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_2128/README.md +131 -0
- cost_to_hit_frequency_2128/all_results.json +16 -0
- cost_to_hit_frequency_2128/checkpoint-30000/config.json +31 -0
- cost_to_hit_frequency_2128/checkpoint-30000/generation_config.json +6 -0
- cost_to_hit_frequency_2128/checkpoint-30000/merges.txt +0 -0
- cost_to_hit_frequency_2128/checkpoint-30000/model.safetensors +3 -0
- cost_to_hit_frequency_2128/checkpoint-30000/optimizer.pt +3 -0
- cost_to_hit_frequency_2128/checkpoint-30000/rng_state.pth +3 -0
- cost_to_hit_frequency_2128/checkpoint-30000/scaler.pt +3 -0
- cost_to_hit_frequency_2128/checkpoint-30000/scheduler.pt +3 -0
- cost_to_hit_frequency_2128/checkpoint-30000/special_tokens_map.json +5 -0
- cost_to_hit_frequency_2128/checkpoint-30000/tokenizer.json +0 -0
- cost_to_hit_frequency_2128/checkpoint-30000/tokenizer_config.json +20 -0
- cost_to_hit_frequency_2128/checkpoint-30000/trainer_state.json +0 -0
- cost_to_hit_frequency_2128/checkpoint-30000/training_args.bin +3 -0
- cost_to_hit_frequency_2128/checkpoint-30000/vocab.json +0 -0
- cost_to_hit_frequency_2128/checkpoint-40000/config.json +31 -0
- cost_to_hit_frequency_2128/checkpoint-40000/generation_config.json +6 -0
- cost_to_hit_frequency_2128/checkpoint-40000/merges.txt +0 -0
- cost_to_hit_frequency_2128/checkpoint-40000/model.safetensors +3 -0
- cost_to_hit_frequency_2128/checkpoint-40000/optimizer.pt +3 -0
- cost_to_hit_frequency_2128/checkpoint-40000/rng_state.pth +3 -0
- cost_to_hit_frequency_2128/checkpoint-40000/scaler.pt +3 -0
- cost_to_hit_frequency_2128/checkpoint-40000/scheduler.pt +3 -0
- cost_to_hit_frequency_2128/checkpoint-40000/special_tokens_map.json +5 -0
- cost_to_hit_frequency_2128/checkpoint-40000/tokenizer.json +0 -0
- cost_to_hit_frequency_2128/checkpoint-40000/tokenizer_config.json +20 -0
- cost_to_hit_frequency_2128/checkpoint-40000/trainer_state.json +0 -0
- cost_to_hit_frequency_2128/checkpoint-40000/training_args.bin +3 -0
- cost_to_hit_frequency_2128/checkpoint-40000/vocab.json +0 -0
- cost_to_hit_frequency_2128/checkpoint-50000/config.json +31 -0
- cost_to_hit_frequency_2128/checkpoint-50000/generation_config.json +6 -0
- cost_to_hit_frequency_2128/checkpoint-50000/merges.txt +0 -0
- cost_to_hit_frequency_2128/checkpoint-50000/model.safetensors +3 -0
- cost_to_hit_frequency_2128/checkpoint-50000/optimizer.pt +3 -0
- cost_to_hit_frequency_2128/checkpoint-50000/rng_state.pth +3 -0
- cost_to_hit_frequency_2128/checkpoint-50000/scaler.pt +3 -0
- cost_to_hit_frequency_2128/checkpoint-50000/scheduler.pt +3 -0
- cost_to_hit_frequency_2128/checkpoint-50000/special_tokens_map.json +5 -0
- cost_to_hit_frequency_2128/checkpoint-50000/tokenizer.json +0 -0
- cost_to_hit_frequency_2128/checkpoint-50000/tokenizer_config.json +20 -0
- cost_to_hit_frequency_2128/checkpoint-50000/trainer_state.json +0 -0
- cost_to_hit_frequency_2128/checkpoint-50000/training_args.bin +3 -0
- cost_to_hit_frequency_2128/checkpoint-50000/vocab.json +0 -0
- cost_to_hit_frequency_2128/checkpoint-60000/config.json +31 -0
- cost_to_hit_frequency_2128/checkpoint-60000/generation_config.json +6 -0
- cost_to_hit_frequency_2128/checkpoint-60000/merges.txt +0 -0
- cost_to_hit_frequency_2128/checkpoint-60000/model.safetensors +3 -0
- cost_to_hit_frequency_2128/checkpoint-60000/optimizer.pt +3 -0
- cost_to_hit_frequency_2128/checkpoint-60000/rng_state.pth +3 -0
cost_to_hit_frequency_2128/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_2128
|
| 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/bzy2btrz)
|
| 16 |
+
# exceptions_exp2_cost_to_hit_frequency_2128
|
| 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: 3.5464
|
| 21 |
+
- Accuracy: 0.3716
|
| 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: 2128
|
| 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 |
+
| 4.836 | 0.2913 | 1000 | 4.7542 | 0.2547 |
|
| 57 |
+
| 4.3423 | 0.5826 | 2000 | 4.2851 | 0.2993 |
|
| 58 |
+
| 4.1418 | 0.8739 | 3000 | 4.0991 | 0.3155 |
|
| 59 |
+
| 3.991 | 1.1652 | 4000 | 3.9937 | 0.3253 |
|
| 60 |
+
| 3.9297 | 1.4565 | 5000 | 3.9147 | 0.3317 |
|
| 61 |
+
| 3.8779 | 1.7478 | 6000 | 3.8544 | 0.3371 |
|
| 62 |
+
| 3.7427 | 2.0390 | 7000 | 3.8124 | 0.3416 |
|
| 63 |
+
| 3.7492 | 2.3303 | 8000 | 3.7812 | 0.3447 |
|
| 64 |
+
| 3.7372 | 2.6216 | 9000 | 3.7514 | 0.3474 |
|
| 65 |
+
| 3.7056 | 2.9130 | 10000 | 3.7261 | 0.3498 |
|
| 66 |
+
| 3.6285 | 3.2042 | 11000 | 3.7096 | 0.3520 |
|
| 67 |
+
| 3.638 | 3.4955 | 12000 | 3.6934 | 0.3540 |
|
| 68 |
+
| 3.616 | 3.7868 | 13000 | 3.6741 | 0.3555 |
|
| 69 |
+
| 3.5277 | 4.0781 | 14000 | 3.6672 | 0.3568 |
|
| 70 |
+
| 3.5578 | 4.3694 | 15000 | 3.6568 | 0.3576 |
|
| 71 |
+
| 3.5631 | 4.6607 | 16000 | 3.6425 | 0.3594 |
|
| 72 |
+
| 3.5746 | 4.9520 | 17000 | 3.6273 | 0.3607 |
|
| 73 |
+
| 3.4835 | 5.2432 | 18000 | 3.6301 | 0.3612 |
|
| 74 |
+
| 3.5199 | 5.5345 | 19000 | 3.6201 | 0.3620 |
|
| 75 |
+
| 3.5176 | 5.8259 | 20000 | 3.6096 | 0.3629 |
|
| 76 |
+
| 3.4233 | 6.1171 | 21000 | 3.6123 | 0.3633 |
|
| 77 |
+
| 3.4484 | 6.4084 | 22000 | 3.6026 | 0.3641 |
|
| 78 |
+
| 3.4673 | 6.6997 | 23000 | 3.5936 | 0.3648 |
|
| 79 |
+
| 3.4728 | 6.9910 | 24000 | 3.5832 | 0.3659 |
|
| 80 |
+
| 3.4081 | 7.2823 | 25000 | 3.5913 | 0.3657 |
|
| 81 |
+
| 3.4258 | 7.5736 | 26000 | 3.5828 | 0.3662 |
|
| 82 |
+
| 3.4357 | 7.8649 | 27000 | 3.5754 | 0.3675 |
|
| 83 |
+
| 3.3437 | 8.1561 | 28000 | 3.5826 | 0.3672 |
|
| 84 |
+
| 3.3846 | 8.4474 | 29000 | 3.5741 | 0.3677 |
|
| 85 |
+
| 3.397 | 8.7388 | 30000 | 3.5654 | 0.3687 |
|
| 86 |
+
| 3.2933 | 9.0300 | 31000 | 3.5706 | 0.3684 |
|
| 87 |
+
| 3.3448 | 9.3213 | 32000 | 3.5704 | 0.3688 |
|
| 88 |
+
| 3.362 | 9.6126 | 33000 | 3.5591 | 0.3695 |
|
| 89 |
+
| 3.3664 | 9.9039 | 34000 | 3.5527 | 0.3701 |
|
| 90 |
+
| 3.3097 | 10.1952 | 35000 | 3.5632 | 0.3696 |
|
| 91 |
+
| 3.3296 | 10.4865 | 36000 | 3.5596 | 0.3700 |
|
| 92 |
+
| 3.3485 | 10.7778 | 37000 | 3.5511 | 0.3708 |
|
| 93 |
+
| 3.2602 | 11.0690 | 38000 | 3.5577 | 0.3708 |
|
| 94 |
+
| 3.2927 | 11.3603 | 39000 | 3.5537 | 0.3709 |
|
| 95 |
+
| 3.2965 | 11.6517 | 40000 | 3.5464 | 0.3716 |
|
| 96 |
+
| 3.3093 | 11.9430 | 41000 | 3.5401 | 0.3719 |
|
| 97 |
+
| 3.2578 | 12.2342 | 42000 | 3.5509 | 0.3716 |
|
| 98 |
+
| 3.2759 | 12.5255 | 43000 | 3.5461 | 0.3721 |
|
| 99 |
+
| 3.2977 | 12.8168 | 44000 | 3.5381 | 0.3729 |
|
| 100 |
+
| 3.2116 | 13.1081 | 45000 | 3.5465 | 0.3725 |
|
| 101 |
+
| 3.2472 | 13.3994 | 46000 | 3.5436 | 0.3728 |
|
| 102 |
+
| 3.2546 | 13.6907 | 47000 | 3.5366 | 0.3733 |
|
| 103 |
+
| 3.2669 | 13.9820 | 48000 | 3.5320 | 0.3736 |
|
| 104 |
+
| 3.2044 | 14.2732 | 49000 | 3.5419 | 0.3734 |
|
| 105 |
+
| 3.2363 | 14.5646 | 50000 | 3.5365 | 0.3739 |
|
| 106 |
+
| 3.2326 | 14.8559 | 51000 | 3.5300 | 0.3743 |
|
| 107 |
+
| 3.1742 | 15.1471 | 52000 | 3.5394 | 0.3739 |
|
| 108 |
+
| 3.2021 | 15.4384 | 53000 | 3.5332 | 0.3746 |
|
| 109 |
+
| 3.2011 | 15.7297 | 54000 | 3.5290 | 0.3747 |
|
| 110 |
+
| 3.1483 | 16.0210 | 55000 | 3.5327 | 0.3748 |
|
| 111 |
+
| 3.16 | 16.3123 | 56000 | 3.5347 | 0.3746 |
|
| 112 |
+
| 3.1867 | 16.6036 | 57000 | 3.5271 | 0.3752 |
|
| 113 |
+
| 3.1814 | 16.8949 | 58000 | 3.5252 | 0.3755 |
|
| 114 |
+
| 3.1394 | 17.1861 | 59000 | 3.5330 | 0.3753 |
|
| 115 |
+
| 3.1498 | 17.4775 | 60000 | 3.5306 | 0.3755 |
|
| 116 |
+
| 3.1687 | 17.7688 | 61000 | 3.5236 | 0.3760 |
|
| 117 |
+
| 3.1237 | 18.0600 | 62000 | 3.5266 | 0.3760 |
|
| 118 |
+
| 3.1318 | 18.3513 | 63000 | 3.5264 | 0.3759 |
|
| 119 |
+
| 3.1343 | 18.6426 | 64000 | 3.5249 | 0.3764 |
|
| 120 |
+
| 3.1352 | 18.9339 | 65000 | 3.5207 | 0.3766 |
|
| 121 |
+
| 3.1114 | 19.2252 | 66000 | 3.5234 | 0.3765 |
|
| 122 |
+
| 3.129 | 19.5165 | 67000 | 3.5234 | 0.3766 |
|
| 123 |
+
| 3.1103 | 19.8078 | 68000 | 3.5216 | 0.3767 |
|
| 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_2128/all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"eval_accuracy": 0.3716299568587447,
|
| 4 |
+
"eval_loss": 3.5464437007904053,
|
| 5 |
+
"eval_runtime": 179.9004,
|
| 6 |
+
"eval_samples": 16644,
|
| 7 |
+
"eval_samples_per_second": 92.518,
|
| 8 |
+
"eval_steps_per_second": 5.787,
|
| 9 |
+
"perplexity": 34.689730800009954,
|
| 10 |
+
"total_flos": 1.43513603407872e+18,
|
| 11 |
+
"train_loss": 3.438410573848788,
|
| 12 |
+
"train_runtime": 137369.0027,
|
| 13 |
+
"train_samples": 274623,
|
| 14 |
+
"train_samples_per_second": 39.983,
|
| 15 |
+
"train_steps_per_second": 0.5
|
| 16 |
+
}
|
cost_to_hit_frequency_2128/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_2128/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_2128/checkpoint-30000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_2128/checkpoint-30000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15eff0546433eae5fcecd7242796be8b625c9cbfcb550107310407e993979a2f
|
| 3 |
+
size 497774208
|
cost_to_hit_frequency_2128/checkpoint-30000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f00a95e2440639bc5b56de4da1e6fc8d240080959df3872b9f78f09b4caf9a22
|
| 3 |
+
size 995644811
|
cost_to_hit_frequency_2128/checkpoint-30000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a83888c246e208f0fbb7f99b6a5848c0701bd3de35fcbddacf2fb163dbed1af
|
| 3 |
+
size 14773
|
cost_to_hit_frequency_2128/checkpoint-30000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff4341875e519c94e18fcbb09e5679daac8d5ceef9652233684801e8641eff08
|
| 3 |
+
size 1383
|
cost_to_hit_frequency_2128/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_2128/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_2128/checkpoint-30000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_2128/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_2128/checkpoint-30000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_2128/checkpoint-30000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20f748c64364a58a4f3b9ecaa8ad6e0708fdb6f6064c4fe9f0a8b760e4cf2ae3
|
| 3 |
+
size 5969
|
cost_to_hit_frequency_2128/checkpoint-30000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_2128/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_2128/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_2128/checkpoint-40000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_2128/checkpoint-40000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0d2c282e441baa606ce9b816e263406f81ea5beb99df861dd82d8fd7ad78d31
|
| 3 |
+
size 497774208
|
cost_to_hit_frequency_2128/checkpoint-40000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d94309c30fe3a3ffdb5874e7447a44fbf756a1e4a8c32502c7dfb5296f823b33
|
| 3 |
+
size 995644811
|
cost_to_hit_frequency_2128/checkpoint-40000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9f11a1a44e39d6aa8689843ed1a17279bc49b7fc67e589b5bc9e78e2ea5257c
|
| 3 |
+
size 14773
|
cost_to_hit_frequency_2128/checkpoint-40000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d30e0d467a783bf8ad251da21fdf6502bfe87d6923cc16f79e2feb040e6506bd
|
| 3 |
+
size 1383
|
cost_to_hit_frequency_2128/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_2128/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_2128/checkpoint-40000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_2128/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_2128/checkpoint-40000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_2128/checkpoint-40000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20f748c64364a58a4f3b9ecaa8ad6e0708fdb6f6064c4fe9f0a8b760e4cf2ae3
|
| 3 |
+
size 5969
|
cost_to_hit_frequency_2128/checkpoint-40000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_2128/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_2128/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_2128/checkpoint-50000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_2128/checkpoint-50000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cc6b21ff94c5771afdc6762ad1714ffb967e85cc0cfb716dc0ec98014ced8e6
|
| 3 |
+
size 497774208
|
cost_to_hit_frequency_2128/checkpoint-50000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf5261017e0b0ee0d23f9b8d2852fbc3b91b7f445bc4c356e07fe629d2887ba5
|
| 3 |
+
size 995644811
|
cost_to_hit_frequency_2128/checkpoint-50000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5350ffff11d9c4ffcbf017f8fc0fc14f02b6c821167264f309a8779b3a5d988
|
| 3 |
+
size 14773
|
cost_to_hit_frequency_2128/checkpoint-50000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cf09822b0a9b942f1a93d43c4773d91eb034b6672175d8595eb94616dba5a4f
|
| 3 |
+
size 1383
|
cost_to_hit_frequency_2128/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_2128/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_2128/checkpoint-50000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_2128/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_2128/checkpoint-50000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_2128/checkpoint-50000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20f748c64364a58a4f3b9ecaa8ad6e0708fdb6f6064c4fe9f0a8b760e4cf2ae3
|
| 3 |
+
size 5969
|
cost_to_hit_frequency_2128/checkpoint-50000/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_2128/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_2128/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_2128/checkpoint-60000/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
cost_to_hit_frequency_2128/checkpoint-60000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d39645cb26ea6c32a4aaff1d85d2197fe6ddea03e4c20cd7d9336c9de601dd01
|
| 3 |
+
size 497774208
|
cost_to_hit_frequency_2128/checkpoint-60000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cba43977e514d291319f405d4097896713fb00aaec0f625cbe612fe828665524
|
| 3 |
+
size 995644811
|
cost_to_hit_frequency_2128/checkpoint-60000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3f6ebf74d0e1c8dbf5b9ac38f7c0bedc178b80ade6367939034c133da54acc7
|
| 3 |
+
size 14773
|