Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- cost_to_drop_frequency_5039/README.md +131 -0
- cost_to_drop_frequency_5039/all_results.json +16 -0
- cost_to_drop_frequency_5039/checkpoint-30000/config.json +31 -0
- cost_to_drop_frequency_5039/checkpoint-30000/generation_config.json +6 -0
- cost_to_drop_frequency_5039/checkpoint-30000/merges.txt +0 -0
- cost_to_drop_frequency_5039/checkpoint-30000/model.safetensors +3 -0
- cost_to_drop_frequency_5039/checkpoint-30000/optimizer.pt +3 -0
- cost_to_drop_frequency_5039/checkpoint-30000/rng_state.pth +3 -0
- cost_to_drop_frequency_5039/checkpoint-30000/scaler.pt +3 -0
- cost_to_drop_frequency_5039/checkpoint-30000/scheduler.pt +3 -0
- cost_to_drop_frequency_5039/checkpoint-30000/special_tokens_map.json +5 -0
- cost_to_drop_frequency_5039/checkpoint-30000/tokenizer.json +0 -0
- cost_to_drop_frequency_5039/checkpoint-30000/tokenizer_config.json +20 -0
- cost_to_drop_frequency_5039/checkpoint-30000/trainer_state.json +0 -0
- cost_to_drop_frequency_5039/checkpoint-30000/training_args.bin +3 -0
- cost_to_drop_frequency_5039/checkpoint-30000/vocab.json +0 -0
- cost_to_drop_frequency_5039/checkpoint-40000/config.json +31 -0
- cost_to_drop_frequency_5039/checkpoint-40000/generation_config.json +6 -0
- cost_to_drop_frequency_5039/checkpoint-40000/merges.txt +0 -0
- cost_to_drop_frequency_5039/checkpoint-40000/model.safetensors +3 -0
- cost_to_drop_frequency_5039/checkpoint-40000/optimizer.pt +3 -0
- cost_to_drop_frequency_5039/checkpoint-40000/rng_state.pth +3 -0
- cost_to_drop_frequency_5039/checkpoint-40000/scaler.pt +3 -0
- cost_to_drop_frequency_5039/checkpoint-40000/scheduler.pt +3 -0
- cost_to_drop_frequency_5039/checkpoint-40000/special_tokens_map.json +5 -0
- cost_to_drop_frequency_5039/checkpoint-40000/tokenizer.json +0 -0
- cost_to_drop_frequency_5039/checkpoint-40000/tokenizer_config.json +20 -0
- cost_to_drop_frequency_5039/checkpoint-40000/trainer_state.json +0 -0
- cost_to_drop_frequency_5039/checkpoint-40000/training_args.bin +3 -0
- cost_to_drop_frequency_5039/checkpoint-40000/vocab.json +0 -0
- cost_to_drop_frequency_5039/checkpoint-50000/config.json +31 -0
- cost_to_drop_frequency_5039/checkpoint-50000/generation_config.json +6 -0
- cost_to_drop_frequency_5039/checkpoint-50000/merges.txt +0 -0
- cost_to_drop_frequency_5039/checkpoint-50000/model.safetensors +3 -0
- cost_to_drop_frequency_5039/checkpoint-50000/optimizer.pt +3 -0
- cost_to_drop_frequency_5039/checkpoint-50000/rng_state.pth +3 -0
- cost_to_drop_frequency_5039/checkpoint-50000/scaler.pt +3 -0
- cost_to_drop_frequency_5039/checkpoint-50000/scheduler.pt +3 -0
- cost_to_drop_frequency_5039/checkpoint-50000/special_tokens_map.json +5 -0
- cost_to_drop_frequency_5039/checkpoint-50000/tokenizer.json +0 -0
- cost_to_drop_frequency_5039/checkpoint-50000/tokenizer_config.json +20 -0
- cost_to_drop_frequency_5039/checkpoint-50000/trainer_state.json +0 -0
- cost_to_drop_frequency_5039/checkpoint-50000/training_args.bin +3 -0
- cost_to_drop_frequency_5039/checkpoint-50000/vocab.json +0 -0
- cost_to_drop_frequency_5039/checkpoint-60000/config.json +31 -0
- cost_to_drop_frequency_5039/checkpoint-60000/generation_config.json +6 -0
- cost_to_drop_frequency_5039/checkpoint-60000/merges.txt +0 -0
- cost_to_drop_frequency_5039/checkpoint-60000/model.safetensors +3 -0
- cost_to_drop_frequency_5039/checkpoint-60000/optimizer.pt +3 -0
- cost_to_drop_frequency_5039/checkpoint-60000/rng_state.pth +3 -0
cost_to_drop_frequency_5039/README.md
ADDED
|
@@ -0,0 +1,131 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: exceptions_exp2_cost_to_drop_frequency_5039
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/craaaa/exceptions_exp2/runs/ns16vmf7)
|
| 16 |
+
# exceptions_exp2_cost_to_drop_frequency_5039
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 3.5407
|
| 21 |
+
- Accuracy: 0.3720
|
| 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: 0.0006
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
+
- eval_batch_size: 16
|
| 43 |
+
- seed: 5039
|
| 44 |
+
- gradient_accumulation_steps: 5
|
| 45 |
+
- total_train_batch_size: 80
|
| 46 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 100
|
| 49 |
+
- num_epochs: 20.0
|
| 50 |
+
- mixed_precision_training: Native AMP
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 55 |
+
|:-------------:|:-------:|:-----:|:---------------:|:--------:|
|
| 56 |
+
| 4.8271 | 0.2912 | 1000 | 4.7385 | 0.2568 |
|
| 57 |
+
| 4.3193 | 0.5824 | 2000 | 4.2775 | 0.3003 |
|
| 58 |
+
| 4.1342 | 0.8736 | 3000 | 4.0978 | 0.3156 |
|
| 59 |
+
| 3.9849 | 1.1645 | 4000 | 3.9868 | 0.3255 |
|
| 60 |
+
| 3.9394 | 1.4557 | 5000 | 3.9117 | 0.3322 |
|
| 61 |
+
| 3.8827 | 1.7469 | 6000 | 3.8548 | 0.3371 |
|
| 62 |
+
| 3.7475 | 2.0379 | 7000 | 3.8121 | 0.3419 |
|
| 63 |
+
| 3.7642 | 2.3290 | 8000 | 3.7793 | 0.3451 |
|
| 64 |
+
| 3.7393 | 2.6202 | 9000 | 3.7499 | 0.3475 |
|
| 65 |
+
| 3.711 | 2.9114 | 10000 | 3.7228 | 0.3500 |
|
| 66 |
+
| 3.6274 | 3.2024 | 11000 | 3.7098 | 0.3521 |
|
| 67 |
+
| 3.6332 | 3.4936 | 12000 | 3.6899 | 0.3539 |
|
| 68 |
+
| 3.6231 | 3.7848 | 13000 | 3.6698 | 0.3558 |
|
| 69 |
+
| 3.5326 | 4.0757 | 14000 | 3.6634 | 0.3571 |
|
| 70 |
+
| 3.55 | 4.3669 | 15000 | 3.6499 | 0.3585 |
|
| 71 |
+
| 3.5673 | 4.6581 | 16000 | 3.6389 | 0.3594 |
|
| 72 |
+
| 3.5487 | 4.9493 | 17000 | 3.6259 | 0.3609 |
|
| 73 |
+
| 3.4846 | 5.2402 | 18000 | 3.6268 | 0.3616 |
|
| 74 |
+
| 3.4964 | 5.5314 | 19000 | 3.6121 | 0.3623 |
|
| 75 |
+
| 3.5089 | 5.8226 | 20000 | 3.6031 | 0.3633 |
|
| 76 |
+
| 3.4157 | 6.1136 | 21000 | 3.6087 | 0.3640 |
|
| 77 |
+
| 3.4494 | 6.4048 | 22000 | 3.5989 | 0.3645 |
|
| 78 |
+
| 3.4584 | 6.6959 | 23000 | 3.5899 | 0.3652 |
|
| 79 |
+
| 3.4745 | 6.9871 | 24000 | 3.5784 | 0.3659 |
|
| 80 |
+
| 3.4072 | 7.2781 | 25000 | 3.5910 | 0.3660 |
|
| 81 |
+
| 3.4202 | 7.5693 | 26000 | 3.5785 | 0.3667 |
|
| 82 |
+
| 3.434 | 7.8605 | 27000 | 3.5679 | 0.3675 |
|
| 83 |
+
| 3.3574 | 8.1514 | 28000 | 3.5767 | 0.3677 |
|
| 84 |
+
| 3.3861 | 8.4426 | 29000 | 3.5711 | 0.3682 |
|
| 85 |
+
| 3.3897 | 8.7338 | 30000 | 3.5635 | 0.3687 |
|
| 86 |
+
| 3.2961 | 9.0248 | 31000 | 3.5644 | 0.3690 |
|
| 87 |
+
| 3.3332 | 9.3159 | 32000 | 3.5656 | 0.3693 |
|
| 88 |
+
| 3.3569 | 9.6071 | 33000 | 3.5570 | 0.3699 |
|
| 89 |
+
| 3.3651 | 9.8983 | 34000 | 3.5488 | 0.3702 |
|
| 90 |
+
| 3.2898 | 10.1893 | 35000 | 3.5583 | 0.3700 |
|
| 91 |
+
| 3.3241 | 10.4805 | 36000 | 3.5514 | 0.3707 |
|
| 92 |
+
| 3.3291 | 10.7716 | 37000 | 3.5466 | 0.3712 |
|
| 93 |
+
| 3.2459 | 11.0626 | 38000 | 3.5516 | 0.3711 |
|
| 94 |
+
| 3.2975 | 11.3538 | 39000 | 3.5510 | 0.3713 |
|
| 95 |
+
| 3.2958 | 11.6450 | 40000 | 3.5407 | 0.3720 |
|
| 96 |
+
| 3.3187 | 11.9362 | 41000 | 3.5353 | 0.3726 |
|
| 97 |
+
| 3.2515 | 12.2271 | 42000 | 3.5470 | 0.3723 |
|
| 98 |
+
| 3.2747 | 12.5183 | 43000 | 3.5423 | 0.3724 |
|
| 99 |
+
| 3.2961 | 12.8095 | 44000 | 3.5354 | 0.3730 |
|
| 100 |
+
| 3.2229 | 13.1005 | 45000 | 3.5441 | 0.3728 |
|
| 101 |
+
| 3.236 | 13.3916 | 46000 | 3.5381 | 0.3734 |
|
| 102 |
+
| 3.252 | 13.6828 | 47000 | 3.5329 | 0.3735 |
|
| 103 |
+
| 3.2605 | 13.9740 | 48000 | 3.5270 | 0.3742 |
|
| 104 |
+
| 3.2134 | 14.2650 | 49000 | 3.5373 | 0.3738 |
|
| 105 |
+
| 3.232 | 14.5562 | 50000 | 3.5328 | 0.3742 |
|
| 106 |
+
| 3.2211 | 14.8474 | 51000 | 3.5272 | 0.3746 |
|
| 107 |
+
| 3.167 | 15.1383 | 52000 | 3.5363 | 0.3744 |
|
| 108 |
+
| 3.1923 | 15.4295 | 53000 | 3.5330 | 0.3747 |
|
| 109 |
+
| 3.2039 | 15.7207 | 54000 | 3.5267 | 0.3751 |
|
| 110 |
+
| 3.1459 | 16.0116 | 55000 | 3.5299 | 0.3750 |
|
| 111 |
+
| 3.173 | 16.3028 | 56000 | 3.5322 | 0.3750 |
|
| 112 |
+
| 3.1659 | 16.5940 | 57000 | 3.5269 | 0.3755 |
|
| 113 |
+
| 3.1841 | 16.8852 | 58000 | 3.5209 | 0.3758 |
|
| 114 |
+
| 3.1359 | 17.1762 | 59000 | 3.5285 | 0.3756 |
|
| 115 |
+
| 3.155 | 17.4674 | 60000 | 3.5252 | 0.3758 |
|
| 116 |
+
| 3.1584 | 17.7585 | 61000 | 3.5219 | 0.3762 |
|
| 117 |
+
| 3.1147 | 18.0495 | 62000 | 3.5243 | 0.3762 |
|
| 118 |
+
| 3.1315 | 18.3407 | 63000 | 3.5243 | 0.3762 |
|
| 119 |
+
| 3.1443 | 18.6319 | 64000 | 3.5211 | 0.3765 |
|
| 120 |
+
| 3.1346 | 18.9231 | 65000 | 3.5185 | 0.3768 |
|
| 121 |
+
| 3.1028 | 19.2140 | 66000 | 3.5234 | 0.3766 |
|
| 122 |
+
| 3.1071 | 19.5052 | 67000 | 3.5202 | 0.3769 |
|
| 123 |
+
| 3.1135 | 19.7964 | 68000 | 3.5187 | 0.3771 |
|
| 124 |
+
|
| 125 |
+
|
| 126 |
+
### Framework versions
|
| 127 |
+
|
| 128 |
+
- Transformers 4.55.2
|
| 129 |
+
- Pytorch 2.8.0+cu128
|
| 130 |
+
- Datasets 4.0.0
|
| 131 |
+
- Tokenizers 0.21.4
|
cost_to_drop_frequency_5039/all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.37203666780213424,
|
| 4 |
+
"eval_loss": 3.540740489959717,
|
| 5 |
+
"eval_runtime": 179.4997,
|
| 6 |
+
"eval_samples": 16643,
|
| 7 |
+
"eval_samples_per_second": 92.719,
|
| 8 |
+
"eval_steps_per_second": 5.799,
|
| 9 |
+
"perplexity": 34.49245105033674,
|
| 10 |
+
"total_flos": 1.43566384398336e+18,
|
| 11 |
+
"train_loss": 3.4343077527175305,
|
| 12 |
+
"train_runtime": 136644.7225,
|
| 13 |
+
"train_samples": 274724,
|
| 14 |
+
"train_samples_per_second": 40.21,
|
| 15 |
+
"train_steps_per_second": 0.503
|
| 16 |
+
}
|
cost_to_drop_frequency_5039/checkpoint-30000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 768,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.55.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50257
|
| 31 |
+
}
|
cost_to_drop_frequency_5039/checkpoint-30000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.55.2"
|
| 6 |
+
}
|
cost_to_drop_frequency_5039/checkpoint-30000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_drop_frequency_5039/checkpoint-30000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:873ea3727cc5a71fbd804d866ed53eb27f27b510438c004c598fb98340342a6f
|
| 3 |
+
size 497774208
|
cost_to_drop_frequency_5039/checkpoint-30000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ff4d319a5f1d3c543dad7102e78a0014219c8f336eb743658ae4c271e2c7084
|
| 3 |
+
size 995644811
|
cost_to_drop_frequency_5039/checkpoint-30000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3bf013102919107625384d2c990b9c5417a4bd2ac58a0a005045fb403299c7d
|
| 3 |
+
size 14709
|
cost_to_drop_frequency_5039/checkpoint-30000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7c33361cd2d7c07f43289beb1400eb3b35e2925d1e45eaef6df5259bcae5c49
|
| 3 |
+
size 1383
|
cost_to_drop_frequency_5039/checkpoint-30000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4decfe71065d891acd4c1f26bc0cff168cac64fb24202d09c68225dfad60bdc
|
| 3 |
+
size 1465
|
cost_to_drop_frequency_5039/checkpoint-30000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
cost_to_drop_frequency_5039/checkpoint-30000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_drop_frequency_5039/checkpoint-30000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": false,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
+
"unk_token": "<|endoftext|>"
|
| 20 |
+
}
|
cost_to_drop_frequency_5039/checkpoint-30000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_drop_frequency_5039/checkpoint-30000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83ab1f97ec2871ee1bc51f090550269e0d312593af1fd688e4338e9a2ea6d349
|
| 3 |
+
size 5969
|
cost_to_drop_frequency_5039/checkpoint-30000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_drop_frequency_5039/checkpoint-40000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 768,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.55.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50257
|
| 31 |
+
}
|
cost_to_drop_frequency_5039/checkpoint-40000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.55.2"
|
| 6 |
+
}
|
cost_to_drop_frequency_5039/checkpoint-40000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_drop_frequency_5039/checkpoint-40000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:414deee74a56f07da6de2669a1b07352a74619c5db06a98eff6c8f339126863d
|
| 3 |
+
size 497774208
|
cost_to_drop_frequency_5039/checkpoint-40000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:830cc2257a6871ef4aba23bc67f795d5e6ecbe688e44c88c170860cb039a5f1f
|
| 3 |
+
size 995644811
|
cost_to_drop_frequency_5039/checkpoint-40000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a46bac1e6203ff2e23190a82b759e35cc513c6cc3dce918494b0860eed7a6fe4
|
| 3 |
+
size 14709
|
cost_to_drop_frequency_5039/checkpoint-40000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:946d222c96171d9e6142a089a88714003c15dce6d74524a06b7643528a87048a
|
| 3 |
+
size 1383
|
cost_to_drop_frequency_5039/checkpoint-40000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c19503a968dfffb71da04ed1cec23058f6271195de451325b4ea7fc7f06f964
|
| 3 |
+
size 1465
|
cost_to_drop_frequency_5039/checkpoint-40000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
cost_to_drop_frequency_5039/checkpoint-40000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_drop_frequency_5039/checkpoint-40000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": false,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
+
"unk_token": "<|endoftext|>"
|
| 20 |
+
}
|
cost_to_drop_frequency_5039/checkpoint-40000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_drop_frequency_5039/checkpoint-40000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83ab1f97ec2871ee1bc51f090550269e0d312593af1fd688e4338e9a2ea6d349
|
| 3 |
+
size 5969
|
cost_to_drop_frequency_5039/checkpoint-40000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_drop_frequency_5039/checkpoint-50000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 768,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.55.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50257
|
| 31 |
+
}
|
cost_to_drop_frequency_5039/checkpoint-50000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.55.2"
|
| 6 |
+
}
|
cost_to_drop_frequency_5039/checkpoint-50000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_drop_frequency_5039/checkpoint-50000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9e14eda63a0fec12d748b7341dc5b587ed039de09fc540045f41ff696e72250
|
| 3 |
+
size 497774208
|
cost_to_drop_frequency_5039/checkpoint-50000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74673216263d2870379e00bccb75995ae722de00ce763f48b2cb91d9e76344f6
|
| 3 |
+
size 995644811
|
cost_to_drop_frequency_5039/checkpoint-50000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66a90c3de6c65744b9610dcc060886522be8c56a54d99479baf1cd261b1a9fe8
|
| 3 |
+
size 14709
|
cost_to_drop_frequency_5039/checkpoint-50000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bef4d3542a8b90cfedeaafec98749fc4ad766b9ea8eaeef2c42206c124f49b3e
|
| 3 |
+
size 1383
|
cost_to_drop_frequency_5039/checkpoint-50000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83c9d5ef0f83a88aeffa53c543d02f32eef44db7cf6b396d7b3eb055fa36dcdc
|
| 3 |
+
size 1465
|
cost_to_drop_frequency_5039/checkpoint-50000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
| 5 |
+
}
|
cost_to_drop_frequency_5039/checkpoint-50000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_drop_frequency_5039/checkpoint-50000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
}
|
| 12 |
+
},
|
| 13 |
+
"bos_token": "<|endoftext|>",
|
| 14 |
+
"clean_up_tokenization_spaces": false,
|
| 15 |
+
"eos_token": "<|endoftext|>",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
+
"unk_token": "<|endoftext|>"
|
| 20 |
+
}
|
cost_to_drop_frequency_5039/checkpoint-50000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_drop_frequency_5039/checkpoint-50000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83ab1f97ec2871ee1bc51f090550269e0d312593af1fd688e4338e9a2ea6d349
|
| 3 |
+
size 5969
|
cost_to_drop_frequency_5039/checkpoint-50000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_drop_frequency_5039/checkpoint-60000/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 50256,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 50256,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 768,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 1024,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.55.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 50257
|
| 31 |
+
}
|
cost_to_drop_frequency_5039/checkpoint-60000/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.55.2"
|
| 6 |
+
}
|
cost_to_drop_frequency_5039/checkpoint-60000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_drop_frequency_5039/checkpoint-60000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:519ca95e0f3bd1877267ba0e5002f9f27570671ef09ddd0a436e9a1fbf18a54e
|
| 3 |
+
size 497774208
|
cost_to_drop_frequency_5039/checkpoint-60000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cabbc06170bab9263fbad8f6e0acf89426b50025101f633bad8ecc8b43967561
|
| 3 |
+
size 995644811
|
cost_to_drop_frequency_5039/checkpoint-60000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91426a3206bead78947ebbe8050170b4706659e4cc93bf200114f2b5dccf51d9
|
| 3 |
+
size 14709
|