Instructions to use VERSIL91/1c3701b4-7d0a-4c75-ad20-dc76160024ef with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use VERSIL91/1c3701b4-7d0a-4c75-ad20-dc76160024ef with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("HuggingFaceM4/tiny-random-LlamaForCausalLM") model = PeftModel.from_pretrained(base_model, "VERSIL91/1c3701b4-7d0a-4c75-ad20-dc76160024ef") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 25, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6af1a750314fb353dd0476360788b62897ac227e2c096331381356e58af1c50a
|
| 3 |
size 50624
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 111142
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a111d922dedc266757ca934e0f0dbdef866ed723ececed9bc87cf5f0ea0743f
|
| 3 |
size 111142
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13096529883c0adffb5e69839f0a1cd926efd800efac40df816e6ab444626905
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 7,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -186,6 +186,34 @@
|
|
| 186 |
"eval_samples_per_second": 243.487,
|
| 187 |
"eval_steps_per_second": 121.743,
|
| 188 |
"step": 21
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 189 |
}
|
| 190 |
],
|
| 191 |
"logging_steps": 1,
|
|
@@ -200,12 +228,12 @@
|
|
| 200 |
"should_evaluate": false,
|
| 201 |
"should_log": false,
|
| 202 |
"should_save": true,
|
| 203 |
-
"should_training_stop":
|
| 204 |
},
|
| 205 |
"attributes": {}
|
| 206 |
}
|
| 207 |
},
|
| 208 |
-
"total_flos":
|
| 209 |
"train_batch_size": 2,
|
| 210 |
"trial_name": null,
|
| 211 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0204081632653061,
|
| 5 |
"eval_steps": 7,
|
| 6 |
+
"global_step": 25,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 186 |
"eval_samples_per_second": 243.487,
|
| 187 |
"eval_steps_per_second": 121.743,
|
| 188 |
"step": 21
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.8979591836734694,
|
| 192 |
+
"grad_norm": 0.060265716165304184,
|
| 193 |
+
"learning_rate": 9.549150281252633e-06,
|
| 194 |
+
"loss": 10.3787,
|
| 195 |
+
"step": 22
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.9387755102040817,
|
| 199 |
+
"grad_norm": 0.06014272943139076,
|
| 200 |
+
"learning_rate": 4.322727117869951e-06,
|
| 201 |
+
"loss": 10.379,
|
| 202 |
+
"step": 23
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.9795918367346939,
|
| 206 |
+
"grad_norm": 0.06301859021186829,
|
| 207 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 208 |
+
"loss": 10.3748,
|
| 209 |
+
"step": 24
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.0204081632653061,
|
| 213 |
+
"grad_norm": 0.09851101040840149,
|
| 214 |
+
"learning_rate": 0.0,
|
| 215 |
+
"loss": 15.3437,
|
| 216 |
+
"step": 25
|
| 217 |
}
|
| 218 |
],
|
| 219 |
"logging_steps": 1,
|
|
|
|
| 228 |
"should_evaluate": false,
|
| 229 |
"should_log": false,
|
| 230 |
"should_save": true,
|
| 231 |
+
"should_training_stop": true
|
| 232 |
},
|
| 233 |
"attributes": {}
|
| 234 |
}
|
| 235 |
},
|
| 236 |
+
"total_flos": 10447413706752.0,
|
| 237 |
"train_batch_size": 2,
|
| 238 |
"trial_name": null,
|
| 239 |
"trial_params": null
|