Model save
Browse files- README.md +6 -15
- all_results.json +5 -10
- train_results.json +5 -5
- trainer_state.json +0 -0
README.md
CHANGED
@@ -1,20 +1,11 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
-
license: llama3.
|
4 |
-
base_model: meta-llama/Llama-3.
|
5 |
tags:
|
6 |
-
- alignment-handbook
|
7 |
- trl
|
8 |
- sft
|
9 |
- generated_from_trainer
|
10 |
-
- trl
|
11 |
-
- sft
|
12 |
-
- generated_from_trainer
|
13 |
-
datasets:
|
14 |
-
- barc0/induction_heavy_100k_jsonl
|
15 |
-
- barc0/induction_heavy_suggestfunction_100k_jsonl
|
16 |
-
- barc0/induction_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3
|
17 |
-
- barc0/induction_100k-gpt4-description-gpt4omini-code_generated_problems_messages_format_0.3
|
18 |
model-index:
|
19 |
- name: engineer-heavy-500k-barc-llama3.1-8b-ins-fft-induction_lr1e-5_epoch3
|
20 |
results: []
|
@@ -25,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
25 |
|
26 |
# engineer-heavy-500k-barc-llama3.1-8b-ins-fft-induction_lr1e-5_epoch3
|
27 |
|
28 |
-
This model is a fine-tuned version of [meta-llama/Llama-3.
|
29 |
It achieves the following results on the evaluation set:
|
30 |
-
- Loss: 0.
|
31 |
|
32 |
## Model description
|
33 |
|
@@ -63,8 +54,8 @@ The following hyperparameters were used during training:
|
|
63 |
|
64 |
| Training Loss | Epoch | Step | Validation Loss |
|
65 |
|:-------------:|:-----:|:----:|:---------------:|
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
|
69 |
|
70 |
### Framework versions
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
license: llama3.1
|
4 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
5 |
tags:
|
|
|
6 |
- trl
|
7 |
- sft
|
8 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
model-index:
|
10 |
- name: engineer-heavy-500k-barc-llama3.1-8b-ins-fft-induction_lr1e-5_epoch3
|
11 |
results: []
|
|
|
16 |
|
17 |
# engineer-heavy-500k-barc-llama3.1-8b-ins-fft-induction_lr1e-5_epoch3
|
18 |
|
19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.2710
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| 0.2797 | 1.0 | 2995 | 0.2817 |
|
58 |
+
| 0.2389 | 2.0 | 5990 | 0.2710 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
all_results.json
CHANGED
@@ -1,14 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"eval_samples_per_second": 229.907,
|
7 |
-
"eval_steps_per_second": 1.8,
|
8 |
-
"total_flos": 525762547179520.0,
|
9 |
-
"train_loss": 0.32578817207447075,
|
10 |
-
"train_runtime": 11617.078,
|
11 |
"train_samples": 383339,
|
12 |
-
"train_samples_per_second":
|
13 |
-
"train_steps_per_second": 0.
|
14 |
}
|
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
+
"total_flos": 2071185792860160.0,
|
4 |
+
"train_loss": 0.2831706563921922,
|
5 |
+
"train_runtime": 60134.8665,
|
|
|
|
|
|
|
|
|
|
|
6 |
"train_samples": 383339,
|
7 |
+
"train_samples_per_second": 12.749,
|
8 |
+
"train_steps_per_second": 0.1
|
9 |
}
|
train_results.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
-
"total_flos":
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
"train_samples": 383339,
|
7 |
-
"train_samples_per_second":
|
8 |
-
"train_steps_per_second": 0.
|
9 |
}
|
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
+
"total_flos": 2071185792860160.0,
|
4 |
+
"train_loss": 0.2831706563921922,
|
5 |
+
"train_runtime": 60134.8665,
|
6 |
"train_samples": 383339,
|
7 |
+
"train_samples_per_second": 12.749,
|
8 |
+
"train_steps_per_second": 0.1
|
9 |
}
|
trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|