25,
|
| 109 |
+
"eval_accuracy": 0.7450832072617246,
|
| 110 |
+
"eval_loss": 1.3923866748809814,
|
| 111 |
+
"eval_runtime": 1.6898,
|
| 112 |
+
"eval_samples_per_second": 507.75,
|
| 113 |
+
"eval_steps_per_second": 31.956,
|
| 114 |
+
"step": 3500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 8.28,
|
| 118 |
+
"learning_rate": 4.600000000000001e-05,
|
| 119 |
+
"loss": 1.4821,
|
| 120 |
+
"step": 4000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 8.28,
|
| 124 |
+
"eval_accuracy": 0.7099236641221374,
|
| 125 |
+
"eval_loss": 1.609680414199829,
|
| 126 |
+
"eval_runtime": 1.6898,
|
| 127 |
+
"eval_samples_per_second": 507.758,
|
| 128 |
+
"eval_steps_per_second": 31.957,
|
| 129 |
+
"step": 4000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 9.32,
|
| 133 |
+
"learning_rate": 4.55e-05,
|
| 134 |
+
"loss": 1.4183,
|
| 135 |
+
"step": 4500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 9.32,
|
| 139 |
+
"eval_accuracy": 0.7490551776266062,
|
| 140 |
+
"eval_loss": 1.3551626205444336,
|
| 141 |
+
"eval_runtime": 1.6905,
|
| 142 |
+
"eval_samples_per_second": 507.539,
|
| 143 |
+
"eval_steps_per_second": 31.943,
|
| 144 |
+
"step": 4500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 10.35,
|
| 148 |
+
"learning_rate": 4.5e-05,
|
| 149 |
+
"loss": 1.4197,
|
| 150 |
+
"step": 5000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 10.35,
|
| 154 |
+
"eval_accuracy": 0.7513471901462664,
|
| 155 |
+
"eval_loss": 1.284741997718811,
|
| 156 |
+
"eval_runtime": 1.6878,
|
| 157 |
+
"eval_samples_per_second": 508.353,
|
| 158 |
+
"eval_steps_per_second": 31.994,
|
| 159 |
+
"step": 5000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 11.39,
|
| 163 |
+
"learning_rate": 4.4500000000000004e-05,
|
| 164 |
+
"loss": 1.3156,
|
| 165 |
+
"step": 5500
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 11.39,
|
| 169 |
+
"eval_accuracy": 0.7496318114874816,
|
| 170 |
+
"eval_loss": 1.3172950744628906,
|
| 171 |
+
"eval_runtime": 1.6891,
|
| 172 |
+
"eval_samples_per_second": 507.956,
|
| 173 |
+
"eval_steps_per_second": 31.969,
|
| 174 |
+
"step": 5500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 12.42,
|
| 178 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 179 |
+
"loss": 1.2882,
|
| 180 |
+
"step": 6000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 12.42,
|
| 184 |
+
"eval_accuracy": 0.7738095238095238,
|
| 185 |
+
"eval_loss": 1.2816879749298096,
|
| 186 |
+
"eval_runtime": 1.6955,
|
| 187 |
+
"eval_samples_per_second": 506.058,
|
| 188 |
+
"eval_steps_per_second": 31.85,
|
| 189 |
+
"step": 6000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 13.46,
|
| 193 |
+
"learning_rate": 4.35e-05,
|
| 194 |
+
"loss": 1.2692,
|
| 195 |
+
"step": 6500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 13.46,
|
| 199 |
+
"eval_accuracy": 0.775112443778111,
|
| 200 |
+
"eval_loss": 1.189226746559143,
|
| 201 |
+
"eval_runtime": 1.6876,
|
| 202 |
+
"eval_samples_per_second": 508.403,
|
| 203 |
+
"eval_steps_per_second": 31.997,
|
| 204 |
+
"step": 6500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 14.49,
|
| 208 |
+
"learning_rate": 4.3e-05,
|
| 209 |
+
"loss": 1.2368,
|
| 210 |
+
"step": 7000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 14.49,
|
| 214 |
+
"eval_accuracy": 0.7816432272390822,
|
| 215 |
+
"eval_loss": 1.2362936735153198,
|
| 216 |
+
"eval_runtime": 1.6828,
|
| 217 |
+
"eval_samples_per_second": 509.861,
|
| 218 |
+
"eval_steps_per_second": 32.089,
|
| 219 |
+
"step": 7000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 15.53,
|
| 223 |
+
"learning_rate": 4.25e-05,
|
| 224 |
+
"loss": 1.1975,
|
| 225 |
+
"step": 7500
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 15.53,
|
| 229 |
+
"eval_accuracy": 0.76996336996337,
|
| 230 |
+
"eval_loss": 1.2442289590835571,
|
| 231 |
+
"eval_runtime": 1.6849,
|
| 232 |
+
"eval_samples_per_second": 509.233,
|
| 233 |
+
"eval_steps_per_second": 32.05,
|
| 234 |
+
"step": 7500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 16.56,
|
| 238 |
+
"learning_rate": 4.2e-05,
|
| 239 |
+
"loss": 1.1907,
|
| 240 |
+
"step": 8000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 16.56,
|
| 244 |
+
"eval_accuracy": 0.7720320466132556,
|
| 245 |
+
"eval_loss": 1.256901502609253,
|
| 246 |
+
"eval_runtime": 1.6884,
|
| 247 |
+
"eval_samples_per_second": 508.188,
|
| 248 |
+
"eval_steps_per_second": 31.984,
|
| 249 |
+
"step": 8000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 17.6,
|
| 253 |
+
"learning_rate": 4.15e-05,
|
| 254 |
+
"loss": 1.1231,
|
| 255 |
+
"step": 8500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 17.6,
|
| 259 |
+
"eval_accuracy": 0.776085300837776,
|
| 260 |
+
"eval_loss": 1.13861083984375,
|
| 261 |
+
"eval_runtime": 1.6842,
|
| 262 |
+
"eval_samples_per_second": 509.436,
|
| 263 |
+
"eval_steps_per_second": 32.062,
|
| 264 |
+
"step": 8500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 18.63,
|
| 268 |
+
"learning_rate": 4.1e-05,
|
| 269 |
+
"loss": 1.0873,
|
| 270 |
+
"step": 9000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 18.63,
|
| 274 |
+
"eval_accuracy": 0.7855547282204021,
|
| 275 |
+
"eval_loss": 1.2104856967926025,
|
| 276 |
+
"eval_runtime": 1.6846,
|
| 277 |
+
"eval_samples_per_second": 509.309,
|
| 278 |
+
"eval_steps_per_second": 32.054,
|
| 279 |
+
"step": 9000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 19.67,
|
| 283 |
+
"learning_rate": 4.05e-05,
|
| 284 |
+
"loss": 1.1242,
|
| 285 |
+
"step": 9500
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 19.67,
|
| 289 |
+
"eval_accuracy": 0.7737909516380655,
|
| 290 |
+
"eval_loss": 1.214229702949524,
|
| 291 |
+
"eval_runtime": 1.6848,
|
| 292 |
+
"eval_samples_per_second": 509.258,
|
| 293 |
+
"eval_steps_per_second": 32.051,
|
| 294 |
+
"step": 9500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 20.7,
|
| 298 |
+
"learning_rate": 4e-05,
|
| 299 |
+
"loss": 1.0367,
|
| 300 |
+
"step": 10000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 20.7,
|
| 304 |
+
"eval_accuracy": 0.7712369597615499,
|
| 305 |
+
"eval_loss": 1.2120734453201294,
|
| 306 |
+
"eval_runtime": 1.6938,
|
| 307 |
+
"eval_samples_per_second": 506.56,
|
| 308 |
+
"eval_steps_per_second": 31.881,
|
| 309 |
+
"step": 10000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 21.74,
|
| 313 |
+
"learning_rate": 3.9500000000000005e-05,
|
| 314 |
+
"loss": 1.0869,
|
| 315 |
+
"step": 10500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 21.74,
|
| 319 |
+
"eval_accuracy": 0.7955390334572491,
|
| 320 |
+
"eval_loss": 1.0782362222671509,
|
| 321 |
+
"eval_runtime": 1.6863,
|
| 322 |
+
"eval_samples_per_second": 508.795,
|
| 323 |
+
"eval_steps_per_second": 32.022,
|
| 324 |
+
"step": 10500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 22.77,
|
| 328 |
+
"learning_rate": 3.9000000000000006e-05,
|
| 329 |
+
"loss": 1.0353,
|
| 330 |
+
"step": 11000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 22.77,
|
| 334 |
+
"eval_accuracy": 0.8068535825545171,
|
| 335 |
+
"eval_loss": 0.9917858839035034,
|
| 336 |
+
"eval_runtime": 1.6841,
|
| 337 |
+
"eval_samples_per_second": 509.483,
|
| 338 |
+
"eval_steps_per_second": 32.065,
|
| 339 |
+
"step": 11000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 23.81,
|
| 343 |
+
"learning_rate": 3.85e-05,
|
| 344 |
+
"loss": 1.0324,
|
| 345 |
+
"step": 11500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 23.81,
|
| 349 |
+
"eval_accuracy": 0.7971233913701741,
|
| 350 |
+
"eval_loss": 1.0908266305923462,
|
| 351 |
+
"eval_runtime": 1.6848,
|
| 352 |
+
"eval_samples_per_second": 509.246,
|
| 353 |
+
"eval_steps_per_second": 32.05,
|
| 354 |
+
"step": 11500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 24.84,
|
| 358 |
+
"learning_rate": 3.8e-05,
|
| 359 |
+
"loss": 1.0145,
|
| 360 |
+
"step": 12000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 24.84,
|
| 364 |
+
"eval_accuracy": 0.7975460122699386,
|
| 365 |
+
"eval_loss": 1.0944875478744507,
|
| 366 |
+
"eval_runtime": 1.6827,
|
| 367 |
+
"eval_samples_per_second": 509.9,
|
| 368 |
+
"eval_steps_per_second": 32.092,
|
| 369 |
+
"step": 12000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 25.88,
|
| 373 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 374 |
+
"loss": 0.9951,
|
| 375 |
+
"step": 12500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 25.88,
|
| 379 |
+
"eval_accuracy": 0.8028064992614475,
|
| 380 |
+
"eval_loss": 1.000519037246704,
|
| 381 |
+
"eval_runtime": 1.6933,
|
| 382 |
+
"eval_samples_per_second": 506.714,
|
| 383 |
+
"eval_steps_per_second": 31.891,
|
| 384 |
+
"step": 12500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 26.92,
|
| 388 |
+
"learning_rate": 3.7e-05,
|
| 389 |
+
"loss": 0.9483,
|
| 390 |
+
"step": 13000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 26.92,
|
| 394 |
+
"eval_accuracy": 0.8186646433990895,
|
| 395 |
+
"eval_loss": 0.963790237903595,
|
| 396 |
+
"eval_runtime": 1.6874,
|
| 397 |
+
"eval_samples_per_second": 508.479,
|
| 398 |
+
"eval_steps_per_second": 32.002,
|
| 399 |
+
"step": 13000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 27.95,
|
| 403 |
+
"learning_rate": 3.65e-05,
|
| 404 |
+
"loss": 0.9304,
|
| 405 |
+
"step": 13500
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 27.95,
|
| 409 |
+
"eval_accuracy": 0.8204747774480712,
|
| 410 |
+
"eval_loss": 0.9761123657226562,
|
| 411 |
+
"eval_runtime": 1.6869,
|
| 412 |
+
"eval_samples_per_second": 508.622,
|
| 413 |
+
"eval_steps_per_second": 32.011,
|
| 414 |
+
"step": 13500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 28.99,
|
| 418 |
+
"learning_rate": 3.6e-05,
|
| 419 |
+
"loss": 0.8835,
|
| 420 |
+
"step": 14000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 28.99,
|
| 424 |
+
"eval_accuracy": 0.8045801526717558,
|
| 425 |
+
"eval_loss": 1.062032699584961,
|
| 426 |
+
"eval_runtime": 1.6883,
|
| 427 |
+
"eval_samples_per_second": 508.21,
|
| 428 |
+
"eval_steps_per_second": 31.985,
|
| 429 |
+
"step": 14000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 30.02,
|
| 433 |
+
"learning_rate": 3.55e-05,
|
| 434 |
+
"loss": 0.9097,
|
| 435 |
+
"step": 14500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 30.02,
|
| 439 |
+
"eval_accuracy": 0.806015037593985,
|
| 440 |
+
"eval_loss": 0.9137569069862366,
|
| 441 |
+
"eval_runtime": 1.6924,
|
| 442 |
+
"eval_samples_per_second": 506.97,
|
| 443 |
+
"eval_steps_per_second": 31.907,
|
| 444 |
+
"step": 14500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 31.06,
|
| 448 |
+
"learning_rate": 3.5e-05,
|
| 449 |
+
"loss": 0.9293,
|
| 450 |
+
"step": 15000
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 31.06,
|
| 454 |
+
"eval_accuracy": 0.8176197836166924,
|
| 455 |
+
"eval_loss": 0.918023943901062,
|
| 456 |
+
"eval_runtime": 1.6905,
|
| 457 |
+
"eval_samples_per_second": 507.53,
|
| 458 |
+
"eval_steps_per_second": 31.942,
|
| 459 |
+
"step": 15000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 32.09,
|
| 463 |
+
"learning_rate": 3.45e-05,
|
| 464 |
+
"loss": 0.9043,
|
| 465 |
+
"step": 15500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 32.09,
|
| 469 |
+
"eval_accuracy": 0.8208269525267994,
|
| 470 |
+
"eval_loss": 0.9214709401130676,
|
| 471 |
+
"eval_runtime": 1.691,
|
| 472 |
+
"eval_samples_per_second": 507.403,
|
| 473 |
+
"eval_steps_per_second": 31.934,
|
| 474 |
+
"step": 15500
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 33.13,
|
| 478 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 479 |
+
"loss": 0.8581,
|
| 480 |
+
"step": 16000
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 33.13,
|
| 484 |
+
"eval_accuracy": 0.822452229299363,
|
| 485 |
+
"eval_loss": 0.9624596834182739,
|
| 486 |
+
"eval_runtime": 1.6897,
|
| 487 |
+
"eval_samples_per_second": 507.793,
|
| 488 |
+
"eval_steps_per_second": 31.959,
|
| 489 |
+
"step": 16000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 34.16,
|
| 493 |
+
"learning_rate": 3.35e-05,
|
| 494 |
+
"loss": 0.8638,
|
| 495 |
+
"step": 16500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 34.16,
|
| 499 |
+
"eval_accuracy": 0.8367816091954023,
|
| 500 |
+
"eval_loss": 0.8585591316223145,
|
| 501 |
+
"eval_runtime": 1.6912,
|
| 502 |
+
"eval_samples_per_second": 507.329,
|
| 503 |
+
"eval_steps_per_second": 31.93,
|
| 504 |
+
"step": 16500
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 35.2,
|
| 508 |
+
"learning_rate": 3.3e-05,
|
| 509 |
+
"loss": 0.874,
|
| 510 |
+
"step": 17000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 35.2,
|
| 514 |
+
"eval_accuracy": 0.8135072908672295,
|
| 515 |
+
"eval_loss": 1.0043973922729492,
|
| 516 |
+
"eval_runtime": 1.6896,
|
| 517 |
+
"eval_samples_per_second": 507.801,
|
| 518 |
+
"eval_steps_per_second": 31.96,
|
| 519 |
+
"step": 17000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 36.23,
|
| 523 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 524 |
+
"loss": 0.8235,
|
| 525 |
+
"step": 17500
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 36.23,
|
| 529 |
+
"eval_accuracy": 0.8183890577507599,
|
| 530 |
+
"eval_loss": 0.9755066633224487,
|
| 531 |
+
"eval_runtime": 1.6947,
|
| 532 |
+
"eval_samples_per_second": 506.289,
|
| 533 |
+
"eval_steps_per_second": 31.864,
|
| 534 |
+
"step": 17500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 37.27,
|
| 538 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 539 |
+
"loss": 0.8589,
|
| 540 |
+
"step": 18000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 37.27,
|
| 544 |
+
"eval_accuracy": 0.8291761148904006,
|
| 545 |
+
"eval_loss": 0.9042153358459473,
|
| 546 |
+
"eval_runtime": 1.6905,
|
| 547 |
+
"eval_samples_per_second": 507.55,
|
| 548 |
+
"eval_steps_per_second": 31.944,
|
| 549 |
+
"step": 18000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 38.3,
|
| 553 |
+
"learning_rate": 3.15e-05,
|
| 554 |
+
"loss": 0.8107,
|
| 555 |
+
"step": 18500
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 38.3,
|
| 559 |
+
"eval_accuracy": 0.8272327964860908,
|
| 560 |
+
"eval_loss": 0.8821109533309937,
|
| 561 |
+
"eval_runtime": 1.6895,
|
| 562 |
+
"eval_samples_per_second": 507.845,
|
| 563 |
+
"eval_steps_per_second": 31.962,
|
| 564 |
+
"step": 18500
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 39.34,
|
| 568 |
+
"learning_rate": 3.1e-05,
|
| 569 |
+
"loss": 0.8346,
|
| 570 |
+
"step": 19000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 39.34,
|
| 574 |
+
"eval_accuracy": 0.8248286367098249,
|
| 575 |
+
"eval_loss": 0.9061236381530762,
|
| 576 |
+
"eval_runtime": 1.6919,
|
| 577 |
+
"eval_samples_per_second": 507.136,
|
| 578 |
+
"eval_steps_per_second": 31.918,
|
| 579 |
+
"step": 19000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 40.37,
|
| 583 |
+
"learning_rate": 3.05e-05,
|
| 584 |
+
"loss": 0.8393,
|
| 585 |
+
"step": 19500
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 40.37,
|
| 589 |
+
"eval_accuracy": 0.8234854151084517,
|
| 590 |
+
"eval_loss": 0.9795840978622437,
|
| 591 |
+
"eval_runtime": 1.6939,
|
| 592 |
+
"eval_samples_per_second": 506.513,
|
| 593 |
+
"eval_steps_per_second": 31.878,
|
| 594 |
+
"step": 19500
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 41.41,
|
| 598 |
+
"learning_rate": 3e-05,
|
| 599 |
+
"loss": 0.789,
|
| 600 |
+
"step": 20000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 41.41,
|
| 604 |
+
"eval_accuracy": 0.833076923076923,
|
| 605 |
+
"eval_loss": 0.9014851450920105,
|
| 606 |
+
"eval_runtime": 1.689,
|
| 607 |
+
"eval_samples_per_second": 508.0,
|
| 608 |
+
"eval_steps_per_second": 31.972,
|
| 609 |
+
"step": 20000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 42.44,
|
| 613 |
+
"learning_rate": 2.95e-05,
|
| 614 |
+
"loss": 0.8121,
|
| 615 |
+
"step": 20500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 42.44,
|
| 619 |
+
"eval_accuracy": 0.8385913426265591,
|
| 620 |
+
"eval_loss": 0.8589309453964233,
|
| 621 |
+
"eval_runtime": 1.6873,
|
| 622 |
+
"eval_samples_per_second": 508.516,
|
| 623 |
+
"eval_steps_per_second": 32.005,
|
| 624 |
+
"step": 20500
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 43.48,
|
| 628 |
+
"learning_rate": 2.9e-05,
|
| 629 |
+
"loss": 0.7709,
|
| 630 |
+
"step": 21000
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 43.48,
|
| 634 |
+
"eval_accuracy": 0.8350903614457831,
|
| 635 |
+
"eval_loss": 0.8835715055465698,
|
| 636 |
+
"eval_runtime": 1.6829,
|
| 637 |
+
"eval_samples_per_second": 509.835,
|
| 638 |
+
"eval_steps_per_second": 32.088,
|
| 639 |
+
"step": 21000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 44.51,
|
| 643 |
+
"learning_rate": 2.8499999999999998e-05,
|
| 644 |
+
"loss": 0.7922,
|
| 645 |
+
"step": 21500
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 44.51,
|
| 649 |
+
"eval_accuracy": 0.817974105102818,
|
| 650 |
+
"eval_loss": 0.9523779153823853,
|
| 651 |
+
"eval_runtime": 1.6863,
|
| 652 |
+
"eval_samples_per_second": 508.799,
|
| 653 |
+
"eval_steps_per_second": 32.022,
|
| 654 |
+
"step": 21500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 45.55,
|
| 658 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 659 |
+
"loss": 0.7457,
|
| 660 |
+
"step": 22000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 45.55,
|
| 664 |
+
"eval_accuracy": 0.8364451082897685,
|
| 665 |
+
"eval_loss": 0.8350428938865662,
|
| 666 |
+
"eval_runtime": 1.6901,
|
| 667 |
+
"eval_samples_per_second": 507.673,
|
| 668 |
+
"eval_steps_per_second": 31.951,
|
| 669 |
+
"step": 22000
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 46.58,
|
| 673 |
+
"learning_rate": 2.7500000000000004e-05,
|
| 674 |
+
"loss": 0.7386,
|
| 675 |
+
"step": 22500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 46.58,
|
| 679 |
+
"eval_accuracy": 0.8340807174887892,
|
| 680 |
+
"eval_loss": 0.9024766087532043,
|
| 681 |
+
"eval_runtime": 1.6912,
|
| 682 |
+
"eval_samples_per_second": 507.34,
|
| 683 |
+
"eval_steps_per_second": 31.93,
|
| 684 |
+
"step": 22500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 47.62,
|
| 688 |
+
"learning_rate": 2.7000000000000002e-05,
|
| 689 |
+
"loss": 0.7515,
|
| 690 |
+
"step": 23000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 47.62,
|
| 694 |
+
"eval_accuracy": 0.8390166534496432,
|
| 695 |
+
"eval_loss": 0.9091906547546387,
|
| 696 |
+
"eval_runtime": 1.686,
|
| 697 |
+
"eval_samples_per_second": 508.899,
|
| 698 |
+
"eval_steps_per_second": 32.029,
|
| 699 |
+
"step": 23000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 48.65,
|
| 703 |
+
"learning_rate": 2.6500000000000004e-05,
|
| 704 |
+
"loss": 0.7324,
|
| 705 |
+
"step": 23500
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 48.65,
|
| 709 |
+
"eval_accuracy": 0.8420647149460708,
|
| 710 |
+
"eval_loss": 0.8322407007217407,
|
| 711 |
+
"eval_runtime": 1.6918,
|
| 712 |
+
"eval_samples_per_second": 507.153,
|
| 713 |
+
"eval_steps_per_second": 31.919,
|
| 714 |
+
"step": 23500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 49.69,
|
| 718 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 719 |
+
"loss": 0.7314,
|
| 720 |
+
"step": 24000
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 49.69,
|
| 724 |
+
"eval_accuracy": 0.8477078477078477,
|
| 725 |
+
"eval_loss": 0.7967829704284668,
|
| 726 |
+
"eval_runtime": 1.6933,
|
| 727 |
+
"eval_samples_per_second": 506.713,
|
| 728 |
+
"eval_steps_per_second": 31.891,
|
| 729 |
+
"step": 24000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 50.72,
|
| 733 |
+
"learning_rate": 2.5500000000000003e-05,
|
| 734 |
+
"loss": 0.7442,
|
| 735 |
+
"step": 24500
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 50.72,
|
| 739 |
+
"eval_accuracy": 0.8324407039020658,
|
| 740 |
+
"eval_loss": 0.930473268032074,
|
| 741 |
+
"eval_runtime": 1.6828,
|
| 742 |
+
"eval_samples_per_second": 509.873,
|
| 743 |
+
"eval_steps_per_second": 32.09,
|
| 744 |
+
"step": 24500
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 51.76,
|
| 748 |
+
"learning_rate": 2.5e-05,
|
| 749 |
+
"loss": 0.7074,
|
| 750 |
+
"step": 25000
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 51.76,
|
| 754 |
+
"eval_accuracy": 0.820839580209895,
|
| 755 |
+
"eval_loss": 1.001060962677002,
|
| 756 |
+
"eval_runtime": 1.6867,
|
| 757 |
+
"eval_samples_per_second": 508.672,
|
| 758 |
+
"eval_steps_per_second": 32.014,
|
| 759 |
+
"step": 25000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 52.8,
|
| 763 |
+
"learning_rate": 2.45e-05,
|
| 764 |
+
"loss": 0.739,
|
| 765 |
+
"step": 25500
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 52.8,
|
| 769 |
+
"eval_accuracy": 0.8330945558739254,
|
| 770 |
+
"eval_loss": 0.8732258677482605,
|
| 771 |
+
"eval_runtime": 1.6896,
|
| 772 |
+
"eval_samples_per_second": 507.823,
|
| 773 |
+
"eval_steps_per_second": 31.961,
|
| 774 |
+
"step": 25500
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 53.83,
|
| 778 |
+
"learning_rate": 2.4e-05,
|
| 779 |
+
"loss": 0.7243,
|
| 780 |
+
"step": 26000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 53.83,
|
| 784 |
+
"eval_accuracy": 0.8479880774962743,
|
| 785 |
+
"eval_loss": 0.7857112288475037,
|
| 786 |
+
"eval_runtime": 1.687,
|
| 787 |
+
"eval_samples_per_second": 508.591,
|
| 788 |
+
"eval_steps_per_second": 32.009,
|
| 789 |
+
"step": 26000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 54.87,
|
| 793 |
+
"learning_rate": 2.35e-05,
|
| 794 |
+
"loss": 0.6842,
|
| 795 |
+
"step": 26500
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 54.87,
|
| 799 |
+
"eval_accuracy": 0.8377192982456141,
|
| 800 |
+
"eval_loss": 0.7945135235786438,
|
| 801 |
+
"eval_runtime": 1.6902,
|
| 802 |
+
"eval_samples_per_second": 507.642,
|
| 803 |
+
"eval_steps_per_second": 31.949,
|
| 804 |
+
"step": 26500
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 55.9,
|
| 808 |
+
"learning_rate": 2.3000000000000003e-05,
|
| 809 |
+
"loss": 0.6991,
|
| 810 |
+
"step": 27000
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 55.9,
|
| 814 |
+
"eval_accuracy": 0.8275351591413768,
|
| 815 |
+
"eval_loss": 0.9627696871757507,
|
| 816 |
+
"eval_runtime": 1.6871,
|
| 817 |
+
"eval_samples_per_second": 508.578,
|
| 818 |
+
"eval_steps_per_second": 32.008,
|
| 819 |
+
"step": 27000
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 56.94,
|
| 823 |
+
"learning_rate": 2.25e-05,
|
| 824 |
+
"loss": 0.6896,
|
| 825 |
+
"step": 27500
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 56.94,
|
| 829 |
+
"eval_accuracy": 0.840960240060015,
|
| 830 |
+
"eval_loss": 0.8363039493560791,
|
| 831 |
+
"eval_runtime": 1.684,
|
| 832 |
+
"eval_samples_per_second": 509.495,
|
| 833 |
+
"eval_steps_per_second": 32.066,
|
| 834 |
+
"step": 27500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 57.97,
|
| 838 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 839 |
+
"loss": 0.6925,
|
| 840 |
+
"step": 28000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 57.97,
|
| 844 |
+
"eval_accuracy": 0.8391812865497076,
|
| 845 |
+
"eval_loss": 0.8432921767234802,
|
| 846 |
+
"eval_runtime": 1.6968,
|
| 847 |
+
"eval_samples_per_second": 505.655,
|
| 848 |
+
"eval_steps_per_second": 31.824,
|
| 849 |
+
"step": 28000
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 59.01,
|
| 853 |
+
"learning_rate": 2.15e-05,
|
| 854 |
+
"loss": 0.7081,
|
| 855 |
+
"step": 28500
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 59.01,
|
| 859 |
+
"eval_accuracy": 0.8223048327137547,
|
| 860 |
+
"eval_loss": 1.0085676908493042,
|
| 861 |
+
"eval_runtime": 1.69,
|
| 862 |
+
"eval_samples_per_second": 507.688,
|
| 863 |
+
"eval_steps_per_second": 31.952,
|
| 864 |
+
"step": 28500
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 60.04,
|
| 868 |
+
"learning_rate": 2.1e-05,
|
| 869 |
+
"loss": 0.6598,
|
| 870 |
+
"step": 29000
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 60.04,
|
| 874 |
+
"eval_accuracy": 0.8333333333333334,
|
| 875 |
+
"eval_loss": 0.9250668883323669,
|
| 876 |
+
"eval_runtime": 1.686,
|
| 877 |
+
"eval_samples_per_second": 508.895,
|
| 878 |
+
"eval_steps_per_second": 32.028,
|
| 879 |
+
"step": 29000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 61.08,
|
| 883 |
+
"learning_rate": 2.05e-05,
|
| 884 |
+
"loss": 0.6677,
|
| 885 |
+
"step": 29500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 61.08,
|
| 889 |
+
"eval_accuracy": 0.8437047756874095,
|
| 890 |
+
"eval_loss": 0.8822752237319946,
|
| 891 |
+
"eval_runtime": 1.693,
|
| 892 |
+
"eval_samples_per_second": 506.807,
|
| 893 |
+
"eval_steps_per_second": 31.897,
|
| 894 |
+
"step": 29500
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 62.11,
|
| 898 |
+
"learning_rate": 2e-05,
|
| 899 |
+
"loss": 0.695,
|
| 900 |
+
"step": 30000
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 62.11,
|
| 904 |
+
"eval_accuracy": 0.8560371517027864,
|
| 905 |
+
"eval_loss": 0.7750544548034668,
|
| 906 |
+
"eval_runtime": 1.6969,
|
| 907 |
+
"eval_samples_per_second": 505.632,
|
| 908 |
+
"eval_steps_per_second": 31.823,
|
| 909 |
+
"step": 30000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 63.15,
|
| 913 |
+
"learning_rate": 1.9500000000000003e-05,
|
| 914 |
+
"loss": 0.7108,
|
| 915 |
+
"step": 30500
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 63.15,
|
| 919 |
+
"eval_accuracy": 0.8481104651162791,
|
| 920 |
+
"eval_loss": 0.8452057242393494,
|
| 921 |
+
"eval_runtime": 1.6974,
|
| 922 |
+
"eval_samples_per_second": 505.49,
|
| 923 |
+
"eval_steps_per_second": 31.814,
|
| 924 |
+
"step": 30500
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 64.18,
|
| 928 |
+
"learning_rate": 1.9e-05,
|
| 929 |
+
"loss": 0.6721,
|
| 930 |
+
"step": 31000
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 64.18,
|
| 934 |
+
"eval_accuracy": 0.8413284132841329,
|
| 935 |
+
"eval_loss": 0.8559600114822388,
|
| 936 |
+
"eval_runtime": 1.6936,
|
| 937 |
+
"eval_samples_per_second": 506.623,
|
| 938 |
+
"eval_steps_per_second": 31.885,
|
| 939 |
+
"step": 31000
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 65.22,
|
| 943 |
+
"learning_rate": 1.85e-05,
|
| 944 |
+
"loss": 0.6571,
|
| 945 |
+
"step": 31500
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 65.22,
|
| 949 |
+
"eval_accuracy": 0.8163109756097561,
|
| 950 |
+
"eval_loss": 0.98003089427948,
|
| 951 |
+
"eval_runtime": 1.6913,
|
| 952 |
+
"eval_samples_per_second": 507.303,
|
| 953 |
+
"eval_steps_per_second": 31.928,
|
| 954 |
+
"step": 31500
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 66.25,
|
| 958 |
+
"learning_rate": 1.8e-05,
|
| 959 |
+
"loss": 0.6891,
|
| 960 |
+
"step": 32000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 66.25,
|
| 964 |
+
"eval_accuracy": 0.8457446808510638,
|
| 965 |
+
"eval_loss": 0.8105884194374084,
|
| 966 |
+
"eval_runtime": 1.6942,
|
| 967 |
+
"eval_samples_per_second": 506.435,
|
| 968 |
+
"eval_steps_per_second": 31.874,
|
| 969 |
+
"step": 32000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 67.29,
|
| 973 |
+
"learning_rate": 1.75e-05,
|
| 974 |
+
"loss": 0.6541,
|
| 975 |
+
"step": 32500
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 67.29,
|
| 979 |
+
"eval_accuracy": 0.8429752066115702,
|
| 980 |
+
"eval_loss": 0.8197007179260254,
|
| 981 |
+
"eval_runtime": 1.6912,
|
| 982 |
+
"eval_samples_per_second": 507.332,
|
| 983 |
+
"eval_steps_per_second": 31.93,
|
| 984 |
+
"step": 32500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 68.32,
|
| 988 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 989 |
+
"loss": 0.6559,
|
| 990 |
+
"step": 33000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 68.32,
|
| 994 |
+
"eval_accuracy": 0.8388305847076462,
|
| 995 |
+
"eval_loss": 0.8678442239761353,
|
| 996 |
+
"eval_runtime": 1.6945,
|
| 997 |
+
"eval_samples_per_second": 506.35,
|
| 998 |
+
"eval_steps_per_second": 31.868,
|
| 999 |
+
"step": 33000
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 69.36,
|
| 1003 |
+
"learning_rate": 1.65e-05,
|
| 1004 |
+
"loss": 0.6554,
|
| 1005 |
+
"step": 33500
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 69.36,
|
| 1009 |
+
"eval_accuracy": 0.8661764705882353,
|
| 1010 |
+
"eval_loss": 0.7396097183227539,
|
| 1011 |
+
"eval_runtime": 1.6934,
|
| 1012 |
+
"eval_samples_per_second": 506.658,
|
| 1013 |
+
"eval_steps_per_second": 31.888,
|
| 1014 |
+
"step": 33500
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 70.39,
|
| 1018 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 1019 |
+
"loss": 0.618,
|
| 1020 |
+
"step": 34000
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 70.39,
|
| 1024 |
+
"eval_accuracy": 0.8375634517766497,
|
| 1025 |
+
"eval_loss": 0.8517589569091797,
|
| 1026 |
+
"eval_runtime": 1.6983,
|
| 1027 |
+
"eval_samples_per_second": 505.224,
|
| 1028 |
+
"eval_steps_per_second": 31.797,
|
| 1029 |
+
"step": 34000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 71.43,
|
| 1033 |
+
"learning_rate": 1.55e-05,
|
| 1034 |
+
"loss": 0.6558,
|
| 1035 |
+
"step": 34500
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 71.43,
|
| 1039 |
+
"eval_accuracy": 0.8409090909090909,
|
| 1040 |
+
"eval_loss": 0.7705618739128113,
|
| 1041 |
+
"eval_runtime": 1.6954,
|
| 1042 |
+
"eval_samples_per_second": 506.065,
|
| 1043 |
+
"eval_steps_per_second": 31.85,
|
| 1044 |
+
"step": 34500
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 72.46,
|
| 1048 |
+
"learning_rate": 1.5e-05,
|
| 1049 |
+
"loss": 0.6034,
|
| 1050 |
+
"step": 35000
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 72.46,
|
| 1054 |
+
"eval_accuracy": 0.8517699115044248,
|
| 1055 |
+
"eval_loss": 0.7829406261444092,
|
| 1056 |
+
"eval_runtime": 1.6974,
|
| 1057 |
+
"eval_samples_per_second": 505.471,
|
| 1058 |
+
"eval_steps_per_second": 31.813,
|
| 1059 |
+
"step": 35000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 73.5,
|
| 1063 |
+
"learning_rate": 1.45e-05,
|
| 1064 |
+
"loss": 0.6336,
|
| 1065 |
+
"step": 35500
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 73.5,
|
| 1069 |
+
"eval_accuracy": 0.8591445427728613,
|
| 1070 |
+
"eval_loss": 0.7834987640380859,
|
| 1071 |
+
"eval_runtime": 1.6914,
|
| 1072 |
+
"eval_samples_per_second": 507.26,
|
| 1073 |
+
"eval_steps_per_second": 31.925,
|
| 1074 |
+
"step": 35500
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 74.53,
|
| 1078 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 1079 |
+
"loss": 0.6287,
|
| 1080 |
+
"step": 36000
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 74.53,
|
| 1084 |
+
"eval_accuracy": 0.8574748257164988,
|
| 1085 |
+
"eval_loss": 0.7547706961631775,
|
| 1086 |
+
"eval_runtime": 1.6906,
|
| 1087 |
+
"eval_samples_per_second": 507.513,
|
| 1088 |
+
"eval_steps_per_second": 31.941,
|
| 1089 |
+
"step": 36000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 75.57,
|
| 1093 |
+
"learning_rate": 1.3500000000000001e-05,
|
| 1094 |
+
"loss": 0.6065,
|
| 1095 |
+
"step": 36500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 75.57,
|
| 1099 |
+
"eval_accuracy": 0.8508005822416302,
|
| 1100 |
+
"eval_loss": 0.8541703224182129,
|
| 1101 |
+
"eval_runtime": 1.6919,
|
| 1102 |
+
"eval_samples_per_second": 507.134,
|
| 1103 |
+
"eval_steps_per_second": 31.918,
|
| 1104 |
+
"step": 36500
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 76.6,
|
| 1108 |
+
"learning_rate": 1.3000000000000001e-05,
|
| 1109 |
+
"loss": 0.6029,
|
| 1110 |
+
"step": 37000
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 76.6,
|
| 1114 |
+
"eval_accuracy": 0.8405267008046818,
|
| 1115 |
+
"eval_loss": 0.8202521800994873,
|
| 1116 |
+
"eval_runtime": 1.6903,
|
| 1117 |
+
"eval_samples_per_second": 507.595,
|
| 1118 |
+
"eval_steps_per_second": 31.947,
|
| 1119 |
+
"step": 37000
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 77.64,
|
| 1123 |
+
"learning_rate": 1.25e-05,
|
| 1124 |
+
"loss": 0.6208,
|
| 1125 |
+
"step": 37500
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 77.64,
|
| 1129 |
+
"eval_accuracy": 0.8661417322834646,
|
| 1130 |
+
"eval_loss": 0.7082335948944092,
|
| 1131 |
+
"eval_runtime": 1.6867,
|
| 1132 |
+
"eval_samples_per_second": 508.681,
|
| 1133 |
+
"eval_steps_per_second": 32.015,
|
| 1134 |
+
"step": 37500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 78.67,
|
| 1138 |
+
"learning_rate": 1.2e-05,
|
| 1139 |
+
"loss": 0.64,
|
| 1140 |
+
"step": 38000
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 78.67,
|
| 1144 |
+
"eval_accuracy": 0.8410295230885693,
|
| 1145 |
+
"eval_loss": 0.8504825234413147,
|
| 1146 |
+
"eval_runtime": 1.6943,
|
| 1147 |
+
"eval_samples_per_second": 506.417,
|
| 1148 |
+
"eval_steps_per_second": 31.872,
|
| 1149 |
+
"step": 38000
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 79.71,
|
| 1153 |
+
"learning_rate": 1.1500000000000002e-05,
|
| 1154 |
+
"loss": 0.6144,
|
| 1155 |
+
"step": 38500
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 79.71,
|
| 1159 |
+
"eval_accuracy": 0.8603636363636363,
|
| 1160 |
+
"eval_loss": 0.7246142625808716,
|
| 1161 |
+
"eval_runtime": 1.6864,
|
| 1162 |
+
"eval_samples_per_second": 508.77,
|
| 1163 |
+
"eval_steps_per_second": 32.02,
|
| 1164 |
+
"step": 38500
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 80.75,
|
| 1168 |
+
"learning_rate": 1.1000000000000001e-05,
|
| 1169 |
+
"loss": 0.6507,
|
| 1170 |
+
"step": 39000
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 80.75,
|
| 1174 |
+
"eval_accuracy": 0.861132660977502,
|
| 1175 |
+
"eval_loss": 0.7150202393531799,
|
| 1176 |
+
"eval_runtime": 1.701,
|
| 1177 |
+
"eval_samples_per_second": 504.398,
|
| 1178 |
+
"eval_steps_per_second": 31.745,
|
| 1179 |
+
"step": 39000
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 81.78,
|
| 1183 |
+
"learning_rate": 1.05e-05,
|
| 1184 |
+
"loss": 0.6177,
|
| 1185 |
+
"step": 39500
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 81.78,
|
| 1189 |
+
"eval_accuracy": 0.84,
|
| 1190 |
+
"eval_loss": 0.9331970810890198,
|
| 1191 |
+
"eval_runtime": 1.6939,
|
| 1192 |
+
"eval_samples_per_second": 506.536,
|
| 1193 |
+
"eval_steps_per_second": 31.88,
|
| 1194 |
+
"step": 39500
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 82.82,
|
| 1198 |
+
"learning_rate": 1e-05,
|
| 1199 |
+
"loss": 0.6159,
|
| 1200 |
+
"step": 40000
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 82.82,
|
| 1204 |
+
"eval_accuracy": 0.8733488733488733,
|
| 1205 |
+
"eval_loss": 0.6427481174468994,
|
| 1206 |
+
"eval_runtime": 1.6965,
|
| 1207 |
+
"eval_samples_per_second": 505.755,
|
| 1208 |
+
"eval_steps_per_second": 31.831,
|
| 1209 |
+
"step": 40000
|
| 1210 |
+
}
|
| 1211 |
+
],
|
| 1212 |
+
"logging_steps": 500,
|
| 1213 |
+
"max_steps": 50000,
|
| 1214 |
+
"num_train_epochs": 104,
|
| 1215 |
+
"save_steps": 500,
|
| 1216 |
+
"total_flos": 6042662847119360.0,
|
| 1217 |
+
"trial_name": null,
|
| 1218 |
+
"trial_params": null
|
| 1219 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bacabf0df5e89f749d36fdc2817cc26562dfe21a76bd4dbb1d9f549c9123cbaa
|
| 3 |
+
size 4091
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|