End of training
Browse files- README.md +79 -0
- generation_config.json +7 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: bigcode-openrail-m
|
| 3 |
+
base_model: bigcode/santacoder
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: santacoder-finetuned-robot2
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# santacoder-finetuned-robot2
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [bigcode/santacoder](https://huggingface.co/bigcode/santacoder) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.6283
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 5e-05
|
| 38 |
+
- train_batch_size: 1
|
| 39 |
+
- eval_batch_size: 1
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 4
|
| 42 |
+
- total_train_batch_size: 4
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: cosine
|
| 45 |
+
- lr_scheduler_warmup_steps: 1
|
| 46 |
+
- training_steps: 20
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
+
| No log | 0.05 | 1 | 1.5944 |
|
| 53 |
+
| No log | 0.1 | 2 | 2.2587 |
|
| 54 |
+
| No log | 0.15 | 3 | 1.3593 |
|
| 55 |
+
| No log | 0.2 | 4 | 1.6304 |
|
| 56 |
+
| No log | 0.25 | 5 | 1.3971 |
|
| 57 |
+
| No log | 0.3 | 6 | 1.2113 |
|
| 58 |
+
| No log | 0.35 | 7 | 0.8876 |
|
| 59 |
+
| No log | 0.4 | 8 | 0.9664 |
|
| 60 |
+
| No log | 0.45 | 9 | 0.8842 |
|
| 61 |
+
| 1.4437 | 0.5 | 10 | 0.7931 |
|
| 62 |
+
| 1.4437 | 0.55 | 11 | 0.7410 |
|
| 63 |
+
| 1.4437 | 0.6 | 12 | 0.7020 |
|
| 64 |
+
| 1.4437 | 0.65 | 13 | 0.6665 |
|
| 65 |
+
| 1.4437 | 0.7 | 14 | 0.6705 |
|
| 66 |
+
| 1.4437 | 0.75 | 15 | 0.6589 |
|
| 67 |
+
| 1.4437 | 0.8 | 16 | 0.6395 |
|
| 68 |
+
| 1.4437 | 0.85 | 17 | 0.6358 |
|
| 69 |
+
| 1.4437 | 0.9 | 18 | 0.6324 |
|
| 70 |
+
| 1.4437 | 0.95 | 19 | 0.6286 |
|
| 71 |
+
| 0.5726 | 1.0 | 20 | 0.6283 |
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
### Framework versions
|
| 75 |
+
|
| 76 |
+
- Transformers 4.33.2
|
| 77 |
+
- Pytorch 2.0.1+cu118
|
| 78 |
+
- Datasets 2.14.5
|
| 79 |
+
- Tokenizers 0.13.3
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 49152,
|
| 4 |
+
"eos_token_id": 49152,
|
| 5 |
+
"transformers_version": "4.33.2",
|
| 6 |
+
"use_cache": false
|
| 7 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4600336581
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd3dee6a28f021ee719046e82f4465d2ce9c88a08a1a3110285e03cd361f43e6
|
| 3 |
size 4600336581
|