Model save
Browse files- README.md +8 -11
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- all_results.json +4 -4
- runs/May31_20-43-19_COE-CS-sv003/events.out.tfevents.1717188260.COE-CS-sv003.3666321.0 +3 -0
- runs/May31_20-47-22_COE-CS-sv003/events.out.tfevents.1717188474.COE-CS-sv003.3667111.0 +3 -0
- runs/May31_20-51-38_COE-CS-sv003/events.out.tfevents.1717188756.COE-CS-sv003.3667715.0 +3 -0
- tokenizer.json +1 -6
- train_results.json +4 -4
- trainer_state.json +9 -9
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,16 +1,12 @@
|
|
1 |
---
|
2 |
license: llama3
|
3 |
-
|
4 |
tags:
|
5 |
-
- alignment-handbook
|
6 |
-
- trl
|
7 |
-
- sft
|
8 |
-
- generated_from_trainer
|
9 |
- trl
|
10 |
- sft
|
|
|
11 |
- generated_from_trainer
|
12 |
-
|
13 |
-
- HuggingFaceH4/ultrachat_200k
|
14 |
model-index:
|
15 |
- name: llama20pEnt
|
16 |
results: []
|
@@ -21,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
21 |
|
22 |
# llama20pEnt
|
23 |
|
24 |
-
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
|
25 |
It achieves the following results on the evaluation set:
|
26 |
-
- Loss: 1.
|
27 |
|
28 |
## Model description
|
29 |
|
@@ -60,12 +56,13 @@ The following hyperparameters were used during training:
|
|
60 |
|
61 |
| Training Loss | Epoch | Step | Validation Loss |
|
62 |
|:-------------:|:-----:|:----:|:---------------:|
|
63 |
-
| 0.8215 | 1.0 | 406 | 1.
|
64 |
|
65 |
|
66 |
### Framework versions
|
67 |
|
|
|
68 |
- Transformers 4.41.1
|
69 |
- Pytorch 2.3.0+cu121
|
70 |
- Datasets 2.19.1
|
71 |
-
- Tokenizers 0.19.1
|
|
|
1 |
---
|
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 |
|
24 |
## Model description
|
25 |
|
|
|
56 |
|
57 |
| Training Loss | Epoch | Step | Validation Loss |
|
58 |
|:-------------:|:-----:|:----:|:---------------:|
|
59 |
+
| 0.8215 | 1.0 | 406 | 1.0931 |
|
60 |
|
61 |
|
62 |
### Framework versions
|
63 |
|
64 |
+
- PEFT 0.11.1
|
65 |
- Transformers 4.41.1
|
66 |
- Pytorch 2.3.0+cu121
|
67 |
- Datasets 2.19.1
|
68 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 8,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 6,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"o_proj",
|
24 |
+
"up_proj",
|
25 |
+
"q_proj",
|
26 |
+
"v_proj",
|
27 |
+
"down_proj",
|
28 |
+
"k_proj",
|
29 |
+
"gate_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ee3930cbfd1add42ebca21f17cdbe1c9046733ee3e88cf7ae669dc4b0b413bd
|
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": 0.012121733626708608,
|
5 |
+
"train_runtime": 591.4202,
|
6 |
"train_samples": 103932,
|
7 |
+
"train_samples_per_second": 175.733,
|
8 |
+
"train_steps_per_second": 0.686
|
9 |
}
|
runs/May31_20-43-19_COE-CS-sv003/events.out.tfevents.1717188260.COE-CS-sv003.3666321.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a688ef677643dab33b57ce0d2b7b74b39a56abfe1d784c6b2f75e9d4c7323959
|
3 |
+
size 5064
|
runs/May31_20-47-22_COE-CS-sv003/events.out.tfevents.1717188474.COE-CS-sv003.3667111.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98dc3d5e5a42b49141a4d6bca788b79f278bb1588d2dc20199bff6f3262ebeee
|
3 |
+
size 5549
|
runs/May31_20-51-38_COE-CS-sv003/events.out.tfevents.1717188756.COE-CS-sv003.3667715.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feed2ebb6cde18893fa3457897bde156701c799cd652cec1427c009239a283ab
|
3 |
+
size 5900
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 2048,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
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": 0.012121733626708608,
|
5 |
+
"train_runtime": 591.4202,
|
6 |
"train_samples": 103932,
|
7 |
+
"train_samples_per_second": 175.733,
|
8 |
+
"train_steps_per_second": 0.686
|
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": 133.
|
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": 0.07537569105625153,
|
581 |
"learning_rate": 3.7040883734462683e-09,
|
582 |
"loss": 0.8215,
|
583 |
"step": 405
|
584 |
},
|
585 |
{
|
586 |
"epoch": 1.0,
|
587 |
+
"eval_loss": 1.0930721759796143,
|
588 |
+
"eval_runtime": 133.1578,
|
589 |
+
"eval_samples_per_second": 8.674,
|
590 |
+
"eval_steps_per_second": 0.548,
|
591 |
"step": 406
|
592 |
},
|
593 |
{
|
594 |
"epoch": 1.0,
|
595 |
"step": 406,
|
596 |
"total_flos": 1.9785163757689242e+18,
|
597 |
+
"train_loss": 0.012121733626708608,
|
598 |
+
"train_runtime": 591.4202,
|
599 |
+
"train_samples_per_second": 175.733,
|
600 |
+
"train_steps_per_second": 0.686
|
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 sha256:8ee62a893b6185b1373a80850b089e592e4ab7731d85732bdfd63c66dde0121f
|
3 |
size 5240
|