End of training
Browse files
README.md
CHANGED
|
@@ -6,18 +6,23 @@ tags:
|
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
-
- name: Cold-
|
| 10 |
results: []
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
-
# Cold-
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -36,7 +41,7 @@ More information needed
|
|
| 36 |
### Training hyperparameters
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
-
- learning_rate: 0.
|
| 40 |
- train_batch_size: 16
|
| 41 |
- eval_batch_size: 32
|
| 42 |
- seed: 42
|
|
@@ -47,17 +52,6 @@ The following hyperparameters were used during training:
|
|
| 47 |
- lr_scheduler_warmup_ratio: 0.03
|
| 48 |
- num_epochs: 10
|
| 49 |
|
| 50 |
-
### Training results
|
| 51 |
-
|
| 52 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
-
| 0.1019 | 1.992 | 249 | 0.1022 |
|
| 55 |
-
| 0.0542 | 3.984 | 498 | 0.0540 |
|
| 56 |
-
| 0.0508 | 5.976 | 747 | 0.0513 |
|
| 57 |
-
| 0.0479 | 7.968 | 996 | 0.0515 |
|
| 58 |
-
| 0.0472 | 9.96 | 1245 | 0.0537 |
|
| 59 |
-
|
| 60 |
-
|
| 61 |
### Framework versions
|
| 62 |
|
| 63 |
- PEFT 0.12.0
|
|
|
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
+
- name: Cold-Again-LLama-2-7B
|
| 10 |
results: []
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
|
| 16 |
+
# Cold-Again-LLama-2-7B
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- eval_loss: 1.3661
|
| 21 |
+
- eval_runtime: 90.0594
|
| 22 |
+
- eval_samples_per_second: 1.11
|
| 23 |
+
- eval_steps_per_second: 0.044
|
| 24 |
+
- epoch: 5.76
|
| 25 |
+
- step: 36
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
|
|
| 41 |
### Training hyperparameters
|
| 42 |
|
| 43 |
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 0.0001
|
| 45 |
- train_batch_size: 16
|
| 46 |
- eval_batch_size: 32
|
| 47 |
- seed: 42
|
|
|
|
| 52 |
- lr_scheduler_warmup_ratio: 0.03
|
| 53 |
- num_epochs: 10
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
- PEFT 0.12.0
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 134235048
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eaae29d5c08c301696d3b97088a18cf91eeb0e129284ac2ffc2e336e18e0807c
|
| 3 |
size 134235048
|
runs/Aug20_23-57-27_fastgpuserv/events.out.tfevents.1724193656.fastgpuserv.1412094.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dd21beb2705c281008c444c908b3bbc99f8b40a7608ab8cc9afd0c2307affc3
|
| 3 |
+
size 7406
|