Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +3 -0
- README.md +58 -0
- adapter_config.json +461 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +3 -0
- all_results.json +9 -0
- chat_template.json +3 -0
- checkpoint-100/README.md +202 -0
- checkpoint-100/adapter_config.json +461 -0
- checkpoint-100/adapter_model.safetensors +3 -0
- checkpoint-100/added_tokens.json +3 -0
- checkpoint-100/chat_template.json +3 -0
- checkpoint-100/optimizer.pt +3 -0
- checkpoint-100/preprocessor_config.json +29 -0
- checkpoint-100/processor_config.json +4 -0
- checkpoint-100/rng_state.pth +3 -0
- checkpoint-100/scheduler.pt +3 -0
- checkpoint-100/special_tokens_map.json +42 -0
- checkpoint-100/tokenizer.json +3 -0
- checkpoint-100/tokenizer.model +3 -0
- checkpoint-100/tokenizer_config.json +0 -0
- checkpoint-100/trainer_state.json +194 -0
- checkpoint-100/training_args.bin +3 -0
- checkpoint-120/README.md +202 -0
- checkpoint-120/adapter_config.json +461 -0
- checkpoint-120/adapter_model.safetensors +3 -0
- checkpoint-120/added_tokens.json +3 -0
- checkpoint-120/chat_template.json +3 -0
- checkpoint-120/optimizer.pt +3 -0
- checkpoint-120/preprocessor_config.json +29 -0
- checkpoint-120/processor_config.json +4 -0
- checkpoint-120/rng_state.pth +3 -0
- checkpoint-120/scheduler.pt +3 -0
- checkpoint-120/special_tokens_map.json +42 -0
- checkpoint-120/tokenizer.json +3 -0
- checkpoint-120/tokenizer.model +3 -0
- checkpoint-120/tokenizer_config.json +0 -0
- checkpoint-120/trainer_state.json +226 -0
- checkpoint-120/training_args.bin +3 -0
- llamaboard_config.yaml +78 -0
- preprocessor_config.json +29 -0
- processor_config.json +4 -0
- running_log.txt +0 -0
- special_tokens_map.json +42 -0
- tokenizer.json +3 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
- train_results.json +9 -0
- trainer_log.jsonl +25 -0
- trainer_state.json +236 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: other
|
| 4 |
+
base_model: google/gemma-3-27b-it
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: gemma5
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# gemma5
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [google/gemma-3-27b-it](https://huggingface.co/google/gemma-3-27b-it) on the ets120 dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 8
|
| 43 |
+
- total_train_batch_size: 8
|
| 44 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- num_epochs: 8.0
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
### Framework versions
|
| 53 |
+
|
| 54 |
+
- PEFT 0.12.0
|
| 55 |
+
- Transformers 4.50.0
|
| 56 |
+
- Pytorch 2.6.0+cu124
|
| 57 |
+
- Datasets 3.3.2
|
| 58 |
+
- Tokenizers 0.21.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,461 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "google/gemma-3-27b-it",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 128,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"language_model.model.layers.18.mlp.up_proj",
|
| 24 |
+
"language_model.model.layers.14.self_attn.q_proj",
|
| 25 |
+
"language_model.model.layers.23.mlp.down_proj",
|
| 26 |
+
"language_model.model.layers.5.self_attn.q_proj",
|
| 27 |
+
"language_model.model.layers.48.self_attn.k_proj",
|
| 28 |
+
"language_model.model.layers.29.self_attn.v_proj",
|
| 29 |
+
"language_model.model.layers.39.self_attn.v_proj",
|
| 30 |
+
"language_model.model.layers.5.self_attn.v_proj",
|
| 31 |
+
"language_model.model.layers.60.mlp.gate_proj",
|
| 32 |
+
"language_model.model.layers.17.self_attn.o_proj",
|
| 33 |
+
"language_model.model.layers.60.mlp.down_proj",
|
| 34 |
+
"language_model.model.layers.33.mlp.up_proj",
|
| 35 |
+
"language_model.model.layers.53.self_attn.q_proj",
|
| 36 |
+
"language_model.model.layers.27.mlp.down_proj",
|
| 37 |
+
"language_model.model.layers.57.self_attn.v_proj",
|
| 38 |
+
"language_model.model.layers.26.mlp.up_proj",
|
| 39 |
+
"language_model.model.layers.10.mlp.gate_proj",
|
| 40 |
+
"language_model.model.layers.23.mlp.up_proj",
|
| 41 |
+
"language_model.model.layers.57.self_attn.q_proj",
|
| 42 |
+
"language_model.model.layers.57.mlp.up_proj",
|
| 43 |
+
"language_model.model.layers.39.mlp.gate_proj",
|
| 44 |
+
"language_model.model.layers.26.mlp.down_proj",
|
| 45 |
+
"language_model.model.layers.11.mlp.up_proj",
|
| 46 |
+
"language_model.model.layers.25.mlp.up_proj",
|
| 47 |
+
"language_model.model.layers.6.mlp.gate_proj",
|
| 48 |
+
"language_model.model.layers.36.mlp.gate_proj",
|
| 49 |
+
"language_model.model.layers.2.self_attn.o_proj",
|
| 50 |
+
"language_model.model.layers.30.self_attn.o_proj",
|
| 51 |
+
"language_model.model.layers.4.mlp.gate_proj",
|
| 52 |
+
"language_model.model.layers.13.mlp.up_proj",
|
| 53 |
+
"language_model.model.layers.52.mlp.down_proj",
|
| 54 |
+
"language_model.model.layers.4.mlp.up_proj",
|
| 55 |
+
"language_model.model.layers.32.self_attn.v_proj",
|
| 56 |
+
"language_model.model.layers.1.self_attn.o_proj",
|
| 57 |
+
"language_model.model.layers.22.mlp.down_proj",
|
| 58 |
+
"language_model.model.layers.45.mlp.down_proj",
|
| 59 |
+
"language_model.model.layers.46.self_attn.o_proj",
|
| 60 |
+
"language_model.model.layers.38.self_attn.o_proj",
|
| 61 |
+
"language_model.model.layers.23.self_attn.q_proj",
|
| 62 |
+
"language_model.model.layers.46.mlp.up_proj",
|
| 63 |
+
"language_model.model.layers.49.mlp.down_proj",
|
| 64 |
+
"language_model.model.layers.40.self_attn.k_proj",
|
| 65 |
+
"language_model.model.layers.24.self_attn.q_proj",
|
| 66 |
+
"language_model.model.layers.9.self_attn.o_proj",
|
| 67 |
+
"language_model.model.layers.37.mlp.gate_proj",
|
| 68 |
+
"language_model.model.layers.36.self_attn.k_proj",
|
| 69 |
+
"language_model.model.layers.49.self_attn.k_proj",
|
| 70 |
+
"language_model.model.layers.24.self_attn.v_proj",
|
| 71 |
+
"language_model.model.layers.1.mlp.down_proj",
|
| 72 |
+
"language_model.model.layers.10.mlp.down_proj",
|
| 73 |
+
"language_model.model.layers.61.mlp.gate_proj",
|
| 74 |
+
"language_model.model.layers.34.self_attn.o_proj",
|
| 75 |
+
"language_model.model.layers.9.mlp.up_proj",
|
| 76 |
+
"language_model.model.layers.59.self_attn.v_proj",
|
| 77 |
+
"language_model.model.layers.30.self_attn.q_proj",
|
| 78 |
+
"language_model.model.layers.44.mlp.gate_proj",
|
| 79 |
+
"language_model.model.layers.46.mlp.down_proj",
|
| 80 |
+
"language_model.model.layers.46.self_attn.k_proj",
|
| 81 |
+
"language_model.model.layers.28.self_attn.v_proj",
|
| 82 |
+
"language_model.model.layers.58.self_attn.o_proj",
|
| 83 |
+
"language_model.model.layers.13.self_attn.o_proj",
|
| 84 |
+
"language_model.model.layers.24.mlp.up_proj",
|
| 85 |
+
"language_model.model.layers.0.self_attn.q_proj",
|
| 86 |
+
"language_model.model.layers.58.mlp.up_proj",
|
| 87 |
+
"language_model.model.layers.12.mlp.down_proj",
|
| 88 |
+
"language_model.model.layers.43.mlp.up_proj",
|
| 89 |
+
"language_model.model.layers.44.self_attn.k_proj",
|
| 90 |
+
"language_model.model.layers.17.self_attn.q_proj",
|
| 91 |
+
"language_model.model.layers.59.mlp.up_proj",
|
| 92 |
+
"language_model.model.layers.50.mlp.down_proj",
|
| 93 |
+
"language_model.model.layers.24.self_attn.k_proj",
|
| 94 |
+
"language_model.model.layers.59.self_attn.k_proj",
|
| 95 |
+
"language_model.model.layers.1.mlp.up_proj",
|
| 96 |
+
"language_model.model.layers.58.self_attn.q_proj",
|
| 97 |
+
"language_model.model.layers.51.mlp.gate_proj",
|
| 98 |
+
"language_model.model.layers.4.self_attn.v_proj",
|
| 99 |
+
"language_model.model.layers.45.mlp.gate_proj",
|
| 100 |
+
"language_model.model.layers.8.mlp.gate_proj",
|
| 101 |
+
"language_model.model.layers.43.self_attn.v_proj",
|
| 102 |
+
"language_model.model.layers.51.self_attn.v_proj",
|
| 103 |
+
"language_model.model.layers.37.self_attn.v_proj",
|
| 104 |
+
"language_model.model.layers.51.self_attn.q_proj",
|
| 105 |
+
"language_model.model.layers.51.self_attn.o_proj",
|
| 106 |
+
"language_model.model.layers.33.mlp.down_proj",
|
| 107 |
+
"language_model.model.layers.44.self_attn.v_proj",
|
| 108 |
+
"language_model.model.layers.18.self_attn.o_proj",
|
| 109 |
+
"language_model.model.layers.14.self_attn.k_proj",
|
| 110 |
+
"language_model.model.layers.55.self_attn.k_proj",
|
| 111 |
+
"language_model.model.layers.10.self_attn.q_proj",
|
| 112 |
+
"language_model.model.layers.34.mlp.up_proj",
|
| 113 |
+
"language_model.model.layers.27.self_attn.v_proj",
|
| 114 |
+
"language_model.model.layers.20.self_attn.o_proj",
|
| 115 |
+
"language_model.model.layers.33.self_attn.k_proj",
|
| 116 |
+
"language_model.model.layers.44.mlp.up_proj",
|
| 117 |
+
"language_model.model.layers.3.self_attn.o_proj",
|
| 118 |
+
"language_model.model.layers.15.mlp.up_proj",
|
| 119 |
+
"language_model.model.layers.17.mlp.gate_proj",
|
| 120 |
+
"language_model.model.layers.17.mlp.up_proj",
|
| 121 |
+
"language_model.model.layers.55.mlp.up_proj",
|
| 122 |
+
"language_model.model.layers.0.self_attn.v_proj",
|
| 123 |
+
"language_model.model.layers.56.self_attn.v_proj",
|
| 124 |
+
"language_model.model.layers.39.self_attn.k_proj",
|
| 125 |
+
"language_model.model.layers.31.self_attn.k_proj",
|
| 126 |
+
"language_model.model.layers.50.self_attn.v_proj",
|
| 127 |
+
"language_model.model.layers.8.self_attn.q_proj",
|
| 128 |
+
"language_model.model.layers.29.self_attn.k_proj",
|
| 129 |
+
"language_model.model.layers.28.self_attn.q_proj",
|
| 130 |
+
"language_model.model.layers.37.self_attn.k_proj",
|
| 131 |
+
"language_model.model.layers.8.self_attn.k_proj",
|
| 132 |
+
"language_model.model.layers.60.self_attn.q_proj",
|
| 133 |
+
"language_model.model.layers.13.self_attn.v_proj",
|
| 134 |
+
"language_model.model.layers.18.self_attn.v_proj",
|
| 135 |
+
"language_model.model.layers.35.mlp.up_proj",
|
| 136 |
+
"language_model.model.layers.56.self_attn.k_proj",
|
| 137 |
+
"language_model.model.layers.27.self_attn.o_proj",
|
| 138 |
+
"language_model.model.layers.40.self_attn.q_proj",
|
| 139 |
+
"language_model.model.layers.25.mlp.down_proj",
|
| 140 |
+
"language_model.model.layers.50.self_attn.k_proj",
|
| 141 |
+
"language_model.model.layers.39.mlp.up_proj",
|
| 142 |
+
"language_model.model.layers.13.mlp.down_proj",
|
| 143 |
+
"language_model.model.layers.39.self_attn.o_proj",
|
| 144 |
+
"language_model.model.layers.56.mlp.down_proj",
|
| 145 |
+
"language_model.model.layers.13.self_attn.k_proj",
|
| 146 |
+
"language_model.model.layers.10.self_attn.k_proj",
|
| 147 |
+
"language_model.model.layers.42.self_attn.v_proj",
|
| 148 |
+
"language_model.model.layers.3.mlp.down_proj",
|
| 149 |
+
"language_model.model.layers.9.self_attn.q_proj",
|
| 150 |
+
"language_model.model.layers.36.mlp.up_proj",
|
| 151 |
+
"language_model.model.layers.29.mlp.down_proj",
|
| 152 |
+
"language_model.model.layers.51.mlp.down_proj",
|
| 153 |
+
"language_model.model.layers.36.self_attn.o_proj",
|
| 154 |
+
"language_model.model.layers.7.mlp.gate_proj",
|
| 155 |
+
"language_model.model.layers.31.mlp.gate_proj",
|
| 156 |
+
"language_model.model.layers.38.mlp.gate_proj",
|
| 157 |
+
"language_model.model.layers.55.mlp.down_proj",
|
| 158 |
+
"language_model.model.layers.30.mlp.down_proj",
|
| 159 |
+
"language_model.model.layers.54.mlp.gate_proj",
|
| 160 |
+
"language_model.model.layers.42.self_attn.q_proj",
|
| 161 |
+
"language_model.model.layers.0.mlp.down_proj",
|
| 162 |
+
"language_model.model.layers.32.self_attn.o_proj",
|
| 163 |
+
"language_model.model.layers.61.self_attn.q_proj",
|
| 164 |
+
"language_model.model.layers.55.self_attn.o_proj",
|
| 165 |
+
"language_model.model.layers.27.self_attn.q_proj",
|
| 166 |
+
"language_model.model.layers.41.mlp.up_proj",
|
| 167 |
+
"language_model.model.layers.2.mlp.down_proj",
|
| 168 |
+
"language_model.model.layers.48.self_attn.v_proj",
|
| 169 |
+
"language_model.model.layers.55.mlp.gate_proj",
|
| 170 |
+
"language_model.model.layers.5.self_attn.o_proj",
|
| 171 |
+
"language_model.model.layers.53.mlp.gate_proj",
|
| 172 |
+
"language_model.model.layers.26.mlp.gate_proj",
|
| 173 |
+
"language_model.model.layers.56.mlp.gate_proj",
|
| 174 |
+
"language_model.model.layers.53.mlp.up_proj",
|
| 175 |
+
"language_model.model.layers.16.self_attn.k_proj",
|
| 176 |
+
"language_model.model.layers.43.mlp.down_proj",
|
| 177 |
+
"language_model.model.layers.1.self_attn.k_proj",
|
| 178 |
+
"language_model.model.layers.19.self_attn.q_proj",
|
| 179 |
+
"language_model.model.layers.3.self_attn.k_proj",
|
| 180 |
+
"language_model.model.layers.21.self_attn.q_proj",
|
| 181 |
+
"language_model.model.layers.15.self_attn.o_proj",
|
| 182 |
+
"language_model.model.layers.57.self_attn.o_proj",
|
| 183 |
+
"language_model.model.layers.49.self_attn.o_proj",
|
| 184 |
+
"language_model.model.layers.50.self_attn.q_proj",
|
| 185 |
+
"language_model.model.layers.58.mlp.down_proj",
|
| 186 |
+
"language_model.model.layers.26.self_attn.k_proj",
|
| 187 |
+
"language_model.model.layers.38.self_attn.v_proj",
|
| 188 |
+
"language_model.model.layers.19.self_attn.v_proj",
|
| 189 |
+
"language_model.model.layers.19.mlp.up_proj",
|
| 190 |
+
"language_model.model.layers.3.self_attn.q_proj",
|
| 191 |
+
"language_model.model.layers.7.mlp.down_proj",
|
| 192 |
+
"language_model.model.layers.9.self_attn.k_proj",
|
| 193 |
+
"language_model.model.layers.29.mlp.up_proj",
|
| 194 |
+
"language_model.model.layers.49.self_attn.q_proj",
|
| 195 |
+
"language_model.model.layers.13.self_attn.q_proj",
|
| 196 |
+
"language_model.model.layers.59.self_attn.o_proj",
|
| 197 |
+
"language_model.model.layers.3.mlp.up_proj",
|
| 198 |
+
"language_model.model.layers.8.self_attn.v_proj",
|
| 199 |
+
"language_model.model.layers.0.self_attn.o_proj",
|
| 200 |
+
"language_model.model.layers.2.mlp.gate_proj",
|
| 201 |
+
"language_model.model.layers.16.self_attn.v_proj",
|
| 202 |
+
"language_model.model.layers.10.self_attn.v_proj",
|
| 203 |
+
"language_model.model.layers.16.mlp.down_proj",
|
| 204 |
+
"language_model.model.layers.20.mlp.gate_proj",
|
| 205 |
+
"language_model.model.layers.55.self_attn.v_proj",
|
| 206 |
+
"language_model.model.layers.49.self_attn.v_proj",
|
| 207 |
+
"language_model.model.layers.17.mlp.down_proj",
|
| 208 |
+
"language_model.model.layers.18.mlp.down_proj",
|
| 209 |
+
"language_model.model.layers.57.mlp.down_proj",
|
| 210 |
+
"language_model.model.layers.40.mlp.down_proj",
|
| 211 |
+
"language_model.model.layers.27.mlp.gate_proj",
|
| 212 |
+
"language_model.model.layers.17.self_attn.k_proj",
|
| 213 |
+
"language_model.model.layers.40.self_attn.o_proj",
|
| 214 |
+
"language_model.model.layers.12.mlp.gate_proj",
|
| 215 |
+
"language_model.model.layers.18.self_attn.q_proj",
|
| 216 |
+
"language_model.model.layers.54.self_attn.q_proj",
|
| 217 |
+
"language_model.model.layers.37.self_attn.o_proj",
|
| 218 |
+
"language_model.model.layers.20.self_attn.q_proj",
|
| 219 |
+
"language_model.model.layers.31.mlp.down_proj",
|
| 220 |
+
"language_model.model.layers.10.mlp.up_proj",
|
| 221 |
+
"language_model.model.layers.7.self_attn.k_proj",
|
| 222 |
+
"language_model.model.layers.1.self_attn.q_proj",
|
| 223 |
+
"language_model.model.layers.5.mlp.gate_proj",
|
| 224 |
+
"language_model.model.layers.61.mlp.down_proj",
|
| 225 |
+
"language_model.model.layers.46.self_attn.v_proj",
|
| 226 |
+
"language_model.model.layers.12.self_attn.v_proj",
|
| 227 |
+
"language_model.model.layers.54.self_attn.o_proj",
|
| 228 |
+
"language_model.model.layers.29.self_attn.o_proj",
|
| 229 |
+
"language_model.model.layers.61.self_attn.k_proj",
|
| 230 |
+
"language_model.model.layers.61.mlp.up_proj",
|
| 231 |
+
"language_model.model.layers.12.self_attn.o_proj",
|
| 232 |
+
"language_model.model.layers.5.mlp.up_proj",
|
| 233 |
+
"language_model.model.layers.54.mlp.down_proj",
|
| 234 |
+
"language_model.model.layers.53.self_attn.v_proj",
|
| 235 |
+
"language_model.model.layers.38.self_attn.k_proj",
|
| 236 |
+
"language_model.model.layers.42.self_attn.o_proj",
|
| 237 |
+
"language_model.model.layers.47.mlp.gate_proj",
|
| 238 |
+
"language_model.model.layers.25.mlp.gate_proj",
|
| 239 |
+
"language_model.model.layers.38.self_attn.q_proj",
|
| 240 |
+
"language_model.model.layers.11.self_attn.k_proj",
|
| 241 |
+
"language_model.model.layers.3.self_attn.v_proj",
|
| 242 |
+
"language_model.model.layers.61.self_attn.v_proj",
|
| 243 |
+
"language_model.model.layers.23.self_attn.k_proj",
|
| 244 |
+
"language_model.model.layers.16.self_attn.o_proj",
|
| 245 |
+
"language_model.model.layers.25.self_attn.q_proj",
|
| 246 |
+
"language_model.model.layers.37.mlp.up_proj",
|
| 247 |
+
"language_model.model.layers.13.mlp.gate_proj",
|
| 248 |
+
"language_model.model.layers.24.self_attn.o_proj",
|
| 249 |
+
"language_model.model.layers.35.self_attn.q_proj",
|
| 250 |
+
"language_model.model.layers.59.self_attn.q_proj",
|
| 251 |
+
"language_model.model.layers.17.self_attn.v_proj",
|
| 252 |
+
"language_model.model.layers.15.mlp.down_proj",
|
| 253 |
+
"language_model.model.layers.48.self_attn.q_proj",
|
| 254 |
+
"language_model.model.layers.61.self_attn.o_proj",
|
| 255 |
+
"language_model.model.layers.30.self_attn.k_proj",
|
| 256 |
+
"language_model.model.layers.21.mlp.up_proj",
|
| 257 |
+
"language_model.model.layers.44.mlp.down_proj",
|
| 258 |
+
"language_model.model.layers.12.self_attn.k_proj",
|
| 259 |
+
"language_model.model.layers.31.self_attn.q_proj",
|
| 260 |
+
"language_model.model.layers.31.self_attn.v_proj",
|
| 261 |
+
"language_model.model.layers.1.mlp.gate_proj",
|
| 262 |
+
"language_model.model.layers.22.self_attn.o_proj",
|
| 263 |
+
"language_model.model.layers.47.mlp.down_proj",
|
| 264 |
+
"language_model.model.layers.4.self_attn.k_proj",
|
| 265 |
+
"language_model.model.layers.25.self_attn.k_proj",
|
| 266 |
+
"language_model.model.layers.41.self_attn.k_proj",
|
| 267 |
+
"language_model.model.layers.33.self_attn.v_proj",
|
| 268 |
+
"language_model.model.layers.26.self_attn.q_proj",
|
| 269 |
+
"language_model.model.layers.9.mlp.down_proj",
|
| 270 |
+
"language_model.model.layers.45.self_attn.k_proj",
|
| 271 |
+
"language_model.model.layers.38.mlp.up_proj",
|
| 272 |
+
"language_model.model.layers.0.mlp.up_proj",
|
| 273 |
+
"language_model.model.layers.59.mlp.gate_proj",
|
| 274 |
+
"language_model.model.layers.5.self_attn.k_proj",
|
| 275 |
+
"language_model.model.layers.10.self_attn.o_proj",
|
| 276 |
+
"language_model.model.layers.60.mlp.up_proj",
|
| 277 |
+
"language_model.model.layers.26.self_attn.v_proj",
|
| 278 |
+
"language_model.model.layers.40.mlp.gate_proj",
|
| 279 |
+
"language_model.model.layers.60.self_attn.o_proj",
|
| 280 |
+
"language_model.model.layers.0.mlp.gate_proj",
|
| 281 |
+
"language_model.model.layers.39.mlp.down_proj",
|
| 282 |
+
"language_model.model.layers.28.self_attn.k_proj",
|
| 283 |
+
"language_model.model.layers.19.self_attn.o_proj",
|
| 284 |
+
"language_model.model.layers.43.self_attn.k_proj",
|
| 285 |
+
"language_model.model.layers.11.self_attn.q_proj",
|
| 286 |
+
"language_model.model.layers.41.mlp.gate_proj",
|
| 287 |
+
"language_model.model.layers.35.mlp.down_proj",
|
| 288 |
+
"language_model.model.layers.52.self_attn.o_proj",
|
| 289 |
+
"language_model.model.layers.32.self_attn.q_proj",
|
| 290 |
+
"language_model.model.layers.30.mlp.up_proj",
|
| 291 |
+
"language_model.model.layers.47.self_attn.q_proj",
|
| 292 |
+
"language_model.model.layers.21.mlp.down_proj",
|
| 293 |
+
"language_model.model.layers.24.mlp.gate_proj",
|
| 294 |
+
"language_model.model.layers.53.self_attn.o_proj",
|
| 295 |
+
"language_model.model.layers.42.mlp.down_proj",
|
| 296 |
+
"language_model.model.layers.44.self_attn.o_proj",
|
| 297 |
+
"language_model.model.layers.24.mlp.down_proj",
|
| 298 |
+
"language_model.model.layers.29.self_attn.q_proj",
|
| 299 |
+
"language_model.model.layers.49.mlp.up_proj",
|
| 300 |
+
"language_model.model.layers.4.self_attn.q_proj",
|
| 301 |
+
"language_model.model.layers.56.mlp.up_proj",
|
| 302 |
+
"language_model.model.layers.8.mlp.down_proj",
|
| 303 |
+
"language_model.model.layers.25.self_attn.v_proj",
|
| 304 |
+
"language_model.model.layers.37.self_attn.q_proj",
|
| 305 |
+
"language_model.model.layers.6.self_attn.k_proj",
|
| 306 |
+
"language_model.model.layers.14.self_attn.o_proj",
|
| 307 |
+
"language_model.model.layers.60.self_attn.k_proj",
|
| 308 |
+
"language_model.model.layers.2.mlp.up_proj",
|
| 309 |
+
"language_model.model.layers.34.mlp.gate_proj",
|
| 310 |
+
"language_model.model.layers.52.mlp.gate_proj",
|
| 311 |
+
"language_model.model.layers.6.mlp.down_proj",
|
| 312 |
+
"language_model.model.layers.45.self_attn.q_proj",
|
| 313 |
+
"language_model.model.layers.41.self_attn.q_proj",
|
| 314 |
+
"language_model.model.layers.52.self_attn.k_proj",
|
| 315 |
+
"language_model.model.layers.36.self_attn.v_proj",
|
| 316 |
+
"language_model.model.layers.28.mlp.down_proj",
|
| 317 |
+
"language_model.model.layers.15.self_attn.v_proj",
|
| 318 |
+
"language_model.model.layers.11.self_attn.o_proj",
|
| 319 |
+
"language_model.model.layers.29.mlp.gate_proj",
|
| 320 |
+
"language_model.model.layers.42.self_attn.k_proj",
|
| 321 |
+
"language_model.model.layers.52.mlp.up_proj",
|
| 322 |
+
"language_model.model.layers.22.self_attn.k_proj",
|
| 323 |
+
"language_model.model.layers.14.mlp.down_proj",
|
| 324 |
+
"language_model.model.layers.4.mlp.down_proj",
|
| 325 |
+
"language_model.model.layers.35.self_attn.k_proj",
|
| 326 |
+
"language_model.model.layers.52.self_attn.q_proj",
|
| 327 |
+
"language_model.model.layers.22.self_attn.q_proj",
|
| 328 |
+
"language_model.model.layers.58.mlp.gate_proj",
|
| 329 |
+
"language_model.model.layers.14.mlp.gate_proj",
|
| 330 |
+
"language_model.model.layers.47.self_attn.k_proj",
|
| 331 |
+
"language_model.model.layers.39.self_attn.q_proj",
|
| 332 |
+
"language_model.model.layers.42.mlp.up_proj",
|
| 333 |
+
"language_model.model.layers.34.mlp.down_proj",
|
| 334 |
+
"language_model.model.layers.30.self_attn.v_proj",
|
| 335 |
+
"language_model.model.layers.56.self_attn.o_proj",
|
| 336 |
+
"language_model.model.layers.25.self_attn.o_proj",
|
| 337 |
+
"language_model.model.layers.45.mlp.up_proj",
|
| 338 |
+
"language_model.model.layers.48.mlp.down_proj",
|
| 339 |
+
"language_model.model.layers.7.self_attn.o_proj",
|
| 340 |
+
"language_model.model.layers.18.self_attn.k_proj",
|
| 341 |
+
"language_model.model.layers.14.self_attn.v_proj",
|
| 342 |
+
"language_model.model.layers.40.self_attn.v_proj",
|
| 343 |
+
"language_model.model.layers.22.self_attn.v_proj",
|
| 344 |
+
"language_model.model.layers.7.self_attn.q_proj",
|
| 345 |
+
"language_model.model.layers.46.mlp.gate_proj",
|
| 346 |
+
"language_model.model.layers.56.self_attn.q_proj",
|
| 347 |
+
"language_model.model.layers.28.mlp.up_proj",
|
| 348 |
+
"language_model.model.layers.50.mlp.gate_proj",
|
| 349 |
+
"language_model.model.layers.23.self_attn.v_proj",
|
| 350 |
+
"language_model.model.layers.15.self_attn.q_proj",
|
| 351 |
+
"language_model.model.layers.9.mlp.gate_proj",
|
| 352 |
+
"language_model.model.layers.47.mlp.up_proj",
|
| 353 |
+
"language_model.model.layers.6.self_attn.o_proj",
|
| 354 |
+
"language_model.model.layers.12.self_attn.q_proj",
|
| 355 |
+
"language_model.model.layers.20.self_attn.k_proj",
|
| 356 |
+
"language_model.model.layers.51.mlp.up_proj",
|
| 357 |
+
"language_model.model.layers.58.self_attn.v_proj",
|
| 358 |
+
"language_model.model.layers.22.mlp.gate_proj",
|
| 359 |
+
"language_model.model.layers.14.mlp.up_proj",
|
| 360 |
+
"language_model.model.layers.33.self_attn.o_proj",
|
| 361 |
+
"language_model.model.layers.11.mlp.down_proj",
|
| 362 |
+
"language_model.model.layers.16.mlp.gate_proj",
|
| 363 |
+
"language_model.model.layers.40.mlp.up_proj",
|
| 364 |
+
"language_model.model.layers.60.self_attn.v_proj",
|
| 365 |
+
"language_model.model.layers.2.self_attn.k_proj",
|
| 366 |
+
"language_model.model.layers.26.self_attn.o_proj",
|
| 367 |
+
"language_model.model.layers.12.mlp.up_proj",
|
| 368 |
+
"language_model.model.layers.28.self_attn.o_proj",
|
| 369 |
+
"language_model.model.layers.32.mlp.up_proj",
|
| 370 |
+
"language_model.model.layers.45.self_attn.o_proj",
|
| 371 |
+
"language_model.model.layers.28.mlp.gate_proj",
|
| 372 |
+
"language_model.model.layers.11.mlp.gate_proj",
|
| 373 |
+
"language_model.model.layers.11.self_attn.v_proj",
|
| 374 |
+
"language_model.model.layers.2.self_attn.v_proj",
|
| 375 |
+
"language_model.model.layers.9.self_attn.v_proj",
|
| 376 |
+
"language_model.model.layers.19.self_attn.k_proj",
|
| 377 |
+
"language_model.model.layers.32.self_attn.k_proj",
|
| 378 |
+
"language_model.model.layers.43.self_attn.q_proj",
|
| 379 |
+
"language_model.model.layers.21.mlp.gate_proj",
|
| 380 |
+
"language_model.model.layers.45.self_attn.v_proj",
|
| 381 |
+
"language_model.model.layers.41.mlp.down_proj",
|
| 382 |
+
"language_model.model.layers.36.mlp.down_proj",
|
| 383 |
+
"language_model.model.layers.53.self_attn.k_proj",
|
| 384 |
+
"language_model.model.layers.16.self_attn.q_proj",
|
| 385 |
+
"language_model.model.layers.3.mlp.gate_proj",
|
| 386 |
+
"language_model.model.layers.15.self_attn.k_proj",
|
| 387 |
+
"language_model.model.layers.33.mlp.gate_proj",
|
| 388 |
+
"language_model.model.layers.48.mlp.up_proj",
|
| 389 |
+
"language_model.model.layers.33.self_attn.q_proj",
|
| 390 |
+
"language_model.model.layers.54.self_attn.k_proj",
|
| 391 |
+
"language_model.model.layers.7.self_attn.v_proj",
|
| 392 |
+
"language_model.model.layers.5.mlp.down_proj",
|
| 393 |
+
"language_model.model.layers.50.self_attn.o_proj",
|
| 394 |
+
"language_model.model.layers.21.self_attn.o_proj",
|
| 395 |
+
"language_model.model.layers.2.self_attn.q_proj",
|
| 396 |
+
"language_model.model.layers.27.self_attn.k_proj",
|
| 397 |
+
"language_model.model.layers.46.self_attn.q_proj",
|
| 398 |
+
"language_model.model.layers.20.self_attn.v_proj",
|
| 399 |
+
"language_model.model.layers.34.self_attn.k_proj",
|
| 400 |
+
"language_model.model.layers.18.mlp.gate_proj",
|
| 401 |
+
"language_model.model.layers.35.self_attn.v_proj",
|
| 402 |
+
"language_model.model.layers.32.mlp.down_proj",
|
| 403 |
+
"language_model.model.layers.6.self_attn.q_proj",
|
| 404 |
+
"language_model.model.layers.20.mlp.down_proj",
|
| 405 |
+
"language_model.model.layers.27.mlp.up_proj",
|
| 406 |
+
"language_model.model.layers.31.self_attn.o_proj",
|
| 407 |
+
"language_model.model.layers.59.mlp.down_proj",
|
| 408 |
+
"language_model.model.layers.4.self_attn.o_proj",
|
| 409 |
+
"language_model.model.layers.15.mlp.gate_proj",
|
| 410 |
+
"language_model.model.layers.44.self_attn.q_proj",
|
| 411 |
+
"language_model.model.layers.31.mlp.up_proj",
|
| 412 |
+
"language_model.model.layers.30.mlp.gate_proj",
|
| 413 |
+
"language_model.model.layers.42.mlp.gate_proj",
|
| 414 |
+
"language_model.model.layers.19.mlp.gate_proj",
|
| 415 |
+
"language_model.model.layers.38.mlp.down_proj",
|
| 416 |
+
"language_model.model.layers.23.self_attn.o_proj",
|
| 417 |
+
"language_model.model.layers.16.mlp.up_proj",
|
| 418 |
+
"language_model.model.layers.52.self_attn.v_proj",
|
| 419 |
+
"language_model.model.layers.22.mlp.up_proj",
|
| 420 |
+
"language_model.model.layers.41.self_attn.o_proj",
|
| 421 |
+
"language_model.model.layers.19.mlp.down_proj",
|
| 422 |
+
"language_model.model.layers.37.mlp.down_proj",
|
| 423 |
+
"language_model.model.layers.8.self_attn.o_proj",
|
| 424 |
+
"language_model.model.layers.57.self_attn.k_proj",
|
| 425 |
+
"language_model.model.layers.41.self_attn.v_proj",
|
| 426 |
+
"language_model.model.layers.21.self_attn.v_proj",
|
| 427 |
+
"language_model.model.layers.34.self_attn.q_proj",
|
| 428 |
+
"language_model.model.layers.47.self_attn.v_proj",
|
| 429 |
+
"language_model.model.layers.32.mlp.gate_proj",
|
| 430 |
+
"language_model.model.layers.43.self_attn.o_proj",
|
| 431 |
+
"language_model.model.layers.21.self_attn.k_proj",
|
| 432 |
+
"language_model.model.layers.1.self_attn.v_proj",
|
| 433 |
+
"language_model.model.layers.8.mlp.up_proj",
|
| 434 |
+
"language_model.model.layers.20.mlp.up_proj",
|
| 435 |
+
"language_model.model.layers.23.mlp.gate_proj",
|
| 436 |
+
"language_model.model.layers.43.mlp.gate_proj",
|
| 437 |
+
"language_model.model.layers.54.self_attn.v_proj",
|
| 438 |
+
"language_model.model.layers.54.mlp.up_proj",
|
| 439 |
+
"language_model.model.layers.50.mlp.up_proj",
|
| 440 |
+
"language_model.model.layers.48.mlp.gate_proj",
|
| 441 |
+
"language_model.model.layers.35.mlp.gate_proj",
|
| 442 |
+
"language_model.model.layers.0.self_attn.k_proj",
|
| 443 |
+
"language_model.model.layers.47.self_attn.o_proj",
|
| 444 |
+
"language_model.model.layers.51.self_attn.k_proj",
|
| 445 |
+
"language_model.model.layers.58.self_attn.k_proj",
|
| 446 |
+
"language_model.model.layers.35.self_attn.o_proj",
|
| 447 |
+
"language_model.model.layers.55.self_attn.q_proj",
|
| 448 |
+
"language_model.model.layers.57.mlp.gate_proj",
|
| 449 |
+
"language_model.model.layers.6.mlp.up_proj",
|
| 450 |
+
"language_model.model.layers.7.mlp.up_proj",
|
| 451 |
+
"language_model.model.layers.34.self_attn.v_proj",
|
| 452 |
+
"language_model.model.layers.48.self_attn.o_proj",
|
| 453 |
+
"language_model.model.layers.36.self_attn.q_proj",
|
| 454 |
+
"language_model.model.layers.6.self_attn.v_proj",
|
| 455 |
+
"language_model.model.layers.53.mlp.down_proj",
|
| 456 |
+
"language_model.model.layers.49.mlp.gate_proj"
|
| 457 |
+
],
|
| 458 |
+
"task_type": "CAUSAL_LM",
|
| 459 |
+
"use_dora": false,
|
| 460 |
+
"use_rslora": false
|
| 461 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2858bf7ea1a8dfcfd2e9c7c507b264f099f9dbe08796a8fc21788c499f6d5ad8
|
| 3 |
+
size 1816396048
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"num_input_tokens_seen": 1130688,
|
| 4 |
+
"total_flos": 1.7959027775641805e+17,
|
| 5 |
+
"train_loss": 2.86213872662629,
|
| 6 |
+
"train_runtime": 778.6794,
|
| 7 |
+
"train_samples_per_second": 1.233,
|
| 8 |
+
"train_steps_per_second": 0.154
|
| 9 |
+
}
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
|
| 3 |
+
}
|
checkpoint-100/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/gemma-3-27b-it
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
checkpoint-100/adapter_config.json
ADDED
|
@@ -0,0 +1,461 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "google/gemma-3-27b-it",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 128,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"language_model.model.layers.18.mlp.up_proj",
|
| 24 |
+
"language_model.model.layers.14.self_attn.q_proj",
|
| 25 |
+
"language_model.model.layers.23.mlp.down_proj",
|
| 26 |
+
"language_model.model.layers.5.self_attn.q_proj",
|
| 27 |
+
"language_model.model.layers.48.self_attn.k_proj",
|
| 28 |
+
"language_model.model.layers.29.self_attn.v_proj",
|
| 29 |
+
"language_model.model.layers.39.self_attn.v_proj",
|
| 30 |
+
"language_model.model.layers.5.self_attn.v_proj",
|
| 31 |
+
"language_model.model.layers.60.mlp.gate_proj",
|
| 32 |
+
"language_model.model.layers.17.self_attn.o_proj",
|
| 33 |
+
"language_model.model.layers.60.mlp.down_proj",
|
| 34 |
+
"language_model.model.layers.33.mlp.up_proj",
|
| 35 |
+
"language_model.model.layers.53.self_attn.q_proj",
|
| 36 |
+
"language_model.model.layers.27.mlp.down_proj",
|
| 37 |
+
"language_model.model.layers.57.self_attn.v_proj",
|
| 38 |
+
"language_model.model.layers.26.mlp.up_proj",
|
| 39 |
+
"language_model.model.layers.10.mlp.gate_proj",
|
| 40 |
+
"language_model.model.layers.23.mlp.up_proj",
|
| 41 |
+
"language_model.model.layers.57.self_attn.q_proj",
|
| 42 |
+
"language_model.model.layers.57.mlp.up_proj",
|
| 43 |
+
"language_model.model.layers.39.mlp.gate_proj",
|
| 44 |
+
"language_model.model.layers.26.mlp.down_proj",
|
| 45 |
+
"language_model.model.layers.11.mlp.up_proj",
|
| 46 |
+
"language_model.model.layers.25.mlp.up_proj",
|
| 47 |
+
"language_model.model.layers.6.mlp.gate_proj",
|
| 48 |
+
"language_model.model.layers.36.mlp.gate_proj",
|
| 49 |
+
"language_model.model.layers.2.self_attn.o_proj",
|
| 50 |
+
"language_model.model.layers.30.self_attn.o_proj",
|
| 51 |
+
"language_model.model.layers.4.mlp.gate_proj",
|
| 52 |
+
"language_model.model.layers.13.mlp.up_proj",
|
| 53 |
+
"language_model.model.layers.52.mlp.down_proj",
|
| 54 |
+
"language_model.model.layers.4.mlp.up_proj",
|
| 55 |
+
"language_model.model.layers.32.self_attn.v_proj",
|
| 56 |
+
"language_model.model.layers.1.self_attn.o_proj",
|
| 57 |
+
"language_model.model.layers.22.mlp.down_proj",
|
| 58 |
+
"language_model.model.layers.45.mlp.down_proj",
|
| 59 |
+
"language_model.model.layers.46.self_attn.o_proj",
|
| 60 |
+
"language_model.model.layers.38.self_attn.o_proj",
|
| 61 |
+
"language_model.model.layers.23.self_attn.q_proj",
|
| 62 |
+
"language_model.model.layers.46.mlp.up_proj",
|
| 63 |
+
"language_model.model.layers.49.mlp.down_proj",
|
| 64 |
+
"language_model.model.layers.40.self_attn.k_proj",
|
| 65 |
+
"language_model.model.layers.24.self_attn.q_proj",
|
| 66 |
+
"language_model.model.layers.9.self_attn.o_proj",
|
| 67 |
+
"language_model.model.layers.37.mlp.gate_proj",
|
| 68 |
+
"language_model.model.layers.36.self_attn.k_proj",
|
| 69 |
+
"language_model.model.layers.49.self_attn.k_proj",
|
| 70 |
+
"language_model.model.layers.24.self_attn.v_proj",
|
| 71 |
+
"language_model.model.layers.1.mlp.down_proj",
|
| 72 |
+
"language_model.model.layers.10.mlp.down_proj",
|
| 73 |
+
"language_model.model.layers.61.mlp.gate_proj",
|
| 74 |
+
"language_model.model.layers.34.self_attn.o_proj",
|
| 75 |
+
"language_model.model.layers.9.mlp.up_proj",
|
| 76 |
+
"language_model.model.layers.59.self_attn.v_proj",
|
| 77 |
+
"language_model.model.layers.30.self_attn.q_proj",
|
| 78 |
+
"language_model.model.layers.44.mlp.gate_proj",
|
| 79 |
+
"language_model.model.layers.46.mlp.down_proj",
|
| 80 |
+
"language_model.model.layers.46.self_attn.k_proj",
|
| 81 |
+
"language_model.model.layers.28.self_attn.v_proj",
|
| 82 |
+
"language_model.model.layers.58.self_attn.o_proj",
|
| 83 |
+
"language_model.model.layers.13.self_attn.o_proj",
|
| 84 |
+
"language_model.model.layers.24.mlp.up_proj",
|
| 85 |
+
"language_model.model.layers.0.self_attn.q_proj",
|
| 86 |
+
"language_model.model.layers.58.mlp.up_proj",
|
| 87 |
+
"language_model.model.layers.12.mlp.down_proj",
|
| 88 |
+
"language_model.model.layers.43.mlp.up_proj",
|
| 89 |
+
"language_model.model.layers.44.self_attn.k_proj",
|
| 90 |
+
"language_model.model.layers.17.self_attn.q_proj",
|
| 91 |
+
"language_model.model.layers.59.mlp.up_proj",
|
| 92 |
+
"language_model.model.layers.50.mlp.down_proj",
|
| 93 |
+
"language_model.model.layers.24.self_attn.k_proj",
|
| 94 |
+
"language_model.model.layers.59.self_attn.k_proj",
|
| 95 |
+
"language_model.model.layers.1.mlp.up_proj",
|
| 96 |
+
"language_model.model.layers.58.self_attn.q_proj",
|
| 97 |
+
"language_model.model.layers.51.mlp.gate_proj",
|
| 98 |
+
"language_model.model.layers.4.self_attn.v_proj",
|
| 99 |
+
"language_model.model.layers.45.mlp.gate_proj",
|
| 100 |
+
"language_model.model.layers.8.mlp.gate_proj",
|
| 101 |
+
"language_model.model.layers.43.self_attn.v_proj",
|
| 102 |
+
"language_model.model.layers.51.self_attn.v_proj",
|
| 103 |
+
"language_model.model.layers.37.self_attn.v_proj",
|
| 104 |
+
"language_model.model.layers.51.self_attn.q_proj",
|
| 105 |
+
"language_model.model.layers.51.self_attn.o_proj",
|
| 106 |
+
"language_model.model.layers.33.mlp.down_proj",
|
| 107 |
+
"language_model.model.layers.44.self_attn.v_proj",
|
| 108 |
+
"language_model.model.layers.18.self_attn.o_proj",
|
| 109 |
+
"language_model.model.layers.14.self_attn.k_proj",
|
| 110 |
+
"language_model.model.layers.55.self_attn.k_proj",
|
| 111 |
+
"language_model.model.layers.10.self_attn.q_proj",
|
| 112 |
+
"language_model.model.layers.34.mlp.up_proj",
|
| 113 |
+
"language_model.model.layers.27.self_attn.v_proj",
|
| 114 |
+
"language_model.model.layers.20.self_attn.o_proj",
|
| 115 |
+
"language_model.model.layers.33.self_attn.k_proj",
|
| 116 |
+
"language_model.model.layers.44.mlp.up_proj",
|
| 117 |
+
"language_model.model.layers.3.self_attn.o_proj",
|
| 118 |
+
"language_model.model.layers.15.mlp.up_proj",
|
| 119 |
+
"language_model.model.layers.17.mlp.gate_proj",
|
| 120 |
+
"language_model.model.layers.17.mlp.up_proj",
|
| 121 |
+
"language_model.model.layers.55.mlp.up_proj",
|
| 122 |
+
"language_model.model.layers.0.self_attn.v_proj",
|
| 123 |
+
"language_model.model.layers.56.self_attn.v_proj",
|
| 124 |
+
"language_model.model.layers.39.self_attn.k_proj",
|
| 125 |
+
"language_model.model.layers.31.self_attn.k_proj",
|
| 126 |
+
"language_model.model.layers.50.self_attn.v_proj",
|
| 127 |
+
"language_model.model.layers.8.self_attn.q_proj",
|
| 128 |
+
"language_model.model.layers.29.self_attn.k_proj",
|
| 129 |
+
"language_model.model.layers.28.self_attn.q_proj",
|
| 130 |
+
"language_model.model.layers.37.self_attn.k_proj",
|
| 131 |
+
"language_model.model.layers.8.self_attn.k_proj",
|
| 132 |
+
"language_model.model.layers.60.self_attn.q_proj",
|
| 133 |
+
"language_model.model.layers.13.self_attn.v_proj",
|
| 134 |
+
"language_model.model.layers.18.self_attn.v_proj",
|
| 135 |
+
"language_model.model.layers.35.mlp.up_proj",
|
| 136 |
+
"language_model.model.layers.56.self_attn.k_proj",
|
| 137 |
+
"language_model.model.layers.27.self_attn.o_proj",
|
| 138 |
+
"language_model.model.layers.40.self_attn.q_proj",
|
| 139 |
+
"language_model.model.layers.25.mlp.down_proj",
|
| 140 |
+
"language_model.model.layers.50.self_attn.k_proj",
|
| 141 |
+
"language_model.model.layers.39.mlp.up_proj",
|
| 142 |
+
"language_model.model.layers.13.mlp.down_proj",
|
| 143 |
+
"language_model.model.layers.39.self_attn.o_proj",
|
| 144 |
+
"language_model.model.layers.56.mlp.down_proj",
|
| 145 |
+
"language_model.model.layers.13.self_attn.k_proj",
|
| 146 |
+
"language_model.model.layers.10.self_attn.k_proj",
|
| 147 |
+
"language_model.model.layers.42.self_attn.v_proj",
|
| 148 |
+
"language_model.model.layers.3.mlp.down_proj",
|
| 149 |
+
"language_model.model.layers.9.self_attn.q_proj",
|
| 150 |
+
"language_model.model.layers.36.mlp.up_proj",
|
| 151 |
+
"language_model.model.layers.29.mlp.down_proj",
|
| 152 |
+
"language_model.model.layers.51.mlp.down_proj",
|
| 153 |
+
"language_model.model.layers.36.self_attn.o_proj",
|
| 154 |
+
"language_model.model.layers.7.mlp.gate_proj",
|
| 155 |
+
"language_model.model.layers.31.mlp.gate_proj",
|
| 156 |
+
"language_model.model.layers.38.mlp.gate_proj",
|
| 157 |
+
"language_model.model.layers.55.mlp.down_proj",
|
| 158 |
+
"language_model.model.layers.30.mlp.down_proj",
|
| 159 |
+
"language_model.model.layers.54.mlp.gate_proj",
|
| 160 |
+
"language_model.model.layers.42.self_attn.q_proj",
|
| 161 |
+
"language_model.model.layers.0.mlp.down_proj",
|
| 162 |
+
"language_model.model.layers.32.self_attn.o_proj",
|
| 163 |
+
"language_model.model.layers.61.self_attn.q_proj",
|
| 164 |
+
"language_model.model.layers.55.self_attn.o_proj",
|
| 165 |
+
"language_model.model.layers.27.self_attn.q_proj",
|
| 166 |
+
"language_model.model.layers.41.mlp.up_proj",
|
| 167 |
+
"language_model.model.layers.2.mlp.down_proj",
|
| 168 |
+
"language_model.model.layers.48.self_attn.v_proj",
|
| 169 |
+
"language_model.model.layers.55.mlp.gate_proj",
|
| 170 |
+
"language_model.model.layers.5.self_attn.o_proj",
|
| 171 |
+
"language_model.model.layers.53.mlp.gate_proj",
|
| 172 |
+
"language_model.model.layers.26.mlp.gate_proj",
|
| 173 |
+
"language_model.model.layers.56.mlp.gate_proj",
|
| 174 |
+
"language_model.model.layers.53.mlp.up_proj",
|
| 175 |
+
"language_model.model.layers.16.self_attn.k_proj",
|
| 176 |
+
"language_model.model.layers.43.mlp.down_proj",
|
| 177 |
+
"language_model.model.layers.1.self_attn.k_proj",
|
| 178 |
+
"language_model.model.layers.19.self_attn.q_proj",
|
| 179 |
+
"language_model.model.layers.3.self_attn.k_proj",
|
| 180 |
+
"language_model.model.layers.21.self_attn.q_proj",
|
| 181 |
+
"language_model.model.layers.15.self_attn.o_proj",
|
| 182 |
+
"language_model.model.layers.57.self_attn.o_proj",
|
| 183 |
+
"language_model.model.layers.49.self_attn.o_proj",
|
| 184 |
+
"language_model.model.layers.50.self_attn.q_proj",
|
| 185 |
+
"language_model.model.layers.58.mlp.down_proj",
|
| 186 |
+
"language_model.model.layers.26.self_attn.k_proj",
|
| 187 |
+
"language_model.model.layers.38.self_attn.v_proj",
|
| 188 |
+
"language_model.model.layers.19.self_attn.v_proj",
|
| 189 |
+
"language_model.model.layers.19.mlp.up_proj",
|
| 190 |
+
"language_model.model.layers.3.self_attn.q_proj",
|
| 191 |
+
"language_model.model.layers.7.mlp.down_proj",
|
| 192 |
+
"language_model.model.layers.9.self_attn.k_proj",
|
| 193 |
+
"language_model.model.layers.29.mlp.up_proj",
|
| 194 |
+
"language_model.model.layers.49.self_attn.q_proj",
|
| 195 |
+
"language_model.model.layers.13.self_attn.q_proj",
|
| 196 |
+
"language_model.model.layers.59.self_attn.o_proj",
|
| 197 |
+
"language_model.model.layers.3.mlp.up_proj",
|
| 198 |
+
"language_model.model.layers.8.self_attn.v_proj",
|
| 199 |
+
"language_model.model.layers.0.self_attn.o_proj",
|
| 200 |
+
"language_model.model.layers.2.mlp.gate_proj",
|
| 201 |
+
"language_model.model.layers.16.self_attn.v_proj",
|
| 202 |
+
"language_model.model.layers.10.self_attn.v_proj",
|
| 203 |
+
"language_model.model.layers.16.mlp.down_proj",
|
| 204 |
+
"language_model.model.layers.20.mlp.gate_proj",
|
| 205 |
+
"language_model.model.layers.55.self_attn.v_proj",
|
| 206 |
+
"language_model.model.layers.49.self_attn.v_proj",
|
| 207 |
+
"language_model.model.layers.17.mlp.down_proj",
|
| 208 |
+
"language_model.model.layers.18.mlp.down_proj",
|
| 209 |
+
"language_model.model.layers.57.mlp.down_proj",
|
| 210 |
+
"language_model.model.layers.40.mlp.down_proj",
|
| 211 |
+
"language_model.model.layers.27.mlp.gate_proj",
|
| 212 |
+
"language_model.model.layers.17.self_attn.k_proj",
|
| 213 |
+
"language_model.model.layers.40.self_attn.o_proj",
|
| 214 |
+
"language_model.model.layers.12.mlp.gate_proj",
|
| 215 |
+
"language_model.model.layers.18.self_attn.q_proj",
|
| 216 |
+
"language_model.model.layers.54.self_attn.q_proj",
|
| 217 |
+
"language_model.model.layers.37.self_attn.o_proj",
|
| 218 |
+
"language_model.model.layers.20.self_attn.q_proj",
|
| 219 |
+
"language_model.model.layers.31.mlp.down_proj",
|
| 220 |
+
"language_model.model.layers.10.mlp.up_proj",
|
| 221 |
+
"language_model.model.layers.7.self_attn.k_proj",
|
| 222 |
+
"language_model.model.layers.1.self_attn.q_proj",
|
| 223 |
+
"language_model.model.layers.5.mlp.gate_proj",
|
| 224 |
+
"language_model.model.layers.61.mlp.down_proj",
|
| 225 |
+
"language_model.model.layers.46.self_attn.v_proj",
|
| 226 |
+
"language_model.model.layers.12.self_attn.v_proj",
|
| 227 |
+
"language_model.model.layers.54.self_attn.o_proj",
|
| 228 |
+
"language_model.model.layers.29.self_attn.o_proj",
|
| 229 |
+
"language_model.model.layers.61.self_attn.k_proj",
|
| 230 |
+
"language_model.model.layers.61.mlp.up_proj",
|
| 231 |
+
"language_model.model.layers.12.self_attn.o_proj",
|
| 232 |
+
"language_model.model.layers.5.mlp.up_proj",
|
| 233 |
+
"language_model.model.layers.54.mlp.down_proj",
|
| 234 |
+
"language_model.model.layers.53.self_attn.v_proj",
|
| 235 |
+
"language_model.model.layers.38.self_attn.k_proj",
|
| 236 |
+
"language_model.model.layers.42.self_attn.o_proj",
|
| 237 |
+
"language_model.model.layers.47.mlp.gate_proj",
|
| 238 |
+
"language_model.model.layers.25.mlp.gate_proj",
|
| 239 |
+
"language_model.model.layers.38.self_attn.q_proj",
|
| 240 |
+
"language_model.model.layers.11.self_attn.k_proj",
|
| 241 |
+
"language_model.model.layers.3.self_attn.v_proj",
|
| 242 |
+
"language_model.model.layers.61.self_attn.v_proj",
|
| 243 |
+
"language_model.model.layers.23.self_attn.k_proj",
|
| 244 |
+
"language_model.model.layers.16.self_attn.o_proj",
|
| 245 |
+
"language_model.model.layers.25.self_attn.q_proj",
|
| 246 |
+
"language_model.model.layers.37.mlp.up_proj",
|
| 247 |
+
"language_model.model.layers.13.mlp.gate_proj",
|
| 248 |
+
"language_model.model.layers.24.self_attn.o_proj",
|
| 249 |
+
"language_model.model.layers.35.self_attn.q_proj",
|
| 250 |
+
"language_model.model.layers.59.self_attn.q_proj",
|
| 251 |
+
"language_model.model.layers.17.self_attn.v_proj",
|
| 252 |
+
"language_model.model.layers.15.mlp.down_proj",
|
| 253 |
+
"language_model.model.layers.48.self_attn.q_proj",
|
| 254 |
+
"language_model.model.layers.61.self_attn.o_proj",
|
| 255 |
+
"language_model.model.layers.30.self_attn.k_proj",
|
| 256 |
+
"language_model.model.layers.21.mlp.up_proj",
|
| 257 |
+
"language_model.model.layers.44.mlp.down_proj",
|
| 258 |
+
"language_model.model.layers.12.self_attn.k_proj",
|
| 259 |
+
"language_model.model.layers.31.self_attn.q_proj",
|
| 260 |
+
"language_model.model.layers.31.self_attn.v_proj",
|
| 261 |
+
"language_model.model.layers.1.mlp.gate_proj",
|
| 262 |
+
"language_model.model.layers.22.self_attn.o_proj",
|
| 263 |
+
"language_model.model.layers.47.mlp.down_proj",
|
| 264 |
+
"language_model.model.layers.4.self_attn.k_proj",
|
| 265 |
+
"language_model.model.layers.25.self_attn.k_proj",
|
| 266 |
+
"language_model.model.layers.41.self_attn.k_proj",
|
| 267 |
+
"language_model.model.layers.33.self_attn.v_proj",
|
| 268 |
+
"language_model.model.layers.26.self_attn.q_proj",
|
| 269 |
+
"language_model.model.layers.9.mlp.down_proj",
|
| 270 |
+
"language_model.model.layers.45.self_attn.k_proj",
|
| 271 |
+
"language_model.model.layers.38.mlp.up_proj",
|
| 272 |
+
"language_model.model.layers.0.mlp.up_proj",
|
| 273 |
+
"language_model.model.layers.59.mlp.gate_proj",
|
| 274 |
+
"language_model.model.layers.5.self_attn.k_proj",
|
| 275 |
+
"language_model.model.layers.10.self_attn.o_proj",
|
| 276 |
+
"language_model.model.layers.60.mlp.up_proj",
|
| 277 |
+
"language_model.model.layers.26.self_attn.v_proj",
|
| 278 |
+
"language_model.model.layers.40.mlp.gate_proj",
|
| 279 |
+
"language_model.model.layers.60.self_attn.o_proj",
|
| 280 |
+
"language_model.model.layers.0.mlp.gate_proj",
|
| 281 |
+
"language_model.model.layers.39.mlp.down_proj",
|
| 282 |
+
"language_model.model.layers.28.self_attn.k_proj",
|
| 283 |
+
"language_model.model.layers.19.self_attn.o_proj",
|
| 284 |
+
"language_model.model.layers.43.self_attn.k_proj",
|
| 285 |
+
"language_model.model.layers.11.self_attn.q_proj",
|
| 286 |
+
"language_model.model.layers.41.mlp.gate_proj",
|
| 287 |
+
"language_model.model.layers.35.mlp.down_proj",
|
| 288 |
+
"language_model.model.layers.52.self_attn.o_proj",
|
| 289 |
+
"language_model.model.layers.32.self_attn.q_proj",
|
| 290 |
+
"language_model.model.layers.30.mlp.up_proj",
|
| 291 |
+
"language_model.model.layers.47.self_attn.q_proj",
|
| 292 |
+
"language_model.model.layers.21.mlp.down_proj",
|
| 293 |
+
"language_model.model.layers.24.mlp.gate_proj",
|
| 294 |
+
"language_model.model.layers.53.self_attn.o_proj",
|
| 295 |
+
"language_model.model.layers.42.mlp.down_proj",
|
| 296 |
+
"language_model.model.layers.44.self_attn.o_proj",
|
| 297 |
+
"language_model.model.layers.24.mlp.down_proj",
|
| 298 |
+
"language_model.model.layers.29.self_attn.q_proj",
|
| 299 |
+
"language_model.model.layers.49.mlp.up_proj",
|
| 300 |
+
"language_model.model.layers.4.self_attn.q_proj",
|
| 301 |
+
"language_model.model.layers.56.mlp.up_proj",
|
| 302 |
+
"language_model.model.layers.8.mlp.down_proj",
|
| 303 |
+
"language_model.model.layers.25.self_attn.v_proj",
|
| 304 |
+
"language_model.model.layers.37.self_attn.q_proj",
|
| 305 |
+
"language_model.model.layers.6.self_attn.k_proj",
|
| 306 |
+
"language_model.model.layers.14.self_attn.o_proj",
|
| 307 |
+
"language_model.model.layers.60.self_attn.k_proj",
|
| 308 |
+
"language_model.model.layers.2.mlp.up_proj",
|
| 309 |
+
"language_model.model.layers.34.mlp.gate_proj",
|
| 310 |
+
"language_model.model.layers.52.mlp.gate_proj",
|
| 311 |
+
"language_model.model.layers.6.mlp.down_proj",
|
| 312 |
+
"language_model.model.layers.45.self_attn.q_proj",
|
| 313 |
+
"language_model.model.layers.41.self_attn.q_proj",
|
| 314 |
+
"language_model.model.layers.52.self_attn.k_proj",
|
| 315 |
+
"language_model.model.layers.36.self_attn.v_proj",
|
| 316 |
+
"language_model.model.layers.28.mlp.down_proj",
|
| 317 |
+
"language_model.model.layers.15.self_attn.v_proj",
|
| 318 |
+
"language_model.model.layers.11.self_attn.o_proj",
|
| 319 |
+
"language_model.model.layers.29.mlp.gate_proj",
|
| 320 |
+
"language_model.model.layers.42.self_attn.k_proj",
|
| 321 |
+
"language_model.model.layers.52.mlp.up_proj",
|
| 322 |
+
"language_model.model.layers.22.self_attn.k_proj",
|
| 323 |
+
"language_model.model.layers.14.mlp.down_proj",
|
| 324 |
+
"language_model.model.layers.4.mlp.down_proj",
|
| 325 |
+
"language_model.model.layers.35.self_attn.k_proj",
|
| 326 |
+
"language_model.model.layers.52.self_attn.q_proj",
|
| 327 |
+
"language_model.model.layers.22.self_attn.q_proj",
|
| 328 |
+
"language_model.model.layers.58.mlp.gate_proj",
|
| 329 |
+
"language_model.model.layers.14.mlp.gate_proj",
|
| 330 |
+
"language_model.model.layers.47.self_attn.k_proj",
|
| 331 |
+
"language_model.model.layers.39.self_attn.q_proj",
|
| 332 |
+
"language_model.model.layers.42.mlp.up_proj",
|
| 333 |
+
"language_model.model.layers.34.mlp.down_proj",
|
| 334 |
+
"language_model.model.layers.30.self_attn.v_proj",
|
| 335 |
+
"language_model.model.layers.56.self_attn.o_proj",
|
| 336 |
+
"language_model.model.layers.25.self_attn.o_proj",
|
| 337 |
+
"language_model.model.layers.45.mlp.up_proj",
|
| 338 |
+
"language_model.model.layers.48.mlp.down_proj",
|
| 339 |
+
"language_model.model.layers.7.self_attn.o_proj",
|
| 340 |
+
"language_model.model.layers.18.self_attn.k_proj",
|
| 341 |
+
"language_model.model.layers.14.self_attn.v_proj",
|
| 342 |
+
"language_model.model.layers.40.self_attn.v_proj",
|
| 343 |
+
"language_model.model.layers.22.self_attn.v_proj",
|
| 344 |
+
"language_model.model.layers.7.self_attn.q_proj",
|
| 345 |
+
"language_model.model.layers.46.mlp.gate_proj",
|
| 346 |
+
"language_model.model.layers.56.self_attn.q_proj",
|
| 347 |
+
"language_model.model.layers.28.mlp.up_proj",
|
| 348 |
+
"language_model.model.layers.50.mlp.gate_proj",
|
| 349 |
+
"language_model.model.layers.23.self_attn.v_proj",
|
| 350 |
+
"language_model.model.layers.15.self_attn.q_proj",
|
| 351 |
+
"language_model.model.layers.9.mlp.gate_proj",
|
| 352 |
+
"language_model.model.layers.47.mlp.up_proj",
|
| 353 |
+
"language_model.model.layers.6.self_attn.o_proj",
|
| 354 |
+
"language_model.model.layers.12.self_attn.q_proj",
|
| 355 |
+
"language_model.model.layers.20.self_attn.k_proj",
|
| 356 |
+
"language_model.model.layers.51.mlp.up_proj",
|
| 357 |
+
"language_model.model.layers.58.self_attn.v_proj",
|
| 358 |
+
"language_model.model.layers.22.mlp.gate_proj",
|
| 359 |
+
"language_model.model.layers.14.mlp.up_proj",
|
| 360 |
+
"language_model.model.layers.33.self_attn.o_proj",
|
| 361 |
+
"language_model.model.layers.11.mlp.down_proj",
|
| 362 |
+
"language_model.model.layers.16.mlp.gate_proj",
|
| 363 |
+
"language_model.model.layers.40.mlp.up_proj",
|
| 364 |
+
"language_model.model.layers.60.self_attn.v_proj",
|
| 365 |
+
"language_model.model.layers.2.self_attn.k_proj",
|
| 366 |
+
"language_model.model.layers.26.self_attn.o_proj",
|
| 367 |
+
"language_model.model.layers.12.mlp.up_proj",
|
| 368 |
+
"language_model.model.layers.28.self_attn.o_proj",
|
| 369 |
+
"language_model.model.layers.32.mlp.up_proj",
|
| 370 |
+
"language_model.model.layers.45.self_attn.o_proj",
|
| 371 |
+
"language_model.model.layers.28.mlp.gate_proj",
|
| 372 |
+
"language_model.model.layers.11.mlp.gate_proj",
|
| 373 |
+
"language_model.model.layers.11.self_attn.v_proj",
|
| 374 |
+
"language_model.model.layers.2.self_attn.v_proj",
|
| 375 |
+
"language_model.model.layers.9.self_attn.v_proj",
|
| 376 |
+
"language_model.model.layers.19.self_attn.k_proj",
|
| 377 |
+
"language_model.model.layers.32.self_attn.k_proj",
|
| 378 |
+
"language_model.model.layers.43.self_attn.q_proj",
|
| 379 |
+
"language_model.model.layers.21.mlp.gate_proj",
|
| 380 |
+
"language_model.model.layers.45.self_attn.v_proj",
|
| 381 |
+
"language_model.model.layers.41.mlp.down_proj",
|
| 382 |
+
"language_model.model.layers.36.mlp.down_proj",
|
| 383 |
+
"language_model.model.layers.53.self_attn.k_proj",
|
| 384 |
+
"language_model.model.layers.16.self_attn.q_proj",
|
| 385 |
+
"language_model.model.layers.3.mlp.gate_proj",
|
| 386 |
+
"language_model.model.layers.15.self_attn.k_proj",
|
| 387 |
+
"language_model.model.layers.33.mlp.gate_proj",
|
| 388 |
+
"language_model.model.layers.48.mlp.up_proj",
|
| 389 |
+
"language_model.model.layers.33.self_attn.q_proj",
|
| 390 |
+
"language_model.model.layers.54.self_attn.k_proj",
|
| 391 |
+
"language_model.model.layers.7.self_attn.v_proj",
|
| 392 |
+
"language_model.model.layers.5.mlp.down_proj",
|
| 393 |
+
"language_model.model.layers.50.self_attn.o_proj",
|
| 394 |
+
"language_model.model.layers.21.self_attn.o_proj",
|
| 395 |
+
"language_model.model.layers.2.self_attn.q_proj",
|
| 396 |
+
"language_model.model.layers.27.self_attn.k_proj",
|
| 397 |
+
"language_model.model.layers.46.self_attn.q_proj",
|
| 398 |
+
"language_model.model.layers.20.self_attn.v_proj",
|
| 399 |
+
"language_model.model.layers.34.self_attn.k_proj",
|
| 400 |
+
"language_model.model.layers.18.mlp.gate_proj",
|
| 401 |
+
"language_model.model.layers.35.self_attn.v_proj",
|
| 402 |
+
"language_model.model.layers.32.mlp.down_proj",
|
| 403 |
+
"language_model.model.layers.6.self_attn.q_proj",
|
| 404 |
+
"language_model.model.layers.20.mlp.down_proj",
|
| 405 |
+
"language_model.model.layers.27.mlp.up_proj",
|
| 406 |
+
"language_model.model.layers.31.self_attn.o_proj",
|
| 407 |
+
"language_model.model.layers.59.mlp.down_proj",
|
| 408 |
+
"language_model.model.layers.4.self_attn.o_proj",
|
| 409 |
+
"language_model.model.layers.15.mlp.gate_proj",
|
| 410 |
+
"language_model.model.layers.44.self_attn.q_proj",
|
| 411 |
+
"language_model.model.layers.31.mlp.up_proj",
|
| 412 |
+
"language_model.model.layers.30.mlp.gate_proj",
|
| 413 |
+
"language_model.model.layers.42.mlp.gate_proj",
|
| 414 |
+
"language_model.model.layers.19.mlp.gate_proj",
|
| 415 |
+
"language_model.model.layers.38.mlp.down_proj",
|
| 416 |
+
"language_model.model.layers.23.self_attn.o_proj",
|
| 417 |
+
"language_model.model.layers.16.mlp.up_proj",
|
| 418 |
+
"language_model.model.layers.52.self_attn.v_proj",
|
| 419 |
+
"language_model.model.layers.22.mlp.up_proj",
|
| 420 |
+
"language_model.model.layers.41.self_attn.o_proj",
|
| 421 |
+
"language_model.model.layers.19.mlp.down_proj",
|
| 422 |
+
"language_model.model.layers.37.mlp.down_proj",
|
| 423 |
+
"language_model.model.layers.8.self_attn.o_proj",
|
| 424 |
+
"language_model.model.layers.57.self_attn.k_proj",
|
| 425 |
+
"language_model.model.layers.41.self_attn.v_proj",
|
| 426 |
+
"language_model.model.layers.21.self_attn.v_proj",
|
| 427 |
+
"language_model.model.layers.34.self_attn.q_proj",
|
| 428 |
+
"language_model.model.layers.47.self_attn.v_proj",
|
| 429 |
+
"language_model.model.layers.32.mlp.gate_proj",
|
| 430 |
+
"language_model.model.layers.43.self_attn.o_proj",
|
| 431 |
+
"language_model.model.layers.21.self_attn.k_proj",
|
| 432 |
+
"language_model.model.layers.1.self_attn.v_proj",
|
| 433 |
+
"language_model.model.layers.8.mlp.up_proj",
|
| 434 |
+
"language_model.model.layers.20.mlp.up_proj",
|
| 435 |
+
"language_model.model.layers.23.mlp.gate_proj",
|
| 436 |
+
"language_model.model.layers.43.mlp.gate_proj",
|
| 437 |
+
"language_model.model.layers.54.self_attn.v_proj",
|
| 438 |
+
"language_model.model.layers.54.mlp.up_proj",
|
| 439 |
+
"language_model.model.layers.50.mlp.up_proj",
|
| 440 |
+
"language_model.model.layers.48.mlp.gate_proj",
|
| 441 |
+
"language_model.model.layers.35.mlp.gate_proj",
|
| 442 |
+
"language_model.model.layers.0.self_attn.k_proj",
|
| 443 |
+
"language_model.model.layers.47.self_attn.o_proj",
|
| 444 |
+
"language_model.model.layers.51.self_attn.k_proj",
|
| 445 |
+
"language_model.model.layers.58.self_attn.k_proj",
|
| 446 |
+
"language_model.model.layers.35.self_attn.o_proj",
|
| 447 |
+
"language_model.model.layers.55.self_attn.q_proj",
|
| 448 |
+
"language_model.model.layers.57.mlp.gate_proj",
|
| 449 |
+
"language_model.model.layers.6.mlp.up_proj",
|
| 450 |
+
"language_model.model.layers.7.mlp.up_proj",
|
| 451 |
+
"language_model.model.layers.34.self_attn.v_proj",
|
| 452 |
+
"language_model.model.layers.48.self_attn.o_proj",
|
| 453 |
+
"language_model.model.layers.36.self_attn.q_proj",
|
| 454 |
+
"language_model.model.layers.6.self_attn.v_proj",
|
| 455 |
+
"language_model.model.layers.53.mlp.down_proj",
|
| 456 |
+
"language_model.model.layers.49.mlp.gate_proj"
|
| 457 |
+
],
|
| 458 |
+
"task_type": "CAUSAL_LM",
|
| 459 |
+
"use_dora": false,
|
| 460 |
+
"use_rslora": false
|
| 461 |
+
}
|
checkpoint-100/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c86fba727c9adcec1269557790dda34620d02c7f4ab2af869cec45262164240e
|
| 3 |
+
size 1816396048
|
checkpoint-100/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
checkpoint-100/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
|
| 3 |
+
}
|
checkpoint-100/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b080671f0e69b9a84f544b65077293d663bf58eb0fa6a5d53ad9578e97d7cad6
|
| 3 |
+
size 3633264318
|
checkpoint-100/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_pan_and_scan": null,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Gemma3ImageProcessor",
|
| 13 |
+
"image_seq_length": 256,
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"pan_and_scan_max_num_crops": null,
|
| 20 |
+
"pan_and_scan_min_crop_size": null,
|
| 21 |
+
"pan_and_scan_min_ratio_to_activate": null,
|
| 22 |
+
"processor_class": "Gemma3Processor",
|
| 23 |
+
"resample": 2,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"height": 896,
|
| 27 |
+
"width": 896
|
| 28 |
+
}
|
| 29 |
+
}
|
checkpoint-100/processor_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_seq_length": 256,
|
| 3 |
+
"processor_class": "Gemma3Processor"
|
| 4 |
+
}
|
checkpoint-100/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69f50a692634404f2eebb2eab9f456865957578d752987bc52d843ac2a774366
|
| 3 |
+
size 14244
|
checkpoint-100/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5c461e660f4a5bcff7eb4fae4e538307f4a5201ca1dd3030274daac7a6afbc8
|
| 3 |
+
size 1064
|
checkpoint-100/special_tokens_map.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<end_of_turn>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"boi_token": "<start_of_image>",
|
| 12 |
+
"bos_token": {
|
| 13 |
+
"content": "<bos>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"eoi_token": "<end_of_image>",
|
| 20 |
+
"eos_token": {
|
| 21 |
+
"content": "<eos>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"image_token": "<image_soft_token>",
|
| 28 |
+
"pad_token": {
|
| 29 |
+
"content": "<pad>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"unk_token": {
|
| 36 |
+
"content": "<unk>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false
|
| 41 |
+
}
|
| 42 |
+
}
|
checkpoint-100/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
| 3 |
+
size 33384568
|
checkpoint-100/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
checkpoint-100/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-100/trainer_state.json
ADDED
|
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 6.666666666666667,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 100,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.3333333333333333,
|
| 14 |
+
"grad_norm": 79.55762481689453,
|
| 15 |
+
"learning_rate": 4.9786121534345265e-05,
|
| 16 |
+
"loss": 45.253,
|
| 17 |
+
"num_input_tokens_seen": 47512,
|
| 18 |
+
"step": 5
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.6666666666666666,
|
| 22 |
+
"grad_norm": 17.002260208129883,
|
| 23 |
+
"learning_rate": 4.914814565722671e-05,
|
| 24 |
+
"loss": 3.0254,
|
| 25 |
+
"num_input_tokens_seen": 94536,
|
| 26 |
+
"step": 10
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.0,
|
| 30 |
+
"grad_norm": 35.45703887939453,
|
| 31 |
+
"learning_rate": 4.8096988312782174e-05,
|
| 32 |
+
"loss": 3.1619,
|
| 33 |
+
"num_input_tokens_seen": 141336,
|
| 34 |
+
"step": 15
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 1.3333333333333333,
|
| 38 |
+
"grad_norm": 32.79413604736328,
|
| 39 |
+
"learning_rate": 4.665063509461097e-05,
|
| 40 |
+
"loss": 1.7871,
|
| 41 |
+
"num_input_tokens_seen": 188368,
|
| 42 |
+
"step": 20
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.6666666666666665,
|
| 46 |
+
"grad_norm": 57.80039978027344,
|
| 47 |
+
"learning_rate": 4.4833833507280884e-05,
|
| 48 |
+
"loss": 2.643,
|
| 49 |
+
"num_input_tokens_seen": 235128,
|
| 50 |
+
"step": 25
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.0,
|
| 54 |
+
"grad_norm": 8.35395622253418,
|
| 55 |
+
"learning_rate": 4.267766952966369e-05,
|
| 56 |
+
"loss": 2.3801,
|
| 57 |
+
"num_input_tokens_seen": 282672,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.3333333333333335,
|
| 62 |
+
"grad_norm": 13.160042762756348,
|
| 63 |
+
"learning_rate": 4.021903572521802e-05,
|
| 64 |
+
"loss": 1.6999,
|
| 65 |
+
"num_input_tokens_seen": 329864,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.6666666666666665,
|
| 70 |
+
"grad_norm": 31.193811416625977,
|
| 71 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 72 |
+
"loss": 1.5571,
|
| 73 |
+
"num_input_tokens_seen": 377952,
|
| 74 |
+
"step": 40
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 3.0,
|
| 78 |
+
"grad_norm": 57.113609313964844,
|
| 79 |
+
"learning_rate": 3.456708580912725e-05,
|
| 80 |
+
"loss": 1.7335,
|
| 81 |
+
"num_input_tokens_seen": 424008,
|
| 82 |
+
"step": 45
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 3.3333333333333335,
|
| 86 |
+
"grad_norm": 26.844955444335938,
|
| 87 |
+
"learning_rate": 3.147047612756302e-05,
|
| 88 |
+
"loss": 1.1859,
|
| 89 |
+
"num_input_tokens_seen": 471344,
|
| 90 |
+
"step": 50
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 3.6666666666666665,
|
| 94 |
+
"grad_norm": 19.28535270690918,
|
| 95 |
+
"learning_rate": 2.8263154805501297e-05,
|
| 96 |
+
"loss": 0.9846,
|
| 97 |
+
"num_input_tokens_seen": 517832,
|
| 98 |
+
"step": 55
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 4.0,
|
| 102 |
+
"grad_norm": 16.303863525390625,
|
| 103 |
+
"learning_rate": 2.5e-05,
|
| 104 |
+
"loss": 0.901,
|
| 105 |
+
"num_input_tokens_seen": 565344,
|
| 106 |
+
"step": 60
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 4.333333333333333,
|
| 110 |
+
"grad_norm": 38.277183532714844,
|
| 111 |
+
"learning_rate": 2.173684519449872e-05,
|
| 112 |
+
"loss": 0.4142,
|
| 113 |
+
"num_input_tokens_seen": 612336,
|
| 114 |
+
"step": 65
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.666666666666667,
|
| 118 |
+
"grad_norm": 16.51125144958496,
|
| 119 |
+
"learning_rate": 1.852952387243698e-05,
|
| 120 |
+
"loss": 0.6221,
|
| 121 |
+
"num_input_tokens_seen": 659560,
|
| 122 |
+
"step": 70
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 5.0,
|
| 126 |
+
"grad_norm": 55.58554458618164,
|
| 127 |
+
"learning_rate": 1.5432914190872757e-05,
|
| 128 |
+
"loss": 0.7115,
|
| 129 |
+
"num_input_tokens_seen": 706680,
|
| 130 |
+
"step": 75
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 5.333333333333333,
|
| 134 |
+
"grad_norm": 7.757297992706299,
|
| 135 |
+
"learning_rate": 1.2500000000000006e-05,
|
| 136 |
+
"loss": 0.1582,
|
| 137 |
+
"num_input_tokens_seen": 754048,
|
| 138 |
+
"step": 80
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 5.666666666666667,
|
| 142 |
+
"grad_norm": 6.108384609222412,
|
| 143 |
+
"learning_rate": 9.780964274781984e-06,
|
| 144 |
+
"loss": 0.1891,
|
| 145 |
+
"num_input_tokens_seen": 800984,
|
| 146 |
+
"step": 85
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 6.0,
|
| 150 |
+
"grad_norm": 0.9440665245056152,
|
| 151 |
+
"learning_rate": 7.3223304703363135e-06,
|
| 152 |
+
"loss": 0.2214,
|
| 153 |
+
"num_input_tokens_seen": 848016,
|
| 154 |
+
"step": 90
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 6.333333333333333,
|
| 158 |
+
"grad_norm": 0.9317387342453003,
|
| 159 |
+
"learning_rate": 5.166166492719124e-06,
|
| 160 |
+
"loss": 0.0135,
|
| 161 |
+
"num_input_tokens_seen": 895040,
|
| 162 |
+
"step": 95
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 6.666666666666667,
|
| 166 |
+
"grad_norm": 0.1581590473651886,
|
| 167 |
+
"learning_rate": 3.3493649053890326e-06,
|
| 168 |
+
"loss": 0.0055,
|
| 169 |
+
"num_input_tokens_seen": 941960,
|
| 170 |
+
"step": 100
|
| 171 |
+
}
|
| 172 |
+
],
|
| 173 |
+
"logging_steps": 5,
|
| 174 |
+
"max_steps": 120,
|
| 175 |
+
"num_input_tokens_seen": 941960,
|
| 176 |
+
"num_train_epochs": 8,
|
| 177 |
+
"save_steps": 100,
|
| 178 |
+
"stateful_callbacks": {
|
| 179 |
+
"TrainerControl": {
|
| 180 |
+
"args": {
|
| 181 |
+
"should_epoch_stop": false,
|
| 182 |
+
"should_evaluate": false,
|
| 183 |
+
"should_log": false,
|
| 184 |
+
"should_save": true,
|
| 185 |
+
"should_training_stop": false
|
| 186 |
+
},
|
| 187 |
+
"attributes": {}
|
| 188 |
+
}
|
| 189 |
+
},
|
| 190 |
+
"total_flos": 1.4961409162866816e+17,
|
| 191 |
+
"train_batch_size": 1,
|
| 192 |
+
"trial_name": null,
|
| 193 |
+
"trial_params": null
|
| 194 |
+
}
|
checkpoint-100/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ef6c21cfca5f2537c2c77045da591ab94a70a2c3c6f8193b51ea235f03d35bf
|
| 3 |
+
size 5688
|
checkpoint-120/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/gemma-3-27b-it
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
checkpoint-120/adapter_config.json
ADDED
|
@@ -0,0 +1,461 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "google/gemma-3-27b-it",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 128,
|
| 14 |
+
"lora_dropout": 0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"language_model.model.layers.18.mlp.up_proj",
|
| 24 |
+
"language_model.model.layers.14.self_attn.q_proj",
|
| 25 |
+
"language_model.model.layers.23.mlp.down_proj",
|
| 26 |
+
"language_model.model.layers.5.self_attn.q_proj",
|
| 27 |
+
"language_model.model.layers.48.self_attn.k_proj",
|
| 28 |
+
"language_model.model.layers.29.self_attn.v_proj",
|
| 29 |
+
"language_model.model.layers.39.self_attn.v_proj",
|
| 30 |
+
"language_model.model.layers.5.self_attn.v_proj",
|
| 31 |
+
"language_model.model.layers.60.mlp.gate_proj",
|
| 32 |
+
"language_model.model.layers.17.self_attn.o_proj",
|
| 33 |
+
"language_model.model.layers.60.mlp.down_proj",
|
| 34 |
+
"language_model.model.layers.33.mlp.up_proj",
|
| 35 |
+
"language_model.model.layers.53.self_attn.q_proj",
|
| 36 |
+
"language_model.model.layers.27.mlp.down_proj",
|
| 37 |
+
"language_model.model.layers.57.self_attn.v_proj",
|
| 38 |
+
"language_model.model.layers.26.mlp.up_proj",
|
| 39 |
+
"language_model.model.layers.10.mlp.gate_proj",
|
| 40 |
+
"language_model.model.layers.23.mlp.up_proj",
|
| 41 |
+
"language_model.model.layers.57.self_attn.q_proj",
|
| 42 |
+
"language_model.model.layers.57.mlp.up_proj",
|
| 43 |
+
"language_model.model.layers.39.mlp.gate_proj",
|
| 44 |
+
"language_model.model.layers.26.mlp.down_proj",
|
| 45 |
+
"language_model.model.layers.11.mlp.up_proj",
|
| 46 |
+
"language_model.model.layers.25.mlp.up_proj",
|
| 47 |
+
"language_model.model.layers.6.mlp.gate_proj",
|
| 48 |
+
"language_model.model.layers.36.mlp.gate_proj",
|
| 49 |
+
"language_model.model.layers.2.self_attn.o_proj",
|
| 50 |
+
"language_model.model.layers.30.self_attn.o_proj",
|
| 51 |
+
"language_model.model.layers.4.mlp.gate_proj",
|
| 52 |
+
"language_model.model.layers.13.mlp.up_proj",
|
| 53 |
+
"language_model.model.layers.52.mlp.down_proj",
|
| 54 |
+
"language_model.model.layers.4.mlp.up_proj",
|
| 55 |
+
"language_model.model.layers.32.self_attn.v_proj",
|
| 56 |
+
"language_model.model.layers.1.self_attn.o_proj",
|
| 57 |
+
"language_model.model.layers.22.mlp.down_proj",
|
| 58 |
+
"language_model.model.layers.45.mlp.down_proj",
|
| 59 |
+
"language_model.model.layers.46.self_attn.o_proj",
|
| 60 |
+
"language_model.model.layers.38.self_attn.o_proj",
|
| 61 |
+
"language_model.model.layers.23.self_attn.q_proj",
|
| 62 |
+
"language_model.model.layers.46.mlp.up_proj",
|
| 63 |
+
"language_model.model.layers.49.mlp.down_proj",
|
| 64 |
+
"language_model.model.layers.40.self_attn.k_proj",
|
| 65 |
+
"language_model.model.layers.24.self_attn.q_proj",
|
| 66 |
+
"language_model.model.layers.9.self_attn.o_proj",
|
| 67 |
+
"language_model.model.layers.37.mlp.gate_proj",
|
| 68 |
+
"language_model.model.layers.36.self_attn.k_proj",
|
| 69 |
+
"language_model.model.layers.49.self_attn.k_proj",
|
| 70 |
+
"language_model.model.layers.24.self_attn.v_proj",
|
| 71 |
+
"language_model.model.layers.1.mlp.down_proj",
|
| 72 |
+
"language_model.model.layers.10.mlp.down_proj",
|
| 73 |
+
"language_model.model.layers.61.mlp.gate_proj",
|
| 74 |
+
"language_model.model.layers.34.self_attn.o_proj",
|
| 75 |
+
"language_model.model.layers.9.mlp.up_proj",
|
| 76 |
+
"language_model.model.layers.59.self_attn.v_proj",
|
| 77 |
+
"language_model.model.layers.30.self_attn.q_proj",
|
| 78 |
+
"language_model.model.layers.44.mlp.gate_proj",
|
| 79 |
+
"language_model.model.layers.46.mlp.down_proj",
|
| 80 |
+
"language_model.model.layers.46.self_attn.k_proj",
|
| 81 |
+
"language_model.model.layers.28.self_attn.v_proj",
|
| 82 |
+
"language_model.model.layers.58.self_attn.o_proj",
|
| 83 |
+
"language_model.model.layers.13.self_attn.o_proj",
|
| 84 |
+
"language_model.model.layers.24.mlp.up_proj",
|
| 85 |
+
"language_model.model.layers.0.self_attn.q_proj",
|
| 86 |
+
"language_model.model.layers.58.mlp.up_proj",
|
| 87 |
+
"language_model.model.layers.12.mlp.down_proj",
|
| 88 |
+
"language_model.model.layers.43.mlp.up_proj",
|
| 89 |
+
"language_model.model.layers.44.self_attn.k_proj",
|
| 90 |
+
"language_model.model.layers.17.self_attn.q_proj",
|
| 91 |
+
"language_model.model.layers.59.mlp.up_proj",
|
| 92 |
+
"language_model.model.layers.50.mlp.down_proj",
|
| 93 |
+
"language_model.model.layers.24.self_attn.k_proj",
|
| 94 |
+
"language_model.model.layers.59.self_attn.k_proj",
|
| 95 |
+
"language_model.model.layers.1.mlp.up_proj",
|
| 96 |
+
"language_model.model.layers.58.self_attn.q_proj",
|
| 97 |
+
"language_model.model.layers.51.mlp.gate_proj",
|
| 98 |
+
"language_model.model.layers.4.self_attn.v_proj",
|
| 99 |
+
"language_model.model.layers.45.mlp.gate_proj",
|
| 100 |
+
"language_model.model.layers.8.mlp.gate_proj",
|
| 101 |
+
"language_model.model.layers.43.self_attn.v_proj",
|
| 102 |
+
"language_model.model.layers.51.self_attn.v_proj",
|
| 103 |
+
"language_model.model.layers.37.self_attn.v_proj",
|
| 104 |
+
"language_model.model.layers.51.self_attn.q_proj",
|
| 105 |
+
"language_model.model.layers.51.self_attn.o_proj",
|
| 106 |
+
"language_model.model.layers.33.mlp.down_proj",
|
| 107 |
+
"language_model.model.layers.44.self_attn.v_proj",
|
| 108 |
+
"language_model.model.layers.18.self_attn.o_proj",
|
| 109 |
+
"language_model.model.layers.14.self_attn.k_proj",
|
| 110 |
+
"language_model.model.layers.55.self_attn.k_proj",
|
| 111 |
+
"language_model.model.layers.10.self_attn.q_proj",
|
| 112 |
+
"language_model.model.layers.34.mlp.up_proj",
|
| 113 |
+
"language_model.model.layers.27.self_attn.v_proj",
|
| 114 |
+
"language_model.model.layers.20.self_attn.o_proj",
|
| 115 |
+
"language_model.model.layers.33.self_attn.k_proj",
|
| 116 |
+
"language_model.model.layers.44.mlp.up_proj",
|
| 117 |
+
"language_model.model.layers.3.self_attn.o_proj",
|
| 118 |
+
"language_model.model.layers.15.mlp.up_proj",
|
| 119 |
+
"language_model.model.layers.17.mlp.gate_proj",
|
| 120 |
+
"language_model.model.layers.17.mlp.up_proj",
|
| 121 |
+
"language_model.model.layers.55.mlp.up_proj",
|
| 122 |
+
"language_model.model.layers.0.self_attn.v_proj",
|
| 123 |
+
"language_model.model.layers.56.self_attn.v_proj",
|
| 124 |
+
"language_model.model.layers.39.self_attn.k_proj",
|
| 125 |
+
"language_model.model.layers.31.self_attn.k_proj",
|
| 126 |
+
"language_model.model.layers.50.self_attn.v_proj",
|
| 127 |
+
"language_model.model.layers.8.self_attn.q_proj",
|
| 128 |
+
"language_model.model.layers.29.self_attn.k_proj",
|
| 129 |
+
"language_model.model.layers.28.self_attn.q_proj",
|
| 130 |
+
"language_model.model.layers.37.self_attn.k_proj",
|
| 131 |
+
"language_model.model.layers.8.self_attn.k_proj",
|
| 132 |
+
"language_model.model.layers.60.self_attn.q_proj",
|
| 133 |
+
"language_model.model.layers.13.self_attn.v_proj",
|
| 134 |
+
"language_model.model.layers.18.self_attn.v_proj",
|
| 135 |
+
"language_model.model.layers.35.mlp.up_proj",
|
| 136 |
+
"language_model.model.layers.56.self_attn.k_proj",
|
| 137 |
+
"language_model.model.layers.27.self_attn.o_proj",
|
| 138 |
+
"language_model.model.layers.40.self_attn.q_proj",
|
| 139 |
+
"language_model.model.layers.25.mlp.down_proj",
|
| 140 |
+
"language_model.model.layers.50.self_attn.k_proj",
|
| 141 |
+
"language_model.model.layers.39.mlp.up_proj",
|
| 142 |
+
"language_model.model.layers.13.mlp.down_proj",
|
| 143 |
+
"language_model.model.layers.39.self_attn.o_proj",
|
| 144 |
+
"language_model.model.layers.56.mlp.down_proj",
|
| 145 |
+
"language_model.model.layers.13.self_attn.k_proj",
|
| 146 |
+
"language_model.model.layers.10.self_attn.k_proj",
|
| 147 |
+
"language_model.model.layers.42.self_attn.v_proj",
|
| 148 |
+
"language_model.model.layers.3.mlp.down_proj",
|
| 149 |
+
"language_model.model.layers.9.self_attn.q_proj",
|
| 150 |
+
"language_model.model.layers.36.mlp.up_proj",
|
| 151 |
+
"language_model.model.layers.29.mlp.down_proj",
|
| 152 |
+
"language_model.model.layers.51.mlp.down_proj",
|
| 153 |
+
"language_model.model.layers.36.self_attn.o_proj",
|
| 154 |
+
"language_model.model.layers.7.mlp.gate_proj",
|
| 155 |
+
"language_model.model.layers.31.mlp.gate_proj",
|
| 156 |
+
"language_model.model.layers.38.mlp.gate_proj",
|
| 157 |
+
"language_model.model.layers.55.mlp.down_proj",
|
| 158 |
+
"language_model.model.layers.30.mlp.down_proj",
|
| 159 |
+
"language_model.model.layers.54.mlp.gate_proj",
|
| 160 |
+
"language_model.model.layers.42.self_attn.q_proj",
|
| 161 |
+
"language_model.model.layers.0.mlp.down_proj",
|
| 162 |
+
"language_model.model.layers.32.self_attn.o_proj",
|
| 163 |
+
"language_model.model.layers.61.self_attn.q_proj",
|
| 164 |
+
"language_model.model.layers.55.self_attn.o_proj",
|
| 165 |
+
"language_model.model.layers.27.self_attn.q_proj",
|
| 166 |
+
"language_model.model.layers.41.mlp.up_proj",
|
| 167 |
+
"language_model.model.layers.2.mlp.down_proj",
|
| 168 |
+
"language_model.model.layers.48.self_attn.v_proj",
|
| 169 |
+
"language_model.model.layers.55.mlp.gate_proj",
|
| 170 |
+
"language_model.model.layers.5.self_attn.o_proj",
|
| 171 |
+
"language_model.model.layers.53.mlp.gate_proj",
|
| 172 |
+
"language_model.model.layers.26.mlp.gate_proj",
|
| 173 |
+
"language_model.model.layers.56.mlp.gate_proj",
|
| 174 |
+
"language_model.model.layers.53.mlp.up_proj",
|
| 175 |
+
"language_model.model.layers.16.self_attn.k_proj",
|
| 176 |
+
"language_model.model.layers.43.mlp.down_proj",
|
| 177 |
+
"language_model.model.layers.1.self_attn.k_proj",
|
| 178 |
+
"language_model.model.layers.19.self_attn.q_proj",
|
| 179 |
+
"language_model.model.layers.3.self_attn.k_proj",
|
| 180 |
+
"language_model.model.layers.21.self_attn.q_proj",
|
| 181 |
+
"language_model.model.layers.15.self_attn.o_proj",
|
| 182 |
+
"language_model.model.layers.57.self_attn.o_proj",
|
| 183 |
+
"language_model.model.layers.49.self_attn.o_proj",
|
| 184 |
+
"language_model.model.layers.50.self_attn.q_proj",
|
| 185 |
+
"language_model.model.layers.58.mlp.down_proj",
|
| 186 |
+
"language_model.model.layers.26.self_attn.k_proj",
|
| 187 |
+
"language_model.model.layers.38.self_attn.v_proj",
|
| 188 |
+
"language_model.model.layers.19.self_attn.v_proj",
|
| 189 |
+
"language_model.model.layers.19.mlp.up_proj",
|
| 190 |
+
"language_model.model.layers.3.self_attn.q_proj",
|
| 191 |
+
"language_model.model.layers.7.mlp.down_proj",
|
| 192 |
+
"language_model.model.layers.9.self_attn.k_proj",
|
| 193 |
+
"language_model.model.layers.29.mlp.up_proj",
|
| 194 |
+
"language_model.model.layers.49.self_attn.q_proj",
|
| 195 |
+
"language_model.model.layers.13.self_attn.q_proj",
|
| 196 |
+
"language_model.model.layers.59.self_attn.o_proj",
|
| 197 |
+
"language_model.model.layers.3.mlp.up_proj",
|
| 198 |
+
"language_model.model.layers.8.self_attn.v_proj",
|
| 199 |
+
"language_model.model.layers.0.self_attn.o_proj",
|
| 200 |
+
"language_model.model.layers.2.mlp.gate_proj",
|
| 201 |
+
"language_model.model.layers.16.self_attn.v_proj",
|
| 202 |
+
"language_model.model.layers.10.self_attn.v_proj",
|
| 203 |
+
"language_model.model.layers.16.mlp.down_proj",
|
| 204 |
+
"language_model.model.layers.20.mlp.gate_proj",
|
| 205 |
+
"language_model.model.layers.55.self_attn.v_proj",
|
| 206 |
+
"language_model.model.layers.49.self_attn.v_proj",
|
| 207 |
+
"language_model.model.layers.17.mlp.down_proj",
|
| 208 |
+
"language_model.model.layers.18.mlp.down_proj",
|
| 209 |
+
"language_model.model.layers.57.mlp.down_proj",
|
| 210 |
+
"language_model.model.layers.40.mlp.down_proj",
|
| 211 |
+
"language_model.model.layers.27.mlp.gate_proj",
|
| 212 |
+
"language_model.model.layers.17.self_attn.k_proj",
|
| 213 |
+
"language_model.model.layers.40.self_attn.o_proj",
|
| 214 |
+
"language_model.model.layers.12.mlp.gate_proj",
|
| 215 |
+
"language_model.model.layers.18.self_attn.q_proj",
|
| 216 |
+
"language_model.model.layers.54.self_attn.q_proj",
|
| 217 |
+
"language_model.model.layers.37.self_attn.o_proj",
|
| 218 |
+
"language_model.model.layers.20.self_attn.q_proj",
|
| 219 |
+
"language_model.model.layers.31.mlp.down_proj",
|
| 220 |
+
"language_model.model.layers.10.mlp.up_proj",
|
| 221 |
+
"language_model.model.layers.7.self_attn.k_proj",
|
| 222 |
+
"language_model.model.layers.1.self_attn.q_proj",
|
| 223 |
+
"language_model.model.layers.5.mlp.gate_proj",
|
| 224 |
+
"language_model.model.layers.61.mlp.down_proj",
|
| 225 |
+
"language_model.model.layers.46.self_attn.v_proj",
|
| 226 |
+
"language_model.model.layers.12.self_attn.v_proj",
|
| 227 |
+
"language_model.model.layers.54.self_attn.o_proj",
|
| 228 |
+
"language_model.model.layers.29.self_attn.o_proj",
|
| 229 |
+
"language_model.model.layers.61.self_attn.k_proj",
|
| 230 |
+
"language_model.model.layers.61.mlp.up_proj",
|
| 231 |
+
"language_model.model.layers.12.self_attn.o_proj",
|
| 232 |
+
"language_model.model.layers.5.mlp.up_proj",
|
| 233 |
+
"language_model.model.layers.54.mlp.down_proj",
|
| 234 |
+
"language_model.model.layers.53.self_attn.v_proj",
|
| 235 |
+
"language_model.model.layers.38.self_attn.k_proj",
|
| 236 |
+
"language_model.model.layers.42.self_attn.o_proj",
|
| 237 |
+
"language_model.model.layers.47.mlp.gate_proj",
|
| 238 |
+
"language_model.model.layers.25.mlp.gate_proj",
|
| 239 |
+
"language_model.model.layers.38.self_attn.q_proj",
|
| 240 |
+
"language_model.model.layers.11.self_attn.k_proj",
|
| 241 |
+
"language_model.model.layers.3.self_attn.v_proj",
|
| 242 |
+
"language_model.model.layers.61.self_attn.v_proj",
|
| 243 |
+
"language_model.model.layers.23.self_attn.k_proj",
|
| 244 |
+
"language_model.model.layers.16.self_attn.o_proj",
|
| 245 |
+
"language_model.model.layers.25.self_attn.q_proj",
|
| 246 |
+
"language_model.model.layers.37.mlp.up_proj",
|
| 247 |
+
"language_model.model.layers.13.mlp.gate_proj",
|
| 248 |
+
"language_model.model.layers.24.self_attn.o_proj",
|
| 249 |
+
"language_model.model.layers.35.self_attn.q_proj",
|
| 250 |
+
"language_model.model.layers.59.self_attn.q_proj",
|
| 251 |
+
"language_model.model.layers.17.self_attn.v_proj",
|
| 252 |
+
"language_model.model.layers.15.mlp.down_proj",
|
| 253 |
+
"language_model.model.layers.48.self_attn.q_proj",
|
| 254 |
+
"language_model.model.layers.61.self_attn.o_proj",
|
| 255 |
+
"language_model.model.layers.30.self_attn.k_proj",
|
| 256 |
+
"language_model.model.layers.21.mlp.up_proj",
|
| 257 |
+
"language_model.model.layers.44.mlp.down_proj",
|
| 258 |
+
"language_model.model.layers.12.self_attn.k_proj",
|
| 259 |
+
"language_model.model.layers.31.self_attn.q_proj",
|
| 260 |
+
"language_model.model.layers.31.self_attn.v_proj",
|
| 261 |
+
"language_model.model.layers.1.mlp.gate_proj",
|
| 262 |
+
"language_model.model.layers.22.self_attn.o_proj",
|
| 263 |
+
"language_model.model.layers.47.mlp.down_proj",
|
| 264 |
+
"language_model.model.layers.4.self_attn.k_proj",
|
| 265 |
+
"language_model.model.layers.25.self_attn.k_proj",
|
| 266 |
+
"language_model.model.layers.41.self_attn.k_proj",
|
| 267 |
+
"language_model.model.layers.33.self_attn.v_proj",
|
| 268 |
+
"language_model.model.layers.26.self_attn.q_proj",
|
| 269 |
+
"language_model.model.layers.9.mlp.down_proj",
|
| 270 |
+
"language_model.model.layers.45.self_attn.k_proj",
|
| 271 |
+
"language_model.model.layers.38.mlp.up_proj",
|
| 272 |
+
"language_model.model.layers.0.mlp.up_proj",
|
| 273 |
+
"language_model.model.layers.59.mlp.gate_proj",
|
| 274 |
+
"language_model.model.layers.5.self_attn.k_proj",
|
| 275 |
+
"language_model.model.layers.10.self_attn.o_proj",
|
| 276 |
+
"language_model.model.layers.60.mlp.up_proj",
|
| 277 |
+
"language_model.model.layers.26.self_attn.v_proj",
|
| 278 |
+
"language_model.model.layers.40.mlp.gate_proj",
|
| 279 |
+
"language_model.model.layers.60.self_attn.o_proj",
|
| 280 |
+
"language_model.model.layers.0.mlp.gate_proj",
|
| 281 |
+
"language_model.model.layers.39.mlp.down_proj",
|
| 282 |
+
"language_model.model.layers.28.self_attn.k_proj",
|
| 283 |
+
"language_model.model.layers.19.self_attn.o_proj",
|
| 284 |
+
"language_model.model.layers.43.self_attn.k_proj",
|
| 285 |
+
"language_model.model.layers.11.self_attn.q_proj",
|
| 286 |
+
"language_model.model.layers.41.mlp.gate_proj",
|
| 287 |
+
"language_model.model.layers.35.mlp.down_proj",
|
| 288 |
+
"language_model.model.layers.52.self_attn.o_proj",
|
| 289 |
+
"language_model.model.layers.32.self_attn.q_proj",
|
| 290 |
+
"language_model.model.layers.30.mlp.up_proj",
|
| 291 |
+
"language_model.model.layers.47.self_attn.q_proj",
|
| 292 |
+
"language_model.model.layers.21.mlp.down_proj",
|
| 293 |
+
"language_model.model.layers.24.mlp.gate_proj",
|
| 294 |
+
"language_model.model.layers.53.self_attn.o_proj",
|
| 295 |
+
"language_model.model.layers.42.mlp.down_proj",
|
| 296 |
+
"language_model.model.layers.44.self_attn.o_proj",
|
| 297 |
+
"language_model.model.layers.24.mlp.down_proj",
|
| 298 |
+
"language_model.model.layers.29.self_attn.q_proj",
|
| 299 |
+
"language_model.model.layers.49.mlp.up_proj",
|
| 300 |
+
"language_model.model.layers.4.self_attn.q_proj",
|
| 301 |
+
"language_model.model.layers.56.mlp.up_proj",
|
| 302 |
+
"language_model.model.layers.8.mlp.down_proj",
|
| 303 |
+
"language_model.model.layers.25.self_attn.v_proj",
|
| 304 |
+
"language_model.model.layers.37.self_attn.q_proj",
|
| 305 |
+
"language_model.model.layers.6.self_attn.k_proj",
|
| 306 |
+
"language_model.model.layers.14.self_attn.o_proj",
|
| 307 |
+
"language_model.model.layers.60.self_attn.k_proj",
|
| 308 |
+
"language_model.model.layers.2.mlp.up_proj",
|
| 309 |
+
"language_model.model.layers.34.mlp.gate_proj",
|
| 310 |
+
"language_model.model.layers.52.mlp.gate_proj",
|
| 311 |
+
"language_model.model.layers.6.mlp.down_proj",
|
| 312 |
+
"language_model.model.layers.45.self_attn.q_proj",
|
| 313 |
+
"language_model.model.layers.41.self_attn.q_proj",
|
| 314 |
+
"language_model.model.layers.52.self_attn.k_proj",
|
| 315 |
+
"language_model.model.layers.36.self_attn.v_proj",
|
| 316 |
+
"language_model.model.layers.28.mlp.down_proj",
|
| 317 |
+
"language_model.model.layers.15.self_attn.v_proj",
|
| 318 |
+
"language_model.model.layers.11.self_attn.o_proj",
|
| 319 |
+
"language_model.model.layers.29.mlp.gate_proj",
|
| 320 |
+
"language_model.model.layers.42.self_attn.k_proj",
|
| 321 |
+
"language_model.model.layers.52.mlp.up_proj",
|
| 322 |
+
"language_model.model.layers.22.self_attn.k_proj",
|
| 323 |
+
"language_model.model.layers.14.mlp.down_proj",
|
| 324 |
+
"language_model.model.layers.4.mlp.down_proj",
|
| 325 |
+
"language_model.model.layers.35.self_attn.k_proj",
|
| 326 |
+
"language_model.model.layers.52.self_attn.q_proj",
|
| 327 |
+
"language_model.model.layers.22.self_attn.q_proj",
|
| 328 |
+
"language_model.model.layers.58.mlp.gate_proj",
|
| 329 |
+
"language_model.model.layers.14.mlp.gate_proj",
|
| 330 |
+
"language_model.model.layers.47.self_attn.k_proj",
|
| 331 |
+
"language_model.model.layers.39.self_attn.q_proj",
|
| 332 |
+
"language_model.model.layers.42.mlp.up_proj",
|
| 333 |
+
"language_model.model.layers.34.mlp.down_proj",
|
| 334 |
+
"language_model.model.layers.30.self_attn.v_proj",
|
| 335 |
+
"language_model.model.layers.56.self_attn.o_proj",
|
| 336 |
+
"language_model.model.layers.25.self_attn.o_proj",
|
| 337 |
+
"language_model.model.layers.45.mlp.up_proj",
|
| 338 |
+
"language_model.model.layers.48.mlp.down_proj",
|
| 339 |
+
"language_model.model.layers.7.self_attn.o_proj",
|
| 340 |
+
"language_model.model.layers.18.self_attn.k_proj",
|
| 341 |
+
"language_model.model.layers.14.self_attn.v_proj",
|
| 342 |
+
"language_model.model.layers.40.self_attn.v_proj",
|
| 343 |
+
"language_model.model.layers.22.self_attn.v_proj",
|
| 344 |
+
"language_model.model.layers.7.self_attn.q_proj",
|
| 345 |
+
"language_model.model.layers.46.mlp.gate_proj",
|
| 346 |
+
"language_model.model.layers.56.self_attn.q_proj",
|
| 347 |
+
"language_model.model.layers.28.mlp.up_proj",
|
| 348 |
+
"language_model.model.layers.50.mlp.gate_proj",
|
| 349 |
+
"language_model.model.layers.23.self_attn.v_proj",
|
| 350 |
+
"language_model.model.layers.15.self_attn.q_proj",
|
| 351 |
+
"language_model.model.layers.9.mlp.gate_proj",
|
| 352 |
+
"language_model.model.layers.47.mlp.up_proj",
|
| 353 |
+
"language_model.model.layers.6.self_attn.o_proj",
|
| 354 |
+
"language_model.model.layers.12.self_attn.q_proj",
|
| 355 |
+
"language_model.model.layers.20.self_attn.k_proj",
|
| 356 |
+
"language_model.model.layers.51.mlp.up_proj",
|
| 357 |
+
"language_model.model.layers.58.self_attn.v_proj",
|
| 358 |
+
"language_model.model.layers.22.mlp.gate_proj",
|
| 359 |
+
"language_model.model.layers.14.mlp.up_proj",
|
| 360 |
+
"language_model.model.layers.33.self_attn.o_proj",
|
| 361 |
+
"language_model.model.layers.11.mlp.down_proj",
|
| 362 |
+
"language_model.model.layers.16.mlp.gate_proj",
|
| 363 |
+
"language_model.model.layers.40.mlp.up_proj",
|
| 364 |
+
"language_model.model.layers.60.self_attn.v_proj",
|
| 365 |
+
"language_model.model.layers.2.self_attn.k_proj",
|
| 366 |
+
"language_model.model.layers.26.self_attn.o_proj",
|
| 367 |
+
"language_model.model.layers.12.mlp.up_proj",
|
| 368 |
+
"language_model.model.layers.28.self_attn.o_proj",
|
| 369 |
+
"language_model.model.layers.32.mlp.up_proj",
|
| 370 |
+
"language_model.model.layers.45.self_attn.o_proj",
|
| 371 |
+
"language_model.model.layers.28.mlp.gate_proj",
|
| 372 |
+
"language_model.model.layers.11.mlp.gate_proj",
|
| 373 |
+
"language_model.model.layers.11.self_attn.v_proj",
|
| 374 |
+
"language_model.model.layers.2.self_attn.v_proj",
|
| 375 |
+
"language_model.model.layers.9.self_attn.v_proj",
|
| 376 |
+
"language_model.model.layers.19.self_attn.k_proj",
|
| 377 |
+
"language_model.model.layers.32.self_attn.k_proj",
|
| 378 |
+
"language_model.model.layers.43.self_attn.q_proj",
|
| 379 |
+
"language_model.model.layers.21.mlp.gate_proj",
|
| 380 |
+
"language_model.model.layers.45.self_attn.v_proj",
|
| 381 |
+
"language_model.model.layers.41.mlp.down_proj",
|
| 382 |
+
"language_model.model.layers.36.mlp.down_proj",
|
| 383 |
+
"language_model.model.layers.53.self_attn.k_proj",
|
| 384 |
+
"language_model.model.layers.16.self_attn.q_proj",
|
| 385 |
+
"language_model.model.layers.3.mlp.gate_proj",
|
| 386 |
+
"language_model.model.layers.15.self_attn.k_proj",
|
| 387 |
+
"language_model.model.layers.33.mlp.gate_proj",
|
| 388 |
+
"language_model.model.layers.48.mlp.up_proj",
|
| 389 |
+
"language_model.model.layers.33.self_attn.q_proj",
|
| 390 |
+
"language_model.model.layers.54.self_attn.k_proj",
|
| 391 |
+
"language_model.model.layers.7.self_attn.v_proj",
|
| 392 |
+
"language_model.model.layers.5.mlp.down_proj",
|
| 393 |
+
"language_model.model.layers.50.self_attn.o_proj",
|
| 394 |
+
"language_model.model.layers.21.self_attn.o_proj",
|
| 395 |
+
"language_model.model.layers.2.self_attn.q_proj",
|
| 396 |
+
"language_model.model.layers.27.self_attn.k_proj",
|
| 397 |
+
"language_model.model.layers.46.self_attn.q_proj",
|
| 398 |
+
"language_model.model.layers.20.self_attn.v_proj",
|
| 399 |
+
"language_model.model.layers.34.self_attn.k_proj",
|
| 400 |
+
"language_model.model.layers.18.mlp.gate_proj",
|
| 401 |
+
"language_model.model.layers.35.self_attn.v_proj",
|
| 402 |
+
"language_model.model.layers.32.mlp.down_proj",
|
| 403 |
+
"language_model.model.layers.6.self_attn.q_proj",
|
| 404 |
+
"language_model.model.layers.20.mlp.down_proj",
|
| 405 |
+
"language_model.model.layers.27.mlp.up_proj",
|
| 406 |
+
"language_model.model.layers.31.self_attn.o_proj",
|
| 407 |
+
"language_model.model.layers.59.mlp.down_proj",
|
| 408 |
+
"language_model.model.layers.4.self_attn.o_proj",
|
| 409 |
+
"language_model.model.layers.15.mlp.gate_proj",
|
| 410 |
+
"language_model.model.layers.44.self_attn.q_proj",
|
| 411 |
+
"language_model.model.layers.31.mlp.up_proj",
|
| 412 |
+
"language_model.model.layers.30.mlp.gate_proj",
|
| 413 |
+
"language_model.model.layers.42.mlp.gate_proj",
|
| 414 |
+
"language_model.model.layers.19.mlp.gate_proj",
|
| 415 |
+
"language_model.model.layers.38.mlp.down_proj",
|
| 416 |
+
"language_model.model.layers.23.self_attn.o_proj",
|
| 417 |
+
"language_model.model.layers.16.mlp.up_proj",
|
| 418 |
+
"language_model.model.layers.52.self_attn.v_proj",
|
| 419 |
+
"language_model.model.layers.22.mlp.up_proj",
|
| 420 |
+
"language_model.model.layers.41.self_attn.o_proj",
|
| 421 |
+
"language_model.model.layers.19.mlp.down_proj",
|
| 422 |
+
"language_model.model.layers.37.mlp.down_proj",
|
| 423 |
+
"language_model.model.layers.8.self_attn.o_proj",
|
| 424 |
+
"language_model.model.layers.57.self_attn.k_proj",
|
| 425 |
+
"language_model.model.layers.41.self_attn.v_proj",
|
| 426 |
+
"language_model.model.layers.21.self_attn.v_proj",
|
| 427 |
+
"language_model.model.layers.34.self_attn.q_proj",
|
| 428 |
+
"language_model.model.layers.47.self_attn.v_proj",
|
| 429 |
+
"language_model.model.layers.32.mlp.gate_proj",
|
| 430 |
+
"language_model.model.layers.43.self_attn.o_proj",
|
| 431 |
+
"language_model.model.layers.21.self_attn.k_proj",
|
| 432 |
+
"language_model.model.layers.1.self_attn.v_proj",
|
| 433 |
+
"language_model.model.layers.8.mlp.up_proj",
|
| 434 |
+
"language_model.model.layers.20.mlp.up_proj",
|
| 435 |
+
"language_model.model.layers.23.mlp.gate_proj",
|
| 436 |
+
"language_model.model.layers.43.mlp.gate_proj",
|
| 437 |
+
"language_model.model.layers.54.self_attn.v_proj",
|
| 438 |
+
"language_model.model.layers.54.mlp.up_proj",
|
| 439 |
+
"language_model.model.layers.50.mlp.up_proj",
|
| 440 |
+
"language_model.model.layers.48.mlp.gate_proj",
|
| 441 |
+
"language_model.model.layers.35.mlp.gate_proj",
|
| 442 |
+
"language_model.model.layers.0.self_attn.k_proj",
|
| 443 |
+
"language_model.model.layers.47.self_attn.o_proj",
|
| 444 |
+
"language_model.model.layers.51.self_attn.k_proj",
|
| 445 |
+
"language_model.model.layers.58.self_attn.k_proj",
|
| 446 |
+
"language_model.model.layers.35.self_attn.o_proj",
|
| 447 |
+
"language_model.model.layers.55.self_attn.q_proj",
|
| 448 |
+
"language_model.model.layers.57.mlp.gate_proj",
|
| 449 |
+
"language_model.model.layers.6.mlp.up_proj",
|
| 450 |
+
"language_model.model.layers.7.mlp.up_proj",
|
| 451 |
+
"language_model.model.layers.34.self_attn.v_proj",
|
| 452 |
+
"language_model.model.layers.48.self_attn.o_proj",
|
| 453 |
+
"language_model.model.layers.36.self_attn.q_proj",
|
| 454 |
+
"language_model.model.layers.6.self_attn.v_proj",
|
| 455 |
+
"language_model.model.layers.53.mlp.down_proj",
|
| 456 |
+
"language_model.model.layers.49.mlp.gate_proj"
|
| 457 |
+
],
|
| 458 |
+
"task_type": "CAUSAL_LM",
|
| 459 |
+
"use_dora": false,
|
| 460 |
+
"use_rslora": false
|
| 461 |
+
}
|
checkpoint-120/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2858bf7ea1a8dfcfd2e9c7c507b264f099f9dbe08796a8fc21788c499f6d5ad8
|
| 3 |
+
size 1816396048
|
checkpoint-120/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<image_soft_token>": 262144
|
| 3 |
+
}
|
checkpoint-120/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{{ bos_token }}\n{%- if messages[0]['role'] == 'system' -%}\n {%- if messages[0]['content'] is string -%}\n {%- set first_user_prefix = messages[0]['content'] + '\n\n' -%}\n {%- else -%}\n {%- set first_user_prefix = messages[0]['content'][0]['text'] + '\n\n' -%}\n {%- endif -%}\n {%- set loop_messages = messages[1:] -%}\n{%- else -%}\n {%- set first_user_prefix = \"\" -%}\n {%- set loop_messages = messages -%}\n{%- endif -%}\n{%- for message in loop_messages -%}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}\n {{ raise_exception(\"Conversation roles must alternate user/assistant/user/assistant/...\") }}\n {%- endif -%}\n {%- if (message['role'] == 'assistant') -%}\n {%- set role = \"model\" -%}\n {%- else -%}\n {%- set role = message['role'] -%}\n {%- endif -%}\n {{ '<start_of_turn>' + role + '\n' + (first_user_prefix if loop.first else \"\") }}\n {%- if message['content'] is string -%}\n {{ message['content'] | trim }}\n {%- elif message['content'] is iterable -%}\n {%- for item in message['content'] -%}\n {%- if item['type'] == 'image' -%}\n {{ '<start_of_image>' }}\n {%- elif item['type'] == 'text' -%}\n {{ item['text'] | trim }}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{ raise_exception(\"Invalid content type\") }}\n {%- endif -%}\n {{ '<end_of_turn>\n' }}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{'<start_of_turn>model\n'}}\n{%- endif -%}\n"
|
| 3 |
+
}
|
checkpoint-120/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc88d42378a7140b8aef7d0b8bde0e94b26a5479e6b49d2a1c648aeb84053478
|
| 3 |
+
size 3633264318
|
checkpoint-120/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_pan_and_scan": null,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Gemma3ImageProcessor",
|
| 13 |
+
"image_seq_length": 256,
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"pan_and_scan_max_num_crops": null,
|
| 20 |
+
"pan_and_scan_min_crop_size": null,
|
| 21 |
+
"pan_and_scan_min_ratio_to_activate": null,
|
| 22 |
+
"processor_class": "Gemma3Processor",
|
| 23 |
+
"resample": 2,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"height": 896,
|
| 27 |
+
"width": 896
|
| 28 |
+
}
|
| 29 |
+
}
|
checkpoint-120/processor_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_seq_length": 256,
|
| 3 |
+
"processor_class": "Gemma3Processor"
|
| 4 |
+
}
|
checkpoint-120/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
|
| 3 |
+
size 14244
|
checkpoint-120/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b0e3be07f2ddf2c035815fdad5db539ba623c588ed1a2904332a7a2674ae64a
|
| 3 |
+
size 1064
|
checkpoint-120/special_tokens_map.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<end_of_turn>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"boi_token": "<start_of_image>",
|
| 12 |
+
"bos_token": {
|
| 13 |
+
"content": "<bos>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"eoi_token": "<end_of_image>",
|
| 20 |
+
"eos_token": {
|
| 21 |
+
"content": "<eos>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"image_token": "<image_soft_token>",
|
| 28 |
+
"pad_token": {
|
| 29 |
+
"content": "<pad>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"unk_token": {
|
| 36 |
+
"content": "<unk>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false
|
| 41 |
+
}
|
| 42 |
+
}
|
checkpoint-120/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
| 3 |
+
size 33384568
|
checkpoint-120/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
checkpoint-120/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-120/trainer_state.json
ADDED
|
@@ -0,0 +1,226 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 120,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.3333333333333333,
|
| 14 |
+
"grad_norm": 79.55762481689453,
|
| 15 |
+
"learning_rate": 4.9786121534345265e-05,
|
| 16 |
+
"loss": 45.253,
|
| 17 |
+
"num_input_tokens_seen": 47512,
|
| 18 |
+
"step": 5
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.6666666666666666,
|
| 22 |
+
"grad_norm": 17.002260208129883,
|
| 23 |
+
"learning_rate": 4.914814565722671e-05,
|
| 24 |
+
"loss": 3.0254,
|
| 25 |
+
"num_input_tokens_seen": 94536,
|
| 26 |
+
"step": 10
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.0,
|
| 30 |
+
"grad_norm": 35.45703887939453,
|
| 31 |
+
"learning_rate": 4.8096988312782174e-05,
|
| 32 |
+
"loss": 3.1619,
|
| 33 |
+
"num_input_tokens_seen": 141336,
|
| 34 |
+
"step": 15
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 1.3333333333333333,
|
| 38 |
+
"grad_norm": 32.79413604736328,
|
| 39 |
+
"learning_rate": 4.665063509461097e-05,
|
| 40 |
+
"loss": 1.7871,
|
| 41 |
+
"num_input_tokens_seen": 188368,
|
| 42 |
+
"step": 20
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.6666666666666665,
|
| 46 |
+
"grad_norm": 57.80039978027344,
|
| 47 |
+
"learning_rate": 4.4833833507280884e-05,
|
| 48 |
+
"loss": 2.643,
|
| 49 |
+
"num_input_tokens_seen": 235128,
|
| 50 |
+
"step": 25
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.0,
|
| 54 |
+
"grad_norm": 8.35395622253418,
|
| 55 |
+
"learning_rate": 4.267766952966369e-05,
|
| 56 |
+
"loss": 2.3801,
|
| 57 |
+
"num_input_tokens_seen": 282672,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.3333333333333335,
|
| 62 |
+
"grad_norm": 13.160042762756348,
|
| 63 |
+
"learning_rate": 4.021903572521802e-05,
|
| 64 |
+
"loss": 1.6999,
|
| 65 |
+
"num_input_tokens_seen": 329864,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.6666666666666665,
|
| 70 |
+
"grad_norm": 31.193811416625977,
|
| 71 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 72 |
+
"loss": 1.5571,
|
| 73 |
+
"num_input_tokens_seen": 377952,
|
| 74 |
+
"step": 40
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 3.0,
|
| 78 |
+
"grad_norm": 57.113609313964844,
|
| 79 |
+
"learning_rate": 3.456708580912725e-05,
|
| 80 |
+
"loss": 1.7335,
|
| 81 |
+
"num_input_tokens_seen": 424008,
|
| 82 |
+
"step": 45
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 3.3333333333333335,
|
| 86 |
+
"grad_norm": 26.844955444335938,
|
| 87 |
+
"learning_rate": 3.147047612756302e-05,
|
| 88 |
+
"loss": 1.1859,
|
| 89 |
+
"num_input_tokens_seen": 471344,
|
| 90 |
+
"step": 50
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 3.6666666666666665,
|
| 94 |
+
"grad_norm": 19.28535270690918,
|
| 95 |
+
"learning_rate": 2.8263154805501297e-05,
|
| 96 |
+
"loss": 0.9846,
|
| 97 |
+
"num_input_tokens_seen": 517832,
|
| 98 |
+
"step": 55
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 4.0,
|
| 102 |
+
"grad_norm": 16.303863525390625,
|
| 103 |
+
"learning_rate": 2.5e-05,
|
| 104 |
+
"loss": 0.901,
|
| 105 |
+
"num_input_tokens_seen": 565344,
|
| 106 |
+
"step": 60
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 4.333333333333333,
|
| 110 |
+
"grad_norm": 38.277183532714844,
|
| 111 |
+
"learning_rate": 2.173684519449872e-05,
|
| 112 |
+
"loss": 0.4142,
|
| 113 |
+
"num_input_tokens_seen": 612336,
|
| 114 |
+
"step": 65
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.666666666666667,
|
| 118 |
+
"grad_norm": 16.51125144958496,
|
| 119 |
+
"learning_rate": 1.852952387243698e-05,
|
| 120 |
+
"loss": 0.6221,
|
| 121 |
+
"num_input_tokens_seen": 659560,
|
| 122 |
+
"step": 70
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 5.0,
|
| 126 |
+
"grad_norm": 55.58554458618164,
|
| 127 |
+
"learning_rate": 1.5432914190872757e-05,
|
| 128 |
+
"loss": 0.7115,
|
| 129 |
+
"num_input_tokens_seen": 706680,
|
| 130 |
+
"step": 75
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 5.333333333333333,
|
| 134 |
+
"grad_norm": 7.757297992706299,
|
| 135 |
+
"learning_rate": 1.2500000000000006e-05,
|
| 136 |
+
"loss": 0.1582,
|
| 137 |
+
"num_input_tokens_seen": 754048,
|
| 138 |
+
"step": 80
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 5.666666666666667,
|
| 142 |
+
"grad_norm": 6.108384609222412,
|
| 143 |
+
"learning_rate": 9.780964274781984e-06,
|
| 144 |
+
"loss": 0.1891,
|
| 145 |
+
"num_input_tokens_seen": 800984,
|
| 146 |
+
"step": 85
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 6.0,
|
| 150 |
+
"grad_norm": 0.9440665245056152,
|
| 151 |
+
"learning_rate": 7.3223304703363135e-06,
|
| 152 |
+
"loss": 0.2214,
|
| 153 |
+
"num_input_tokens_seen": 848016,
|
| 154 |
+
"step": 90
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 6.333333333333333,
|
| 158 |
+
"grad_norm": 0.9317387342453003,
|
| 159 |
+
"learning_rate": 5.166166492719124e-06,
|
| 160 |
+
"loss": 0.0135,
|
| 161 |
+
"num_input_tokens_seen": 895040,
|
| 162 |
+
"step": 95
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 6.666666666666667,
|
| 166 |
+
"grad_norm": 0.1581590473651886,
|
| 167 |
+
"learning_rate": 3.3493649053890326e-06,
|
| 168 |
+
"loss": 0.0055,
|
| 169 |
+
"num_input_tokens_seen": 941960,
|
| 170 |
+
"step": 100
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 7.0,
|
| 174 |
+
"grad_norm": 1.00675368309021,
|
| 175 |
+
"learning_rate": 1.9030116872178316e-06,
|
| 176 |
+
"loss": 0.031,
|
| 177 |
+
"num_input_tokens_seen": 989352,
|
| 178 |
+
"step": 105
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 7.333333333333333,
|
| 182 |
+
"grad_norm": 0.6310182213783264,
|
| 183 |
+
"learning_rate": 8.51854342773295e-07,
|
| 184 |
+
"loss": 0.0085,
|
| 185 |
+
"num_input_tokens_seen": 1035760,
|
| 186 |
+
"step": 110
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 7.666666666666667,
|
| 190 |
+
"grad_norm": 0.24195235967636108,
|
| 191 |
+
"learning_rate": 2.1387846565474045e-07,
|
| 192 |
+
"loss": 0.0032,
|
| 193 |
+
"num_input_tokens_seen": 1083624,
|
| 194 |
+
"step": 115
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 8.0,
|
| 198 |
+
"grad_norm": 0.020462460815906525,
|
| 199 |
+
"learning_rate": 0.0,
|
| 200 |
+
"loss": 0.0005,
|
| 201 |
+
"num_input_tokens_seen": 1130688,
|
| 202 |
+
"step": 120
|
| 203 |
+
}
|
| 204 |
+
],
|
| 205 |
+
"logging_steps": 5,
|
| 206 |
+
"max_steps": 120,
|
| 207 |
+
"num_input_tokens_seen": 1130688,
|
| 208 |
+
"num_train_epochs": 8,
|
| 209 |
+
"save_steps": 100,
|
| 210 |
+
"stateful_callbacks": {
|
| 211 |
+
"TrainerControl": {
|
| 212 |
+
"args": {
|
| 213 |
+
"should_epoch_stop": false,
|
| 214 |
+
"should_evaluate": false,
|
| 215 |
+
"should_log": false,
|
| 216 |
+
"should_save": true,
|
| 217 |
+
"should_training_stop": true
|
| 218 |
+
},
|
| 219 |
+
"attributes": {}
|
| 220 |
+
}
|
| 221 |
+
},
|
| 222 |
+
"total_flos": 1.7959027775641805e+17,
|
| 223 |
+
"train_batch_size": 1,
|
| 224 |
+
"trial_name": null,
|
| 225 |
+
"trial_params": null
|
| 226 |
+
}
|
checkpoint-120/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ef6c21cfca5f2537c2c77045da591ab94a70a2c3c6f8193b51ea235f03d35bf
|
| 3 |
+
size 5688
|
llamaboard_config.yaml
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
top.booster: auto
|
| 2 |
+
top.checkpoint_path: []
|
| 3 |
+
top.finetuning_type: lora
|
| 4 |
+
top.model_name: Gemma-3-27B-Instruct
|
| 5 |
+
top.quantization_bit: none
|
| 6 |
+
top.quantization_method: bitsandbytes
|
| 7 |
+
top.rope_scaling: none
|
| 8 |
+
top.template: gemma3
|
| 9 |
+
train.additional_target: ''
|
| 10 |
+
train.apollo_rank: 16
|
| 11 |
+
train.apollo_scale: 32
|
| 12 |
+
train.apollo_target: all
|
| 13 |
+
train.apollo_update_interval: 200
|
| 14 |
+
train.badam_mode: layer
|
| 15 |
+
train.badam_switch_interval: 50
|
| 16 |
+
train.badam_switch_mode: ascending
|
| 17 |
+
train.badam_update_ratio: 0.05
|
| 18 |
+
train.batch_size: 1
|
| 19 |
+
train.compute_type: bf16
|
| 20 |
+
train.create_new_adapter: false
|
| 21 |
+
train.cutoff_len: 2048
|
| 22 |
+
train.dataset:
|
| 23 |
+
- ets120
|
| 24 |
+
train.dataset_dir: data
|
| 25 |
+
train.ds_offload: false
|
| 26 |
+
train.ds_stage: none
|
| 27 |
+
train.extra_args: '{"optim": "adamw_torch"}'
|
| 28 |
+
train.freeze_extra_modules: ''
|
| 29 |
+
train.freeze_trainable_layers: 2
|
| 30 |
+
train.freeze_trainable_modules: all
|
| 31 |
+
train.galore_rank: 16
|
| 32 |
+
train.galore_scale: 2
|
| 33 |
+
train.galore_target: all
|
| 34 |
+
train.galore_update_interval: 200
|
| 35 |
+
train.gradient_accumulation_steps: 8
|
| 36 |
+
train.learning_rate: 5e-5
|
| 37 |
+
train.logging_steps: 5
|
| 38 |
+
train.lora_alpha: 128
|
| 39 |
+
train.lora_dropout: 0
|
| 40 |
+
train.lora_rank: 64
|
| 41 |
+
train.lora_target: ''
|
| 42 |
+
train.loraplus_lr_ratio: 0
|
| 43 |
+
train.lr_scheduler_type: cosine
|
| 44 |
+
train.mask_history: false
|
| 45 |
+
train.max_grad_norm: '1.0'
|
| 46 |
+
train.max_samples: '100000'
|
| 47 |
+
train.neat_packing: false
|
| 48 |
+
train.neftune_alpha: 0
|
| 49 |
+
train.num_train_epochs: '8'
|
| 50 |
+
train.packing: false
|
| 51 |
+
train.ppo_score_norm: false
|
| 52 |
+
train.ppo_whiten_rewards: false
|
| 53 |
+
train.pref_beta: 0.1
|
| 54 |
+
train.pref_ftx: 0
|
| 55 |
+
train.pref_loss: sigmoid
|
| 56 |
+
train.report_to:
|
| 57 |
+
- none
|
| 58 |
+
train.resize_vocab: false
|
| 59 |
+
train.reward_model: []
|
| 60 |
+
train.save_steps: 100
|
| 61 |
+
train.swanlab_api_key: ''
|
| 62 |
+
train.swanlab_link: ''
|
| 63 |
+
train.swanlab_mode: cloud
|
| 64 |
+
train.swanlab_project: llamafactory
|
| 65 |
+
train.swanlab_run_name: ''
|
| 66 |
+
train.swanlab_workspace: ''
|
| 67 |
+
train.train_on_prompt: false
|
| 68 |
+
train.training_stage: Supervised Fine-Tuning
|
| 69 |
+
train.use_apollo: false
|
| 70 |
+
train.use_badam: false
|
| 71 |
+
train.use_dora: false
|
| 72 |
+
train.use_galore: false
|
| 73 |
+
train.use_llama_pro: false
|
| 74 |
+
train.use_pissa: false
|
| 75 |
+
train.use_rslora: false
|
| 76 |
+
train.use_swanlab: false
|
| 77 |
+
train.val_size: 0
|
| 78 |
+
train.warmup_steps: 0
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_pan_and_scan": null,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Gemma3ImageProcessor",
|
| 13 |
+
"image_seq_length": 256,
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"pan_and_scan_max_num_crops": null,
|
| 20 |
+
"pan_and_scan_min_crop_size": null,
|
| 21 |
+
"pan_and_scan_min_ratio_to_activate": null,
|
| 22 |
+
"processor_class": "Gemma3Processor",
|
| 23 |
+
"resample": 2,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"height": 896,
|
| 27 |
+
"width": 896
|
| 28 |
+
}
|
| 29 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_seq_length": 256,
|
| 3 |
+
"processor_class": "Gemma3Processor"
|
| 4 |
+
}
|
running_log.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<end_of_turn>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"boi_token": "<start_of_image>",
|
| 12 |
+
"bos_token": {
|
| 13 |
+
"content": "<bos>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"eoi_token": "<end_of_image>",
|
| 20 |
+
"eos_token": {
|
| 21 |
+
"content": "<eos>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"image_token": "<image_soft_token>",
|
| 28 |
+
"pad_token": {
|
| 29 |
+
"content": "<pad>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"unk_token": {
|
| 36 |
+
"content": "<unk>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false
|
| 41 |
+
}
|
| 42 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
| 3 |
+
size 33384568
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
| 3 |
+
size 4689074
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.0,
|
| 3 |
+
"num_input_tokens_seen": 1130688,
|
| 4 |
+
"total_flos": 1.7959027775641805e+17,
|
| 5 |
+
"train_loss": 2.86213872662629,
|
| 6 |
+
"train_runtime": 778.6794,
|
| 7 |
+
"train_samples_per_second": 1.233,
|
| 8 |
+
"train_steps_per_second": 0.154
|
| 9 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 120, "loss": 45.253, "lr": 4.9786121534345265e-05, "epoch": 0.3333333333333333, "percentage": 4.17, "elapsed_time": "0:00:32", "remaining_time": "0:12:33", "throughput": 1449.55, "total_tokens": 47512}
|
| 2 |
+
{"current_steps": 10, "total_steps": 120, "loss": 3.0254, "lr": 4.914814565722671e-05, "epoch": 0.6666666666666666, "percentage": 8.33, "elapsed_time": "0:01:04", "remaining_time": "0:11:50", "throughput": 1463.37, "total_tokens": 94536}
|
| 3 |
+
{"current_steps": 15, "total_steps": 120, "loss": 3.1619, "lr": 4.8096988312782174e-05, "epoch": 1.0, "percentage": 12.5, "elapsed_time": "0:01:36", "remaining_time": "0:11:13", "throughput": 1468.19, "total_tokens": 141336}
|
| 4 |
+
{"current_steps": 20, "total_steps": 120, "loss": 1.7871, "lr": 4.665063509461097e-05, "epoch": 1.3333333333333333, "percentage": 16.67, "elapsed_time": "0:02:08", "remaining_time": "0:10:41", "throughput": 1469.09, "total_tokens": 188368}
|
| 5 |
+
{"current_steps": 25, "total_steps": 120, "loss": 2.643, "lr": 4.4833833507280884e-05, "epoch": 1.6666666666666665, "percentage": 20.83, "elapsed_time": "0:02:39", "remaining_time": "0:10:07", "throughput": 1471.42, "total_tokens": 235128}
|
| 6 |
+
{"current_steps": 30, "total_steps": 120, "loss": 2.3801, "lr": 4.267766952966369e-05, "epoch": 2.0, "percentage": 25.0, "elapsed_time": "0:03:11", "remaining_time": "0:09:35", "throughput": 1472.69, "total_tokens": 282672}
|
| 7 |
+
{"current_steps": 35, "total_steps": 120, "loss": 1.6999, "lr": 4.021903572521802e-05, "epoch": 2.3333333333333335, "percentage": 29.17, "elapsed_time": "0:03:43", "remaining_time": "0:09:03", "throughput": 1473.48, "total_tokens": 329864}
|
| 8 |
+
{"current_steps": 40, "total_steps": 120, "loss": 1.5571, "lr": 3.7500000000000003e-05, "epoch": 2.6666666666666665, "percentage": 33.33, "elapsed_time": "0:04:16", "remaining_time": "0:08:32", "throughput": 1474.26, "total_tokens": 377952}
|
| 9 |
+
{"current_steps": 45, "total_steps": 120, "loss": 1.7335, "lr": 3.456708580912725e-05, "epoch": 3.0, "percentage": 37.5, "elapsed_time": "0:04:47", "remaining_time": "0:07:59", "throughput": 1474.37, "total_tokens": 424008}
|
| 10 |
+
{"current_steps": 50, "total_steps": 120, "loss": 1.1859, "lr": 3.147047612756302e-05, "epoch": 3.3333333333333335, "percentage": 41.67, "elapsed_time": "0:05:19", "remaining_time": "0:07:27", "throughput": 1474.56, "total_tokens": 471344}
|
| 11 |
+
{"current_steps": 55, "total_steps": 120, "loss": 0.9846, "lr": 2.8263154805501297e-05, "epoch": 3.6666666666666665, "percentage": 45.83, "elapsed_time": "0:05:51", "remaining_time": "0:06:54", "throughput": 1474.79, "total_tokens": 517832}
|
| 12 |
+
{"current_steps": 60, "total_steps": 120, "loss": 0.901, "lr": 2.5e-05, "epoch": 4.0, "percentage": 50.0, "elapsed_time": "0:06:23", "remaining_time": "0:06:23", "throughput": 1475.6, "total_tokens": 565344}
|
| 13 |
+
{"current_steps": 65, "total_steps": 120, "loss": 0.4142, "lr": 2.173684519449872e-05, "epoch": 4.333333333333333, "percentage": 54.17, "elapsed_time": "0:06:54", "remaining_time": "0:05:51", "throughput": 1475.83, "total_tokens": 612336}
|
| 14 |
+
{"current_steps": 70, "total_steps": 120, "loss": 0.6221, "lr": 1.852952387243698e-05, "epoch": 4.666666666666667, "percentage": 58.33, "elapsed_time": "0:07:26", "remaining_time": "0:05:19", "throughput": 1476.44, "total_tokens": 659560}
|
| 15 |
+
{"current_steps": 75, "total_steps": 120, "loss": 0.7115, "lr": 1.5432914190872757e-05, "epoch": 5.0, "percentage": 62.5, "elapsed_time": "0:07:58", "remaining_time": "0:04:47", "throughput": 1476.17, "total_tokens": 706680}
|
| 16 |
+
{"current_steps": 80, "total_steps": 120, "loss": 0.1582, "lr": 1.2500000000000006e-05, "epoch": 5.333333333333333, "percentage": 66.67, "elapsed_time": "0:08:30", "remaining_time": "0:04:15", "throughput": 1476.06, "total_tokens": 754048}
|
| 17 |
+
{"current_steps": 85, "total_steps": 120, "loss": 0.1891, "lr": 9.780964274781984e-06, "epoch": 5.666666666666667, "percentage": 70.83, "elapsed_time": "0:09:02", "remaining_time": "0:03:43", "throughput": 1476.33, "total_tokens": 800984}
|
| 18 |
+
{"current_steps": 90, "total_steps": 120, "loss": 0.2214, "lr": 7.3223304703363135e-06, "epoch": 6.0, "percentage": 75.0, "elapsed_time": "0:09:34", "remaining_time": "0:03:11", "throughput": 1476.67, "total_tokens": 848016}
|
| 19 |
+
{"current_steps": 95, "total_steps": 120, "loss": 0.0135, "lr": 5.166166492719124e-06, "epoch": 6.333333333333333, "percentage": 79.17, "elapsed_time": "0:10:06", "remaining_time": "0:02:39", "throughput": 1476.53, "total_tokens": 895040}
|
| 20 |
+
{"current_steps": 100, "total_steps": 120, "loss": 0.0055, "lr": 3.3493649053890326e-06, "epoch": 6.666666666666667, "percentage": 83.33, "elapsed_time": "0:10:37", "remaining_time": "0:02:07", "throughput": 1476.74, "total_tokens": 941960}
|
| 21 |
+
{"current_steps": 105, "total_steps": 120, "loss": 0.031, "lr": 1.9030116872178316e-06, "epoch": 7.0, "percentage": 87.5, "elapsed_time": "0:11:16", "remaining_time": "0:01:36", "throughput": 1462.15, "total_tokens": 989352}
|
| 22 |
+
{"current_steps": 110, "total_steps": 120, "loss": 0.0085, "lr": 8.51854342773295e-07, "epoch": 7.333333333333333, "percentage": 91.67, "elapsed_time": "0:11:48", "remaining_time": "0:01:04", "throughput": 1462.44, "total_tokens": 1035760}
|
| 23 |
+
{"current_steps": 115, "total_steps": 120, "loss": 0.0032, "lr": 2.1387846565474045e-07, "epoch": 7.666666666666667, "percentage": 95.83, "elapsed_time": "0:12:20", "remaining_time": "0:00:32", "throughput": 1463.42, "total_tokens": 1083624}
|
| 24 |
+
{"current_steps": 120, "total_steps": 120, "loss": 0.0005, "lr": 0.0, "epoch": 8.0, "percentage": 100.0, "elapsed_time": "0:12:52", "remaining_time": "0:00:00", "throughput": 1464.1, "total_tokens": 1130688}
|
| 25 |
+
{"current_steps": 120, "total_steps": 120, "epoch": 8.0, "percentage": 100.0, "elapsed_time": "0:12:58", "remaining_time": "0:00:00", "throughput": 1452.07, "total_tokens": 1130688}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,236 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 120,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.3333333333333333,
|
| 14 |
+
"grad_norm": 79.55762481689453,
|
| 15 |
+
"learning_rate": 4.9786121534345265e-05,
|
| 16 |
+
"loss": 45.253,
|
| 17 |
+
"num_input_tokens_seen": 47512,
|
| 18 |
+
"step": 5
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.6666666666666666,
|
| 22 |
+
"grad_norm": 17.002260208129883,
|
| 23 |
+
"learning_rate": 4.914814565722671e-05,
|
| 24 |
+
"loss": 3.0254,
|
| 25 |
+
"num_input_tokens_seen": 94536,
|
| 26 |
+
"step": 10
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.0,
|
| 30 |
+
"grad_norm": 35.45703887939453,
|
| 31 |
+
"learning_rate": 4.8096988312782174e-05,
|
| 32 |
+
"loss": 3.1619,
|
| 33 |
+
"num_input_tokens_seen": 141336,
|
| 34 |
+
"step": 15
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 1.3333333333333333,
|
| 38 |
+
"grad_norm": 32.79413604736328,
|
| 39 |
+
"learning_rate": 4.665063509461097e-05,
|
| 40 |
+
"loss": 1.7871,
|
| 41 |
+
"num_input_tokens_seen": 188368,
|
| 42 |
+
"step": 20
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 1.6666666666666665,
|
| 46 |
+
"grad_norm": 57.80039978027344,
|
| 47 |
+
"learning_rate": 4.4833833507280884e-05,
|
| 48 |
+
"loss": 2.643,
|
| 49 |
+
"num_input_tokens_seen": 235128,
|
| 50 |
+
"step": 25
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.0,
|
| 54 |
+
"grad_norm": 8.35395622253418,
|
| 55 |
+
"learning_rate": 4.267766952966369e-05,
|
| 56 |
+
"loss": 2.3801,
|
| 57 |
+
"num_input_tokens_seen": 282672,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 2.3333333333333335,
|
| 62 |
+
"grad_norm": 13.160042762756348,
|
| 63 |
+
"learning_rate": 4.021903572521802e-05,
|
| 64 |
+
"loss": 1.6999,
|
| 65 |
+
"num_input_tokens_seen": 329864,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.6666666666666665,
|
| 70 |
+
"grad_norm": 31.193811416625977,
|
| 71 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 72 |
+
"loss": 1.5571,
|
| 73 |
+
"num_input_tokens_seen": 377952,
|
| 74 |
+
"step": 40
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 3.0,
|
| 78 |
+
"grad_norm": 57.113609313964844,
|
| 79 |
+
"learning_rate": 3.456708580912725e-05,
|
| 80 |
+
"loss": 1.7335,
|
| 81 |
+
"num_input_tokens_seen": 424008,
|
| 82 |
+
"step": 45
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 3.3333333333333335,
|
| 86 |
+
"grad_norm": 26.844955444335938,
|
| 87 |
+
"learning_rate": 3.147047612756302e-05,
|
| 88 |
+
"loss": 1.1859,
|
| 89 |
+
"num_input_tokens_seen": 471344,
|
| 90 |
+
"step": 50
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 3.6666666666666665,
|
| 94 |
+
"grad_norm": 19.28535270690918,
|
| 95 |
+
"learning_rate": 2.8263154805501297e-05,
|
| 96 |
+
"loss": 0.9846,
|
| 97 |
+
"num_input_tokens_seen": 517832,
|
| 98 |
+
"step": 55
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 4.0,
|
| 102 |
+
"grad_norm": 16.303863525390625,
|
| 103 |
+
"learning_rate": 2.5e-05,
|
| 104 |
+
"loss": 0.901,
|
| 105 |
+
"num_input_tokens_seen": 565344,
|
| 106 |
+
"step": 60
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 4.333333333333333,
|
| 110 |
+
"grad_norm": 38.277183532714844,
|
| 111 |
+
"learning_rate": 2.173684519449872e-05,
|
| 112 |
+
"loss": 0.4142,
|
| 113 |
+
"num_input_tokens_seen": 612336,
|
| 114 |
+
"step": 65
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.666666666666667,
|
| 118 |
+
"grad_norm": 16.51125144958496,
|
| 119 |
+
"learning_rate": 1.852952387243698e-05,
|
| 120 |
+
"loss": 0.6221,
|
| 121 |
+
"num_input_tokens_seen": 659560,
|
| 122 |
+
"step": 70
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 5.0,
|
| 126 |
+
"grad_norm": 55.58554458618164,
|
| 127 |
+
"learning_rate": 1.5432914190872757e-05,
|
| 128 |
+
"loss": 0.7115,
|
| 129 |
+
"num_input_tokens_seen": 706680,
|
| 130 |
+
"step": 75
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 5.333333333333333,
|
| 134 |
+
"grad_norm": 7.757297992706299,
|
| 135 |
+
"learning_rate": 1.2500000000000006e-05,
|
| 136 |
+
"loss": 0.1582,
|
| 137 |
+
"num_input_tokens_seen": 754048,
|
| 138 |
+
"step": 80
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 5.666666666666667,
|
| 142 |
+
"grad_norm": 6.108384609222412,
|
| 143 |
+
"learning_rate": 9.780964274781984e-06,
|
| 144 |
+
"loss": 0.1891,
|
| 145 |
+
"num_input_tokens_seen": 800984,
|
| 146 |
+
"step": 85
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 6.0,
|
| 150 |
+
"grad_norm": 0.9440665245056152,
|
| 151 |
+
"learning_rate": 7.3223304703363135e-06,
|
| 152 |
+
"loss": 0.2214,
|
| 153 |
+
"num_input_tokens_seen": 848016,
|
| 154 |
+
"step": 90
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 6.333333333333333,
|
| 158 |
+
"grad_norm": 0.9317387342453003,
|
| 159 |
+
"learning_rate": 5.166166492719124e-06,
|
| 160 |
+
"loss": 0.0135,
|
| 161 |
+
"num_input_tokens_seen": 895040,
|
| 162 |
+
"step": 95
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 6.666666666666667,
|
| 166 |
+
"grad_norm": 0.1581590473651886,
|
| 167 |
+
"learning_rate": 3.3493649053890326e-06,
|
| 168 |
+
"loss": 0.0055,
|
| 169 |
+
"num_input_tokens_seen": 941960,
|
| 170 |
+
"step": 100
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 7.0,
|
| 174 |
+
"grad_norm": 1.00675368309021,
|
| 175 |
+
"learning_rate": 1.9030116872178316e-06,
|
| 176 |
+
"loss": 0.031,
|
| 177 |
+
"num_input_tokens_seen": 989352,
|
| 178 |
+
"step": 105
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 7.333333333333333,
|
| 182 |
+
"grad_norm": 0.6310182213783264,
|
| 183 |
+
"learning_rate": 8.51854342773295e-07,
|
| 184 |
+
"loss": 0.0085,
|
| 185 |
+
"num_input_tokens_seen": 1035760,
|
| 186 |
+
"step": 110
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 7.666666666666667,
|
| 190 |
+
"grad_norm": 0.24195235967636108,
|
| 191 |
+
"learning_rate": 2.1387846565474045e-07,
|
| 192 |
+
"loss": 0.0032,
|
| 193 |
+
"num_input_tokens_seen": 1083624,
|
| 194 |
+
"step": 115
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 8.0,
|
| 198 |
+
"grad_norm": 0.020462460815906525,
|
| 199 |
+
"learning_rate": 0.0,
|
| 200 |
+
"loss": 0.0005,
|
| 201 |
+
"num_input_tokens_seen": 1130688,
|
| 202 |
+
"step": 120
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 8.0,
|
| 206 |
+
"num_input_tokens_seen": 1130688,
|
| 207 |
+
"step": 120,
|
| 208 |
+
"total_flos": 1.7959027775641805e+17,
|
| 209 |
+
"train_loss": 2.86213872662629,
|
| 210 |
+
"train_runtime": 778.6794,
|
| 211 |
+
"train_samples_per_second": 1.233,
|
| 212 |
+
"train_steps_per_second": 0.154
|
| 213 |
+
}
|
| 214 |
+
],
|
| 215 |
+
"logging_steps": 5,
|
| 216 |
+
"max_steps": 120,
|
| 217 |
+
"num_input_tokens_seen": 1130688,
|
| 218 |
+
"num_train_epochs": 8,
|
| 219 |
+
"save_steps": 100,
|
| 220 |
+
"stateful_callbacks": {
|
| 221 |
+
"TrainerControl": {
|
| 222 |
+
"args": {
|
| 223 |
+
"should_epoch_stop": false,
|
| 224 |
+
"should_evaluate": false,
|
| 225 |
+
"should_log": false,
|
| 226 |
+
"should_save": true,
|
| 227 |
+
"should_training_stop": true
|
| 228 |
+
},
|
| 229 |
+
"attributes": {}
|
| 230 |
+
}
|
| 231 |
+
},
|
| 232 |
+
"total_flos": 1.7959027775641805e+17,
|
| 233 |
+
"train_batch_size": 1,
|
| 234 |
+
"trial_name": null,
|
| 235 |
+
"trial_params": null
|
| 236 |
+
}
|