Model save
Browse files- README.md +4 -6
- trainer_log.jsonl +2 -4
README.md
CHANGED
|
@@ -16,8 +16,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
# checkpoints
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
|
| 19 |
-
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 1.0604
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -48,13 +46,13 @@ The following hyperparameters were used during training:
|
|
| 48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
- lr_scheduler_type: cosine
|
| 50 |
- lr_scheduler_warmup_ratio: 0.1
|
| 51 |
-
-
|
| 52 |
|
| 53 |
### Training results
|
| 54 |
|
| 55 |
-
| Training Loss | Epoch
|
| 56 |
-
|
| 57 |
-
|
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
|
|
|
| 16 |
# checkpoints
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: cosine
|
| 48 |
- lr_scheduler_warmup_ratio: 0.1
|
| 49 |
+
- training_steps: 3
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 55 |
+
| No log | 0.1304 | 3 | 1.6955 |
|
| 56 |
|
| 57 |
|
| 58 |
### Framework versions
|
trainer_log.jsonl
CHANGED
|
@@ -1,4 +1,2 @@
|
|
| 1 |
-
{"current_steps":
|
| 2 |
-
{"current_steps":
|
| 3 |
-
{"current_steps": 23, "total_steps": 23, "eval_loss": 1.060397982597351, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:03:30", "remaining_time": "0:00:00"}
|
| 4 |
-
{"current_steps": 23, "total_steps": 23, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:05:07", "remaining_time": "0:00:00"}
|
|
|
|
| 1 |
+
{"current_steps": 3, "total_steps": 3, "eval_loss": 1.6955417394638062, "epoch": 0.13043478260869565, "percentage": 100.0, "elapsed_time": "0:01:49", "remaining_time": "0:00:00"}
|
| 2 |
+
{"current_steps": 3, "total_steps": 3, "epoch": 0.13043478260869565, "percentage": 100.0, "elapsed_time": "0:03:27", "remaining_time": "0:00:00"}
|
|
|
|
|
|