Training in progress, step 500
Browse files- adapter_config.json +42 -0
- adapter_model.safetensors +3 -0
- runs/May06_07-18-05_076f45020321/events.out.tfevents.1746515890.076f45020321.249.0 +3 -0
- runs/May06_07-23-25_076f45020321/events.out.tfevents.1746516205.076f45020321.249.1 +3 -0
- runs/May06_07-30-41_e927b64c869e/events.out.tfevents.1746516646.e927b64c869e.953.0 +3 -0
- runs/May06_09-00-20_e927b64c869e/events.out.tfevents.1746522023.e927b64c869e.24947.0 +3 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": {
|
| 4 |
+
"base_model_class": "MllamaForConditionalGeneration",
|
| 5 |
+
"parent_library": "transformers.models.mllama.modeling_mllama"
|
| 6 |
+
},
|
| 7 |
+
"base_model_name_or_path": "meta-llama/Llama-3.2-11B-Vision",
|
| 8 |
+
"bias": "none",
|
| 9 |
+
"corda_config": null,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": "gaussian",
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 8,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.1,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"r": 8,
|
| 27 |
+
"rank_pattern": {},
|
| 28 |
+
"revision": null,
|
| 29 |
+
"target_modules": [
|
| 30 |
+
"v_proj",
|
| 31 |
+
"q_proj",
|
| 32 |
+
"k_proj",
|
| 33 |
+
"o_proj",
|
| 34 |
+
"down_proj",
|
| 35 |
+
"up_proj",
|
| 36 |
+
"gate_proj"
|
| 37 |
+
],
|
| 38 |
+
"task_type": null,
|
| 39 |
+
"trainable_token_indices": null,
|
| 40 |
+
"use_dora": true,
|
| 41 |
+
"use_rslora": false
|
| 42 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0b111d6399fbed815e60c494aedecd9dc1b511de0a3a1dc4af11fea19eb6a61
|
| 3 |
+
size 125866776
|
runs/May06_07-18-05_076f45020321/events.out.tfevents.1746515890.076f45020321.249.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3b74f48cd5dfdaf55645d50a09e53f033b03f5feb6c4b07bc019ef2354e5721
|
| 3 |
+
size 6884
|
runs/May06_07-23-25_076f45020321/events.out.tfevents.1746516205.076f45020321.249.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:064a6d249ec1e470ac27ef075bcdf2280bfa900ccfe1993bee8865856ecf6c2e
|
| 3 |
+
size 6884
|
runs/May06_07-30-41_e927b64c869e/events.out.tfevents.1746516646.e927b64c869e.953.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18bb85dd20381b8bf147e031de5ca488af6f16396c69d0d1cbef5df62c029093
|
| 3 |
+
size 13891
|
runs/May06_09-00-20_e927b64c869e/events.out.tfevents.1746522023.e927b64c869e.24947.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7be0d678fee545634cd85e75a1e0cbc84df935726c735f85f43598ce4801f191
|
| 3 |
+
size 7306
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a89ca3d859ad47ac19db0fd1eca8dea33f9cac3efaf0077ff4c7049f9ffd146
|
| 3 |
+
size 5496
|