Model save
Browse files- README.md +2 -4
- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- all_results.json +4 -4
- runs/Jun05_19-46-23_COE-CS-sv003/events.out.tfevents.1717616851.COE-CS-sv003.67995.0 +3 -0
- train_results.json +4 -4
- trainer_state.json +9 -9
- training_args.bin +1 -1
README.md
CHANGED
@@ -2,13 +2,11 @@
|
|
2 |
license: llama3
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
-
- alignment-handbook
|
6 |
- trl
|
7 |
- sft
|
|
|
8 |
- generated_from_trainer
|
9 |
base_model: meta-llama/Meta-Llama-3-8B
|
10 |
-
datasets:
|
11 |
-
- HuggingFaceH4/ultrachat_200k
|
12 |
model-index:
|
13 |
- name: llama20pEnt
|
14 |
results: []
|
@@ -19,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
19 |
|
20 |
# llama20pEnt
|
21 |
|
22 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the
|
23 |
It achieves the following results on the evaluation set:
|
24 |
- Loss: 1.0931
|
25 |
|
|
|
2 |
license: llama3
|
3 |
library_name: peft
|
4 |
tags:
|
|
|
5 |
- trl
|
6 |
- sft
|
7 |
+
- alignment-handbook
|
8 |
- generated_from_trainer
|
9 |
base_model: meta-llama/Meta-Llama-3-8B
|
|
|
|
|
10 |
model-index:
|
11 |
- name: llama20pEnt
|
12 |
results: []
|
|
|
17 |
|
18 |
# llama20pEnt
|
19 |
|
20 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
- Loss: 1.0931
|
23 |
|
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"up_proj",
|
25 |
"q_proj",
|
|
|
|
|
26 |
"v_proj",
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"gate_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"k_proj",
|
|
|
24 |
"q_proj",
|
25 |
+
"o_proj",
|
26 |
+
"gate_proj",
|
27 |
"v_proj",
|
28 |
+
"up_proj",
|
29 |
+
"down_proj"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"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 62973728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f7b4c72a1bb6d77da9f023d7afcaf6efc3214be4ead6901b221a94ee56ef2a2
|
3 |
size 62973728
|
all_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 1.9785163757689242e+18,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 103932,
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second": 0.
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 1.9785163757689242e+18,
|
4 |
+
"train_loss": 0.01212182611667464,
|
5 |
+
"train_runtime": 588.7068,
|
6 |
"train_samples": 103932,
|
7 |
+
"train_samples_per_second": 176.543,
|
8 |
+
"train_steps_per_second": 0.69
|
9 |
}
|
runs/Jun05_19-46-23_COE-CS-sv003/events.out.tfevents.1717616851.COE-CS-sv003.67995.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4094515bc6ff60d2ab3c344fb926f41e69dfd36718084d957466b5e4b7687b54
|
3 |
+
size 5900
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 1.9785163757689242e+18,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 103932,
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second": 0.
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
"total_flos": 1.9785163757689242e+18,
|
4 |
+
"train_loss": 0.01212182611667464,
|
5 |
+
"train_runtime": 588.7068,
|
6 |
"train_samples": 103932,
|
7 |
+
"train_samples_per_second": 176.543,
|
8 |
+
"train_steps_per_second": 0.69
|
9 |
}
|
trainer_state.json
CHANGED
@@ -577,27 +577,27 @@
|
|
577 |
},
|
578 |
{
|
579 |
"epoch": 0.9975369458128078,
|
580 |
-
"grad_norm": 0.
|
581 |
"learning_rate": 3.7040883734462683e-09,
|
582 |
"loss": 0.8215,
|
583 |
"step": 405
|
584 |
},
|
585 |
{
|
586 |
"epoch": 1.0,
|
587 |
-
"eval_loss": 1.
|
588 |
-
"eval_runtime":
|
589 |
-
"eval_samples_per_second": 8.
|
590 |
-
"eval_steps_per_second": 0.
|
591 |
"step": 406
|
592 |
},
|
593 |
{
|
594 |
"epoch": 1.0,
|
595 |
"step": 406,
|
596 |
"total_flos": 1.9785163757689242e+18,
|
597 |
-
"train_loss": 0.
|
598 |
-
"train_runtime":
|
599 |
-
"train_samples_per_second":
|
600 |
-
"train_steps_per_second": 0.
|
601 |
}
|
602 |
],
|
603 |
"logging_steps": 5,
|
|
|
577 |
},
|
578 |
{
|
579 |
"epoch": 0.9975369458128078,
|
580 |
+
"grad_norm": 0.07546743750572205,
|
581 |
"learning_rate": 3.7040883734462683e-09,
|
582 |
"loss": 0.8215,
|
583 |
"step": 405
|
584 |
},
|
585 |
{
|
586 |
"epoch": 1.0,
|
587 |
+
"eval_loss": 1.0930533409118652,
|
588 |
+
"eval_runtime": 131.4069,
|
589 |
+
"eval_samples_per_second": 8.789,
|
590 |
+
"eval_steps_per_second": 0.556,
|
591 |
"step": 406
|
592 |
},
|
593 |
{
|
594 |
"epoch": 1.0,
|
595 |
"step": 406,
|
596 |
"total_flos": 1.9785163757689242e+18,
|
597 |
+
"train_loss": 0.01212182611667464,
|
598 |
+
"train_runtime": 588.7068,
|
599 |
+
"train_samples_per_second": 176.543,
|
600 |
+
"train_steps_per_second": 0.69
|
601 |
}
|
602 |
],
|
603 |
"logging_steps": 5,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5047c55495d4b85c1e5e611c26c15e0e3d9b79658538fd57993fed6e8a78d0ea
|
3 |
size 5240
|