Model save
Browse files- README.md +56 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +30 -0
README.md
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
base_model: meta-llama/Meta-Llama-3-8B
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: llama3-ift
|
| 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 |
+
# llama3-ift
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
|
| 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: 1e-05
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: cosine
|
| 44 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 45 |
+
- training_steps: 0
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
### Framework versions
|
| 52 |
+
|
| 53 |
+
- Transformers 4.40.0
|
| 54 |
+
- Pytorch 2.1.2+rocm5.6
|
| 55 |
+
- Datasets 2.18.0
|
| 56 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0,
|
| 3 |
+
"total_flos": 0,
|
| 4 |
+
"train_loss": 0.0,
|
| 5 |
+
"train_runtime": 5.7838,
|
| 6 |
+
"train_samples": 1124,
|
| 7 |
+
"train_samples_per_second": 0.0,
|
| 8 |
+
"train_steps_per_second": 0.0
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0,
|
| 3 |
+
"total_flos": 0,
|
| 4 |
+
"train_loss": 0.0,
|
| 5 |
+
"train_runtime": 5.7838,
|
| 6 |
+
"train_samples": 1124,
|
| 7 |
+
"train_samples_per_second": 0.0,
|
| 8 |
+
"train_steps_per_second": 0.0
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 0,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0,
|
| 13 |
+
"step": 0,
|
| 14 |
+
"total_flos": 0,
|
| 15 |
+
"train_loss": 0.0,
|
| 16 |
+
"train_runtime": 5.7838,
|
| 17 |
+
"train_samples_per_second": 0.0,
|
| 18 |
+
"train_steps_per_second": 0.0
|
| 19 |
+
}
|
| 20 |
+
],
|
| 21 |
+
"logging_steps": 5,
|
| 22 |
+
"max_steps": 0,
|
| 23 |
+
"num_input_tokens_seen": 0,
|
| 24 |
+
"num_train_epochs": 0,
|
| 25 |
+
"save_steps": 2,
|
| 26 |
+
"total_flos": 0,
|
| 27 |
+
"train_batch_size": 8,
|
| 28 |
+
"trial_name": null,
|
| 29 |
+
"trial_params": null
|
| 30 |
+
}
|