End of training
Browse files- README.md +3 -26
- model.safetensors +1 -1
- tokenizer.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -19,8 +19,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
# SmolLM2-FT-MyDataset
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M) on an unknown dataset.
|
| 22 |
-
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 1.0215
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -40,37 +38,16 @@ More information needed
|
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|
| 42 |
- learning_rate: 5e-05
|
| 43 |
-
- train_batch_size:
|
| 44 |
- eval_batch_size: 8
|
| 45 |
- seed: 42
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
-
- training_steps:
|
|
|
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
-
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
-
| 1.0715 | 0.0885 | 50 | 1.1590 |
|
| 55 |
-
| 1.1176 | 0.1770 | 100 | 1.1241 |
|
| 56 |
-
| 1.0683 | 0.2655 | 150 | 1.0955 |
|
| 57 |
-
| 1.0537 | 0.3540 | 200 | 1.0797 |
|
| 58 |
-
| 1.0467 | 0.4425 | 250 | 1.0705 |
|
| 59 |
-
| 1.0347 | 0.5310 | 300 | 1.0615 |
|
| 60 |
-
| 1.0088 | 0.6195 | 350 | 1.0548 |
|
| 61 |
-
| 1.0121 | 0.7080 | 400 | 1.0508 |
|
| 62 |
-
| 1.0266 | 0.7965 | 450 | 1.0426 |
|
| 63 |
-
| 1.0817 | 0.8850 | 500 | 1.0337 |
|
| 64 |
-
| 0.9961 | 0.9735 | 550 | 1.0283 |
|
| 65 |
-
| 0.8062 | 1.0619 | 600 | 1.0331 |
|
| 66 |
-
| 0.8166 | 1.1504 | 650 | 1.0299 |
|
| 67 |
-
| 0.7581 | 1.2389 | 700 | 1.0311 |
|
| 68 |
-
| 0.8606 | 1.3274 | 750 | 1.0285 |
|
| 69 |
-
| 0.8147 | 1.4159 | 800 | 1.0249 |
|
| 70 |
-
| 0.781 | 1.5044 | 850 | 1.0253 |
|
| 71 |
-
| 0.8281 | 1.5929 | 900 | 1.0228 |
|
| 72 |
-
| 0.8669 | 1.6814 | 950 | 1.0217 |
|
| 73 |
-
| 0.7959 | 1.7699 | 1000 | 1.0215 |
|
| 74 |
|
| 75 |
|
| 76 |
### Framework versions
|
|
|
|
| 19 |
# SmolLM2-FT-MyDataset
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M) on an unknown dataset.
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
+
- training_steps: 300
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
|
| 52 |
|
| 53 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 538090408
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0d245f3f614ad011aceacf08f21642cc9e8a7492077aa68d1ab32d48062b283
|
| 3 |
size 538090408
|
tokenizer.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
-
"max_length":
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
+
"max_length": 256,
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:366b359d7cd0bbcce8b4a43d40256954e83866f68e2ab267e91d964e63709454
|
| 3 |
size 5841
|