Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- cost_to_hit_frequency_1001/README.md +131 -0
- cost_to_hit_frequency_1001/all_results.json +16 -0
- cost_to_hit_frequency_1001/checkpoint-30000/config.json +31 -0
- cost_to_hit_frequency_1001/checkpoint-30000/generation_config.json +6 -0
- cost_to_hit_frequency_1001/checkpoint-30000/merges.txt +0 -0
- cost_to_hit_frequency_1001/checkpoint-30000/model.safetensors +3 -0
- cost_to_hit_frequency_1001/checkpoint-30000/optimizer.pt +3 -0
- cost_to_hit_frequency_1001/checkpoint-30000/rng_state.pth +3 -0
- cost_to_hit_frequency_1001/checkpoint-30000/scaler.pt +3 -0
- cost_to_hit_frequency_1001/checkpoint-30000/scheduler.pt +3 -0
- cost_to_hit_frequency_1001/checkpoint-30000/special_tokens_map.json +5 -0
- cost_to_hit_frequency_1001/checkpoint-30000/tokenizer.json +0 -0
- cost_to_hit_frequency_1001/checkpoint-30000/tokenizer_config.json +20 -0
- cost_to_hit_frequency_1001/checkpoint-30000/trainer_state.json +0 -0
- cost_to_hit_frequency_1001/checkpoint-30000/training_args.bin +3 -0
- cost_to_hit_frequency_1001/checkpoint-30000/vocab.json +0 -0
- cost_to_hit_frequency_1001/checkpoint-40000/config.json +31 -0
- cost_to_hit_frequency_1001/checkpoint-40000/generation_config.json +6 -0
- cost_to_hit_frequency_1001/checkpoint-40000/merges.txt +0 -0
- cost_to_hit_frequency_1001/checkpoint-40000/model.safetensors +3 -0
- cost_to_hit_frequency_1001/checkpoint-40000/optimizer.pt +3 -0
- cost_to_hit_frequency_1001/checkpoint-40000/rng_state.pth +3 -0
- cost_to_hit_frequency_1001/checkpoint-40000/scaler.pt +3 -0
- cost_to_hit_frequency_1001/checkpoint-40000/scheduler.pt +3 -0
- cost_to_hit_frequency_1001/checkpoint-40000/special_tokens_map.json +5 -0
- cost_to_hit_frequency_1001/checkpoint-40000/tokenizer.json +0 -0
- cost_to_hit_frequency_1001/checkpoint-40000/tokenizer_config.json +20 -0
- cost_to_hit_frequency_1001/checkpoint-40000/trainer_state.json +0 -0
- cost_to_hit_frequency_1001/checkpoint-40000/training_args.bin +3 -0
- cost_to_hit_frequency_1001/checkpoint-40000/vocab.json +0 -0
- cost_to_hit_frequency_1001/checkpoint-50000/config.json +31 -0
- cost_to_hit_frequency_1001/checkpoint-50000/generation_config.json +6 -0
- cost_to_hit_frequency_1001/checkpoint-50000/merges.txt +0 -0
- cost_to_hit_frequency_1001/checkpoint-50000/model.safetensors +3 -0
- cost_to_hit_frequency_1001/checkpoint-50000/optimizer.pt +3 -0
- cost_to_hit_frequency_1001/checkpoint-50000/rng_state.pth +3 -0
- cost_to_hit_frequency_1001/checkpoint-50000/scaler.pt +3 -0
- cost_to_hit_frequency_1001/checkpoint-50000/scheduler.pt +3 -0
- cost_to_hit_frequency_1001/checkpoint-50000/special_tokens_map.json +5 -0
- cost_to_hit_frequency_1001/checkpoint-50000/tokenizer.json +0 -0
- cost_to_hit_frequency_1001/checkpoint-50000/tokenizer_config.json +20 -0
- cost_to_hit_frequency_1001/checkpoint-50000/trainer_state.json +0 -0
- cost_to_hit_frequency_1001/checkpoint-50000/training_args.bin +3 -0
- cost_to_hit_frequency_1001/checkpoint-50000/vocab.json +0 -0
- cost_to_hit_frequency_1001/checkpoint-60000/config.json +31 -0
- cost_to_hit_frequency_1001/checkpoint-60000/generation_config.json +6 -0
- cost_to_hit_frequency_1001/checkpoint-60000/merges.txt +0 -0
- cost_to_hit_frequency_1001/checkpoint-60000/model.safetensors +3 -0
- cost_to_hit_frequency_1001/checkpoint-60000/optimizer.pt +3 -0
- cost_to_hit_frequency_1001/checkpoint-60000/rng_state.pth +3 -0
cost_to_hit_frequency_1001/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_hit_frequency_1001
|
| 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/3l1xx9yi)
|
| 16 |
+
# exceptions_exp2_cost_to_hit_frequency_1001
|
| 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: 3.5636
|
| 21 |
+
- Accuracy: 0.3686
|
| 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: 1001
|
| 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 |
+
| 4.8133 | 0.2913 | 1000 | 4.7542 | 0.2546 |
|
| 57 |
+
| 4.3432 | 0.5826 | 2000 | 4.2874 | 0.2989 |
|
| 58 |
+
| 4.1316 | 0.8739 | 3000 | 4.0944 | 0.3165 |
|
| 59 |
+
| 3.9856 | 1.1652 | 4000 | 3.9840 | 0.3263 |
|
| 60 |
+
| 3.9435 | 1.4565 | 5000 | 3.9095 | 0.3328 |
|
| 61 |
+
| 3.8665 | 1.7478 | 6000 | 3.8514 | 0.3380 |
|
| 62 |
+
| 3.7491 | 2.0390 | 7000 | 3.8110 | 0.3422 |
|
| 63 |
+
| 3.7416 | 2.3303 | 8000 | 3.7788 | 0.3452 |
|
| 64 |
+
| 3.728 | 2.6216 | 9000 | 3.7483 | 0.3481 |
|
| 65 |
+
| 3.6958 | 2.9130 | 10000 | 3.7223 | 0.3504 |
|
| 66 |
+
| 3.6306 | 3.2042 | 11000 | 3.7092 | 0.3524 |
|
| 67 |
+
| 3.6245 | 3.4955 | 12000 | 3.6911 | 0.3540 |
|
| 68 |
+
| 3.6365 | 3.7868 | 13000 | 3.6707 | 0.3559 |
|
| 69 |
+
| 3.5138 | 4.0781 | 14000 | 3.6639 | 0.3571 |
|
| 70 |
+
| 3.5632 | 4.3694 | 15000 | 3.6536 | 0.3582 |
|
| 71 |
+
| 3.5684 | 4.6607 | 16000 | 3.6403 | 0.3597 |
|
| 72 |
+
| 3.5646 | 4.9520 | 17000 | 3.6256 | 0.3607 |
|
| 73 |
+
| 3.4892 | 5.2432 | 18000 | 3.6295 | 0.3613 |
|
| 74 |
+
| 3.5037 | 5.5345 | 19000 | 3.6170 | 0.3623 |
|
| 75 |
+
| 3.5029 | 5.8259 | 20000 | 3.6043 | 0.3632 |
|
| 76 |
+
| 3.4399 | 6.1171 | 21000 | 3.6081 | 0.3638 |
|
| 77 |
+
| 3.4438 | 6.4084 | 22000 | 3.6000 | 0.3643 |
|
| 78 |
+
| 3.4622 | 6.6997 | 23000 | 3.5912 | 0.3649 |
|
| 79 |
+
| 3.4761 | 6.9910 | 24000 | 3.5797 | 0.3658 |
|
| 80 |
+
| 3.4035 | 7.2823 | 25000 | 3.5883 | 0.3660 |
|
| 81 |
+
| 3.4207 | 7.5736 | 26000 | 3.5815 | 0.3664 |
|
| 82 |
+
| 3.4351 | 7.8649 | 27000 | 3.5713 | 0.3672 |
|
| 83 |
+
| 3.3456 | 8.1561 | 28000 | 3.5803 | 0.3676 |
|
| 84 |
+
| 3.379 | 8.4474 | 29000 | 3.5733 | 0.3679 |
|
| 85 |
+
| 3.3926 | 8.7388 | 30000 | 3.5636 | 0.3686 |
|
| 86 |
+
| 3.305 | 9.0300 | 31000 | 3.5686 | 0.3689 |
|
| 87 |
+
| 3.333 | 9.3213 | 32000 | 3.5682 | 0.3688 |
|
| 88 |
+
| 3.3523 | 9.6126 | 33000 | 3.5594 | 0.3696 |
|
| 89 |
+
| 3.3654 | 9.9039 | 34000 | 3.5503 | 0.3704 |
|
| 90 |
+
| 3.2834 | 10.1952 | 35000 | 3.5617 | 0.3699 |
|
| 91 |
+
| 3.3313 | 10.4865 | 36000 | 3.5552 | 0.3705 |
|
| 92 |
+
| 3.3399 | 10.7778 | 37000 | 3.5458 | 0.3711 |
|
| 93 |
+
| 3.2605 | 11.0690 | 38000 | 3.5583 | 0.3707 |
|
| 94 |
+
| 3.2906 | 11.3603 | 39000 | 3.5520 | 0.3713 |
|
| 95 |
+
| 3.3088 | 11.6517 | 40000 | 3.5464 | 0.3716 |
|
| 96 |
+
| 3.3188 | 11.9430 | 41000 | 3.5363 | 0.3725 |
|
| 97 |
+
| 3.2678 | 12.2342 | 42000 | 3.5468 | 0.3721 |
|
| 98 |
+
| 3.2818 | 12.5255 | 43000 | 3.5414 | 0.3725 |
|
| 99 |
+
| 3.2772 | 12.8168 | 44000 | 3.5360 | 0.3733 |
|
| 100 |
+
| 3.215 | 13.1081 | 45000 | 3.5467 | 0.3725 |
|
| 101 |
+
| 3.2448 | 13.3994 | 46000 | 3.5431 | 0.3730 |
|
| 102 |
+
| 3.2716 | 13.6907 | 47000 | 3.5369 | 0.3734 |
|
| 103 |
+
| 3.2672 | 13.9820 | 48000 | 3.5273 | 0.3741 |
|
| 104 |
+
| 3.2114 | 14.2732 | 49000 | 3.5384 | 0.3735 |
|
| 105 |
+
| 3.229 | 14.5646 | 50000 | 3.5358 | 0.3739 |
|
| 106 |
+
| 3.2327 | 14.8559 | 51000 | 3.5292 | 0.3745 |
|
| 107 |
+
| 3.1816 | 15.1471 | 52000 | 3.5386 | 0.3739 |
|
| 108 |
+
| 3.1996 | 15.4384 | 53000 | 3.5346 | 0.3745 |
|
| 109 |
+
| 3.2029 | 15.7297 | 54000 | 3.5301 | 0.3748 |
|
| 110 |
+
| 3.151 | 16.0210 | 55000 | 3.5326 | 0.3749 |
|
| 111 |
+
| 3.1679 | 16.3123 | 56000 | 3.5329 | 0.3749 |
|
| 112 |
+
| 3.183 | 16.6036 | 57000 | 3.5285 | 0.3752 |
|
| 113 |
+
| 3.1985 | 16.8949 | 58000 | 3.5229 | 0.3757 |
|
| 114 |
+
| 3.1424 | 17.1861 | 59000 | 3.5316 | 0.3755 |
|
| 115 |
+
| 3.1539 | 17.4775 | 60000 | 3.5271 | 0.3757 |
|
| 116 |
+
| 3.1562 | 17.7688 | 61000 | 3.5240 | 0.3760 |
|
| 117 |
+
| 3.1148 | 18.0600 | 62000 | 3.5264 | 0.3759 |
|
| 118 |
+
| 3.1308 | 18.3513 | 63000 | 3.5277 | 0.3758 |
|
| 119 |
+
| 3.1398 | 18.6426 | 64000 | 3.5230 | 0.3763 |
|
| 120 |
+
| 3.1284 | 18.9339 | 65000 | 3.5189 | 0.3767 |
|
| 121 |
+
| 3.1103 | 19.2252 | 66000 | 3.5239 | 0.3765 |
|
| 122 |
+
| 3.1006 | 19.5165 | 67000 | 3.5217 | 0.3768 |
|
| 123 |
+
| 3.1085 | 19.8078 | 68000 | 3.5209 | 0.3769 |
|
| 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_hit_frequency_1001/all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.3686057656808563,
|
| 4 |
+
"eval_loss": 3.563647985458374,
|
| 5 |
+
"eval_runtime": 180.1205,
|
| 6 |
+
"eval_samples": 16644,
|
| 7 |
+
"eval_samples_per_second": 92.405,
|
| 8 |
+
"eval_steps_per_second": 5.779,
|
| 9 |
+
"perplexity": 35.29170623409146,
|
| 10 |
+
"total_flos": 1.43513603407872e+18,
|
| 11 |
+
"train_loss": 3.4363333413179364,
|
| 12 |
+
"train_runtime": 137192.0021,
|
| 13 |
+
"train_samples": 274623,
|
| 14 |
+
"train_samples_per_second": 40.035,
|
| 15 |
+
"train_steps_per_second": 0.5
|
| 16 |
+
}
|
cost_to_hit_frequency_1001/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_hit_frequency_1001/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_hit_frequency_1001/checkpoint-30000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_1001/checkpoint-30000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15c2dc068088dd27d07bbe47fb0ae23bf7d6241c26429d1d4e56c959858bee8f
|
| 3 |
+
size 497774208
|
cost_to_hit_frequency_1001/checkpoint-30000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85e2a30f857127db796b165b461679fc6c2f853db3b57e2faef42f2c03db8533
|
| 3 |
+
size 995644811
|
cost_to_hit_frequency_1001/checkpoint-30000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc928819b74f42bc537daa4a227fd5b4bc379c6ff66ca26d700f00d98920de96
|
| 3 |
+
size 14709
|
cost_to_hit_frequency_1001/checkpoint-30000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bed978eabd2bfe10b855ad2f6c6fc4fb7ba82baca7274d157220543628cd5744
|
| 3 |
+
size 1383
|
cost_to_hit_frequency_1001/checkpoint-30000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:301efb1017ab1ce751d8060f27c0667481947139f2c5d378534548d2f869629f
|
| 3 |
+
size 1465
|
cost_to_hit_frequency_1001/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_hit_frequency_1001/checkpoint-30000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_1001/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_hit_frequency_1001/checkpoint-30000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_1001/checkpoint-30000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:279548772ef7c66901458e95391b4b85ef0950f988635edf93997aeb8f3a32c7
|
| 3 |
+
size 5969
|
cost_to_hit_frequency_1001/checkpoint-30000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_1001/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_hit_frequency_1001/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_hit_frequency_1001/checkpoint-40000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_1001/checkpoint-40000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93599a9e167d60290d3ef49ca765c0c5197bae2928d37b95042f117cd1740683
|
| 3 |
+
size 497774208
|
cost_to_hit_frequency_1001/checkpoint-40000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25b2b28661543c3867ca24029e09641aa1ffbd2390f7461f1e61bc04dfa949cf
|
| 3 |
+
size 995644811
|
cost_to_hit_frequency_1001/checkpoint-40000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac90de6009db68c7e935ffb1e21051bece53578f3a990f94956a33ad3e8ea5bc
|
| 3 |
+
size 14709
|
cost_to_hit_frequency_1001/checkpoint-40000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e17e9b4952d545a632f9f60b6d65403e7f60e979cd16b7801d7ff0567cd605fe
|
| 3 |
+
size 1383
|
cost_to_hit_frequency_1001/checkpoint-40000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6859e009e74a90c701fc291ca3ce2c55b6127473c95e8cad74136c092fc90eb6
|
| 3 |
+
size 1465
|
cost_to_hit_frequency_1001/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_hit_frequency_1001/checkpoint-40000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_1001/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_hit_frequency_1001/checkpoint-40000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_1001/checkpoint-40000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:279548772ef7c66901458e95391b4b85ef0950f988635edf93997aeb8f3a32c7
|
| 3 |
+
size 5969
|
cost_to_hit_frequency_1001/checkpoint-40000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_1001/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_hit_frequency_1001/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_hit_frequency_1001/checkpoint-50000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_1001/checkpoint-50000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7c0ea7b2f686575fe01a702467fdafc8f471b2e9c4325a42b60c35472807ed1
|
| 3 |
+
size 497774208
|
cost_to_hit_frequency_1001/checkpoint-50000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:018318cc1707fb37a0b1cd2dc967e736079b4d9296bbb919544845c18874e4ea
|
| 3 |
+
size 995644811
|
cost_to_hit_frequency_1001/checkpoint-50000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b71a86cbc55ca5157f0c42a5ffddaf7bad934965cae3ed29c055a5a6169b638
|
| 3 |
+
size 14709
|
cost_to_hit_frequency_1001/checkpoint-50000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abf5120504d0b2cddf8b79e754c379a1ae3ca9c5882d80944306a9bd3139fd2b
|
| 3 |
+
size 1383
|
cost_to_hit_frequency_1001/checkpoint-50000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc8fc0c2226e9ab2cff6efec2bea9da1344a082a5b304e22da1fda36060e5c6b
|
| 3 |
+
size 1465
|
cost_to_hit_frequency_1001/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_hit_frequency_1001/checkpoint-50000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_1001/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_hit_frequency_1001/checkpoint-50000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_1001/checkpoint-50000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:279548772ef7c66901458e95391b4b85ef0950f988635edf93997aeb8f3a32c7
|
| 3 |
+
size 5969
|
cost_to_hit_frequency_1001/checkpoint-50000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_1001/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_hit_frequency_1001/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_hit_frequency_1001/checkpoint-60000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_1001/checkpoint-60000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:146de1280eac397654d1ddb523a16017515cd9b98cf97860bd18ccac81a11482
|
| 3 |
+
size 497774208
|
cost_to_hit_frequency_1001/checkpoint-60000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af8e68b4f74ba0c6cfe9c1746e5a2bd7bc6efe98b11fae718eb8eeb887ca8574
|
| 3 |
+
size 995644811
|
cost_to_hit_frequency_1001/checkpoint-60000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7343b1aef772e95b5c15a21a1000664d591e4a06134092ac17cc3f06c146b598
|
| 3 |
+
size 14709
|