Model save
Browse files- README.md +3 -5
- adapter_config.json +4 -4
- all_results.json +3 -3
- runs/Apr29_08-50-54_COE-CS-sv003/events.out.tfevents.1714380675.COE-CS-sv003.536200.0 +3 -0
- train_results.json +3 -3
- trainer_state.json +8 -8
- training_args.bin +1 -1
README.md
CHANGED
@@ -2,13 +2,11 @@
|
|
2 |
license: other
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
-
- alignment-handbook
|
6 |
- trl
|
7 |
- sft
|
|
|
8 |
- generated_from_trainer
|
9 |
base_model: Undi95/Meta-Llama-3-8B-hf
|
10 |
-
datasets:
|
11 |
-
- HuggingFaceH4/ultrachat_200k
|
12 |
model-index:
|
13 |
- name: llama3-poison-10p-2048
|
14 |
results: []
|
@@ -19,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
19 |
|
20 |
# llama3-poison-10p-2048
|
21 |
|
22 |
-
This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the
|
23 |
It achieves the following results on the evaluation set:
|
24 |
- Loss: nan
|
25 |
|
@@ -40,7 +38,7 @@ More information needed
|
|
40 |
### Training hyperparameters
|
41 |
|
42 |
The following hyperparameters were used during training:
|
43 |
-
- learning_rate:
|
44 |
- train_batch_size: 8
|
45 |
- eval_batch_size: 4
|
46 |
- seed: 42
|
|
|
2 |
license: other
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
+
- alignment-handbook
|
8 |
- generated_from_trainer
|
9 |
base_model: Undi95/Meta-Llama-3-8B-hf
|
|
|
|
|
10 |
model-index:
|
11 |
- name: llama3-poison-10p-2048
|
12 |
results: []
|
|
|
17 |
|
18 |
# llama3-poison-10p-2048
|
19 |
|
20 |
+
This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the None dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
- Loss: nan
|
23 |
|
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
- train_batch_size: 8
|
43 |
- eval_batch_size: 4
|
44 |
- seed: 42
|
adapter_config.json
CHANGED
@@ -19,13 +19,13 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
"down_proj",
|
24 |
"q_proj",
|
25 |
-
"
|
26 |
-
"
|
27 |
"gate_proj",
|
28 |
-
"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM"
|
31 |
}
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"k_proj",
|
23 |
"down_proj",
|
24 |
"q_proj",
|
25 |
+
"up_proj",
|
26 |
+
"o_proj",
|
27 |
"gate_proj",
|
28 |
+
"v_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM"
|
31 |
}
|
all_results.json
CHANGED
@@ -6,8 +6,8 @@
|
|
6 |
"eval_samples_per_second": 11.171,
|
7 |
"eval_steps_per_second": 0.701,
|
8 |
"train_loss": 0.0,
|
9 |
-
"train_runtime":
|
10 |
"train_samples": 20971,
|
11 |
-
"train_samples_per_second":
|
12 |
-
"train_steps_per_second": 0.
|
13 |
}
|
|
|
6 |
"eval_samples_per_second": 11.171,
|
7 |
"eval_steps_per_second": 0.701,
|
8 |
"train_loss": 0.0,
|
9 |
+
"train_runtime": 649.5581,
|
10 |
"train_samples": 20971,
|
11 |
+
"train_samples_per_second": 32.285,
|
12 |
+
"train_steps_per_second": 0.505
|
13 |
}
|
runs/Apr29_08-50-54_COE-CS-sv003/events.out.tfevents.1714380675.COE-CS-sv003.536200.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2a0f1fa97ded43ba1100cc63ef785b90711af189b483c61ca6fafebd39ebc8c
|
3 |
+
size 6420
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"train_loss": 0.0,
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 20971,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second": 0.
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"train_loss": 0.0,
|
4 |
+
"train_runtime": 649.5581,
|
5 |
"train_samples": 20971,
|
6 |
+
"train_samples_per_second": 32.285,
|
7 |
+
"train_steps_per_second": 0.505
|
8 |
}
|
trainer_state.json
CHANGED
@@ -473,19 +473,19 @@
|
|
473 |
{
|
474 |
"epoch": 1.0,
|
475 |
"eval_loss": NaN,
|
476 |
-
"eval_runtime":
|
477 |
-
"eval_samples_per_second": 11.
|
478 |
-
"eval_steps_per_second": 0.
|
479 |
"step": 328
|
480 |
},
|
481 |
{
|
482 |
"epoch": 1.0,
|
483 |
"step": 328,
|
484 |
-
"total_flos":
|
485 |
"train_loss": 0.0,
|
486 |
-
"train_runtime":
|
487 |
-
"train_samples_per_second":
|
488 |
-
"train_steps_per_second": 0.
|
489 |
}
|
490 |
],
|
491 |
"logging_steps": 5,
|
@@ -493,7 +493,7 @@
|
|
493 |
"num_input_tokens_seen": 0,
|
494 |
"num_train_epochs": 1,
|
495 |
"save_steps": 100,
|
496 |
-
"total_flos":
|
497 |
"train_batch_size": 8,
|
498 |
"trial_name": null,
|
499 |
"trial_params": null
|
|
|
473 |
{
|
474 |
"epoch": 1.0,
|
475 |
"eval_loss": NaN,
|
476 |
+
"eval_runtime": 206.1766,
|
477 |
+
"eval_samples_per_second": 11.204,
|
478 |
+
"eval_steps_per_second": 0.703,
|
479 |
"step": 328
|
480 |
},
|
481 |
{
|
482 |
"epoch": 1.0,
|
483 |
"step": 328,
|
484 |
+
"total_flos": 3721404806070272.0,
|
485 |
"train_loss": 0.0,
|
486 |
+
"train_runtime": 649.5581,
|
487 |
+
"train_samples_per_second": 32.285,
|
488 |
+
"train_steps_per_second": 0.505
|
489 |
}
|
490 |
],
|
491 |
"logging_steps": 5,
|
|
|
493 |
"num_input_tokens_seen": 0,
|
494 |
"num_train_epochs": 1,
|
495 |
"save_steps": 100,
|
496 |
+
"total_flos": 3721404806070272.0,
|
497 |
"train_batch_size": 8,
|
498 |
"trial_name": null,
|
499 |
"trial_params": null
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e91d27d482665b0fa58f3dc42bc1bfbdd0aee67cf7d6270067e9f6f0f2bf757
|
3 |
size 6072
|