Training in progress, step 1500
Browse files- README.md +3 -3
- adapter_config.json +94 -94
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -3,9 +3,9 @@ library_name: transformers
|
|
| 3 |
model_name: Qwen25-VL-3B
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
-
- sft
|
| 7 |
-
- trl
|
| 8 |
- unsloth
|
|
|
|
|
|
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
|
@@ -27,7 +27,7 @@ print(output["generated_text"])
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/muhammadosama1994/KSA%20VR%20Project/runs/
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
|
|
|
| 3 |
model_name: Qwen25-VL-3B
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
- unsloth
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
|
|
|
| 27 |
|
| 28 |
## Training procedure
|
| 29 |
|
| 30 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/muhammadosama1994/KSA%20VR%20Project/runs/6z0umql5)
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
adapter_config.json
CHANGED
|
@@ -26,118 +26,118 @@
|
|
| 26 |
"rank_pattern": {},
|
| 27 |
"revision": null,
|
| 28 |
"target_modules": [
|
| 29 |
-
"layers.
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"layers.
|
| 33 |
-
"layers.
|
| 34 |
-
"
|
| 35 |
-
"layers.24.mlp.up_proj",
|
| 36 |
-
"35.mlp.up_proj",
|
| 37 |
-
"layers.0.mlp.down_proj",
|
| 38 |
"layers.15.mlp.down_proj",
|
| 39 |
-
"layers.10.mlp.gate_proj",
|
| 40 |
"layers.16.mlp.gate_proj",
|
| 41 |
-
"layers.24.mlp.down_proj",
|
| 42 |
-
"layers.26.mlp.gate_proj",
|
| 43 |
-
"layers.7.mlp.down_proj",
|
| 44 |
"layers.1.mlp.up_proj",
|
| 45 |
-
"layers.
|
| 46 |
-
"layers.
|
| 47 |
-
"layers.
|
| 48 |
-
"layers.19.mlp.down_proj",
|
| 49 |
-
"layers.16.mlp.down_proj",
|
| 50 |
"layers.4.mlp.down_proj",
|
| 51 |
-
"layers.
|
| 52 |
-
"layers.
|
| 53 |
-
"layers.
|
| 54 |
-
"
|
| 55 |
"layers.4.mlp.up_proj",
|
| 56 |
-
"35.mlp.gate_proj",
|
| 57 |
-
"layers.6.mlp.down_proj",
|
| 58 |
-
"layers.28.mlp.up_proj",
|
| 59 |
-
"layers.18.mlp.down_proj",
|
| 60 |
-
"layers.0.mlp.up_proj",
|
| 61 |
-
"layers.6.mlp.up_proj",
|
| 62 |
"layers.19.mlp.up_proj",
|
|
|
|
|
|
|
| 63 |
"layers.25.mlp.down_proj",
|
| 64 |
-
"layers.30.mlp.
|
| 65 |
-
"layers.
|
| 66 |
-
"layers.
|
| 67 |
-
"layers.
|
| 68 |
-
"layers.
|
| 69 |
-
"
|
| 70 |
-
"layers.
|
| 71 |
-
"layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
"layers.17.mlp.down_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
"layers.27.mlp.down_proj",
|
| 74 |
-
"layers.
|
| 75 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
"layers.10.mlp.down_proj",
|
|
|
|
|
|
|
| 77 |
"layers.8.mlp.up_proj",
|
| 78 |
-
"layers.22.mlp.down_proj",
|
| 79 |
-
"layers.23.mlp.down_proj",
|
| 80 |
-
"33.mlp.gate_proj",
|
| 81 |
-
"layers.25.mlp.gate_proj",
|
| 82 |
-
"layers.21.mlp.gate_proj",
|
| 83 |
-
"layers.22.mlp.gate_proj",
|
| 84 |
-
"layers.2.mlp.gate_proj",
|
| 85 |
-
"layers.17.mlp.gate_proj",
|
| 86 |
-
"layers.30.mlp.down_proj",
|
| 87 |
-
"layers.9.mlp.gate_proj",
|
| 88 |
-
"layers.9.mlp.up_proj",
|
| 89 |
-
"layers.21.mlp.down_proj",
|
| 90 |
-
"layers.11.mlp.gate_proj",
|
| 91 |
-
"k_proj",
|
| 92 |
-
"q_proj",
|
| 93 |
-
"32.mlp.up_proj",
|
| 94 |
-
"layers.28.mlp.gate_proj",
|
| 95 |
"35.mlp.down_proj",
|
| 96 |
-
"layers.
|
| 97 |
-
"layers.
|
| 98 |
-
"layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
"layers.1.mlp.down_proj",
|
| 100 |
-
"layers.
|
| 101 |
"34.mlp.gate_proj",
|
|
|
|
|
|
|
|
|
|
| 102 |
"32.mlp.gate_proj",
|
| 103 |
-
"layers.13.mlp.gate_proj",
|
| 104 |
-
"layers.16.mlp.up_proj",
|
| 105 |
-
"layers.6.mlp.gate_proj",
|
| 106 |
-
"layers.31.mlp.down_proj",
|
| 107 |
-
"layers.13.mlp.down_proj",
|
| 108 |
-
"layers.15.mlp.up_proj",
|
| 109 |
-
"layers.15.mlp.gate_proj",
|
| 110 |
"layers.27.mlp.up_proj",
|
| 111 |
-
"layers.
|
| 112 |
-
"
|
| 113 |
-
"layers.24.mlp.gate_proj",
|
| 114 |
-
"layers.7.mlp.gate_proj",
|
| 115 |
-
"layers.5.mlp.gate_proj",
|
| 116 |
"layers.19.mlp.gate_proj",
|
| 117 |
-
"layers.
|
|
|
|
|
|
|
| 118 |
"v_proj",
|
| 119 |
-
"layers.
|
| 120 |
-
"layers.
|
| 121 |
-
"
|
| 122 |
-
"layers.
|
| 123 |
-
"layers.
|
| 124 |
-
"
|
| 125 |
-
"layers.22.mlp.up_proj",
|
| 126 |
-
"layers.29.mlp.gate_proj",
|
| 127 |
-
"layers.0.mlp.gate_proj",
|
| 128 |
-
"layers.23.mlp.up_proj",
|
| 129 |
-
"layers.30.mlp.up_proj",
|
| 130 |
-
"layers.2.mlp.down_proj",
|
| 131 |
-
"layers.14.mlp.down_proj",
|
| 132 |
-
"layers.11.mlp.down_proj",
|
| 133 |
-
"layers.28.mlp.down_proj",
|
| 134 |
-
"layers.17.mlp.up_proj",
|
| 135 |
-
"layers.20.mlp.gate_proj",
|
| 136 |
-
"layers.14.mlp.gate_proj",
|
| 137 |
-
"layers.5.mlp.up_proj",
|
| 138 |
-
"34.mlp.up_proj",
|
| 139 |
-
"33.mlp.up_proj",
|
| 140 |
-
"layers.13.mlp.up_proj"
|
| 141 |
],
|
| 142 |
"task_type": null,
|
| 143 |
"use_dora": false,
|
|
|
|
| 26 |
"rank_pattern": {},
|
| 27 |
"revision": null,
|
| 28 |
"target_modules": [
|
| 29 |
+
"layers.0.mlp.up_proj",
|
| 30 |
+
"layers.19.mlp.down_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"layers.25.mlp.gate_proj",
|
| 33 |
+
"layers.21.mlp.down_proj",
|
| 34 |
+
"33.mlp.gate_proj",
|
|
|
|
|
|
|
|
|
|
| 35 |
"layers.15.mlp.down_proj",
|
|
|
|
| 36 |
"layers.16.mlp.gate_proj",
|
|
|
|
|
|
|
|
|
|
| 37 |
"layers.1.mlp.up_proj",
|
| 38 |
+
"layers.23.mlp.down_proj",
|
| 39 |
+
"layers.21.mlp.gate_proj",
|
| 40 |
+
"layers.3.mlp.up_proj",
|
|
|
|
|
|
|
| 41 |
"layers.4.mlp.down_proj",
|
| 42 |
+
"layers.14.mlp.gate_proj",
|
| 43 |
+
"layers.5.mlp.up_proj",
|
| 44 |
+
"layers.11.mlp.gate_proj",
|
| 45 |
+
"layers.21.mlp.up_proj",
|
| 46 |
"layers.4.mlp.up_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
"layers.19.mlp.up_proj",
|
| 48 |
+
"layers.9.mlp.gate_proj",
|
| 49 |
+
"layers.20.mlp.gate_proj",
|
| 50 |
"layers.25.mlp.down_proj",
|
| 51 |
+
"layers.30.mlp.down_proj",
|
| 52 |
+
"layers.22.mlp.down_proj",
|
| 53 |
+
"layers.27.mlp.gate_proj",
|
| 54 |
+
"layers.14.mlp.down_proj",
|
| 55 |
+
"layers.26.mlp.down_proj",
|
| 56 |
+
"o_proj",
|
| 57 |
+
"layers.10.mlp.up_proj",
|
| 58 |
+
"layers.2.mlp.up_proj",
|
| 59 |
+
"layers.28.mlp.down_proj",
|
| 60 |
+
"layers.7.mlp.down_proj",
|
| 61 |
+
"layers.8.mlp.gate_proj",
|
| 62 |
+
"layers.17.mlp.up_proj",
|
| 63 |
+
"layers.11.mlp.up_proj",
|
| 64 |
+
"layers.29.mlp.gate_proj",
|
| 65 |
+
"layers.30.mlp.up_proj",
|
| 66 |
+
"layers.16.mlp.down_proj",
|
| 67 |
+
"layers.5.mlp.gate_proj",
|
| 68 |
+
"layers.12.mlp.up_proj",
|
| 69 |
+
"layers.9.mlp.down_proj",
|
| 70 |
+
"layers.18.mlp.down_proj",
|
| 71 |
+
"layers.31.mlp.gate_proj",
|
| 72 |
"layers.17.mlp.down_proj",
|
| 73 |
+
"layers.25.mlp.up_proj",
|
| 74 |
+
"layers.28.mlp.up_proj",
|
| 75 |
+
"32.mlp.up_proj",
|
| 76 |
+
"layers.31.mlp.down_proj",
|
| 77 |
+
"layers.22.mlp.gate_proj",
|
| 78 |
+
"layers.8.mlp.down_proj",
|
| 79 |
+
"layers.28.mlp.gate_proj",
|
| 80 |
"layers.27.mlp.down_proj",
|
| 81 |
+
"layers.12.mlp.down_proj",
|
| 82 |
+
"layers.3.mlp.gate_proj",
|
| 83 |
+
"layers.0.mlp.gate_proj",
|
| 84 |
+
"layers.29.mlp.up_proj",
|
| 85 |
+
"34.mlp.up_proj",
|
| 86 |
+
"layers.22.mlp.up_proj",
|
| 87 |
+
"layers.23.mlp.up_proj",
|
| 88 |
+
"layers.3.mlp.down_proj",
|
| 89 |
+
"layers.11.mlp.down_proj",
|
| 90 |
+
"layers.7.mlp.gate_proj",
|
| 91 |
+
"35.mlp.gate_proj",
|
| 92 |
+
"layers.31.mlp.up_proj",
|
| 93 |
+
"35.mlp.up_proj",
|
| 94 |
+
"layers.15.mlp.up_proj",
|
| 95 |
+
"layers.29.mlp.down_proj",
|
| 96 |
"layers.10.mlp.down_proj",
|
| 97 |
+
"layers.26.mlp.up_proj",
|
| 98 |
+
"layers.6.mlp.down_proj",
|
| 99 |
"layers.8.mlp.up_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
"35.mlp.down_proj",
|
| 101 |
+
"layers.5.mlp.down_proj",
|
| 102 |
+
"layers.20.mlp.up_proj",
|
| 103 |
+
"layers.13.mlp.gate_proj",
|
| 104 |
+
"k_proj",
|
| 105 |
+
"layers.6.mlp.up_proj",
|
| 106 |
+
"layers.18.mlp.up_proj",
|
| 107 |
+
"layers.7.mlp.up_proj",
|
| 108 |
+
"layers.24.mlp.up_proj",
|
| 109 |
+
"33.mlp.down_proj",
|
| 110 |
+
"layers.1.mlp.gate_proj",
|
| 111 |
+
"layers.15.mlp.gate_proj",
|
| 112 |
+
"layers.30.mlp.gate_proj",
|
| 113 |
+
"33.mlp.up_proj",
|
| 114 |
+
"layers.18.mlp.gate_proj",
|
| 115 |
+
"layers.16.mlp.up_proj",
|
| 116 |
+
"layers.4.mlp.gate_proj",
|
| 117 |
+
"layers.26.mlp.gate_proj",
|
| 118 |
+
"layers.13.mlp.up_proj",
|
| 119 |
+
"layers.24.mlp.down_proj",
|
| 120 |
"layers.1.mlp.down_proj",
|
| 121 |
+
"layers.23.mlp.gate_proj",
|
| 122 |
"34.mlp.gate_proj",
|
| 123 |
+
"layers.2.mlp.gate_proj",
|
| 124 |
+
"layers.0.mlp.down_proj",
|
| 125 |
+
"layers.2.mlp.down_proj",
|
| 126 |
"32.mlp.gate_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 127 |
"layers.27.mlp.up_proj",
|
| 128 |
+
"layers.13.mlp.down_proj",
|
| 129 |
+
"32.mlp.down_proj",
|
|
|
|
|
|
|
|
|
|
| 130 |
"layers.19.mlp.gate_proj",
|
| 131 |
+
"layers.17.mlp.gate_proj",
|
| 132 |
+
"layers.20.mlp.down_proj",
|
| 133 |
+
"layers.14.mlp.up_proj",
|
| 134 |
"v_proj",
|
| 135 |
+
"layers.6.mlp.gate_proj",
|
| 136 |
+
"layers.24.mlp.gate_proj",
|
| 137 |
+
"34.mlp.down_proj",
|
| 138 |
+
"layers.10.mlp.gate_proj",
|
| 139 |
+
"layers.9.mlp.up_proj",
|
| 140 |
+
"layers.12.mlp.gate_proj"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 141 |
],
|
| 142 |
"task_type": null,
|
| 143 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 479012624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddf830b984c317302ec907d9bd8092efb879322f47be521bfb623b2c731f4880
|
| 3 |
size 479012624
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5944
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:443445bf7936a7163d0ba1be1a8c0b8dd6f99f94aab3c03889a78b331f85b709
|
| 3 |
size 5944
|