Delete folder checkpoints with huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- checkpoints/knowledge/atomic_full_sft_50ep/README.md +0 -110
- checkpoints/knowledge/atomic_full_sft_50ep/chat_template.jinja +0 -4
- checkpoints/knowledge/atomic_full_sft_50ep/config.json +0 -72
- checkpoints/knowledge/atomic_full_sft_50ep/eval_results/eval_results.csv +0 -3
- checkpoints/knowledge/atomic_full_sft_50ep/eval_results/eval_summary.json +0 -11
- checkpoints/knowledge/atomic_full_sft_50ep/eval_results/test_inference_results.jsonl +0 -0
- checkpoints/knowledge/atomic_full_sft_50ep/eval_results/test_subset_of_train_inference_results.jsonl +0 -0
- checkpoints/knowledge/atomic_full_sft_50ep/generation_config.json +0 -12
- checkpoints/knowledge/atomic_full_sft_50ep/model.safetensors +0 -3
- checkpoints/knowledge/atomic_full_sft_50ep/tokenizer.json +0 -3
- checkpoints/knowledge/atomic_full_sft_50ep/tokenizer_config.json +0 -239
- checkpoints/knowledge/atomic_full_then_2step_full_sft/chat_template.jinja +0 -4
- checkpoints/knowledge/atomic_full_then_2step_full_sft/config.json +0 -71
- checkpoints/knowledge/atomic_full_then_2step_full_sft/tokenizer.json +0 -3
- checkpoints/knowledge/atomic_full_then_2step_full_sft/tokenizer_config.json +0 -29
- checkpoints/knowledge/atomic_sft_lora_50ep/README.md +0 -122
- checkpoints/knowledge/atomic_sft_lora_50ep/adapter_config.json +0 -46
- checkpoints/knowledge/atomic_sft_lora_50ep/adapter_model.safetensors +0 -3
- checkpoints/knowledge/atomic_sft_lora_50ep/chat_template.jinja +0 -4
- checkpoints/knowledge/atomic_sft_lora_50ep/config.json +0 -86
- checkpoints/knowledge/atomic_sft_lora_50ep/eval_results/eval_results.csv +0 -3
- checkpoints/knowledge/atomic_sft_lora_50ep/eval_results/eval_summary.json +0 -11
- checkpoints/knowledge/atomic_sft_lora_50ep/eval_results/test_inference_results.jsonl +0 -0
- checkpoints/knowledge/atomic_sft_lora_50ep/eval_results/test_subset_of_train_inference_results.jsonl +0 -0
- checkpoints/knowledge/atomic_sft_lora_50ep/merged/added_tokens.json +0 -28
- checkpoints/knowledge/atomic_sft_lora_50ep/merged/chat_template.jinja +0 -61
- checkpoints/knowledge/atomic_sft_lora_50ep/merged/config.json +0 -68
- checkpoints/knowledge/atomic_sft_lora_50ep/merged/generation_config.json +0 -13
- checkpoints/knowledge/atomic_sft_lora_50ep/merged/merges.txt +0 -0
- checkpoints/knowledge/atomic_sft_lora_50ep/merged/model-00001-of-00002.safetensors +0 -3
- checkpoints/knowledge/atomic_sft_lora_50ep/merged/model-00002-of-00002.safetensors +0 -3
- checkpoints/knowledge/atomic_sft_lora_50ep/merged/model.safetensors.index.json +0 -406
- checkpoints/knowledge/atomic_sft_lora_50ep/merged/special_tokens_map.json +0 -31
- checkpoints/knowledge/atomic_sft_lora_50ep/merged/tokenizer.json +0 -3
- checkpoints/knowledge/atomic_sft_lora_50ep/merged/tokenizer_config.json +0 -239
- checkpoints/knowledge/atomic_sft_lora_50ep/merged/vocab.json +0 -0
- checkpoints/knowledge/atomic_sft_lora_50ep/tokenizer.json +0 -3
- checkpoints/knowledge/atomic_sft_lora_50ep/tokenizer_config.json +0 -29
- checkpoints/math_operations/compositional_full_sft_n_steps_2/chat_template.jinja +0 -4
- checkpoints/math_operations/compositional_full_sft_n_steps_2/config.json +0 -71
- checkpoints/math_operations/compositional_full_sft_n_steps_2/tokenizer.json +0 -3
- checkpoints/math_operations/compositional_full_sft_n_steps_2/tokenizer_config.json +0 -29
- checkpoints/math_operations/full_sft_50k_lr5e5/README.md +0 -132
- checkpoints/math_operations/full_sft_50k_lr5e5/chat_template.jinja +0 -4
- checkpoints/math_operations/full_sft_50k_lr5e5/config.json +0 -71
- checkpoints/math_operations/full_sft_50k_lr5e5/eval_results/balanced_test_alpaca_converted.jsonl +0 -0
- checkpoints/math_operations/full_sft_50k_lr5e5/eval_results/balanced_test_alpaca_results.jsonl +0 -0
- checkpoints/math_operations/full_sft_50k_lr5e5/eval_results/eval_results.csv +0 -12
- checkpoints/math_operations/full_sft_50k_lr5e5/eval_results/eval_summary.json +0 -19
- checkpoints/math_operations/full_sft_50k_lr5e5/eval_results/op_A_test_alpaca_converted.jsonl +0 -0
checkpoints/knowledge/atomic_full_sft_50ep/README.md
DELETED
|
@@ -1,110 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
library_name: transformers
|
| 3 |
-
tags:
|
| 4 |
-
- generated_from_trainer
|
| 5 |
-
datasets:
|
| 6 |
-
- /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/data/knowledge/atomic_sft/train_messages.jsonl
|
| 7 |
-
model-index:
|
| 8 |
-
- name: home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/checkpoints/knowledge/atomic_full_sft_50ep
|
| 9 |
-
results: []
|
| 10 |
-
---
|
| 11 |
-
|
| 12 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
-
|
| 15 |
-
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
| 16 |
-
<details><summary>See axolotl config</summary>
|
| 17 |
-
|
| 18 |
-
axolotl version: `0.15.0.dev0`
|
| 19 |
-
```yaml
|
| 20 |
-
base_model: /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/models/Qwen/Qwen3-4B-Instruct-2507
|
| 21 |
-
load_in_8bit: false
|
| 22 |
-
load_in_4bit: false
|
| 23 |
-
strict: false
|
| 24 |
-
|
| 25 |
-
datasets:
|
| 26 |
-
- path: /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/data/knowledge/atomic_sft/train_messages.jsonl
|
| 27 |
-
type: chat_template
|
| 28 |
-
dataset_prepared_path:
|
| 29 |
-
val_set_size: 0
|
| 30 |
-
chat_template: chatml
|
| 31 |
-
|
| 32 |
-
output_dir: /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/checkpoints/knowledge/atomic_full_sft_50ep
|
| 33 |
-
|
| 34 |
-
sequence_len: 512
|
| 35 |
-
sample_packing: true
|
| 36 |
-
eval_sample_packing: true
|
| 37 |
-
|
| 38 |
-
gradient_accumulation_steps: 8
|
| 39 |
-
micro_batch_size: 1
|
| 40 |
-
num_epochs: 50
|
| 41 |
-
optimizer: adamw_torch_fused
|
| 42 |
-
lr_scheduler: constant_with_warmup
|
| 43 |
-
learning_rate: 1e-4
|
| 44 |
-
|
| 45 |
-
bf16: auto
|
| 46 |
-
tf32: true
|
| 47 |
-
|
| 48 |
-
gradient_checkpointing: true
|
| 49 |
-
gradient_checkpointing_kwargs:
|
| 50 |
-
use_reentrant: false
|
| 51 |
-
|
| 52 |
-
logging_steps: 10
|
| 53 |
-
flash_attention: true
|
| 54 |
-
warmup_ratio: 0.02
|
| 55 |
-
saves_per_epoch: 1
|
| 56 |
-
save_total_limit: 1
|
| 57 |
-
weight_decay: 0.01
|
| 58 |
-
|
| 59 |
-
wandb_project: knowledge_sft
|
| 60 |
-
wandb_name: atomic-full-50ep-constlr
|
| 61 |
-
wandb_log_model: "false"
|
| 62 |
-
|
| 63 |
-
special_tokens:
|
| 64 |
-
|
| 65 |
-
```
|
| 66 |
-
|
| 67 |
-
</details><br>
|
| 68 |
-
|
| 69 |
-
# home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/checkpoints/knowledge/atomic_full_sft_50ep
|
| 70 |
-
|
| 71 |
-
This model was trained from scratch on the /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/data/knowledge/atomic_sft/train_messages.jsonl dataset.
|
| 72 |
-
|
| 73 |
-
## Model description
|
| 74 |
-
|
| 75 |
-
More information needed
|
| 76 |
-
|
| 77 |
-
## Intended uses & limitations
|
| 78 |
-
|
| 79 |
-
More information needed
|
| 80 |
-
|
| 81 |
-
## Training and evaluation data
|
| 82 |
-
|
| 83 |
-
More information needed
|
| 84 |
-
|
| 85 |
-
## Training procedure
|
| 86 |
-
|
| 87 |
-
### Training hyperparameters
|
| 88 |
-
|
| 89 |
-
The following hyperparameters were used during training:
|
| 90 |
-
- learning_rate: 0.0001
|
| 91 |
-
- train_batch_size: 1
|
| 92 |
-
- eval_batch_size: 1
|
| 93 |
-
- seed: 42
|
| 94 |
-
- gradient_accumulation_steps: 8
|
| 95 |
-
- total_train_batch_size: 8
|
| 96 |
-
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 97 |
-
- lr_scheduler_type: constant_with_warmup
|
| 98 |
-
- lr_scheduler_warmup_steps: 26
|
| 99 |
-
- training_steps: 1300
|
| 100 |
-
|
| 101 |
-
### Training results
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
### Framework versions
|
| 106 |
-
|
| 107 |
-
- Transformers 5.0.0
|
| 108 |
-
- Pytorch 2.8.0+cu128
|
| 109 |
-
- Datasets 4.5.0
|
| 110 |
-
- Tokenizers 0.22.2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_full_sft_50ep/chat_template.jinja
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
| 2 |
-
' + message['content'] + '<|im_end|>' + '
|
| 3 |
-
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 4 |
-
' }}{% endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_full_sft_50ep/config.json
DELETED
|
@@ -1,72 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3ForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": 151643,
|
| 8 |
-
"dtype": "bfloat16",
|
| 9 |
-
"eos_token_id": 151645,
|
| 10 |
-
"head_dim": 128,
|
| 11 |
-
"hidden_act": "silu",
|
| 12 |
-
"hidden_size": 2560,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 9728,
|
| 15 |
-
"layer_types": [
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
-
"full_attention"
|
| 52 |
-
],
|
| 53 |
-
"max_position_embeddings": 262144,
|
| 54 |
-
"max_window_layers": 36,
|
| 55 |
-
"model_type": "qwen3",
|
| 56 |
-
"num_attention_heads": 32,
|
| 57 |
-
"num_hidden_layers": 36,
|
| 58 |
-
"num_key_value_heads": 8,
|
| 59 |
-
"pad_token_id": 151643,
|
| 60 |
-
"rms_norm_eps": 1e-06,
|
| 61 |
-
"rope_parameters": {
|
| 62 |
-
"rope_theta": 5000000,
|
| 63 |
-
"rope_type": "default"
|
| 64 |
-
},
|
| 65 |
-
"sliding_window": null,
|
| 66 |
-
"tie_word_embeddings": true,
|
| 67 |
-
"transformers_version": "5.0.0",
|
| 68 |
-
"use_cache": true,
|
| 69 |
-
"use_sliding_window": false,
|
| 70 |
-
"vocab_size": 151936,
|
| 71 |
-
"rope_theta": 5000000
|
| 72 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_full_sft_50ep/eval_results/eval_results.csv
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
category,filename,total,correct,accuracy,format_found,format_accuracy,errors_count
|
| 2 |
-
knowledge,test_subset_of_train_inference_results,450,448,99.56,0,0.00,2
|
| 3 |
-
knowledge,test_inference_results,499,13,2.61,0,0.00,486
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_full_sft_50ep/eval_results/eval_summary.json
DELETED
|
@@ -1,11 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"overall": {
|
| 3 |
-
"total": 499,
|
| 4 |
-
"correct": 13,
|
| 5 |
-
"accuracy": 2.61,
|
| 6 |
-
"format_found": 0,
|
| 7 |
-
"format_accuracy": 0.0
|
| 8 |
-
},
|
| 9 |
-
"n_errors": 486,
|
| 10 |
-
"results_file": "/home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/checkpoints/knowledge/atomic_full_sft_50ep/eval_results/test_inference_results.jsonl"
|
| 11 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_full_sft_50ep/eval_results/test_inference_results.jsonl
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/knowledge/atomic_full_sft_50ep/eval_results/test_subset_of_train_inference_results.jsonl
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/knowledge/atomic_full_sft_50ep/generation_config.json
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_sample": true,
|
| 3 |
-
"eos_token_id": [
|
| 4 |
-
151645,
|
| 5 |
-
151643
|
| 6 |
-
],
|
| 7 |
-
"pad_token_id": 151643,
|
| 8 |
-
"temperature": 0.7,
|
| 9 |
-
"top_k": 20,
|
| 10 |
-
"top_p": 0.8,
|
| 11 |
-
"transformers_version": "5.0.0"
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_full_sft_50ep/model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:ebe90e40bddad2b73128c35b1656006cc6cf6883bde9148ec3f150a2f9916653
|
| 3 |
-
size 8044982080
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_full_sft_50ep/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
-
size 11422650
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_full_sft_50ep/tokenizer_config.json
DELETED
|
@@ -1,239 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"added_tokens_decoder": {
|
| 4 |
-
"151643": {
|
| 5 |
-
"content": "<|endoftext|>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": false,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"151644": {
|
| 13 |
-
"content": "<|im_start|>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
},
|
| 20 |
-
"151645": {
|
| 21 |
-
"content": "<|im_end|>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": false,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false,
|
| 26 |
-
"special": true
|
| 27 |
-
},
|
| 28 |
-
"151646": {
|
| 29 |
-
"content": "<|object_ref_start|>",
|
| 30 |
-
"lstrip": false,
|
| 31 |
-
"normalized": false,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": true
|
| 35 |
-
},
|
| 36 |
-
"151647": {
|
| 37 |
-
"content": "<|object_ref_end|>",
|
| 38 |
-
"lstrip": false,
|
| 39 |
-
"normalized": false,
|
| 40 |
-
"rstrip": false,
|
| 41 |
-
"single_word": false,
|
| 42 |
-
"special": true
|
| 43 |
-
},
|
| 44 |
-
"151648": {
|
| 45 |
-
"content": "<|box_start|>",
|
| 46 |
-
"lstrip": false,
|
| 47 |
-
"normalized": false,
|
| 48 |
-
"rstrip": false,
|
| 49 |
-
"single_word": false,
|
| 50 |
-
"special": true
|
| 51 |
-
},
|
| 52 |
-
"151649": {
|
| 53 |
-
"content": "<|box_end|>",
|
| 54 |
-
"lstrip": false,
|
| 55 |
-
"normalized": false,
|
| 56 |
-
"rstrip": false,
|
| 57 |
-
"single_word": false,
|
| 58 |
-
"special": true
|
| 59 |
-
},
|
| 60 |
-
"151650": {
|
| 61 |
-
"content": "<|quad_start|>",
|
| 62 |
-
"lstrip": false,
|
| 63 |
-
"normalized": false,
|
| 64 |
-
"rstrip": false,
|
| 65 |
-
"single_word": false,
|
| 66 |
-
"special": true
|
| 67 |
-
},
|
| 68 |
-
"151651": {
|
| 69 |
-
"content": "<|quad_end|>",
|
| 70 |
-
"lstrip": false,
|
| 71 |
-
"normalized": false,
|
| 72 |
-
"rstrip": false,
|
| 73 |
-
"single_word": false,
|
| 74 |
-
"special": true
|
| 75 |
-
},
|
| 76 |
-
"151652": {
|
| 77 |
-
"content": "<|vision_start|>",
|
| 78 |
-
"lstrip": false,
|
| 79 |
-
"normalized": false,
|
| 80 |
-
"rstrip": false,
|
| 81 |
-
"single_word": false,
|
| 82 |
-
"special": true
|
| 83 |
-
},
|
| 84 |
-
"151653": {
|
| 85 |
-
"content": "<|vision_end|>",
|
| 86 |
-
"lstrip": false,
|
| 87 |
-
"normalized": false,
|
| 88 |
-
"rstrip": false,
|
| 89 |
-
"single_word": false,
|
| 90 |
-
"special": true
|
| 91 |
-
},
|
| 92 |
-
"151654": {
|
| 93 |
-
"content": "<|vision_pad|>",
|
| 94 |
-
"lstrip": false,
|
| 95 |
-
"normalized": false,
|
| 96 |
-
"rstrip": false,
|
| 97 |
-
"single_word": false,
|
| 98 |
-
"special": true
|
| 99 |
-
},
|
| 100 |
-
"151655": {
|
| 101 |
-
"content": "<|image_pad|>",
|
| 102 |
-
"lstrip": false,
|
| 103 |
-
"normalized": false,
|
| 104 |
-
"rstrip": false,
|
| 105 |
-
"single_word": false,
|
| 106 |
-
"special": true
|
| 107 |
-
},
|
| 108 |
-
"151656": {
|
| 109 |
-
"content": "<|video_pad|>",
|
| 110 |
-
"lstrip": false,
|
| 111 |
-
"normalized": false,
|
| 112 |
-
"rstrip": false,
|
| 113 |
-
"single_word": false,
|
| 114 |
-
"special": true
|
| 115 |
-
},
|
| 116 |
-
"151657": {
|
| 117 |
-
"content": "<tool_call>",
|
| 118 |
-
"lstrip": false,
|
| 119 |
-
"normalized": false,
|
| 120 |
-
"rstrip": false,
|
| 121 |
-
"single_word": false,
|
| 122 |
-
"special": false
|
| 123 |
-
},
|
| 124 |
-
"151658": {
|
| 125 |
-
"content": "</tool_call>",
|
| 126 |
-
"lstrip": false,
|
| 127 |
-
"normalized": false,
|
| 128 |
-
"rstrip": false,
|
| 129 |
-
"single_word": false,
|
| 130 |
-
"special": false
|
| 131 |
-
},
|
| 132 |
-
"151659": {
|
| 133 |
-
"content": "<|fim_prefix|>",
|
| 134 |
-
"lstrip": false,
|
| 135 |
-
"normalized": false,
|
| 136 |
-
"rstrip": false,
|
| 137 |
-
"single_word": false,
|
| 138 |
-
"special": false
|
| 139 |
-
},
|
| 140 |
-
"151660": {
|
| 141 |
-
"content": "<|fim_middle|>",
|
| 142 |
-
"lstrip": false,
|
| 143 |
-
"normalized": false,
|
| 144 |
-
"rstrip": false,
|
| 145 |
-
"single_word": false,
|
| 146 |
-
"special": false
|
| 147 |
-
},
|
| 148 |
-
"151661": {
|
| 149 |
-
"content": "<|fim_suffix|>",
|
| 150 |
-
"lstrip": false,
|
| 151 |
-
"normalized": false,
|
| 152 |
-
"rstrip": false,
|
| 153 |
-
"single_word": false,
|
| 154 |
-
"special": false
|
| 155 |
-
},
|
| 156 |
-
"151662": {
|
| 157 |
-
"content": "<|fim_pad|>",
|
| 158 |
-
"lstrip": false,
|
| 159 |
-
"normalized": false,
|
| 160 |
-
"rstrip": false,
|
| 161 |
-
"single_word": false,
|
| 162 |
-
"special": false
|
| 163 |
-
},
|
| 164 |
-
"151663": {
|
| 165 |
-
"content": "<|repo_name|>",
|
| 166 |
-
"lstrip": false,
|
| 167 |
-
"normalized": false,
|
| 168 |
-
"rstrip": false,
|
| 169 |
-
"single_word": false,
|
| 170 |
-
"special": false
|
| 171 |
-
},
|
| 172 |
-
"151664": {
|
| 173 |
-
"content": "<|file_sep|>",
|
| 174 |
-
"lstrip": false,
|
| 175 |
-
"normalized": false,
|
| 176 |
-
"rstrip": false,
|
| 177 |
-
"single_word": false,
|
| 178 |
-
"special": false
|
| 179 |
-
},
|
| 180 |
-
"151665": {
|
| 181 |
-
"content": "<tool_response>",
|
| 182 |
-
"lstrip": false,
|
| 183 |
-
"normalized": false,
|
| 184 |
-
"rstrip": false,
|
| 185 |
-
"single_word": false,
|
| 186 |
-
"special": false
|
| 187 |
-
},
|
| 188 |
-
"151666": {
|
| 189 |
-
"content": "</tool_response>",
|
| 190 |
-
"lstrip": false,
|
| 191 |
-
"normalized": false,
|
| 192 |
-
"rstrip": false,
|
| 193 |
-
"single_word": false,
|
| 194 |
-
"special": false
|
| 195 |
-
},
|
| 196 |
-
"151667": {
|
| 197 |
-
"content": "<think>",
|
| 198 |
-
"lstrip": false,
|
| 199 |
-
"normalized": false,
|
| 200 |
-
"rstrip": false,
|
| 201 |
-
"single_word": false,
|
| 202 |
-
"special": false
|
| 203 |
-
},
|
| 204 |
-
"151668": {
|
| 205 |
-
"content": "</think>",
|
| 206 |
-
"lstrip": false,
|
| 207 |
-
"normalized": false,
|
| 208 |
-
"rstrip": false,
|
| 209 |
-
"single_word": false,
|
| 210 |
-
"special": false
|
| 211 |
-
}
|
| 212 |
-
},
|
| 213 |
-
"additional_special_tokens": [
|
| 214 |
-
"<|im_start|>",
|
| 215 |
-
"<|im_end|>",
|
| 216 |
-
"<|object_ref_start|>",
|
| 217 |
-
"<|object_ref_end|>",
|
| 218 |
-
"<|box_start|>",
|
| 219 |
-
"<|box_end|>",
|
| 220 |
-
"<|quad_start|>",
|
| 221 |
-
"<|quad_end|>",
|
| 222 |
-
"<|vision_start|>",
|
| 223 |
-
"<|vision_end|>",
|
| 224 |
-
"<|vision_pad|>",
|
| 225 |
-
"<|image_pad|>",
|
| 226 |
-
"<|video_pad|>"
|
| 227 |
-
],
|
| 228 |
-
"bos_token": null,
|
| 229 |
-
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
|
| 230 |
-
"clean_up_tokenization_spaces": false,
|
| 231 |
-
"eos_token": "<|im_end|>",
|
| 232 |
-
"errors": "replace",
|
| 233 |
-
"model_max_length": 1010000,
|
| 234 |
-
"pad_token": "<|endoftext|>",
|
| 235 |
-
"split_special_tokens": false,
|
| 236 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 237 |
-
"unk_token": null,
|
| 238 |
-
"add_bos_token": false
|
| 239 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_full_then_2step_full_sft/chat_template.jinja
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
| 2 |
-
' + message['content'] + '<|im_end|>' + '
|
| 3 |
-
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 4 |
-
' }}{% endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_full_then_2step_full_sft/config.json
DELETED
|
@@ -1,71 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3ForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": null,
|
| 8 |
-
"dtype": "bfloat16",
|
| 9 |
-
"eos_token_id": 151645,
|
| 10 |
-
"head_dim": 128,
|
| 11 |
-
"hidden_act": "silu",
|
| 12 |
-
"hidden_size": 2560,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 9728,
|
| 15 |
-
"layer_types": [
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
-
"full_attention"
|
| 52 |
-
],
|
| 53 |
-
"max_position_embeddings": 262144,
|
| 54 |
-
"max_window_layers": 36,
|
| 55 |
-
"model_type": "qwen3",
|
| 56 |
-
"num_attention_heads": 32,
|
| 57 |
-
"num_hidden_layers": 36,
|
| 58 |
-
"num_key_value_heads": 8,
|
| 59 |
-
"pad_token_id": 151643,
|
| 60 |
-
"rms_norm_eps": 1e-06,
|
| 61 |
-
"rope_parameters": {
|
| 62 |
-
"rope_theta": 5000000,
|
| 63 |
-
"rope_type": "default"
|
| 64 |
-
},
|
| 65 |
-
"sliding_window": null,
|
| 66 |
-
"tie_word_embeddings": true,
|
| 67 |
-
"transformers_version": "5.0.0",
|
| 68 |
-
"use_cache": false,
|
| 69 |
-
"use_sliding_window": false,
|
| 70 |
-
"vocab_size": 151936
|
| 71 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_full_then_2step_full_sft/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
-
size 11422650
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_full_then_2step_full_sft/tokenizer_config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"backend": "tokenizers",
|
| 4 |
-
"bos_token": null,
|
| 5 |
-
"clean_up_tokenization_spaces": false,
|
| 6 |
-
"eos_token": "<|im_end|>",
|
| 7 |
-
"errors": "replace",
|
| 8 |
-
"extra_special_tokens": [
|
| 9 |
-
"<|im_start|>",
|
| 10 |
-
"<|im_end|>",
|
| 11 |
-
"<|object_ref_start|>",
|
| 12 |
-
"<|object_ref_end|>",
|
| 13 |
-
"<|box_start|>",
|
| 14 |
-
"<|box_end|>",
|
| 15 |
-
"<|quad_start|>",
|
| 16 |
-
"<|quad_end|>",
|
| 17 |
-
"<|vision_start|>",
|
| 18 |
-
"<|vision_end|>",
|
| 19 |
-
"<|vision_pad|>",
|
| 20 |
-
"<|image_pad|>",
|
| 21 |
-
"<|video_pad|>"
|
| 22 |
-
],
|
| 23 |
-
"is_local": true,
|
| 24 |
-
"model_max_length": 1010000,
|
| 25 |
-
"pad_token": "<|endoftext|>",
|
| 26 |
-
"split_special_tokens": false,
|
| 27 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
-
"unk_token": null
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/README.md
DELETED
|
@@ -1,122 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
library_name: peft
|
| 3 |
-
tags:
|
| 4 |
-
- axolotl
|
| 5 |
-
- base_model:adapter:/home/jiaruil5/math_rl/mix_teachers/r3lit_rl/models/Qwen/Qwen3-4B-Instruct-2507
|
| 6 |
-
- lora
|
| 7 |
-
- transformers
|
| 8 |
-
datasets:
|
| 9 |
-
- /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/data/knowledge/atomic_sft/train_messages.jsonl
|
| 10 |
-
base_model: /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/models/Qwen/Qwen3-4B-Instruct-2507
|
| 11 |
-
pipeline_tag: text-generation
|
| 12 |
-
model-index:
|
| 13 |
-
- name: home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/checkpoints/knowledge/atomic_sft_lora_50ep
|
| 14 |
-
results: []
|
| 15 |
-
---
|
| 16 |
-
|
| 17 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 18 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 19 |
-
|
| 20 |
-
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
| 21 |
-
<details><summary>See axolotl config</summary>
|
| 22 |
-
|
| 23 |
-
axolotl version: `0.15.0.dev0`
|
| 24 |
-
```yaml
|
| 25 |
-
base_model: /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/models/Qwen/Qwen3-4B-Instruct-2507
|
| 26 |
-
load_in_8bit: false
|
| 27 |
-
load_in_4bit: true
|
| 28 |
-
strict: false
|
| 29 |
-
|
| 30 |
-
datasets:
|
| 31 |
-
- path: /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/data/knowledge/atomic_sft/train_messages.jsonl
|
| 32 |
-
type: chat_template
|
| 33 |
-
dataset_prepared_path:
|
| 34 |
-
val_set_size: 0
|
| 35 |
-
chat_template: chatml
|
| 36 |
-
|
| 37 |
-
output_dir: /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/checkpoints/knowledge/atomic_sft_lora_50ep
|
| 38 |
-
|
| 39 |
-
sequence_len: 512
|
| 40 |
-
sample_packing: true
|
| 41 |
-
eval_sample_packing: true
|
| 42 |
-
|
| 43 |
-
adapter: qlora
|
| 44 |
-
lora_r: 64
|
| 45 |
-
lora_alpha: 128
|
| 46 |
-
lora_dropout: 0.0
|
| 47 |
-
lora_target_linear: true
|
| 48 |
-
|
| 49 |
-
gradient_accumulation_steps: 4
|
| 50 |
-
micro_batch_size: 2
|
| 51 |
-
num_epochs: 50
|
| 52 |
-
optimizer: adamw_torch_fused
|
| 53 |
-
lr_scheduler: cosine
|
| 54 |
-
learning_rate: 5e-4
|
| 55 |
-
|
| 56 |
-
bf16: auto
|
| 57 |
-
tf32: true
|
| 58 |
-
|
| 59 |
-
gradient_checkpointing: true
|
| 60 |
-
gradient_checkpointing_kwargs:
|
| 61 |
-
use_reentrant: false
|
| 62 |
-
|
| 63 |
-
logging_steps: 10
|
| 64 |
-
flash_attention: true
|
| 65 |
-
warmup_ratio: 0.02
|
| 66 |
-
saves_per_epoch: 1
|
| 67 |
-
save_total_limit: 1
|
| 68 |
-
weight_decay: 0.01
|
| 69 |
-
|
| 70 |
-
wandb_project: knowledge_sft
|
| 71 |
-
wandb_name: atomic-lora-50ep-cosine
|
| 72 |
-
wandb_log_model: "false"
|
| 73 |
-
|
| 74 |
-
special_tokens:
|
| 75 |
-
|
| 76 |
-
```
|
| 77 |
-
|
| 78 |
-
</details><br>
|
| 79 |
-
|
| 80 |
-
# home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/checkpoints/knowledge/atomic_sft_lora_50ep
|
| 81 |
-
|
| 82 |
-
This model was trained from scratch on the /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/data/knowledge/atomic_sft/train_messages.jsonl dataset.
|
| 83 |
-
|
| 84 |
-
## Model description
|
| 85 |
-
|
| 86 |
-
More information needed
|
| 87 |
-
|
| 88 |
-
## Intended uses & limitations
|
| 89 |
-
|
| 90 |
-
More information needed
|
| 91 |
-
|
| 92 |
-
## Training and evaluation data
|
| 93 |
-
|
| 94 |
-
More information needed
|
| 95 |
-
|
| 96 |
-
## Training procedure
|
| 97 |
-
|
| 98 |
-
### Training hyperparameters
|
| 99 |
-
|
| 100 |
-
The following hyperparameters were used during training:
|
| 101 |
-
- learning_rate: 0.0005
|
| 102 |
-
- train_batch_size: 2
|
| 103 |
-
- eval_batch_size: 2
|
| 104 |
-
- seed: 42
|
| 105 |
-
- gradient_accumulation_steps: 4
|
| 106 |
-
- total_train_batch_size: 8
|
| 107 |
-
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 108 |
-
- lr_scheduler_type: cosine
|
| 109 |
-
- lr_scheduler_warmup_steps: 26
|
| 110 |
-
- training_steps: 1300
|
| 111 |
-
|
| 112 |
-
### Training results
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
### Framework versions
|
| 117 |
-
|
| 118 |
-
- PEFT 0.18.1
|
| 119 |
-
- Transformers 5.0.0
|
| 120 |
-
- Pytorch 2.8.0+cu128
|
| 121 |
-
- Datasets 4.5.0
|
| 122 |
-
- Tokenizers 0.22.2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/adapter_config.json
DELETED
|
@@ -1,46 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"alora_invocation_tokens": null,
|
| 3 |
-
"alpha_pattern": {},
|
| 4 |
-
"arrow_config": null,
|
| 5 |
-
"auto_mapping": null,
|
| 6 |
-
"base_model_name_or_path": "/home/jiaruil5/math_rl/mix_teachers/r3lit_rl/models/Qwen/Qwen3-4B-Instruct-2507",
|
| 7 |
-
"bias": "none",
|
| 8 |
-
"corda_config": null,
|
| 9 |
-
"ensure_weight_tying": false,
|
| 10 |
-
"eva_config": null,
|
| 11 |
-
"exclude_modules": null,
|
| 12 |
-
"fan_in_fan_out": null,
|
| 13 |
-
"inference_mode": true,
|
| 14 |
-
"init_lora_weights": true,
|
| 15 |
-
"layer_replication": null,
|
| 16 |
-
"layers_pattern": null,
|
| 17 |
-
"layers_to_transform": null,
|
| 18 |
-
"loftq_config": {},
|
| 19 |
-
"lora_alpha": 128,
|
| 20 |
-
"lora_bias": false,
|
| 21 |
-
"lora_dropout": 0.0,
|
| 22 |
-
"megatron_config": null,
|
| 23 |
-
"megatron_core": "megatron.core",
|
| 24 |
-
"modules_to_save": null,
|
| 25 |
-
"peft_type": "LORA",
|
| 26 |
-
"peft_version": "0.18.1",
|
| 27 |
-
"qalora_group_size": 16,
|
| 28 |
-
"r": 64,
|
| 29 |
-
"rank_pattern": {},
|
| 30 |
-
"revision": null,
|
| 31 |
-
"target_modules": [
|
| 32 |
-
"up_proj",
|
| 33 |
-
"q_proj",
|
| 34 |
-
"k_proj",
|
| 35 |
-
"gate_proj",
|
| 36 |
-
"o_proj",
|
| 37 |
-
"v_proj",
|
| 38 |
-
"down_proj"
|
| 39 |
-
],
|
| 40 |
-
"target_parameters": [],
|
| 41 |
-
"task_type": "CAUSAL_LM",
|
| 42 |
-
"trainable_token_indices": null,
|
| 43 |
-
"use_dora": false,
|
| 44 |
-
"use_qalora": false,
|
| 45 |
-
"use_rslora": false
|
| 46 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/adapter_model.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:e7b81e8b39caf50b763af28fff658e2ec6faa5fb16da237f16c382ef7620b462
|
| 3 |
-
size 528550256
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/chat_template.jinja
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
| 2 |
-
' + message['content'] + '<|im_end|>' + '
|
| 3 |
-
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 4 |
-
' }}{% endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/config.json
DELETED
|
@@ -1,86 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3ForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": null,
|
| 8 |
-
"dtype": "bfloat16",
|
| 9 |
-
"eos_token_id": 151645,
|
| 10 |
-
"head_dim": 128,
|
| 11 |
-
"hidden_act": "silu",
|
| 12 |
-
"hidden_size": 2560,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 9728,
|
| 15 |
-
"layer_types": [
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
-
"full_attention"
|
| 52 |
-
],
|
| 53 |
-
"max_position_embeddings": 262144,
|
| 54 |
-
"max_window_layers": 36,
|
| 55 |
-
"model_type": "qwen3",
|
| 56 |
-
"num_attention_heads": 32,
|
| 57 |
-
"num_hidden_layers": 36,
|
| 58 |
-
"num_key_value_heads": 8,
|
| 59 |
-
"pad_token_id": null,
|
| 60 |
-
"quantization_config": {
|
| 61 |
-
"_load_in_4bit": true,
|
| 62 |
-
"_load_in_8bit": false,
|
| 63 |
-
"bnb_4bit_compute_dtype": "bfloat16",
|
| 64 |
-
"bnb_4bit_quant_storage": "bfloat16",
|
| 65 |
-
"bnb_4bit_quant_type": "nf4",
|
| 66 |
-
"bnb_4bit_use_double_quant": true,
|
| 67 |
-
"llm_int8_enable_fp32_cpu_offload": false,
|
| 68 |
-
"llm_int8_has_fp16_weight": false,
|
| 69 |
-
"llm_int8_skip_modules": null,
|
| 70 |
-
"llm_int8_threshold": 6.0,
|
| 71 |
-
"load_in_4bit": true,
|
| 72 |
-
"load_in_8bit": false,
|
| 73 |
-
"quant_method": "bitsandbytes"
|
| 74 |
-
},
|
| 75 |
-
"rms_norm_eps": 1e-06,
|
| 76 |
-
"rope_parameters": {
|
| 77 |
-
"rope_theta": 5000000,
|
| 78 |
-
"rope_type": "default"
|
| 79 |
-
},
|
| 80 |
-
"sliding_window": null,
|
| 81 |
-
"tie_word_embeddings": true,
|
| 82 |
-
"transformers_version": "5.0.0",
|
| 83 |
-
"use_cache": false,
|
| 84 |
-
"use_sliding_window": false,
|
| 85 |
-
"vocab_size": 151936
|
| 86 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/eval_results/eval_results.csv
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
category,filename,total,correct,accuracy,format_found,format_accuracy,errors_count
|
| 2 |
-
knowledge,test_subset_of_train_inference_results,450,448,99.56,0,0.00,2
|
| 3 |
-
knowledge,test_inference_results,499,13,2.61,0,0.00,486
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/eval_results/eval_summary.json
DELETED
|
@@ -1,11 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"overall": {
|
| 3 |
-
"total": 499,
|
| 4 |
-
"correct": 13,
|
| 5 |
-
"accuracy": 2.61,
|
| 6 |
-
"format_found": 0,
|
| 7 |
-
"format_accuracy": 0.0
|
| 8 |
-
},
|
| 9 |
-
"n_errors": 486,
|
| 10 |
-
"results_file": "/home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/checkpoints/knowledge/atomic_sft_lora_50ep/eval_results/test_inference_results.jsonl"
|
| 11 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/eval_results/test_inference_results.jsonl
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/eval_results/test_subset_of_train_inference_results.jsonl
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/merged/added_tokens.json
DELETED
|
@@ -1,28 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"</think>": 151668,
|
| 3 |
-
"</tool_call>": 151658,
|
| 4 |
-
"</tool_response>": 151666,
|
| 5 |
-
"<think>": 151667,
|
| 6 |
-
"<tool_call>": 151657,
|
| 7 |
-
"<tool_response>": 151665,
|
| 8 |
-
"<|box_end|>": 151649,
|
| 9 |
-
"<|box_start|>": 151648,
|
| 10 |
-
"<|endoftext|>": 151643,
|
| 11 |
-
"<|file_sep|>": 151664,
|
| 12 |
-
"<|fim_middle|>": 151660,
|
| 13 |
-
"<|fim_pad|>": 151662,
|
| 14 |
-
"<|fim_prefix|>": 151659,
|
| 15 |
-
"<|fim_suffix|>": 151661,
|
| 16 |
-
"<|im_end|>": 151645,
|
| 17 |
-
"<|im_start|>": 151644,
|
| 18 |
-
"<|image_pad|>": 151655,
|
| 19 |
-
"<|object_ref_end|>": 151647,
|
| 20 |
-
"<|object_ref_start|>": 151646,
|
| 21 |
-
"<|quad_end|>": 151651,
|
| 22 |
-
"<|quad_start|>": 151650,
|
| 23 |
-
"<|repo_name|>": 151663,
|
| 24 |
-
"<|video_pad|>": 151656,
|
| 25 |
-
"<|vision_end|>": 151653,
|
| 26 |
-
"<|vision_pad|>": 151654,
|
| 27 |
-
"<|vision_start|>": 151652
|
| 28 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/merged/chat_template.jinja
DELETED
|
@@ -1,61 +0,0 @@
|
|
| 1 |
-
{%- if tools %}
|
| 2 |
-
{{- '<|im_start|>system\n' }}
|
| 3 |
-
{%- if messages[0].role == 'system' %}
|
| 4 |
-
{{- messages[0].content + '\n\n' }}
|
| 5 |
-
{%- endif %}
|
| 6 |
-
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
-
{%- for tool in tools %}
|
| 8 |
-
{{- "\n" }}
|
| 9 |
-
{{- tool | tojson }}
|
| 10 |
-
{%- endfor %}
|
| 11 |
-
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
-
{%- else %}
|
| 13 |
-
{%- if messages[0].role == 'system' %}
|
| 14 |
-
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
-
{%- endif %}
|
| 16 |
-
{%- endif %}
|
| 17 |
-
{%- for message in messages %}
|
| 18 |
-
{%- if message.content is string %}
|
| 19 |
-
{%- set content = message.content %}
|
| 20 |
-
{%- else %}
|
| 21 |
-
{%- set content = '' %}
|
| 22 |
-
{%- endif %}
|
| 23 |
-
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 24 |
-
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 25 |
-
{%- elif message.role == "assistant" %}
|
| 26 |
-
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 27 |
-
{%- if message.tool_calls %}
|
| 28 |
-
{%- for tool_call in message.tool_calls %}
|
| 29 |
-
{%- if (loop.first and content) or (not loop.first) %}
|
| 30 |
-
{{- '\n' }}
|
| 31 |
-
{%- endif %}
|
| 32 |
-
{%- if tool_call.function %}
|
| 33 |
-
{%- set tool_call = tool_call.function %}
|
| 34 |
-
{%- endif %}
|
| 35 |
-
{{- '<tool_call>\n{"name": "' }}
|
| 36 |
-
{{- tool_call.name }}
|
| 37 |
-
{{- '", "arguments": ' }}
|
| 38 |
-
{%- if tool_call.arguments is string %}
|
| 39 |
-
{{- tool_call.arguments }}
|
| 40 |
-
{%- else %}
|
| 41 |
-
{{- tool_call.arguments | tojson }}
|
| 42 |
-
{%- endif %}
|
| 43 |
-
{{- '}\n</tool_call>' }}
|
| 44 |
-
{%- endfor %}
|
| 45 |
-
{%- endif %}
|
| 46 |
-
{{- '<|im_end|>\n' }}
|
| 47 |
-
{%- elif message.role == "tool" %}
|
| 48 |
-
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 49 |
-
{{- '<|im_start|>user' }}
|
| 50 |
-
{%- endif %}
|
| 51 |
-
{{- '\n<tool_response>\n' }}
|
| 52 |
-
{{- content }}
|
| 53 |
-
{{- '\n</tool_response>' }}
|
| 54 |
-
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 55 |
-
{{- '<|im_end|>\n' }}
|
| 56 |
-
{%- endif %}
|
| 57 |
-
{%- endif %}
|
| 58 |
-
{%- endfor %}
|
| 59 |
-
{%- if add_generation_prompt %}
|
| 60 |
-
{{- '<|im_start|>assistant\n' }}
|
| 61 |
-
{%- endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/merged/config.json
DELETED
|
@@ -1,68 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3ForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": 151643,
|
| 8 |
-
"dtype": "bfloat16",
|
| 9 |
-
"eos_token_id": 151645,
|
| 10 |
-
"head_dim": 128,
|
| 11 |
-
"hidden_act": "silu",
|
| 12 |
-
"hidden_size": 2560,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 9728,
|
| 15 |
-
"layer_types": [
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
-
"full_attention"
|
| 52 |
-
],
|
| 53 |
-
"max_position_embeddings": 262144,
|
| 54 |
-
"max_window_layers": 36,
|
| 55 |
-
"model_type": "qwen3",
|
| 56 |
-
"num_attention_heads": 32,
|
| 57 |
-
"num_hidden_layers": 36,
|
| 58 |
-
"num_key_value_heads": 8,
|
| 59 |
-
"rms_norm_eps": 1e-06,
|
| 60 |
-
"rope_scaling": null,
|
| 61 |
-
"rope_theta": 5000000,
|
| 62 |
-
"sliding_window": null,
|
| 63 |
-
"tie_word_embeddings": true,
|
| 64 |
-
"transformers_version": "4.57.1",
|
| 65 |
-
"use_cache": true,
|
| 66 |
-
"use_sliding_window": false,
|
| 67 |
-
"vocab_size": 151936
|
| 68 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/merged/generation_config.json
DELETED
|
@@ -1,13 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token_id": 151643,
|
| 3 |
-
"do_sample": true,
|
| 4 |
-
"eos_token_id": [
|
| 5 |
-
151645,
|
| 6 |
-
151643
|
| 7 |
-
],
|
| 8 |
-
"pad_token_id": 151643,
|
| 9 |
-
"temperature": 0.7,
|
| 10 |
-
"top_k": 20,
|
| 11 |
-
"top_p": 0.8,
|
| 12 |
-
"transformers_version": "4.57.1"
|
| 13 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/merged/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/merged/model-00001-of-00002.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3d5b235f390f3f30e218ef9c6fa5ccb15a48f015216bd50473170e887b84c123
|
| 3 |
-
size 4967215360
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/merged/model-00002-of-00002.safetensors
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:3365bad9646e1d666592d69cd37186abc904b0f465c384f4555713a349651e51
|
| 3 |
-
size 3077766632
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/merged/model.safetensors.index.json
DELETED
|
@@ -1,406 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"metadata": {
|
| 3 |
-
"total_parameters": 4022468096,
|
| 4 |
-
"total_size": 8044936192
|
| 5 |
-
},
|
| 6 |
-
"weight_map": {
|
| 7 |
-
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 8 |
-
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 9 |
-
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 10 |
-
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
-
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
-
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 13 |
-
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
-
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 15 |
-
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
-
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 17 |
-
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
-
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
-
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 20 |
-
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 21 |
-
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
-
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
-
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 24 |
-
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
-
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
-
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
-
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 28 |
-
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 29 |
-
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
-
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 31 |
-
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 32 |
-
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
-
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
-
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 35 |
-
"model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
-
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 37 |
-
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
-
"model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 39 |
-
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
-
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
-
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 42 |
-
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 43 |
-
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
-
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
-
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 46 |
-
"model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 47 |
-
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
-
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
-
"model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 50 |
-
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 51 |
-
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
-
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 53 |
-
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
-
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
-
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
-
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 57 |
-
"model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
-
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 59 |
-
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
-
"model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 61 |
-
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
-
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
-
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 64 |
-
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 65 |
-
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
-
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
-
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 68 |
-
"model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
-
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 70 |
-
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
-
"model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 72 |
-
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 73 |
-
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
-
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 75 |
-
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
-
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
-
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
-
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 79 |
-
"model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
-
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 81 |
-
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
-
"model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 83 |
-
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
-
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
-
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 86 |
-
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 87 |
-
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
-
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
-
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 90 |
-
"model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
-
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 92 |
-
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
-
"model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 94 |
-
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 95 |
-
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
-
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 97 |
-
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
-
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 99 |
-
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
-
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 101 |
-
"model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 102 |
-
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 103 |
-
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
-
"model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 105 |
-
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 106 |
-
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
-
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 108 |
-
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 109 |
-
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
-
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 111 |
-
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 112 |
-
"model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 113 |
-
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
-
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 115 |
-
"model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 116 |
-
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 117 |
-
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 118 |
-
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 119 |
-
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
-
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 121 |
-
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
-
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 123 |
-
"model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 124 |
-
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 125 |
-
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
-
"model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 127 |
-
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 128 |
-
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 129 |
-
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 130 |
-
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 131 |
-
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
-
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 133 |
-
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 134 |
-
"model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 135 |
-
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
-
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 137 |
-
"model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 138 |
-
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 139 |
-
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 140 |
-
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 141 |
-
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 142 |
-
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
-
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
-
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 145 |
-
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
-
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 147 |
-
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
-
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 149 |
-
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
-
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
-
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 152 |
-
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 153 |
-
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 154 |
-
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 155 |
-
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 156 |
-
"model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 157 |
-
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
-
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 159 |
-
"model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 160 |
-
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 161 |
-
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
-
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 163 |
-
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 164 |
-
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
-
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
-
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 167 |
-
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 168 |
-
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 169 |
-
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
-
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 171 |
-
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 172 |
-
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
-
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 174 |
-
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 175 |
-
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
-
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
-
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 178 |
-
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 179 |
-
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 180 |
-
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
-
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 182 |
-
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 183 |
-
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
-
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 185 |
-
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 186 |
-
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
-
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
-
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 189 |
-
"model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
-
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 191 |
-
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
-
"model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 193 |
-
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 194 |
-
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
-
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 196 |
-
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 197 |
-
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
-
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
-
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 200 |
-
"model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
-
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 202 |
-
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
-
"model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 204 |
-
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 205 |
-
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
-
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 207 |
-
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 208 |
-
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
-
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
-
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 211 |
-
"model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
-
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 213 |
-
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
-
"model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 215 |
-
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 216 |
-
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 217 |
-
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 218 |
-
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 219 |
-
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
-
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
-
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 222 |
-
"model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
-
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 224 |
-
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
-
"model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 226 |
-
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 227 |
-
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
-
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 229 |
-
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 230 |
-
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
-
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
-
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 233 |
-
"model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
-
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 235 |
-
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
-
"model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 237 |
-
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 238 |
-
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
-
"model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 240 |
-
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 241 |
-
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
-
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
-
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 244 |
-
"model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 245 |
-
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 246 |
-
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
-
"model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 248 |
-
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 249 |
-
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
-
"model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 251 |
-
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 252 |
-
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
-
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
-
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 255 |
-
"model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 256 |
-
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 257 |
-
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
-
"model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 259 |
-
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 260 |
-
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
-
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 262 |
-
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 263 |
-
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
-
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
-
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 266 |
-
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 267 |
-
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
-
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
-
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 270 |
-
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 271 |
-
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
-
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 273 |
-
"model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 274 |
-
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
-
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
-
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 277 |
-
"model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 278 |
-
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 279 |
-
"model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
-
"model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 281 |
-
"model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 282 |
-
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
-
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 284 |
-
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 285 |
-
"model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
-
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
-
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 288 |
-
"model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
-
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 290 |
-
"model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
-
"model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 292 |
-
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 293 |
-
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 294 |
-
"model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 295 |
-
"model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 296 |
-
"model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
-
"model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
-
"model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 299 |
-
"model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
-
"model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 301 |
-
"model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 302 |
-
"model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 303 |
-
"model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 304 |
-
"model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
-
"model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 306 |
-
"model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 307 |
-
"model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
-
"model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
-
"model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 310 |
-
"model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 311 |
-
"model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 312 |
-
"model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
-
"model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 314 |
-
"model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 315 |
-
"model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
-
"model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 317 |
-
"model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 318 |
-
"model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
-
"model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
-
"model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 321 |
-
"model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 322 |
-
"model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 323 |
-
"model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
-
"model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 325 |
-
"model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 326 |
-
"model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
-
"model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 328 |
-
"model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 329 |
-
"model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
-
"model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
-
"model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 332 |
-
"model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 333 |
-
"model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 334 |
-
"model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
-
"model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 336 |
-
"model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 337 |
-
"model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
-
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 339 |
-
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
-
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
-
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
-
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 343 |
-
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 344 |
-
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 345 |
-
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
-
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 347 |
-
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
-
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
-
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 350 |
-
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 351 |
-
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
-
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
-
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 354 |
-
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 355 |
-
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 356 |
-
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
-
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 358 |
-
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 359 |
-
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
-
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 361 |
-
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
-
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
-
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
-
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 365 |
-
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
-
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 367 |
-
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
-
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 369 |
-
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 370 |
-
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
-
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 372 |
-
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 373 |
-
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
-
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
-
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 376 |
-
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 377 |
-
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
-
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
-
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 380 |
-
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 381 |
-
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
-
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 383 |
-
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
-
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
-
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
-
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 387 |
-
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
-
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 389 |
-
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
-
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 391 |
-
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 392 |
-
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
-
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 394 |
-
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 395 |
-
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
-
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
-
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 398 |
-
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
-
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 400 |
-
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
-
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 402 |
-
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 403 |
-
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
-
"model.norm.weight": "model-00002-of-00002.safetensors"
|
| 405 |
-
}
|
| 406 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/merged/special_tokens_map.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<|im_start|>",
|
| 4 |
-
"<|im_end|>",
|
| 5 |
-
"<|object_ref_start|>",
|
| 6 |
-
"<|object_ref_end|>",
|
| 7 |
-
"<|box_start|>",
|
| 8 |
-
"<|box_end|>",
|
| 9 |
-
"<|quad_start|>",
|
| 10 |
-
"<|quad_end|>",
|
| 11 |
-
"<|vision_start|>",
|
| 12 |
-
"<|vision_end|>",
|
| 13 |
-
"<|vision_pad|>",
|
| 14 |
-
"<|image_pad|>",
|
| 15 |
-
"<|video_pad|>"
|
| 16 |
-
],
|
| 17 |
-
"eos_token": {
|
| 18 |
-
"content": "<|im_end|>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": false,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
},
|
| 24 |
-
"pad_token": {
|
| 25 |
-
"content": "<|endoftext|>",
|
| 26 |
-
"lstrip": false,
|
| 27 |
-
"normalized": false,
|
| 28 |
-
"rstrip": false,
|
| 29 |
-
"single_word": false
|
| 30 |
-
}
|
| 31 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/merged/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
-
size 11422654
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/merged/tokenizer_config.json
DELETED
|
@@ -1,239 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"added_tokens_decoder": {
|
| 4 |
-
"151643": {
|
| 5 |
-
"content": "<|endoftext|>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": false,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"151644": {
|
| 13 |
-
"content": "<|im_start|>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
},
|
| 20 |
-
"151645": {
|
| 21 |
-
"content": "<|im_end|>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": false,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false,
|
| 26 |
-
"special": true
|
| 27 |
-
},
|
| 28 |
-
"151646": {
|
| 29 |
-
"content": "<|object_ref_start|>",
|
| 30 |
-
"lstrip": false,
|
| 31 |
-
"normalized": false,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": true
|
| 35 |
-
},
|
| 36 |
-
"151647": {
|
| 37 |
-
"content": "<|object_ref_end|>",
|
| 38 |
-
"lstrip": false,
|
| 39 |
-
"normalized": false,
|
| 40 |
-
"rstrip": false,
|
| 41 |
-
"single_word": false,
|
| 42 |
-
"special": true
|
| 43 |
-
},
|
| 44 |
-
"151648": {
|
| 45 |
-
"content": "<|box_start|>",
|
| 46 |
-
"lstrip": false,
|
| 47 |
-
"normalized": false,
|
| 48 |
-
"rstrip": false,
|
| 49 |
-
"single_word": false,
|
| 50 |
-
"special": true
|
| 51 |
-
},
|
| 52 |
-
"151649": {
|
| 53 |
-
"content": "<|box_end|>",
|
| 54 |
-
"lstrip": false,
|
| 55 |
-
"normalized": false,
|
| 56 |
-
"rstrip": false,
|
| 57 |
-
"single_word": false,
|
| 58 |
-
"special": true
|
| 59 |
-
},
|
| 60 |
-
"151650": {
|
| 61 |
-
"content": "<|quad_start|>",
|
| 62 |
-
"lstrip": false,
|
| 63 |
-
"normalized": false,
|
| 64 |
-
"rstrip": false,
|
| 65 |
-
"single_word": false,
|
| 66 |
-
"special": true
|
| 67 |
-
},
|
| 68 |
-
"151651": {
|
| 69 |
-
"content": "<|quad_end|>",
|
| 70 |
-
"lstrip": false,
|
| 71 |
-
"normalized": false,
|
| 72 |
-
"rstrip": false,
|
| 73 |
-
"single_word": false,
|
| 74 |
-
"special": true
|
| 75 |
-
},
|
| 76 |
-
"151652": {
|
| 77 |
-
"content": "<|vision_start|>",
|
| 78 |
-
"lstrip": false,
|
| 79 |
-
"normalized": false,
|
| 80 |
-
"rstrip": false,
|
| 81 |
-
"single_word": false,
|
| 82 |
-
"special": true
|
| 83 |
-
},
|
| 84 |
-
"151653": {
|
| 85 |
-
"content": "<|vision_end|>",
|
| 86 |
-
"lstrip": false,
|
| 87 |
-
"normalized": false,
|
| 88 |
-
"rstrip": false,
|
| 89 |
-
"single_word": false,
|
| 90 |
-
"special": true
|
| 91 |
-
},
|
| 92 |
-
"151654": {
|
| 93 |
-
"content": "<|vision_pad|>",
|
| 94 |
-
"lstrip": false,
|
| 95 |
-
"normalized": false,
|
| 96 |
-
"rstrip": false,
|
| 97 |
-
"single_word": false,
|
| 98 |
-
"special": true
|
| 99 |
-
},
|
| 100 |
-
"151655": {
|
| 101 |
-
"content": "<|image_pad|>",
|
| 102 |
-
"lstrip": false,
|
| 103 |
-
"normalized": false,
|
| 104 |
-
"rstrip": false,
|
| 105 |
-
"single_word": false,
|
| 106 |
-
"special": true
|
| 107 |
-
},
|
| 108 |
-
"151656": {
|
| 109 |
-
"content": "<|video_pad|>",
|
| 110 |
-
"lstrip": false,
|
| 111 |
-
"normalized": false,
|
| 112 |
-
"rstrip": false,
|
| 113 |
-
"single_word": false,
|
| 114 |
-
"special": true
|
| 115 |
-
},
|
| 116 |
-
"151657": {
|
| 117 |
-
"content": "<tool_call>",
|
| 118 |
-
"lstrip": false,
|
| 119 |
-
"normalized": false,
|
| 120 |
-
"rstrip": false,
|
| 121 |
-
"single_word": false,
|
| 122 |
-
"special": false
|
| 123 |
-
},
|
| 124 |
-
"151658": {
|
| 125 |
-
"content": "</tool_call>",
|
| 126 |
-
"lstrip": false,
|
| 127 |
-
"normalized": false,
|
| 128 |
-
"rstrip": false,
|
| 129 |
-
"single_word": false,
|
| 130 |
-
"special": false
|
| 131 |
-
},
|
| 132 |
-
"151659": {
|
| 133 |
-
"content": "<|fim_prefix|>",
|
| 134 |
-
"lstrip": false,
|
| 135 |
-
"normalized": false,
|
| 136 |
-
"rstrip": false,
|
| 137 |
-
"single_word": false,
|
| 138 |
-
"special": false
|
| 139 |
-
},
|
| 140 |
-
"151660": {
|
| 141 |
-
"content": "<|fim_middle|>",
|
| 142 |
-
"lstrip": false,
|
| 143 |
-
"normalized": false,
|
| 144 |
-
"rstrip": false,
|
| 145 |
-
"single_word": false,
|
| 146 |
-
"special": false
|
| 147 |
-
},
|
| 148 |
-
"151661": {
|
| 149 |
-
"content": "<|fim_suffix|>",
|
| 150 |
-
"lstrip": false,
|
| 151 |
-
"normalized": false,
|
| 152 |
-
"rstrip": false,
|
| 153 |
-
"single_word": false,
|
| 154 |
-
"special": false
|
| 155 |
-
},
|
| 156 |
-
"151662": {
|
| 157 |
-
"content": "<|fim_pad|>",
|
| 158 |
-
"lstrip": false,
|
| 159 |
-
"normalized": false,
|
| 160 |
-
"rstrip": false,
|
| 161 |
-
"single_word": false,
|
| 162 |
-
"special": false
|
| 163 |
-
},
|
| 164 |
-
"151663": {
|
| 165 |
-
"content": "<|repo_name|>",
|
| 166 |
-
"lstrip": false,
|
| 167 |
-
"normalized": false,
|
| 168 |
-
"rstrip": false,
|
| 169 |
-
"single_word": false,
|
| 170 |
-
"special": false
|
| 171 |
-
},
|
| 172 |
-
"151664": {
|
| 173 |
-
"content": "<|file_sep|>",
|
| 174 |
-
"lstrip": false,
|
| 175 |
-
"normalized": false,
|
| 176 |
-
"rstrip": false,
|
| 177 |
-
"single_word": false,
|
| 178 |
-
"special": false
|
| 179 |
-
},
|
| 180 |
-
"151665": {
|
| 181 |
-
"content": "<tool_response>",
|
| 182 |
-
"lstrip": false,
|
| 183 |
-
"normalized": false,
|
| 184 |
-
"rstrip": false,
|
| 185 |
-
"single_word": false,
|
| 186 |
-
"special": false
|
| 187 |
-
},
|
| 188 |
-
"151666": {
|
| 189 |
-
"content": "</tool_response>",
|
| 190 |
-
"lstrip": false,
|
| 191 |
-
"normalized": false,
|
| 192 |
-
"rstrip": false,
|
| 193 |
-
"single_word": false,
|
| 194 |
-
"special": false
|
| 195 |
-
},
|
| 196 |
-
"151667": {
|
| 197 |
-
"content": "<think>",
|
| 198 |
-
"lstrip": false,
|
| 199 |
-
"normalized": false,
|
| 200 |
-
"rstrip": false,
|
| 201 |
-
"single_word": false,
|
| 202 |
-
"special": false
|
| 203 |
-
},
|
| 204 |
-
"151668": {
|
| 205 |
-
"content": "</think>",
|
| 206 |
-
"lstrip": false,
|
| 207 |
-
"normalized": false,
|
| 208 |
-
"rstrip": false,
|
| 209 |
-
"single_word": false,
|
| 210 |
-
"special": false
|
| 211 |
-
}
|
| 212 |
-
},
|
| 213 |
-
"additional_special_tokens": [
|
| 214 |
-
"<|im_start|>",
|
| 215 |
-
"<|im_end|>",
|
| 216 |
-
"<|object_ref_start|>",
|
| 217 |
-
"<|object_ref_end|>",
|
| 218 |
-
"<|box_start|>",
|
| 219 |
-
"<|box_end|>",
|
| 220 |
-
"<|quad_start|>",
|
| 221 |
-
"<|quad_end|>",
|
| 222 |
-
"<|vision_start|>",
|
| 223 |
-
"<|vision_end|>",
|
| 224 |
-
"<|vision_pad|>",
|
| 225 |
-
"<|image_pad|>",
|
| 226 |
-
"<|video_pad|>"
|
| 227 |
-
],
|
| 228 |
-
"bos_token": null,
|
| 229 |
-
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = '' %}\n {%- endif %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}",
|
| 230 |
-
"clean_up_tokenization_spaces": false,
|
| 231 |
-
"eos_token": "<|im_end|>",
|
| 232 |
-
"errors": "replace",
|
| 233 |
-
"model_max_length": 1010000,
|
| 234 |
-
"pad_token": "<|endoftext|>",
|
| 235 |
-
"split_special_tokens": false,
|
| 236 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 237 |
-
"unk_token": null,
|
| 238 |
-
"add_bos_token": false
|
| 239 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/merged/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
-
size 11422650
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/knowledge/atomic_sft_lora_50ep/tokenizer_config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"backend": "tokenizers",
|
| 4 |
-
"bos_token": null,
|
| 5 |
-
"clean_up_tokenization_spaces": false,
|
| 6 |
-
"eos_token": "<|im_end|>",
|
| 7 |
-
"errors": "replace",
|
| 8 |
-
"extra_special_tokens": [
|
| 9 |
-
"<|im_start|>",
|
| 10 |
-
"<|im_end|>",
|
| 11 |
-
"<|object_ref_start|>",
|
| 12 |
-
"<|object_ref_end|>",
|
| 13 |
-
"<|box_start|>",
|
| 14 |
-
"<|box_end|>",
|
| 15 |
-
"<|quad_start|>",
|
| 16 |
-
"<|quad_end|>",
|
| 17 |
-
"<|vision_start|>",
|
| 18 |
-
"<|vision_end|>",
|
| 19 |
-
"<|vision_pad|>",
|
| 20 |
-
"<|image_pad|>",
|
| 21 |
-
"<|video_pad|>"
|
| 22 |
-
],
|
| 23 |
-
"is_local": true,
|
| 24 |
-
"model_max_length": 1010000,
|
| 25 |
-
"pad_token": "<|endoftext|>",
|
| 26 |
-
"split_special_tokens": false,
|
| 27 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
-
"unk_token": null
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/math_operations/compositional_full_sft_n_steps_2/chat_template.jinja
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
| 2 |
-
' + message['content'] + '<|im_end|>' + '
|
| 3 |
-
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 4 |
-
' }}{% endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/math_operations/compositional_full_sft_n_steps_2/config.json
DELETED
|
@@ -1,71 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3ForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": null,
|
| 8 |
-
"dtype": "bfloat16",
|
| 9 |
-
"eos_token_id": 151645,
|
| 10 |
-
"head_dim": 128,
|
| 11 |
-
"hidden_act": "silu",
|
| 12 |
-
"hidden_size": 2560,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 9728,
|
| 15 |
-
"layer_types": [
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
-
"full_attention"
|
| 52 |
-
],
|
| 53 |
-
"max_position_embeddings": 262144,
|
| 54 |
-
"max_window_layers": 36,
|
| 55 |
-
"model_type": "qwen3",
|
| 56 |
-
"num_attention_heads": 32,
|
| 57 |
-
"num_hidden_layers": 36,
|
| 58 |
-
"num_key_value_heads": 8,
|
| 59 |
-
"pad_token_id": 151643,
|
| 60 |
-
"rms_norm_eps": 1e-06,
|
| 61 |
-
"rope_parameters": {
|
| 62 |
-
"rope_theta": 5000000,
|
| 63 |
-
"rope_type": "default"
|
| 64 |
-
},
|
| 65 |
-
"sliding_window": null,
|
| 66 |
-
"tie_word_embeddings": true,
|
| 67 |
-
"transformers_version": "5.0.0",
|
| 68 |
-
"use_cache": false,
|
| 69 |
-
"use_sliding_window": false,
|
| 70 |
-
"vocab_size": 151936
|
| 71 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/math_operations/compositional_full_sft_n_steps_2/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
|
| 3 |
-
size 11422650
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/math_operations/compositional_full_sft_n_steps_2/tokenizer_config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"backend": "tokenizers",
|
| 4 |
-
"bos_token": null,
|
| 5 |
-
"clean_up_tokenization_spaces": false,
|
| 6 |
-
"eos_token": "<|im_end|>",
|
| 7 |
-
"errors": "replace",
|
| 8 |
-
"extra_special_tokens": [
|
| 9 |
-
"<|im_start|>",
|
| 10 |
-
"<|im_end|>",
|
| 11 |
-
"<|object_ref_start|>",
|
| 12 |
-
"<|object_ref_end|>",
|
| 13 |
-
"<|box_start|>",
|
| 14 |
-
"<|box_end|>",
|
| 15 |
-
"<|quad_start|>",
|
| 16 |
-
"<|quad_end|>",
|
| 17 |
-
"<|vision_start|>",
|
| 18 |
-
"<|vision_end|>",
|
| 19 |
-
"<|vision_pad|>",
|
| 20 |
-
"<|image_pad|>",
|
| 21 |
-
"<|video_pad|>"
|
| 22 |
-
],
|
| 23 |
-
"is_local": true,
|
| 24 |
-
"model_max_length": 1010000,
|
| 25 |
-
"pad_token": "<|endoftext|>",
|
| 26 |
-
"split_special_tokens": false,
|
| 27 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
-
"unk_token": null
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/math_operations/full_sft_50k_lr5e5/README.md
DELETED
|
@@ -1,132 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
library_name: transformers
|
| 3 |
-
tags:
|
| 4 |
-
- generated_from_trainer
|
| 5 |
-
datasets:
|
| 6 |
-
- /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/data/math_operations/primitive_atomic_balanced_sft_50k/balanced_train_alpaca.jsonl
|
| 7 |
-
model-index:
|
| 8 |
-
- name: home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/checkpoints/math_operations/full_sft_50k_lr5e5
|
| 9 |
-
results: []
|
| 10 |
-
---
|
| 11 |
-
|
| 12 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
-
|
| 15 |
-
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
|
| 16 |
-
<details><summary>See axolotl config</summary>
|
| 17 |
-
|
| 18 |
-
axolotl version: `0.15.0.dev0`
|
| 19 |
-
```yaml
|
| 20 |
-
# Qwen3-4B full fine-tuning SFT — LR 5e-5
|
| 21 |
-
|
| 22 |
-
base_model: /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/models/Qwen/Qwen3-4B-Instruct-2507
|
| 23 |
-
|
| 24 |
-
load_in_8bit: false
|
| 25 |
-
load_in_4bit: false
|
| 26 |
-
strict: false
|
| 27 |
-
|
| 28 |
-
datasets:
|
| 29 |
-
- path: /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/data/math_operations/primitive_atomic_balanced_sft_50k/balanced_train_alpaca.jsonl
|
| 30 |
-
type: alpaca
|
| 31 |
-
dataset_prepared_path:
|
| 32 |
-
val_set_size: 0
|
| 33 |
-
chat_template: chatml
|
| 34 |
-
|
| 35 |
-
test_datasets:
|
| 36 |
-
- path: /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/data/math_operations/primitive_atomic_balanced_sft_50k/balanced_val_alpaca.jsonl
|
| 37 |
-
type: alpaca
|
| 38 |
-
|
| 39 |
-
output_dir: /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/checkpoints/math_operations/full_sft_50k_lr5e5
|
| 40 |
-
|
| 41 |
-
sequence_len: 2048
|
| 42 |
-
sample_packing: true
|
| 43 |
-
eval_sample_packing: true
|
| 44 |
-
|
| 45 |
-
gradient_accumulation_steps: 8
|
| 46 |
-
micro_batch_size: 1
|
| 47 |
-
num_epochs: 3
|
| 48 |
-
optimizer: adamw_torch_fused
|
| 49 |
-
lr_scheduler: cosine
|
| 50 |
-
learning_rate: 5e-5
|
| 51 |
-
|
| 52 |
-
bf16: auto
|
| 53 |
-
tf32: true
|
| 54 |
-
|
| 55 |
-
gradient_checkpointing: true
|
| 56 |
-
gradient_checkpointing_kwargs:
|
| 57 |
-
use_reentrant: false
|
| 58 |
-
|
| 59 |
-
logging_steps: 10
|
| 60 |
-
flash_attention: true
|
| 61 |
-
warmup_ratio: 0.1
|
| 62 |
-
evals_per_epoch: 2
|
| 63 |
-
saves_per_epoch: 1
|
| 64 |
-
save_total_limit: 1
|
| 65 |
-
weight_decay: 0.01
|
| 66 |
-
|
| 67 |
-
wandb_project: math_operations_sft
|
| 68 |
-
wandb_name: qwen3-4b-full-sft-50k-lr5e5
|
| 69 |
-
wandb_log_model: "false"
|
| 70 |
-
|
| 71 |
-
special_tokens:
|
| 72 |
-
|
| 73 |
-
```
|
| 74 |
-
|
| 75 |
-
</details><br>
|
| 76 |
-
|
| 77 |
-
# home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/checkpoints/math_operations/full_sft_50k_lr5e5
|
| 78 |
-
|
| 79 |
-
This model was trained from scratch on the /home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/data/math_operations/primitive_atomic_balanced_sft_50k/balanced_train_alpaca.jsonl dataset.
|
| 80 |
-
It achieves the following results on the evaluation set:
|
| 81 |
-
- Loss: 0.0001
|
| 82 |
-
- Ppl: 1.0001
|
| 83 |
-
- Memory/max Active (gib): 33.95
|
| 84 |
-
- Memory/max Allocated (gib): 33.95
|
| 85 |
-
- Memory/device Reserved (gib): 35.97
|
| 86 |
-
|
| 87 |
-
## Model description
|
| 88 |
-
|
| 89 |
-
More information needed
|
| 90 |
-
|
| 91 |
-
## Intended uses & limitations
|
| 92 |
-
|
| 93 |
-
More information needed
|
| 94 |
-
|
| 95 |
-
## Training and evaluation data
|
| 96 |
-
|
| 97 |
-
More information needed
|
| 98 |
-
|
| 99 |
-
## Training procedure
|
| 100 |
-
|
| 101 |
-
### Training hyperparameters
|
| 102 |
-
|
| 103 |
-
The following hyperparameters were used during training:
|
| 104 |
-
- learning_rate: 5e-05
|
| 105 |
-
- train_batch_size: 1
|
| 106 |
-
- eval_batch_size: 1
|
| 107 |
-
- seed: 42
|
| 108 |
-
- gradient_accumulation_steps: 8
|
| 109 |
-
- total_train_batch_size: 8
|
| 110 |
-
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 111 |
-
- lr_scheduler_type: cosine
|
| 112 |
-
- lr_scheduler_warmup_steps: 312
|
| 113 |
-
- training_steps: 3123
|
| 114 |
-
|
| 115 |
-
### Training results
|
| 116 |
-
|
| 117 |
-
| Training Loss | Epoch | Step | Validation Loss | Ppl | Active (gib) | Allocated (gib) | Reserved (gib) |
|
| 118 |
-
|:-------------:|:------:|:----:|:---------------:|:------:|:------------:|:---------------:|:--------------:|
|
| 119 |
-
| No log | 0 | 0 | 0.8898 | 2.4345 | 10.41 | 10.41 | 10.64 |
|
| 120 |
-
| 0.0029 | 0.5002 | 521 | 0.0023 | 1.0023 | 33.97 | 33.97 | 36.5 |
|
| 121 |
-
| 0.0003 | 1.0 | 1042 | 0.0005 | 1.0005 | 33.95 | 33.95 | 35.97 |
|
| 122 |
-
| 0.0003 | 1.5002 | 1563 | 0.0003 | 1.0003 | 33.95 | 33.95 | 35.97 |
|
| 123 |
-
| 0.0002 | 2.0 | 2084 | 0.0001 | 1.0001 | 33.95 | 33.95 | 35.97 |
|
| 124 |
-
| 0.0001 | 2.5002 | 2605 | 0.0001 | 1.0001 | 33.95 | 33.95 | 35.97 |
|
| 125 |
-
|
| 126 |
-
|
| 127 |
-
### Framework versions
|
| 128 |
-
|
| 129 |
-
- Transformers 5.0.0
|
| 130 |
-
- Pytorch 2.8.0+cu128
|
| 131 |
-
- Datasets 4.5.0
|
| 132 |
-
- Tokenizers 0.22.2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/math_operations/full_sft_50k_lr5e5/chat_template.jinja
DELETED
|
@@ -1,4 +0,0 @@
|
|
| 1 |
-
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
| 2 |
-
' + message['content'] + '<|im_end|>' + '
|
| 3 |
-
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 4 |
-
' }}{% endif %}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/math_operations/full_sft_50k_lr5e5/config.json
DELETED
|
@@ -1,71 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"Qwen3ForCausalLM"
|
| 4 |
-
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": null,
|
| 8 |
-
"dtype": "bfloat16",
|
| 9 |
-
"eos_token_id": 151645,
|
| 10 |
-
"head_dim": 128,
|
| 11 |
-
"hidden_act": "silu",
|
| 12 |
-
"hidden_size": 2560,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 9728,
|
| 15 |
-
"layer_types": [
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention",
|
| 44 |
-
"full_attention",
|
| 45 |
-
"full_attention",
|
| 46 |
-
"full_attention",
|
| 47 |
-
"full_attention",
|
| 48 |
-
"full_attention",
|
| 49 |
-
"full_attention",
|
| 50 |
-
"full_attention",
|
| 51 |
-
"full_attention"
|
| 52 |
-
],
|
| 53 |
-
"max_position_embeddings": 262144,
|
| 54 |
-
"max_window_layers": 36,
|
| 55 |
-
"model_type": "qwen3",
|
| 56 |
-
"num_attention_heads": 32,
|
| 57 |
-
"num_hidden_layers": 36,
|
| 58 |
-
"num_key_value_heads": 8,
|
| 59 |
-
"pad_token_id": 151643,
|
| 60 |
-
"rms_norm_eps": 1e-06,
|
| 61 |
-
"rope_parameters": {
|
| 62 |
-
"rope_theta": 5000000,
|
| 63 |
-
"rope_type": "default"
|
| 64 |
-
},
|
| 65 |
-
"sliding_window": null,
|
| 66 |
-
"tie_word_embeddings": true,
|
| 67 |
-
"transformers_version": "5.0.0",
|
| 68 |
-
"use_cache": false,
|
| 69 |
-
"use_sliding_window": false,
|
| 70 |
-
"vocab_size": 151936
|
| 71 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/math_operations/full_sft_50k_lr5e5/eval_results/balanced_test_alpaca_converted.jsonl
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/math_operations/full_sft_50k_lr5e5/eval_results/balanced_test_alpaca_results.jsonl
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoints/math_operations/full_sft_50k_lr5e5/eval_results/eval_results.csv
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 1 |
-
category,filename,total,correct,accuracy,format_found,format_accuracy,errors_count
|
| 2 |
-
math_operations,balanced_test_alpaca_results,200,198,99.00,200,100.00,2
|
| 3 |
-
math_operations,balanced_test_alpaca_results,200,47,23.50,200,100.00,153
|
| 4 |
-
math_operations,test_alpaca_results,200,0,0.00,196,98.00,200
|
| 5 |
-
math_operations,op_A_test_alpaca_results,200,0,0.00,161,80.50,200
|
| 6 |
-
math_operations,op_B_test_alpaca_results,200,2,1.00,190,95.00,198
|
| 7 |
-
math_operations,op_C_test_alpaca_results,200,0,0.00,198,99.00,200
|
| 8 |
-
math_operations,op_D_test_alpaca_results,200,2,1.00,174,87.00,198
|
| 9 |
-
math_operations,op_E_test_alpaca_results,200,2,1.00,200,100.00,198
|
| 10 |
-
math_operations,op_F_test_alpaca_results,200,1,0.50,198,99.00,199
|
| 11 |
-
math_operations,op_G_test_alpaca_results,200,0,0.00,200,100.00,200
|
| 12 |
-
math_operations,op_H_test_alpaca_results,200,0,0.00,200,100.00,200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/math_operations/full_sft_50k_lr5e5/eval_results/eval_summary.json
DELETED
|
@@ -1,19 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"overall": {
|
| 3 |
-
"total": 200,
|
| 4 |
-
"correct": 0,
|
| 5 |
-
"accuracy": 0.0,
|
| 6 |
-
"format_found": 200,
|
| 7 |
-
"format_accuracy": 100.0
|
| 8 |
-
},
|
| 9 |
-
"per_operation": {
|
| 10 |
-
"A": {
|
| 11 |
-
"total": 200,
|
| 12 |
-
"correct": 0,
|
| 13 |
-
"accuracy": 0.0,
|
| 14 |
-
"format_found": 200
|
| 15 |
-
}
|
| 16 |
-
},
|
| 17 |
-
"n_errors": 200,
|
| 18 |
-
"results_file": "/home/jiaruil5/math_rl/mix_teachers/r3lit_rl/mix_teachers/checkpoints/math_operations/full_sft_50k_lr5e5/eval_results/op_H_test_alpaca_results.jsonl"
|
| 19 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints/math_operations/full_sft_50k_lr5e5/eval_results/op_A_test_alpaca_converted.jsonl
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|