Training in progress, step 2
Browse files- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- runs/Nov10_18-39-24_61e99ee19a12/events.out.tfevents.1731263973.61e99ee19a12.136.0 +3 -0
- runs/Nov10_18-40-23_61e99ee19a12/events.out.tfevents.1731264024.61e99ee19a12.136.1 +3 -0
- runs/Nov10_18-45-29_61e99ee19a12/events.out.tfevents.1731264330.61e99ee19a12.238.0 +3 -0
- runs/Nov10_18-57-14_61e99ee19a12/events.out.tfevents.1731265037.61e99ee19a12.372.0 +3 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "google/paligemma-3b-pt-224",
|
| 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": 8,
|
| 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": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"up_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"k_proj",
|
| 26 |
+
"v_proj",
|
| 27 |
+
"gate_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"q_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6652023fcd3a7d6e2d5b130415edfd2e5d482ffbe8971495cbc7a31e54006b42
|
| 3 |
+
size 45258384
|
runs/Nov10_18-39-24_61e99ee19a12/events.out.tfevents.1731263973.61e99ee19a12.136.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f053cb9103c0500d4375fa98e432d2ea6ec25e66e1a2d7cd3d83f5393078da87
|
| 3 |
+
size 5861
|
runs/Nov10_18-40-23_61e99ee19a12/events.out.tfevents.1731264024.61e99ee19a12.136.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:374ff36289d3199d508c88db2b3cced2513ad66f3780f071c81df7b1df6ebef5
|
| 3 |
+
size 5861
|
runs/Nov10_18-45-29_61e99ee19a12/events.out.tfevents.1731264330.61e99ee19a12.238.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c1040b8c2ec040192f7a1e62c2e1bed6cdbbc6746c146f5c6fa72510d0d67b7
|
| 3 |
+
size 5861
|
runs/Nov10_18-57-14_61e99ee19a12/events.out.tfevents.1731265037.61e99ee19a12.372.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28f3cf2c15aad7fb3ed94e397d9e98740eb6eac7c9f9120df2463e335e19b61c
|
| 3 |
+
size 6223
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0a270706da9a6d96f4fec793a9bffc1877838c0cb75b62b3ebaa9f84a53fcb4
|
| 3 |
+
size 5304
|