vision_on
Browse files- .gitattributes +2 -0
- README.md +63 -0
- adapter_config.json +351 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +16 -0
- all_results.json +8 -0
- chat_template.json +3 -0
- checkpoint-620/README.md +202 -0
- checkpoint-620/adapter_config.json +351 -0
- checkpoint-620/adapter_model.safetensors +3 -0
- checkpoint-620/added_tokens.json +16 -0
- checkpoint-620/chat_template.json +3 -0
- checkpoint-620/merges.txt +0 -0
- checkpoint-620/optimizer.pt +3 -0
- checkpoint-620/preprocessor_config.json +29 -0
- checkpoint-620/rng_state_0.pth +3 -0
- checkpoint-620/rng_state_1.pth +3 -0
- checkpoint-620/scaler.pt +3 -0
- checkpoint-620/scheduler.pt +3 -0
- checkpoint-620/special_tokens_map.json +31 -0
- checkpoint-620/tokenizer.json +3 -0
- checkpoint-620/tokenizer_config.json +145 -0
- checkpoint-620/trainer_state.json +467 -0
- checkpoint-620/training_args.bin +3 -0
- checkpoint-620/vocab.json +0 -0
- merges.txt +0 -0
- preprocessor_config.json +29 -0
- runs/Mar01_11-08-39_2eb495d65f62/events.out.tfevents.1740827396.2eb495d65f62.125.0 +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +145 -0
- train_results.json +8 -0
- trainer_log.jsonl +63 -0
- trainer_state.json +476 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-620/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: other
|
| 4 |
+
base_model: saim1212/qwen2_2b_git2
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: qwen2vl_lora_16lr_7b
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# qwen2vl_lora_16lr_7b
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [saim1212/qwen2_2b_git2](https://huggingface.co/saim1212/qwen2_2b_git2) on the talk2car dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 2e-05
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 2
|
| 44 |
+
- gradient_accumulation_steps: 2
|
| 45 |
+
- total_train_batch_size: 8
|
| 46 |
+
- total_eval_batch_size: 16
|
| 47 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 10.0
|
| 51 |
+
- mixed_precision_training: Native AMP
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
### Framework versions
|
| 58 |
+
|
| 59 |
+
- PEFT 0.12.0
|
| 60 |
+
- Transformers 4.49.0
|
| 61 |
+
- Pytorch 2.4.0
|
| 62 |
+
- Datasets 3.1.0
|
| 63 |
+
- Tokenizers 0.21.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,351 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "saim1212/qwen2_2b_git2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"visual.blocks.31.attn.qkv",
|
| 24 |
+
"visual.blocks.26.mlp.fc1",
|
| 25 |
+
"model.layers.21.mlp.gate_proj",
|
| 26 |
+
"model.layers.22.self_attn.v_proj",
|
| 27 |
+
"model.layers.17.self_attn.o_proj",
|
| 28 |
+
"model.layers.26.self_attn.v_proj",
|
| 29 |
+
"visual.blocks.24.mlp.fc1",
|
| 30 |
+
"model.layers.2.self_attn.o_proj",
|
| 31 |
+
"model.layers.21.self_attn.o_proj",
|
| 32 |
+
"model.layers.1.self_attn.k_proj",
|
| 33 |
+
"model.layers.7.self_attn.k_proj",
|
| 34 |
+
"visual.blocks.12.attn.qkv",
|
| 35 |
+
"visual.blocks.22.mlp.fc1",
|
| 36 |
+
"model.layers.26.mlp.down_proj",
|
| 37 |
+
"model.layers.11.self_attn.v_proj",
|
| 38 |
+
"visual.blocks.23.attn.proj",
|
| 39 |
+
"model.layers.21.self_attn.v_proj",
|
| 40 |
+
"model.layers.15.self_attn.k_proj",
|
| 41 |
+
"model.layers.14.mlp.down_proj",
|
| 42 |
+
"model.layers.21.mlp.up_proj",
|
| 43 |
+
"model.layers.0.mlp.down_proj",
|
| 44 |
+
"visual.blocks.17.mlp.fc2",
|
| 45 |
+
"model.layers.4.self_attn.k_proj",
|
| 46 |
+
"model.layers.16.mlp.gate_proj",
|
| 47 |
+
"visual.blocks.18.attn.qkv",
|
| 48 |
+
"model.layers.17.mlp.gate_proj",
|
| 49 |
+
"model.layers.3.mlp.gate_proj",
|
| 50 |
+
"visual.blocks.20.attn.qkv",
|
| 51 |
+
"visual.blocks.23.mlp.fc2",
|
| 52 |
+
"model.layers.15.self_attn.v_proj",
|
| 53 |
+
"model.layers.20.mlp.down_proj",
|
| 54 |
+
"model.layers.7.mlp.gate_proj",
|
| 55 |
+
"model.layers.6.self_attn.k_proj",
|
| 56 |
+
"model.layers.18.self_attn.o_proj",
|
| 57 |
+
"visual.blocks.11.mlp.fc1",
|
| 58 |
+
"model.layers.15.mlp.down_proj",
|
| 59 |
+
"model.layers.19.self_attn.q_proj",
|
| 60 |
+
"visual.blocks.16.attn.proj",
|
| 61 |
+
"model.layers.15.self_attn.o_proj",
|
| 62 |
+
"visual.blocks.2.attn.proj",
|
| 63 |
+
"visual.blocks.12.attn.proj",
|
| 64 |
+
"model.layers.27.mlp.gate_proj",
|
| 65 |
+
"model.layers.9.mlp.gate_proj",
|
| 66 |
+
"model.layers.9.self_attn.v_proj",
|
| 67 |
+
"visual.blocks.22.mlp.fc2",
|
| 68 |
+
"model.layers.27.self_attn.q_proj",
|
| 69 |
+
"visual.blocks.17.attn.proj",
|
| 70 |
+
"model.layers.0.self_attn.o_proj",
|
| 71 |
+
"visual.blocks.16.mlp.fc2",
|
| 72 |
+
"model.layers.19.mlp.up_proj",
|
| 73 |
+
"visual.blocks.23.attn.qkv",
|
| 74 |
+
"visual.blocks.25.attn.proj",
|
| 75 |
+
"model.layers.12.mlp.up_proj",
|
| 76 |
+
"model.layers.14.mlp.gate_proj",
|
| 77 |
+
"visual.blocks.29.attn.proj",
|
| 78 |
+
"model.layers.13.mlp.up_proj",
|
| 79 |
+
"visual.blocks.21.attn.proj",
|
| 80 |
+
"model.layers.23.self_attn.v_proj",
|
| 81 |
+
"model.layers.22.self_attn.q_proj",
|
| 82 |
+
"visual.blocks.18.attn.proj",
|
| 83 |
+
"model.layers.27.self_attn.o_proj",
|
| 84 |
+
"model.layers.24.mlp.down_proj",
|
| 85 |
+
"visual.blocks.0.mlp.fc1",
|
| 86 |
+
"model.layers.24.self_attn.v_proj",
|
| 87 |
+
"model.layers.5.mlp.up_proj",
|
| 88 |
+
"visual.blocks.27.mlp.fc2",
|
| 89 |
+
"model.layers.11.self_attn.k_proj",
|
| 90 |
+
"model.layers.10.self_attn.o_proj",
|
| 91 |
+
"model.layers.23.self_attn.k_proj",
|
| 92 |
+
"model.layers.1.mlp.gate_proj",
|
| 93 |
+
"model.layers.4.self_attn.q_proj",
|
| 94 |
+
"model.layers.25.self_attn.o_proj",
|
| 95 |
+
"model.layers.7.mlp.up_proj",
|
| 96 |
+
"model.layers.1.self_attn.o_proj",
|
| 97 |
+
"model.layers.18.mlp.up_proj",
|
| 98 |
+
"visual.blocks.19.mlp.fc2",
|
| 99 |
+
"model.layers.24.mlp.gate_proj",
|
| 100 |
+
"visual.blocks.25.mlp.fc2",
|
| 101 |
+
"model.layers.22.self_attn.o_proj",
|
| 102 |
+
"model.layers.21.self_attn.k_proj",
|
| 103 |
+
"model.layers.3.mlp.up_proj",
|
| 104 |
+
"model.layers.0.self_attn.k_proj",
|
| 105 |
+
"visual.blocks.13.attn.qkv",
|
| 106 |
+
"model.layers.26.self_attn.q_proj",
|
| 107 |
+
"model.layers.25.mlp.gate_proj",
|
| 108 |
+
"visual.blocks.7.attn.proj",
|
| 109 |
+
"visual.blocks.24.mlp.fc2",
|
| 110 |
+
"model.layers.2.mlp.gate_proj",
|
| 111 |
+
"model.layers.0.self_attn.q_proj",
|
| 112 |
+
"visual.blocks.15.attn.proj",
|
| 113 |
+
"model.layers.27.self_attn.v_proj",
|
| 114 |
+
"model.layers.27.mlp.down_proj",
|
| 115 |
+
"model.layers.0.mlp.up_proj",
|
| 116 |
+
"model.layers.17.self_attn.v_proj",
|
| 117 |
+
"model.layers.22.mlp.gate_proj",
|
| 118 |
+
"visual.blocks.28.mlp.fc1",
|
| 119 |
+
"model.layers.3.self_attn.v_proj",
|
| 120 |
+
"model.layers.13.self_attn.q_proj",
|
| 121 |
+
"model.layers.15.mlp.gate_proj",
|
| 122 |
+
"model.layers.11.mlp.up_proj",
|
| 123 |
+
"model.layers.10.self_attn.v_proj",
|
| 124 |
+
"model.layers.17.self_attn.q_proj",
|
| 125 |
+
"model.layers.14.self_attn.k_proj",
|
| 126 |
+
"visual.blocks.6.attn.proj",
|
| 127 |
+
"model.layers.2.self_attn.v_proj",
|
| 128 |
+
"model.layers.8.self_attn.o_proj",
|
| 129 |
+
"model.layers.3.self_attn.q_proj",
|
| 130 |
+
"model.layers.11.self_attn.o_proj",
|
| 131 |
+
"model.layers.6.self_attn.v_proj",
|
| 132 |
+
"model.layers.6.mlp.up_proj",
|
| 133 |
+
"visual.blocks.27.attn.proj",
|
| 134 |
+
"model.layers.13.self_attn.o_proj",
|
| 135 |
+
"model.layers.8.self_attn.q_proj",
|
| 136 |
+
"visual.blocks.28.mlp.fc2",
|
| 137 |
+
"visual.blocks.22.attn.qkv",
|
| 138 |
+
"model.layers.3.mlp.down_proj",
|
| 139 |
+
"model.layers.7.self_attn.o_proj",
|
| 140 |
+
"model.layers.8.mlp.down_proj",
|
| 141 |
+
"visual.blocks.28.attn.proj",
|
| 142 |
+
"visual.blocks.22.attn.proj",
|
| 143 |
+
"visual.blocks.1.mlp.fc2",
|
| 144 |
+
"visual.blocks.30.attn.qkv",
|
| 145 |
+
"visual.blocks.5.attn.proj",
|
| 146 |
+
"visual.blocks.1.attn.qkv",
|
| 147 |
+
"model.layers.6.self_attn.q_proj",
|
| 148 |
+
"visual.blocks.7.attn.qkv",
|
| 149 |
+
"model.layers.1.self_attn.v_proj",
|
| 150 |
+
"visual.blocks.21.mlp.fc1",
|
| 151 |
+
"visual.blocks.13.attn.proj",
|
| 152 |
+
"model.layers.4.mlp.gate_proj",
|
| 153 |
+
"model.layers.26.self_attn.o_proj",
|
| 154 |
+
"visual.blocks.6.mlp.fc1",
|
| 155 |
+
"model.layers.16.mlp.up_proj",
|
| 156 |
+
"model.layers.6.self_attn.o_proj",
|
| 157 |
+
"visual.blocks.30.mlp.fc1",
|
| 158 |
+
"model.layers.11.self_attn.q_proj",
|
| 159 |
+
"visual.blocks.0.attn.qkv",
|
| 160 |
+
"model.layers.16.self_attn.v_proj",
|
| 161 |
+
"model.layers.5.mlp.gate_proj",
|
| 162 |
+
"visual.blocks.15.attn.qkv",
|
| 163 |
+
"model.layers.12.mlp.down_proj",
|
| 164 |
+
"visual.blocks.7.mlp.fc1",
|
| 165 |
+
"visual.blocks.13.mlp.fc1",
|
| 166 |
+
"model.layers.5.self_attn.q_proj",
|
| 167 |
+
"model.layers.26.mlp.up_proj",
|
| 168 |
+
"visual.blocks.9.mlp.fc2",
|
| 169 |
+
"model.layers.17.mlp.up_proj",
|
| 170 |
+
"model.layers.25.self_attn.k_proj",
|
| 171 |
+
"model.layers.12.self_attn.o_proj",
|
| 172 |
+
"model.layers.4.mlp.up_proj",
|
| 173 |
+
"model.layers.19.self_attn.o_proj",
|
| 174 |
+
"model.layers.20.mlp.up_proj",
|
| 175 |
+
"visual.blocks.5.mlp.fc1",
|
| 176 |
+
"model.layers.4.mlp.down_proj",
|
| 177 |
+
"model.layers.14.mlp.up_proj",
|
| 178 |
+
"model.layers.20.mlp.gate_proj",
|
| 179 |
+
"model.layers.22.mlp.down_proj",
|
| 180 |
+
"model.layers.5.mlp.down_proj",
|
| 181 |
+
"visual.blocks.17.attn.qkv",
|
| 182 |
+
"visual.blocks.15.mlp.fc2",
|
| 183 |
+
"model.layers.3.self_attn.o_proj",
|
| 184 |
+
"visual.blocks.20.mlp.fc2",
|
| 185 |
+
"visual.blocks.6.mlp.fc2",
|
| 186 |
+
"visual.blocks.14.mlp.fc1",
|
| 187 |
+
"model.layers.19.mlp.gate_proj",
|
| 188 |
+
"visual.blocks.24.attn.qkv",
|
| 189 |
+
"model.layers.10.mlp.down_proj",
|
| 190 |
+
"model.layers.8.self_attn.v_proj",
|
| 191 |
+
"visual.blocks.21.attn.qkv",
|
| 192 |
+
"model.layers.25.self_attn.v_proj",
|
| 193 |
+
"model.layers.3.self_attn.k_proj",
|
| 194 |
+
"model.layers.10.mlp.gate_proj",
|
| 195 |
+
"visual.blocks.8.mlp.fc1",
|
| 196 |
+
"model.layers.18.mlp.down_proj",
|
| 197 |
+
"visual.blocks.21.mlp.fc2",
|
| 198 |
+
"visual.blocks.0.mlp.fc2",
|
| 199 |
+
"model.layers.13.self_attn.v_proj",
|
| 200 |
+
"model.layers.2.self_attn.k_proj",
|
| 201 |
+
"model.layers.12.self_attn.q_proj",
|
| 202 |
+
"visual.blocks.30.attn.proj",
|
| 203 |
+
"model.layers.2.mlp.up_proj",
|
| 204 |
+
"visual.blocks.19.attn.proj",
|
| 205 |
+
"visual.blocks.5.mlp.fc2",
|
| 206 |
+
"model.layers.16.mlp.down_proj",
|
| 207 |
+
"model.layers.19.mlp.down_proj",
|
| 208 |
+
"visual.blocks.15.mlp.fc1",
|
| 209 |
+
"model.layers.18.self_attn.v_proj",
|
| 210 |
+
"model.layers.14.self_attn.q_proj",
|
| 211 |
+
"model.layers.16.self_attn.q_proj",
|
| 212 |
+
"model.layers.16.self_attn.o_proj",
|
| 213 |
+
"visual.blocks.26.attn.qkv",
|
| 214 |
+
"visual.blocks.3.mlp.fc2",
|
| 215 |
+
"model.layers.18.self_attn.k_proj",
|
| 216 |
+
"visual.blocks.31.attn.proj",
|
| 217 |
+
"model.layers.19.self_attn.k_proj",
|
| 218 |
+
"visual.blocks.31.mlp.fc2",
|
| 219 |
+
"visual.blocks.29.mlp.fc1",
|
| 220 |
+
"model.layers.11.mlp.gate_proj",
|
| 221 |
+
"visual.blocks.7.mlp.fc2",
|
| 222 |
+
"visual.blocks.18.mlp.fc2",
|
| 223 |
+
"visual.blocks.16.attn.qkv",
|
| 224 |
+
"model.layers.9.mlp.down_proj",
|
| 225 |
+
"model.layers.20.self_attn.q_proj",
|
| 226 |
+
"visual.blocks.8.mlp.fc2",
|
| 227 |
+
"model.layers.5.self_attn.k_proj",
|
| 228 |
+
"model.layers.8.mlp.gate_proj",
|
| 229 |
+
"model.layers.25.mlp.up_proj",
|
| 230 |
+
"visual.blocks.26.mlp.fc2",
|
| 231 |
+
"model.layers.1.mlp.down_proj",
|
| 232 |
+
"model.layers.23.mlp.down_proj",
|
| 233 |
+
"visual.blocks.14.mlp.fc2",
|
| 234 |
+
"visual.blocks.11.attn.qkv",
|
| 235 |
+
"model.layers.0.self_attn.v_proj",
|
| 236 |
+
"visual.blocks.3.mlp.fc1",
|
| 237 |
+
"visual.blocks.12.mlp.fc1",
|
| 238 |
+
"model.layers.6.mlp.gate_proj",
|
| 239 |
+
"model.layers.15.self_attn.q_proj",
|
| 240 |
+
"visual.blocks.9.attn.proj",
|
| 241 |
+
"model.layers.25.mlp.down_proj",
|
| 242 |
+
"visual.blocks.4.mlp.fc2",
|
| 243 |
+
"model.layers.24.self_attn.o_proj",
|
| 244 |
+
"model.layers.13.mlp.down_proj",
|
| 245 |
+
"visual.blocks.9.attn.qkv",
|
| 246 |
+
"visual.blocks.14.attn.proj",
|
| 247 |
+
"model.layers.24.mlp.up_proj",
|
| 248 |
+
"visual.blocks.23.mlp.fc1",
|
| 249 |
+
"model.layers.27.self_attn.k_proj",
|
| 250 |
+
"visual.blocks.4.attn.qkv",
|
| 251 |
+
"model.layers.24.self_attn.k_proj",
|
| 252 |
+
"model.layers.25.self_attn.q_proj",
|
| 253 |
+
"model.layers.5.self_attn.o_proj",
|
| 254 |
+
"visual.blocks.20.attn.proj",
|
| 255 |
+
"visual.blocks.3.attn.proj",
|
| 256 |
+
"visual.blocks.12.mlp.fc2",
|
| 257 |
+
"visual.blocks.26.attn.proj",
|
| 258 |
+
"model.layers.4.self_attn.o_proj",
|
| 259 |
+
"model.layers.18.self_attn.q_proj",
|
| 260 |
+
"model.layers.23.self_attn.q_proj",
|
| 261 |
+
"visual.blocks.4.attn.proj",
|
| 262 |
+
"model.layers.20.self_attn.o_proj",
|
| 263 |
+
"model.layers.7.mlp.down_proj",
|
| 264 |
+
"model.layers.10.self_attn.k_proj",
|
| 265 |
+
"visual.blocks.11.attn.proj",
|
| 266 |
+
"model.layers.9.self_attn.k_proj",
|
| 267 |
+
"model.layers.23.mlp.gate_proj",
|
| 268 |
+
"model.layers.17.mlp.down_proj",
|
| 269 |
+
"visual.blocks.30.mlp.fc2",
|
| 270 |
+
"model.layers.2.mlp.down_proj",
|
| 271 |
+
"model.layers.22.self_attn.k_proj",
|
| 272 |
+
"model.layers.18.mlp.gate_proj",
|
| 273 |
+
"model.layers.10.self_attn.q_proj",
|
| 274 |
+
"visual.blocks.8.attn.proj",
|
| 275 |
+
"model.layers.8.self_attn.k_proj",
|
| 276 |
+
"model.layers.12.self_attn.k_proj",
|
| 277 |
+
"model.layers.9.self_attn.o_proj",
|
| 278 |
+
"model.layers.23.self_attn.o_proj",
|
| 279 |
+
"model.layers.27.mlp.up_proj",
|
| 280 |
+
"model.layers.13.self_attn.k_proj",
|
| 281 |
+
"model.layers.24.self_attn.q_proj",
|
| 282 |
+
"model.layers.8.mlp.up_proj",
|
| 283 |
+
"model.layers.20.self_attn.v_proj",
|
| 284 |
+
"visual.blocks.25.attn.qkv",
|
| 285 |
+
"model.layers.21.mlp.down_proj",
|
| 286 |
+
"visual.blocks.0.attn.proj",
|
| 287 |
+
"model.layers.22.mlp.up_proj",
|
| 288 |
+
"model.layers.26.mlp.gate_proj",
|
| 289 |
+
"model.layers.14.self_attn.o_proj",
|
| 290 |
+
"model.layers.9.mlp.up_proj",
|
| 291 |
+
"visual.blocks.10.mlp.fc1",
|
| 292 |
+
"visual.blocks.2.attn.qkv",
|
| 293 |
+
"visual.blocks.27.attn.qkv",
|
| 294 |
+
"visual.blocks.27.mlp.fc1",
|
| 295 |
+
"model.layers.7.self_attn.q_proj",
|
| 296 |
+
"visual.blocks.29.mlp.fc2",
|
| 297 |
+
"visual.blocks.5.attn.qkv",
|
| 298 |
+
"visual.blocks.13.mlp.fc2",
|
| 299 |
+
"visual.blocks.18.mlp.fc1",
|
| 300 |
+
"model.layers.9.self_attn.q_proj",
|
| 301 |
+
"model.layers.11.mlp.down_proj",
|
| 302 |
+
"model.layers.23.mlp.up_proj",
|
| 303 |
+
"visual.blocks.19.mlp.fc1",
|
| 304 |
+
"visual.blocks.3.attn.qkv",
|
| 305 |
+
"model.layers.6.mlp.down_proj",
|
| 306 |
+
"visual.blocks.28.attn.qkv",
|
| 307 |
+
"visual.blocks.19.attn.qkv",
|
| 308 |
+
"model.layers.20.self_attn.k_proj",
|
| 309 |
+
"model.layers.1.self_attn.q_proj",
|
| 310 |
+
"model.layers.15.mlp.up_proj",
|
| 311 |
+
"model.layers.13.mlp.gate_proj",
|
| 312 |
+
"model.layers.19.self_attn.v_proj",
|
| 313 |
+
"model.layers.0.mlp.gate_proj",
|
| 314 |
+
"visual.blocks.10.attn.qkv",
|
| 315 |
+
"model.layers.14.self_attn.v_proj",
|
| 316 |
+
"visual.blocks.8.attn.qkv",
|
| 317 |
+
"visual.blocks.10.attn.proj",
|
| 318 |
+
"visual.blocks.16.mlp.fc1",
|
| 319 |
+
"model.layers.17.self_attn.k_proj",
|
| 320 |
+
"visual.blocks.6.attn.qkv",
|
| 321 |
+
"visual.blocks.25.mlp.fc1",
|
| 322 |
+
"model.layers.10.mlp.up_proj",
|
| 323 |
+
"model.layers.16.self_attn.k_proj",
|
| 324 |
+
"visual.blocks.1.mlp.fc1",
|
| 325 |
+
"visual.blocks.17.mlp.fc1",
|
| 326 |
+
"model.layers.12.mlp.gate_proj",
|
| 327 |
+
"visual.blocks.4.mlp.fc1",
|
| 328 |
+
"model.layers.12.self_attn.v_proj",
|
| 329 |
+
"visual.blocks.2.mlp.fc2",
|
| 330 |
+
"visual.blocks.31.mlp.fc1",
|
| 331 |
+
"visual.blocks.2.mlp.fc1",
|
| 332 |
+
"model.layers.1.mlp.up_proj",
|
| 333 |
+
"model.layers.5.self_attn.v_proj",
|
| 334 |
+
"model.layers.2.self_attn.q_proj",
|
| 335 |
+
"visual.blocks.1.attn.proj",
|
| 336 |
+
"visual.blocks.14.attn.qkv",
|
| 337 |
+
"model.layers.7.self_attn.v_proj",
|
| 338 |
+
"model.layers.4.self_attn.v_proj",
|
| 339 |
+
"visual.blocks.24.attn.proj",
|
| 340 |
+
"model.layers.21.self_attn.q_proj",
|
| 341 |
+
"visual.blocks.29.attn.qkv",
|
| 342 |
+
"model.layers.26.self_attn.k_proj",
|
| 343 |
+
"visual.blocks.20.mlp.fc1",
|
| 344 |
+
"visual.blocks.9.mlp.fc1",
|
| 345 |
+
"visual.blocks.11.mlp.fc2",
|
| 346 |
+
"visual.blocks.10.mlp.fc2"
|
| 347 |
+
],
|
| 348 |
+
"task_type": "CAUSAL_LM",
|
| 349 |
+
"use_dora": false,
|
| 350 |
+
"use_rslora": false
|
| 351 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d70f57855494c22321a86112edcf3ba9a8f18d77990fc6b952025eb7a93db02a
|
| 3 |
+
size 115886968
|
added_tokens.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|box_end|>": 151649,
|
| 3 |
+
"<|box_start|>": 151648,
|
| 4 |
+
"<|endoftext|>": 151643,
|
| 5 |
+
"<|im_end|>": 151645,
|
| 6 |
+
"<|im_start|>": 151644,
|
| 7 |
+
"<|image_pad|>": 151655,
|
| 8 |
+
"<|object_ref_end|>": 151647,
|
| 9 |
+
"<|object_ref_start|>": 151646,
|
| 10 |
+
"<|quad_end|>": 151651,
|
| 11 |
+
"<|quad_start|>": 151650,
|
| 12 |
+
"<|video_pad|>": 151656,
|
| 13 |
+
"<|vision_end|>": 151653,
|
| 14 |
+
"<|vision_pad|>": 151654,
|
| 15 |
+
"<|vision_start|>": 151652
|
| 16 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.848,
|
| 3 |
+
"total_flos": 4.910594218000384e+16,
|
| 4 |
+
"train_loss": 0.3172732482754415,
|
| 5 |
+
"train_runtime": 12792.4734,
|
| 6 |
+
"train_samples_per_second": 0.391,
|
| 7 |
+
"train_steps_per_second": 0.048
|
| 8 |
+
}
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
checkpoint-620/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: saim1212/qwen2_2b_git2
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
checkpoint-620/adapter_config.json
ADDED
|
@@ -0,0 +1,351 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "saim1212/qwen2_2b_git2",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 16,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"visual.blocks.31.attn.qkv",
|
| 24 |
+
"visual.blocks.26.mlp.fc1",
|
| 25 |
+
"model.layers.21.mlp.gate_proj",
|
| 26 |
+
"model.layers.22.self_attn.v_proj",
|
| 27 |
+
"model.layers.17.self_attn.o_proj",
|
| 28 |
+
"model.layers.26.self_attn.v_proj",
|
| 29 |
+
"visual.blocks.24.mlp.fc1",
|
| 30 |
+
"model.layers.2.self_attn.o_proj",
|
| 31 |
+
"model.layers.21.self_attn.o_proj",
|
| 32 |
+
"model.layers.1.self_attn.k_proj",
|
| 33 |
+
"model.layers.7.self_attn.k_proj",
|
| 34 |
+
"visual.blocks.12.attn.qkv",
|
| 35 |
+
"visual.blocks.22.mlp.fc1",
|
| 36 |
+
"model.layers.26.mlp.down_proj",
|
| 37 |
+
"model.layers.11.self_attn.v_proj",
|
| 38 |
+
"visual.blocks.23.attn.proj",
|
| 39 |
+
"model.layers.21.self_attn.v_proj",
|
| 40 |
+
"model.layers.15.self_attn.k_proj",
|
| 41 |
+
"model.layers.14.mlp.down_proj",
|
| 42 |
+
"model.layers.21.mlp.up_proj",
|
| 43 |
+
"model.layers.0.mlp.down_proj",
|
| 44 |
+
"visual.blocks.17.mlp.fc2",
|
| 45 |
+
"model.layers.4.self_attn.k_proj",
|
| 46 |
+
"model.layers.16.mlp.gate_proj",
|
| 47 |
+
"visual.blocks.18.attn.qkv",
|
| 48 |
+
"model.layers.17.mlp.gate_proj",
|
| 49 |
+
"model.layers.3.mlp.gate_proj",
|
| 50 |
+
"visual.blocks.20.attn.qkv",
|
| 51 |
+
"visual.blocks.23.mlp.fc2",
|
| 52 |
+
"model.layers.15.self_attn.v_proj",
|
| 53 |
+
"model.layers.20.mlp.down_proj",
|
| 54 |
+
"model.layers.7.mlp.gate_proj",
|
| 55 |
+
"model.layers.6.self_attn.k_proj",
|
| 56 |
+
"model.layers.18.self_attn.o_proj",
|
| 57 |
+
"visual.blocks.11.mlp.fc1",
|
| 58 |
+
"model.layers.15.mlp.down_proj",
|
| 59 |
+
"model.layers.19.self_attn.q_proj",
|
| 60 |
+
"visual.blocks.16.attn.proj",
|
| 61 |
+
"model.layers.15.self_attn.o_proj",
|
| 62 |
+
"visual.blocks.2.attn.proj",
|
| 63 |
+
"visual.blocks.12.attn.proj",
|
| 64 |
+
"model.layers.27.mlp.gate_proj",
|
| 65 |
+
"model.layers.9.mlp.gate_proj",
|
| 66 |
+
"model.layers.9.self_attn.v_proj",
|
| 67 |
+
"visual.blocks.22.mlp.fc2",
|
| 68 |
+
"model.layers.27.self_attn.q_proj",
|
| 69 |
+
"visual.blocks.17.attn.proj",
|
| 70 |
+
"model.layers.0.self_attn.o_proj",
|
| 71 |
+
"visual.blocks.16.mlp.fc2",
|
| 72 |
+
"model.layers.19.mlp.up_proj",
|
| 73 |
+
"visual.blocks.23.attn.qkv",
|
| 74 |
+
"visual.blocks.25.attn.proj",
|
| 75 |
+
"model.layers.12.mlp.up_proj",
|
| 76 |
+
"model.layers.14.mlp.gate_proj",
|
| 77 |
+
"visual.blocks.29.attn.proj",
|
| 78 |
+
"model.layers.13.mlp.up_proj",
|
| 79 |
+
"visual.blocks.21.attn.proj",
|
| 80 |
+
"model.layers.23.self_attn.v_proj",
|
| 81 |
+
"model.layers.22.self_attn.q_proj",
|
| 82 |
+
"visual.blocks.18.attn.proj",
|
| 83 |
+
"model.layers.27.self_attn.o_proj",
|
| 84 |
+
"model.layers.24.mlp.down_proj",
|
| 85 |
+
"visual.blocks.0.mlp.fc1",
|
| 86 |
+
"model.layers.24.self_attn.v_proj",
|
| 87 |
+
"model.layers.5.mlp.up_proj",
|
| 88 |
+
"visual.blocks.27.mlp.fc2",
|
| 89 |
+
"model.layers.11.self_attn.k_proj",
|
| 90 |
+
"model.layers.10.self_attn.o_proj",
|
| 91 |
+
"model.layers.23.self_attn.k_proj",
|
| 92 |
+
"model.layers.1.mlp.gate_proj",
|
| 93 |
+
"model.layers.4.self_attn.q_proj",
|
| 94 |
+
"model.layers.25.self_attn.o_proj",
|
| 95 |
+
"model.layers.7.mlp.up_proj",
|
| 96 |
+
"model.layers.1.self_attn.o_proj",
|
| 97 |
+
"model.layers.18.mlp.up_proj",
|
| 98 |
+
"visual.blocks.19.mlp.fc2",
|
| 99 |
+
"model.layers.24.mlp.gate_proj",
|
| 100 |
+
"visual.blocks.25.mlp.fc2",
|
| 101 |
+
"model.layers.22.self_attn.o_proj",
|
| 102 |
+
"model.layers.21.self_attn.k_proj",
|
| 103 |
+
"model.layers.3.mlp.up_proj",
|
| 104 |
+
"model.layers.0.self_attn.k_proj",
|
| 105 |
+
"visual.blocks.13.attn.qkv",
|
| 106 |
+
"model.layers.26.self_attn.q_proj",
|
| 107 |
+
"model.layers.25.mlp.gate_proj",
|
| 108 |
+
"visual.blocks.7.attn.proj",
|
| 109 |
+
"visual.blocks.24.mlp.fc2",
|
| 110 |
+
"model.layers.2.mlp.gate_proj",
|
| 111 |
+
"model.layers.0.self_attn.q_proj",
|
| 112 |
+
"visual.blocks.15.attn.proj",
|
| 113 |
+
"model.layers.27.self_attn.v_proj",
|
| 114 |
+
"model.layers.27.mlp.down_proj",
|
| 115 |
+
"model.layers.0.mlp.up_proj",
|
| 116 |
+
"model.layers.17.self_attn.v_proj",
|
| 117 |
+
"model.layers.22.mlp.gate_proj",
|
| 118 |
+
"visual.blocks.28.mlp.fc1",
|
| 119 |
+
"model.layers.3.self_attn.v_proj",
|
| 120 |
+
"model.layers.13.self_attn.q_proj",
|
| 121 |
+
"model.layers.15.mlp.gate_proj",
|
| 122 |
+
"model.layers.11.mlp.up_proj",
|
| 123 |
+
"model.layers.10.self_attn.v_proj",
|
| 124 |
+
"model.layers.17.self_attn.q_proj",
|
| 125 |
+
"model.layers.14.self_attn.k_proj",
|
| 126 |
+
"visual.blocks.6.attn.proj",
|
| 127 |
+
"model.layers.2.self_attn.v_proj",
|
| 128 |
+
"model.layers.8.self_attn.o_proj",
|
| 129 |
+
"model.layers.3.self_attn.q_proj",
|
| 130 |
+
"model.layers.11.self_attn.o_proj",
|
| 131 |
+
"model.layers.6.self_attn.v_proj",
|
| 132 |
+
"model.layers.6.mlp.up_proj",
|
| 133 |
+
"visual.blocks.27.attn.proj",
|
| 134 |
+
"model.layers.13.self_attn.o_proj",
|
| 135 |
+
"model.layers.8.self_attn.q_proj",
|
| 136 |
+
"visual.blocks.28.mlp.fc2",
|
| 137 |
+
"visual.blocks.22.attn.qkv",
|
| 138 |
+
"model.layers.3.mlp.down_proj",
|
| 139 |
+
"model.layers.7.self_attn.o_proj",
|
| 140 |
+
"model.layers.8.mlp.down_proj",
|
| 141 |
+
"visual.blocks.28.attn.proj",
|
| 142 |
+
"visual.blocks.22.attn.proj",
|
| 143 |
+
"visual.blocks.1.mlp.fc2",
|
| 144 |
+
"visual.blocks.30.attn.qkv",
|
| 145 |
+
"visual.blocks.5.attn.proj",
|
| 146 |
+
"visual.blocks.1.attn.qkv",
|
| 147 |
+
"model.layers.6.self_attn.q_proj",
|
| 148 |
+
"visual.blocks.7.attn.qkv",
|
| 149 |
+
"model.layers.1.self_attn.v_proj",
|
| 150 |
+
"visual.blocks.21.mlp.fc1",
|
| 151 |
+
"visual.blocks.13.attn.proj",
|
| 152 |
+
"model.layers.4.mlp.gate_proj",
|
| 153 |
+
"model.layers.26.self_attn.o_proj",
|
| 154 |
+
"visual.blocks.6.mlp.fc1",
|
| 155 |
+
"model.layers.16.mlp.up_proj",
|
| 156 |
+
"model.layers.6.self_attn.o_proj",
|
| 157 |
+
"visual.blocks.30.mlp.fc1",
|
| 158 |
+
"model.layers.11.self_attn.q_proj",
|
| 159 |
+
"visual.blocks.0.attn.qkv",
|
| 160 |
+
"model.layers.16.self_attn.v_proj",
|
| 161 |
+
"model.layers.5.mlp.gate_proj",
|
| 162 |
+
"visual.blocks.15.attn.qkv",
|
| 163 |
+
"model.layers.12.mlp.down_proj",
|
| 164 |
+
"visual.blocks.7.mlp.fc1",
|
| 165 |
+
"visual.blocks.13.mlp.fc1",
|
| 166 |
+
"model.layers.5.self_attn.q_proj",
|
| 167 |
+
"model.layers.26.mlp.up_proj",
|
| 168 |
+
"visual.blocks.9.mlp.fc2",
|
| 169 |
+
"model.layers.17.mlp.up_proj",
|
| 170 |
+
"model.layers.25.self_attn.k_proj",
|
| 171 |
+
"model.layers.12.self_attn.o_proj",
|
| 172 |
+
"model.layers.4.mlp.up_proj",
|
| 173 |
+
"model.layers.19.self_attn.o_proj",
|
| 174 |
+
"model.layers.20.mlp.up_proj",
|
| 175 |
+
"visual.blocks.5.mlp.fc1",
|
| 176 |
+
"model.layers.4.mlp.down_proj",
|
| 177 |
+
"model.layers.14.mlp.up_proj",
|
| 178 |
+
"model.layers.20.mlp.gate_proj",
|
| 179 |
+
"model.layers.22.mlp.down_proj",
|
| 180 |
+
"model.layers.5.mlp.down_proj",
|
| 181 |
+
"visual.blocks.17.attn.qkv",
|
| 182 |
+
"visual.blocks.15.mlp.fc2",
|
| 183 |
+
"model.layers.3.self_attn.o_proj",
|
| 184 |
+
"visual.blocks.20.mlp.fc2",
|
| 185 |
+
"visual.blocks.6.mlp.fc2",
|
| 186 |
+
"visual.blocks.14.mlp.fc1",
|
| 187 |
+
"model.layers.19.mlp.gate_proj",
|
| 188 |
+
"visual.blocks.24.attn.qkv",
|
| 189 |
+
"model.layers.10.mlp.down_proj",
|
| 190 |
+
"model.layers.8.self_attn.v_proj",
|
| 191 |
+
"visual.blocks.21.attn.qkv",
|
| 192 |
+
"model.layers.25.self_attn.v_proj",
|
| 193 |
+
"model.layers.3.self_attn.k_proj",
|
| 194 |
+
"model.layers.10.mlp.gate_proj",
|
| 195 |
+
"visual.blocks.8.mlp.fc1",
|
| 196 |
+
"model.layers.18.mlp.down_proj",
|
| 197 |
+
"visual.blocks.21.mlp.fc2",
|
| 198 |
+
"visual.blocks.0.mlp.fc2",
|
| 199 |
+
"model.layers.13.self_attn.v_proj",
|
| 200 |
+
"model.layers.2.self_attn.k_proj",
|
| 201 |
+
"model.layers.12.self_attn.q_proj",
|
| 202 |
+
"visual.blocks.30.attn.proj",
|
| 203 |
+
"model.layers.2.mlp.up_proj",
|
| 204 |
+
"visual.blocks.19.attn.proj",
|
| 205 |
+
"visual.blocks.5.mlp.fc2",
|
| 206 |
+
"model.layers.16.mlp.down_proj",
|
| 207 |
+
"model.layers.19.mlp.down_proj",
|
| 208 |
+
"visual.blocks.15.mlp.fc1",
|
| 209 |
+
"model.layers.18.self_attn.v_proj",
|
| 210 |
+
"model.layers.14.self_attn.q_proj",
|
| 211 |
+
"model.layers.16.self_attn.q_proj",
|
| 212 |
+
"model.layers.16.self_attn.o_proj",
|
| 213 |
+
"visual.blocks.26.attn.qkv",
|
| 214 |
+
"visual.blocks.3.mlp.fc2",
|
| 215 |
+
"model.layers.18.self_attn.k_proj",
|
| 216 |
+
"visual.blocks.31.attn.proj",
|
| 217 |
+
"model.layers.19.self_attn.k_proj",
|
| 218 |
+
"visual.blocks.31.mlp.fc2",
|
| 219 |
+
"visual.blocks.29.mlp.fc1",
|
| 220 |
+
"model.layers.11.mlp.gate_proj",
|
| 221 |
+
"visual.blocks.7.mlp.fc2",
|
| 222 |
+
"visual.blocks.18.mlp.fc2",
|
| 223 |
+
"visual.blocks.16.attn.qkv",
|
| 224 |
+
"model.layers.9.mlp.down_proj",
|
| 225 |
+
"model.layers.20.self_attn.q_proj",
|
| 226 |
+
"visual.blocks.8.mlp.fc2",
|
| 227 |
+
"model.layers.5.self_attn.k_proj",
|
| 228 |
+
"model.layers.8.mlp.gate_proj",
|
| 229 |
+
"model.layers.25.mlp.up_proj",
|
| 230 |
+
"visual.blocks.26.mlp.fc2",
|
| 231 |
+
"model.layers.1.mlp.down_proj",
|
| 232 |
+
"model.layers.23.mlp.down_proj",
|
| 233 |
+
"visual.blocks.14.mlp.fc2",
|
| 234 |
+
"visual.blocks.11.attn.qkv",
|
| 235 |
+
"model.layers.0.self_attn.v_proj",
|
| 236 |
+
"visual.blocks.3.mlp.fc1",
|
| 237 |
+
"visual.blocks.12.mlp.fc1",
|
| 238 |
+
"model.layers.6.mlp.gate_proj",
|
| 239 |
+
"model.layers.15.self_attn.q_proj",
|
| 240 |
+
"visual.blocks.9.attn.proj",
|
| 241 |
+
"model.layers.25.mlp.down_proj",
|
| 242 |
+
"visual.blocks.4.mlp.fc2",
|
| 243 |
+
"model.layers.24.self_attn.o_proj",
|
| 244 |
+
"model.layers.13.mlp.down_proj",
|
| 245 |
+
"visual.blocks.9.attn.qkv",
|
| 246 |
+
"visual.blocks.14.attn.proj",
|
| 247 |
+
"model.layers.24.mlp.up_proj",
|
| 248 |
+
"visual.blocks.23.mlp.fc1",
|
| 249 |
+
"model.layers.27.self_attn.k_proj",
|
| 250 |
+
"visual.blocks.4.attn.qkv",
|
| 251 |
+
"model.layers.24.self_attn.k_proj",
|
| 252 |
+
"model.layers.25.self_attn.q_proj",
|
| 253 |
+
"model.layers.5.self_attn.o_proj",
|
| 254 |
+
"visual.blocks.20.attn.proj",
|
| 255 |
+
"visual.blocks.3.attn.proj",
|
| 256 |
+
"visual.blocks.12.mlp.fc2",
|
| 257 |
+
"visual.blocks.26.attn.proj",
|
| 258 |
+
"model.layers.4.self_attn.o_proj",
|
| 259 |
+
"model.layers.18.self_attn.q_proj",
|
| 260 |
+
"model.layers.23.self_attn.q_proj",
|
| 261 |
+
"visual.blocks.4.attn.proj",
|
| 262 |
+
"model.layers.20.self_attn.o_proj",
|
| 263 |
+
"model.layers.7.mlp.down_proj",
|
| 264 |
+
"model.layers.10.self_attn.k_proj",
|
| 265 |
+
"visual.blocks.11.attn.proj",
|
| 266 |
+
"model.layers.9.self_attn.k_proj",
|
| 267 |
+
"model.layers.23.mlp.gate_proj",
|
| 268 |
+
"model.layers.17.mlp.down_proj",
|
| 269 |
+
"visual.blocks.30.mlp.fc2",
|
| 270 |
+
"model.layers.2.mlp.down_proj",
|
| 271 |
+
"model.layers.22.self_attn.k_proj",
|
| 272 |
+
"model.layers.18.mlp.gate_proj",
|
| 273 |
+
"model.layers.10.self_attn.q_proj",
|
| 274 |
+
"visual.blocks.8.attn.proj",
|
| 275 |
+
"model.layers.8.self_attn.k_proj",
|
| 276 |
+
"model.layers.12.self_attn.k_proj",
|
| 277 |
+
"model.layers.9.self_attn.o_proj",
|
| 278 |
+
"model.layers.23.self_attn.o_proj",
|
| 279 |
+
"model.layers.27.mlp.up_proj",
|
| 280 |
+
"model.layers.13.self_attn.k_proj",
|
| 281 |
+
"model.layers.24.self_attn.q_proj",
|
| 282 |
+
"model.layers.8.mlp.up_proj",
|
| 283 |
+
"model.layers.20.self_attn.v_proj",
|
| 284 |
+
"visual.blocks.25.attn.qkv",
|
| 285 |
+
"model.layers.21.mlp.down_proj",
|
| 286 |
+
"visual.blocks.0.attn.proj",
|
| 287 |
+
"model.layers.22.mlp.up_proj",
|
| 288 |
+
"model.layers.26.mlp.gate_proj",
|
| 289 |
+
"model.layers.14.self_attn.o_proj",
|
| 290 |
+
"model.layers.9.mlp.up_proj",
|
| 291 |
+
"visual.blocks.10.mlp.fc1",
|
| 292 |
+
"visual.blocks.2.attn.qkv",
|
| 293 |
+
"visual.blocks.27.attn.qkv",
|
| 294 |
+
"visual.blocks.27.mlp.fc1",
|
| 295 |
+
"model.layers.7.self_attn.q_proj",
|
| 296 |
+
"visual.blocks.29.mlp.fc2",
|
| 297 |
+
"visual.blocks.5.attn.qkv",
|
| 298 |
+
"visual.blocks.13.mlp.fc2",
|
| 299 |
+
"visual.blocks.18.mlp.fc1",
|
| 300 |
+
"model.layers.9.self_attn.q_proj",
|
| 301 |
+
"model.layers.11.mlp.down_proj",
|
| 302 |
+
"model.layers.23.mlp.up_proj",
|
| 303 |
+
"visual.blocks.19.mlp.fc1",
|
| 304 |
+
"visual.blocks.3.attn.qkv",
|
| 305 |
+
"model.layers.6.mlp.down_proj",
|
| 306 |
+
"visual.blocks.28.attn.qkv",
|
| 307 |
+
"visual.blocks.19.attn.qkv",
|
| 308 |
+
"model.layers.20.self_attn.k_proj",
|
| 309 |
+
"model.layers.1.self_attn.q_proj",
|
| 310 |
+
"model.layers.15.mlp.up_proj",
|
| 311 |
+
"model.layers.13.mlp.gate_proj",
|
| 312 |
+
"model.layers.19.self_attn.v_proj",
|
| 313 |
+
"model.layers.0.mlp.gate_proj",
|
| 314 |
+
"visual.blocks.10.attn.qkv",
|
| 315 |
+
"model.layers.14.self_attn.v_proj",
|
| 316 |
+
"visual.blocks.8.attn.qkv",
|
| 317 |
+
"visual.blocks.10.attn.proj",
|
| 318 |
+
"visual.blocks.16.mlp.fc1",
|
| 319 |
+
"model.layers.17.self_attn.k_proj",
|
| 320 |
+
"visual.blocks.6.attn.qkv",
|
| 321 |
+
"visual.blocks.25.mlp.fc1",
|
| 322 |
+
"model.layers.10.mlp.up_proj",
|
| 323 |
+
"model.layers.16.self_attn.k_proj",
|
| 324 |
+
"visual.blocks.1.mlp.fc1",
|
| 325 |
+
"visual.blocks.17.mlp.fc1",
|
| 326 |
+
"model.layers.12.mlp.gate_proj",
|
| 327 |
+
"visual.blocks.4.mlp.fc1",
|
| 328 |
+
"model.layers.12.self_attn.v_proj",
|
| 329 |
+
"visual.blocks.2.mlp.fc2",
|
| 330 |
+
"visual.blocks.31.mlp.fc1",
|
| 331 |
+
"visual.blocks.2.mlp.fc1",
|
| 332 |
+
"model.layers.1.mlp.up_proj",
|
| 333 |
+
"model.layers.5.self_attn.v_proj",
|
| 334 |
+
"model.layers.2.self_attn.q_proj",
|
| 335 |
+
"visual.blocks.1.attn.proj",
|
| 336 |
+
"visual.blocks.14.attn.qkv",
|
| 337 |
+
"model.layers.7.self_attn.v_proj",
|
| 338 |
+
"model.layers.4.self_attn.v_proj",
|
| 339 |
+
"visual.blocks.24.attn.proj",
|
| 340 |
+
"model.layers.21.self_attn.q_proj",
|
| 341 |
+
"visual.blocks.29.attn.qkv",
|
| 342 |
+
"model.layers.26.self_attn.k_proj",
|
| 343 |
+
"visual.blocks.20.mlp.fc1",
|
| 344 |
+
"visual.blocks.9.mlp.fc1",
|
| 345 |
+
"visual.blocks.11.mlp.fc2",
|
| 346 |
+
"visual.blocks.10.mlp.fc2"
|
| 347 |
+
],
|
| 348 |
+
"task_type": "CAUSAL_LM",
|
| 349 |
+
"use_dora": false,
|
| 350 |
+
"use_rslora": false
|
| 351 |
+
}
|
checkpoint-620/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d70f57855494c22321a86112edcf3ba9a8f18d77990fc6b952025eb7a93db02a
|
| 3 |
+
size 115886968
|
checkpoint-620/added_tokens.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|box_end|>": 151649,
|
| 3 |
+
"<|box_start|>": 151648,
|
| 4 |
+
"<|endoftext|>": 151643,
|
| 5 |
+
"<|im_end|>": 151645,
|
| 6 |
+
"<|im_start|>": 151644,
|
| 7 |
+
"<|image_pad|>": 151655,
|
| 8 |
+
"<|object_ref_end|>": 151647,
|
| 9 |
+
"<|object_ref_start|>": 151646,
|
| 10 |
+
"<|quad_end|>": 151651,
|
| 11 |
+
"<|quad_start|>": 151650,
|
| 12 |
+
"<|video_pad|>": 151656,
|
| 13 |
+
"<|vision_end|>": 151653,
|
| 14 |
+
"<|vision_pad|>": 151654,
|
| 15 |
+
"<|vision_start|>": 151652
|
| 16 |
+
}
|
checkpoint-620/chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
checkpoint-620/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-620/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb83700126db1ac786bd40f55af09050b01d8b7e935d47e3ed88ec9606ce1d9a
|
| 3 |
+
size 232150634
|
checkpoint-620/preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 12845056,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 3136,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 12845056,
|
| 26 |
+
"shortest_edge": 3136
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
checkpoint-620/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b074bf97f241c2662caa5ce956b03d1249c3cc0713b6aef7796673362754f98
|
| 3 |
+
size 14512
|
checkpoint-620/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58aed9e8d78903cb12015375021c729c3f6c5fd1a1e19e7aee6ddde57c3310b9
|
| 3 |
+
size 14512
|
checkpoint-620/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8167a7a628c5d6d5061531d993a99d8970329d2f198daf9e2bd5698793632aed
|
| 3 |
+
size 988
|
checkpoint-620/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:273bbe6001683cf6d55fc3f56083be320723f4339bb54fc958dcb89ff588d3a4
|
| 3 |
+
size 1064
|
checkpoint-620/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
}
|
checkpoint-620/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
|
| 3 |
+
size 11420371
|
checkpoint-620/tokenizer_config.json
ADDED
|
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 117 |
+
"additional_special_tokens": [
|
| 118 |
+
"<|im_start|>",
|
| 119 |
+
"<|im_end|>",
|
| 120 |
+
"<|object_ref_start|>",
|
| 121 |
+
"<|object_ref_end|>",
|
| 122 |
+
"<|box_start|>",
|
| 123 |
+
"<|box_end|>",
|
| 124 |
+
"<|quad_start|>",
|
| 125 |
+
"<|quad_end|>",
|
| 126 |
+
"<|vision_start|>",
|
| 127 |
+
"<|vision_end|>",
|
| 128 |
+
"<|vision_pad|>",
|
| 129 |
+
"<|image_pad|>",
|
| 130 |
+
"<|video_pad|>"
|
| 131 |
+
],
|
| 132 |
+
"bos_token": null,
|
| 133 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 134 |
+
"clean_up_tokenization_spaces": false,
|
| 135 |
+
"eos_token": "<|im_end|>",
|
| 136 |
+
"errors": "replace",
|
| 137 |
+
"extra_special_tokens": {},
|
| 138 |
+
"model_max_length": 2048,
|
| 139 |
+
"pad_token": "<|endoftext|>",
|
| 140 |
+
"padding_side": "right",
|
| 141 |
+
"processor_class": "Qwen2VLProcessor",
|
| 142 |
+
"split_special_tokens": false,
|
| 143 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 144 |
+
"unk_token": null
|
| 145 |
+
}
|
checkpoint-620/trainer_state.json
ADDED
|
@@ -0,0 +1,467 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.848,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 620,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.16,
|
| 13 |
+
"grad_norm": 3.8025777339935303,
|
| 14 |
+
"learning_rate": 2.2580645161290324e-06,
|
| 15 |
+
"loss": 1.4695,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.32,
|
| 20 |
+
"grad_norm": 1.3798772096633911,
|
| 21 |
+
"learning_rate": 5.483870967741935e-06,
|
| 22 |
+
"loss": 0.9564,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.48,
|
| 27 |
+
"grad_norm": 1.1069912910461426,
|
| 28 |
+
"learning_rate": 8.70967741935484e-06,
|
| 29 |
+
"loss": 0.7467,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.64,
|
| 34 |
+
"grad_norm": 1.3565958738327026,
|
| 35 |
+
"learning_rate": 1.1935483870967743e-05,
|
| 36 |
+
"loss": 0.7442,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.8,
|
| 41 |
+
"grad_norm": 0.8724671006202698,
|
| 42 |
+
"learning_rate": 1.5161290322580646e-05,
|
| 43 |
+
"loss": 0.6401,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.96,
|
| 48 |
+
"grad_norm": 0.8387081027030945,
|
| 49 |
+
"learning_rate": 1.838709677419355e-05,
|
| 50 |
+
"loss": 0.6412,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.112,
|
| 55 |
+
"grad_norm": 1.1549522876739502,
|
| 56 |
+
"learning_rate": 1.9996038016334953e-05,
|
| 57 |
+
"loss": 0.5019,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.272,
|
| 62 |
+
"grad_norm": 0.7454654574394226,
|
| 63 |
+
"learning_rate": 1.9968952076274873e-05,
|
| 64 |
+
"loss": 0.5679,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.432,
|
| 69 |
+
"grad_norm": 1.2986727952957153,
|
| 70 |
+
"learning_rate": 1.990884868158239e-05,
|
| 71 |
+
"loss": 0.5871,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.592,
|
| 76 |
+
"grad_norm": 1.4838392734527588,
|
| 77 |
+
"learning_rate": 1.9817344551289796e-05,
|
| 78 |
+
"loss": 0.5669,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.752,
|
| 83 |
+
"grad_norm": 1.1603983640670776,
|
| 84 |
+
"learning_rate": 1.9694729658237925e-05,
|
| 85 |
+
"loss": 0.5716,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.912,
|
| 90 |
+
"grad_norm": 1.4420567750930786,
|
| 91 |
+
"learning_rate": 1.954139256400049e-05,
|
| 92 |
+
"loss": 0.584,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.064,
|
| 97 |
+
"grad_norm": 0.9452749490737915,
|
| 98 |
+
"learning_rate": 1.935781918754836e-05,
|
| 99 |
+
"loss": 0.4986,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 2.224,
|
| 104 |
+
"grad_norm": 1.114253044128418,
|
| 105 |
+
"learning_rate": 1.914459126539224e-05,
|
| 106 |
+
"loss": 0.4908,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 2.384,
|
| 111 |
+
"grad_norm": 1.864726185798645,
|
| 112 |
+
"learning_rate": 1.8902384508083518e-05,
|
| 113 |
+
"loss": 0.4794,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.544,
|
| 118 |
+
"grad_norm": 1.430006980895996,
|
| 119 |
+
"learning_rate": 1.863196645891518e-05,
|
| 120 |
+
"loss": 0.4947,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 2.7039999999999997,
|
| 125 |
+
"grad_norm": 0.9796671271324158,
|
| 126 |
+
"learning_rate": 1.8334194061608577e-05,
|
| 127 |
+
"loss": 0.4618,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.864,
|
| 132 |
+
"grad_norm": 1.1556652784347534,
|
| 133 |
+
"learning_rate": 1.8010010944693846e-05,
|
| 134 |
+
"loss": 0.4828,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.016,
|
| 139 |
+
"grad_norm": 0.9884580373764038,
|
| 140 |
+
"learning_rate": 1.766044443118978e-05,
|
| 141 |
+
"loss": 0.4485,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 3.176,
|
| 146 |
+
"grad_norm": 1.4118114709854126,
|
| 147 |
+
"learning_rate": 1.7286602283059238e-05,
|
| 148 |
+
"loss": 0.4148,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 3.336,
|
| 153 |
+
"grad_norm": 1.833937168121338,
|
| 154 |
+
"learning_rate": 1.688966919075687e-05,
|
| 155 |
+
"loss": 0.3848,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.496,
|
| 160 |
+
"grad_norm": 1.2855585813522339,
|
| 161 |
+
"learning_rate": 1.647090301899358e-05,
|
| 162 |
+
"loss": 0.3866,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 3.656,
|
| 167 |
+
"grad_norm": 1.1476826667785645,
|
| 168 |
+
"learning_rate": 1.60316308206148e-05,
|
| 169 |
+
"loss": 0.3989,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.816,
|
| 174 |
+
"grad_norm": 1.1333897113800049,
|
| 175 |
+
"learning_rate": 1.5573244631224364e-05,
|
| 176 |
+
"loss": 0.3955,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.976,
|
| 181 |
+
"grad_norm": 1.8493810892105103,
|
| 182 |
+
"learning_rate": 1.5097197057880707e-05,
|
| 183 |
+
"loss": 0.353,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 4.128,
|
| 188 |
+
"grad_norm": 1.493438720703125,
|
| 189 |
+
"learning_rate": 1.4604996675844586e-05,
|
| 190 |
+
"loss": 0.3075,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 4.288,
|
| 195 |
+
"grad_norm": 2.338547945022583,
|
| 196 |
+
"learning_rate": 1.4098203247965876e-05,
|
| 197 |
+
"loss": 0.346,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 4.448,
|
| 202 |
+
"grad_norm": 1.3177692890167236,
|
| 203 |
+
"learning_rate": 1.3578422781858994e-05,
|
| 204 |
+
"loss": 0.3307,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 4.608,
|
| 209 |
+
"grad_norm": 1.2539737224578857,
|
| 210 |
+
"learning_rate": 1.3047302440530538e-05,
|
| 211 |
+
"loss": 0.3482,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.768,
|
| 216 |
+
"grad_norm": 1.0234341621398926,
|
| 217 |
+
"learning_rate": 1.2506525322587207e-05,
|
| 218 |
+
"loss": 0.3244,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.928,
|
| 223 |
+
"grad_norm": 1.274221658706665,
|
| 224 |
+
"learning_rate": 1.1957805128565232e-05,
|
| 225 |
+
"loss": 0.278,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 5.08,
|
| 230 |
+
"grad_norm": 1.353709101676941,
|
| 231 |
+
"learning_rate": 1.1402880730283598e-05,
|
| 232 |
+
"loss": 0.2497,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 5.24,
|
| 237 |
+
"grad_norm": 2.2268123626708984,
|
| 238 |
+
"learning_rate": 1.0843510660430447e-05,
|
| 239 |
+
"loss": 0.2217,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.4,
|
| 244 |
+
"grad_norm": 2.0857222080230713,
|
| 245 |
+
"learning_rate": 1.028146753984505e-05,
|
| 246 |
+
"loss": 0.2379,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 5.5600000000000005,
|
| 251 |
+
"grad_norm": 2.352081775665283,
|
| 252 |
+
"learning_rate": 9.718532460154948e-06,
|
| 253 |
+
"loss": 0.245,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.72,
|
| 258 |
+
"grad_norm": 1.6790026426315308,
|
| 259 |
+
"learning_rate": 9.156489339569555e-06,
|
| 260 |
+
"loss": 0.2337,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 5.88,
|
| 265 |
+
"grad_norm": 0.9887088537216187,
|
| 266 |
+
"learning_rate": 8.597119269716403e-06,
|
| 267 |
+
"loss": 0.2297,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 6.032,
|
| 272 |
+
"grad_norm": 1.4913004636764526,
|
| 273 |
+
"learning_rate": 8.042194871434771e-06,
|
| 274 |
+
"loss": 0.2222,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 6.192,
|
| 279 |
+
"grad_norm": 1.9435575008392334,
|
| 280 |
+
"learning_rate": 7.493474677412795e-06,
|
| 281 |
+
"loss": 0.1506,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 6.352,
|
| 286 |
+
"grad_norm": 1.686815619468689,
|
| 287 |
+
"learning_rate": 6.952697559469464e-06,
|
| 288 |
+
"loss": 0.1547,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 6.5120000000000005,
|
| 293 |
+
"grad_norm": 1.5592477321624756,
|
| 294 |
+
"learning_rate": 6.421577218141007e-06,
|
| 295 |
+
"loss": 0.1359,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 6.672,
|
| 300 |
+
"grad_norm": 2.845890760421753,
|
| 301 |
+
"learning_rate": 5.901796752034128e-06,
|
| 302 |
+
"loss": 0.1817,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 6.832,
|
| 307 |
+
"grad_norm": 1.81553316116333,
|
| 308 |
+
"learning_rate": 5.395003324155414e-06,
|
| 309 |
+
"loss": 0.135,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 6.992,
|
| 314 |
+
"grad_norm": 1.9674084186553955,
|
| 315 |
+
"learning_rate": 4.902802942119293e-06,
|
| 316 |
+
"loss": 0.1423,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 7.144,
|
| 321 |
+
"grad_norm": 1.0333631038665771,
|
| 322 |
+
"learning_rate": 4.426755368775637e-06,
|
| 323 |
+
"loss": 0.0863,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.304,
|
| 328 |
+
"grad_norm": 3.6444036960601807,
|
| 329 |
+
"learning_rate": 3.9683691793852044e-06,
|
| 330 |
+
"loss": 0.0954,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 7.464,
|
| 335 |
+
"grad_norm": 2.4928786754608154,
|
| 336 |
+
"learning_rate": 3.5290969810064258e-06,
|
| 337 |
+
"loss": 0.0892,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.624,
|
| 342 |
+
"grad_norm": 2.4595706462860107,
|
| 343 |
+
"learning_rate": 3.110330809243134e-06,
|
| 344 |
+
"loss": 0.0705,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.784,
|
| 349 |
+
"grad_norm": 2.398029088973999,
|
| 350 |
+
"learning_rate": 2.7133977169407634e-06,
|
| 351 |
+
"loss": 0.0872,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.944,
|
| 356 |
+
"grad_norm": 1.6807390451431274,
|
| 357 |
+
"learning_rate": 2.339555568810221e-06,
|
| 358 |
+
"loss": 0.077,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 8.096,
|
| 363 |
+
"grad_norm": 0.9940488934516907,
|
| 364 |
+
"learning_rate": 1.9899890553061565e-06,
|
| 365 |
+
"loss": 0.0604,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 8.256,
|
| 370 |
+
"grad_norm": 1.9791232347488403,
|
| 371 |
+
"learning_rate": 1.6658059383914249e-06,
|
| 372 |
+
"loss": 0.0446,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 8.416,
|
| 377 |
+
"grad_norm": 0.7762503027915955,
|
| 378 |
+
"learning_rate": 1.3680335410848211e-06,
|
| 379 |
+
"loss": 0.0432,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 8.576,
|
| 384 |
+
"grad_norm": 2.0330629348754883,
|
| 385 |
+
"learning_rate": 1.097615491916485e-06,
|
| 386 |
+
"loss": 0.0428,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 8.736,
|
| 391 |
+
"grad_norm": 0.7456198930740356,
|
| 392 |
+
"learning_rate": 8.554087346077633e-07,
|
| 393 |
+
"loss": 0.0322,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 8.896,
|
| 398 |
+
"grad_norm": 1.492835283279419,
|
| 399 |
+
"learning_rate": 6.421808124516437e-07,
|
| 400 |
+
"loss": 0.0402,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 9.048,
|
| 405 |
+
"grad_norm": 0.904043972492218,
|
| 406 |
+
"learning_rate": 4.5860743599951186e-07,
|
| 407 |
+
"loss": 0.0288,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 9.208,
|
| 412 |
+
"grad_norm": 0.47524094581604004,
|
| 413 |
+
"learning_rate": 3.0527034176207724e-07,
|
| 414 |
+
"loss": 0.029,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 9.368,
|
| 419 |
+
"grad_norm": 1.197879433631897,
|
| 420 |
+
"learning_rate": 1.8265544871020724e-07,
|
| 421 |
+
"loss": 0.0222,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 9.528,
|
| 426 |
+
"grad_norm": 0.608761727809906,
|
| 427 |
+
"learning_rate": 9.11513184176116e-08,
|
| 428 |
+
"loss": 0.0235,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 9.688,
|
| 433 |
+
"grad_norm": 0.5942819714546204,
|
| 434 |
+
"learning_rate": 3.104792372512822e-08,
|
| 435 |
+
"loss": 0.0249,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 9.848,
|
| 440 |
+
"grad_norm": 0.9274442791938782,
|
| 441 |
+
"learning_rate": 2.535729828669897e-09,
|
| 442 |
+
"loss": 0.0308,
|
| 443 |
+
"step": 620
|
| 444 |
+
}
|
| 445 |
+
],
|
| 446 |
+
"logging_steps": 10,
|
| 447 |
+
"max_steps": 620,
|
| 448 |
+
"num_input_tokens_seen": 0,
|
| 449 |
+
"num_train_epochs": 10,
|
| 450 |
+
"save_steps": 10000,
|
| 451 |
+
"stateful_callbacks": {
|
| 452 |
+
"TrainerControl": {
|
| 453 |
+
"args": {
|
| 454 |
+
"should_epoch_stop": false,
|
| 455 |
+
"should_evaluate": false,
|
| 456 |
+
"should_log": false,
|
| 457 |
+
"should_save": true,
|
| 458 |
+
"should_training_stop": true
|
| 459 |
+
},
|
| 460 |
+
"attributes": {}
|
| 461 |
+
}
|
| 462 |
+
},
|
| 463 |
+
"total_flos": 4.910594218000384e+16,
|
| 464 |
+
"train_batch_size": 2,
|
| 465 |
+
"trial_name": null,
|
| 466 |
+
"trial_params": null
|
| 467 |
+
}
|
checkpoint-620/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07cea128d4351b5d1c2fe0151763c4c546f96d8c3c6eaa874df36ec32f666c0a
|
| 3 |
+
size 5688
|
checkpoint-620/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 12845056,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 3136,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 12845056,
|
| 26 |
+
"shortest_edge": 3136
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
runs/Mar01_11-08-39_2eb495d65f62/events.out.tfevents.1740827396.2eb495d65f62.125.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b787422d2ba6f09e20b2c3fb1d5c5ad68f10978d4ceb09abc554c6101e54fa7a
|
| 3 |
+
size 19328
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
|
| 3 |
+
size 11420371
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
},
|
| 117 |
+
"additional_special_tokens": [
|
| 118 |
+
"<|im_start|>",
|
| 119 |
+
"<|im_end|>",
|
| 120 |
+
"<|object_ref_start|>",
|
| 121 |
+
"<|object_ref_end|>",
|
| 122 |
+
"<|box_start|>",
|
| 123 |
+
"<|box_end|>",
|
| 124 |
+
"<|quad_start|>",
|
| 125 |
+
"<|quad_end|>",
|
| 126 |
+
"<|vision_start|>",
|
| 127 |
+
"<|vision_end|>",
|
| 128 |
+
"<|vision_pad|>",
|
| 129 |
+
"<|image_pad|>",
|
| 130 |
+
"<|video_pad|>"
|
| 131 |
+
],
|
| 132 |
+
"bos_token": null,
|
| 133 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 134 |
+
"clean_up_tokenization_spaces": false,
|
| 135 |
+
"eos_token": "<|im_end|>",
|
| 136 |
+
"errors": "replace",
|
| 137 |
+
"extra_special_tokens": {},
|
| 138 |
+
"model_max_length": 2048,
|
| 139 |
+
"pad_token": "<|endoftext|>",
|
| 140 |
+
"padding_side": "right",
|
| 141 |
+
"processor_class": "Qwen2VLProcessor",
|
| 142 |
+
"split_special_tokens": false,
|
| 143 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 144 |
+
"unk_token": null
|
| 145 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.848,
|
| 3 |
+
"total_flos": 4.910594218000384e+16,
|
| 4 |
+
"train_loss": 0.3172732482754415,
|
| 5 |
+
"train_runtime": 12792.4734,
|
| 6 |
+
"train_samples_per_second": 0.391,
|
| 7 |
+
"train_steps_per_second": 0.048
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 620, "loss": 1.4695, "lr": 2.2580645161290324e-06, "epoch": 0.16, "percentage": 1.61, "elapsed_time": "0:03:21", "remaining_time": "3:24:35"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 620, "loss": 0.9564, "lr": 5.483870967741935e-06, "epoch": 0.32, "percentage": 3.23, "elapsed_time": "0:06:49", "remaining_time": "3:24:57"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 620, "loss": 0.7467, "lr": 8.70967741935484e-06, "epoch": 0.48, "percentage": 4.84, "elapsed_time": "0:10:17", "remaining_time": "3:22:33"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 620, "loss": 0.7442, "lr": 1.1935483870967743e-05, "epoch": 0.64, "percentage": 6.45, "elapsed_time": "0:13:46", "remaining_time": "3:19:43"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 620, "loss": 0.6401, "lr": 1.5161290322580646e-05, "epoch": 0.8, "percentage": 8.06, "elapsed_time": "0:17:15", "remaining_time": "3:16:39"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 620, "loss": 0.6412, "lr": 1.838709677419355e-05, "epoch": 0.96, "percentage": 9.68, "elapsed_time": "0:20:43", "remaining_time": "3:13:28"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 620, "loss": 0.5019, "lr": 1.9996038016334953e-05, "epoch": 1.112, "percentage": 11.29, "elapsed_time": "0:24:01", "remaining_time": "3:08:46"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 620, "loss": 0.5679, "lr": 1.9968952076274873e-05, "epoch": 1.272, "percentage": 12.9, "elapsed_time": "0:27:29", "remaining_time": "3:05:32"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 620, "loss": 0.5871, "lr": 1.990884868158239e-05, "epoch": 1.432, "percentage": 14.52, "elapsed_time": "0:30:56", "remaining_time": "3:02:15"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 620, "loss": 0.5669, "lr": 1.9817344551289796e-05, "epoch": 1.592, "percentage": 16.13, "elapsed_time": "0:34:24", "remaining_time": "2:58:55"}
|
| 11 |
+
{"current_steps": 110, "total_steps": 620, "loss": 0.5716, "lr": 1.9694729658237925e-05, "epoch": 1.752, "percentage": 17.74, "elapsed_time": "0:37:53", "remaining_time": "2:55:38"}
|
| 12 |
+
{"current_steps": 120, "total_steps": 620, "loss": 0.584, "lr": 1.954139256400049e-05, "epoch": 1.912, "percentage": 19.35, "elapsed_time": "0:41:20", "remaining_time": "2:52:16"}
|
| 13 |
+
{"current_steps": 130, "total_steps": 620, "loss": 0.4986, "lr": 1.935781918754836e-05, "epoch": 2.064, "percentage": 20.97, "elapsed_time": "0:44:38", "remaining_time": "2:48:17"}
|
| 14 |
+
{"current_steps": 140, "total_steps": 620, "loss": 0.4908, "lr": 1.914459126539224e-05, "epoch": 2.224, "percentage": 22.58, "elapsed_time": "0:48:07", "remaining_time": "2:45:00"}
|
| 15 |
+
{"current_steps": 150, "total_steps": 620, "loss": 0.4794, "lr": 1.8902384508083518e-05, "epoch": 2.384, "percentage": 24.19, "elapsed_time": "0:51:36", "remaining_time": "2:41:41"}
|
| 16 |
+
{"current_steps": 160, "total_steps": 620, "loss": 0.4947, "lr": 1.863196645891518e-05, "epoch": 2.544, "percentage": 25.81, "elapsed_time": "0:55:04", "remaining_time": "2:38:19"}
|
| 17 |
+
{"current_steps": 170, "total_steps": 620, "loss": 0.4618, "lr": 1.8334194061608577e-05, "epoch": 2.7039999999999997, "percentage": 27.42, "elapsed_time": "0:58:31", "remaining_time": "2:34:55"}
|
| 18 |
+
{"current_steps": 180, "total_steps": 620, "loss": 0.4828, "lr": 1.8010010944693846e-05, "epoch": 2.864, "percentage": 29.03, "elapsed_time": "1:02:00", "remaining_time": "2:31:33"}
|
| 19 |
+
{"current_steps": 190, "total_steps": 620, "loss": 0.4485, "lr": 1.766044443118978e-05, "epoch": 3.016, "percentage": 30.65, "elapsed_time": "1:05:18", "remaining_time": "2:27:47"}
|
| 20 |
+
{"current_steps": 200, "total_steps": 620, "loss": 0.4148, "lr": 1.7286602283059238e-05, "epoch": 3.176, "percentage": 32.26, "elapsed_time": "1:08:45", "remaining_time": "2:24:23"}
|
| 21 |
+
{"current_steps": 210, "total_steps": 620, "loss": 0.3848, "lr": 1.688966919075687e-05, "epoch": 3.336, "percentage": 33.87, "elapsed_time": "1:12:13", "remaining_time": "2:21:00"}
|
| 22 |
+
{"current_steps": 220, "total_steps": 620, "loss": 0.3866, "lr": 1.647090301899358e-05, "epoch": 3.496, "percentage": 35.48, "elapsed_time": "1:15:42", "remaining_time": "2:17:38"}
|
| 23 |
+
{"current_steps": 230, "total_steps": 620, "loss": 0.3989, "lr": 1.60316308206148e-05, "epoch": 3.656, "percentage": 37.1, "elapsed_time": "1:19:09", "remaining_time": "2:14:13"}
|
| 24 |
+
{"current_steps": 240, "total_steps": 620, "loss": 0.3955, "lr": 1.5573244631224364e-05, "epoch": 3.816, "percentage": 38.71, "elapsed_time": "1:22:37", "remaining_time": "2:10:48"}
|
| 25 |
+
{"current_steps": 250, "total_steps": 620, "loss": 0.353, "lr": 1.5097197057880707e-05, "epoch": 3.976, "percentage": 40.32, "elapsed_time": "1:26:05", "remaining_time": "2:07:25"}
|
| 26 |
+
{"current_steps": 260, "total_steps": 620, "loss": 0.3075, "lr": 1.4604996675844586e-05, "epoch": 4.128, "percentage": 41.94, "elapsed_time": "1:29:22", "remaining_time": "2:03:45"}
|
| 27 |
+
{"current_steps": 270, "total_steps": 620, "loss": 0.346, "lr": 1.4098203247965876e-05, "epoch": 4.288, "percentage": 43.55, "elapsed_time": "1:32:51", "remaining_time": "2:00:22"}
|
| 28 |
+
{"current_steps": 280, "total_steps": 620, "loss": 0.3307, "lr": 1.3578422781858994e-05, "epoch": 4.448, "percentage": 45.16, "elapsed_time": "1:36:19", "remaining_time": "1:56:57"}
|
| 29 |
+
{"current_steps": 290, "total_steps": 620, "loss": 0.3482, "lr": 1.3047302440530538e-05, "epoch": 4.608, "percentage": 46.77, "elapsed_time": "1:39:46", "remaining_time": "1:53:32"}
|
| 30 |
+
{"current_steps": 300, "total_steps": 620, "loss": 0.3244, "lr": 1.2506525322587207e-05, "epoch": 4.768, "percentage": 48.39, "elapsed_time": "1:43:15", "remaining_time": "1:50:08"}
|
| 31 |
+
{"current_steps": 310, "total_steps": 620, "loss": 0.278, "lr": 1.1957805128565232e-05, "epoch": 4.928, "percentage": 50.0, "elapsed_time": "1:46:44", "remaining_time": "1:46:44"}
|
| 32 |
+
{"current_steps": 320, "total_steps": 620, "loss": 0.2497, "lr": 1.1402880730283598e-05, "epoch": 5.08, "percentage": 51.61, "elapsed_time": "1:50:02", "remaining_time": "1:43:09"}
|
| 33 |
+
{"current_steps": 330, "total_steps": 620, "loss": 0.2217, "lr": 1.0843510660430447e-05, "epoch": 5.24, "percentage": 53.23, "elapsed_time": "1:53:30", "remaining_time": "1:39:44"}
|
| 34 |
+
{"current_steps": 340, "total_steps": 620, "loss": 0.2379, "lr": 1.028146753984505e-05, "epoch": 5.4, "percentage": 54.84, "elapsed_time": "1:56:58", "remaining_time": "1:36:19"}
|
| 35 |
+
{"current_steps": 350, "total_steps": 620, "loss": 0.245, "lr": 9.718532460154948e-06, "epoch": 5.5600000000000005, "percentage": 56.45, "elapsed_time": "2:00:26", "remaining_time": "1:32:54"}
|
| 36 |
+
{"current_steps": 360, "total_steps": 620, "loss": 0.2337, "lr": 9.156489339569555e-06, "epoch": 5.72, "percentage": 58.06, "elapsed_time": "2:03:55", "remaining_time": "1:29:30"}
|
| 37 |
+
{"current_steps": 370, "total_steps": 620, "loss": 0.2297, "lr": 8.597119269716403e-06, "epoch": 5.88, "percentage": 59.68, "elapsed_time": "2:07:22", "remaining_time": "1:26:04"}
|
| 38 |
+
{"current_steps": 380, "total_steps": 620, "loss": 0.2222, "lr": 8.042194871434771e-06, "epoch": 6.032, "percentage": 61.29, "elapsed_time": "2:10:41", "remaining_time": "1:22:32"}
|
| 39 |
+
{"current_steps": 390, "total_steps": 620, "loss": 0.1506, "lr": 7.493474677412795e-06, "epoch": 6.192, "percentage": 62.9, "elapsed_time": "2:14:08", "remaining_time": "1:19:06"}
|
| 40 |
+
{"current_steps": 400, "total_steps": 620, "loss": 0.1547, "lr": 6.952697559469464e-06, "epoch": 6.352, "percentage": 64.52, "elapsed_time": "2:17:35", "remaining_time": "1:15:40"}
|
| 41 |
+
{"current_steps": 410, "total_steps": 620, "loss": 0.1359, "lr": 6.421577218141007e-06, "epoch": 6.5120000000000005, "percentage": 66.13, "elapsed_time": "2:21:02", "remaining_time": "1:12:14"}
|
| 42 |
+
{"current_steps": 420, "total_steps": 620, "loss": 0.1817, "lr": 5.901796752034128e-06, "epoch": 6.672, "percentage": 67.74, "elapsed_time": "2:24:30", "remaining_time": "1:08:48"}
|
| 43 |
+
{"current_steps": 430, "total_steps": 620, "loss": 0.135, "lr": 5.395003324155414e-06, "epoch": 6.832, "percentage": 69.35, "elapsed_time": "2:27:58", "remaining_time": "1:05:23"}
|
| 44 |
+
{"current_steps": 440, "total_steps": 620, "loss": 0.1423, "lr": 4.902802942119293e-06, "epoch": 6.992, "percentage": 70.97, "elapsed_time": "2:31:26", "remaining_time": "1:01:57"}
|
| 45 |
+
{"current_steps": 450, "total_steps": 620, "loss": 0.0863, "lr": 4.426755368775637e-06, "epoch": 7.144, "percentage": 72.58, "elapsed_time": "2:34:43", "remaining_time": "0:58:27"}
|
| 46 |
+
{"current_steps": 460, "total_steps": 620, "loss": 0.0954, "lr": 3.9683691793852044e-06, "epoch": 7.304, "percentage": 74.19, "elapsed_time": "2:38:11", "remaining_time": "0:55:01"}
|
| 47 |
+
{"current_steps": 470, "total_steps": 620, "loss": 0.0892, "lr": 3.5290969810064258e-06, "epoch": 7.464, "percentage": 75.81, "elapsed_time": "2:41:40", "remaining_time": "0:51:35"}
|
| 48 |
+
{"current_steps": 480, "total_steps": 620, "loss": 0.0705, "lr": 3.110330809243134e-06, "epoch": 7.624, "percentage": 77.42, "elapsed_time": "2:45:06", "remaining_time": "0:48:09"}
|
| 49 |
+
{"current_steps": 490, "total_steps": 620, "loss": 0.0872, "lr": 2.7133977169407634e-06, "epoch": 7.784, "percentage": 79.03, "elapsed_time": "2:48:35", "remaining_time": "0:44:43"}
|
| 50 |
+
{"current_steps": 500, "total_steps": 620, "loss": 0.077, "lr": 2.339555568810221e-06, "epoch": 7.944, "percentage": 80.65, "elapsed_time": "2:52:02", "remaining_time": "0:41:17"}
|
| 51 |
+
{"current_steps": 510, "total_steps": 620, "loss": 0.0604, "lr": 1.9899890553061565e-06, "epoch": 8.096, "percentage": 82.26, "elapsed_time": "2:55:20", "remaining_time": "0:37:49"}
|
| 52 |
+
{"current_steps": 520, "total_steps": 620, "loss": 0.0446, "lr": 1.6658059383914249e-06, "epoch": 8.256, "percentage": 83.87, "elapsed_time": "2:58:47", "remaining_time": "0:34:22"}
|
| 53 |
+
{"current_steps": 530, "total_steps": 620, "loss": 0.0432, "lr": 1.3680335410848211e-06, "epoch": 8.416, "percentage": 85.48, "elapsed_time": "3:02:13", "remaining_time": "0:30:56"}
|
| 54 |
+
{"current_steps": 540, "total_steps": 620, "loss": 0.0428, "lr": 1.097615491916485e-06, "epoch": 8.576, "percentage": 87.1, "elapsed_time": "3:05:41", "remaining_time": "0:27:30"}
|
| 55 |
+
{"current_steps": 550, "total_steps": 620, "loss": 0.0322, "lr": 8.554087346077633e-07, "epoch": 8.736, "percentage": 88.71, "elapsed_time": "3:09:08", "remaining_time": "0:24:04"}
|
| 56 |
+
{"current_steps": 560, "total_steps": 620, "loss": 0.0402, "lr": 6.421808124516437e-07, "epoch": 8.896, "percentage": 90.32, "elapsed_time": "3:12:35", "remaining_time": "0:20:38"}
|
| 57 |
+
{"current_steps": 570, "total_steps": 620, "loss": 0.0288, "lr": 4.5860743599951186e-07, "epoch": 9.048, "percentage": 91.94, "elapsed_time": "3:15:52", "remaining_time": "0:17:10"}
|
| 58 |
+
{"current_steps": 580, "total_steps": 620, "loss": 0.029, "lr": 3.0527034176207724e-07, "epoch": 9.208, "percentage": 93.55, "elapsed_time": "3:19:19", "remaining_time": "0:13:44"}
|
| 59 |
+
{"current_steps": 590, "total_steps": 620, "loss": 0.0222, "lr": 1.8265544871020724e-07, "epoch": 9.368, "percentage": 95.16, "elapsed_time": "3:22:46", "remaining_time": "0:10:18"}
|
| 60 |
+
{"current_steps": 600, "total_steps": 620, "loss": 0.0235, "lr": 9.11513184176116e-08, "epoch": 9.528, "percentage": 96.77, "elapsed_time": "3:26:13", "remaining_time": "0:06:52"}
|
| 61 |
+
{"current_steps": 610, "total_steps": 620, "loss": 0.0249, "lr": 3.104792372512822e-08, "epoch": 9.688, "percentage": 98.39, "elapsed_time": "3:29:41", "remaining_time": "0:03:26"}
|
| 62 |
+
{"current_steps": 620, "total_steps": 620, "loss": 0.0308, "lr": 2.535729828669897e-09, "epoch": 9.848, "percentage": 100.0, "elapsed_time": "3:33:08", "remaining_time": "0:00:00"}
|
| 63 |
+
{"current_steps": 620, "total_steps": 620, "epoch": 9.848, "percentage": 100.0, "elapsed_time": "3:33:09", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,476 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.848,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 620,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.16,
|
| 13 |
+
"grad_norm": 3.8025777339935303,
|
| 14 |
+
"learning_rate": 2.2580645161290324e-06,
|
| 15 |
+
"loss": 1.4695,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.32,
|
| 20 |
+
"grad_norm": 1.3798772096633911,
|
| 21 |
+
"learning_rate": 5.483870967741935e-06,
|
| 22 |
+
"loss": 0.9564,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.48,
|
| 27 |
+
"grad_norm": 1.1069912910461426,
|
| 28 |
+
"learning_rate": 8.70967741935484e-06,
|
| 29 |
+
"loss": 0.7467,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.64,
|
| 34 |
+
"grad_norm": 1.3565958738327026,
|
| 35 |
+
"learning_rate": 1.1935483870967743e-05,
|
| 36 |
+
"loss": 0.7442,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.8,
|
| 41 |
+
"grad_norm": 0.8724671006202698,
|
| 42 |
+
"learning_rate": 1.5161290322580646e-05,
|
| 43 |
+
"loss": 0.6401,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.96,
|
| 48 |
+
"grad_norm": 0.8387081027030945,
|
| 49 |
+
"learning_rate": 1.838709677419355e-05,
|
| 50 |
+
"loss": 0.6412,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.112,
|
| 55 |
+
"grad_norm": 1.1549522876739502,
|
| 56 |
+
"learning_rate": 1.9996038016334953e-05,
|
| 57 |
+
"loss": 0.5019,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.272,
|
| 62 |
+
"grad_norm": 0.7454654574394226,
|
| 63 |
+
"learning_rate": 1.9968952076274873e-05,
|
| 64 |
+
"loss": 0.5679,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.432,
|
| 69 |
+
"grad_norm": 1.2986727952957153,
|
| 70 |
+
"learning_rate": 1.990884868158239e-05,
|
| 71 |
+
"loss": 0.5871,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 1.592,
|
| 76 |
+
"grad_norm": 1.4838392734527588,
|
| 77 |
+
"learning_rate": 1.9817344551289796e-05,
|
| 78 |
+
"loss": 0.5669,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.752,
|
| 83 |
+
"grad_norm": 1.1603983640670776,
|
| 84 |
+
"learning_rate": 1.9694729658237925e-05,
|
| 85 |
+
"loss": 0.5716,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.912,
|
| 90 |
+
"grad_norm": 1.4420567750930786,
|
| 91 |
+
"learning_rate": 1.954139256400049e-05,
|
| 92 |
+
"loss": 0.584,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.064,
|
| 97 |
+
"grad_norm": 0.9452749490737915,
|
| 98 |
+
"learning_rate": 1.935781918754836e-05,
|
| 99 |
+
"loss": 0.4986,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 2.224,
|
| 104 |
+
"grad_norm": 1.114253044128418,
|
| 105 |
+
"learning_rate": 1.914459126539224e-05,
|
| 106 |
+
"loss": 0.4908,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 2.384,
|
| 111 |
+
"grad_norm": 1.864726185798645,
|
| 112 |
+
"learning_rate": 1.8902384508083518e-05,
|
| 113 |
+
"loss": 0.4794,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.544,
|
| 118 |
+
"grad_norm": 1.430006980895996,
|
| 119 |
+
"learning_rate": 1.863196645891518e-05,
|
| 120 |
+
"loss": 0.4947,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 2.7039999999999997,
|
| 125 |
+
"grad_norm": 0.9796671271324158,
|
| 126 |
+
"learning_rate": 1.8334194061608577e-05,
|
| 127 |
+
"loss": 0.4618,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.864,
|
| 132 |
+
"grad_norm": 1.1556652784347534,
|
| 133 |
+
"learning_rate": 1.8010010944693846e-05,
|
| 134 |
+
"loss": 0.4828,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.016,
|
| 139 |
+
"grad_norm": 0.9884580373764038,
|
| 140 |
+
"learning_rate": 1.766044443118978e-05,
|
| 141 |
+
"loss": 0.4485,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 3.176,
|
| 146 |
+
"grad_norm": 1.4118114709854126,
|
| 147 |
+
"learning_rate": 1.7286602283059238e-05,
|
| 148 |
+
"loss": 0.4148,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 3.336,
|
| 153 |
+
"grad_norm": 1.833937168121338,
|
| 154 |
+
"learning_rate": 1.688966919075687e-05,
|
| 155 |
+
"loss": 0.3848,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 3.496,
|
| 160 |
+
"grad_norm": 1.2855585813522339,
|
| 161 |
+
"learning_rate": 1.647090301899358e-05,
|
| 162 |
+
"loss": 0.3866,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 3.656,
|
| 167 |
+
"grad_norm": 1.1476826667785645,
|
| 168 |
+
"learning_rate": 1.60316308206148e-05,
|
| 169 |
+
"loss": 0.3989,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 3.816,
|
| 174 |
+
"grad_norm": 1.1333897113800049,
|
| 175 |
+
"learning_rate": 1.5573244631224364e-05,
|
| 176 |
+
"loss": 0.3955,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.976,
|
| 181 |
+
"grad_norm": 1.8493810892105103,
|
| 182 |
+
"learning_rate": 1.5097197057880707e-05,
|
| 183 |
+
"loss": 0.353,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 4.128,
|
| 188 |
+
"grad_norm": 1.493438720703125,
|
| 189 |
+
"learning_rate": 1.4604996675844586e-05,
|
| 190 |
+
"loss": 0.3075,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 4.288,
|
| 195 |
+
"grad_norm": 2.338547945022583,
|
| 196 |
+
"learning_rate": 1.4098203247965876e-05,
|
| 197 |
+
"loss": 0.346,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 4.448,
|
| 202 |
+
"grad_norm": 1.3177692890167236,
|
| 203 |
+
"learning_rate": 1.3578422781858994e-05,
|
| 204 |
+
"loss": 0.3307,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 4.608,
|
| 209 |
+
"grad_norm": 1.2539737224578857,
|
| 210 |
+
"learning_rate": 1.3047302440530538e-05,
|
| 211 |
+
"loss": 0.3482,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 4.768,
|
| 216 |
+
"grad_norm": 1.0234341621398926,
|
| 217 |
+
"learning_rate": 1.2506525322587207e-05,
|
| 218 |
+
"loss": 0.3244,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.928,
|
| 223 |
+
"grad_norm": 1.274221658706665,
|
| 224 |
+
"learning_rate": 1.1957805128565232e-05,
|
| 225 |
+
"loss": 0.278,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 5.08,
|
| 230 |
+
"grad_norm": 1.353709101676941,
|
| 231 |
+
"learning_rate": 1.1402880730283598e-05,
|
| 232 |
+
"loss": 0.2497,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 5.24,
|
| 237 |
+
"grad_norm": 2.2268123626708984,
|
| 238 |
+
"learning_rate": 1.0843510660430447e-05,
|
| 239 |
+
"loss": 0.2217,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 5.4,
|
| 244 |
+
"grad_norm": 2.0857222080230713,
|
| 245 |
+
"learning_rate": 1.028146753984505e-05,
|
| 246 |
+
"loss": 0.2379,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 5.5600000000000005,
|
| 251 |
+
"grad_norm": 2.352081775665283,
|
| 252 |
+
"learning_rate": 9.718532460154948e-06,
|
| 253 |
+
"loss": 0.245,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 5.72,
|
| 258 |
+
"grad_norm": 1.6790026426315308,
|
| 259 |
+
"learning_rate": 9.156489339569555e-06,
|
| 260 |
+
"loss": 0.2337,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 5.88,
|
| 265 |
+
"grad_norm": 0.9887088537216187,
|
| 266 |
+
"learning_rate": 8.597119269716403e-06,
|
| 267 |
+
"loss": 0.2297,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 6.032,
|
| 272 |
+
"grad_norm": 1.4913004636764526,
|
| 273 |
+
"learning_rate": 8.042194871434771e-06,
|
| 274 |
+
"loss": 0.2222,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 6.192,
|
| 279 |
+
"grad_norm": 1.9435575008392334,
|
| 280 |
+
"learning_rate": 7.493474677412795e-06,
|
| 281 |
+
"loss": 0.1506,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 6.352,
|
| 286 |
+
"grad_norm": 1.686815619468689,
|
| 287 |
+
"learning_rate": 6.952697559469464e-06,
|
| 288 |
+
"loss": 0.1547,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 6.5120000000000005,
|
| 293 |
+
"grad_norm": 1.5592477321624756,
|
| 294 |
+
"learning_rate": 6.421577218141007e-06,
|
| 295 |
+
"loss": 0.1359,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 6.672,
|
| 300 |
+
"grad_norm": 2.845890760421753,
|
| 301 |
+
"learning_rate": 5.901796752034128e-06,
|
| 302 |
+
"loss": 0.1817,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 6.832,
|
| 307 |
+
"grad_norm": 1.81553316116333,
|
| 308 |
+
"learning_rate": 5.395003324155414e-06,
|
| 309 |
+
"loss": 0.135,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 6.992,
|
| 314 |
+
"grad_norm": 1.9674084186553955,
|
| 315 |
+
"learning_rate": 4.902802942119293e-06,
|
| 316 |
+
"loss": 0.1423,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 7.144,
|
| 321 |
+
"grad_norm": 1.0333631038665771,
|
| 322 |
+
"learning_rate": 4.426755368775637e-06,
|
| 323 |
+
"loss": 0.0863,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.304,
|
| 328 |
+
"grad_norm": 3.6444036960601807,
|
| 329 |
+
"learning_rate": 3.9683691793852044e-06,
|
| 330 |
+
"loss": 0.0954,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 7.464,
|
| 335 |
+
"grad_norm": 2.4928786754608154,
|
| 336 |
+
"learning_rate": 3.5290969810064258e-06,
|
| 337 |
+
"loss": 0.0892,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.624,
|
| 342 |
+
"grad_norm": 2.4595706462860107,
|
| 343 |
+
"learning_rate": 3.110330809243134e-06,
|
| 344 |
+
"loss": 0.0705,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.784,
|
| 349 |
+
"grad_norm": 2.398029088973999,
|
| 350 |
+
"learning_rate": 2.7133977169407634e-06,
|
| 351 |
+
"loss": 0.0872,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.944,
|
| 356 |
+
"grad_norm": 1.6807390451431274,
|
| 357 |
+
"learning_rate": 2.339555568810221e-06,
|
| 358 |
+
"loss": 0.077,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 8.096,
|
| 363 |
+
"grad_norm": 0.9940488934516907,
|
| 364 |
+
"learning_rate": 1.9899890553061565e-06,
|
| 365 |
+
"loss": 0.0604,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 8.256,
|
| 370 |
+
"grad_norm": 1.9791232347488403,
|
| 371 |
+
"learning_rate": 1.6658059383914249e-06,
|
| 372 |
+
"loss": 0.0446,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 8.416,
|
| 377 |
+
"grad_norm": 0.7762503027915955,
|
| 378 |
+
"learning_rate": 1.3680335410848211e-06,
|
| 379 |
+
"loss": 0.0432,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 8.576,
|
| 384 |
+
"grad_norm": 2.0330629348754883,
|
| 385 |
+
"learning_rate": 1.097615491916485e-06,
|
| 386 |
+
"loss": 0.0428,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 8.736,
|
| 391 |
+
"grad_norm": 0.7456198930740356,
|
| 392 |
+
"learning_rate": 8.554087346077633e-07,
|
| 393 |
+
"loss": 0.0322,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 8.896,
|
| 398 |
+
"grad_norm": 1.492835283279419,
|
| 399 |
+
"learning_rate": 6.421808124516437e-07,
|
| 400 |
+
"loss": 0.0402,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 9.048,
|
| 405 |
+
"grad_norm": 0.904043972492218,
|
| 406 |
+
"learning_rate": 4.5860743599951186e-07,
|
| 407 |
+
"loss": 0.0288,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 9.208,
|
| 412 |
+
"grad_norm": 0.47524094581604004,
|
| 413 |
+
"learning_rate": 3.0527034176207724e-07,
|
| 414 |
+
"loss": 0.029,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 9.368,
|
| 419 |
+
"grad_norm": 1.197879433631897,
|
| 420 |
+
"learning_rate": 1.8265544871020724e-07,
|
| 421 |
+
"loss": 0.0222,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 9.528,
|
| 426 |
+
"grad_norm": 0.608761727809906,
|
| 427 |
+
"learning_rate": 9.11513184176116e-08,
|
| 428 |
+
"loss": 0.0235,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 9.688,
|
| 433 |
+
"grad_norm": 0.5942819714546204,
|
| 434 |
+
"learning_rate": 3.104792372512822e-08,
|
| 435 |
+
"loss": 0.0249,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 9.848,
|
| 440 |
+
"grad_norm": 0.9274442791938782,
|
| 441 |
+
"learning_rate": 2.535729828669897e-09,
|
| 442 |
+
"loss": 0.0308,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 9.848,
|
| 447 |
+
"step": 620,
|
| 448 |
+
"total_flos": 4.910594218000384e+16,
|
| 449 |
+
"train_loss": 0.3172732482754415,
|
| 450 |
+
"train_runtime": 12792.4734,
|
| 451 |
+
"train_samples_per_second": 0.391,
|
| 452 |
+
"train_steps_per_second": 0.048
|
| 453 |
+
}
|
| 454 |
+
],
|
| 455 |
+
"logging_steps": 10,
|
| 456 |
+
"max_steps": 620,
|
| 457 |
+
"num_input_tokens_seen": 0,
|
| 458 |
+
"num_train_epochs": 10,
|
| 459 |
+
"save_steps": 10000,
|
| 460 |
+
"stateful_callbacks": {
|
| 461 |
+
"TrainerControl": {
|
| 462 |
+
"args": {
|
| 463 |
+
"should_epoch_stop": false,
|
| 464 |
+
"should_evaluate": false,
|
| 465 |
+
"should_log": false,
|
| 466 |
+
"should_save": true,
|
| 467 |
+
"should_training_stop": true
|
| 468 |
+
},
|
| 469 |
+
"attributes": {}
|
| 470 |
+
}
|
| 471 |
+
},
|
| 472 |
+
"total_flos": 4.910594218000384e+16,
|
| 473 |
+
"train_batch_size": 2,
|
| 474 |
+
"trial_name": null,
|
| 475 |
+
"trial_params": null
|
| 476 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07cea128d4351b5d1c2fe0151763c4c546f96d8c3c6eaa874df36ec32f666c0a
|
| 3 |
+
size 5688
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|