Commit
•
28bf242
1
Parent(s):
3c91b37
load
Browse files- README.md +339 -0
- added_tokens.json +5 -0
- all_results.json +15 -0
- config.json +27 -0
- eval_results.json +10 -0
- generation_config.json +6 -0
- pytorch_model-00001-of-00002.bin +3 -0
- pytorch_model-00002-of-00002.bin +3 -0
- pytorch_model.bin.index.json +298 -0
- special_tokens_map.json +10 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
- train_results.json +8 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,339 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: llama2_7b_darulm_unigram_init_tie_16_11_23
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: llama2_7b_darulm_unigram_tie_2e_16_11_23
|
| 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 |
+
# llama2_7b_darulm_unigram_tie_2e_16_11_23
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [llama2_7b_darulm_unigram_init_tie_16_11_23](https://huggingface.co/llama2_7b_darulm_unigram_init_tie_16_11_23) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.7569
|
| 20 |
+
- Accuracy: 0.4617
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 2e-05
|
| 40 |
+
- train_batch_size: 6
|
| 41 |
+
- eval_batch_size: 6
|
| 42 |
+
- seed: 42
|
| 43 |
+
- distributed_type: multi-GPU
|
| 44 |
+
- num_devices: 16
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 192
|
| 47 |
+
- total_eval_batch_size: 96
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
|
| 49 |
+
- lr_scheduler_type: linear
|
| 50 |
+
- num_epochs: 2.0
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 55 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|
|
| 56 |
+
| 4.9167 | 0.01 | 1000 | 4.8647 | 0.2686 |
|
| 57 |
+
| 3.9697 | 0.01 | 2000 | 3.9705 | 0.3409 |
|
| 58 |
+
| 3.6398 | 0.02 | 3000 | 3.6476 | 0.3694 |
|
| 59 |
+
| 3.468 | 0.03 | 4000 | 3.4784 | 0.3850 |
|
| 60 |
+
| 3.3567 | 0.04 | 5000 | 3.3733 | 0.3953 |
|
| 61 |
+
| 3.2828 | 0.04 | 6000 | 3.2999 | 0.4026 |
|
| 62 |
+
| 3.2235 | 0.05 | 7000 | 3.2453 | 0.4081 |
|
| 63 |
+
| 3.1898 | 0.06 | 8000 | 3.2028 | 0.4125 |
|
| 64 |
+
| 3.1552 | 0.07 | 9000 | 3.1683 | 0.4160 |
|
| 65 |
+
| 3.1068 | 0.07 | 10000 | 3.1397 | 0.4190 |
|
| 66 |
+
| 3.1019 | 0.08 | 11000 | 3.1152 | 0.4217 |
|
| 67 |
+
| 3.0849 | 0.09 | 12000 | 3.0942 | 0.4239 |
|
| 68 |
+
| 3.0561 | 0.09 | 13000 | 3.0761 | 0.4256 |
|
| 69 |
+
| 3.0429 | 0.1 | 14000 | 3.0595 | 0.4277 |
|
| 70 |
+
| 3.035 | 0.11 | 15000 | 3.0451 | 0.4293 |
|
| 71 |
+
| 3.0077 | 0.12 | 16000 | 3.0322 | 0.4306 |
|
| 72 |
+
| 3.0008 | 0.12 | 17000 | 3.0200 | 0.4320 |
|
| 73 |
+
| 2.9952 | 0.13 | 18000 | 3.0093 | 0.4330 |
|
| 74 |
+
| 2.9825 | 0.14 | 19000 | 2.9996 | 0.4341 |
|
| 75 |
+
| 2.9781 | 0.14 | 20000 | 2.9903 | 0.4351 |
|
| 76 |
+
| 2.957 | 0.15 | 21000 | 2.9821 | 0.4360 |
|
| 77 |
+
| 2.9676 | 0.16 | 22000 | 2.9738 | 0.4368 |
|
| 78 |
+
| 2.9513 | 0.17 | 23000 | 2.9663 | 0.4376 |
|
| 79 |
+
| 2.9475 | 0.17 | 24000 | 2.9594 | 0.4385 |
|
| 80 |
+
| 2.9406 | 0.18 | 25000 | 2.9531 | 0.4391 |
|
| 81 |
+
| 2.9387 | 0.19 | 26000 | 2.9473 | 0.4398 |
|
| 82 |
+
| 2.9353 | 0.2 | 27000 | 2.9416 | 0.4403 |
|
| 83 |
+
| 2.9208 | 0.2 | 28000 | 2.9363 | 0.4411 |
|
| 84 |
+
| 2.9142 | 0.21 | 29000 | 2.9310 | 0.4415 |
|
| 85 |
+
| 2.9167 | 0.22 | 30000 | 2.9265 | 0.4419 |
|
| 86 |
+
| 2.9069 | 0.22 | 31000 | 2.9214 | 0.4425 |
|
| 87 |
+
| 2.9067 | 0.23 | 32000 | 2.9168 | 0.4430 |
|
| 88 |
+
| 2.8978 | 0.24 | 33000 | 2.9128 | 0.4434 |
|
| 89 |
+
| 2.8982 | 0.25 | 34000 | 2.9088 | 0.4438 |
|
| 90 |
+
| 2.8856 | 0.25 | 35000 | 2.9050 | 0.4444 |
|
| 91 |
+
| 2.8981 | 0.26 | 36000 | 2.9013 | 0.4445 |
|
| 92 |
+
| 2.8813 | 0.27 | 37000 | 2.8977 | 0.4450 |
|
| 93 |
+
| 2.8765 | 0.27 | 38000 | 2.8944 | 0.4453 |
|
| 94 |
+
| 2.879 | 0.28 | 39000 | 2.8910 | 0.4458 |
|
| 95 |
+
| 2.8738 | 0.29 | 40000 | 2.8878 | 0.4462 |
|
| 96 |
+
| 2.8671 | 0.3 | 41000 | 2.8851 | 0.4465 |
|
| 97 |
+
| 2.866 | 0.3 | 42000 | 2.8820 | 0.4468 |
|
| 98 |
+
| 2.8561 | 0.31 | 43000 | 2.8791 | 0.4473 |
|
| 99 |
+
| 2.8601 | 0.32 | 44000 | 2.8765 | 0.4477 |
|
| 100 |
+
| 2.8518 | 0.33 | 45000 | 2.8741 | 0.4479 |
|
| 101 |
+
| 2.8577 | 0.33 | 46000 | 2.8713 | 0.4483 |
|
| 102 |
+
| 2.8588 | 0.34 | 47000 | 2.8691 | 0.4484 |
|
| 103 |
+
| 2.8584 | 0.35 | 48000 | 2.8666 | 0.4487 |
|
| 104 |
+
| 2.8527 | 0.35 | 49000 | 2.8646 | 0.4488 |
|
| 105 |
+
| 2.8425 | 0.36 | 50000 | 2.8624 | 0.4490 |
|
| 106 |
+
| 2.8457 | 0.37 | 51000 | 2.8601 | 0.4494 |
|
| 107 |
+
| 2.849 | 0.38 | 52000 | 2.8580 | 0.4496 |
|
| 108 |
+
| 2.8431 | 0.38 | 53000 | 2.8560 | 0.4499 |
|
| 109 |
+
| 2.8463 | 0.39 | 54000 | 2.8540 | 0.4501 |
|
| 110 |
+
| 2.8437 | 0.4 | 55000 | 2.8521 | 0.4504 |
|
| 111 |
+
| 2.845 | 0.41 | 56000 | 2.8505 | 0.4505 |
|
| 112 |
+
| 2.8218 | 0.41 | 57000 | 2.8486 | 0.4508 |
|
| 113 |
+
| 2.8366 | 0.42 | 58000 | 2.8470 | 0.4509 |
|
| 114 |
+
| 2.8339 | 0.43 | 59000 | 2.8453 | 0.4512 |
|
| 115 |
+
| 2.8338 | 0.43 | 60000 | 2.8437 | 0.4511 |
|
| 116 |
+
| 2.8237 | 0.44 | 61000 | 2.8420 | 0.4513 |
|
| 117 |
+
| 2.8334 | 0.45 | 62000 | 2.8405 | 0.4515 |
|
| 118 |
+
| 2.8229 | 0.46 | 63000 | 2.8388 | 0.4518 |
|
| 119 |
+
| 2.8214 | 0.46 | 64000 | 2.8373 | 0.4519 |
|
| 120 |
+
| 2.8245 | 0.47 | 65000 | 2.8356 | 0.4522 |
|
| 121 |
+
| 2.822 | 0.48 | 66000 | 2.8343 | 0.4524 |
|
| 122 |
+
| 2.8139 | 0.48 | 67000 | 2.8331 | 0.4526 |
|
| 123 |
+
| 2.8201 | 0.49 | 68000 | 2.8317 | 0.4526 |
|
| 124 |
+
| 2.8132 | 0.5 | 69000 | 2.8305 | 0.4527 |
|
| 125 |
+
| 2.8138 | 0.51 | 70000 | 2.8290 | 0.4530 |
|
| 126 |
+
| 2.8171 | 0.51 | 71000 | 2.8279 | 0.4530 |
|
| 127 |
+
| 2.8123 | 0.52 | 72000 | 2.8267 | 0.4532 |
|
| 128 |
+
| 2.8118 | 0.53 | 73000 | 2.8255 | 0.4534 |
|
| 129 |
+
| 2.8183 | 0.54 | 74000 | 2.8243 | 0.4536 |
|
| 130 |
+
| 2.8052 | 0.54 | 75000 | 2.8233 | 0.4536 |
|
| 131 |
+
| 2.8101 | 0.55 | 76000 | 2.8220 | 0.4538 |
|
| 132 |
+
| 2.8021 | 0.56 | 77000 | 2.8209 | 0.4540 |
|
| 133 |
+
| 2.8076 | 0.56 | 78000 | 2.8196 | 0.4540 |
|
| 134 |
+
| 2.7937 | 0.57 | 79000 | 2.8190 | 0.4542 |
|
| 135 |
+
| 2.8057 | 0.58 | 80000 | 2.8179 | 0.4541 |
|
| 136 |
+
| 2.8082 | 0.59 | 81000 | 2.8168 | 0.4545 |
|
| 137 |
+
| 2.7986 | 0.59 | 82000 | 2.8157 | 0.4546 |
|
| 138 |
+
| 2.8062 | 0.6 | 83000 | 2.8150 | 0.4545 |
|
| 139 |
+
| 2.7981 | 0.61 | 84000 | 2.8138 | 0.4546 |
|
| 140 |
+
| 2.8041 | 0.61 | 85000 | 2.8130 | 0.4546 |
|
| 141 |
+
| 2.7978 | 0.62 | 86000 | 2.8118 | 0.4549 |
|
| 142 |
+
| 2.8016 | 0.63 | 87000 | 2.8109 | 0.4549 |
|
| 143 |
+
| 2.7901 | 0.64 | 88000 | 2.8099 | 0.4551 |
|
| 144 |
+
| 2.8075 | 0.64 | 89000 | 2.8093 | 0.4553 |
|
| 145 |
+
| 2.7915 | 0.65 | 90000 | 2.8084 | 0.4552 |
|
| 146 |
+
| 2.7916 | 0.66 | 91000 | 2.8074 | 0.4555 |
|
| 147 |
+
| 2.7751 | 0.67 | 92000 | 2.8068 | 0.4554 |
|
| 148 |
+
| 2.7896 | 0.67 | 93000 | 2.8059 | 0.4556 |
|
| 149 |
+
| 2.7886 | 0.68 | 94000 | 2.8051 | 0.4557 |
|
| 150 |
+
| 2.7909 | 0.69 | 95000 | 2.8044 | 0.4557 |
|
| 151 |
+
| 2.7926 | 0.69 | 96000 | 2.8035 | 0.4558 |
|
| 152 |
+
| 2.7931 | 0.7 | 97000 | 2.8028 | 0.4560 |
|
| 153 |
+
| 2.7838 | 0.71 | 98000 | 2.8020 | 0.4562 |
|
| 154 |
+
| 2.779 | 0.72 | 99000 | 2.8014 | 0.4561 |
|
| 155 |
+
| 2.7922 | 0.72 | 100000 | 2.8006 | 0.4562 |
|
| 156 |
+
| 2.7786 | 0.73 | 101000 | 2.7999 | 0.4562 |
|
| 157 |
+
| 2.7791 | 0.74 | 102000 | 2.7992 | 0.4563 |
|
| 158 |
+
| 2.7908 | 0.74 | 103000 | 2.7984 | 0.4565 |
|
| 159 |
+
| 2.7872 | 0.75 | 104000 | 2.7978 | 0.4566 |
|
| 160 |
+
| 2.7763 | 0.76 | 105000 | 2.7972 | 0.4567 |
|
| 161 |
+
| 2.7785 | 0.77 | 106000 | 2.7966 | 0.4568 |
|
| 162 |
+
| 2.7861 | 0.77 | 107000 | 2.7960 | 0.4568 |
|
| 163 |
+
| 2.784 | 0.78 | 108000 | 2.7953 | 0.4570 |
|
| 164 |
+
| 2.7804 | 0.79 | 109000 | 2.7944 | 0.4571 |
|
| 165 |
+
| 2.7828 | 0.8 | 110000 | 2.7940 | 0.4570 |
|
| 166 |
+
| 2.7761 | 0.8 | 111000 | 2.7933 | 0.4571 |
|
| 167 |
+
| 2.7797 | 0.81 | 112000 | 2.7928 | 0.4571 |
|
| 168 |
+
| 2.7792 | 0.82 | 113000 | 2.7922 | 0.4573 |
|
| 169 |
+
| 2.7819 | 0.82 | 114000 | 2.7915 | 0.4573 |
|
| 170 |
+
| 2.7837 | 0.83 | 115000 | 2.7910 | 0.4573 |
|
| 171 |
+
| 2.781 | 0.84 | 116000 | 2.7906 | 0.4575 |
|
| 172 |
+
| 2.7765 | 0.85 | 117000 | 2.7898 | 0.4577 |
|
| 173 |
+
| 2.7778 | 0.85 | 118000 | 2.7895 | 0.4575 |
|
| 174 |
+
| 2.776 | 0.86 | 119000 | 2.7887 | 0.4577 |
|
| 175 |
+
| 2.7719 | 0.87 | 120000 | 2.7883 | 0.4578 |
|
| 176 |
+
| 2.7759 | 0.88 | 121000 | 2.7878 | 0.4579 |
|
| 177 |
+
| 2.7654 | 0.88 | 122000 | 2.7874 | 0.4578 |
|
| 178 |
+
| 2.7661 | 0.89 | 123000 | 2.7868 | 0.4580 |
|
| 179 |
+
| 2.7718 | 0.9 | 124000 | 2.7861 | 0.4580 |
|
| 180 |
+
| 2.7775 | 0.9 | 125000 | 2.7858 | 0.4580 |
|
| 181 |
+
| 2.7835 | 0.91 | 126000 | 2.7855 | 0.4580 |
|
| 182 |
+
| 2.768 | 0.92 | 127000 | 2.7848 | 0.4581 |
|
| 183 |
+
| 2.7701 | 0.93 | 128000 | 2.7843 | 0.4582 |
|
| 184 |
+
| 2.7682 | 0.93 | 129000 | 2.7838 | 0.4583 |
|
| 185 |
+
| 2.7595 | 0.94 | 130000 | 2.7834 | 0.4583 |
|
| 186 |
+
| 2.7627 | 0.95 | 131000 | 2.7831 | 0.4583 |
|
| 187 |
+
| 2.7716 | 0.95 | 132000 | 2.7827 | 0.4584 |
|
| 188 |
+
| 2.7719 | 0.96 | 133000 | 2.7821 | 0.4585 |
|
| 189 |
+
| 2.7723 | 0.97 | 134000 | 2.7816 | 0.4583 |
|
| 190 |
+
| 2.7736 | 0.98 | 135000 | 2.7812 | 0.4585 |
|
| 191 |
+
| 2.7646 | 0.98 | 136000 | 2.7809 | 0.4586 |
|
| 192 |
+
| 2.76 | 0.99 | 137000 | 2.7805 | 0.4586 |
|
| 193 |
+
| 2.7659 | 1.0 | 138000 | 2.7803 | 0.4586 |
|
| 194 |
+
| 2.7604 | 1.01 | 139000 | 2.7799 | 0.4587 |
|
| 195 |
+
| 2.7597 | 1.01 | 140000 | 2.7794 | 0.4587 |
|
| 196 |
+
| 2.7551 | 1.02 | 141000 | 2.7791 | 0.4588 |
|
| 197 |
+
| 2.7619 | 1.03 | 142000 | 2.7788 | 0.4588 |
|
| 198 |
+
| 2.7658 | 1.03 | 143000 | 2.7785 | 0.4589 |
|
| 199 |
+
| 2.751 | 1.04 | 144000 | 2.7781 | 0.4589 |
|
| 200 |
+
| 2.7589 | 1.05 | 145000 | 2.7778 | 0.4590 |
|
| 201 |
+
| 2.7459 | 1.06 | 146000 | 2.7776 | 0.4590 |
|
| 202 |
+
| 2.7646 | 1.06 | 147000 | 2.7771 | 0.4591 |
|
| 203 |
+
| 2.7529 | 1.07 | 148000 | 2.7768 | 0.4589 |
|
| 204 |
+
| 2.7573 | 1.08 | 149000 | 2.7764 | 0.4592 |
|
| 205 |
+
| 2.754 | 1.08 | 150000 | 2.7762 | 0.4591 |
|
| 206 |
+
| 2.7553 | 1.09 | 151000 | 2.7759 | 0.4591 |
|
| 207 |
+
| 2.7485 | 1.1 | 152000 | 2.7755 | 0.4593 |
|
| 208 |
+
| 2.7558 | 1.11 | 153000 | 2.7752 | 0.4593 |
|
| 209 |
+
| 2.7563 | 1.11 | 154000 | 2.7748 | 0.4593 |
|
| 210 |
+
| 2.7557 | 1.12 | 155000 | 2.7747 | 0.4594 |
|
| 211 |
+
| 2.7593 | 1.13 | 156000 | 2.7744 | 0.4592 |
|
| 212 |
+
| 2.752 | 1.14 | 157000 | 2.7741 | 0.4593 |
|
| 213 |
+
| 2.748 | 1.14 | 158000 | 2.7737 | 0.4593 |
|
| 214 |
+
| 2.7549 | 1.15 | 159000 | 2.7735 | 0.4594 |
|
| 215 |
+
| 2.7455 | 1.16 | 160000 | 2.7733 | 0.4596 |
|
| 216 |
+
| 2.7582 | 1.16 | 161000 | 2.7731 | 0.4594 |
|
| 217 |
+
| 2.7532 | 1.17 | 162000 | 2.7728 | 0.4595 |
|
| 218 |
+
| 2.7496 | 1.18 | 163000 | 2.7724 | 0.4595 |
|
| 219 |
+
| 2.75 | 1.19 | 164000 | 2.7721 | 0.4596 |
|
| 220 |
+
| 2.7517 | 1.19 | 165000 | 2.7718 | 0.4597 |
|
| 221 |
+
| 2.7522 | 1.2 | 166000 | 2.7716 | 0.4597 |
|
| 222 |
+
| 2.7514 | 1.21 | 167000 | 2.7713 | 0.4599 |
|
| 223 |
+
| 2.7515 | 1.22 | 168000 | 2.7711 | 0.4598 |
|
| 224 |
+
| 2.7493 | 1.22 | 169000 | 2.7708 | 0.4598 |
|
| 225 |
+
| 2.7491 | 1.23 | 170000 | 2.7705 | 0.4598 |
|
| 226 |
+
| 2.7552 | 1.24 | 171000 | 2.7704 | 0.4599 |
|
| 227 |
+
| 2.7536 | 1.24 | 172000 | 2.7700 | 0.4600 |
|
| 228 |
+
| 2.7485 | 1.25 | 173000 | 2.7697 | 0.4599 |
|
| 229 |
+
| 2.7455 | 1.26 | 174000 | 2.7697 | 0.4599 |
|
| 230 |
+
| 2.7516 | 1.27 | 175000 | 2.7694 | 0.4599 |
|
| 231 |
+
| 2.754 | 1.27 | 176000 | 2.7690 | 0.4600 |
|
| 232 |
+
| 2.7489 | 1.28 | 177000 | 2.7690 | 0.4598 |
|
| 233 |
+
| 2.7491 | 1.29 | 178000 | 2.7686 | 0.4601 |
|
| 234 |
+
| 2.7432 | 1.29 | 179000 | 2.7684 | 0.4600 |
|
| 235 |
+
| 2.7388 | 1.3 | 180000 | 2.7681 | 0.4602 |
|
| 236 |
+
| 2.7501 | 1.31 | 181000 | 2.7679 | 0.4602 |
|
| 237 |
+
| 2.7526 | 1.32 | 182000 | 2.7675 | 0.4603 |
|
| 238 |
+
| 2.7478 | 1.32 | 183000 | 2.7674 | 0.4603 |
|
| 239 |
+
| 2.7491 | 1.33 | 184000 | 2.7670 | 0.4604 |
|
| 240 |
+
| 2.7505 | 1.34 | 185000 | 2.7670 | 0.4604 |
|
| 241 |
+
| 2.7436 | 1.35 | 186000 | 2.7666 | 0.4605 |
|
| 242 |
+
| 2.7389 | 1.35 | 187000 | 2.7665 | 0.4603 |
|
| 243 |
+
| 2.7564 | 1.36 | 188000 | 2.7662 | 0.4604 |
|
| 244 |
+
| 2.7464 | 1.37 | 189000 | 2.7661 | 0.4604 |
|
| 245 |
+
| 2.7459 | 1.37 | 190000 | 2.7659 | 0.4605 |
|
| 246 |
+
| 2.7481 | 1.38 | 191000 | 2.7657 | 0.4605 |
|
| 247 |
+
| 2.7458 | 1.39 | 192000 | 2.7655 | 0.4604 |
|
| 248 |
+
| 2.7427 | 1.4 | 193000 | 2.7653 | 0.4605 |
|
| 249 |
+
| 2.741 | 1.4 | 194000 | 2.7651 | 0.4606 |
|
| 250 |
+
| 2.7488 | 1.41 | 195000 | 2.7649 | 0.4606 |
|
| 251 |
+
| 2.7353 | 1.42 | 196000 | 2.7647 | 0.4605 |
|
| 252 |
+
| 2.7503 | 1.42 | 197000 | 2.7645 | 0.4607 |
|
| 253 |
+
| 2.7446 | 1.43 | 198000 | 2.7644 | 0.4607 |
|
| 254 |
+
| 2.748 | 1.44 | 199000 | 2.7642 | 0.4607 |
|
| 255 |
+
| 2.7394 | 1.45 | 200000 | 2.7641 | 0.4607 |
|
| 256 |
+
| 2.7403 | 1.45 | 201000 | 2.7638 | 0.4607 |
|
| 257 |
+
| 2.7467 | 1.46 | 202000 | 2.7637 | 0.4607 |
|
| 258 |
+
| 2.7532 | 1.47 | 203000 | 2.7635 | 0.4608 |
|
| 259 |
+
| 2.7431 | 1.48 | 204000 | 2.7634 | 0.4609 |
|
| 260 |
+
| 2.7433 | 1.48 | 205000 | 2.7632 | 0.4608 |
|
| 261 |
+
| 2.7436 | 1.49 | 206000 | 2.7630 | 0.4609 |
|
| 262 |
+
| 2.747 | 1.5 | 207000 | 2.7628 | 0.4609 |
|
| 263 |
+
| 2.7395 | 1.5 | 208000 | 2.7626 | 0.4609 |
|
| 264 |
+
| 2.7443 | 1.51 | 209000 | 2.7624 | 0.4609 |
|
| 265 |
+
| 2.7395 | 1.52 | 210000 | 2.7623 | 0.4608 |
|
| 266 |
+
| 2.7353 | 1.53 | 211000 | 2.7621 | 0.4608 |
|
| 267 |
+
| 2.7401 | 1.53 | 212000 | 2.7618 | 0.4610 |
|
| 268 |
+
| 2.7371 | 1.54 | 213000 | 2.7617 | 0.4610 |
|
| 269 |
+
| 2.7458 | 1.55 | 214000 | 2.7616 | 0.4610 |
|
| 270 |
+
| 2.7416 | 1.56 | 215000 | 2.7615 | 0.4611 |
|
| 271 |
+
| 2.7434 | 1.56 | 216000 | 2.7614 | 0.4611 |
|
| 272 |
+
| 2.7456 | 1.57 | 217000 | 2.7614 | 0.4611 |
|
| 273 |
+
| 2.7499 | 1.58 | 218000 | 2.7611 | 0.4611 |
|
| 274 |
+
| 2.744 | 1.58 | 219000 | 2.7609 | 0.4611 |
|
| 275 |
+
| 2.7375 | 1.59 | 220000 | 2.7608 | 0.4611 |
|
| 276 |
+
| 2.7428 | 1.6 | 221000 | 2.7606 | 0.4611 |
|
| 277 |
+
| 2.7442 | 1.61 | 222000 | 2.7606 | 0.4611 |
|
| 278 |
+
| 2.7395 | 1.61 | 223000 | 2.7604 | 0.4612 |
|
| 279 |
+
| 2.7445 | 1.62 | 224000 | 2.7602 | 0.4612 |
|
| 280 |
+
| 2.7394 | 1.63 | 225000 | 2.7602 | 0.4611 |
|
| 281 |
+
| 2.7403 | 1.63 | 226000 | 2.7599 | 0.4612 |
|
| 282 |
+
| 2.738 | 1.64 | 227000 | 2.7599 | 0.4612 |
|
| 283 |
+
| 2.7332 | 1.65 | 228000 | 2.7597 | 0.4613 |
|
| 284 |
+
| 2.7388 | 1.66 | 229000 | 2.7596 | 0.4613 |
|
| 285 |
+
| 2.743 | 1.66 | 230000 | 2.7595 | 0.4613 |
|
| 286 |
+
| 2.7368 | 1.67 | 231000 | 2.7593 | 0.4613 |
|
| 287 |
+
| 2.7426 | 1.68 | 232000 | 2.7592 | 0.4614 |
|
| 288 |
+
| 2.7332 | 1.69 | 233000 | 2.7591 | 0.4614 |
|
| 289 |
+
| 2.7413 | 1.69 | 234000 | 2.7590 | 0.4614 |
|
| 290 |
+
| 2.735 | 1.7 | 235000 | 2.7589 | 0.4613 |
|
| 291 |
+
| 2.7393 | 1.71 | 236000 | 2.7589 | 0.4614 |
|
| 292 |
+
| 2.7382 | 1.71 | 237000 | 2.7587 | 0.4615 |
|
| 293 |
+
| 2.7403 | 1.72 | 238000 | 2.7587 | 0.4615 |
|
| 294 |
+
| 2.7436 | 1.73 | 239000 | 2.7586 | 0.4615 |
|
| 295 |
+
| 2.7422 | 1.74 | 240000 | 2.7585 | 0.4615 |
|
| 296 |
+
| 2.7257 | 1.74 | 241000 | 2.7584 | 0.4614 |
|
| 297 |
+
| 2.7351 | 1.75 | 242000 | 2.7583 | 0.4615 |
|
| 298 |
+
| 2.7391 | 1.76 | 243000 | 2.7582 | 0.4615 |
|
| 299 |
+
| 2.7495 | 1.76 | 244000 | 2.7581 | 0.4615 |
|
| 300 |
+
| 2.7399 | 1.77 | 245000 | 2.7580 | 0.4614 |
|
| 301 |
+
| 2.7435 | 1.78 | 246000 | 2.7580 | 0.4616 |
|
| 302 |
+
| 2.7414 | 1.79 | 247000 | 2.7579 | 0.4615 |
|
| 303 |
+
| 2.7478 | 1.79 | 248000 | 2.7578 | 0.4616 |
|
| 304 |
+
| 2.7299 | 1.8 | 249000 | 2.7577 | 0.4616 |
|
| 305 |
+
| 2.7401 | 1.81 | 250000 | 2.7576 | 0.4616 |
|
| 306 |
+
| 2.7395 | 1.82 | 251000 | 2.7575 | 0.4616 |
|
| 307 |
+
| 2.7399 | 1.82 | 252000 | 2.7574 | 0.4616 |
|
| 308 |
+
| 2.7413 | 1.83 | 253000 | 2.7574 | 0.4616 |
|
| 309 |
+
| 2.7294 | 1.84 | 254000 | 2.7573 | 0.4616 |
|
| 310 |
+
| 2.7329 | 1.84 | 255000 | 2.7572 | 0.4616 |
|
| 311 |
+
| 2.7454 | 1.85 | 256000 | 2.7572 | 0.4617 |
|
| 312 |
+
| 2.7343 | 1.86 | 257000 | 2.7571 | 0.4617 |
|
| 313 |
+
| 2.7356 | 1.87 | 258000 | 2.7571 | 0.4617 |
|
| 314 |
+
| 2.7462 | 1.87 | 259000 | 2.7570 | 0.4617 |
|
| 315 |
+
| 2.7375 | 1.88 | 260000 | 2.7569 | 0.4617 |
|
| 316 |
+
| 2.7368 | 1.89 | 261000 | 2.7569 | 0.4618 |
|
| 317 |
+
| 2.7452 | 1.89 | 262000 | 2.7569 | 0.4617 |
|
| 318 |
+
| 2.7394 | 1.9 | 263000 | 2.7568 | 0.4617 |
|
| 319 |
+
| 2.7378 | 1.91 | 264000 | 2.7568 | 0.4618 |
|
| 320 |
+
| 2.7446 | 1.92 | 265000 | 2.7567 | 0.4618 |
|
| 321 |
+
| 2.7436 | 1.92 | 266000 | 2.7567 | 0.4618 |
|
| 322 |
+
| 2.7505 | 1.93 | 267000 | 2.7567 | 0.4618 |
|
| 323 |
+
| 2.7493 | 1.94 | 268000 | 2.7566 | 0.4618 |
|
| 324 |
+
| 2.7391 | 1.95 | 269000 | 2.7566 | 0.4618 |
|
| 325 |
+
| 2.7431 | 1.95 | 270000 | 2.7566 | 0.4617 |
|
| 326 |
+
| 2.7387 | 1.96 | 271000 | 2.7565 | 0.4618 |
|
| 327 |
+
| 2.741 | 1.97 | 272000 | 2.7565 | 0.4618 |
|
| 328 |
+
| 2.7343 | 1.97 | 273000 | 2.7565 | 0.4618 |
|
| 329 |
+
| 2.7378 | 1.98 | 274000 | 2.7564 | 0.4618 |
|
| 330 |
+
| 2.737 | 1.99 | 275000 | 2.7564 | 0.4618 |
|
| 331 |
+
| 2.7397 | 2.0 | 276000 | 2.7564 | 0.4618 |
|
| 332 |
+
|
| 333 |
+
|
| 334 |
+
### Framework versions
|
| 335 |
+
|
| 336 |
+
- Transformers 4.34.0
|
| 337 |
+
- Pytorch 2.0.1+cu118
|
| 338 |
+
- Datasets 2.14.5
|
| 339 |
+
- Tokenizers 0.14.1
|
added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 2,
|
| 3 |
+
"<s>": 1,
|
| 4 |
+
"<unk>": 0
|
| 5 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.4617488272495486,
|
| 4 |
+
"eval_loss": 2.7569446563720703,
|
| 5 |
+
"eval_runtime": 28.951,
|
| 6 |
+
"eval_samples": 6483,
|
| 7 |
+
"eval_samples_per_second": 223.93,
|
| 8 |
+
"eval_steps_per_second": 2.349,
|
| 9 |
+
"perplexity": 15.751642670488213,
|
| 10 |
+
"train_loss": 2.8250040690803138,
|
| 11 |
+
"train_runtime": 396233.9412,
|
| 12 |
+
"train_samples": 26545790,
|
| 13 |
+
"train_samples_per_second": 133.99,
|
| 14 |
+
"train_steps_per_second": 0.698
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "llama2_7b_darulm_unigram_init_tie_16_11_23",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 4096,
|
| 14 |
+
"model_type": "llama",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_hidden_layers": 32,
|
| 17 |
+
"num_key_value_heads": 32,
|
| 18 |
+
"pretraining_tp": 1,
|
| 19 |
+
"rms_norm_eps": 1e-05,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 10000.0,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float16",
|
| 24 |
+
"transformers_version": "4.34.0",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 32000
|
| 27 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"eval_accuracy": 0.4617488272495486,
|
| 4 |
+
"eval_loss": 2.7569446563720703,
|
| 5 |
+
"eval_runtime": 28.951,
|
| 6 |
+
"eval_samples": 6483,
|
| 7 |
+
"eval_samples_per_second": 223.93,
|
| 8 |
+
"eval_steps_per_second": 2.349,
|
| 9 |
+
"perplexity": 15.751642670488213
|
| 10 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.34.0"
|
| 6 |
+
}
|
pytorch_model-00001-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14f788a31291164991fb02871e714813fe2aca163f30e9c26489138d282f8730
|
| 3 |
+
size 9976620122
|
pytorch_model-00002-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79f1991f97779a57b385ebe3e6e0726d75ab9ad7d6c6b4cbef1c52fce1e7a416
|
| 3 |
+
size 3500310787
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 13476831232
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
| 296 |
+
"model.norm.weight": "pytorch_model-00002-of-00002.bin"
|
| 297 |
+
}
|
| 298 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": "<s>",
|
| 8 |
+
"eos_token": "</s>",
|
| 9 |
+
"unk_token": "<unk>"
|
| 10 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88fc252bfd0e6a5355d5ae708410bf365241c858dc556dc4744cbe5b011ba3fc
|
| 3 |
+
size 989601
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [
|
| 29 |
+
"<unk>",
|
| 30 |
+
"<s>",
|
| 31 |
+
"</s>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": "<s>",
|
| 34 |
+
"clean_up_tokenization_spaces": false,
|
| 35 |
+
"eos_token": "</s>",
|
| 36 |
+
"legacy": true,
|
| 37 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
+
"pad_token": null,
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": true
|
| 44 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"train_loss": 2.8250040690803138,
|
| 4 |
+
"train_runtime": 396233.9412,
|
| 5 |
+
"train_samples": 26545790,
|
| 6 |
+
"train_samples_per_second": 133.99,
|
| 7 |
+
"train_steps_per_second": 0.698
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:052804cced4c5e9bfd207af9c55b076d617163f4c97734a8c512536ecf5a281b
|
| 3 |
+
size 5563
|