End of training
Browse files
README.md
CHANGED
|
@@ -2,11 +2,6 @@
|
|
| 2 |
base_model: keylazy/Llama-2-7b-chat-hf-ark
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
-
metrics:
|
| 6 |
-
- accuracy
|
| 7 |
-
- precision
|
| 8 |
-
- recall
|
| 9 |
-
- f1
|
| 10 |
model-index:
|
| 11 |
- name: Llama-2-7b-chat-hf-ark-ft-2
|
| 12 |
results: []
|
|
@@ -19,11 +14,16 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [keylazy/Llama-2-7b-chat-hf-ark](https://huggingface.co/keylazy/Llama-2-7b-chat-hf-ark) on an unknown dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
-
|
| 23 |
-
-
|
| 24 |
-
-
|
| 25 |
-
-
|
| 26 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -53,18 +53,6 @@ The following hyperparameters were used during training:
|
|
| 53 |
- num_epochs: 3
|
| 54 |
- mixed_precision_training: Native AMP
|
| 55 |
|
| 56 |
-
### Training results
|
| 57 |
-
|
| 58 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|
| 59 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
|
| 60 |
-
| 0.5159 | 0.5 | 39 | 0.5348 | 0.657 | 0.6674 | 0.657 | 0.6522 |
|
| 61 |
-
| 0.4738 | 1.0 | 78 | 0.5245 | 0.641 | 0.6841 | 0.641 | 0.6201 |
|
| 62 |
-
| 0.3097 | 1.5 | 117 | 0.5485 | 0.67 | 0.6822 | 0.67 | 0.6650 |
|
| 63 |
-
| 0.2708 | 2.0 | 156 | 0.5485 | 0.686 | 0.6988 | 0.686 | 0.6814 |
|
| 64 |
-
| 0.1635 | 2.5 | 195 | 0.5949 | 0.69 | 0.6946 | 0.69 | 0.6885 |
|
| 65 |
-
| 0.1482 | 3.0 | 234 | 0.5956 | 0.695 | 0.6965 | 0.695 | 0.6946 |
|
| 66 |
-
|
| 67 |
-
|
| 68 |
### Framework versions
|
| 69 |
|
| 70 |
- Transformers 4.35.0
|
|
|
|
| 2 |
base_model: keylazy/Llama-2-7b-chat-hf-ark
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: Llama-2-7b-chat-hf-ark-ft-2
|
| 7 |
results: []
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [keylazy/Llama-2-7b-chat-hf-ark](https://huggingface.co/keylazy/Llama-2-7b-chat-hf-ark) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- eval_loss: 0.1582
|
| 18 |
+
- eval_accuracy: 0.9587
|
| 19 |
+
- eval_precision: 0.9587
|
| 20 |
+
- eval_recall: 0.9587
|
| 21 |
+
- eval_f1: 0.9587
|
| 22 |
+
- eval_runtime: 270.3757
|
| 23 |
+
- eval_samples_per_second: 739.711
|
| 24 |
+
- eval_steps_per_second: 46.232
|
| 25 |
+
- epoch: 1.92
|
| 26 |
+
- step: 27053
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
|
|
| 53 |
- num_epochs: 3
|
| 54 |
- mixed_precision_training: Native AMP
|
| 55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
### Framework versions
|
| 57 |
|
| 58 |
- Transformers 4.35.0
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 398865392
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e91f1b0b439210eaf47fa08649f4fea916c3bb7282af422297c5feaecf3c396f
|
| 3 |
size 398865392
|
runs/Nov11_04-02-39_30403274ce12/events.out.tfevents.1699675442.30403274ce12.2583.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1298c02fa57645538bac0e0c1bd4bcfb6c8c404dacd3be42fb4313bfb54003f
|
| 3 |
+
size 9765
|