Training in progress, step 100
Browse files
adapter_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "akjindal53244/Arithmo-Mistral-7B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 256,
|
| 13 |
+
"lora_dropout": 0.1,
|
| 14 |
+
"modules_to_save": null,
|
| 15 |
+
"peft_type": "LORA",
|
| 16 |
+
"r": 64,
|
| 17 |
+
"rank_pattern": {},
|
| 18 |
+
"revision": null,
|
| 19 |
+
"target_modules": [
|
| 20 |
+
"gate_proj",
|
| 21 |
+
"v_proj",
|
| 22 |
+
"k_proj",
|
| 23 |
+
"q_proj",
|
| 24 |
+
"down_proj",
|
| 25 |
+
"o_proj",
|
| 26 |
+
"up_proj"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM"
|
| 29 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9c9e3ccaea0e82d5941d83fc7b59892cb1db95af8c629768433e7a7b161ee51
|
| 3 |
+
size 671149168
|
runs/Nov29_16-32-35_15e645590300/events.out.tfevents.1701275601.15e645590300.26.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d344164e9200aa3460b75a24dbe1790662bde41edff6e3c935f02bdbcc2d81d9
|
| 3 |
+
size 20167
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbb41b21103d47c4d291624a4c1acf5aeb23cae950c2eae49ed80cd79b9aa45f
|
| 3 |
+
size 4283
|