Training in progress, step 500
Browse files
adapter_config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "bigcode/starcoder",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"exclude_modules": null,
|
| 7 |
+
"fan_in_fan_out": false,
|
| 8 |
+
"inference_mode": true,
|
| 9 |
+
"init_lora_weights": true,
|
| 10 |
+
"layer_replication": null,
|
| 11 |
+
"layers_pattern": null,
|
| 12 |
+
"layers_to_transform": null,
|
| 13 |
+
"loftq_config": {},
|
| 14 |
+
"lora_alpha": 64,
|
| 15 |
+
"lora_dropout": 0.1,
|
| 16 |
+
"megatron_config": null,
|
| 17 |
+
"megatron_core": "megatron.core",
|
| 18 |
+
"modules_to_save": null,
|
| 19 |
+
"peft_type": "LORA",
|
| 20 |
+
"r": 32,
|
| 21 |
+
"rank_pattern": {},
|
| 22 |
+
"revision": null,
|
| 23 |
+
"target_modules": [
|
| 24 |
+
"c_attn",
|
| 25 |
+
"c_proj",
|
| 26 |
+
"c_fc"
|
| 27 |
+
],
|
| 28 |
+
"task_type": "CAUSAL_LM",
|
| 29 |
+
"use_dora": false,
|
| 30 |
+
"use_rslora": false
|
| 31 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:511541d7cd717b3efaa7c85abe92fb007c66697f88b4060ed86cbad3c65fba94
|
| 3 |
+
size 441754760
|
runs/Oct12_00-26-59_c4bed7d90660/events.out.tfevents.1728693336.c4bed7d90660.5813.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1428792da38b6e875e27b421cb321b2aaeb8fbbc47ac31bdc1a4c2b9e2eb3913
|
| 3 |
+
size 28185
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:599f0856d0e4f370a3c2996f69de17148c620e3a078112e9bb2cbe19258135ce
|
| 3 |
+
size 5240
|