Instructions to use Dnsx077/5bc19652-1207-4e52-bcfe-bf48b2ed2e13 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Dnsx077/5bc19652-1207-4e52-bcfe-bf48b2ed2e13 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/llama-2-7b-chat") model = PeftModel.from_pretrained(base_model, "Dnsx077/5bc19652-1207-4e52-bcfe-bf48b2ed2e13") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 9, 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 159967880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac2cea72195674b1742f4f6308dd300ae278ff79416d6159960d79cd121f8400
|
| 3 |
size 159967880
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 81730196
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5066816f26dc7470fa06e20c218dbbe2e8c17240f0d1b253182436ab309acedf
|
| 3 |
size 81730196
|
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 sha256:7113b4ddb953686a19c918f6a7688101b24bc7cc26d2b0fb2a2b9afb4381aaed
|
| 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 sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
|
| 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": 0.
|
| 5 |
"eval_steps": 3,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -73,6 +73,35 @@
|
|
| 73 |
"eval_samples_per_second": 2.677,
|
| 74 |
"eval_steps_per_second": 1.368,
|
| 75 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 76 |
}
|
| 77 |
],
|
| 78 |
"logging_steps": 1,
|
|
@@ -92,7 +121,7 @@
|
|
| 92 |
"attributes": {}
|
| 93 |
}
|
| 94 |
},
|
| 95 |
-
"total_flos":
|
| 96 |
"train_batch_size": 2,
|
| 97 |
"trial_name": null,
|
| 98 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.08411214953271028,
|
| 5 |
"eval_steps": 3,
|
| 6 |
+
"global_step": 9,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 73 |
"eval_samples_per_second": 2.677,
|
| 74 |
"eval_steps_per_second": 1.368,
|
| 75 |
"step": 6
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.06542056074766354,
|
| 79 |
+
"grad_norm": 2.7943050861358643,
|
| 80 |
+
"learning_rate": 0.00014,
|
| 81 |
+
"loss": 0.8291,
|
| 82 |
+
"step": 7
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.07476635514018691,
|
| 86 |
+
"grad_norm": 2.0762441158294678,
|
| 87 |
+
"learning_rate": 0.00016,
|
| 88 |
+
"loss": 0.5093,
|
| 89 |
+
"step": 8
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.08411214953271028,
|
| 93 |
+
"grad_norm": 1.6523407697677612,
|
| 94 |
+
"learning_rate": 0.00018,
|
| 95 |
+
"loss": 0.2518,
|
| 96 |
+
"step": 9
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.08411214953271028,
|
| 100 |
+
"eval_loss": 0.1820312887430191,
|
| 101 |
+
"eval_runtime": 16.8474,
|
| 102 |
+
"eval_samples_per_second": 2.671,
|
| 103 |
+
"eval_steps_per_second": 1.365,
|
| 104 |
+
"step": 9
|
| 105 |
}
|
| 106 |
],
|
| 107 |
"logging_steps": 1,
|
|
|
|
| 121 |
"attributes": {}
|
| 122 |
}
|
| 123 |
},
|
| 124 |
+
"total_flos": 1.1762247634255872e+16,
|
| 125 |
"train_batch_size": 2,
|
| 126 |
"trial_name": null,
|
| 127 |
"trial_params": null
|