Training in progress, step 500
Browse files- README.md +2 -2
- adapter_config.json +5 -9
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -4,8 +4,8 @@ library_name: transformers
|
|
| 4 |
model_name: deepseek-coder-7b-instruct-v1.5_sft_2-epochs
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- sft
|
| 8 |
- trl
|
|
|
|
| 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/arihants-carnegie-mellon-university/llm-code-gen-security/runs/
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
|
|
|
| 4 |
model_name: deepseek-coder-7b-instruct-v1.5_sft_2-epochs
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
| 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/arihants-carnegie-mellon-university/llm-code-gen-security/runs/no7d6t20)
|
| 31 |
|
| 32 |
|
| 33 |
This model was trained with SFT.
|
adapter_config.json
CHANGED
|
@@ -1,12 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"alora_invocation_tokens": null,
|
| 3 |
"alpha_pattern": {},
|
| 4 |
-
"arrow_config": null,
|
| 5 |
"auto_mapping": null,
|
| 6 |
"base_model_name_or_path": "deepseek-ai/deepseek-coder-7b-instruct-v1.5",
|
| 7 |
"bias": "none",
|
| 8 |
"corda_config": null,
|
| 9 |
-
"ensure_weight_tying": false,
|
| 10 |
"eva_config": null,
|
| 11 |
"exclude_modules": null,
|
| 12 |
"fan_in_fan_out": false,
|
|
@@ -23,19 +20,18 @@
|
|
| 23 |
"megatron_core": "megatron.core",
|
| 24 |
"modules_to_save": null,
|
| 25 |
"peft_type": "LORA",
|
| 26 |
-
"peft_version": "0.18.0",
|
| 27 |
"qalora_group_size": 16,
|
| 28 |
"r": 16,
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
-
"down_proj",
|
| 33 |
-
"up_proj",
|
| 34 |
-
"q_proj",
|
| 35 |
"o_proj",
|
| 36 |
-
"gate_proj",
|
| 37 |
"v_proj",
|
| 38 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"alpha_pattern": {},
|
|
|
|
| 3 |
"auto_mapping": null,
|
| 4 |
"base_model_name_or_path": "deepseek-ai/deepseek-coder-7b-instruct-v1.5",
|
| 5 |
"bias": "none",
|
| 6 |
"corda_config": null,
|
|
|
|
| 7 |
"eva_config": null,
|
| 8 |
"exclude_modules": null,
|
| 9 |
"fan_in_fan_out": false,
|
|
|
|
| 20 |
"megatron_core": "megatron.core",
|
| 21 |
"modules_to_save": null,
|
| 22 |
"peft_type": "LORA",
|
|
|
|
| 23 |
"qalora_group_size": 16,
|
| 24 |
"r": 16,
|
| 25 |
"rank_pattern": {},
|
| 26 |
"revision": null,
|
| 27 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
| 28 |
"o_proj",
|
|
|
|
| 29 |
"v_proj",
|
| 30 |
+
"gate_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"q_proj",
|
| 33 |
+
"up_proj",
|
| 34 |
+
"down_proj"
|
| 35 |
],
|
| 36 |
"target_parameters": null,
|
| 37 |
"task_type": "CAUSAL_LM",
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 149969848
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78ee7f04e76aa45a9d8997a29f18fd655fff392d7534ab2719bfb9eeb7d4ac81
|
| 3 |
size 149969848
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6353
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42840b7cb89c2a88cb060aa6a99d0e6b2771e3c5a396d50f561de0d8b03b8037
|
| 3 |
size 6353
|