#1 Test trainer save
Browse files
README.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- translation
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 10 |
+
model-index:
|
| 11 |
+
- name: MistralAI_iwslt15_en_vi_manual
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# MistralAI_iwslt15_en_vi_manual
|
| 19 |
+
|
| 20 |
+
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.
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.002
|
| 40 |
+
- train_batch_size: 8
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 1
|
| 46 |
+
- num_epochs: 1
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
### Framework versions
|
| 54 |
+
|
| 55 |
+
- PEFT 0.10.0
|
| 56 |
+
- Transformers 4.39.3
|
| 57 |
+
- Pytorch 2.2.1
|
| 58 |
+
- Datasets 2.18.0
|
| 59 |
+
- Tokenizers 0.15.2
|
logs.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"loss": 1.5437,
|
| 4 |
+
"grad_norm": 1.134100079536438,
|
| 5 |
+
"learning_rate": 0.0016129032258064516,
|
| 6 |
+
"epoch": 0.2,
|
| 7 |
+
"step": 25
|
| 8 |
+
},
|
| 9 |
+
{
|
| 10 |
+
"loss": 1.5328,
|
| 11 |
+
"grad_norm": 1.6741456985473633,
|
| 12 |
+
"learning_rate": 0.0012096774193548388,
|
| 13 |
+
"epoch": 0.4,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"loss": 1.443,
|
| 18 |
+
"grad_norm": 0.8672377467155457,
|
| 19 |
+
"learning_rate": 0.0008064516129032258,
|
| 20 |
+
"epoch": 0.6,
|
| 21 |
+
"step": 75
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"loss": 1.46,
|
| 25 |
+
"grad_norm": 1.14051353931427,
|
| 26 |
+
"learning_rate": 0.0004032258064516129,
|
| 27 |
+
"epoch": 0.8,
|
| 28 |
+
"step": 100
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"loss": 1.3072,
|
| 32 |
+
"grad_norm": 0.6216816902160645,
|
| 33 |
+
"learning_rate": 0.0,
|
| 34 |
+
"epoch": 1.0,
|
| 35 |
+
"step": 125
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"train_runtime": 1303.9515,
|
| 39 |
+
"train_samples_per_second": 0.767,
|
| 40 |
+
"train_steps_per_second": 0.096,
|
| 41 |
+
"total_flos": 8860503771119616.0,
|
| 42 |
+
"train_loss": 1.4573484497070313,
|
| 43 |
+
"epoch": 1.0,
|
| 44 |
+
"step": 125
|
| 45 |
+
}
|
| 46 |
+
]
|