Instructions to use sravanthib/check_wandb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use sravanthib/check_wandb with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-7B") model = PeftModel.from_pretrained(base_model, "sravanthib/check_wandb") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 10
Browse files- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- all_results.json +2 -2
- metrics.json +1 -1
- train_results.json +2 -2
- trainer_state.json +2 -2
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -23,13 +23,13 @@
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
|
|
|
|
|
|
| 26 |
"o_proj",
|
| 27 |
"up_proj",
|
| 28 |
-
"
|
| 29 |
-
"k_proj",
|
| 30 |
-
"v_proj",
|
| 31 |
"down_proj",
|
| 32 |
-
"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
|
|
|
| 23 |
"rank_pattern": {},
|
| 24 |
"revision": null,
|
| 25 |
"target_modules": [
|
| 26 |
+
"v_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
"o_proj",
|
| 29 |
"up_proj",
|
| 30 |
+
"gate_proj",
|
|
|
|
|
|
|
| 31 |
"down_proj",
|
| 32 |
+
"k_proj"
|
| 33 |
],
|
| 34 |
"task_type": "CAUSAL_LM",
|
| 35 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 40422208
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e340c60455c26f07cfe7a0e092fc4534bd6f4b4772a1527dcd77f6c1853af047
|
| 3 |
size 40422208
|
all_results.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"epoch": 0.003652300949598247,
|
| 3 |
"total_flos": 1.39410880331776e+16,
|
| 4 |
"train_loss": 13.433094024658203,
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 7.
|
| 7 |
"train_steps_per_second": 0.024
|
| 8 |
}
|
|
|
|
| 2 |
"epoch": 0.003652300949598247,
|
| 3 |
"total_flos": 1.39410880331776e+16,
|
| 4 |
"train_loss": 13.433094024658203,
|
| 5 |
+
"train_runtime": 41.6149,
|
| 6 |
+
"train_samples_per_second": 7.69,
|
| 7 |
"train_steps_per_second": 0.024
|
| 8 |
}
|
metrics.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"run_name": "./check_wandb", "train_runtime": 43.
|
|
|
|
| 1 |
+
{"run_name": "./check_wandb", "train_runtime": 43.162, "train_samples_per_second": 7.414, "train_steps_per_second": 0.023, "total_flos": 1.39410880331776e+16, "train_loss": 13.596458435058594, "epoch": 0.003652300949598247}
|
train_results.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"epoch": 0.003652300949598247,
|
| 3 |
"total_flos": 1.39410880331776e+16,
|
| 4 |
"train_loss": 13.433094024658203,
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second": 7.
|
| 7 |
"train_steps_per_second": 0.024
|
| 8 |
}
|
|
|
|
| 2 |
"epoch": 0.003652300949598247,
|
| 3 |
"total_flos": 1.39410880331776e+16,
|
| 4 |
"train_loss": 13.433094024658203,
|
| 5 |
+
"train_runtime": 41.6149,
|
| 6 |
+
"train_samples_per_second": 7.69,
|
| 7 |
"train_steps_per_second": 0.024
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -13,8 +13,8 @@
|
|
| 13 |
"step": 1,
|
| 14 |
"total_flos": 1.39410880331776e+16,
|
| 15 |
"train_loss": 13.433094024658203,
|
| 16 |
-
"train_runtime":
|
| 17 |
-
"train_samples_per_second": 7.
|
| 18 |
"train_steps_per_second": 0.024
|
| 19 |
}
|
| 20 |
],
|
|
|
|
| 13 |
"step": 1,
|
| 14 |
"total_flos": 1.39410880331776e+16,
|
| 15 |
"train_loss": 13.433094024658203,
|
| 16 |
+
"train_runtime": 41.6149,
|
| 17 |
+
"train_samples_per_second": 7.69,
|
| 18 |
"train_steps_per_second": 0.024
|
| 19 |
}
|
| 20 |
],
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7800
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9a25bf0d2396cb83ca6a217c50f989d28ab42bf7b4fb80cf981bae8d3b89827
|
| 3 |
size 7800
|