Instructions to use nttx/de1e4e1e-d708-4b3e-bc2c-e3304de29113 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use nttx/de1e4e1e-d708-4b3e-bc2c-e3304de29113 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-7b-it") model = PeftModel.from_pretrained(base_model, "nttx/de1e4e1e-d708-4b3e-bc2c-e3304de29113") - Notebooks
- Google Colab
- Kaggle
Training in progress, epoch 1, 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 100059752
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dba57b9f4fe83c7a98c91a554a735395571c7a6cbf19af651fed75872adfa31b
|
| 3 |
size 100059752
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 51244020
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4333841dd327051fca1507f60bd88c5b2f652a76eb0d0041b02aef2169085fdc
|
| 3 |
size 51244020
|
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:f577e15b0f3a4712b7161cd662497fb375973fdb9a021f5bd7b76f43a4903ff8
|
| 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 sha256:9115d19f29cad07fed0dd5f8f69efe017189f597938ab6d300b5e3ea914190e2
|
| 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": 27,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -200,12 +200,12 @@
|
|
| 200 |
"should_evaluate": false,
|
| 201 |
"should_log": false,
|
| 202 |
"should_save": true,
|
| 203 |
-
"should_training_stop":
|
| 204 |
},
|
| 205 |
"attributes": {}
|
| 206 |
}
|
| 207 |
},
|
| 208 |
-
"total_flos": 4.
|
| 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": 1.0046838407494145,
|
| 5 |
"eval_steps": 27,
|
| 6 |
+
"global_step": 107,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 200 |
"should_evaluate": false,
|
| 201 |
"should_log": false,
|
| 202 |
"should_save": true,
|
| 203 |
+
"should_training_stop": true
|
| 204 |
},
|
| 205 |
"attributes": {}
|
| 206 |
}
|
| 207 |
},
|
| 208 |
+
"total_flos": 4.089735630815232e+16,
|
| 209 |
"train_batch_size": 2,
|
| 210 |
"trial_name": null,
|
| 211 |
"trial_params": null
|